| 5 1 4 1 1 2 1 1 1 1 2 1 1 5 5 1 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ASIX AX8817X based USB 2.0 Ethernet Devices * Copyright (C) 2003-2006 David Hollis <dhollis@davehollis.com> * Copyright (C) 2005 Phil Chang <pchang23@sbcglobal.net> * Copyright (C) 2006 James Painter <jamie.painter@iname.com> * Copyright (c) 2002-2003 TiVo Inc. */ #include "asix.h" #define PHY_MODE_MARVELL 0x0000 #define MII_MARVELL_LED_CTRL 0x0018 #define MII_MARVELL_STATUS 0x001b #define MII_MARVELL_CTRL 0x0014 #define MARVELL_LED_MANUAL 0x0019 #define MARVELL_STATUS_HWCFG 0x0004 #define MARVELL_CTRL_TXDELAY 0x0002 #define MARVELL_CTRL_RXDELAY 0x0080 #define PHY_MODE_RTL8211CL 0x000C #define AX88772A_PHY14H 0x14 #define AX88772A_PHY14H_DEFAULT 0x442C #define AX88772A_PHY15H 0x15 #define AX88772A_PHY15H_DEFAULT 0x03C8 #define AX88772A_PHY16H 0x16 #define AX88772A_PHY16H_DEFAULT 0x4044 struct ax88172_int_data { __le16 res1; u8 link; __le16 res2; u8 status; __le16 res3; } __packed; static void asix_status(struct usbnet *dev, struct urb *urb) { struct ax88172_int_data *event; int link; if (urb->actual_length < 8) return; event = urb->transfer_buffer; link = event->link & 0x01; if (netif_carrier_ok(dev->net) != link) { usbnet_link_change(dev, link, 1); netdev_dbg(dev->net, "Link Status is: %d\n", link); } } static void asix_set_netdev_dev_addr(struct usbnet *dev, u8 *addr) { if (is_valid_ether_addr(addr)) { eth_hw_addr_set(dev->net, addr); } else { netdev_info(dev->net, "invalid hw address, using random\n"); eth_hw_addr_random(dev->net); } } /* Get the PHY Identifier from the PHYSID1 & PHYSID2 MII registers */ static u32 asix_get_phyid(struct usbnet *dev) { int phy_reg; u32 phy_id; int i; /* Poll for the rare case the FW or phy isn't ready yet. */ for (i = 0; i < 100; i++) { phy_reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID1); if (phy_reg < 0) return 0; if (phy_reg != 0 && phy_reg != 0xFFFF) break; mdelay(1); } if (phy_reg <= 0 || phy_reg == 0xFFFF) return 0; phy_id = (phy_reg & 0xffff) << 16; phy_reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID2); if (phy_reg < 0) return 0; phy_id |= (phy_reg & 0xffff); return phy_id; } static u32 asix_get_link(struct net_device *net) { struct usbnet *dev = netdev_priv(net); return mii_link_ok(&dev->mii); } static int asix_ioctl (struct net_device *net, struct ifreq *rq, int cmd) { struct usbnet *dev = netdev_priv(net); return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL); } /* We need to override some ethtool_ops so we require our own structure so we don't interfere with other usbnet devices that may be connected at the same time. */ static const struct ethtool_ops ax88172_ethtool_ops = { .get_drvinfo = asix_get_drvinfo, .get_link = asix_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .get_wol = asix_get_wol, .set_wol = asix_set_wol, .get_eeprom_len = asix_get_eeprom_len, .get_eeprom = asix_get_eeprom, .set_eeprom = asix_set_eeprom, .nway_reset = usbnet_nway_reset, .get_link_ksettings = usbnet_get_link_ksettings_mii, .set_link_ksettings = usbnet_set_link_ksettings_mii, }; static void ax88172_set_multicast(struct net_device *net) { struct usbnet *dev = netdev_priv(net); struct asix_data *data = (struct asix_data *)&dev->data; u8 rx_ctl = 0x8c; if (net->flags & IFF_PROMISC) { rx_ctl |= 0x01; } else if (net->flags & IFF_ALLMULTI || netdev_mc_count(net) > AX_MAX_MCAST) { rx_ctl |= 0x02; } else if (netdev_mc_empty(net)) { /* just broadcast and directed */ } else { /* We use the 20 byte dev->data * for our 8 byte filter buffer * to avoid allocating memory that * is tricky to free later */ struct netdev_hw_addr *ha; u32 crc_bits; memset(data->multi_filter, 0, AX_MCAST_FILTER_SIZE); /* Build the multicast hash filter. */ netdev_for_each_mc_addr(ha, net) { crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26; data->multi_filter[crc_bits >> 3] |= 1 << (crc_bits & 7); } asix_write_cmd_async(dev, AX_CMD_WRITE_MULTI_FILTER, 0, 0, AX_MCAST_FILTER_SIZE, data->multi_filter); rx_ctl |= 0x10; } asix_write_cmd_async(dev, AX_CMD_WRITE_RX_CTL, rx_ctl, 0, 0, NULL); } static int ax88172_link_reset(struct usbnet *dev) { u8 mode; struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET }; mii_check_media(&dev->mii, 1, 1); mii_ethtool_gset(&dev->mii, &ecmd); mode = AX88172_MEDIUM_DEFAULT; if (ecmd.duplex != DUPLEX_FULL) mode |= ~AX88172_MEDIUM_FD; netdev_dbg(dev->net, "ax88172_link_reset() speed: %u duplex: %d setting mode to 0x%04x\n", ethtool_cmd_speed(&ecmd), ecmd.duplex, mode); asix_write_medium_mode(dev, mode, 0); return 0; } static const struct net_device_ops ax88172_netdev_ops = { .ndo_open = usbnet_open, .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_change_mtu = usbnet_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = asix_ioctl, .ndo_set_rx_mode = ax88172_set_multicast, }; static void asix_phy_reset(struct usbnet *dev, unsigned int reset_bits) { unsigned int timeout = 5000; asix_mdio_write(dev->net, dev->mii.phy_id, MII_BMCR, reset_bits); /* give phy_id a chance to process reset */ udelay(500); /* See IEEE 802.3 "22.2.4.1.1 Reset": 500ms max */ while (timeout--) { if (asix_mdio_read(dev->net, dev->mii.phy_id, MII_BMCR) & BMCR_RESET) udelay(100); else return; } netdev_err(dev->net, "BMCR_RESET timeout on phy_id %d\n", dev->mii.phy_id); } static int ax88172_bind(struct usbnet *dev, struct usb_interface *intf) { int ret = 0; u8 buf[ETH_ALEN] = {0}; int i; unsigned long gpio_bits = dev->driver_info->data; usbnet_get_endpoints(dev,intf); /* Toggle the GPIOs in a manufacturer/model specific way */ for (i = 2; i >= 0; i--) { ret = asix_write_cmd(dev, AX_CMD_WRITE_GPIOS, (gpio_bits >> (i * 8)) & 0xff, 0, 0, NULL, 0); if (ret < 0) goto out; msleep(5); } ret = asix_write_rx_ctl(dev, 0x80, 0); if (ret < 0) goto out; /* Get the MAC address */ ret = asix_read_cmd(dev, AX88172_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0); if (ret < 0) { netdev_dbg(dev->net, "read AX_CMD_READ_NODE_ID failed: %d\n", ret); goto out; } asix_set_netdev_dev_addr(dev, buf); /* Initialize MII structure */ dev->mii.dev = dev->net; dev->mii.mdio_read = asix_mdio_read; dev->mii.mdio_write = asix_mdio_write; dev->mii.phy_id_mask = 0x3f; dev->mii.reg_num_mask = 0x1f; dev->mii.phy_id = asix_read_phy_addr(dev, true); if (dev->mii.phy_id < 0) return dev->mii.phy_id; dev->net->netdev_ops = &ax88172_netdev_ops; dev->net->ethtool_ops = &ax88172_ethtool_ops; dev->net->needed_headroom = 4; /* cf asix_tx_fixup() */ dev->net->needed_tailroom = 4; /* cf asix_tx_fixup() */ asix_phy_reset(dev, BMCR_RESET); asix_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE, ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP); mii_nway_restart(&dev->mii); return 0; out: return ret; } static void ax88772_ethtool_get_strings(struct net_device *netdev, u32 sset, u8 *data) { switch (sset) { case ETH_SS_TEST: net_selftest_get_strings(data); break; } } static int ax88772_ethtool_get_sset_count(struct net_device *ndev, int sset) { switch (sset) { case ETH_SS_TEST: return net_selftest_get_count(); default: return -EOPNOTSUPP; } } static void ax88772_ethtool_get_pauseparam(struct net_device *ndev, struct ethtool_pauseparam *pause) { struct usbnet *dev = netdev_priv(ndev); struct asix_common_private *priv = dev->driver_priv; phylink_ethtool_get_pauseparam(priv->phylink, pause); } static int ax88772_ethtool_set_pauseparam(struct net_device *ndev, struct ethtool_pauseparam *pause) { struct usbnet *dev = netdev_priv(ndev); struct asix_common_private *priv = dev->driver_priv; return phylink_ethtool_set_pauseparam(priv->phylink, pause); } static const struct ethtool_ops ax88772_ethtool_ops = { .get_drvinfo = asix_get_drvinfo, .get_link = usbnet_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .get_wol = asix_get_wol, .set_wol = asix_set_wol, .get_eeprom_len = asix_get_eeprom_len, .get_eeprom = asix_get_eeprom, .set_eeprom = asix_set_eeprom, .nway_reset = phy_ethtool_nway_reset, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, .self_test = net_selftest, .get_strings = ax88772_ethtool_get_strings, .get_sset_count = ax88772_ethtool_get_sset_count, .get_pauseparam = ax88772_ethtool_get_pauseparam, .set_pauseparam = ax88772_ethtool_set_pauseparam, }; static int ax88772_reset(struct usbnet *dev) { struct asix_data *data = (struct asix_data *)&dev->data; struct asix_common_private *priv = dev->driver_priv; int ret; /* Rewrite MAC address */ ether_addr_copy(data->mac_addr, dev->net->dev_addr); ret = asix_write_cmd(dev, AX_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN, data->mac_addr, 0); if (ret < 0) goto out; /* Set RX_CTL to default values with 2k buffer, and enable cactus */ ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL, 0); if (ret < 0) goto out; ret = asix_write_medium_mode(dev, AX88772_MEDIUM_DEFAULT, 0); if (ret < 0) goto out; phylink_start(priv->phylink); return 0; out: return ret; } static int ax88772_hw_reset(struct usbnet *dev, int in_pm) { struct asix_data *data = (struct asix_data *)&dev->data; struct asix_common_private *priv = dev->driver_priv; u16 rx_ctl; int ret; ret = asix_write_gpio(dev, AX_GPIO_RSE | AX_GPIO_GPO_2 | AX_GPIO_GPO2EN, 5, in_pm); if (ret < 0) goto out; ret = asix_write_cmd(dev, AX_CMD_SW_PHY_SELECT, priv->embd_phy, 0, 0, NULL, in_pm); if (ret < 0) { netdev_dbg(dev->net, "Select PHY #1 failed: %d\n", ret); goto out; } if (priv->embd_phy) { ret = asix_sw_reset(dev, AX_SWRESET_IPPD, in_pm); if (ret < 0) goto out; usleep_range(10000, 11000); ret = asix_sw_reset(dev, AX_SWRESET_CLEAR, in_pm); if (ret < 0) goto out; msleep(60); ret = asix_sw_reset(dev, AX_SWRESET_IPRL | AX_SWRESET_PRL, in_pm); if (ret < 0) goto out; } else { ret = asix_sw_reset(dev, AX_SWRESET_IPPD | AX_SWRESET_PRL, in_pm); if (ret < 0) goto out; } msleep(150); if (in_pm && (!asix_mdio_read_nopm(dev->net, dev->mii.phy_id, MII_PHYSID1))){ ret = -EIO; goto out; } ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL, in_pm); if (ret < 0) goto out; ret = asix_write_medium_mode(dev, AX88772_MEDIUM_DEFAULT, in_pm); if (ret < 0) goto out; ret = asix_write_cmd(dev, AX_CMD_WRITE_IPG0, AX88772_IPG0_DEFAULT | AX88772_IPG1_DEFAULT, AX88772_IPG2_DEFAULT, 0, NULL, in_pm); if (ret < 0) { netdev_dbg(dev->net, "Write IPG,IPG1,IPG2 failed: %d\n", ret); goto out; } /* Rewrite MAC address */ ether_addr_copy(data->mac_addr, dev->net->dev_addr); ret = asix_write_cmd(dev, AX_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN, data->mac_addr, in_pm); if (ret < 0) goto out; /* Set RX_CTL to default values with 2k buffer, and enable cactus */ ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL, in_pm); if (ret < 0) goto out; rx_ctl = asix_read_rx_ctl(dev, in_pm); netdev_dbg(dev->net, "RX_CTL is 0x%04x after all initializations\n", rx_ctl); rx_ctl = asix_read_medium_status(dev, in_pm); netdev_dbg(dev->net, "Medium Status is 0x%04x after all initializations\n", rx_ctl); return 0; out: return ret; } static int ax88772a_hw_reset(struct usbnet *dev, int in_pm) { struct asix_data *data = (struct asix_data *)&dev->data; struct asix_common_private *priv = dev->driver_priv; u16 rx_ctl, phy14h, phy15h, phy16h; int ret; ret = asix_write_gpio(dev, AX_GPIO_RSE, 5, in_pm); if (ret < 0) goto out; ret = asix_write_cmd(dev, AX_CMD_SW_PHY_SELECT, priv->embd_phy | AX_PHYSEL_SSEN, 0, 0, NULL, in_pm); if (ret < 0) { netdev_dbg(dev->net, "Select PHY #1 failed: %d\n", ret); goto out; } usleep_range(10000, 11000); ret = asix_sw_reset(dev, AX_SWRESET_IPPD | AX_SWRESET_IPRL, in_pm); if (ret < 0) goto out; usleep_range(10000, 11000); ret = asix_sw_reset(dev, AX_SWRESET_IPRL, in_pm); if (ret < 0) goto out; msleep(160); ret = asix_sw_reset(dev, AX_SWRESET_CLEAR, in_pm); if (ret < 0) goto out; ret = asix_sw_reset(dev, AX_SWRESET_IPRL, in_pm); if (ret < 0) goto out; msleep(200); if (in_pm && (!asix_mdio_read_nopm(dev->net, dev->mii.phy_id, MII_PHYSID1))) { ret = -1; goto out; } if (priv->chipcode == AX_AX88772B_CHIPCODE) { ret = asix_write_cmd(dev, AX_QCTCTRL, 0x8000, 0x8001, 0, NULL, in_pm); if (ret < 0) { netdev_dbg(dev->net, "Write BQ setting failed: %d\n", ret); goto out; } } else if (priv->chipcode == AX_AX88772A_CHIPCODE) { /* Check if the PHY registers have default settings */ phy14h = asix_mdio_read_nopm(dev->net, dev->mii.phy_id, AX88772A_PHY14H); phy15h = asix_mdio_read_nopm(dev->net, dev->mii.phy_id, AX88772A_PHY15H); phy16h = asix_mdio_read_nopm(dev->net, dev->mii.phy_id, AX88772A_PHY16H); netdev_dbg(dev->net, "772a_hw_reset: MR20=0x%x MR21=0x%x MR22=0x%x\n", phy14h, phy15h, phy16h); /* Restore PHY registers default setting if not */ if (phy14h != AX88772A_PHY14H_DEFAULT) asix_mdio_write_nopm(dev->net, dev->mii.phy_id, AX88772A_PHY14H, AX88772A_PHY14H_DEFAULT); if (phy15h != AX88772A_PHY15H_DEFAULT) asix_mdio_write_nopm(dev->net, dev->mii.phy_id, AX88772A_PHY15H, AX88772A_PHY15H_DEFAULT); if (phy16h != AX88772A_PHY16H_DEFAULT) asix_mdio_write_nopm(dev->net, dev->mii.phy_id, AX88772A_PHY16H, AX88772A_PHY16H_DEFAULT); } ret = asix_write_cmd(dev, AX_CMD_WRITE_IPG0, AX88772_IPG0_DEFAULT | AX88772_IPG1_DEFAULT, AX88772_IPG2_DEFAULT, 0, NULL, in_pm); if (ret < 0) { netdev_dbg(dev->net, "Write IPG,IPG1,IPG2 failed: %d\n", ret); goto out; } /* Rewrite MAC address */ memcpy(data->mac_addr, dev->net->dev_addr, ETH_ALEN); ret = asix_write_cmd(dev, AX_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN, data->mac_addr, in_pm); if (ret < 0) goto out; /* Set RX_CTL to default values with 2k buffer, and enable cactus */ ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL, in_pm); if (ret < 0) goto out; ret = asix_write_medium_mode(dev, AX88772_MEDIUM_DEFAULT, in_pm); if (ret < 0) return ret; /* Set RX_CTL to default values with 2k buffer, and enable cactus */ ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL, in_pm); if (ret < 0) goto out; rx_ctl = asix_read_rx_ctl(dev, in_pm); netdev_dbg(dev->net, "RX_CTL is 0x%04x after all initializations\n", rx_ctl); rx_ctl = asix_read_medium_status(dev, in_pm); netdev_dbg(dev->net, "Medium Status is 0x%04x after all initializations\n", rx_ctl); return 0; out: return ret; } static const struct net_device_ops ax88772_netdev_ops = { .ndo_open = usbnet_open, .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_change_mtu = usbnet_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = asix_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = asix_set_multicast, }; static void ax88772_suspend(struct usbnet *dev) { struct asix_common_private *priv = dev->driver_priv; u16 medium; if (netif_running(dev->net)) { rtnl_lock(); phylink_suspend(priv->phylink, false); rtnl_unlock(); } /* Stop MAC operation */ medium = asix_read_medium_status(dev, 1); medium &= ~AX_MEDIUM_RE; asix_write_medium_mode(dev, medium, 1); netdev_dbg(dev->net, "ax88772_suspend: medium=0x%04x\n", asix_read_medium_status(dev, 1)); } static int asix_suspend(struct usb_interface *intf, pm_message_t message) { struct usbnet *dev = usb_get_intfdata(intf); struct asix_common_private *priv = dev->driver_priv; if (priv && priv->suspend) priv->suspend(dev); return usbnet_suspend(intf, message); } static void ax88772_resume(struct usbnet *dev) { struct asix_common_private *priv = dev->driver_priv; int i; for (i = 0; i < 3; i++) if (!priv->reset(dev, 1)) break; if (netif_running(dev->net)) { rtnl_lock(); phylink_resume(priv->phylink); rtnl_unlock(); } } static int asix_resume(struct usb_interface *intf) { struct usbnet *dev = usb_get_intfdata(intf); struct asix_common_private *priv = dev->driver_priv; if (priv && priv->resume) priv->resume(dev); return usbnet_resume(intf); } static int ax88772_init_mdio(struct usbnet *dev) { struct asix_common_private *priv = dev->driver_priv; int ret; priv->mdio = mdiobus_alloc(); if (!priv->mdio) return -ENOMEM; priv->mdio->priv = dev; priv->mdio->read = &asix_mdio_bus_read; priv->mdio->write = &asix_mdio_bus_write; priv->mdio->name = "Asix MDIO Bus"; /* mii bus name is usb-<usb bus number>-<usb device number> */ snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); ret = mdiobus_register(priv->mdio); if (ret) { netdev_err(dev->net, "Could not register MDIO bus (err %d)\n", ret); mdiobus_free(priv->mdio); priv->mdio = NULL; } return ret; } static void ax88772_mdio_unregister(struct asix_common_private *priv) { mdiobus_unregister(priv->mdio); mdiobus_free(priv->mdio); } static int ax88772_init_phy(struct usbnet *dev) { struct asix_common_private *priv = dev->driver_priv; int ret; priv->phydev = mdiobus_get_phy(priv->mdio, priv->phy_addr); if (!priv->phydev) { netdev_err(dev->net, "Could not find PHY\n"); return -ENODEV; } ret = phylink_connect_phy(priv->phylink, priv->phydev); if (ret) { netdev_err(dev->net, "Could not connect PHY\n"); return ret; } phy_suspend(priv->phydev); priv->phydev->mac_managed_pm = true; phy_attached_info(priv->phydev); if (priv->embd_phy) return 0; /* In case main PHY is not the embedded PHY and MAC is RMII clock * provider, we need to suspend embedded PHY by keeping PLL enabled * (AX_SWRESET_IPPD == 0). */ priv->phydev_int = mdiobus_get_phy(priv->mdio, AX_EMBD_PHY_ADDR); if (!priv->phydev_int) { rtnl_lock(); phylink_disconnect_phy(priv->phylink); rtnl_unlock(); netdev_err(dev->net, "Could not find internal PHY\n"); return -ENODEV; } priv->phydev_int->mac_managed_pm = true; phy_suspend(priv->phydev_int); return 0; } static void ax88772_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { /* Nothing to do */ } static void ax88772_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { struct usbnet *dev = netdev_priv(to_net_dev(config->dev)); asix_write_medium_mode(dev, 0, 0); usbnet_link_change(dev, false, false); } static void ax88772_mac_link_up(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause) { struct usbnet *dev = netdev_priv(to_net_dev(config->dev)); u16 m = AX_MEDIUM_AC | AX_MEDIUM_RE; m |= duplex ? AX_MEDIUM_FD : 0; switch (speed) { case SPEED_100: m |= AX_MEDIUM_PS; break; case SPEED_10: break; default: return; } if (tx_pause) m |= AX_MEDIUM_TFC; if (rx_pause) m |= AX_MEDIUM_RFC; asix_write_medium_mode(dev, m, 0); usbnet_link_change(dev, true, false); } static const struct phylink_mac_ops ax88772_phylink_mac_ops = { .mac_config = ax88772_mac_config, .mac_link_down = ax88772_mac_link_down, .mac_link_up = ax88772_mac_link_up, }; static int ax88772_phylink_setup(struct usbnet *dev) { struct asix_common_private *priv = dev->driver_priv; phy_interface_t phy_if_mode; struct phylink *phylink; priv->phylink_config.dev = &dev->net->dev; priv->phylink_config.type = PHYLINK_NETDEV; priv->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10 | MAC_100; __set_bit(PHY_INTERFACE_MODE_INTERNAL, priv->phylink_config.supported_interfaces); __set_bit(PHY_INTERFACE_MODE_RMII, priv->phylink_config.supported_interfaces); if (priv->embd_phy) phy_if_mode = PHY_INTERFACE_MODE_INTERNAL; else phy_if_mode = PHY_INTERFACE_MODE_RMII; phylink = phylink_create(&priv->phylink_config, dev->net->dev.fwnode, phy_if_mode, &ax88772_phylink_mac_ops); if (IS_ERR(phylink)) return PTR_ERR(phylink); priv->phylink = phylink; return 0; } static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) { struct asix_common_private *priv; u8 buf[ETH_ALEN] = {0}; int ret, i; priv = devm_kzalloc(&dev->udev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; dev->driver_priv = priv; usbnet_get_endpoints(dev, intf); /* Maybe the boot loader passed the MAC address via device tree */ if (!eth_platform_get_mac_address(&dev->udev->dev, buf)) { netif_dbg(dev, ifup, dev->net, "MAC address read from device tree"); } else { /* Try getting the MAC address from EEPROM */ if (dev->driver_info->data & FLAG_EEPROM_MAC) { for (i = 0; i < (ETH_ALEN >> 1); i++) { ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x04 + i, 0, 2, buf + i * 2, 0); if (ret < 0) break; } } else { ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0); } if (ret < 0) { netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret); return ret; } } asix_set_netdev_dev_addr(dev, buf); dev->net->netdev_ops = &ax88772_netdev_ops; dev->net->ethtool_ops = &ax88772_ethtool_ops; dev->net->needed_headroom = 4; /* cf asix_tx_fixup() */ dev->net->needed_tailroom = 4; /* cf asix_tx_fixup() */ ret = asix_read_phy_addr(dev, true); if (ret < 0) return ret; priv->phy_addr = ret; priv->embd_phy = ((priv->phy_addr & 0x1f) == AX_EMBD_PHY_ADDR); ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG, 0, 0, 1, &priv->chipcode, 0); if (ret < 0) { netdev_dbg(dev->net, "Failed to read STATMNGSTS_REG: %d\n", ret); return ret; } priv->chipcode &= AX_CHIPCODE_MASK; priv->resume = ax88772_resume; priv->suspend = ax88772_suspend; if (priv->chipcode == AX_AX88772_CHIPCODE) priv->reset = ax88772_hw_reset; else priv->reset = ax88772a_hw_reset; ret = priv->reset(dev, 0); if (ret < 0) { netdev_dbg(dev->net, "Failed to reset AX88772: %d\n", ret); return ret; } /* Asix framing packs multiple eth frames into a 2K usb bulk transfer */ if (dev->driver_info->flags & FLAG_FRAMING_AX) { /* hard_mtu is still the default - the device does not support jumbo eth frames */ dev->rx_urb_size = 2048; } priv->presvd_phy_bmcr = 0; priv->presvd_phy_advertise = 0; ret = ax88772_init_mdio(dev); if (ret) goto mdio_err; ret = ax88772_phylink_setup(dev); if (ret) goto phylink_err; ret = ax88772_init_phy(dev); if (ret) goto initphy_err; return 0; initphy_err: phylink_destroy(priv->phylink); phylink_err: ax88772_mdio_unregister(priv); mdio_err: return ret; } static int ax88772_stop(struct usbnet *dev) { struct asix_common_private *priv = dev->driver_priv; phylink_stop(priv->phylink); return 0; } static void ax88772_unbind(struct usbnet *dev, struct usb_interface *intf) { struct asix_common_private *priv = dev->driver_priv; rtnl_lock(); phylink_disconnect_phy(priv->phylink); rtnl_unlock(); phylink_destroy(priv->phylink); ax88772_mdio_unregister(priv); asix_rx_fixup_common_free(dev->driver_priv); } static void ax88178_unbind(struct usbnet *dev, struct usb_interface *intf) { asix_rx_fixup_common_free(dev->driver_priv); kfree(dev->driver_priv); } static const struct ethtool_ops ax88178_ethtool_ops = { .get_drvinfo = asix_get_drvinfo, .get_link = asix_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .get_wol = asix_get_wol, .set_wol = asix_set_wol, .get_eeprom_len = asix_get_eeprom_len, .get_eeprom = asix_get_eeprom, .set_eeprom = asix_set_eeprom, .nway_reset = usbnet_nway_reset, .get_link_ksettings = usbnet_get_link_ksettings_mii, .set_link_ksettings = usbnet_set_link_ksettings_mii, }; static int marvell_phy_init(struct usbnet *dev) { struct asix_data *data = (struct asix_data *)&dev->data; u16 reg; netdev_dbg(dev->net, "marvell_phy_init()\n"); reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_MARVELL_STATUS); netdev_dbg(dev->net, "MII_MARVELL_STATUS = 0x%04x\n", reg); asix_mdio_write(dev->net, dev->mii.phy_id, MII_MARVELL_CTRL, MARVELL_CTRL_RXDELAY | MARVELL_CTRL_TXDELAY); if (data->ledmode) { reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_MARVELL_LED_CTRL); netdev_dbg(dev->net, "MII_MARVELL_LED_CTRL (1) = 0x%04x\n", reg); reg &= 0xf8ff; reg |= (1 + 0x0100); asix_mdio_write(dev->net, dev->mii.phy_id, MII_MARVELL_LED_CTRL, reg); reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_MARVELL_LED_CTRL); netdev_dbg(dev->net, "MII_MARVELL_LED_CTRL (2) = 0x%04x\n", reg); } return 0; } static int rtl8211cl_phy_init(struct usbnet *dev) { struct asix_data *data = (struct asix_data *)&dev->data; netdev_dbg(dev->net, "rtl8211cl_phy_init()\n"); asix_mdio_write (dev->net, dev->mii.phy_id, 0x1f, 0x0005); asix_mdio_write (dev->net, dev->mii.phy_id, 0x0c, 0); asix_mdio_write (dev->net, dev->mii.phy_id, 0x01, asix_mdio_read (dev->net, dev->mii.phy_id, 0x01) | 0x0080); asix_mdio_write (dev->net, dev->mii.phy_id, 0x1f, 0); if (data->ledmode == 12) { asix_mdio_write (dev->net, dev->mii.phy_id, 0x1f, 0x0002); asix_mdio_write (dev->net, dev->mii.phy_id, 0x1a, 0x00cb); asix_mdio_write (dev->net, dev->mii.phy_id, 0x1f, 0); } return 0; } static int marvell_led_status(struct usbnet *dev, u16 speed) { u16 reg = asix_mdio_read(dev->net, dev->mii.phy_id, MARVELL_LED_MANUAL); netdev_dbg(dev->net, "marvell_led_status() read 0x%04x\n", reg); /* Clear out the center LED bits - 0x03F0 */ reg &= 0xfc0f; switch (speed) { case SPEED_1000: reg |= 0x03e0; break; case SPEED_100: reg |= 0x03b0; break; default: reg |= 0x02f0; } netdev_dbg(dev->net, "marvell_led_status() writing 0x%04x\n", reg); asix_mdio_write(dev->net, dev->mii.phy_id, MARVELL_LED_MANUAL, reg); return 0; } static int ax88178_reset(struct usbnet *dev) { struct asix_data *data = (struct asix_data *)&dev->data; int ret; __le16 eeprom; u8 status; int gpio0 = 0; u32 phyid; ret = asix_read_cmd(dev, AX_CMD_READ_GPIOS, 0, 0, 1, &status, 0); if (ret < 0) { netdev_dbg(dev->net, "Failed to read GPIOS: %d\n", ret); return ret; } netdev_dbg(dev->net, "GPIO Status: 0x%04x\n", status); asix_write_cmd(dev, AX_CMD_WRITE_ENABLE, 0, 0, 0, NULL, 0); ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x0017, 0, 2, &eeprom, 0); if (ret < 0) { netdev_dbg(dev->net, "Failed to read EEPROM: %d\n", ret); return ret; } asix_write_cmd(dev, AX_CMD_WRITE_DISABLE, 0, 0, 0, NULL, 0); netdev_dbg(dev->net, "EEPROM index 0x17 is 0x%04x\n", eeprom); if (eeprom == cpu_to_le16(0xffff)) { data->phymode = PHY_MODE_MARVELL; data->ledmode = 0; gpio0 = 1; } else { data->phymode = le16_to_cpu(eeprom) & 0x7F; data->ledmode = le16_to_cpu(eeprom) >> 8; gpio0 = (le16_to_cpu(eeprom) & 0x80) ? 0 : 1; } netdev_dbg(dev->net, "GPIO0: %d, PhyMode: %d\n", gpio0, data->phymode); /* Power up external GigaPHY through AX88178 GPIO pin */ asix_write_gpio(dev, AX_GPIO_RSE | AX_GPIO_GPO_1 | AX_GPIO_GPO1EN, 40, 0); if ((le16_to_cpu(eeprom) >> 8) != 1) { asix_write_gpio(dev, 0x003c, 30, 0); asix_write_gpio(dev, 0x001c, 300, 0); asix_write_gpio(dev, 0x003c, 30, 0); } else { netdev_dbg(dev->net, "gpio phymode == 1 path\n"); asix_write_gpio(dev, AX_GPIO_GPO1EN, 30, 0); asix_write_gpio(dev, AX_GPIO_GPO1EN | AX_GPIO_GPO_1, 30, 0); } /* Read PHYID register *AFTER* powering up PHY */ phyid = asix_get_phyid(dev); netdev_dbg(dev->net, "PHYID=0x%08x\n", phyid); /* Set AX88178 to enable MII/GMII/RGMII interface for external PHY */ asix_write_cmd(dev, AX_CMD_SW_PHY_SELECT, 0, 0, 0, NULL, 0); asix_sw_reset(dev, 0, 0); msleep(150); asix_sw_reset(dev, AX_SWRESET_PRL | AX_SWRESET_IPPD, 0); msleep(150); asix_write_rx_ctl(dev, 0, 0); if (data->phymode == PHY_MODE_MARVELL) { marvell_phy_init(dev); msleep(60); } else if (data->phymode == PHY_MODE_RTL8211CL) rtl8211cl_phy_init(dev); asix_phy_reset(dev, BMCR_RESET | BMCR_ANENABLE); asix_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE, ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP); asix_mdio_write(dev->net, dev->mii.phy_id, MII_CTRL1000, ADVERTISE_1000FULL); asix_write_medium_mode(dev, AX88178_MEDIUM_DEFAULT, 0); mii_nway_restart(&dev->mii); /* Rewrite MAC address */ memcpy(data->mac_addr, dev->net->dev_addr, ETH_ALEN); ret = asix_write_cmd(dev, AX_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN, data->mac_addr, 0); if (ret < 0) return ret; ret = asix_write_rx_ctl(dev, AX_DEFAULT_RX_CTL, 0); if (ret < 0) return ret; return 0; } static int ax88178_link_reset(struct usbnet *dev) { u16 mode; struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET }; struct asix_data *data = (struct asix_data *)&dev->data; u32 speed; netdev_dbg(dev->net, "ax88178_link_reset()\n"); mii_check_media(&dev->mii, 1, 1); mii_ethtool_gset(&dev->mii, &ecmd); mode = AX88178_MEDIUM_DEFAULT; speed = ethtool_cmd_speed(&ecmd); if (speed == SPEED_1000) mode |= AX_MEDIUM_GM; else if (speed == SPEED_100) mode |= AX_MEDIUM_PS; else mode &= ~(AX_MEDIUM_PS | AX_MEDIUM_GM); mode |= AX_MEDIUM_ENCK; if (ecmd.duplex == DUPLEX_FULL) mode |= AX_MEDIUM_FD; else mode &= ~AX_MEDIUM_FD; netdev_dbg(dev->net, "ax88178_link_reset() speed: %u duplex: %d setting mode to 0x%04x\n", speed, ecmd.duplex, mode); asix_write_medium_mode(dev, mode, 0); if (data->phymode == PHY_MODE_MARVELL && data->ledmode) marvell_led_status(dev, speed); return 0; } static void ax88178_set_mfb(struct usbnet *dev) { u16 mfb = AX_RX_CTL_MFB_16384; u16 rxctl; u16 medium; int old_rx_urb_size = dev->rx_urb_size; if (dev->hard_mtu < 2048) { dev->rx_urb_size = 2048; mfb = AX_RX_CTL_MFB_2048; } else if (dev->hard_mtu < 4096) { dev->rx_urb_size = 4096; mfb = AX_RX_CTL_MFB_4096; } else if (dev->hard_mtu < 8192) { dev->rx_urb_size = 8192; mfb = AX_RX_CTL_MFB_8192; } else if (dev->hard_mtu < 16384) { dev->rx_urb_size = 16384; mfb = AX_RX_CTL_MFB_16384; } rxctl = asix_read_rx_ctl(dev, 0); asix_write_rx_ctl(dev, (rxctl & ~AX_RX_CTL_MFB_16384) | mfb, 0); medium = asix_read_medium_status(dev, 0); if (dev->net->mtu > 1500) medium |= AX_MEDIUM_JFE; else medium &= ~AX_MEDIUM_JFE; asix_write_medium_mode(dev, medium, 0); if (dev->rx_urb_size > old_rx_urb_size) usbnet_unlink_rx_urbs(dev); } static int ax88178_change_mtu(struct net_device *net, int new_mtu) { struct usbnet *dev = netdev_priv(net); int ll_mtu = new_mtu + net->hard_header_len + 4; netdev_dbg(dev->net, "ax88178_change_mtu() new_mtu=%d\n", new_mtu); if ((ll_mtu % dev->maxpacket) == 0) return -EDOM; WRITE_ONCE(net->mtu, new_mtu); dev->hard_mtu = net->mtu + net->hard_header_len; ax88178_set_mfb(dev); /* max qlen depend on hard_mtu and rx_urb_size */ usbnet_update_max_qlen(dev); return 0; } static const struct net_device_ops ax88178_netdev_ops = { .ndo_open = usbnet_open, .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = asix_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = asix_set_multicast, .ndo_eth_ioctl = asix_ioctl, .ndo_change_mtu = ax88178_change_mtu, }; static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf) { int ret; u8 buf[ETH_ALEN] = {0}; usbnet_get_endpoints(dev,intf); /* Get the MAC address */ ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0); if (ret < 0) { netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret); return ret; } asix_set_netdev_dev_addr(dev, buf); /* Initialize MII structure */ dev->mii.dev = dev->net; dev->mii.mdio_read = asix_mdio_read; dev->mii.mdio_write = asix_mdio_write; dev->mii.phy_id_mask = 0x1f; dev->mii.reg_num_mask = 0xff; dev->mii.supports_gmii = 1; dev->mii.phy_id = asix_read_phy_addr(dev, true); if (dev->mii.phy_id < 0) return dev->mii.phy_id; dev->net->netdev_ops = &ax88178_netdev_ops; dev->net->ethtool_ops = &ax88178_ethtool_ops; dev->net->max_mtu = 16384 - (dev->net->hard_header_len + 4); /* Blink LEDS so users know driver saw dongle */ asix_sw_reset(dev, 0, 0); msleep(150); asix_sw_reset(dev, AX_SWRESET_PRL | AX_SWRESET_IPPD, 0); msleep(150); /* Asix framing packs multiple eth frames into a 2K usb bulk transfer */ if (dev->driver_info->flags & FLAG_FRAMING_AX) { /* hard_mtu is still the default - the device does not support jumbo eth frames */ dev->rx_urb_size = 2048; } dev->driver_priv = kzalloc(sizeof(struct asix_common_private), GFP_KERNEL); if (!dev->driver_priv) return -ENOMEM; return 0; } static const struct driver_info ax8817x_info = { .description = "ASIX AX8817x USB 2.0 Ethernet", .bind = ax88172_bind, .status = asix_status, .link_reset = ax88172_link_reset, .reset = ax88172_link_reset, .flags = FLAG_ETHER | FLAG_LINK_INTR, .data = 0x00130103, }; static const struct driver_info dlink_dub_e100_info = { .description = "DLink DUB-E100 USB Ethernet", .bind = ax88172_bind, .status = asix_status, .link_reset = ax88172_link_reset, .reset = ax88172_link_reset, .flags = FLAG_ETHER | FLAG_LINK_INTR, .data = 0x009f9d9f, }; static const struct driver_info netgear_fa120_info = { .description = "Netgear FA-120 USB Ethernet", .bind = ax88172_bind, .status = asix_status, .link_reset = ax88172_link_reset, .reset = ax88172_link_reset, .flags = FLAG_ETHER | FLAG_LINK_INTR, .data = 0x00130103, }; static const struct driver_info hawking_uf200_info = { .description = "Hawking UF200 USB Ethernet", .bind = ax88172_bind, .status = asix_status, .link_reset = ax88172_link_reset, .reset = ax88172_link_reset, .flags = FLAG_ETHER | FLAG_LINK_INTR, .data = 0x001f1d1f, }; static const struct driver_info ax88772_info = { .description = "ASIX AX88772 USB 2.0 Ethernet", .bind = ax88772_bind, .unbind = ax88772_unbind, .status = asix_status, .reset = ax88772_reset, .stop = ax88772_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, .rx_fixup = asix_rx_fixup_common, .tx_fixup = asix_tx_fixup, }; static const struct driver_info ax88772b_info = { .description = "ASIX AX88772B USB 2.0 Ethernet", .bind = ax88772_bind, .unbind = ax88772_unbind, .status = asix_status, .reset = ax88772_reset, .stop = ax88772_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, .rx_fixup = asix_rx_fixup_common, .tx_fixup = asix_tx_fixup, .data = FLAG_EEPROM_MAC, }; static const struct driver_info lxausb_t1l_info = { .description = "Linux Automation GmbH USB 10Base-T1L", .bind = ax88772_bind, .unbind = ax88772_unbind, .status = asix_status, .reset = ax88772_reset, .stop = ax88772_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, .rx_fixup = asix_rx_fixup_common, .tx_fixup = asix_tx_fixup, .data = FLAG_EEPROM_MAC, }; static const struct driver_info ax88178_info = { .description = "ASIX AX88178 USB 2.0 Ethernet", .bind = ax88178_bind, .unbind = ax88178_unbind, .status = asix_status, .link_reset = ax88178_link_reset, .reset = ax88178_reset, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, .rx_fixup = asix_rx_fixup_common, .tx_fixup = asix_tx_fixup, }; /* * USBLINK 20F9 "USB 2.0 LAN" USB ethernet adapter, typically found in * no-name packaging. * USB device strings are: * 1: Manufacturer: USBLINK * 2: Product: HG20F9 USB2.0 * 3: Serial: 000003 * Appears to be compatible with Asix 88772B. */ static const struct driver_info hg20f9_info = { .description = "HG20F9 USB 2.0 Ethernet", .bind = ax88772_bind, .unbind = ax88772_unbind, .status = asix_status, .reset = ax88772_reset, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, .rx_fixup = asix_rx_fixup_common, .tx_fixup = asix_tx_fixup, .data = FLAG_EEPROM_MAC, }; static const struct usb_device_id products [] = { { // Linksys USB200M USB_DEVICE (0x077b, 0x2226), .driver_info = (unsigned long) &ax8817x_info, }, { // Netgear FA120 USB_DEVICE (0x0846, 0x1040), .driver_info = (unsigned long) &netgear_fa120_info, }, { // DLink DUB-E100 USB_DEVICE (0x2001, 0x1a00), .driver_info = (unsigned long) &dlink_dub_e100_info, }, { // Intellinet, ST Lab USB Ethernet USB_DEVICE (0x0b95, 0x1720), .driver_info = (unsigned long) &ax8817x_info, }, { // Hawking UF200, TrendNet TU2-ET100 USB_DEVICE (0x07b8, 0x420a), .driver_info = (unsigned long) &hawking_uf200_info, }, { // Billionton Systems, USB2AR USB_DEVICE (0x08dd, 0x90ff), .driver_info = (unsigned long) &ax8817x_info, }, { // Billionton Systems, GUSB2AM-1G-B USB_DEVICE(0x08dd, 0x0114), .driver_info = (unsigned long) &ax88178_info, }, { // ATEN UC210T USB_DEVICE (0x0557, 0x2009), .driver_info = (unsigned long) &ax8817x_info, }, { // Buffalo LUA-U2-KTX USB_DEVICE (0x0411, 0x003d), .driver_info = (unsigned long) &ax8817x_info, }, { // Buffalo LUA-U2-GT 10/100/1000 USB_DEVICE (0x0411, 0x006e), .driver_info = (unsigned long) &ax88178_info, }, { // Sitecom LN-029 "USB 2.0 10/100 Ethernet adapter" USB_DEVICE (0x6189, 0x182d), .driver_info = (unsigned long) &ax8817x_info, }, { // Sitecom LN-031 "USB 2.0 10/100/1000 Ethernet adapter" USB_DEVICE (0x0df6, 0x0056), .driver_info = (unsigned long) &ax88178_info, }, { // Sitecom LN-028 "USB 2.0 10/100/1000 Ethernet adapter" USB_DEVICE (0x0df6, 0x061c), .driver_info = (unsigned long) &ax88178_info, }, { // corega FEther USB2-TX USB_DEVICE (0x07aa, 0x0017), .driver_info = (unsigned long) &ax8817x_info, }, { // Surecom EP-1427X-2 USB_DEVICE (0x1189, 0x0893), .driver_info = (unsigned long) &ax8817x_info, }, { // goodway corp usb gwusb2e USB_DEVICE (0x1631, 0x6200), .driver_info = (unsigned long) &ax8817x_info, }, { // JVC MP-PRX1 Port Replicator USB_DEVICE (0x04f1, 0x3008), .driver_info = (unsigned long) &ax8817x_info, }, { // Lenovo U2L100P 10/100 USB_DEVICE (0x17ef, 0x7203), .driver_info = (unsigned long)&ax88772b_info, }, { // ASIX AX88772B 10/100 USB_DEVICE (0x0b95, 0x772b), .driver_info = (unsigned long) &ax88772b_info, }, { // ASIX AX88772 10/100 USB_DEVICE (0x0b95, 0x7720), .driver_info = (unsigned long) &ax88772_info, }, { // ASIX AX88178 10/100/1000 USB_DEVICE (0x0b95, 0x1780), .driver_info = (unsigned long) &ax88178_info, }, { // Logitec LAN-GTJ/U2A USB_DEVICE (0x0789, 0x0160), .driver_info = (unsigned long) &ax88178_info, }, { // Linksys USB200M Rev 2 USB_DEVICE (0x13b1, 0x0018), .driver_info = (unsigned long) &ax88772_info, }, { // 0Q0 cable ethernet USB_DEVICE (0x1557, 0x7720), .driver_info = (unsigned long) &ax88772_info, }, { // DLink DUB-E100 H/W Ver B1 USB_DEVICE (0x07d1, 0x3c05), .driver_info = (unsigned long) &ax88772_info, }, { // DLink DUB-E100 H/W Ver B1 Alternate USB_DEVICE (0x2001, 0x3c05), .driver_info = (unsigned long) &ax88772_info, }, { // DLink DUB-E100 H/W Ver C1 USB_DEVICE (0x2001, 0x1a02), .driver_info = (unsigned long) &ax88772_info, }, { // Linksys USB1000 USB_DEVICE (0x1737, 0x0039), .driver_info = (unsigned long) &ax88178_info, }, { // IO-DATA ETG-US2 USB_DEVICE (0x04bb, 0x0930), .driver_info = (unsigned long) &ax88178_info, }, { // Belkin F5D5055 USB_DEVICE(0x050d, 0x5055), .driver_info = (unsigned long) &ax88178_info, }, { // Apple USB Ethernet Adapter USB_DEVICE(0x05ac, 0x1402), .driver_info = (unsigned long) &ax88772_info, }, { // Cables-to-Go USB Ethernet Adapter USB_DEVICE(0x0b95, 0x772a), .driver_info = (unsigned long) &ax88772_info, }, { // ABOCOM for pci USB_DEVICE(0x14ea, 0xab11), .driver_info = (unsigned long) &ax88178_info, }, { // ASIX 88772a USB_DEVICE(0x0db0, 0xa877), .driver_info = (unsigned long) &ax88772_info, }, { // Asus USB Ethernet Adapter USB_DEVICE (0x0b95, 0x7e2b), .driver_info = (unsigned long)&ax88772b_info, }, { /* ASIX 88172a demo board */ USB_DEVICE(0x0b95, 0x172a), .driver_info = (unsigned long) &ax88172a_info, }, { /* * USBLINK HG20F9 "USB 2.0 LAN" * Appears to have gazumped Linksys's manufacturer ID but * doesn't (yet) conflict with any known Linksys product. */ USB_DEVICE(0x066b, 0x20f9), .driver_info = (unsigned long) &hg20f9_info, }, { // Linux Automation GmbH USB 10Base-T1L USB_DEVICE(0x33f7, 0x0004), .driver_info = (unsigned long) &lxausb_t1l_info, }, { }, // END }; MODULE_DEVICE_TABLE(usb, products); static struct usb_driver asix_driver = { .name = DRIVER_NAME, .id_table = products, .probe = usbnet_probe, .suspend = asix_suspend, .resume = asix_resume, .reset_resume = asix_resume, .disconnect = usbnet_disconnect, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; module_usb_driver(asix_driver); MODULE_AUTHOR("David Hollis"); MODULE_VERSION(DRIVER_VERSION); MODULE_DESCRIPTION("ASIX AX8817X based USB 2.0 Ethernet Devices"); MODULE_LICENSE("GPL"); |
| 6 6 11 1 1 2 1 7 6 6 6 4 2 6 6 6 6 6 6 6 4 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 | // 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_ids.h> #include <linux/bpf_local_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate.h> #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) static struct bpf_local_storage_map_bucket * select_bucket(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; } static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (!map->ops->map_local_storage_charge) return 0; return map->ops->map_local_storage_charge(smap, owner, size); } static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (map->ops->map_local_storage_uncharge) map->ops->map_local_storage_uncharge(smap, owner, size); } static struct bpf_local_storage __rcu ** owner_storage(struct bpf_local_storage_map *smap, void *owner) { struct bpf_map *map = &smap->map; return map->ops->map_owner_storage_ptr(owner); } static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed_lockless(&selem->snode); } static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed_lockless(&selem->map_node); } static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); } struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, bool charge_mem, gfp_t gfp_flags) { struct bpf_local_storage_elem *selem; if (charge_mem && mem_charge(smap, owner, smap->elem_size)) return NULL; if (smap->bpf_ma) { migrate_disable(); selem = bpf_mem_cache_alloc_flags(&smap->selem_ma, gfp_flags); migrate_enable(); if (selem) /* Keep the original bpf_map_kzalloc behavior * before started using the bpf_mem_cache_alloc. * * No need to use zero_map_value. The bpf_selem_free() * only does bpf_mem_cache_free when there is * no other bpf prog is using the selem. */ memset(SDATA(selem)->data, 0, smap->map.value_size); } else { selem = bpf_map_kzalloc(&smap->map, smap->elem_size, gfp_flags | __GFP_NOWARN); } if (selem) { if (value) copy_map_value(&smap->map, SDATA(selem)->data, value); /* No need to call check_and_init_map_value as memory is zero init */ return selem; } if (charge_mem) mem_uncharge(smap, owner, smap->elem_size); return NULL; } /* rcu tasks trace callback for bpf_ma == false */ static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; /* If RCU Tasks Trace grace period implies RCU grace period, do * kfree(), else do kfree_rcu(). */ local_storage = container_of(rcu, struct bpf_local_storage, rcu); if (rcu_trace_implies_rcu_gp()) kfree(local_storage); else kfree_rcu(local_storage, rcu); } static void bpf_local_storage_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; local_storage = container_of(rcu, struct bpf_local_storage, rcu); bpf_mem_cache_raw_free(local_storage); } static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_local_storage_free_rcu(rcu); else call_rcu(rcu, bpf_local_storage_free_rcu); } /* Handle bpf_ma == false */ static void __bpf_local_storage_free(struct bpf_local_storage *local_storage, bool vanilla_rcu) { if (vanilla_rcu) kfree_rcu(local_storage, rcu); else call_rcu_tasks_trace(&local_storage->rcu, __bpf_local_storage_free_trace_rcu); } static void bpf_local_storage_free(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool bpf_ma, bool reuse_now) { if (!local_storage) return; if (!bpf_ma) { __bpf_local_storage_free(local_storage, reuse_now); return; } if (!reuse_now) { call_rcu_tasks_trace(&local_storage->rcu, bpf_local_storage_free_trace_rcu); return; } if (smap) { migrate_disable(); bpf_mem_cache_free(&smap->storage_ma, local_storage); migrate_enable(); } else { /* smap could be NULL if the selem that triggered * this 'local_storage' creation had been long gone. * In this case, directly do call_rcu(). */ call_rcu(&local_storage->rcu, bpf_local_storage_free_rcu); } } /* rcu tasks trace callback for bpf_ma == false */ static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); if (rcu_trace_implies_rcu_gp()) kfree(selem); else kfree_rcu(selem, rcu); } /* Handle bpf_ma == false */ static void __bpf_selem_free(struct bpf_local_storage_elem *selem, bool vanilla_rcu) { if (vanilla_rcu) kfree_rcu(selem, rcu); else call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu); } static void bpf_selem_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); bpf_mem_cache_raw_free(selem); } static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_selem_free_rcu(rcu); else call_rcu(rcu, bpf_selem_free_rcu); } void bpf_selem_free(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, bool reuse_now) { bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); if (!smap->bpf_ma) { __bpf_selem_free(selem, reuse_now); return; } if (!reuse_now) { call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); } else { /* Instead of using the vanilla call_rcu(), * bpf_mem_cache_free will be able to reuse selem * immediately. */ migrate_disable(); bpf_mem_cache_free(&smap->selem_ma, selem); migrate_enable(); } } /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, bool uncharge_mem, bool reuse_now) { struct bpf_local_storage_map *smap; bool free_local_storage; void *owner; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); owner = local_storage->owner; /* All uncharging on the owner must be done first. * The owner may be freed once the last selem is unlinked * from local_storage. */ if (uncharge_mem) mem_uncharge(smap, owner, smap->elem_size); free_local_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); if (free_local_storage) { mem_uncharge(smap, owner, sizeof(struct bpf_local_storage)); local_storage->owner = NULL; /* After this RCU_INIT, owner may be freed and cannot be used */ RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); /* local_storage is not freed now. local_storage->lock is * still held and raw_spin_unlock_bh(&local_storage->lock) * will be done by the caller. * * Although the unlock will be done under * rcu_read_lock(), it is more intuitive to * read if the freeing of the storage is done * after the raw_spin_unlock_bh(&local_storage->lock). * * Hence, a "bool free_local_storage" is returned * to the caller which then calls then frees the storage after * all the RCU grace periods have expired. */ } hlist_del_init_rcu(&selem->snode); if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); bpf_selem_free(selem, smap, reuse_now); if (rcu_access_pointer(local_storage->smap) == smap) RCU_INIT_POINTER(local_storage->smap, NULL); return free_local_storage; } static bool check_storage_bpf_ma(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *storage_smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *selem_smap; /* local_storage->smap may be NULL. If it is, get the bpf_ma * from any selem in the local_storage->list. The bpf_ma of all * local_storage and selem should have the same value * for the same map type. * * If the local_storage->list is already empty, the caller will not * care about the bpf_ma value also because the caller is not * responsible to free the local_storage. */ if (storage_smap) return storage_smap->bpf_ma; if (!selem) { struct hlist_node *n; n = rcu_dereference_check(hlist_first_rcu(&local_storage->list), bpf_rcu_lock_held()); if (!n) return false; selem = hlist_entry(n, struct bpf_local_storage_elem, snode); } selem_smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); return selem_smap->bpf_ma; } static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, bool reuse_now) { struct bpf_local_storage_map *storage_smap; struct bpf_local_storage *local_storage; bool bpf_ma, free_local_storage = false; unsigned long flags; if (unlikely(!selem_linked_to_storage_lockless(selem))) /* selem has already been unlinked from sk */ return; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held()); bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, selem); raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, true, reuse_now); raw_spin_unlock_irqrestore(&local_storage->lock, flags); if (free_local_storage) bpf_local_storage_free(local_storage, storage_smap, bpf_ma, reuse_now); } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem) { RCU_INIT_POINTER(selem->local_storage, local_storage); hlist_add_head_rcu(&selem->snode, &local_storage->list); } static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; unsigned long flags; if (unlikely(!selem_linked_to_map_lockless(selem))) /* selem has already be unlinked from smap */ return; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); b = select_bucket(smap, selem); raw_spin_lock_irqsave(&b->lock, flags); if (likely(selem_linked_to_map(selem))) hlist_del_init_rcu(&selem->map_node); raw_spin_unlock_irqrestore(&b->lock, flags); } void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); unsigned long flags; raw_spin_lock_irqsave(&b->lock, flags); RCU_INIT_POINTER(SDATA(selem)->smap, smap); hlist_add_head_rcu(&selem->map_node, &b->list); raw_spin_unlock_irqrestore(&b->lock, flags); } void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from * the local_storage. */ bpf_selem_unlink_map(selem); bpf_selem_unlink_storage(selem, reuse_now); } void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { unsigned long flags; /* spinlock is needed to avoid racing with the * parallel delete. Otherwise, publishing an already * deleted sdata to the cache will become a use-after-free * problem in the next bpf_local_storage_lookup(). */ raw_spin_lock_irqsave(&local_storage->lock, flags); if (selem_linked_to_storage(selem)) rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); raw_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, u64 map_flags) { if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) /* elem already exists */ return -EEXIST; if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) /* elem doesn't exist, cannot update it */ return -ENOENT; return 0; } int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *first_selem, gfp_t gfp_flags) { struct bpf_local_storage *prev_storage, *storage; struct bpf_local_storage **owner_storage_ptr; int err; err = mem_charge(smap, owner, sizeof(*storage)); if (err) return err; if (smap->bpf_ma) { migrate_disable(); storage = bpf_mem_cache_alloc_flags(&smap->storage_ma, gfp_flags); migrate_enable(); } else { storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), gfp_flags | __GFP_NOWARN); } if (!storage) { err = -ENOMEM; goto uncharge; } RCU_INIT_POINTER(storage->smap, smap); INIT_HLIST_HEAD(&storage->list); raw_spin_lock_init(&storage->lock); storage->owner = owner; bpf_selem_link_storage_nolock(storage, first_selem); bpf_selem_link_map(smap, first_selem); owner_storage_ptr = (struct bpf_local_storage **)owner_storage(smap, owner); /* Publish storage to the owner. * Instead of using any lock of the kernel object (i.e. owner), * cmpxchg will work with any kernel object regardless what * the running context is, bh, irq...etc. * * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) * is protected by the storage->lock. Hence, when freeing * the owner->storage, the storage->lock must be held before * setting owner->storage ptr to NULL. */ prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); if (unlikely(prev_storage)) { bpf_selem_unlink_map(first_selem); err = -EAGAIN; goto uncharge; /* Note that even first_selem was linked to smap's * bucket->list, first_selem can be freed immediately * (instead of kfree_rcu) because * bpf_local_storage_map_free() does a * synchronize_rcu_mult (waiting for both sleepable and * normal programs) before walking the bucket->list. * Hence, no one is accessing selem from the * bucket->list under rcu_read_lock(). */ } return 0; uncharge: bpf_local_storage_free(storage, smap, smap->bpf_ma, true); mem_uncharge(smap, owner, sizeof(*storage)); return err; } /* sk cannot be going away because it is linking new elem * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). * Otherwise, it will become a leak (and other memory issues * during map destruction). */ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags, gfp_t gfp_flags) { struct bpf_local_storage_data *old_sdata = NULL; struct bpf_local_storage_elem *alloc_selem, *selem = NULL; struct bpf_local_storage *local_storage; unsigned long flags; int err; /* BPF_EXIST and BPF_NOEXIST cannot be both set */ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || /* BPF_F_LOCK can only be used in a value with spin_lock */ unlikely((map_flags & BPF_F_LOCK) && !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))) return ERR_PTR(-EINVAL); if (gfp_flags == GFP_KERNEL && (map_flags & ~BPF_F_LOCK) != BPF_NOEXIST) return ERR_PTR(-EINVAL); local_storage = rcu_dereference_check(*owner_storage(smap, owner), bpf_rcu_lock_held()); if (!local_storage || hlist_empty(&local_storage->list)) { /* Very first elem for the owner */ err = check_flags(NULL, map_flags); if (err) return ERR_PTR(err); selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags); if (!selem) return ERR_PTR(-ENOMEM); err = bpf_local_storage_alloc(owner, smap, selem, gfp_flags); if (err) { bpf_selem_free(selem, smap, true); mem_uncharge(smap, owner, smap->elem_size); return ERR_PTR(err); } return SDATA(selem); } if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { /* Hoping to find an old_sdata to do inline update * such that it can avoid taking the local_storage->lock * and changing the lists. */ old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; } } /* A lookup has just been done before and concluded a new selem is * needed. The chance of an unnecessary alloc is unlikely. */ alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags); if (!alloc_selem) return ERR_PTR(-ENOMEM); raw_spin_lock_irqsave(&local_storage->lock, flags); /* Recheck local_storage->list under local_storage->lock */ if (unlikely(hlist_empty(&local_storage->list))) { /* A parallel del is happening and local_storage is going * away. It has just been checked before, so very * unlikely. Return instead of retry to keep things * simple. */ err = -EAGAIN; goto unlock; } old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) goto unlock; if (old_sdata && (map_flags & BPF_F_LOCK)) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); selem = SELEM(old_sdata); goto unlock; } alloc_selem = NULL; /* First, link the new selem to the map */ bpf_selem_link_map(smap, selem); /* Second, link (and publish) the new selem to local_storage */ bpf_selem_link_storage_nolock(local_storage, selem); /* Third, remove old selem, SELEM(old_sdata) */ if (old_sdata) { bpf_selem_unlink_map(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), true, false); } unlock: raw_spin_unlock_irqrestore(&local_storage->lock, flags); if (alloc_selem) { mem_uncharge(smap, owner, smap->elem_size); bpf_selem_free(alloc_selem, smap, true); } return err ? ERR_PTR(err) : SDATA(selem); } static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) { u64 min_usage = U64_MAX; u16 i, res = 0; spin_lock(&cache->idx_lock); for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { if (cache->idx_usage_counts[i] < min_usage) { min_usage = cache->idx_usage_counts[i]; res = i; /* Found a free cache_idx */ if (!min_usage) break; } } cache->idx_usage_counts[res]++; spin_unlock(&cache->idx_lock); return res; } static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, u16 idx) { spin_lock(&cache->idx_lock); cache->idx_usage_counts[idx]--; spin_unlock(&cache->idx_lock); } int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->max_entries || attr->key_size != sizeof(int) || !attr->value_size || /* Enforce BTF for userspace sk dumping */ !attr->btf_key_type_id || !attr->btf_value_type_id) return -EINVAL; if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) return -E2BIG; return 0; } int bpf_local_storage_map_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { u32 int_data; if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) return -EINVAL; int_data = *(u32 *)(key_type + 1); if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) return -EINVAL; return 0; } void bpf_local_storage_destroy(struct bpf_local_storage *local_storage) { struct bpf_local_storage_map *storage_smap; struct bpf_local_storage_elem *selem; bool bpf_ma, free_storage = false; struct hlist_node *n; unsigned long flags; storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held()); bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, NULL); /* Neither the bpf_prog nor the bpf_map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added to or deleted from the * local_storage->list by the bpf_prog or by the bpf_map's syscall. * * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the local_storage->list and * the map's bucket->list. */ raw_spin_lock_irqsave(&local_storage->lock, flags); hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { /* Always unlink from map before unlinking from * local_storage. */ bpf_selem_unlink_map(selem); /* If local_storage list has only one element, the * bpf_selem_unlink_storage_nolock() will return true. * Otherwise, it will return false. The current loop iteration * intends to remove all local storage. So the last iteration * of the loop will set the free_cgroup_storage to true. */ free_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, true, true); } raw_spin_unlock_irqrestore(&local_storage->lock, flags); if (free_storage) bpf_local_storage_free(local_storage, storage_smap, bpf_ma, true); } u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) { struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map; u64 usage = sizeof(*smap); /* The dynamically callocated selems are not counted currently. */ usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log); return usage; } /* When bpf_ma == true, the bpf_mem_alloc is used to allocate and free memory. * A deadlock free allocator is useful for storage that the bpf prog can easily * get a hold of the owner PTR_TO_BTF_ID in any context. eg. bpf_get_current_task_btf. * The task and cgroup storage fall into this case. The bpf_mem_alloc reuses * memory immediately. To be reuse-immediate safe, the owner destruction * code path needs to go through a rcu grace period before calling * bpf_local_storage_destroy(). * * When bpf_ma == false, the kmalloc and kfree are used. */ struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, struct bpf_local_storage_cache *cache, bool bpf_ma) { struct bpf_local_storage_map *smap; unsigned int i; u32 nbuckets; int err; smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); nbuckets = roundup_pow_of_two(num_possible_cpus()); /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); smap->buckets = bpf_map_kvcalloc(&smap->map, sizeof(*smap->buckets), nbuckets, GFP_USER | __GFP_NOWARN); if (!smap->buckets) { err = -ENOMEM; goto free_smap; } for (i = 0; i < nbuckets; i++) { INIT_HLIST_HEAD(&smap->buckets[i].list); raw_spin_lock_init(&smap->buckets[i].lock); } smap->elem_size = offsetof(struct bpf_local_storage_elem, sdata.data[attr->value_size]); smap->bpf_ma = bpf_ma; if (bpf_ma) { err = bpf_mem_alloc_init(&smap->selem_ma, smap->elem_size, false); if (err) goto free_smap; err = bpf_mem_alloc_init(&smap->storage_ma, sizeof(struct bpf_local_storage), false); if (err) { bpf_mem_alloc_destroy(&smap->selem_ma); goto free_smap; } } smap->cache_idx = bpf_local_storage_cache_idx_get(cache); return &smap->map; free_smap: kvfree(smap->buckets); bpf_map_area_free(smap); return ERR_PTR(err); } void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache, int __percpu *busy_counter) { struct bpf_local_storage_map_bucket *b; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; unsigned int i; smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(cache, smap->cache_idx); /* Note that this map might be concurrently cloned from * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone * RCU read section to finish before proceeding. New RCU * read sections should be prevented via bpf_map_inc_not_zero. */ synchronize_rcu(); /* bpf prog and the userspace can no longer access this map * now. No new selem (of this map) can be added * to the owner->storage or to the map bucket's list. * * The elem of this map can be cleaned up here * or when the storage is freed e.g. * by bpf_sk_storage_free() during __sk_destruct(). */ for (i = 0; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); /* No one is adding to b->list now */ while ((selem = hlist_entry_safe( rcu_dereference_raw(hlist_first_rcu(&b->list)), struct bpf_local_storage_elem, map_node))) { if (busy_counter) { migrate_disable(); this_cpu_inc(*busy_counter); } bpf_selem_unlink(selem, true); if (busy_counter) { this_cpu_dec(*busy_counter); migrate_enable(); } cond_resched_rcu(); } rcu_read_unlock(); } /* While freeing the storage we may still need to access the map. * * e.g. when bpf_sk_storage_free() has unlinked selem from the map * which then made the above while((selem = ...)) loop * exit immediately. * * However, while freeing the storage one still needs to access the * smap->elem_size to do the uncharging in * bpf_selem_unlink_storage_nolock(). * * Hence, wait another rcu grace period for the storage to be freed. */ synchronize_rcu(); if (smap->bpf_ma) { bpf_mem_alloc_destroy(&smap->selem_ma); bpf_mem_alloc_destroy(&smap->storage_ma); } kvfree(smap->buckets); bpf_map_area_free(smap); } |
| 19 12 18 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 | /* * linux/fs/nls/nls_cp863.c * * Charset cp863 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00c2, 0x00e0, 0x00b6, 0x00e7, 0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x2017, 0x00c0, 0x00a7, /* 0x90*/ 0x00c9, 0x00c8, 0x00ca, 0x00f4, 0x00cb, 0x00cf, 0x00fb, 0x00f9, 0x00a4, 0x00d4, 0x00dc, 0x00a2, 0x00a3, 0x00d9, 0x00db, 0x0192, /* 0xa0*/ 0x00a6, 0x00b4, 0x00f3, 0x00fa, 0x00a8, 0x00b8, 0x00b3, 0x00af, 0x00ce, 0x2310, 0x00ac, 0x00bd, 0x00bc, 0x00be, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, /* 0xd0*/ 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, /* 0xe0*/ 0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4, 0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229, /* 0xf0*/ 0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0x00, 0x9b, 0x9c, 0x98, 0x00, 0xa0, 0x8f, /* 0xa0-0xa7 */ 0xa4, 0x00, 0x00, 0xae, 0xaa, 0x00, 0x00, 0xa7, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0xa6, 0xa1, 0xe6, 0x86, 0xfa, /* 0xb0-0xb7 */ 0xa5, 0x00, 0x00, 0xaf, 0xac, 0xab, 0xad, 0x00, /* 0xb8-0xbf */ 0x8e, 0x00, 0x84, 0x00, 0x00, 0x00, 0x00, 0x80, /* 0xc0-0xc7 */ 0x91, 0x90, 0x92, 0x94, 0x00, 0x00, 0xa8, 0x95, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x99, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x9d, 0x00, 0x9e, 0x9a, 0x00, 0x00, 0xe1, /* 0xd8-0xdf */ 0x85, 0x00, 0x83, 0x00, 0x00, 0x00, 0x00, 0x87, /* 0xe0-0xe7 */ 0x8a, 0x82, 0x88, 0x89, 0x00, 0x00, 0x8c, 0x8b, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0xa2, 0x93, 0x00, 0x00, 0xf6, /* 0xf0-0xf7 */ 0x00, 0x97, 0xa3, 0x96, 0x81, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x9f, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0xe2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0xe9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0xe4, 0x00, 0x00, 0xe8, 0x00, /* 0xa0-0xa7 */ 0x00, 0xea, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0xe0, 0x00, 0x00, 0xeb, 0xee, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0xe3, 0x00, 0x00, 0xe5, 0xe7, 0x00, 0xed, 0x00, /* 0xc0-0xc7 */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x8d, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, /* 0x78-0x7f */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xf9, 0xfb, 0x00, 0x00, 0x00, 0xec, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0xef, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xf7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0xf0, 0x00, 0x00, 0xf3, 0xf2, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page23[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xa9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0xf4, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0xd5, 0xd6, 0xc9, 0xb8, 0xb7, 0xbb, /* 0x50-0x57 */ 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6, 0xc7, /* 0x58-0x5f */ 0xcc, 0xb5, 0xb6, 0xb9, 0xd1, 0xd2, 0xcb, 0xcf, /* 0x60-0x67 */ 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0xdd, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xde, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, NULL, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, page22, page23, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x87, 0x81, 0x82, 0x83, 0x83, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x85, 0x8f, /* 0x88-0x8f */ 0x82, 0x8a, 0x88, 0x93, 0x89, 0x8b, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x93, 0x81, 0x9b, 0x9c, 0x97, 0x96, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0x8c, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0x00, 0xe3, 0xe5, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xed, 0x00, 0x00, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x9a, 0x90, 0x84, 0x84, 0x8e, 0x86, 0x80, /* 0x80-0x87 */ 0x92, 0x94, 0x91, 0x95, 0xa8, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x99, 0x94, 0x95, 0x9e, 0x9d, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x00, /* 0x98-0x9f */ 0xa0, 0xa1, 0x00, 0x00, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0x00, 0xe1, 0xe2, 0x00, 0xe4, 0xe4, 0x00, 0x00, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0x00, 0xec, 0xe8, 0x00, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp863", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp863(void) { return register_nls(&table); } static void __exit exit_nls_cp863(void) { unregister_nls(&table); } module_init(init_nls_cp863) module_exit(exit_nls_cp863) MODULE_LICENSE("Dual BSD/GPL"); |
| 5 1 1 1 1 19 11 8 3 9 2 7 4 10 1 11 6 5 6 5 11 10 1 1 1 1 1 1 1 3 3 1 1 12 1 2 1 1 2 1 1 2 2 1 1 4 4 5 5 8 2 3 2 5 5 4 4 4 1 38 10 19 9 3 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2014 Fraunhofer ITWM * * Written by: * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de> */ #include <linux/err.h> #include <linux/bug.h> #include <linux/completion.h> #include <linux/ieee802154.h> #include <linux/rculist.h> #include <crypto/aead.h> #include <crypto/skcipher.h> #include "ieee802154_i.h" #include "llsec.h" static void llsec_key_put(struct mac802154_llsec_key *key); static bool llsec_key_id_equal(const struct ieee802154_llsec_key_id *a, const struct ieee802154_llsec_key_id *b); static void llsec_dev_free(struct mac802154_llsec_device *dev); void mac802154_llsec_init(struct mac802154_llsec *sec) { memset(sec, 0, sizeof(*sec)); memset(&sec->params.default_key_source, 0xFF, IEEE802154_ADDR_LEN); INIT_LIST_HEAD(&sec->table.security_levels); INIT_LIST_HEAD(&sec->table.devices); INIT_LIST_HEAD(&sec->table.keys); hash_init(sec->devices_short); hash_init(sec->devices_hw); rwlock_init(&sec->lock); } void mac802154_llsec_destroy(struct mac802154_llsec *sec) { struct ieee802154_llsec_seclevel *sl, *sn; struct ieee802154_llsec_device *dev, *dn; struct ieee802154_llsec_key_entry *key, *kn; list_for_each_entry_safe(sl, sn, &sec->table.security_levels, list) { struct mac802154_llsec_seclevel *msl; msl = container_of(sl, struct mac802154_llsec_seclevel, level); list_del(&sl->list); kfree_sensitive(msl); } list_for_each_entry_safe(dev, dn, &sec->table.devices, list) { struct mac802154_llsec_device *mdev; mdev = container_of(dev, struct mac802154_llsec_device, dev); list_del(&dev->list); llsec_dev_free(mdev); } list_for_each_entry_safe(key, kn, &sec->table.keys, list) { struct mac802154_llsec_key *mkey; mkey = container_of(key->key, struct mac802154_llsec_key, key); list_del(&key->list); llsec_key_put(mkey); kfree_sensitive(key); } } int mac802154_llsec_get_params(struct mac802154_llsec *sec, struct ieee802154_llsec_params *params) { read_lock_bh(&sec->lock); *params = sec->params; read_unlock_bh(&sec->lock); return 0; } int mac802154_llsec_set_params(struct mac802154_llsec *sec, const struct ieee802154_llsec_params *params, int changed) { write_lock_bh(&sec->lock); if (changed & IEEE802154_LLSEC_PARAM_ENABLED) sec->params.enabled = params->enabled; if (changed & IEEE802154_LLSEC_PARAM_FRAME_COUNTER) sec->params.frame_counter = params->frame_counter; if (changed & IEEE802154_LLSEC_PARAM_OUT_LEVEL) sec->params.out_level = params->out_level; if (changed & IEEE802154_LLSEC_PARAM_OUT_KEY) sec->params.out_key = params->out_key; if (changed & IEEE802154_LLSEC_PARAM_KEY_SOURCE) sec->params.default_key_source = params->default_key_source; if (changed & IEEE802154_LLSEC_PARAM_PAN_ID) sec->params.pan_id = params->pan_id; if (changed & IEEE802154_LLSEC_PARAM_HWADDR) sec->params.hwaddr = params->hwaddr; if (changed & IEEE802154_LLSEC_PARAM_COORD_HWADDR) sec->params.coord_hwaddr = params->coord_hwaddr; if (changed & IEEE802154_LLSEC_PARAM_COORD_SHORTADDR) sec->params.coord_shortaddr = params->coord_shortaddr; write_unlock_bh(&sec->lock); return 0; } static struct mac802154_llsec_key* llsec_key_alloc(const struct ieee802154_llsec_key *template) { const int authsizes[3] = { 4, 8, 16 }; struct mac802154_llsec_key *key; int i; key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) return NULL; kref_init(&key->ref); key->key = *template; BUILD_BUG_ON(ARRAY_SIZE(authsizes) != ARRAY_SIZE(key->tfm)); for (i = 0; i < ARRAY_SIZE(key->tfm); i++) { key->tfm[i] = crypto_alloc_aead("ccm(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(key->tfm[i])) goto err_tfm; if (crypto_aead_setkey(key->tfm[i], template->key, IEEE802154_LLSEC_KEY_SIZE)) goto err_tfm; if (crypto_aead_setauthsize(key->tfm[i], authsizes[i])) goto err_tfm; } key->tfm0 = crypto_alloc_sync_skcipher("ctr(aes)", 0, 0); if (IS_ERR(key->tfm0)) goto err_tfm; if (crypto_sync_skcipher_setkey(key->tfm0, template->key, IEEE802154_LLSEC_KEY_SIZE)) goto err_tfm0; return key; err_tfm0: crypto_free_sync_skcipher(key->tfm0); err_tfm: for (i = 0; i < ARRAY_SIZE(key->tfm); i++) if (!IS_ERR_OR_NULL(key->tfm[i])) crypto_free_aead(key->tfm[i]); kfree_sensitive(key); return NULL; } static void llsec_key_release(struct kref *ref) { struct mac802154_llsec_key *key; int i; key = container_of(ref, struct mac802154_llsec_key, ref); for (i = 0; i < ARRAY_SIZE(key->tfm); i++) crypto_free_aead(key->tfm[i]); crypto_free_sync_skcipher(key->tfm0); kfree_sensitive(key); } static struct mac802154_llsec_key* llsec_key_get(struct mac802154_llsec_key *key) { kref_get(&key->ref); return key; } static void llsec_key_put(struct mac802154_llsec_key *key) { kref_put(&key->ref, llsec_key_release); } static bool llsec_key_id_equal(const struct ieee802154_llsec_key_id *a, const struct ieee802154_llsec_key_id *b) { if (a->mode != b->mode) return false; if (a->mode == IEEE802154_SCF_KEY_IMPLICIT) return ieee802154_addr_equal(&a->device_addr, &b->device_addr); if (a->id != b->id) return false; switch (a->mode) { case IEEE802154_SCF_KEY_INDEX: return true; case IEEE802154_SCF_KEY_SHORT_INDEX: return a->short_source == b->short_source; case IEEE802154_SCF_KEY_HW_INDEX: return a->extended_source == b->extended_source; } return false; } int mac802154_llsec_key_add(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *id, const struct ieee802154_llsec_key *key) { struct mac802154_llsec_key *mkey = NULL; struct ieee802154_llsec_key_entry *pos, *new; if (!(key->frame_types & (1 << IEEE802154_FC_TYPE_MAC_CMD)) && key->cmd_frame_ids) return -EINVAL; list_for_each_entry(pos, &sec->table.keys, list) { if (llsec_key_id_equal(&pos->id, id)) return -EEXIST; if (memcmp(pos->key->key, key->key, IEEE802154_LLSEC_KEY_SIZE)) continue; mkey = container_of(pos->key, struct mac802154_llsec_key, key); /* Don't allow multiple instances of the same AES key to have * different allowed frame types/command frame ids, as this is * not possible in the 802.15.4 PIB. */ if (pos->key->frame_types != key->frame_types || pos->key->cmd_frame_ids != key->cmd_frame_ids) return -EEXIST; break; } new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return -ENOMEM; if (!mkey) mkey = llsec_key_alloc(key); else mkey = llsec_key_get(mkey); if (!mkey) goto fail; new->id = *id; new->key = &mkey->key; list_add_rcu(&new->list, &sec->table.keys); return 0; fail: kfree_sensitive(new); return -ENOMEM; } static void mac802154_llsec_key_del_rcu(struct rcu_head *rcu) { struct ieee802154_llsec_key_entry *pos; struct mac802154_llsec_key *mkey; pos = container_of(rcu, struct ieee802154_llsec_key_entry, rcu); mkey = container_of(pos->key, struct mac802154_llsec_key, key); llsec_key_put(mkey); kfree_sensitive(pos); } int mac802154_llsec_key_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_key_entry *pos; list_for_each_entry(pos, &sec->table.keys, list) { if (llsec_key_id_equal(&pos->id, key)) { list_del_rcu(&pos->list); call_rcu(&pos->rcu, mac802154_llsec_key_del_rcu); return 0; } } return -ENOENT; } static bool llsec_dev_use_shortaddr(__le16 short_addr) { return short_addr != cpu_to_le16(IEEE802154_ADDR_UNDEF) && short_addr != cpu_to_le16(0xffff); } static u32 llsec_dev_hash_short(__le16 short_addr, __le16 pan_id) { return ((__force u16)short_addr) << 16 | (__force u16)pan_id; } static u64 llsec_dev_hash_long(__le64 hwaddr) { return (__force u64)hwaddr; } static struct mac802154_llsec_device* llsec_dev_find_short(struct mac802154_llsec *sec, __le16 short_addr, __le16 pan_id) { struct mac802154_llsec_device *dev; u32 key = llsec_dev_hash_short(short_addr, pan_id); hash_for_each_possible_rcu(sec->devices_short, dev, bucket_s, key) { if (dev->dev.short_addr == short_addr && dev->dev.pan_id == pan_id) return dev; } return NULL; } static struct mac802154_llsec_device* llsec_dev_find_long(struct mac802154_llsec *sec, __le64 hwaddr) { struct mac802154_llsec_device *dev; u64 key = llsec_dev_hash_long(hwaddr); hash_for_each_possible_rcu(sec->devices_hw, dev, bucket_hw, key) { if (dev->dev.hwaddr == hwaddr) return dev; } return NULL; } static void llsec_dev_free(struct mac802154_llsec_device *dev) { struct ieee802154_llsec_device_key *pos, *pn; struct mac802154_llsec_device_key *devkey; list_for_each_entry_safe(pos, pn, &dev->dev.keys, list) { devkey = container_of(pos, struct mac802154_llsec_device_key, devkey); list_del(&pos->list); kfree_sensitive(devkey); } kfree_sensitive(dev); } int mac802154_llsec_dev_add(struct mac802154_llsec *sec, const struct ieee802154_llsec_device *dev) { struct mac802154_llsec_device *entry; u32 skey = llsec_dev_hash_short(dev->short_addr, dev->pan_id); u64 hwkey = llsec_dev_hash_long(dev->hwaddr); BUILD_BUG_ON(sizeof(hwkey) != IEEE802154_ADDR_LEN); if ((llsec_dev_use_shortaddr(dev->short_addr) && llsec_dev_find_short(sec, dev->short_addr, dev->pan_id)) || llsec_dev_find_long(sec, dev->hwaddr)) return -EEXIST; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; entry->dev = *dev; spin_lock_init(&entry->lock); INIT_LIST_HEAD(&entry->dev.keys); if (llsec_dev_use_shortaddr(dev->short_addr)) hash_add_rcu(sec->devices_short, &entry->bucket_s, skey); else INIT_HLIST_NODE(&entry->bucket_s); hash_add_rcu(sec->devices_hw, &entry->bucket_hw, hwkey); list_add_tail_rcu(&entry->dev.list, &sec->table.devices); return 0; } static void llsec_dev_free_rcu(struct rcu_head *rcu) { llsec_dev_free(container_of(rcu, struct mac802154_llsec_device, rcu)); } int mac802154_llsec_dev_del(struct mac802154_llsec *sec, __le64 device_addr) { struct mac802154_llsec_device *pos; pos = llsec_dev_find_long(sec, device_addr); if (!pos) return -ENOENT; hash_del_rcu(&pos->bucket_s); hash_del_rcu(&pos->bucket_hw); list_del_rcu(&pos->dev.list); call_rcu(&pos->rcu, llsec_dev_free_rcu); return 0; } static struct mac802154_llsec_device_key* llsec_devkey_find(struct mac802154_llsec_device *dev, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_device_key *devkey; list_for_each_entry_rcu(devkey, &dev->dev.keys, list) { if (!llsec_key_id_equal(key, &devkey->key_id)) continue; return container_of(devkey, struct mac802154_llsec_device_key, devkey); } return NULL; } int mac802154_llsec_devkey_add(struct mac802154_llsec *sec, __le64 dev_addr, const struct ieee802154_llsec_device_key *key) { struct mac802154_llsec_device *dev; struct mac802154_llsec_device_key *devkey; dev = llsec_dev_find_long(sec, dev_addr); if (!dev) return -ENOENT; if (llsec_devkey_find(dev, &key->key_id)) return -EEXIST; devkey = kmalloc(sizeof(*devkey), GFP_KERNEL); if (!devkey) return -ENOMEM; devkey->devkey = *key; list_add_tail_rcu(&devkey->devkey.list, &dev->dev.keys); return 0; } int mac802154_llsec_devkey_del(struct mac802154_llsec *sec, __le64 dev_addr, const struct ieee802154_llsec_device_key *key) { struct mac802154_llsec_device *dev; struct mac802154_llsec_device_key *devkey; dev = llsec_dev_find_long(sec, dev_addr); if (!dev) return -ENOENT; devkey = llsec_devkey_find(dev, &key->key_id); if (!devkey) return -ENOENT; list_del_rcu(&devkey->devkey.list); kfree_rcu(devkey, rcu); return 0; } static struct mac802154_llsec_seclevel* llsec_find_seclevel(const struct mac802154_llsec *sec, const struct ieee802154_llsec_seclevel *sl) { struct ieee802154_llsec_seclevel *pos; list_for_each_entry(pos, &sec->table.security_levels, list) { if (pos->frame_type != sl->frame_type || (pos->frame_type == IEEE802154_FC_TYPE_MAC_CMD && pos->cmd_frame_id != sl->cmd_frame_id) || pos->device_override != sl->device_override || pos->sec_levels != sl->sec_levels) continue; return container_of(pos, struct mac802154_llsec_seclevel, level); } return NULL; } int mac802154_llsec_seclevel_add(struct mac802154_llsec *sec, const struct ieee802154_llsec_seclevel *sl) { struct mac802154_llsec_seclevel *entry; if (llsec_find_seclevel(sec, sl)) return -EEXIST; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; entry->level = *sl; list_add_tail_rcu(&entry->level.list, &sec->table.security_levels); return 0; } int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_seclevel *sl) { struct mac802154_llsec_seclevel *pos; pos = llsec_find_seclevel(sec, sl); if (!pos) return -ENOENT; list_del_rcu(&pos->level.list); kfree_rcu(pos, rcu); return 0; } static int llsec_recover_addr(struct mac802154_llsec *sec, struct ieee802154_addr *addr) { __le16 caddr = sec->params.coord_shortaddr; addr->pan_id = sec->params.pan_id; if (caddr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { return -EINVAL; } else if (caddr == cpu_to_le16(IEEE802154_ADDR_UNDEF)) { addr->extended_addr = sec->params.coord_hwaddr; addr->mode = IEEE802154_ADDR_LONG; } else { addr->short_addr = sec->params.coord_shortaddr; addr->mode = IEEE802154_ADDR_SHORT; } return 0; } static struct mac802154_llsec_key* llsec_lookup_key(struct mac802154_llsec *sec, const struct ieee802154_hdr *hdr, const struct ieee802154_addr *addr, struct ieee802154_llsec_key_id *key_id) { struct ieee802154_addr devaddr = *addr; u8 key_id_mode = hdr->sec.key_id_mode; struct ieee802154_llsec_key_entry *key_entry; struct mac802154_llsec_key *key; if (key_id_mode == IEEE802154_SCF_KEY_IMPLICIT && devaddr.mode == IEEE802154_ADDR_NONE) { if (hdr->fc.type == IEEE802154_FC_TYPE_BEACON) { devaddr.extended_addr = sec->params.coord_hwaddr; devaddr.mode = IEEE802154_ADDR_LONG; } else if (llsec_recover_addr(sec, &devaddr) < 0) { return NULL; } } list_for_each_entry_rcu(key_entry, &sec->table.keys, list) { const struct ieee802154_llsec_key_id *id = &key_entry->id; if (!(key_entry->key->frame_types & BIT(hdr->fc.type))) continue; if (id->mode != key_id_mode) continue; if (key_id_mode == IEEE802154_SCF_KEY_IMPLICIT) { if (ieee802154_addr_equal(&devaddr, &id->device_addr)) goto found; } else { if (id->id != hdr->sec.key_id) continue; if ((key_id_mode == IEEE802154_SCF_KEY_INDEX) || (key_id_mode == IEEE802154_SCF_KEY_SHORT_INDEX && id->short_source == hdr->sec.short_src) || (key_id_mode == IEEE802154_SCF_KEY_HW_INDEX && id->extended_source == hdr->sec.extended_src)) goto found; } } return NULL; found: key = container_of(key_entry->key, struct mac802154_llsec_key, key); if (key_id) *key_id = key_entry->id; return llsec_key_get(key); } static void llsec_geniv(u8 iv[16], __le64 addr, const struct ieee802154_sechdr *sec) { __be64 addr_bytes = (__force __be64) swab64((__force u64) addr); __be32 frame_counter = (__force __be32) swab32((__force u32) sec->frame_counter); iv[0] = 1; /* L' = L - 1 = 1 */ memcpy(iv + 1, &addr_bytes, sizeof(addr_bytes)); memcpy(iv + 9, &frame_counter, sizeof(frame_counter)); iv[13] = sec->level; iv[14] = 0; iv[15] = 1; } static int llsec_do_encrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec, const struct ieee802154_hdr *hdr, struct mac802154_llsec_key *key) { u8 iv[16]; struct scatterlist src; SYNC_SKCIPHER_REQUEST_ON_STACK(req, key->tfm0); int err, datalen; unsigned char *data; llsec_geniv(iv, sec->params.hwaddr, &hdr->sec); /* Compute data payload offset and data length */ data = skb_mac_header(skb) + skb->mac_len; datalen = skb_tail_pointer(skb) - data; sg_init_one(&src, data, datalen); skcipher_request_set_sync_tfm(req, key->tfm0); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &src, &src, datalen, iv); err = crypto_skcipher_encrypt(req); skcipher_request_zero(req); return err; } static struct crypto_aead* llsec_tfm_by_len(struct mac802154_llsec_key *key, int authlen) { int i; for (i = 0; i < ARRAY_SIZE(key->tfm); i++) if (crypto_aead_authsize(key->tfm[i]) == authlen) return key->tfm[i]; BUG(); } static int llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, const struct ieee802154_hdr *hdr, struct mac802154_llsec_key *key) { u8 iv[16]; unsigned char *data; int authlen, assoclen, datalen, rc; struct scatterlist sg; struct aead_request *req; authlen = ieee802154_sechdr_authtag_len(&hdr->sec); llsec_geniv(iv, sec->params.hwaddr, &hdr->sec); req = aead_request_alloc(llsec_tfm_by_len(key, authlen), GFP_ATOMIC); if (!req) return -ENOMEM; assoclen = skb->mac_len; data = skb_mac_header(skb) + skb->mac_len; datalen = skb_tail_pointer(skb) - data; skb_put(skb, authlen); sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen + authlen); if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) { assoclen += datalen; datalen = 0; } aead_request_set_callback(req, 0, NULL, NULL); aead_request_set_crypt(req, &sg, &sg, datalen, iv); aead_request_set_ad(req, assoclen); rc = crypto_aead_encrypt(req); kfree_sensitive(req); return rc; } static int llsec_do_encrypt(struct sk_buff *skb, const struct mac802154_llsec *sec, const struct ieee802154_hdr *hdr, struct mac802154_llsec_key *key) { if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC) return llsec_do_encrypt_unauth(skb, sec, hdr, key); else return llsec_do_encrypt_auth(skb, sec, hdr, key); } int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb) { struct ieee802154_hdr hdr; int rc, authlen, hlen; struct mac802154_llsec_key *key; u32 frame_ctr; hlen = ieee802154_hdr_pull(skb, &hdr); /* TODO: control frames security support */ if (hlen < 0 || (hdr.fc.type != IEEE802154_FC_TYPE_DATA && hdr.fc.type != IEEE802154_FC_TYPE_BEACON)) return -EINVAL; if (!hdr.fc.security_enabled || (hdr.sec.level == IEEE802154_SCF_SECLEVEL_NONE)) { skb_push(skb, hlen); return 0; } authlen = ieee802154_sechdr_authtag_len(&hdr.sec); if (skb->len + hlen + authlen + IEEE802154_MFR_SIZE > IEEE802154_MTU) return -EMSGSIZE; rcu_read_lock(); read_lock_bh(&sec->lock); if (!sec->params.enabled) { rc = -EINVAL; goto fail_read; } key = llsec_lookup_key(sec, &hdr, &hdr.dest, NULL); if (!key) { rc = -ENOKEY; goto fail_read; } read_unlock_bh(&sec->lock); write_lock_bh(&sec->lock); frame_ctr = be32_to_cpu(sec->params.frame_counter); hdr.sec.frame_counter = cpu_to_le32(frame_ctr); if (frame_ctr == 0xFFFFFFFF) { write_unlock_bh(&sec->lock); llsec_key_put(key); rc = -EOVERFLOW; goto fail; } sec->params.frame_counter = cpu_to_be32(frame_ctr + 1); write_unlock_bh(&sec->lock); rcu_read_unlock(); skb->mac_len = ieee802154_hdr_push(skb, &hdr); skb_reset_mac_header(skb); rc = llsec_do_encrypt(skb, sec, &hdr, key); llsec_key_put(key); return rc; fail_read: read_unlock_bh(&sec->lock); fail: rcu_read_unlock(); return rc; } static struct mac802154_llsec_device* llsec_lookup_dev(struct mac802154_llsec *sec, const struct ieee802154_addr *addr) { struct ieee802154_addr devaddr = *addr; struct mac802154_llsec_device *dev = NULL; if (devaddr.mode == IEEE802154_ADDR_NONE && llsec_recover_addr(sec, &devaddr) < 0) return NULL; if (devaddr.mode == IEEE802154_ADDR_SHORT) { u32 key = llsec_dev_hash_short(devaddr.short_addr, devaddr.pan_id); hash_for_each_possible_rcu(sec->devices_short, dev, bucket_s, key) { if (dev->dev.pan_id == devaddr.pan_id && dev->dev.short_addr == devaddr.short_addr) return dev; } } else { u64 key = llsec_dev_hash_long(devaddr.extended_addr); hash_for_each_possible_rcu(sec->devices_hw, dev, bucket_hw, key) { if (dev->dev.hwaddr == devaddr.extended_addr) return dev; } } return NULL; } static int llsec_lookup_seclevel(const struct mac802154_llsec *sec, u8 frame_type, u8 cmd_frame_id, struct ieee802154_llsec_seclevel *rlevel) { struct ieee802154_llsec_seclevel *level; list_for_each_entry_rcu(level, &sec->table.security_levels, list) { if (level->frame_type == frame_type && (frame_type != IEEE802154_FC_TYPE_MAC_CMD || level->cmd_frame_id == cmd_frame_id)) { *rlevel = *level; return 0; } } return -EINVAL; } static int llsec_do_decrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec, const struct ieee802154_hdr *hdr, struct mac802154_llsec_key *key, __le64 dev_addr) { u8 iv[16]; unsigned char *data; int datalen; struct scatterlist src; SYNC_SKCIPHER_REQUEST_ON_STACK(req, key->tfm0); int err; llsec_geniv(iv, dev_addr, &hdr->sec); data = skb_mac_header(skb) + skb->mac_len; datalen = skb_tail_pointer(skb) - data; sg_init_one(&src, data, datalen); skcipher_request_set_sync_tfm(req, key->tfm0); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &src, &src, datalen, iv); err = crypto_skcipher_decrypt(req); skcipher_request_zero(req); return err; } static int llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec, const struct ieee802154_hdr *hdr, struct mac802154_llsec_key *key, __le64 dev_addr) { u8 iv[16]; unsigned char *data; int authlen, datalen, assoclen, rc; struct scatterlist sg; struct aead_request *req; authlen = ieee802154_sechdr_authtag_len(&hdr->sec); llsec_geniv(iv, dev_addr, &hdr->sec); req = aead_request_alloc(llsec_tfm_by_len(key, authlen), GFP_ATOMIC); if (!req) return -ENOMEM; assoclen = skb->mac_len; data = skb_mac_header(skb) + skb->mac_len; datalen = skb_tail_pointer(skb) - data; sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen); if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) { assoclen += datalen - authlen; datalen = authlen; } aead_request_set_callback(req, 0, NULL, NULL); aead_request_set_crypt(req, &sg, &sg, datalen, iv); aead_request_set_ad(req, assoclen); rc = crypto_aead_decrypt(req); kfree_sensitive(req); skb_trim(skb, skb->len - authlen); return rc; } static int llsec_do_decrypt(struct sk_buff *skb, const struct mac802154_llsec *sec, const struct ieee802154_hdr *hdr, struct mac802154_llsec_key *key, __le64 dev_addr) { if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC) return llsec_do_decrypt_unauth(skb, sec, hdr, key, dev_addr); else return llsec_do_decrypt_auth(skb, sec, hdr, key, dev_addr); } static int llsec_update_devkey_record(struct mac802154_llsec_device *dev, const struct ieee802154_llsec_key_id *in_key) { struct mac802154_llsec_device_key *devkey; devkey = llsec_devkey_find(dev, in_key); if (!devkey) { struct mac802154_llsec_device_key *next; next = kzalloc(sizeof(*devkey), GFP_ATOMIC); if (!next) return -ENOMEM; next->devkey.key_id = *in_key; spin_lock_bh(&dev->lock); devkey = llsec_devkey_find(dev, in_key); if (!devkey) list_add_rcu(&next->devkey.list, &dev->dev.keys); else kfree_sensitive(next); spin_unlock_bh(&dev->lock); } return 0; } static int llsec_update_devkey_info(struct mac802154_llsec_device *dev, const struct ieee802154_llsec_key_id *in_key, u32 frame_counter) { struct mac802154_llsec_device_key *devkey = NULL; if (dev->dev.key_mode == IEEE802154_LLSEC_DEVKEY_RESTRICT) { devkey = llsec_devkey_find(dev, in_key); if (!devkey) return -ENOENT; } if (dev->dev.key_mode == IEEE802154_LLSEC_DEVKEY_RECORD) { int rc = llsec_update_devkey_record(dev, in_key); if (rc < 0) return rc; } spin_lock_bh(&dev->lock); if ((!devkey && frame_counter < dev->dev.frame_counter) || (devkey && frame_counter < devkey->devkey.frame_counter)) { spin_unlock_bh(&dev->lock); return -EINVAL; } if (devkey) devkey->devkey.frame_counter = frame_counter + 1; else dev->dev.frame_counter = frame_counter + 1; spin_unlock_bh(&dev->lock); return 0; } int mac802154_llsec_decrypt(struct mac802154_llsec *sec, struct sk_buff *skb) { struct ieee802154_hdr hdr; struct mac802154_llsec_key *key; struct ieee802154_llsec_key_id key_id; struct mac802154_llsec_device *dev; struct ieee802154_llsec_seclevel seclevel; int err; __le64 dev_addr; u32 frame_ctr; if (ieee802154_hdr_peek(skb, &hdr) < 0) return -EINVAL; if (!hdr.fc.security_enabled) return 0; if (hdr.fc.version == 0) return -EINVAL; read_lock_bh(&sec->lock); if (!sec->params.enabled) { read_unlock_bh(&sec->lock); return -EINVAL; } read_unlock_bh(&sec->lock); rcu_read_lock(); key = llsec_lookup_key(sec, &hdr, &hdr.source, &key_id); if (!key) { err = -ENOKEY; goto fail; } dev = llsec_lookup_dev(sec, &hdr.source); if (!dev) { err = -EINVAL; goto fail_dev; } if (llsec_lookup_seclevel(sec, hdr.fc.type, 0, &seclevel) < 0) { err = -EINVAL; goto fail_dev; } if (!(seclevel.sec_levels & BIT(hdr.sec.level)) && (hdr.sec.level == 0 && seclevel.device_override && !dev->dev.seclevel_exempt)) { err = -EINVAL; goto fail_dev; } frame_ctr = le32_to_cpu(hdr.sec.frame_counter); if (frame_ctr == 0xffffffff) { err = -EOVERFLOW; goto fail_dev; } err = llsec_update_devkey_info(dev, &key_id, frame_ctr); if (err) goto fail_dev; dev_addr = dev->dev.hwaddr; rcu_read_unlock(); err = llsec_do_decrypt(skb, sec, &hdr, key, dev_addr); llsec_key_put(key); return err; fail_dev: llsec_key_put(key); fail: rcu_read_unlock(); return err; } |
| 3 6 6 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Kernel-based Virtual Machine driver for Linux * * This header defines architecture specific interfaces, x86 version */ #ifndef _ASM_X86_KVM_HOST_H #define _ASM_X86_KVM_HOST_H #include <linux/types.h> #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/tracepoint.h> #include <linux/cpumask.h> #include <linux/irq_work.h> #include <linux/irq.h> #include <linux/workqueue.h> #include <linux/kvm.h> #include <linux/kvm_para.h> #include <linux/kvm_types.h> #include <linux/perf_event.h> #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> #include <linux/irqbypass.h> #include <linux/hyperv.h> #include <linux/kfifo.h> #include <asm/apic.h> #include <asm/pvclock-abi.h> #include <asm/desc.h> #include <asm/mtrr.h> #include <asm/msr-index.h> #include <asm/asm.h> #include <asm/kvm_page_track.h> #include <asm/kvm_vcpu_regs.h> #include <asm/hyperv-tlfs.h> #define __KVM_HAVE_ARCH_VCPU_DEBUGFS /* * CONFIG_KVM_MAX_NR_VCPUS is defined iff CONFIG_KVM!=n, provide a dummy max if * KVM is disabled (arbitrarily use the default from CONFIG_KVM_MAX_NR_VCPUS). */ #ifdef CONFIG_KVM_MAX_NR_VCPUS #define KVM_MAX_VCPUS CONFIG_KVM_MAX_NR_VCPUS #else #define KVM_MAX_VCPUS 1024 #endif /* * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs * might be larger than the actual number of VCPUs because the * APIC ID encodes CPU topology information. * * In the worst case, we'll need less than one extra bit for the * Core ID, and less than one extra bit for the Package (Die) ID, * so ratio of 4 should be enough. */ #define KVM_VCPU_ID_RATIO 4 #define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) /* memory slots that are not exposed to userspace */ #define KVM_INTERNAL_MEM_SLOTS 3 #define KVM_HALT_POLL_NS_DEFAULT 200000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) #define KVM_BUS_LOCK_DETECTION_VALID_MODE (KVM_BUS_LOCK_DETECTION_OFF | \ KVM_BUS_LOCK_DETECTION_EXIT) #define KVM_X86_NOTIFY_VMEXIT_VALID_BITS (KVM_X86_NOTIFY_VMEXIT_ENABLED | \ KVM_X86_NOTIFY_VMEXIT_USER) /* x86-specific vcpu->requests bit members */ #define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) #define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) #define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) #define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) #define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) #define KVM_REQ_LOAD_MMU_PGD KVM_ARCH_REQ(5) #define KVM_REQ_EVENT KVM_ARCH_REQ(6) #define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) #define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) #define KVM_REQ_NMI KVM_ARCH_REQ(9) #define KVM_REQ_PMU KVM_ARCH_REQ(10) #define KVM_REQ_PMI KVM_ARCH_REQ(11) #ifdef CONFIG_KVM_SMM #define KVM_REQ_SMI KVM_ARCH_REQ(12) #endif #define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13) #define KVM_REQ_MCLOCK_INPROGRESS \ KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_SCAN_IOAPIC \ KVM_ARCH_REQ_FLAGS(15, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_GLOBAL_CLOCK_UPDATE KVM_ARCH_REQ(16) #define KVM_REQ_APIC_PAGE_RELOAD \ KVM_ARCH_REQ_FLAGS(17, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_HV_CRASH KVM_ARCH_REQ(18) #define KVM_REQ_IOAPIC_EOI_EXIT KVM_ARCH_REQ(19) #define KVM_REQ_HV_RESET KVM_ARCH_REQ(20) #define KVM_REQ_HV_EXIT KVM_ARCH_REQ(21) #define KVM_REQ_HV_STIMER KVM_ARCH_REQ(22) #define KVM_REQ_LOAD_EOI_EXITMAP KVM_ARCH_REQ(23) #define KVM_REQ_GET_NESTED_STATE_PAGES KVM_ARCH_REQ(24) #define KVM_REQ_APICV_UPDATE \ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) #define KVM_REQ_TLB_FLUSH_GUEST \ KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) #define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_FREE_OBSOLETE_ROOTS \ KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_HV_TLB_FLUSH \ KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE KVM_ARCH_REQ(34) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) #define CR4_RESERVED_BITS \ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \ | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \ | X86_CR4_LAM_SUP)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) #define INVALID_PAGE (~(hpa_t)0) #define VALID_PAGE(x) ((x) != INVALID_PAGE) /* KVM Hugepage definitions for x86 */ #define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G #define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1) #define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9) #define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) #define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) #define KVM_MEMSLOT_PAGES_TO_MMU_PAGES_RATIO 50 #define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 256 #define KVM_NR_FIXED_MTRR_REGION 88 #define KVM_NR_VAR_MTRR 8 #define ASYNC_PF_PER_VCPU 64 enum kvm_reg { VCPU_REGS_RAX = __VCPU_REGS_RAX, VCPU_REGS_RCX = __VCPU_REGS_RCX, VCPU_REGS_RDX = __VCPU_REGS_RDX, VCPU_REGS_RBX = __VCPU_REGS_RBX, VCPU_REGS_RSP = __VCPU_REGS_RSP, VCPU_REGS_RBP = __VCPU_REGS_RBP, VCPU_REGS_RSI = __VCPU_REGS_RSI, VCPU_REGS_RDI = __VCPU_REGS_RDI, #ifdef CONFIG_X86_64 VCPU_REGS_R8 = __VCPU_REGS_R8, VCPU_REGS_R9 = __VCPU_REGS_R9, VCPU_REGS_R10 = __VCPU_REGS_R10, VCPU_REGS_R11 = __VCPU_REGS_R11, VCPU_REGS_R12 = __VCPU_REGS_R12, VCPU_REGS_R13 = __VCPU_REGS_R13, VCPU_REGS_R14 = __VCPU_REGS_R14, VCPU_REGS_R15 = __VCPU_REGS_R15, #endif VCPU_REGS_RIP, NR_VCPU_REGS, VCPU_EXREG_PDPTR = NR_VCPU_REGS, VCPU_EXREG_CR0, VCPU_EXREG_CR3, VCPU_EXREG_CR4, VCPU_EXREG_RFLAGS, VCPU_EXREG_SEGMENTS, VCPU_EXREG_EXIT_INFO_1, VCPU_EXREG_EXIT_INFO_2, }; enum { VCPU_SREG_ES, VCPU_SREG_CS, VCPU_SREG_SS, VCPU_SREG_DS, VCPU_SREG_FS, VCPU_SREG_GS, VCPU_SREG_TR, VCPU_SREG_LDTR, }; enum exit_fastpath_completion { EXIT_FASTPATH_NONE, EXIT_FASTPATH_REENTER_GUEST, EXIT_FASTPATH_EXIT_HANDLED, }; typedef enum exit_fastpath_completion fastpath_t; struct x86_emulate_ctxt; struct x86_exception; union kvm_smram; enum x86_intercept; enum x86_intercept_stage; #define KVM_NR_DB_REGS 4 #define DR6_BUS_LOCK (1 << 11) #define DR6_BD (1 << 13) #define DR6_BS (1 << 14) #define DR6_BT (1 << 15) #define DR6_RTM (1 << 16) /* * DR6_ACTIVE_LOW combines fixed-1 and active-low bits. * We can regard all the bits in DR6_FIXED_1 as active_low bits; * they will never be 0 for now, but when they are defined * in the future it will require no code change. * * DR6_ACTIVE_LOW is also used as the init/reset value for DR6. */ #define DR6_ACTIVE_LOW 0xffff0ff0 #define DR6_VOLATILE 0x0001e80f #define DR6_FIXED_1 (DR6_ACTIVE_LOW & ~DR6_VOLATILE) #define DR7_BP_EN_MASK 0x000000ff #define DR7_GE (1 << 9) #define DR7_GD (1 << 13) #define DR7_FIXED_1 0x00000400 #define DR7_VOLATILE 0xffff2bff #define KVM_GUESTDBG_VALID_MASK \ (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_SINGLESTEP | \ KVM_GUESTDBG_USE_HW_BP | \ KVM_GUESTDBG_USE_SW_BP | \ KVM_GUESTDBG_INJECT_BP | \ KVM_GUESTDBG_INJECT_DB | \ KVM_GUESTDBG_BLOCKIRQ) #define PFERR_PRESENT_MASK BIT(0) #define PFERR_WRITE_MASK BIT(1) #define PFERR_USER_MASK BIT(2) #define PFERR_RSVD_MASK BIT(3) #define PFERR_FETCH_MASK BIT(4) #define PFERR_PK_MASK BIT(5) #define PFERR_SGX_MASK BIT(15) #define PFERR_GUEST_RMP_MASK BIT_ULL(31) #define PFERR_GUEST_FINAL_MASK BIT_ULL(32) #define PFERR_GUEST_PAGE_MASK BIT_ULL(33) #define PFERR_GUEST_ENC_MASK BIT_ULL(34) #define PFERR_GUEST_SIZEM_MASK BIT_ULL(35) #define PFERR_GUEST_VMPL_MASK BIT_ULL(36) /* * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks * when emulating instructions that triggers implicit access. */ #define PFERR_IMPLICIT_ACCESS BIT_ULL(48) /* * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred * when the guest was accessing private memory. */ #define PFERR_PRIVATE_ACCESS BIT_ULL(49) #define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ PFERR_WRITE_MASK | \ PFERR_PRESENT_MASK) /* apic attention bits */ #define KVM_APIC_CHECK_VAPIC 0 /* * The following bit is set with PV-EOI, unset on EOI. * We detect PV-EOI changes by guest by comparing * this bit with PV-EOI in guest memory. * See the implementation in apic_update_pv_eoi. */ #define KVM_APIC_PV_EOI_PENDING 1 struct kvm_kernel_irq_routing_entry; /* * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page * also includes TDP pages) to determine whether or not a page can be used in * the given MMU context. This is a subset of the overall kvm_cpu_role to * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows * allocating 2 bytes per gfn instead of 4 bytes per gfn. * * Upper-level shadow pages having gptes are tracked for write-protection via * gfn_write_track. As above, gfn_write_track is a 16 bit counter, so KVM must * not create more than 2^16-1 upper-level shadow pages at a single gfn, * otherwise gfn_write_track will overflow and explosions will ensue. * * A unique shadow page (SP) for a gfn is created if and only if an existing SP * cannot be reused. The ability to reuse a SP is tracked by its role, which * incorporates various mode bits and properties of the SP. Roughly speaking, * the number of unique SPs that can theoretically be created is 2^n, where n * is the number of bits that are used to compute the role. * * But, even though there are 19 bits in the mask below, not all combinations * of modes and flags are possible: * * - invalid shadow pages are not accounted, so the bits are effectively 18 * * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); * execonly and ad_disabled are only used for nested EPT which has * has_4_byte_gpte=0. Therefore, 2 bits are always unused. * * - the 4 bits of level are effectively limited to the values 2/3/4/5, * as 4k SPs are not tracked (allowed to go unsync). In addition non-PAE * paging has exactly one upper level, making level completely redundant * when has_4_byte_gpte=1. * * - on top of this, smep_andnot_wp and smap_andnot_wp are only set if * cr0_wp=0, therefore these three bits only give rise to 5 possibilities. * * Therefore, the maximum number of possible upper-level shadow pages for a * single gfn is a bit less than 2^13. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; unsigned has_4_byte_gpte:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; unsigned invalid:1; unsigned efer_nx:1; unsigned cr0_wp:1; unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; unsigned ad_disabled:1; unsigned guest_mode:1; unsigned passthrough:1; unsigned :5; /* * This is left at the top of the word so that * kvm_memslots_for_spte_role can extract it with a * simple shift. While there is room, give it a whole * byte so it is also faster to load it from memory. */ unsigned smm:8; }; }; /* * kvm_mmu_extended_role complements kvm_mmu_page_role, tracking properties * relevant to the current MMU configuration. When loading CR0, CR4, or EFER, * including on nested transitions, if nothing in the full role changes then * MMU re-configuration can be skipped. @valid bit is set on first usage so we * don't treat all-zero structure as valid data. * * The properties that are tracked in the extended role but not the page role * are for things that either (a) do not affect the validity of the shadow page * or (b) are indirectly reflected in the shadow page's role. For example, * CR4.PKE only affects permission checks for software walks of the guest page * tables (because KVM doesn't support Protection Keys with shadow paging), and * CR0.PG, CR4.PAE, and CR4.PSE are indirectly reflected in role.level. * * Note, SMEP and SMAP are not redundant with sm*p_andnot_wp in the page role. * If CR0.WP=1, KVM can reuse shadow pages for the guest regardless of SMEP and * SMAP, but the MMU's permission checks for software walks need to be SMEP and * SMAP aware regardless of CR0.WP. */ union kvm_mmu_extended_role { u32 word; struct { unsigned int valid:1; unsigned int execonly:1; unsigned int cr4_pse:1; unsigned int cr4_pke:1; unsigned int cr4_smap:1; unsigned int cr4_smep:1; unsigned int cr4_la57:1; unsigned int efer_lma:1; }; }; union kvm_cpu_role { u64 as_u64; struct { union kvm_mmu_page_role base; union kvm_mmu_extended_role ext; }; }; struct kvm_rmap_head { unsigned long val; }; struct kvm_pio_request { unsigned long linear_rip; unsigned long count; int in; int port; int size; }; #define PT64_ROOT_MAX_LEVEL 5 struct rsvd_bits_validate { u64 rsvd_bits_mask[2][PT64_ROOT_MAX_LEVEL]; u64 bad_mt_xwr; }; struct kvm_mmu_root_info { gpa_t pgd; hpa_t hpa; }; #define KVM_MMU_ROOT_INFO_INVALID \ ((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE }) #define KVM_MMU_NUM_PREV_ROOTS 3 #define KVM_MMU_ROOT_CURRENT BIT(0) #define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) #define KVM_MMU_ROOTS_ALL (BIT(1 + KVM_MMU_NUM_PREV_ROOTS) - 1) #define KVM_HAVE_MMU_RWLOCK struct kvm_mmu_page; struct kvm_page_fault; /* * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit, * and 2-level 32-bit). The kvm_mmu structure abstracts the details of the * current mmu mode. */ struct kvm_mmu { unsigned long (*get_guest_pgd)(struct kvm_vcpu *vcpu); u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); int (*page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void (*inject_page_fault)(struct kvm_vcpu *vcpu, struct x86_exception *fault); gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gpa_t gva_or_gpa, u64 access, struct x86_exception *exception); int (*sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i); struct kvm_mmu_root_info root; union kvm_cpu_role cpu_role; union kvm_mmu_page_role root_role; /* * The pkru_mask indicates if protection key checks are needed. It * consists of 16 domains indexed by page fault error code bits [4:1], * with PFEC.RSVD replaced by ACC_USER_MASK from the page tables. * Each domain has 2 bits which are ANDed with AD and WD from PKRU. */ u32 pkru_mask; struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS]; /* * Bitmap; bit set = permission fault * Byte index: page fault error code [4:1] * Bit index: pte permissions in ACC_* format */ u8 permissions[16]; u64 *pae_root; u64 *pml4_root; u64 *pml5_root; /* * check zero bits on shadow page table entries, these * bits include not only hardware reserved bits but also * the bits spte never used. */ struct rsvd_bits_validate shadow_zero_check; struct rsvd_bits_validate guest_rsvd_check; u64 pdptrs[4]; /* pae */ }; enum pmc_type { KVM_PMC_GP = 0, KVM_PMC_FIXED, }; struct kvm_pmc { enum pmc_type type; u8 idx; bool is_paused; bool intr; /* * Base value of the PMC counter, relative to the *consumed* count in * the associated perf_event. This value includes counter updates from * the perf_event and emulated_count since the last time the counter * was reprogrammed, but it is *not* the current value as seen by the * guest or userspace. * * The count is relative to the associated perf_event so that KVM * doesn't need to reprogram the perf_event every time the guest writes * to the counter. */ u64 counter; /* * PMC events triggered by KVM emulation that haven't been fully * processed, i.e. haven't undergone overflow detection. */ u64 emulated_counter; u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; /* * only for creating or reusing perf_event, * eventsel value for general purpose counters, * ctrl value for fixed counters. */ u64 current_config; }; /* More counters may conflict with other existing Architectural MSRs */ #define KVM_INTEL_PMC_MAX_GENERIC 8 #define MSR_ARCH_PERFMON_PERFCTR_MAX (MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define MSR_ARCH_PERFMON_EVENTSEL_MAX (MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define KVM_PMC_MAX_FIXED 3 #define MSR_ARCH_PERFMON_FIXED_CTR_MAX (MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1) #define KVM_AMD_PMC_MAX_GENERIC 6 struct kvm_pmu { u8 version; unsigned nr_arch_gp_counters; unsigned nr_arch_fixed_counters; unsigned available_event_types; u64 fixed_ctr_ctrl; u64 fixed_ctr_ctrl_mask; u64 global_ctrl; u64 global_status; u64 counter_bitmask[2]; u64 global_ctrl_mask; u64 global_status_mask; u64 reserved_bits; u64 raw_event_mask; struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; /* * Overlay the bitmap with a 64-bit atomic so that all bits can be * set in a single access, e.g. to reprogram all counters when the PMU * filter changes. */ union { DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); atomic64_t __reprogram_pmi; }; DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX); DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX); u64 ds_area; u64 pebs_enable; u64 pebs_enable_mask; u64 pebs_data_cfg; u64 pebs_data_cfg_mask; /* * If a guest counter is cross-mapped to host counter with different * index, its PEBS capability will be temporarily disabled. * * The user should make sure that this mask is updated * after disabling interrupts and before perf_guest_get_msrs(); */ u64 host_cross_mapped_mask; /* * The gate to release perf_events not marked in * pmc_in_use only once in a vcpu time slice. */ bool need_cleanup; /* * The total number of programmed perf_events and it helps to avoid * redundant check before cleanup if guest don't use vPMU at all. */ u8 event_count; }; struct kvm_pmu_ops; enum { KVM_DEBUGREG_BP_ENABLED = 1, KVM_DEBUGREG_WONT_EXIT = 2, }; struct kvm_mtrr_range { u64 base; u64 mask; struct list_head node; }; struct kvm_mtrr { struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR]; mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; u64 deftype; struct list_head head; }; /* Hyper-V SynIC timer */ struct kvm_vcpu_hv_stimer { struct hrtimer timer; int index; union hv_stimer_config config; u64 count; u64 exp_time; struct hv_message msg; bool msg_pending; }; /* Hyper-V synthetic interrupt controller (SynIC)*/ struct kvm_vcpu_hv_synic { u64 version; u64 control; u64 msg_page; u64 evt_page; atomic64_t sint[HV_SYNIC_SINT_COUNT]; atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT]; DECLARE_BITMAP(auto_eoi_bitmap, 256); DECLARE_BITMAP(vec_bitmap, 256); bool active; bool dont_zero_synic_pages; }; /* The maximum number of entries on the TLB flush fifo. */ #define KVM_HV_TLB_FLUSH_FIFO_SIZE (16) /* * Note: the following 'magic' entry is made up by KVM to avoid putting * anything besides GVA on the TLB flush fifo. It is theoretically possible * to observe a request to flush 4095 PFNs starting from 0xfffffffffffff000 * which will look identical. KVM's action to 'flush everything' instead of * flushing these particular addresses is, however, fully legitimate as * flushing more than requested is always OK. */ #define KVM_HV_TLB_FLUSHALL_ENTRY ((u64)-1) enum hv_tlb_flush_fifos { HV_L1_TLB_FLUSH_FIFO, HV_L2_TLB_FLUSH_FIFO, HV_NR_TLB_FLUSH_FIFOS, }; struct kvm_vcpu_hv_tlb_flush_fifo { spinlock_t write_lock; DECLARE_KFIFO(entries, u64, KVM_HV_TLB_FLUSH_FIFO_SIZE); }; /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { struct kvm_vcpu *vcpu; u32 vp_index; u64 hv_vapic; s64 runtime_offset; struct kvm_vcpu_hv_synic synic; struct kvm_hyperv_exit exit; struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); bool enforce_cpuid; struct { u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */ u32 features_ebx; /* HYPERV_CPUID_FEATURES.EBX */ u32 features_edx; /* HYPERV_CPUID_FEATURES.EDX */ u32 enlightenments_eax; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ u32 enlightenments_ebx; /* HYPERV_CPUID_ENLIGHTMENT_INFO.EBX */ u32 syndbg_cap_eax; /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */ u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */ } cpuid_cache; struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS]; /* Preallocated buffer for handling hypercalls passing sparse vCPU set */ u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS]; struct hv_vp_assist_page vp_assist_page; struct { u64 pa_page_gpa; u64 vm_id; u32 vp_id; } nested; }; struct kvm_hypervisor_cpuid { u32 base; u32 limit; }; #ifdef CONFIG_KVM_XEN /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; u32 current_runstate; u8 upcall_vector; struct gfn_to_pfn_cache vcpu_info_cache; struct gfn_to_pfn_cache vcpu_time_info_cache; struct gfn_to_pfn_cache runstate_cache; struct gfn_to_pfn_cache runstate2_cache; u64 last_steal; u64 runstate_entry_time; u64 runstate_times[4]; unsigned long evtchn_pending_sel; u32 vcpu_id; /* The Xen / ACPI vCPU ID */ u32 timer_virq; u64 timer_expires; /* In guest epoch */ atomic_t timer_pending; struct hrtimer timer; int poll_evtchn; struct timer_list poll_timer; struct kvm_hypervisor_cpuid cpuid; }; #endif struct kvm_queued_exception { bool pending; bool injected; bool has_error_code; u8 vector; u32 error_code; unsigned long payload; bool has_payload; }; struct kvm_vcpu_arch { /* * rip and regs accesses must go through * kvm_{register,rip}_{read,write} functions. */ unsigned long regs[NR_VCPU_REGS]; u32 regs_avail; u32 regs_dirty; unsigned long cr0; unsigned long cr0_guest_owned_bits; unsigned long cr2; unsigned long cr3; unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr4_guest_rsvd_bits; unsigned long cr8; u32 host_pkru; u32 pkru; u32 hflags; u64 efer; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ bool load_eoi_exitmap_pending; DECLARE_BITMAP(ioapic_handled_vectors, 256); unsigned long apic_attention; int32_t apic_arb_prio; int mp_state; u64 ia32_misc_enable_msr; u64 smbase; u64 smi_count; bool at_instruction_boundary; bool tpr_access_reporting; bool xfd_no_write_intercept; u64 ia32_xss; u64 microcode_version; u64 arch_capabilities; u64 perf_capabilities; /* * Paging state of the vcpu * * If the vcpu runs in guest mode with two level paging this still saves * the paging mode of the l1 guest. This context is always used to * handle faults. */ struct kvm_mmu *mmu; /* Non-nested MMU for L1 */ struct kvm_mmu root_mmu; /* L1 MMU when running nested */ struct kvm_mmu guest_mmu; /* * Paging state of an L2 guest (used for nested npt) * * This context will save all necessary information to walk page tables * of an L2 guest. This context is only initialized for page table * walking and not for faulting since we never handle l2 page faults on * the host. */ struct kvm_mmu nested_mmu; /* * Pointer to the mmu context currently used for * gva_to_gpa translations. */ struct kvm_mmu *walk_mmu; struct kvm_mmu_memory_cache mmu_pte_list_desc_cache; struct kvm_mmu_memory_cache mmu_shadow_page_cache; struct kvm_mmu_memory_cache mmu_shadowed_info_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; /* * QEMU userspace and the guest each have their own FPU state. * In vcpu_run, we switch between the user and guest FPU contexts. * While running a VCPU, the VCPU thread will have the guest FPU * context. * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The * "guest_fpstate" state here contains the guest FPU context, with the * host PRKU bits. */ struct fpu_guest guest_fpu; u64 xcr0; u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; void *sev_pio_data; unsigned sev_pio_count; u8 event_exit_inst_len; bool exception_from_userspace; /* Exceptions to be injected to the guest. */ struct kvm_queued_exception exception; /* Exception VM-Exits to be synthesized to L1. */ struct kvm_queued_exception exception_vmexit; struct kvm_queued_interrupt { bool injected; bool soft; u8 nr; } interrupt; int halt_request; /* real mode on Intel only */ int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; struct kvm_hypervisor_cpuid kvm_cpuid; bool is_amd_compatible; /* * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly * when "struct kvm_vcpu_arch" is no longer defined in an * arch/x86/include/asm header. The max is mostly arbitrary, i.e. * can be increased as necessary. */ #define KVM_MAX_NR_GOVERNED_FEATURES BITS_PER_LONG /* * Track whether or not the guest is allowed to use features that are * governed by KVM, where "governed" means KVM needs to manage state * and/or explicitly enable the feature in hardware. Typically, but * not always, governed features can be used by the guest if and only * if both KVM and userspace want to expose the feature to the guest. */ struct { DECLARE_BITMAP(enabled, KVM_MAX_NR_GOVERNED_FEATURES); } governed_features; u64 reserved_gpa_bits; int maxphyaddr; /* emulate context */ struct x86_emulate_ctxt *emulate_ctxt; bool emulate_regs_need_sync_to_vcpu; bool emulate_regs_need_sync_from_vcpu; int (*complete_userspace_io)(struct kvm_vcpu *vcpu); gpa_t time; struct pvclock_vcpu_time_info hv_clock; unsigned int hw_tsc_khz; struct gfn_to_pfn_cache pv_time; /* set guest stopped flag in pvclock flags field */ bool pvclock_set_guest_stopped_request; struct { u8 preempted; u64 msr_val; u64 last_steal; struct gfn_to_hva_cache cache; } st; u64 l1_tsc_offset; u64 tsc_offset; /* current tsc offset */ u64 last_guest_tsc; u64 last_host_tsc; u64 tsc_offset_adjustment; u64 this_tsc_nsec; u64 this_tsc_write; u64 this_tsc_generation; bool tsc_catchup; bool tsc_always_catchup; s8 virtual_tsc_shift; u32 virtual_tsc_mult; u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; u64 msr_ia32_power_ctl; u64 l1_tsc_scaling_ratio; u64 tsc_scaling_ratio; /* current scaling ratio */ atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ /* Number of NMIs pending injection, not including hardware vNMIs. */ unsigned int nmi_pending; bool nmi_injected; /* Trying to inject an NMI this entry */ bool smi_pending; /* SMI queued after currently running handler */ u8 handling_intr_from_guest; struct kvm_mtrr mtrr_state; u64 pat; unsigned switch_db_regs; unsigned long db[KVM_NR_DB_REGS]; unsigned long dr6; unsigned long dr7; unsigned long eff_db[KVM_NR_DB_REGS]; unsigned long guest_debug_dr7; u64 msr_platform_info; u64 msr_misc_features_enables; u64 mcg_cap; u64 mcg_status; u64 mcg_ctl; u64 mcg_ext_ctl; u64 *mce_banks; u64 *mci_ctl2_banks; /* Cache MMIO info */ u64 mmio_gva; unsigned mmio_access; gfn_t mmio_gfn; u64 mmio_gen; struct kvm_pmu pmu; /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; #ifdef CONFIG_KVM_HYPERV bool hyperv_enabled; struct kvm_vcpu_hv *hyperv; #endif #ifdef CONFIG_KVM_XEN struct kvm_vcpu_xen xen; #endif cpumask_var_t wbinvd_dirty_mask; unsigned long last_retry_eip; unsigned long last_retry_addr; struct { bool halted; gfn_t gfns[ASYNC_PF_PER_VCPU]; struct gfn_to_hva_cache data; u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */ u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */ u16 vec; u32 id; bool send_user_only; u32 host_apf_flags; bool delivery_as_pf_vmexit; bool pageready_pending; } apf; /* OSVW MSRs (AMD only) */ struct { u64 length; u64 status; } osvw; struct { u64 msr_val; struct gfn_to_hva_cache data; } pv_eoi; u64 msr_kvm_poll_control; /* pv related host specific info */ struct { bool pv_unhalted; } pv; int pending_ioapic_eoi; int pending_external_vector; /* be preempted when it's in kernel-mode(cpl=0) */ bool preempted_in_kernel; /* Flush the L1 Data cache for L1TF mitigation on VMENTER */ bool l1tf_flush_l1d; /* Host CPU on which VM-entry was most recently attempted */ int last_vmentry_cpu; /* AMD MSRC001_0015 Hardware Configuration */ u64 msr_hwcr; /* pv related cpuid info */ struct { /* * value of the eax register in the KVM_CPUID_FEATURES CPUID * leaf. */ u32 features; /* * indicates whether pv emulation should be disabled if features * are not present in the guest's cpuid */ bool enforce; } pv_cpuid; /* Protected Guests */ bool guest_state_protected; /* * Set when PDPTS were loaded directly by the userspace without * reading the guest memory */ bool pdptrs_from_userspace; #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; #endif }; struct kvm_lpage_info { int disallow_lpage; }; struct kvm_arch_memory_slot { struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; unsigned short *gfn_write_track; }; /* * Track the mode of the optimized logical map, as the rules for decoding the * destination vary per mode. Enabling the optimized logical map requires all * software-enabled local APIs to be in the same mode, each addressable APIC to * be mapped to only one MDA, and each MDA to map to at most one APIC. */ enum kvm_apic_logical_mode { /* All local APICs are software disabled. */ KVM_APIC_MODE_SW_DISABLED, /* All software enabled local APICs in xAPIC cluster addressing mode. */ KVM_APIC_MODE_XAPIC_CLUSTER, /* All software enabled local APICs in xAPIC flat addressing mode. */ KVM_APIC_MODE_XAPIC_FLAT, /* All software enabled local APICs in x2APIC mode. */ KVM_APIC_MODE_X2APIC, /* * Optimized map disabled, e.g. not all local APICs in the same logical * mode, same logical ID assigned to multiple APICs, etc. */ KVM_APIC_MODE_MAP_DISABLED, }; struct kvm_apic_map { struct rcu_head rcu; enum kvm_apic_logical_mode logical_mode; u32 max_apic_id; union { struct kvm_lapic *xapic_flat_map[8]; struct kvm_lapic *xapic_cluster_map[16][4]; }; struct kvm_lapic *phys_map[]; }; /* Hyper-V synthetic debugger (SynDbg)*/ struct kvm_hv_syndbg { struct { u64 control; u64 status; u64 send_page; u64 recv_page; u64 pending_page; } control; u64 options; }; /* Current state of Hyper-V TSC page clocksource */ enum hv_tsc_page_status { /* TSC page was not set up or disabled */ HV_TSC_PAGE_UNSET = 0, /* TSC page MSR was written by the guest, update pending */ HV_TSC_PAGE_GUEST_CHANGED, /* TSC page update was triggered from the host side */ HV_TSC_PAGE_HOST_CHANGED, /* TSC page was properly set up and is currently active */ HV_TSC_PAGE_SET, /* TSC page was set up with an inaccessible GPA */ HV_TSC_PAGE_BROKEN, }; #ifdef CONFIG_KVM_HYPERV /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; u64 hv_guest_os_id; u64 hv_hypercall; u64 hv_tsc_page; enum hv_tsc_page_status hv_tsc_page_status; /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; u64 hv_crash_ctl; struct ms_hyperv_tsc_page tsc_ref; struct idr conn_to_evt; u64 hv_reenlightenment_control; u64 hv_tsc_emulation_control; u64 hv_tsc_emulation_status; u64 hv_invtsc_control; /* How many vCPUs have VP index != vCPU index */ atomic_t num_mismatched_vp_indexes; /* * How many SynICs use 'AutoEOI' feature * (protected by arch.apicv_update_lock) */ unsigned int synic_auto_eoi_used; struct kvm_hv_syndbg hv_syndbg; bool xsaves_xsavec_checked; }; #endif struct msr_bitmap_range { u32 flags; u32 nmsrs; u32 base; unsigned long *bitmap; }; #ifdef CONFIG_KVM_XEN /* Xen emulation context */ struct kvm_xen { struct mutex xen_lock; u32 xen_version; bool long_mode; bool runstate_update_flag; u8 upcall_vector; struct gfn_to_pfn_cache shinfo_cache; struct idr evtchn_ports; unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; }; #endif enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ }; struct kvm_x86_msr_filter { u8 count; bool default_allow:1; struct msr_bitmap_range ranges[16]; }; struct kvm_x86_pmu_event_filter { __u32 action; __u32 nevents; __u32 fixed_counter_bitmap; __u32 flags; __u32 nr_includes; __u32 nr_excludes; __u64 *includes; __u64 *excludes; __u64 events[]; }; enum kvm_apicv_inhibit { /********************************************************************/ /* INHIBITs that are relevant to both Intel's APICv and AMD's AVIC. */ /********************************************************************/ /* * APIC acceleration is disabled by a module parameter * and/or not supported in hardware. */ APICV_INHIBIT_REASON_DISABLE, /* * APIC acceleration is inhibited because AutoEOI feature is * being used by a HyperV guest. */ APICV_INHIBIT_REASON_HYPERV, /* * APIC acceleration is inhibited because the userspace didn't yet * enable the kernel/split irqchip. */ APICV_INHIBIT_REASON_ABSENT, /* APIC acceleration is inhibited because KVM_GUESTDBG_BLOCKIRQ * (out of band, debug measure of blocking all interrupts on this vCPU) * was enabled, to avoid AVIC/APICv bypassing it. */ APICV_INHIBIT_REASON_BLOCKIRQ, /* * APICv is disabled because not all vCPUs have a 1:1 mapping between * APIC ID and vCPU, _and_ KVM is not applying its x2APIC hotplug hack. */ APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED, /* * For simplicity, the APIC acceleration is inhibited * first time either APIC ID or APIC base are changed by the guest * from their reset values. */ APICV_INHIBIT_REASON_APIC_ID_MODIFIED, APICV_INHIBIT_REASON_APIC_BASE_MODIFIED, /******************************************************/ /* INHIBITs that are relevant only to the AMD's AVIC. */ /******************************************************/ /* * AVIC is inhibited on a vCPU because it runs a nested guest. * * This is needed because unlike APICv, the peers of this vCPU * cannot use the doorbell mechanism to signal interrupts via AVIC when * a vCPU runs nested. */ APICV_INHIBIT_REASON_NESTED, /* * On SVM, the wait for the IRQ window is implemented with pending vIRQ, * which cannot be injected when the AVIC is enabled, thus AVIC * is inhibited while KVM waits for IRQ window. */ APICV_INHIBIT_REASON_IRQWIN, /* * PIT (i8254) 're-inject' mode, relies on EOI intercept, * which AVIC doesn't support for edge triggered interrupts. */ APICV_INHIBIT_REASON_PIT_REINJ, /* * AVIC is disabled because SEV doesn't support it. */ APICV_INHIBIT_REASON_SEV, /* * AVIC is disabled because not all vCPUs with a valid LDR have a 1:1 * mapping between logical ID and vCPU. */ APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED, }; struct kvm_arch { unsigned long n_used_mmu_pages; unsigned long n_requested_mmu_pages; unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; u8 mmu_valid_gen; u8 vm_type; bool has_private_mem; bool has_protected_state; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; /* * A list of kvm_mmu_page structs that, if zapped, could possibly be * replaced by an NX huge page. A shadow page is on this list if its * existence disallows an NX huge page (nx_huge_page_disallowed is set) * and there are no other conditions that prevent a huge page, e.g. * the backing host page is huge, dirtly logging is not enabled for its * memslot, etc... Note, zapping shadow pages on this list doesn't * guarantee an NX huge page will be created in its stead, e.g. if the * guest attempts to execute from the region then KVM obviously can't * create an NX huge page (without hanging the guest). */ struct list_head possible_nx_huge_pages; #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING struct kvm_page_track_notifier_head track_notifier_head; #endif /* * Protects marking pages unsync during page faults, as TDP MMU page * faults only take mmu_lock for read. For simplicity, the unsync * pages lock is always taken when marking pages unsync regardless of * whether mmu_lock is held for read or write. */ spinlock_t mmu_unsync_pages_lock; u64 shadow_mmio_value; struct iommu_domain *iommu_domain; bool iommu_noncoherent; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA atomic_t noncoherent_dma_count; #define __KVM_HAVE_ARCH_ASSIGNED_DEVICE atomic_t assigned_device_count; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; bool apic_access_memslot_enabled; bool apic_access_memslot_inhibited; /* Protects apicv_inhibit_reasons */ struct rw_semaphore apicv_update_lock; unsigned long apicv_inhibit_reasons; gpa_t wall_clock; bool mwait_in_guest; bool hlt_in_guest; bool pause_in_guest; bool cstate_in_guest; unsigned long irq_sources_bitmap; s64 kvmclock_offset; /* * This also protects nr_vcpus_matched_tsc which is read from a * preemption-disabled region, so it must be a raw spinlock. */ raw_spinlock_t tsc_write_lock; u64 last_tsc_nsec; u64 last_tsc_write; u32 last_tsc_khz; u64 last_tsc_offset; u64 cur_tsc_nsec; u64 cur_tsc_write; u64 cur_tsc_offset; u64 cur_tsc_generation; int nr_vcpus_matched_tsc; u32 default_tsc_khz; bool user_set_tsc; seqcount_raw_spinlock_t pvclock_sc; bool use_master_clock; u64 master_kernel_ns; u64 master_cycle_now; struct delayed_work kvmclock_update_work; struct delayed_work kvmclock_sync_work; struct kvm_xen_hvm_config xen_hvm_config; /* reads protected by irq_srcu, writes by irq_lock */ struct hlist_head mask_notifier_list; #ifdef CONFIG_KVM_HYPERV struct kvm_hv hyperv; #endif #ifdef CONFIG_KVM_XEN struct kvm_xen xen; #endif bool backwards_tsc_observed; bool boot_vcpu_runs_old_kvmclock; u32 bsp_vcpu_id; u64 disabled_quirks; enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; bool disabled_lapic_found; bool x2apic_format; bool x2apic_broadcast_quirk_disabled; bool guest_can_read_msr_platform_info; bool exception_payload_enabled; bool triple_fault_event; bool bus_lock_detection_enabled; bool enable_pmu; u32 notify_window; u32 notify_vmexit_flags; /* * If exit_on_emulation_error is set, and the in-kernel instruction * emulator fails to emulate an instruction, allow userspace * the opportunity to look at it. */ bool exit_on_emulation_error; /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ u32 user_space_msr_mask; struct kvm_x86_msr_filter __rcu *msr_filter; u32 hypercall_exit_enabled; /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_huge_page_recovery_thread; #ifdef CONFIG_X86_64 /* The number of TDP MMU pages across all roots. */ atomic64_t tdp_mmu_pages; /* * List of struct kvm_mmu_pages being used as roots. * All struct kvm_mmu_pages in the list should have * tdp_mmu_page set. * * For reads, this list is protected by: * the MMU lock in read mode + RCU or * the MMU lock in write mode * * For writes, this list is protected by tdp_mmu_pages_lock; see * below for the details. * * Roots will remain in the list until their tdp_mmu_root_count * drops to zero, at which point the thread that decremented the * count to zero should removed the root from the list and clean * it up, freeing the root after an RCU grace period. */ struct list_head tdp_mmu_roots; /* * Protects accesses to the following fields when the MMU lock * is held in read mode: * - tdp_mmu_roots (above) * - the link field of kvm_mmu_page structs used by the TDP MMU * - possible_nx_huge_pages; * - the possible_nx_huge_page_link field of kvm_mmu_page structs used * by the TDP MMU * Because the lock is only taken within the MMU lock, strictly * speaking it is redundant to acquire this lock when the thread * holds the MMU lock in write mode. However it often simplifies * the code to do so. */ spinlock_t tdp_mmu_pages_lock; #endif /* CONFIG_X86_64 */ /* * If set, at least one shadow root has been allocated. This flag * is used as one input when determining whether certain memslot * related allocations are necessary. */ bool shadow_root_allocated; #ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING /* * If set, the VM has (or had) an external write tracking user, and * thus all write tracking metadata has been allocated, even if KVM * itself isn't using write tracking. */ bool external_write_tracking_enabled; #endif #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; spinlock_t hv_root_tdp_lock; struct hv_partition_assist_pg *hv_pa_pg; #endif /* * VM-scope maximum vCPU ID. Used to determine the size of structures * that increase along with the maximum vCPU ID, in which case, using * the global KVM_MAX_VCPU_IDS may lead to significant memory waste. */ u32 max_vcpu_ids; bool disable_nx_huge_pages; /* * Memory caches used to allocate shadow pages when performing eager * page splitting. No need for a shadowed_info_cache since eager page * splitting only allocates direct shadow pages. * * Protected by kvm->slots_lock. */ struct kvm_mmu_memory_cache split_shadow_page_cache; struct kvm_mmu_memory_cache split_page_header_cache; /* * Memory cache used to allocate pte_list_desc structs while splitting * huge pages. In the worst case, to split one huge page, 512 * pte_list_desc structs are needed to add each lower level leaf sptep * to the rmap plus 1 to extend the parent_ptes rmap of the lower level * page table. * * Protected by kvm->slots_lock. */ #define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1) struct kvm_mmu_memory_cache split_desc_cache; }; struct kvm_vm_stat { struct kvm_vm_stat_generic generic; u64 mmu_shadow_zapped; u64 mmu_pte_write; u64 mmu_pde_zapped; u64 mmu_flooded; u64 mmu_recycled; u64 mmu_cache_miss; u64 mmu_unsync; union { struct { atomic64_t pages_4k; atomic64_t pages_2m; atomic64_t pages_1g; }; atomic64_t pages[KVM_NR_PAGE_SIZES]; }; u64 nx_lpage_splits; u64 max_mmu_page_hash_collisions; u64 max_mmu_rmap_size; }; struct kvm_vcpu_stat { struct kvm_vcpu_stat_generic generic; u64 pf_taken; u64 pf_fixed; u64 pf_emulate; u64 pf_spurious; u64 pf_fast; u64 pf_mmio_spte_created; u64 pf_guest; u64 tlb_flush; u64 invlpg; u64 exits; u64 io_exits; u64 mmio_exits; u64 signal_exits; u64 irq_window_exits; u64 nmi_window_exits; u64 l1d_flush; u64 halt_exits; u64 request_irq_exits; u64 irq_exits; u64 host_state_reload; u64 fpu_reload; u64 insn_emulation; u64 insn_emulation_fail; u64 hypercalls; u64 irq_injections; u64 nmi_injections; u64 req_event; u64 nested_run; u64 directed_yield_attempted; u64 directed_yield_successful; u64 preemption_reported; u64 preemption_other; u64 guest_mode; u64 notify_window_exits; }; struct x86_instruction_info; struct msr_data { bool host_initiated; u32 index; u64 data; }; struct kvm_lapic_irq { u32 vector; u16 delivery_mode; u16 dest_mode; bool level; u16 trig_mode; u32 shorthand; u32 dest_id; bool msi_redir_hint; }; static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) { return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; } struct kvm_x86_ops { const char *name; int (*check_processor_compatibility)(void); int (*hardware_enable)(void); void (*hardware_disable)(void); void (*hardware_unsetup)(void); bool (*has_emulated_msr)(struct kvm *kvm, u32 index); void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu); unsigned int vm_size; int (*vm_init)(struct kvm *kvm); void (*vm_destroy)(struct kvm *kvm); /* Create, but do not attach this VCPU */ int (*vcpu_precreate)(struct kvm *kvm); int (*vcpu_create)(struct kvm_vcpu *vcpu); void (*vcpu_free)(struct kvm_vcpu *vcpu); void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); void (*prepare_switch_to_guest)(struct kvm_vcpu *vcpu); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); void (*update_exception_bitmap)(struct kvm_vcpu *vcpu); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); void (*get_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int (*get_cpl)(struct kvm_vcpu *vcpu); void (*set_segment)(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); bool (*is_valid_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); void (*post_set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); bool (*is_valid_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); int (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); bool (*get_if_flag)(struct kvm_vcpu *vcpu); void (*flush_tlb_all)(struct kvm_vcpu *vcpu); void (*flush_tlb_current)(struct kvm_vcpu *vcpu); #if IS_ENABLED(CONFIG_HYPERV) int (*flush_remote_tlbs)(struct kvm *kvm); int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); #endif /* * Flush any TLB entries associated with the given GVA. * Does not need to flush GPA->HPA mappings. * Can potentially get non-canonical addresses through INVLPGs, which * the implementation may choose to ignore if appropriate. */ void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr); /* * Flush any TLB entries created by the guest. Like tlb_flush_gva(), * does not need to flush GPA->HPA mappings. */ void (*flush_tlb_guest)(struct kvm_vcpu *vcpu); int (*vcpu_pre_run)(struct kvm_vcpu *vcpu); enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu, bool force_immediate_exit); int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); void (*update_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, unsigned char *hypercall_addr); void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected); void (*inject_nmi)(struct kvm_vcpu *vcpu); void (*inject_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection); int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); /* Whether or not a virtual NMI is pending in hardware. */ bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu); /* * Attempt to pend a virtual NMI in hardware. Returns %true on success * to allow using static_call_ret0 as the fallback. */ bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu); void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason); const unsigned long required_apicv_inhibits; bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(int isr); bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); void (*deliver_interrupt)(struct kvm_lapic *apic, int delivery_mode, int trig_mode, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); u8 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); bool (*has_wbinvd_exit)(void); u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu); /* * Retrieve somewhat arbitrary exit information. Intended to * be used only from within tracepoints or error paths. */ void (*get_exit_info)(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, u32 *exit_int_info, u32 *exit_int_info_err_code); int (*check_intercept)(struct kvm_vcpu *vcpu, struct x86_instruction_info *info, enum x86_intercept_stage stage, struct x86_exception *exception); void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); void (*sched_in)(struct kvm_vcpu *vcpu, int cpu); /* * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A zero * value indicates CPU dirty logging is unsupported or disabled. */ int cpu_dirty_log_size; void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu); const struct kvm_x86_nested_ops *nested_ops; void (*vcpu_blocking)(struct kvm_vcpu *vcpu); void (*vcpu_unblocking)(struct kvm_vcpu *vcpu); int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void (*pi_start_assignment)(struct kvm *kvm); void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, bool *expired); void (*cancel_hv_timer)(struct kvm_vcpu *vcpu); void (*setup_mce)(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM_SMM int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram); int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram); void (*enable_smi_window)(struct kvm_vcpu *vcpu); #endif int (*dev_get_attr)(u32 group, u64 attr, u64 *val); int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp); int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); void (*guest_memory_reclaimed)(struct kvm *kvm); int (*get_msr_feature)(struct kvm_msr_entry *entry); int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); /* * Returns vCPU specific APICv inhibit reasons */ unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu); gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu); int (*gmem_prepare)(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order); void (*gmem_invalidate)(kvm_pfn_t start, kvm_pfn_t end); int (*private_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn); }; struct kvm_x86_nested_ops { void (*leave_nested)(struct kvm_vcpu *vcpu); bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, u32 error_code); int (*check_events)(struct kvm_vcpu *vcpu); bool (*has_events)(struct kvm_vcpu *vcpu); void (*triple_fault)(struct kvm_vcpu *vcpu); int (*get_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, unsigned user_data_size); int (*set_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, struct kvm_nested_state *kvm_state); bool (*get_nested_state_pages)(struct kvm_vcpu *vcpu); int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int (*enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu); void (*hv_inject_synthetic_vmexit_post_tlb_flush)(struct kvm_vcpu *vcpu); }; struct kvm_x86_init_ops { int (*hardware_setup)(void); unsigned int (*handle_intel_pt_intr)(void); struct kvm_x86_ops *runtime_ops; struct kvm_pmu_ops *pmu_ops; }; struct kvm_arch_async_pf { u32 token; gfn_t gfn; unsigned long cr3; bool direct_map; u64 error_code; }; extern u32 __read_mostly kvm_nr_uret_msrs; extern u64 __read_mostly host_efer; extern bool __read_mostly allow_smaller_maxphyaddr; extern bool __read_mostly enable_apicv; extern struct kvm_x86_ops kvm_x86_ops; #define KVM_X86_OP(func) \ DECLARE_STATIC_CALL(kvm_x86_##func, *(((struct kvm_x86_ops *)0)->func)); #define KVM_X86_OP_OPTIONAL KVM_X86_OP #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP #include <asm/kvm-x86-ops.h> int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops); void kvm_x86_vendor_exit(void); #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); } #define __KVM_HAVE_ARCH_VM_FREE void kvm_arch_free_vm(struct kvm *kvm); #if IS_ENABLED(CONFIG_HYPERV) #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { if (kvm_x86_ops.flush_remote_tlbs && !static_call(kvm_x86_flush_remote_tlbs)(kvm)) return 0; else return -ENOTSUPP; } #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { if (!kvm_x86_ops.flush_remote_tlbs_range) return -EOPNOTSUPP; return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages); } #endif /* CONFIG_HYPERV */ enum kvm_intr_type { /* Values are arbitrary, but must be non-zero. */ KVM_HANDLING_IRQ = 1, KVM_HANDLING_NMI, }; /* Enable perf NMI and timer modes to work, and minimise false positives. */ #define kvm_arch_pmi_in_guest(vcpu) \ ((vcpu) && (vcpu)->arch.handling_intr_from_guest && \ (!!in_nmi() == ((vcpu)->arch.handling_intr_from_guest == KVM_HANDLING_NMI))) void __init kvm_mmu_x86_module_init(void); int kvm_mmu_vendor_module_init(void); void kvm_mmu_vendor_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, const struct kvm_memory_slot *memslot, int start_level); void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *memslot, int target_level); void kvm_mmu_try_split_huge_pages(struct kvm *kvm, const struct kvm_memory_slot *memslot, u64 start, u64 end, int target_level); void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, const struct kvm_memory_slot *memslot); void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); struct kvm_irq_mask_notifier { void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked); int irq; struct hlist_node link; }; void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn); void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq, struct kvm_irq_mask_notifier *kimn); void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, bool mask); extern bool tdp_enabled; u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); /* * EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing * userspace I/O) to indicate that the emulation context * should be reused as is, i.e. skip initialization of * emulation context, instruction fetch and decode. * * EMULTYPE_TRAP_UD - Set when emulating an intercepted #UD from hardware. * Indicates that only select instructions (tagged with * EmulateOnUD) should be emulated (to minimize the emulator * attack surface). See also EMULTYPE_TRAP_UD_FORCED. * * EMULTYPE_SKIP - Set when emulating solely to skip an instruction, i.e. to * decode the instruction length. For use *only* by * kvm_x86_ops.skip_emulated_instruction() implementations if * EMULTYPE_COMPLETE_USER_EXIT is not set. * * EMULTYPE_ALLOW_RETRY_PF - Set when the emulator should resume the guest to * retry native execution under certain conditions, * Can only be set in conjunction with EMULTYPE_PF. * * EMULTYPE_TRAP_UD_FORCED - Set when emulating an intercepted #UD that was * triggered by KVM's magic "force emulation" prefix, * which is opt in via module param (off by default). * Bypasses EmulateOnUD restriction despite emulating * due to an intercepted #UD (see EMULTYPE_TRAP_UD). * Used to test the full emulator from userspace. * * EMULTYPE_VMWARE_GP - Set when emulating an intercepted #GP for VMware * backdoor emulation, which is opt in via module param. * VMware backdoor emulation handles select instructions * and reinjects the #GP for all other cases. * * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which * case the CR2/GPA value pass on the stack is valid. * * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility * state and inject single-step #DBs after skipping * an instruction (after completing userspace I/O). * * EMULTYPE_WRITE_PF_TO_SP - Set when emulating an intercepted page fault that * is attempting to write a gfn that contains one or * more of the PTEs used to translate the write itself, * and the owning page table is being shadowed by KVM. * If emulation of the faulting instruction fails and * this flag is set, KVM will exit to userspace instead * of retrying emulation as KVM cannot make forward * progress. * * If emulation fails for a write to guest page tables, * KVM unprotects (zaps) the shadow page for the target * gfn and resumes the guest to retry the non-emulatable * instruction (on hardware). Unprotecting the gfn * doesn't allow forward progress for a self-changing * access because doing so also zaps the translation for * the gfn, i.e. retrying the instruction will hit a * !PRESENT fault, which results in a new shadow page * and sends KVM back to square one. */ #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) #define EMULTYPE_ALLOW_RETRY_PF (1 << 3) #define EMULTYPE_TRAP_UD_FORCED (1 << 4) #define EMULTYPE_VMWARE_GP (1 << 5) #define EMULTYPE_PF (1 << 6) #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) #define EMULTYPE_WRITE_PF_TO_SP (1 << 8) int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, u8 ndata); void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, bool host_initiated); int kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data); int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data); int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu); int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu); int kvm_emulate_as_nop(struct kvm_vcpu *vcpu); int kvm_emulate_invd(struct kvm_vcpu *vcpu); int kvm_emulate_mwait(struct kvm_vcpu *vcpu); int kvm_handle_invalid_op(struct kvm_vcpu *vcpu); int kvm_emulate_monitor(struct kvm_vcpu *vcpu); int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int kvm_emulate_halt_noskip(struct kvm_vcpu *vcpu); int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code); void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0); void kvm_post_set_cr4(struct kvm_vcpu *vcpu, unsigned long old_cr4, unsigned long cr4); int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val); unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu); int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); int kvm_emulate_rdpmc(struct kvm_vcpu *vcpu); void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload); void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl); bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr); static inline int __kvm_irq_line_state(unsigned long *irq_state, int irq_source_id, int level) { /* Logical OR for level trig interrupt */ if (level) __set_bit(irq_source_id, irq_state); else __clear_bit(irq_source_id, irq_state); return !!(*irq_state); } int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level); void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu); void kvm_update_dr7(struct kvm_vcpu *vcpu); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); bool kvm_apicv_activated(struct kvm *kvm); bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu); void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set); void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set); static inline void kvm_set_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason) { kvm_set_or_clear_apicv_inhibit(kvm, reason, true); } static inline void kvm_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason) { kvm_set_or_clear_apicv_inhibit(kvm, reason, false); } unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3, int op_64_bit, int cpl); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva); void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, unsigned long roots); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid); void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); #ifdef CONFIG_KVM_PRIVATE_MEM #define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem) #else #define kvm_arch_has_private_mem(kvm) false #endif static inline u16 kvm_read_ldt(void) { u16 ldt; asm("sldt %0" : "=g"(ldt)); return ldt; } static inline void kvm_load_ldt(u16 sel) { asm("lldt %0" : : "rm"(sel)); } #ifdef CONFIG_X86_64 static inline unsigned long read_msr(unsigned long msr) { u64 value; rdmsrl(msr, value); return value; } #endif static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) { kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); } #define TSS_IOPB_BASE_OFFSET 0x66 #define TSS_BASE_SIZE 0x68 #define TSS_IOPB_SIZE (65536 / 8) #define TSS_REDIRECTION_SIZE (256 / 8) #define RMODE_TSS_SIZE \ (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1) enum { TASK_SWITCH_CALL = 0, TASK_SWITCH_IRET = 1, TASK_SWITCH_JMP = 2, TASK_SWITCH_GATE = 3, }; #define HF_GUEST_MASK (1 << 0) /* VCPU is in guest-mode */ #ifdef CONFIG_KVM_SMM #define HF_SMM_MASK (1 << 1) #define HF_SMM_INSIDE_NMI_MASK (1 << 2) # define KVM_MAX_NR_ADDRESS_SPACES 2 /* SMM is currently unsupported for guests with private memory. */ # define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2) # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) #else # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) #endif int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); int kvm_add_user_return_msr(u32 msr); int kvm_find_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); static inline bool kvm_is_supported_user_return_msr(u32 msr) { return kvm_find_user_return_msr(msr) >= 0; } u64 kvm_scale_tsc(u64 tsc, u64 ratio); u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier); u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier); unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); void kvm_make_scan_ioapic_request(struct kvm *kvm); void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap); bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu); bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu); extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, struct kvm_lapic_irq *irq); static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ return (irq->delivery_mode == APIC_DM_FIXED || irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) { static_call_cond(kvm_x86_vcpu_blocking)(vcpu); } static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) { static_call_cond(kvm_x86_vcpu_unblocking)(vcpu); } static inline int kvm_cpu_get_apicid(int mps_cpu) { #ifdef CONFIG_X86_LOCAL_APIC return default_cpu_present_to_apicid(mps_cpu); #else WARN_ON_ONCE(1); return BAD_APICID; #endif } int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); #define KVM_CLOCK_VALID_FLAGS \ (KVM_CLOCK_TSC_STABLE | KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC) #define KVM_X86_VALID_QUIRKS \ (KVM_X86_QUIRK_LINT0_REENABLED | \ KVM_X86_QUIRK_CD_NW_CLEARED | \ KVM_X86_QUIRK_LAPIC_MMIO_HOLE | \ KVM_X86_QUIRK_OUT_7E_INC_RIP | \ KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \ KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) /* * KVM previously used a u32 field in kvm_run to indicate the hypercall was * initiated from long mode. KVM now sets bit 0 to indicate long mode, but the * remaining 31 lower bits must be 0 to preserve ABI. */ #define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1) #endif /* _ASM_X86_KVM_HOST_H */ |
| 25 25 15 5 10 10 16 16 20 20 20 20 17 2 1 11 3 16 10 1 1 3 4 2 1 22 1 20 1 9 4 20 2 5 1 9 3 25 1 24 24 3 8 13 24 1 2 13 9 8 14 25 3 16 5 2 20 2 15 56 4 17 2 2 15 15 15 15 15 17 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 | // SPDX-License-Identifier: GPL-2.0+ /* * the_nilfs shared structure. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * * Written by Ryusuke Konishi. * */ #include <linux/buffer_head.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/random.h> #include <linux/log2.h> #include <linux/crc32.h> #include "nilfs.h" #include "segment.h" #include "alloc.h" #include "cpfile.h" #include "sufile.h" #include "dat.h" #include "segbuf.h" static int nilfs_valid_sb(struct nilfs_super_block *sbp); void nilfs_set_last_segment(struct the_nilfs *nilfs, sector_t start_blocknr, u64 seq, __u64 cno) { spin_lock(&nilfs->ns_last_segment_lock); nilfs->ns_last_pseg = start_blocknr; nilfs->ns_last_seq = seq; nilfs->ns_last_cno = cno; if (!nilfs_sb_dirty(nilfs)) { if (nilfs->ns_prev_seq == nilfs->ns_last_seq) goto stay_cursor; set_nilfs_sb_dirty(nilfs); } nilfs->ns_prev_seq = nilfs->ns_last_seq; stay_cursor: spin_unlock(&nilfs->ns_last_segment_lock); } /** * alloc_nilfs - allocate a nilfs object * @sb: super block instance * * Return Value: On success, pointer to the_nilfs is returned. * On error, NULL is returned. */ struct the_nilfs *alloc_nilfs(struct super_block *sb) { struct the_nilfs *nilfs; nilfs = kzalloc(sizeof(*nilfs), GFP_KERNEL); if (!nilfs) return NULL; nilfs->ns_sb = sb; nilfs->ns_bdev = sb->s_bdev; atomic_set(&nilfs->ns_ndirtyblks, 0); init_rwsem(&nilfs->ns_sem); mutex_init(&nilfs->ns_snapshot_mount_mutex); INIT_LIST_HEAD(&nilfs->ns_dirty_files); INIT_LIST_HEAD(&nilfs->ns_gc_inodes); spin_lock_init(&nilfs->ns_inode_lock); spin_lock_init(&nilfs->ns_next_gen_lock); spin_lock_init(&nilfs->ns_last_segment_lock); nilfs->ns_cptree = RB_ROOT; spin_lock_init(&nilfs->ns_cptree_lock); init_rwsem(&nilfs->ns_segctor_sem); nilfs->ns_sb_update_freq = NILFS_SB_FREQ; return nilfs; } /** * destroy_nilfs - destroy nilfs object * @nilfs: nilfs object to be released */ void destroy_nilfs(struct the_nilfs *nilfs) { might_sleep(); if (nilfs_init(nilfs)) { brelse(nilfs->ns_sbh[0]); brelse(nilfs->ns_sbh[1]); } kfree(nilfs); } static int nilfs_load_super_root(struct the_nilfs *nilfs, struct super_block *sb, sector_t sr_block) { struct buffer_head *bh_sr; struct nilfs_super_root *raw_sr; struct nilfs_super_block **sbp = nilfs->ns_sbp; struct nilfs_inode *rawi; unsigned int dat_entry_size, segment_usage_size, checkpoint_size; unsigned int inode_size; int err; err = nilfs_read_super_root_block(nilfs, sr_block, &bh_sr, 1); if (unlikely(err)) return err; down_read(&nilfs->ns_sem); dat_entry_size = le16_to_cpu(sbp[0]->s_dat_entry_size); checkpoint_size = le16_to_cpu(sbp[0]->s_checkpoint_size); segment_usage_size = le16_to_cpu(sbp[0]->s_segment_usage_size); up_read(&nilfs->ns_sem); inode_size = nilfs->ns_inode_size; rawi = (void *)bh_sr->b_data + NILFS_SR_DAT_OFFSET(inode_size); err = nilfs_dat_read(sb, dat_entry_size, rawi, &nilfs->ns_dat); if (err) goto failed; rawi = (void *)bh_sr->b_data + NILFS_SR_CPFILE_OFFSET(inode_size); err = nilfs_cpfile_read(sb, checkpoint_size, rawi, &nilfs->ns_cpfile); if (err) goto failed_dat; rawi = (void *)bh_sr->b_data + NILFS_SR_SUFILE_OFFSET(inode_size); err = nilfs_sufile_read(sb, segment_usage_size, rawi, &nilfs->ns_sufile); if (err) goto failed_cpfile; raw_sr = (struct nilfs_super_root *)bh_sr->b_data; nilfs->ns_nongc_ctime = le64_to_cpu(raw_sr->sr_nongc_ctime); failed: brelse(bh_sr); return err; failed_cpfile: iput(nilfs->ns_cpfile); failed_dat: iput(nilfs->ns_dat); goto failed; } static void nilfs_init_recovery_info(struct nilfs_recovery_info *ri) { memset(ri, 0, sizeof(*ri)); INIT_LIST_HEAD(&ri->ri_used_segments); } static void nilfs_clear_recovery_info(struct nilfs_recovery_info *ri) { nilfs_dispose_segment_list(&ri->ri_used_segments); } /** * nilfs_store_log_cursor - load log cursor from a super block * @nilfs: nilfs object * @sbp: buffer storing super block to be read * * nilfs_store_log_cursor() reads the last position of the log * containing a super root from a given super block, and initializes * relevant information on the nilfs object preparatory for log * scanning and recovery. */ static int nilfs_store_log_cursor(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) { int ret = 0; nilfs->ns_last_pseg = le64_to_cpu(sbp->s_last_pseg); nilfs->ns_last_cno = le64_to_cpu(sbp->s_last_cno); nilfs->ns_last_seq = le64_to_cpu(sbp->s_last_seq); nilfs->ns_prev_seq = nilfs->ns_last_seq; nilfs->ns_seg_seq = nilfs->ns_last_seq; nilfs->ns_segnum = nilfs_get_segnum_of_block(nilfs, nilfs->ns_last_pseg); nilfs->ns_cno = nilfs->ns_last_cno + 1; if (nilfs->ns_segnum >= nilfs->ns_nsegments) { nilfs_err(nilfs->ns_sb, "pointed segment number is out of range: segnum=%llu, nsegments=%lu", (unsigned long long)nilfs->ns_segnum, nilfs->ns_nsegments); ret = -EINVAL; } return ret; } /** * nilfs_get_blocksize - get block size from raw superblock data * @sb: super block instance * @sbp: superblock raw data buffer * @blocksize: place to store block size * * nilfs_get_blocksize() calculates the block size from the block size * exponent information written in @sbp and stores it in @blocksize, * or aborts with an error message if it's too large. * * Return Value: On success, 0 is returned. If the block size is too * large, -EINVAL is returned. */ static int nilfs_get_blocksize(struct super_block *sb, struct nilfs_super_block *sbp, int *blocksize) { unsigned int shift_bits = le32_to_cpu(sbp->s_log_block_size); if (unlikely(shift_bits > ilog2(NILFS_MAX_BLOCK_SIZE) - BLOCK_SIZE_BITS)) { nilfs_err(sb, "too large filesystem blocksize: 2 ^ %u KiB", shift_bits); return -EINVAL; } *blocksize = BLOCK_SIZE << shift_bits; return 0; } /** * load_nilfs - load and recover the nilfs * @nilfs: the_nilfs structure to be released * @sb: super block instance used to recover past segment * * load_nilfs() searches and load the latest super root, * attaches the last segment, and does recovery if needed. * The caller must call this exclusively for simultaneous mounts. */ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) { struct nilfs_recovery_info ri; unsigned int s_flags = sb->s_flags; int really_read_only = bdev_read_only(nilfs->ns_bdev); int valid_fs = nilfs_valid_fs(nilfs); int err; if (!valid_fs) { nilfs_warn(sb, "mounting unchecked fs"); if (s_flags & SB_RDONLY) { nilfs_info(sb, "recovery required for readonly filesystem"); nilfs_info(sb, "write access will be enabled during recovery"); } } nilfs_init_recovery_info(&ri); err = nilfs_search_super_root(nilfs, &ri); if (unlikely(err)) { struct nilfs_super_block **sbp = nilfs->ns_sbp; int blocksize; if (err != -EINVAL) goto scan_error; if (!nilfs_valid_sb(sbp[1])) { nilfs_warn(sb, "unable to fall back to spare super block"); goto scan_error; } nilfs_info(sb, "trying rollback from an earlier position"); /* * restore super block with its spare and reconfigure * relevant states of the nilfs object. */ memcpy(sbp[0], sbp[1], nilfs->ns_sbsize); nilfs->ns_crc_seed = le32_to_cpu(sbp[0]->s_crc_seed); nilfs->ns_sbwtime = le64_to_cpu(sbp[0]->s_wtime); /* verify consistency between two super blocks */ err = nilfs_get_blocksize(sb, sbp[0], &blocksize); if (err) goto scan_error; if (blocksize != nilfs->ns_blocksize) { nilfs_warn(sb, "blocksize differs between two super blocks (%d != %d)", blocksize, nilfs->ns_blocksize); err = -EINVAL; goto scan_error; } err = nilfs_store_log_cursor(nilfs, sbp[0]); if (err) goto scan_error; /* drop clean flag to allow roll-forward and recovery */ nilfs->ns_mount_state &= ~NILFS_VALID_FS; valid_fs = 0; err = nilfs_search_super_root(nilfs, &ri); if (err) goto scan_error; } err = nilfs_load_super_root(nilfs, sb, ri.ri_super_root); if (unlikely(err)) { nilfs_err(sb, "error %d while loading super root", err); goto failed; } err = nilfs_sysfs_create_device_group(sb); if (unlikely(err)) goto sysfs_error; if (valid_fs) goto skip_recovery; if (s_flags & SB_RDONLY) { __u64 features; if (nilfs_test_opt(nilfs, NORECOVERY)) { nilfs_info(sb, "norecovery option specified, skipping roll-forward recovery"); goto skip_recovery; } features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) & ~NILFS_FEATURE_COMPAT_RO_SUPP; if (features) { nilfs_err(sb, "couldn't proceed with recovery because of unsupported optional features (%llx)", (unsigned long long)features); err = -EROFS; goto failed_unload; } if (really_read_only) { nilfs_err(sb, "write access unavailable, cannot proceed"); err = -EROFS; goto failed_unload; } sb->s_flags &= ~SB_RDONLY; } else if (nilfs_test_opt(nilfs, NORECOVERY)) { nilfs_err(sb, "recovery cancelled because norecovery option was specified for a read/write mount"); err = -EINVAL; goto failed_unload; } err = nilfs_salvage_orphan_logs(nilfs, sb, &ri); if (err) goto failed_unload; down_write(&nilfs->ns_sem); nilfs->ns_mount_state |= NILFS_VALID_FS; /* set "clean" flag */ err = nilfs_cleanup_super(sb); up_write(&nilfs->ns_sem); if (err) { nilfs_err(sb, "error %d updating super block. recovery unfinished.", err); goto failed_unload; } nilfs_info(sb, "recovery complete"); skip_recovery: nilfs_clear_recovery_info(&ri); sb->s_flags = s_flags; return 0; scan_error: nilfs_err(sb, "error %d while searching super root", err); goto failed; failed_unload: nilfs_sysfs_delete_device_group(nilfs); sysfs_error: iput(nilfs->ns_cpfile); iput(nilfs->ns_sufile); iput(nilfs->ns_dat); failed: nilfs_clear_recovery_info(&ri); sb->s_flags = s_flags; return err; } static unsigned long long nilfs_max_size(unsigned int blkbits) { unsigned int max_bits; unsigned long long res = MAX_LFS_FILESIZE; /* page cache limit */ max_bits = blkbits + NILFS_BMAP_KEY_BIT; /* bmap size limit */ if (max_bits < 64) res = min_t(unsigned long long, res, (1ULL << max_bits) - 1); return res; } /** * nilfs_nrsvsegs - calculate the number of reserved segments * @nilfs: nilfs object * @nsegs: total number of segments */ unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs) { return max_t(unsigned long, NILFS_MIN_NRSVSEGS, DIV_ROUND_UP(nsegs * nilfs->ns_r_segments_percentage, 100)); } /** * nilfs_max_segment_count - calculate the maximum number of segments * @nilfs: nilfs object */ static u64 nilfs_max_segment_count(struct the_nilfs *nilfs) { u64 max_count = U64_MAX; max_count = div64_ul(max_count, nilfs->ns_blocks_per_segment); return min_t(u64, max_count, ULONG_MAX); } void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs) { nilfs->ns_nsegments = nsegs; nilfs->ns_nrsvsegs = nilfs_nrsvsegs(nilfs, nsegs); } static int nilfs_store_disk_layout(struct the_nilfs *nilfs, struct nilfs_super_block *sbp) { u64 nsegments, nblocks; if (le32_to_cpu(sbp->s_rev_level) < NILFS_MIN_SUPP_REV) { nilfs_err(nilfs->ns_sb, "unsupported revision (superblock rev.=%d.%d, current rev.=%d.%d). Please check the version of mkfs.nilfs(2).", le32_to_cpu(sbp->s_rev_level), le16_to_cpu(sbp->s_minor_rev_level), NILFS_CURRENT_REV, NILFS_MINOR_REV); return -EINVAL; } nilfs->ns_sbsize = le16_to_cpu(sbp->s_bytes); if (nilfs->ns_sbsize > BLOCK_SIZE) return -EINVAL; nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size); if (nilfs->ns_inode_size > nilfs->ns_blocksize) { nilfs_err(nilfs->ns_sb, "too large inode size: %d bytes", nilfs->ns_inode_size); return -EINVAL; } else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) { nilfs_err(nilfs->ns_sb, "too small inode size: %d bytes", nilfs->ns_inode_size); return -EINVAL; } nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino); nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) { nilfs_err(nilfs->ns_sb, "too short segment: %lu blocks", nilfs->ns_blocks_per_segment); return -EINVAL; } nilfs->ns_first_data_block = le64_to_cpu(sbp->s_first_data_block); nilfs->ns_r_segments_percentage = le32_to_cpu(sbp->s_r_segments_percentage); if (nilfs->ns_r_segments_percentage < 1 || nilfs->ns_r_segments_percentage > 99) { nilfs_err(nilfs->ns_sb, "invalid reserved segments percentage: %lu", nilfs->ns_r_segments_percentage); return -EINVAL; } nsegments = le64_to_cpu(sbp->s_nsegments); if (nsegments > nilfs_max_segment_count(nilfs)) { nilfs_err(nilfs->ns_sb, "segment count %llu exceeds upper limit (%llu segments)", (unsigned long long)nsegments, (unsigned long long)nilfs_max_segment_count(nilfs)); return -EINVAL; } nblocks = sb_bdev_nr_blocks(nilfs->ns_sb); if (nblocks) { u64 min_block_count = nsegments * nilfs->ns_blocks_per_segment; /* * To avoid failing to mount early device images without a * second superblock, exclude that block count from the * "min_block_count" calculation. */ if (nblocks < min_block_count) { nilfs_err(nilfs->ns_sb, "total number of segment blocks %llu exceeds device size (%llu blocks)", (unsigned long long)min_block_count, (unsigned long long)nblocks); return -EINVAL; } } nilfs_set_nsegments(nilfs, nsegments); nilfs->ns_crc_seed = le32_to_cpu(sbp->s_crc_seed); return 0; } static int nilfs_valid_sb(struct nilfs_super_block *sbp) { static unsigned char sum[4]; const int sumoff = offsetof(struct nilfs_super_block, s_sum); size_t bytes; u32 crc; if (!sbp || le16_to_cpu(sbp->s_magic) != NILFS_SUPER_MAGIC) return 0; bytes = le16_to_cpu(sbp->s_bytes); if (bytes < sumoff + 4 || bytes > BLOCK_SIZE) return 0; crc = crc32_le(le32_to_cpu(sbp->s_crc_seed), (unsigned char *)sbp, sumoff); crc = crc32_le(crc, sum, 4); crc = crc32_le(crc, (unsigned char *)sbp + sumoff + 4, bytes - sumoff - 4); return crc == le32_to_cpu(sbp->s_sum); } /** * nilfs_sb2_bad_offset - check the location of the second superblock * @sbp: superblock raw data buffer * @offset: byte offset of second superblock calculated from device size * * nilfs_sb2_bad_offset() checks if the position on the second * superblock is valid or not based on the filesystem parameters * stored in @sbp. If @offset points to a location within the segment * area, or if the parameters themselves are not normal, it is * determined to be invalid. * * Return Value: true if invalid, false if valid. */ static bool nilfs_sb2_bad_offset(struct nilfs_super_block *sbp, u64 offset) { unsigned int shift_bits = le32_to_cpu(sbp->s_log_block_size); u32 blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment); u64 nsegments = le64_to_cpu(sbp->s_nsegments); u64 index; if (blocks_per_segment < NILFS_SEG_MIN_BLOCKS || shift_bits > ilog2(NILFS_MAX_BLOCK_SIZE) - BLOCK_SIZE_BITS) return true; index = offset >> (shift_bits + BLOCK_SIZE_BITS); do_div(index, blocks_per_segment); return index < nsegments; } static void nilfs_release_super_block(struct the_nilfs *nilfs) { int i; for (i = 0; i < 2; i++) { if (nilfs->ns_sbp[i]) { brelse(nilfs->ns_sbh[i]); nilfs->ns_sbh[i] = NULL; nilfs->ns_sbp[i] = NULL; } } } void nilfs_fall_back_super_block(struct the_nilfs *nilfs) { brelse(nilfs->ns_sbh[0]); nilfs->ns_sbh[0] = nilfs->ns_sbh[1]; nilfs->ns_sbp[0] = nilfs->ns_sbp[1]; nilfs->ns_sbh[1] = NULL; nilfs->ns_sbp[1] = NULL; } void nilfs_swap_super_block(struct the_nilfs *nilfs) { struct buffer_head *tsbh = nilfs->ns_sbh[0]; struct nilfs_super_block *tsbp = nilfs->ns_sbp[0]; nilfs->ns_sbh[0] = nilfs->ns_sbh[1]; nilfs->ns_sbp[0] = nilfs->ns_sbp[1]; nilfs->ns_sbh[1] = tsbh; nilfs->ns_sbp[1] = tsbp; } static int nilfs_load_super_block(struct the_nilfs *nilfs, struct super_block *sb, int blocksize, struct nilfs_super_block **sbpp) { struct nilfs_super_block **sbp = nilfs->ns_sbp; struct buffer_head **sbh = nilfs->ns_sbh; u64 sb2off, devsize = bdev_nr_bytes(nilfs->ns_bdev); int valid[2], swp = 0, older; if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) { nilfs_err(sb, "device size too small"); return -EINVAL; } sb2off = NILFS_SB2_OFFSET_BYTES(devsize); sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize, &sbh[0]); sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]); if (!sbp[0]) { if (!sbp[1]) { nilfs_err(sb, "unable to read superblock"); return -EIO; } nilfs_warn(sb, "unable to read primary superblock (blocksize = %d)", blocksize); } else if (!sbp[1]) { nilfs_warn(sb, "unable to read secondary superblock (blocksize = %d)", blocksize); } /* * Compare two super blocks and set 1 in swp if the secondary * super block is valid and newer. Otherwise, set 0 in swp. */ valid[0] = nilfs_valid_sb(sbp[0]); valid[1] = nilfs_valid_sb(sbp[1]); swp = valid[1] && (!valid[0] || le64_to_cpu(sbp[1]->s_last_cno) > le64_to_cpu(sbp[0]->s_last_cno)); if (valid[swp] && nilfs_sb2_bad_offset(sbp[swp], sb2off)) { brelse(sbh[1]); sbh[1] = NULL; sbp[1] = NULL; valid[1] = 0; swp = 0; } if (!valid[swp]) { nilfs_release_super_block(nilfs); nilfs_err(sb, "couldn't find nilfs on the device"); return -EINVAL; } if (!valid[!swp]) nilfs_warn(sb, "broken superblock, retrying with spare superblock (blocksize = %d)", blocksize); if (swp) nilfs_swap_super_block(nilfs); /* * Calculate the array index of the older superblock data. * If one has been dropped, set index 0 pointing to the remaining one, * otherwise set index 1 pointing to the old one (including if both * are the same). * * Divided case valid[0] valid[1] swp -> older * ------------------------------------------------------------- * Both SBs are invalid 0 0 N/A (Error) * SB1 is invalid 0 1 1 0 * SB2 is invalid 1 0 0 0 * SB2 is newer 1 1 1 0 * SB2 is older or the same 1 1 0 1 */ older = valid[1] ^ swp; nilfs->ns_sbwcount = 0; nilfs->ns_sbwtime = le64_to_cpu(sbp[0]->s_wtime); nilfs->ns_prot_seq = le64_to_cpu(sbp[older]->s_last_seq); *sbpp = sbp[0]; return 0; } /** * init_nilfs - initialize a NILFS instance. * @nilfs: the_nilfs structure * @sb: super block * * init_nilfs() performs common initialization per block device (e.g. * reading the super block, getting disk layout information, initializing * shared fields in the_nilfs). * * Return Value: On success, 0 is returned. On error, a negative error * code is returned. */ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb) { struct nilfs_super_block *sbp; int blocksize; int err; down_write(&nilfs->ns_sem); blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE); if (!blocksize) { nilfs_err(sb, "unable to set blocksize"); err = -EINVAL; goto out; } err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp); if (err) goto out; err = nilfs_store_magic(sb, sbp); if (err) goto failed_sbh; err = nilfs_check_feature_compatibility(sb, sbp); if (err) goto failed_sbh; err = nilfs_get_blocksize(sb, sbp, &blocksize); if (err) goto failed_sbh; if (blocksize < NILFS_MIN_BLOCK_SIZE) { nilfs_err(sb, "couldn't mount because of unsupported filesystem blocksize %d", blocksize); err = -EINVAL; goto failed_sbh; } if (sb->s_blocksize != blocksize) { int hw_blocksize = bdev_logical_block_size(sb->s_bdev); if (blocksize < hw_blocksize) { nilfs_err(sb, "blocksize %d too small for device (sector-size = %d)", blocksize, hw_blocksize); err = -EINVAL; goto failed_sbh; } nilfs_release_super_block(nilfs); if (!sb_set_blocksize(sb, blocksize)) { nilfs_err(sb, "bad blocksize %d", blocksize); err = -EINVAL; goto out; } err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp); if (err) goto out; /* * Not to failed_sbh; sbh is released automatically * when reloading fails. */ } nilfs->ns_blocksize_bits = sb->s_blocksize_bits; nilfs->ns_blocksize = blocksize; get_random_bytes(&nilfs->ns_next_generation, sizeof(nilfs->ns_next_generation)); err = nilfs_store_disk_layout(nilfs, sbp); if (err) goto failed_sbh; sb->s_maxbytes = nilfs_max_size(sb->s_blocksize_bits); nilfs->ns_mount_state = le16_to_cpu(sbp->s_state); err = nilfs_store_log_cursor(nilfs, sbp); if (err) goto failed_sbh; set_nilfs_init(nilfs); err = 0; out: up_write(&nilfs->ns_sem); return err; failed_sbh: nilfs_release_super_block(nilfs); goto out; } int nilfs_discard_segments(struct the_nilfs *nilfs, __u64 *segnump, size_t nsegs) { sector_t seg_start, seg_end; sector_t start = 0, nblocks = 0; unsigned int sects_per_block; __u64 *sn; int ret = 0; sects_per_block = (1 << nilfs->ns_blocksize_bits) / bdev_logical_block_size(nilfs->ns_bdev); for (sn = segnump; sn < segnump + nsegs; sn++) { nilfs_get_segment_range(nilfs, *sn, &seg_start, &seg_end); if (!nblocks) { start = seg_start; nblocks = seg_end - seg_start + 1; } else if (start + nblocks == seg_start) { nblocks += seg_end - seg_start + 1; } else { ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, GFP_NOFS); if (ret < 0) return ret; nblocks = 0; } } if (nblocks) ret = blkdev_issue_discard(nilfs->ns_bdev, start * sects_per_block, nblocks * sects_per_block, GFP_NOFS); return ret; } int nilfs_count_free_blocks(struct the_nilfs *nilfs, sector_t *nblocks) { unsigned long ncleansegs; ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile); *nblocks = (sector_t)ncleansegs * nilfs->ns_blocks_per_segment; return 0; } int nilfs_near_disk_full(struct the_nilfs *nilfs) { unsigned long ncleansegs, nincsegs; ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile); nincsegs = atomic_read(&nilfs->ns_ndirtyblks) / nilfs->ns_blocks_per_segment + 1; return ncleansegs <= nilfs->ns_nrsvsegs + nincsegs; } struct nilfs_root *nilfs_lookup_root(struct the_nilfs *nilfs, __u64 cno) { struct rb_node *n; struct nilfs_root *root; spin_lock(&nilfs->ns_cptree_lock); n = nilfs->ns_cptree.rb_node; while (n) { root = rb_entry(n, struct nilfs_root, rb_node); if (cno < root->cno) { n = n->rb_left; } else if (cno > root->cno) { n = n->rb_right; } else { refcount_inc(&root->count); spin_unlock(&nilfs->ns_cptree_lock); return root; } } spin_unlock(&nilfs->ns_cptree_lock); return NULL; } struct nilfs_root * nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno) { struct rb_node **p, *parent; struct nilfs_root *root, *new; int err; root = nilfs_lookup_root(nilfs, cno); if (root) return root; new = kzalloc(sizeof(*root), GFP_KERNEL); if (!new) return NULL; spin_lock(&nilfs->ns_cptree_lock); p = &nilfs->ns_cptree.rb_node; parent = NULL; while (*p) { parent = *p; root = rb_entry(parent, struct nilfs_root, rb_node); if (cno < root->cno) { p = &(*p)->rb_left; } else if (cno > root->cno) { p = &(*p)->rb_right; } else { refcount_inc(&root->count); spin_unlock(&nilfs->ns_cptree_lock); kfree(new); return root; } } new->cno = cno; new->ifile = NULL; new->nilfs = nilfs; refcount_set(&new->count, 1); atomic64_set(&new->inodes_count, 0); atomic64_set(&new->blocks_count, 0); rb_link_node(&new->rb_node, parent, p); rb_insert_color(&new->rb_node, &nilfs->ns_cptree); spin_unlock(&nilfs->ns_cptree_lock); err = nilfs_sysfs_create_snapshot_group(new); if (err) { kfree(new); new = NULL; } return new; } void nilfs_put_root(struct nilfs_root *root) { struct the_nilfs *nilfs = root->nilfs; if (refcount_dec_and_lock(&root->count, &nilfs->ns_cptree_lock)) { rb_erase(&root->rb_node, &nilfs->ns_cptree); spin_unlock(&nilfs->ns_cptree_lock); nilfs_sysfs_delete_snapshot_group(root); iput(root->ifile); kfree(root); } } |
| 7 7 6 1 5 7 1 5 1 5 6 6 6 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 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to sysfs handling */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/blktrace_api.h> #include <linux/debugfs.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" #include "blk-wbt.h" #include "blk-cgroup.h" #include "blk-throttle.h" struct queue_sysfs_entry { struct attribute attr; ssize_t (*show)(struct request_queue *, char *); ssize_t (*store)(struct request_queue *, const char *, size_t); }; static ssize_t queue_var_show(unsigned long var, char *page) { return sprintf(page, "%lu\n", var); } static ssize_t queue_var_store(unsigned long *var, const char *page, size_t count) { int err; unsigned long v; err = kstrtoul(page, 10, &v); if (err || v > UINT_MAX) return -EINVAL; *var = v; return count; } static ssize_t queue_requests_show(struct request_queue *q, char *page) { return queue_var_show(q->nr_requests, page); } static ssize_t queue_requests_store(struct request_queue *q, const char *page, size_t count) { unsigned long nr; int ret, err; if (!queue_is_mq(q)) return -EINVAL; ret = queue_var_store(&nr, page, count); if (ret < 0) return ret; if (nr < BLKDEV_MIN_RQ) nr = BLKDEV_MIN_RQ; err = blk_mq_update_nr_requests(q, nr); if (err) return err; return ret; } static ssize_t queue_ra_show(struct request_queue *q, char *page) { unsigned long ra_kb; if (!q->disk) return -EINVAL; ra_kb = q->disk->bdi->ra_pages << (PAGE_SHIFT - 10); return queue_var_show(ra_kb, page); } static ssize_t queue_ra_store(struct request_queue *q, const char *page, size_t count) { unsigned long ra_kb; ssize_t ret; if (!q->disk) return -EINVAL; ret = queue_var_store(&ra_kb, page, count); if (ret < 0) return ret; q->disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); return ret; } static ssize_t queue_max_sectors_show(struct request_queue *q, char *page) { int max_sectors_kb = queue_max_sectors(q) >> 1; return queue_var_show(max_sectors_kb, page); } static ssize_t queue_max_segments_show(struct request_queue *q, char *page) { return queue_var_show(queue_max_segments(q), page); } static ssize_t queue_max_discard_segments_show(struct request_queue *q, char *page) { return queue_var_show(queue_max_discard_segments(q), page); } static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page) { return queue_var_show(q->limits.max_integrity_segments, page); } static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) { return queue_var_show(queue_max_segment_size(q), page); } static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page) { return queue_var_show(queue_logical_block_size(q), page); } static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page) { return queue_var_show(queue_physical_block_size(q), page); } static ssize_t queue_chunk_sectors_show(struct request_queue *q, char *page) { return queue_var_show(q->limits.chunk_sectors, page); } static ssize_t queue_io_min_show(struct request_queue *q, char *page) { return queue_var_show(queue_io_min(q), page); } static ssize_t queue_io_opt_show(struct request_queue *q, char *page) { return queue_var_show(queue_io_opt(q), page); } static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page) { return queue_var_show(q->limits.discard_granularity, page); } static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page) { return sprintf(page, "%llu\n", (unsigned long long)q->limits.max_hw_discard_sectors << 9); } static ssize_t queue_discard_max_show(struct request_queue *q, char *page) { return sprintf(page, "%llu\n", (unsigned long long)q->limits.max_discard_sectors << 9); } static ssize_t queue_discard_max_store(struct request_queue *q, const char *page, size_t count) { unsigned long max_discard_bytes; struct queue_limits lim; ssize_t ret; int err; ret = queue_var_store(&max_discard_bytes, page, count); if (ret < 0) return ret; if (max_discard_bytes & (q->limits.discard_granularity - 1)) return -EINVAL; if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX) return -EINVAL; blk_mq_freeze_queue(q); lim = queue_limits_start_update(q); lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT; err = queue_limits_commit_update(q, &lim); blk_mq_unfreeze_queue(q); if (err) return err; return ret; } static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page) { return queue_var_show(0, page); } static ssize_t queue_write_same_max_show(struct request_queue *q, char *page) { return queue_var_show(0, page); } static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page) { return sprintf(page, "%llu\n", (unsigned long long)q->limits.max_write_zeroes_sectors << 9); } static ssize_t queue_zone_write_granularity_show(struct request_queue *q, char *page) { return queue_var_show(queue_zone_write_granularity(q), page); } static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page) { unsigned long long max_sectors = queue_max_zone_append_sectors(q); return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT); } static ssize_t queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) { unsigned long max_sectors_kb; struct queue_limits lim; ssize_t ret; int err; ret = queue_var_store(&max_sectors_kb, page, count); if (ret < 0) return ret; blk_mq_freeze_queue(q); lim = queue_limits_start_update(q); lim.max_user_sectors = max_sectors_kb << 1; err = queue_limits_commit_update(q, &lim); blk_mq_unfreeze_queue(q); if (err) return err; return ret; } static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page) { int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1; return queue_var_show(max_hw_sectors_kb, page); } static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page) { return queue_var_show(q->limits.virt_boundary_mask, page); } static ssize_t queue_dma_alignment_show(struct request_queue *q, char *page) { return queue_var_show(queue_dma_alignment(q), page); } #define QUEUE_SYSFS_BIT_FNS(name, flag, neg) \ static ssize_t \ queue_##name##_show(struct request_queue *q, char *page) \ { \ int bit; \ bit = test_bit(QUEUE_FLAG_##flag, &q->queue_flags); \ return queue_var_show(neg ? !bit : bit, page); \ } \ static ssize_t \ queue_##name##_store(struct request_queue *q, const char *page, size_t count) \ { \ unsigned long val; \ ssize_t ret; \ ret = queue_var_store(&val, page, count); \ if (ret < 0) \ return ret; \ if (neg) \ val = !val; \ \ if (val) \ blk_queue_flag_set(QUEUE_FLAG_##flag, q); \ else \ blk_queue_flag_clear(QUEUE_FLAG_##flag, q); \ return ret; \ } QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1); QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0); QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0); QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0); #undef QUEUE_SYSFS_BIT_FNS static ssize_t queue_zoned_show(struct request_queue *q, char *page) { if (blk_queue_is_zoned(q)) return sprintf(page, "host-managed\n"); return sprintf(page, "none\n"); } static ssize_t queue_nr_zones_show(struct request_queue *q, char *page) { return queue_var_show(disk_nr_zones(q->disk), page); } static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page) { return queue_var_show(bdev_max_open_zones(q->disk->part0), page); } static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page) { return queue_var_show(bdev_max_active_zones(q->disk->part0), page); } static ssize_t queue_nomerges_show(struct request_queue *q, char *page) { return queue_var_show((blk_queue_nomerges(q) << 1) | blk_queue_noxmerges(q), page); } static ssize_t queue_nomerges_store(struct request_queue *q, const char *page, size_t count) { unsigned long nm; ssize_t ret = queue_var_store(&nm, page, count); if (ret < 0) return ret; blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, q); if (nm == 2) blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); else if (nm) blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); return ret; } static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page) { bool set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags); bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags); return queue_var_show(set << force, page); } static ssize_t queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count) { ssize_t ret = -EINVAL; #ifdef CONFIG_SMP unsigned long val; ret = queue_var_store(&val, page, count); if (ret < 0) return ret; if (val == 2) { blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, q); } else if (val == 1) { blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); } else if (val == 0) { blk_queue_flag_clear(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); } #endif return ret; } static ssize_t queue_poll_delay_show(struct request_queue *q, char *page) { return sprintf(page, "%d\n", -1); } static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page, size_t count) { return count; } static ssize_t queue_poll_show(struct request_queue *q, char *page) { return queue_var_show(test_bit(QUEUE_FLAG_POLL, &q->queue_flags), page); } static ssize_t queue_poll_store(struct request_queue *q, const char *page, size_t count) { if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) return -EINVAL; pr_info_ratelimited("writes to the poll attribute are ignored.\n"); pr_info_ratelimited("please use driver specific parameters instead.\n"); return count; } static ssize_t queue_io_timeout_show(struct request_queue *q, char *page) { return sprintf(page, "%u\n", jiffies_to_msecs(q->rq_timeout)); } static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page, size_t count) { unsigned int val; int err; err = kstrtou32(page, 10, &val); if (err || val == 0) return -EINVAL; blk_queue_rq_timeout(q, msecs_to_jiffies(val)); return count; } static ssize_t queue_wc_show(struct request_queue *q, char *page) { if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) return sprintf(page, "write back\n"); return sprintf(page, "write through\n"); } static ssize_t queue_wc_store(struct request_queue *q, const char *page, size_t count) { if (!strncmp(page, "write back", 10)) { if (!test_bit(QUEUE_FLAG_HW_WC, &q->queue_flags)) return -EINVAL; blk_queue_flag_set(QUEUE_FLAG_WC, q); } else if (!strncmp(page, "write through", 13) || !strncmp(page, "none", 4)) { blk_queue_flag_clear(QUEUE_FLAG_WC, q); } else { return -EINVAL; } return count; } static ssize_t queue_fua_show(struct request_queue *q, char *page) { return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags)); } static ssize_t queue_dax_show(struct request_queue *q, char *page) { return queue_var_show(blk_queue_dax(q), page); } #define QUEUE_RO_ENTRY(_prefix, _name) \ static struct queue_sysfs_entry _prefix##_entry = { \ .attr = { .name = _name, .mode = 0444 }, \ .show = _prefix##_show, \ }; #define QUEUE_RW_ENTRY(_prefix, _name) \ static struct queue_sysfs_entry _prefix##_entry = { \ .attr = { .name = _name, .mode = 0644 }, \ .show = _prefix##_show, \ .store = _prefix##_store, \ }; QUEUE_RW_ENTRY(queue_requests, "nr_requests"); QUEUE_RW_ENTRY(queue_ra, "read_ahead_kb"); QUEUE_RW_ENTRY(queue_max_sectors, "max_sectors_kb"); QUEUE_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb"); QUEUE_RO_ENTRY(queue_max_segments, "max_segments"); QUEUE_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments"); QUEUE_RO_ENTRY(queue_max_segment_size, "max_segment_size"); QUEUE_RW_ENTRY(elv_iosched, "scheduler"); QUEUE_RO_ENTRY(queue_logical_block_size, "logical_block_size"); QUEUE_RO_ENTRY(queue_physical_block_size, "physical_block_size"); QUEUE_RO_ENTRY(queue_chunk_sectors, "chunk_sectors"); QUEUE_RO_ENTRY(queue_io_min, "minimum_io_size"); QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size"); QUEUE_RO_ENTRY(queue_max_discard_segments, "max_discard_segments"); QUEUE_RO_ENTRY(queue_discard_granularity, "discard_granularity"); QUEUE_RO_ENTRY(queue_discard_max_hw, "discard_max_hw_bytes"); QUEUE_RW_ENTRY(queue_discard_max, "discard_max_bytes"); QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data"); QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes"); QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes"); QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes"); QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity"); QUEUE_RO_ENTRY(queue_zoned, "zoned"); QUEUE_RO_ENTRY(queue_nr_zones, "nr_zones"); QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones"); QUEUE_RO_ENTRY(queue_max_active_zones, "max_active_zones"); QUEUE_RW_ENTRY(queue_nomerges, "nomerges"); QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity"); QUEUE_RW_ENTRY(queue_poll, "io_poll"); QUEUE_RW_ENTRY(queue_poll_delay, "io_poll_delay"); QUEUE_RW_ENTRY(queue_wc, "write_cache"); QUEUE_RO_ENTRY(queue_fua, "fua"); QUEUE_RO_ENTRY(queue_dax, "dax"); QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout"); QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask"); QUEUE_RO_ENTRY(queue_dma_alignment, "dma_alignment"); /* legacy alias for logical_block_size: */ static struct queue_sysfs_entry queue_hw_sector_size_entry = { .attr = {.name = "hw_sector_size", .mode = 0444 }, .show = queue_logical_block_size_show, }; QUEUE_RW_ENTRY(queue_nonrot, "rotational"); QUEUE_RW_ENTRY(queue_iostats, "iostats"); QUEUE_RW_ENTRY(queue_random, "add_random"); QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes"); #ifdef CONFIG_BLK_WBT static ssize_t queue_var_store64(s64 *var, const char *page) { int err; s64 v; err = kstrtos64(page, 10, &v); if (err < 0) return err; *var = v; return 0; } static ssize_t queue_wb_lat_show(struct request_queue *q, char *page) { if (!wbt_rq_qos(q)) return -EINVAL; if (wbt_disabled(q)) return sprintf(page, "0\n"); return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000)); } static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, size_t count) { struct rq_qos *rqos; ssize_t ret; s64 val; ret = queue_var_store64(&val, page); if (ret < 0) return ret; if (val < -1) return -EINVAL; rqos = wbt_rq_qos(q); if (!rqos) { ret = wbt_init(q->disk); if (ret) return ret; } if (val == -1) val = wbt_default_latency_nsec(q); else if (val >= 0) val *= 1000ULL; if (wbt_get_min_lat(q) == val) return count; /* * Ensure that the queue is idled, in case the latency update * ends up either enabling or disabling wbt completely. We can't * have IO inflight if that happens. */ blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); wbt_set_min_lat(q, val); blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); return count; } QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec"); #endif /* Common attributes for bio-based and request-based queues. */ static struct attribute *queue_attrs[] = { &queue_ra_entry.attr, &queue_max_hw_sectors_entry.attr, &queue_max_sectors_entry.attr, &queue_max_segments_entry.attr, &queue_max_discard_segments_entry.attr, &queue_max_integrity_segments_entry.attr, &queue_max_segment_size_entry.attr, &queue_hw_sector_size_entry.attr, &queue_logical_block_size_entry.attr, &queue_physical_block_size_entry.attr, &queue_chunk_sectors_entry.attr, &queue_io_min_entry.attr, &queue_io_opt_entry.attr, &queue_discard_granularity_entry.attr, &queue_discard_max_entry.attr, &queue_discard_max_hw_entry.attr, &queue_discard_zeroes_data_entry.attr, &queue_write_same_max_entry.attr, &queue_write_zeroes_max_entry.attr, &queue_zone_append_max_entry.attr, &queue_zone_write_granularity_entry.attr, &queue_nonrot_entry.attr, &queue_zoned_entry.attr, &queue_nr_zones_entry.attr, &queue_max_open_zones_entry.attr, &queue_max_active_zones_entry.attr, &queue_nomerges_entry.attr, &queue_iostats_entry.attr, &queue_stable_writes_entry.attr, &queue_random_entry.attr, &queue_poll_entry.attr, &queue_wc_entry.attr, &queue_fua_entry.attr, &queue_dax_entry.attr, &queue_poll_delay_entry.attr, &queue_virt_boundary_mask_entry.attr, &queue_dma_alignment_entry.attr, NULL, }; /* Request-based queue attributes that are not relevant for bio-based queues. */ static struct attribute *blk_mq_queue_attrs[] = { &queue_requests_entry.attr, &elv_iosched_entry.attr, &queue_rq_affinity_entry.attr, &queue_io_timeout_entry.attr, #ifdef CONFIG_BLK_WBT &queue_wb_lat_entry.attr, #endif NULL, }; static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr, int n) { struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; if ((attr == &queue_max_open_zones_entry.attr || attr == &queue_max_active_zones_entry.attr) && !blk_queue_is_zoned(q)) return 0; return attr->mode; } static umode_t blk_mq_queue_attr_visible(struct kobject *kobj, struct attribute *attr, int n) { struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; if (!queue_is_mq(q)) return 0; if (attr == &queue_io_timeout_entry.attr && !q->mq_ops->timeout) return 0; return attr->mode; } static struct attribute_group queue_attr_group = { .attrs = queue_attrs, .is_visible = queue_attr_visible, }; static struct attribute_group blk_mq_queue_attr_group = { .attrs = blk_mq_queue_attrs, .is_visible = blk_mq_queue_attr_visible, }; #define to_queue(atr) container_of((atr), struct queue_sysfs_entry, attr) static ssize_t queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct queue_sysfs_entry *entry = to_queue(attr); struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; ssize_t res; if (!entry->show) return -EIO; mutex_lock(&q->sysfs_lock); res = entry->show(q, page); mutex_unlock(&q->sysfs_lock); return res; } static ssize_t queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *page, size_t length) { struct queue_sysfs_entry *entry = to_queue(attr); struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; ssize_t res; if (!entry->store) return -EIO; mutex_lock(&q->sysfs_lock); res = entry->store(q, page, length); mutex_unlock(&q->sysfs_lock); return res; } static const struct sysfs_ops queue_sysfs_ops = { .show = queue_attr_show, .store = queue_attr_store, }; static const struct attribute_group *blk_queue_attr_groups[] = { &queue_attr_group, &blk_mq_queue_attr_group, NULL }; static void blk_queue_release(struct kobject *kobj) { /* nothing to do here, all data is associated with the parent gendisk */ } static const struct kobj_type blk_queue_ktype = { .default_groups = blk_queue_attr_groups, .sysfs_ops = &queue_sysfs_ops, .release = blk_queue_release, }; static void blk_debugfs_remove(struct gendisk *disk) { struct request_queue *q = disk->queue; mutex_lock(&q->debugfs_mutex); blk_trace_shutdown(q); debugfs_remove_recursive(q->debugfs_dir); q->debugfs_dir = NULL; q->sched_debugfs_dir = NULL; q->rqos_debugfs_dir = NULL; mutex_unlock(&q->debugfs_mutex); } /** * blk_register_queue - register a block layer queue with sysfs * @disk: Disk of which the request queue should be registered with sysfs. */ int blk_register_queue(struct gendisk *disk) { struct request_queue *q = disk->queue; int ret; mutex_lock(&q->sysfs_dir_lock); kobject_init(&disk->queue_kobj, &blk_queue_ktype); ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue"); if (ret < 0) goto out_put_queue_kobj; if (queue_is_mq(q)) { ret = blk_mq_sysfs_register(disk); if (ret) goto out_put_queue_kobj; } mutex_lock(&q->sysfs_lock); mutex_lock(&q->debugfs_mutex); q->debugfs_dir = debugfs_create_dir(disk->disk_name, blk_debugfs_root); if (queue_is_mq(q)) blk_mq_debugfs_register(q); mutex_unlock(&q->debugfs_mutex); ret = disk_register_independent_access_ranges(disk); if (ret) goto out_debugfs_remove; if (q->elevator) { ret = elv_register_queue(q, false); if (ret) goto out_unregister_ia_ranges; } ret = blk_crypto_sysfs_register(disk); if (ret) goto out_elv_unregister; blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); wbt_enable_default(disk); /* Now everything is ready and send out KOBJ_ADD uevent */ kobject_uevent(&disk->queue_kobj, KOBJ_ADD); if (q->elevator) kobject_uevent(&q->elevator->kobj, KOBJ_ADD); mutex_unlock(&q->sysfs_lock); mutex_unlock(&q->sysfs_dir_lock); /* * SCSI probing may synchronously create and destroy a lot of * request_queues for non-existent devices. Shutting down a fully * functional queue takes measureable wallclock time as RCU grace * periods are involved. To avoid excessive latency in these * cases, a request_queue starts out in a degraded mode which is * faster to shut down and is made fully functional here as * request_queues for non-existent devices never get registered. */ if (!blk_queue_init_done(q)) { blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); percpu_ref_switch_to_percpu(&q->q_usage_counter); } return ret; out_elv_unregister: elv_unregister_queue(q); out_unregister_ia_ranges: disk_unregister_independent_access_ranges(disk); out_debugfs_remove: blk_debugfs_remove(disk); mutex_unlock(&q->sysfs_lock); out_put_queue_kobj: kobject_put(&disk->queue_kobj); mutex_unlock(&q->sysfs_dir_lock); return ret; } /** * blk_unregister_queue - counterpart of blk_register_queue() * @disk: Disk of which the request queue should be unregistered from sysfs. * * Note: the caller is responsible for guaranteeing that this function is called * after blk_register_queue() has finished. */ void blk_unregister_queue(struct gendisk *disk) { struct request_queue *q = disk->queue; if (WARN_ON(!q)) return; /* Return early if disk->queue was never registered. */ if (!blk_queue_registered(q)) return; /* * Since sysfs_remove_dir() prevents adding new directory entries * before removal of existing entries starts, protect against * concurrent elv_iosched_store() calls. */ mutex_lock(&q->sysfs_lock); blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q); mutex_unlock(&q->sysfs_lock); mutex_lock(&q->sysfs_dir_lock); /* * Remove the sysfs attributes before unregistering the queue data * structures that can be modified through sysfs. */ if (queue_is_mq(q)) blk_mq_sysfs_unregister(disk); blk_crypto_sysfs_unregister(disk); mutex_lock(&q->sysfs_lock); elv_unregister_queue(q); disk_unregister_independent_access_ranges(disk); mutex_unlock(&q->sysfs_lock); /* Now that we've deleted all child objects, we can delete the queue. */ kobject_uevent(&disk->queue_kobj, KOBJ_REMOVE); kobject_del(&disk->queue_kobj); mutex_unlock(&q->sysfs_dir_lock); blk_debugfs_remove(disk); } |
| 158 82 187 363 92 1 347 101 101 101 101 101 101 355 284 297 346 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_X86_MMU_H #define __KVM_X86_MMU_H #include <linux/kvm_host.h> #include "kvm_cache_regs.h" #include "cpuid.h" extern bool __read_mostly enable_mmio_caching; #define PT_WRITABLE_SHIFT 1 #define PT_USER_SHIFT 2 #define PT_PRESENT_MASK (1ULL << 0) #define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT) #define PT_USER_MASK (1ULL << PT_USER_SHIFT) #define PT_PWT_MASK (1ULL << 3) #define PT_PCD_MASK (1ULL << 4) #define PT_ACCESSED_SHIFT 5 #define PT_ACCESSED_MASK (1ULL << PT_ACCESSED_SHIFT) #define PT_DIRTY_SHIFT 6 #define PT_DIRTY_MASK (1ULL << PT_DIRTY_SHIFT) #define PT_PAGE_SIZE_SHIFT 7 #define PT_PAGE_SIZE_MASK (1ULL << PT_PAGE_SIZE_SHIFT) #define PT_PAT_MASK (1ULL << 7) #define PT_GLOBAL_MASK (1ULL << 8) #define PT64_NX_SHIFT 63 #define PT64_NX_MASK (1ULL << PT64_NX_SHIFT) #define PT_PAT_SHIFT 7 #define PT_DIR_PAT_SHIFT 12 #define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT) #define PT64_ROOT_5LEVEL 5 #define PT64_ROOT_4LEVEL 4 #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 #define KVM_MMU_CR4_ROLE_BITS (X86_CR4_PSE | X86_CR4_PAE | X86_CR4_LA57 | \ X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE) #define KVM_MMU_CR0_ROLE_BITS (X86_CR0_PG | X86_CR0_WP) #define KVM_MMU_EFER_ROLE_BITS (EFER_LME | EFER_NX) static __always_inline u64 rsvd_bits(int s, int e) { BUILD_BUG_ON(__builtin_constant_p(e) && __builtin_constant_p(s) && e < s); if (__builtin_constant_p(e)) BUILD_BUG_ON(e > 63); else e &= 63; if (e < s) return 0; return ((2ULL << (e - s)) - 1) << s; } /* * The number of non-reserved physical address bits irrespective of features * that repurpose legal bits, e.g. MKTME. */ extern u8 __read_mostly shadow_phys_bits; static inline gfn_t kvm_mmu_max_gfn(void) { /* * Note that this uses the host MAXPHYADDR, not the guest's. * EPT/NPT cannot support GPAs that would exceed host.MAXPHYADDR; * assuming KVM is running on bare metal, guest accesses beyond * host.MAXPHYADDR will hit a #PF(RSVD) and never cause a vmexit * (either EPT Violation/Misconfig or #NPF), and so KVM will never * install a SPTE for such addresses. If KVM is running as a VM * itself, on the other hand, it might see a MAXPHYADDR that is less * than hardware's real MAXPHYADDR. Using the host MAXPHYADDR * disallows such SPTEs entirely and simplifies the TDP MMU. */ int max_gpa_bits = likely(tdp_enabled) ? shadow_phys_bits : 52; return (1ULL << (max_gpa_bits - PAGE_SHIFT)) - 1; } static inline u8 kvm_get_shadow_phys_bits(void) { /* * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected * in CPU detection code, but the processor treats those reduced bits as * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at * the physical address bits reported by CPUID. */ if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008)) return cpuid_eax(0x80000008) & 0xff; /* * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with * custom CPUID. Proceed with whatever the kernel found since these features * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008). */ return boot_cpu_data.x86_phys_bits; } u8 kvm_mmu_get_max_tdp_level(void); void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask); void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only); void kvm_init_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, unsigned long cr4, u64 efer, gpa_t nested_cr3); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, int huge_page_level, bool accessed_dirty, gpa_t new_eptp); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu); void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); void kvm_mmu_sync_prev_roots(struct kvm_vcpu *vcpu); void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes); static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { if (likely(vcpu->arch.mmu->root.hpa != INVALID_PAGE)) return 0; return kvm_mmu_load(vcpu); } static inline unsigned long kvm_get_pcid(struct kvm_vcpu *vcpu, gpa_t cr3) { BUILD_BUG_ON((X86_CR3_PCID_MASK & PAGE_MASK) != 0); return kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE) ? cr3 & X86_CR3_PCID_MASK : 0; } static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) { return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu)); } static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu) { if (!guest_can_use(vcpu, X86_FEATURE_LAM)) return 0; return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57); } static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) { u64 root_hpa = vcpu->arch.mmu->root.hpa; if (!VALID_PAGE(root_hpa)) return; static_call(kvm_x86_load_mmu_pgd)(vcpu, root_hpa, vcpu->arch.mmu->root_role.level); } static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { /* * When EPT is enabled, KVM may passthrough CR0.WP to the guest, i.e. * @mmu's snapshot of CR0.WP and thus all related paging metadata may * be stale. Refresh CR0.WP and the metadata on-demand when checking * for permission faults. Exempt nested MMUs, i.e. MMUs for shadowing * nEPT and nNPT, as CR0.WP is ignored in both cases. Note, KVM does * need to refresh nested_mmu, a.k.a. the walker used to translate L2 * GVAs to GPAs, as that "MMU" needs to honor L2's CR0.WP. */ if (!tdp_enabled || mmu == &vcpu->arch.guest_mmu) return; __kvm_mmu_refresh_passthrough_bits(vcpu, mmu); } /* * Check if a given access (described through the I/D, W/R and U/S bits of a * page fault error code pfec) causes a permission fault with the given PTE * access rights (in ACC_* format). * * Return zero if the access does not fault; return the page fault error code * if the access faults. */ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned pte_access, unsigned pte_pkey, u64 access) { /* strip nested paging fault error codes */ unsigned int pfec = access; unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); /* * For explicit supervisor accesses, SMAP is disabled if EFLAGS.AC = 1. * For implicit supervisor accesses, SMAP cannot be overridden. * * SMAP works on supervisor accesses only, and not_smap can * be set or not set when user access with neither has any bearing * on the result. * * We put the SMAP checking bit in place of the PFERR_RSVD_MASK bit; * this bit will always be zero in pfec, but it will be one in index * if SMAP checks are being disabled. */ u64 implicit_access = access & PFERR_IMPLICIT_ACCESS; bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC; int index = (pfec | (not_smap ? PFERR_RSVD_MASK : 0)) >> 1; u32 errcode = PFERR_PRESENT_MASK; bool fault; kvm_mmu_refresh_passthrough_bits(vcpu, mmu); fault = (mmu->permissions[index] >> pte_access) & 1; WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK)); if (unlikely(mmu->pkru_mask)) { u32 pkru_bits, offset; /* * PKRU defines 32 bits, there are 16 domains and 2 * attribute bits per domain in pkru. pte_pkey is the * index of the protection domain, so pte_pkey * 2 is * is the index of the first bit for the domain. */ pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3; /* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */ offset = (pfec & ~1) | ((pte_access & PT_USER_MASK) ? PFERR_RSVD_MASK : 0); pkru_bits &= mmu->pkru_mask >> offset; errcode |= -pkru_bits & PFERR_PK_MASK; fault |= (pkru_bits != 0); } return -(u32)fault & errcode; } bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma); static inline bool kvm_mmu_honors_guest_mtrrs(struct kvm *kvm) { return __kvm_mmu_honors_guest_mtrrs(kvm_arch_has_noncoherent_dma(kvm)); } int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); static inline bool kvm_shadow_root_allocated(struct kvm *kvm) { /* * Read shadow_root_allocated before related pointers. Hence, threads * reading shadow_root_allocated in any lock context are guaranteed to * see the pointers. Pairs with smp_store_release in * mmu_first_shadow_root_alloc. */ return smp_load_acquire(&kvm->arch.shadow_root_allocated); } #ifdef CONFIG_X86_64 extern bool tdp_mmu_enabled; #else #define tdp_mmu_enabled false #endif static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) { return !tdp_mmu_enabled || kvm_shadow_root_allocated(kvm); } static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) { /* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */ return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); } static inline unsigned long __kvm_mmu_slot_lpages(struct kvm_memory_slot *slot, unsigned long npages, int level) { return gfn_to_index(slot->base_gfn + npages - 1, slot->base_gfn, level) + 1; } static inline unsigned long kvm_mmu_slot_lpages(struct kvm_memory_slot *slot, int level) { return __kvm_mmu_slot_lpages(slot, slot->npages, level); } static inline void kvm_update_page_stats(struct kvm *kvm, int level, int count) { atomic64_add(count, &kvm->stat.pages[level - 1]); } gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u64 access, struct x86_exception *exception); static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gpa_t gpa, u64 access, struct x86_exception *exception) { if (mmu != &vcpu->arch.nested_mmu) return gpa; return translate_nested_gpa(vcpu, gpa, access, exception); } #endif |
| 21 8 2 2 6 6 6 7 7 1 129 96 62 124 7 5 2 5 2 3 4 2 5 3 4 3 4 7 7 7 131 131 49 49 6 9 7 7 10 5 4 13 10 7 2 23 36 1 1 1 1 38 38 38 38 1 1 34 2 33 3 36 36 36 36 36 1 34 3 42 36 3 4 16 42 3 42 42 16 9 1 25 23 3 44 10 52 42 10 4 51 51 22 22 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2012-2013 Samsung Electronics Co., Ltd. */ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/module.h> #include <linux/init.h> #include <linux/time.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/statfs.h> #include <linux/seq_file.h> #include <linux/blkdev.h> #include <linux/fs_struct.h> #include <linux/iversion.h> #include <linux/nls.h> #include <linux/buffer_head.h> #include <linux/magic.h> #include "exfat_raw.h" #include "exfat_fs.h" static char exfat_default_iocharset[] = CONFIG_EXFAT_DEFAULT_IOCHARSET; static struct kmem_cache *exfat_inode_cachep; static void exfat_free_iocharset(struct exfat_sb_info *sbi) { if (sbi->options.iocharset != exfat_default_iocharset) kfree(sbi->options.iocharset); } static void exfat_put_super(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); mutex_lock(&sbi->s_lock); exfat_free_bitmap(sbi); brelse(sbi->boot_bh); mutex_unlock(&sbi->s_lock); } static int exfat_sync_fs(struct super_block *sb, int wait) { struct exfat_sb_info *sbi = EXFAT_SB(sb); int err = 0; if (!wait) return 0; /* If there are some dirty buffers in the bdev inode */ mutex_lock(&sbi->s_lock); sync_blockdev(sb->s_bdev); if (exfat_clear_volume_dirty(sb)) err = -EIO; mutex_unlock(&sbi->s_lock); return err; } static int exfat_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); unsigned long long id = huge_encode_dev(sb->s_bdev->bd_dev); if (sbi->used_clusters == EXFAT_CLUSTERS_UNTRACKED) { mutex_lock(&sbi->s_lock); if (exfat_count_used_clusters(sb, &sbi->used_clusters)) { mutex_unlock(&sbi->s_lock); return -EIO; } mutex_unlock(&sbi->s_lock); } buf->f_type = sb->s_magic; buf->f_bsize = sbi->cluster_size; buf->f_blocks = sbi->num_clusters - 2; /* clu 0 & 1 */ buf->f_bfree = buf->f_blocks - sbi->used_clusters; buf->f_bavail = buf->f_bfree; buf->f_fsid = u64_to_fsid(id); /* Unicode utf16 255 characters */ buf->f_namelen = EXFAT_MAX_FILE_LEN * NLS_MAX_CHARSET_SIZE; return 0; } static int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flags) { struct exfat_sb_info *sbi = EXFAT_SB(sb); struct boot_sector *p_boot = (struct boot_sector *)sbi->boot_bh->b_data; /* retain persistent-flags */ new_flags |= sbi->vol_flags_persistent; /* flags are not changed */ if (sbi->vol_flags == new_flags) return 0; sbi->vol_flags = new_flags; /* skip updating volume dirty flag, * if this volume has been mounted with read-only */ if (sb_rdonly(sb)) return 0; p_boot->vol_flags = cpu_to_le16(new_flags); set_buffer_uptodate(sbi->boot_bh); mark_buffer_dirty(sbi->boot_bh); __sync_dirty_buffer(sbi->boot_bh, REQ_SYNC | REQ_FUA | REQ_PREFLUSH); return 0; } int exfat_set_volume_dirty(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); return exfat_set_vol_flags(sb, sbi->vol_flags | VOLUME_DIRTY); } int exfat_clear_volume_dirty(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); return exfat_set_vol_flags(sb, sbi->vol_flags & ~VOLUME_DIRTY); } static int exfat_show_options(struct seq_file *m, struct dentry *root) { struct super_block *sb = root->d_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_mount_options *opts = &sbi->options; /* Show partition info */ if (!uid_eq(opts->fs_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, opts->fs_uid)); if (!gid_eq(opts->fs_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, opts->fs_gid)); seq_printf(m, ",fmask=%04o,dmask=%04o", opts->fs_fmask, opts->fs_dmask); if (opts->allow_utime) seq_printf(m, ",allow_utime=%04o", opts->allow_utime); if (opts->utf8) seq_puts(m, ",iocharset=utf8"); else if (sbi->nls_io) seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); if (opts->errors == EXFAT_ERRORS_CONT) seq_puts(m, ",errors=continue"); else if (opts->errors == EXFAT_ERRORS_PANIC) seq_puts(m, ",errors=panic"); else seq_puts(m, ",errors=remount-ro"); if (opts->discard) seq_puts(m, ",discard"); if (opts->keep_last_dots) seq_puts(m, ",keep_last_dots"); if (opts->sys_tz) seq_puts(m, ",sys_tz"); else if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); if (opts->zero_size_dir) seq_puts(m, ",zero_size_dir"); return 0; } static struct inode *exfat_alloc_inode(struct super_block *sb) { struct exfat_inode_info *ei; ei = alloc_inode_sb(sb, exfat_inode_cachep, GFP_NOFS); if (!ei) return NULL; init_rwsem(&ei->truncate_lock); return &ei->vfs_inode; } static void exfat_free_inode(struct inode *inode) { kmem_cache_free(exfat_inode_cachep, EXFAT_I(inode)); } static const struct super_operations exfat_sops = { .alloc_inode = exfat_alloc_inode, .free_inode = exfat_free_inode, .write_inode = exfat_write_inode, .evict_inode = exfat_evict_inode, .put_super = exfat_put_super, .sync_fs = exfat_sync_fs, .statfs = exfat_statfs, .show_options = exfat_show_options, }; enum { Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, Opt_charset, Opt_errors, Opt_discard, Opt_keep_last_dots, Opt_sys_tz, Opt_time_offset, Opt_zero_size_dir, /* Deprecated options */ Opt_utf8, Opt_debug, Opt_namecase, Opt_codepage, }; static const struct constant_table exfat_param_enums[] = { { "continue", EXFAT_ERRORS_CONT }, { "panic", EXFAT_ERRORS_PANIC }, { "remount-ro", EXFAT_ERRORS_RO }, {} }; static const struct fs_parameter_spec exfat_parameters[] = { fsparam_u32("uid", Opt_uid), fsparam_u32("gid", Opt_gid), fsparam_u32oct("umask", Opt_umask), fsparam_u32oct("dmask", Opt_dmask), fsparam_u32oct("fmask", Opt_fmask), fsparam_u32oct("allow_utime", Opt_allow_utime), fsparam_string("iocharset", Opt_charset), fsparam_enum("errors", Opt_errors, exfat_param_enums), fsparam_flag("discard", Opt_discard), fsparam_flag("keep_last_dots", Opt_keep_last_dots), fsparam_flag("sys_tz", Opt_sys_tz), fsparam_s32("time_offset", Opt_time_offset), fsparam_flag("zero_size_dir", Opt_zero_size_dir), __fsparam(NULL, "utf8", Opt_utf8, fs_param_deprecated, NULL), __fsparam(NULL, "debug", Opt_debug, fs_param_deprecated, NULL), __fsparam(fs_param_is_u32, "namecase", Opt_namecase, fs_param_deprecated, NULL), __fsparam(fs_param_is_u32, "codepage", Opt_codepage, fs_param_deprecated, NULL), {} }; static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct exfat_sb_info *sbi = fc->s_fs_info; struct exfat_mount_options *opts = &sbi->options; struct fs_parse_result result; int opt; opt = fs_parse(fc, exfat_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_uid: opts->fs_uid = make_kuid(current_user_ns(), result.uint_32); break; case Opt_gid: opts->fs_gid = make_kgid(current_user_ns(), result.uint_32); break; case Opt_umask: opts->fs_fmask = result.uint_32; opts->fs_dmask = result.uint_32; break; case Opt_dmask: opts->fs_dmask = result.uint_32; break; case Opt_fmask: opts->fs_fmask = result.uint_32; break; case Opt_allow_utime: opts->allow_utime = result.uint_32 & 0022; break; case Opt_charset: exfat_free_iocharset(sbi); opts->iocharset = param->string; param->string = NULL; break; case Opt_errors: opts->errors = result.uint_32; break; case Opt_discard: opts->discard = 1; break; case Opt_keep_last_dots: opts->keep_last_dots = 1; break; case Opt_sys_tz: opts->sys_tz = 1; break; case Opt_time_offset: /* * Make the limit 24 just in case someone invents something * unusual. */ if (result.int_32 < -24 * 60 || result.int_32 > 24 * 60) return -EINVAL; opts->time_offset = result.int_32; break; case Opt_zero_size_dir: opts->zero_size_dir = true; break; case Opt_utf8: case Opt_debug: case Opt_namecase: case Opt_codepage: break; default: return -EINVAL; } return 0; } static void exfat_hash_init(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); int i; spin_lock_init(&sbi->inode_hash_lock); for (i = 0; i < EXFAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); } static int exfat_read_root(struct inode *inode) { struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_chain cdir; int num_subdirs, num_clu = 0; exfat_chain_set(&ei->dir, sbi->root_dir, 0, ALLOC_FAT_CHAIN); ei->entry = -1; ei->start_clu = sbi->root_dir; ei->flags = ALLOC_FAT_CHAIN; ei->type = TYPE_DIR; ei->version = 0; ei->hint_bmap.off = EXFAT_EOF_CLUSTER; ei->hint_stat.eidx = 0; ei->hint_stat.clu = sbi->root_dir; ei->hint_femp.eidx = EXFAT_HINT_NONE; exfat_chain_set(&cdir, sbi->root_dir, 0, ALLOC_FAT_CHAIN); if (exfat_count_num_clusters(sb, &cdir, &num_clu)) return -EIO; i_size_write(inode, num_clu << sbi->cluster_size_bits); num_subdirs = exfat_count_dir_entries(sb, &cdir); if (num_subdirs < 0) return -EIO; set_nlink(inode, num_subdirs + EXFAT_MIN_SUBDIR); inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = 0; inode->i_mode = exfat_make_mode(sbi, EXFAT_ATTR_SUBDIR, 0777); inode->i_op = &exfat_dir_inode_operations; inode->i_fop = &exfat_dir_operations; inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; ei->i_pos = ((loff_t)sbi->root_dir << 32) | 0xffffffff; ei->i_size_aligned = i_size_read(inode); ei->i_size_ondisk = i_size_read(inode); exfat_save_attr(inode, EXFAT_ATTR_SUBDIR); ei->i_crtime = simple_inode_init_ts(inode); exfat_truncate_inode_atime(inode); return 0; } static int exfat_calibrate_blocksize(struct super_block *sb, int logical_sect) { struct exfat_sb_info *sbi = EXFAT_SB(sb); if (!is_power_of_2(logical_sect)) { exfat_err(sb, "bogus logical sector size %u", logical_sect); return -EIO; } if (logical_sect < sb->s_blocksize) { exfat_err(sb, "logical sector size too small for device (logical sector size = %u)", logical_sect); return -EIO; } if (logical_sect > sb->s_blocksize) { brelse(sbi->boot_bh); sbi->boot_bh = NULL; if (!sb_set_blocksize(sb, logical_sect)) { exfat_err(sb, "unable to set blocksize %u", logical_sect); return -EIO; } sbi->boot_bh = sb_bread(sb, 0); if (!sbi->boot_bh) { exfat_err(sb, "unable to read boot sector (logical sector size = %lu)", sb->s_blocksize); return -EIO; } } return 0; } static int exfat_read_boot_sector(struct super_block *sb) { struct boot_sector *p_boot; struct exfat_sb_info *sbi = EXFAT_SB(sb); /* set block size to read super block */ sb_min_blocksize(sb, 512); /* read boot sector */ sbi->boot_bh = sb_bread(sb, 0); if (!sbi->boot_bh) { exfat_err(sb, "unable to read boot sector"); return -EIO; } p_boot = (struct boot_sector *)sbi->boot_bh->b_data; /* check the validity of BOOT */ if (le16_to_cpu((p_boot->signature)) != BOOT_SIGNATURE) { exfat_err(sb, "invalid boot record signature"); return -EINVAL; } if (memcmp(p_boot->fs_name, STR_EXFAT, BOOTSEC_FS_NAME_LEN)) { exfat_err(sb, "invalid fs_name"); /* fs_name may unprintable */ return -EINVAL; } /* * must_be_zero field must be filled with zero to prevent mounting * from FAT volume. */ if (memchr_inv(p_boot->must_be_zero, 0, sizeof(p_boot->must_be_zero))) return -EINVAL; if (p_boot->num_fats != 1 && p_boot->num_fats != 2) { exfat_err(sb, "bogus number of FAT structure"); return -EINVAL; } /* * sect_size_bits could be at least 9 and at most 12. */ if (p_boot->sect_size_bits < EXFAT_MIN_SECT_SIZE_BITS || p_boot->sect_size_bits > EXFAT_MAX_SECT_SIZE_BITS) { exfat_err(sb, "bogus sector size bits : %u", p_boot->sect_size_bits); return -EINVAL; } /* * sect_per_clus_bits could be at least 0 and at most 25 - sect_size_bits. */ if (p_boot->sect_per_clus_bits > EXFAT_MAX_SECT_PER_CLUS_BITS(p_boot)) { exfat_err(sb, "bogus sectors bits per cluster : %u", p_boot->sect_per_clus_bits); return -EINVAL; } sbi->sect_per_clus = 1 << p_boot->sect_per_clus_bits; sbi->sect_per_clus_bits = p_boot->sect_per_clus_bits; sbi->cluster_size_bits = p_boot->sect_per_clus_bits + p_boot->sect_size_bits; sbi->cluster_size = 1 << sbi->cluster_size_bits; sbi->num_FAT_sectors = le32_to_cpu(p_boot->fat_length); sbi->FAT1_start_sector = le32_to_cpu(p_boot->fat_offset); sbi->FAT2_start_sector = le32_to_cpu(p_boot->fat_offset); if (p_boot->num_fats == 2) sbi->FAT2_start_sector += sbi->num_FAT_sectors; sbi->data_start_sector = le32_to_cpu(p_boot->clu_offset); sbi->num_sectors = le64_to_cpu(p_boot->vol_length); /* because the cluster index starts with 2 */ sbi->num_clusters = le32_to_cpu(p_boot->clu_count) + EXFAT_RESERVED_CLUSTERS; sbi->root_dir = le32_to_cpu(p_boot->root_cluster); sbi->dentries_per_clu = 1 << (sbi->cluster_size_bits - DENTRY_SIZE_BITS); sbi->vol_flags = le16_to_cpu(p_boot->vol_flags); sbi->vol_flags_persistent = sbi->vol_flags & (VOLUME_DIRTY | MEDIA_FAILURE); sbi->clu_srch_ptr = EXFAT_FIRST_CLUSTER; sbi->used_clusters = EXFAT_CLUSTERS_UNTRACKED; /* check consistencies */ if ((u64)sbi->num_FAT_sectors << p_boot->sect_size_bits < (u64)sbi->num_clusters * 4) { exfat_err(sb, "bogus fat length"); return -EINVAL; } if (sbi->data_start_sector < (u64)sbi->FAT1_start_sector + (u64)sbi->num_FAT_sectors * p_boot->num_fats) { exfat_err(sb, "bogus data start sector"); return -EINVAL; } if (sbi->vol_flags & VOLUME_DIRTY) exfat_warn(sb, "Volume was not properly unmounted. Some data may be corrupt. Please run fsck."); if (sbi->vol_flags & MEDIA_FAILURE) exfat_warn(sb, "Medium has reported failures. Some data may be lost."); /* exFAT file size is limited by a disk volume size */ sb->s_maxbytes = (u64)(sbi->num_clusters - EXFAT_RESERVED_CLUSTERS) << sbi->cluster_size_bits; /* check logical sector size */ if (exfat_calibrate_blocksize(sb, 1 << p_boot->sect_size_bits)) return -EIO; return 0; } static int exfat_verify_boot_region(struct super_block *sb) { struct buffer_head *bh = NULL; u32 chksum = 0; __le32 *p_sig, *p_chksum; int sn, i; /* read boot sector sub-regions */ for (sn = 0; sn < 11; sn++) { bh = sb_bread(sb, sn); if (!bh) return -EIO; if (sn != 0 && sn <= 8) { /* extended boot sector sub-regions */ p_sig = (__le32 *)&bh->b_data[sb->s_blocksize - 4]; if (le32_to_cpu(*p_sig) != EXBOOT_SIGNATURE) exfat_warn(sb, "Invalid exboot-signature(sector = %d): 0x%08x", sn, le32_to_cpu(*p_sig)); } chksum = exfat_calc_chksum32(bh->b_data, sb->s_blocksize, chksum, sn ? CS_DEFAULT : CS_BOOT_SECTOR); brelse(bh); } /* boot checksum sub-regions */ bh = sb_bread(sb, sn); if (!bh) return -EIO; for (i = 0; i < sb->s_blocksize; i += sizeof(u32)) { p_chksum = (__le32 *)&bh->b_data[i]; if (le32_to_cpu(*p_chksum) != chksum) { exfat_err(sb, "Invalid boot checksum (boot checksum : 0x%08x, checksum : 0x%08x)", le32_to_cpu(*p_chksum), chksum); brelse(bh); return -EINVAL; } } brelse(bh); return 0; } /* mount the file system volume */ static int __exfat_fill_super(struct super_block *sb) { int ret; struct exfat_sb_info *sbi = EXFAT_SB(sb); ret = exfat_read_boot_sector(sb); if (ret) { exfat_err(sb, "failed to read boot sector"); goto free_bh; } ret = exfat_verify_boot_region(sb); if (ret) { exfat_err(sb, "invalid boot region"); goto free_bh; } ret = exfat_create_upcase_table(sb); if (ret) { exfat_err(sb, "failed to load upcase table"); goto free_bh; } ret = exfat_load_bitmap(sb); if (ret) { exfat_err(sb, "failed to load alloc-bitmap"); goto free_bh; } ret = exfat_count_used_clusters(sb, &sbi->used_clusters); if (ret) { exfat_err(sb, "failed to scan clusters"); goto free_alloc_bitmap; } return 0; free_alloc_bitmap: exfat_free_bitmap(sbi); free_bh: brelse(sbi->boot_bh); return ret; } static int exfat_fill_super(struct super_block *sb, struct fs_context *fc) { struct exfat_sb_info *sbi = sb->s_fs_info; struct exfat_mount_options *opts = &sbi->options; struct inode *root_inode; int err; if (opts->allow_utime == (unsigned short)-1) opts->allow_utime = ~opts->fs_dmask & 0022; if (opts->discard && !bdev_max_discard_sectors(sb->s_bdev)) { exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard"); opts->discard = 0; } sb->s_flags |= SB_NODIRATIME; sb->s_magic = EXFAT_SUPER_MAGIC; sb->s_op = &exfat_sops; sb->s_time_gran = 10 * NSEC_PER_MSEC; sb->s_time_min = EXFAT_MIN_TIMESTAMP_SECS; sb->s_time_max = EXFAT_MAX_TIMESTAMP_SECS; err = __exfat_fill_super(sb); if (err) { exfat_err(sb, "failed to recognize exfat type"); goto check_nls_io; } /* set up enough so that it can read an inode */ exfat_hash_init(sb); if (!strcmp(sbi->options.iocharset, "utf8")) opts->utf8 = 1; else { sbi->nls_io = load_nls(sbi->options.iocharset); if (!sbi->nls_io) { exfat_err(sb, "IO charset %s not found", sbi->options.iocharset); err = -EINVAL; goto free_table; } } if (sbi->options.utf8) sb->s_d_op = &exfat_utf8_dentry_ops; else sb->s_d_op = &exfat_dentry_ops; root_inode = new_inode(sb); if (!root_inode) { exfat_err(sb, "failed to allocate root inode"); err = -ENOMEM; goto free_table; } root_inode->i_ino = EXFAT_ROOT_INO; inode_set_iversion(root_inode, 1); err = exfat_read_root(root_inode); if (err) { exfat_err(sb, "failed to initialize root inode"); goto put_inode; } exfat_hash_inode(root_inode, EXFAT_I(root_inode)->i_pos); insert_inode_hash(root_inode); sb->s_root = d_make_root(root_inode); if (!sb->s_root) { exfat_err(sb, "failed to get the root dentry"); err = -ENOMEM; goto free_table; } return 0; put_inode: iput(root_inode); sb->s_root = NULL; free_table: exfat_free_bitmap(sbi); brelse(sbi->boot_bh); check_nls_io: return err; } static int exfat_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, exfat_fill_super); } static void exfat_free_sbi(struct exfat_sb_info *sbi) { exfat_free_iocharset(sbi); kfree(sbi); } static void exfat_free(struct fs_context *fc) { struct exfat_sb_info *sbi = fc->s_fs_info; if (sbi) exfat_free_sbi(sbi); } static int exfat_reconfigure(struct fs_context *fc) { fc->sb_flags |= SB_NODIRATIME; /* volume flag will be updated in exfat_sync_fs */ sync_filesystem(fc->root->d_sb); return 0; } static const struct fs_context_operations exfat_context_ops = { .parse_param = exfat_parse_param, .get_tree = exfat_get_tree, .free = exfat_free, .reconfigure = exfat_reconfigure, }; static int exfat_init_fs_context(struct fs_context *fc) { struct exfat_sb_info *sbi; sbi = kzalloc(sizeof(struct exfat_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; mutex_init(&sbi->s_lock); mutex_init(&sbi->bitmap_lock); ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); sbi->options.fs_uid = current_uid(); sbi->options.fs_gid = current_gid(); sbi->options.fs_fmask = current->fs->umask; sbi->options.fs_dmask = current->fs->umask; sbi->options.allow_utime = -1; sbi->options.iocharset = exfat_default_iocharset; sbi->options.errors = EXFAT_ERRORS_RO; fc->s_fs_info = sbi; fc->ops = &exfat_context_ops; return 0; } static void delayed_free(struct rcu_head *p) { struct exfat_sb_info *sbi = container_of(p, struct exfat_sb_info, rcu); unload_nls(sbi->nls_io); exfat_free_upcase_table(sbi); exfat_free_sbi(sbi); } static void exfat_kill_sb(struct super_block *sb) { struct exfat_sb_info *sbi = sb->s_fs_info; kill_block_super(sb); if (sbi) call_rcu(&sbi->rcu, delayed_free); } static struct file_system_type exfat_fs_type = { .owner = THIS_MODULE, .name = "exfat", .init_fs_context = exfat_init_fs_context, .parameters = exfat_parameters, .kill_sb = exfat_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; static void exfat_inode_init_once(void *foo) { struct exfat_inode_info *ei = (struct exfat_inode_info *)foo; spin_lock_init(&ei->cache_lru_lock); ei->nr_caches = 0; ei->cache_valid_id = EXFAT_CACHE_VALID + 1; INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_hash_fat); inode_init_once(&ei->vfs_inode); } static int __init init_exfat_fs(void) { int err; err = exfat_cache_init(); if (err) return err; exfat_inode_cachep = kmem_cache_create("exfat_inode_cache", sizeof(struct exfat_inode_info), 0, SLAB_RECLAIM_ACCOUNT, exfat_inode_init_once); if (!exfat_inode_cachep) { err = -ENOMEM; goto shutdown_cache; } err = register_filesystem(&exfat_fs_type); if (err) goto destroy_cache; return 0; destroy_cache: kmem_cache_destroy(exfat_inode_cachep); shutdown_cache: exfat_cache_shutdown(); return err; } static void __exit exit_exfat_fs(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(exfat_inode_cachep); unregister_filesystem(&exfat_fs_type); exfat_cache_shutdown(); } module_init(init_exfat_fs); module_exit(exit_exfat_fs); MODULE_ALIAS_FS("exfat"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("exFAT filesystem support"); MODULE_AUTHOR("Samsung Electronics Co., Ltd."); |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org> * (C) 2011 Intra2net AG <https://www.intra2net.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/nfnetlink_acct.h> #include <linux/netfilter/xt_nfacct.h> MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("Xtables: match for the extended accounting infrastructure"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_nfacct"); MODULE_ALIAS("ip6t_nfacct"); static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) { int overquota; const struct xt_nfacct_match_info *info = par->targinfo; nfnl_acct_update(skb, info->nfacct); overquota = nfnl_acct_overquota(xt_net(par), info->nfacct); return overquota != NFACCT_UNDERQUOTA; } static int nfacct_mt_checkentry(const struct xt_mtchk_param *par) { struct xt_nfacct_match_info *info = par->matchinfo; struct nf_acct *nfacct; nfacct = nfnl_acct_find_get(par->net, info->name); if (nfacct == NULL) { pr_info_ratelimited("accounting object `%s' does not exists\n", info->name); return -ENOENT; } info->nfacct = nfacct; return 0; } static void nfacct_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_nfacct_match_info *info = par->matchinfo; nfnl_acct_put(info->nfacct); } static struct xt_match nfacct_mt_reg[] __read_mostly = { { .name = "nfacct", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = nfacct_mt_checkentry, .match = nfacct_mt, .destroy = nfacct_mt_destroy, .matchsize = sizeof(struct xt_nfacct_match_info), .usersize = offsetof(struct xt_nfacct_match_info, nfacct), .me = THIS_MODULE, }, { .name = "nfacct", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = nfacct_mt_checkentry, .match = nfacct_mt, .destroy = nfacct_mt_destroy, .matchsize = sizeof(struct xt_nfacct_match_info_v1), .usersize = offsetof(struct xt_nfacct_match_info_v1, nfacct), .me = THIS_MODULE, }, }; static int __init nfacct_mt_init(void) { return xt_register_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg)); } static void __exit nfacct_mt_exit(void) { xt_unregister_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg)); } module_init(nfacct_mt_init); module_exit(nfacct_mt_exit); |
| 5 5 5 1 1 4 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * DES & Triple DES EDE Cipher Algorithms. * * Copyright (c) 2005 Dag Arne Osvik <da@osvik.no> */ #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/crypto.h> #include <linux/errno.h> #include <linux/fips.h> #include <linux/init.h> #include <linux/module.h> #include <linux/string.h> #include <linux/types.h> #include <asm/unaligned.h> #include <crypto/des.h> #include <crypto/internal/des.h> #define ROL(x, r) ((x) = rol32((x), (r))) #define ROR(x, r) ((x) = ror32((x), (r))) /* Lookup tables for key expansion */ static const u8 pc1[256] = { 0x00, 0x00, 0x40, 0x04, 0x10, 0x10, 0x50, 0x14, 0x04, 0x40, 0x44, 0x44, 0x14, 0x50, 0x54, 0x54, 0x02, 0x02, 0x42, 0x06, 0x12, 0x12, 0x52, 0x16, 0x06, 0x42, 0x46, 0x46, 0x16, 0x52, 0x56, 0x56, 0x80, 0x08, 0xc0, 0x0c, 0x90, 0x18, 0xd0, 0x1c, 0x84, 0x48, 0xc4, 0x4c, 0x94, 0x58, 0xd4, 0x5c, 0x82, 0x0a, 0xc2, 0x0e, 0x92, 0x1a, 0xd2, 0x1e, 0x86, 0x4a, 0xc6, 0x4e, 0x96, 0x5a, 0xd6, 0x5e, 0x20, 0x20, 0x60, 0x24, 0x30, 0x30, 0x70, 0x34, 0x24, 0x60, 0x64, 0x64, 0x34, 0x70, 0x74, 0x74, 0x22, 0x22, 0x62, 0x26, 0x32, 0x32, 0x72, 0x36, 0x26, 0x62, 0x66, 0x66, 0x36, 0x72, 0x76, 0x76, 0xa0, 0x28, 0xe0, 0x2c, 0xb0, 0x38, 0xf0, 0x3c, 0xa4, 0x68, 0xe4, 0x6c, 0xb4, 0x78, 0xf4, 0x7c, 0xa2, 0x2a, 0xe2, 0x2e, 0xb2, 0x3a, 0xf2, 0x3e, 0xa6, 0x6a, 0xe6, 0x6e, 0xb6, 0x7a, 0xf6, 0x7e, 0x08, 0x80, 0x48, 0x84, 0x18, 0x90, 0x58, 0x94, 0x0c, 0xc0, 0x4c, 0xc4, 0x1c, 0xd0, 0x5c, 0xd4, 0x0a, 0x82, 0x4a, 0x86, 0x1a, 0x92, 0x5a, 0x96, 0x0e, 0xc2, 0x4e, 0xc6, 0x1e, 0xd2, 0x5e, 0xd6, 0x88, 0x88, 0xc8, 0x8c, 0x98, 0x98, 0xd8, 0x9c, 0x8c, 0xc8, 0xcc, 0xcc, 0x9c, 0xd8, 0xdc, 0xdc, 0x8a, 0x8a, 0xca, 0x8e, 0x9a, 0x9a, 0xda, 0x9e, 0x8e, 0xca, 0xce, 0xce, 0x9e, 0xda, 0xde, 0xde, 0x28, 0xa0, 0x68, 0xa4, 0x38, 0xb0, 0x78, 0xb4, 0x2c, 0xe0, 0x6c, 0xe4, 0x3c, 0xf0, 0x7c, 0xf4, 0x2a, 0xa2, 0x6a, 0xa6, 0x3a, 0xb2, 0x7a, 0xb6, 0x2e, 0xe2, 0x6e, 0xe6, 0x3e, 0xf2, 0x7e, 0xf6, 0xa8, 0xa8, 0xe8, 0xac, 0xb8, 0xb8, 0xf8, 0xbc, 0xac, 0xe8, 0xec, 0xec, 0xbc, 0xf8, 0xfc, 0xfc, 0xaa, 0xaa, 0xea, 0xae, 0xba, 0xba, 0xfa, 0xbe, 0xae, 0xea, 0xee, 0xee, 0xbe, 0xfa, 0xfe, 0xfe }; static const u8 rs[256] = { 0x00, 0x00, 0x80, 0x80, 0x02, 0x02, 0x82, 0x82, 0x04, 0x04, 0x84, 0x84, 0x06, 0x06, 0x86, 0x86, 0x08, 0x08, 0x88, 0x88, 0x0a, 0x0a, 0x8a, 0x8a, 0x0c, 0x0c, 0x8c, 0x8c, 0x0e, 0x0e, 0x8e, 0x8e, 0x10, 0x10, 0x90, 0x90, 0x12, 0x12, 0x92, 0x92, 0x14, 0x14, 0x94, 0x94, 0x16, 0x16, 0x96, 0x96, 0x18, 0x18, 0x98, 0x98, 0x1a, 0x1a, 0x9a, 0x9a, 0x1c, 0x1c, 0x9c, 0x9c, 0x1e, 0x1e, 0x9e, 0x9e, 0x20, 0x20, 0xa0, 0xa0, 0x22, 0x22, 0xa2, 0xa2, 0x24, 0x24, 0xa4, 0xa4, 0x26, 0x26, 0xa6, 0xa6, 0x28, 0x28, 0xa8, 0xa8, 0x2a, 0x2a, 0xaa, 0xaa, 0x2c, 0x2c, 0xac, 0xac, 0x2e, 0x2e, 0xae, 0xae, 0x30, 0x30, 0xb0, 0xb0, 0x32, 0x32, 0xb2, 0xb2, 0x34, 0x34, 0xb4, 0xb4, 0x36, 0x36, 0xb6, 0xb6, 0x38, 0x38, 0xb8, 0xb8, 0x3a, 0x3a, 0xba, 0xba, 0x3c, 0x3c, 0xbc, 0xbc, 0x3e, 0x3e, 0xbe, 0xbe, 0x40, 0x40, 0xc0, 0xc0, 0x42, 0x42, 0xc2, 0xc2, 0x44, 0x44, 0xc4, 0xc4, 0x46, 0x46, 0xc6, 0xc6, 0x48, 0x48, 0xc8, 0xc8, 0x4a, 0x4a, 0xca, 0xca, 0x4c, 0x4c, 0xcc, 0xcc, 0x4e, 0x4e, 0xce, 0xce, 0x50, 0x50, 0xd0, 0xd0, 0x52, 0x52, 0xd2, 0xd2, 0x54, 0x54, 0xd4, 0xd4, 0x56, 0x56, 0xd6, 0xd6, 0x58, 0x58, 0xd8, 0xd8, 0x5a, 0x5a, 0xda, 0xda, 0x5c, 0x5c, 0xdc, 0xdc, 0x5e, 0x5e, 0xde, 0xde, 0x60, 0x60, 0xe0, 0xe0, 0x62, 0x62, 0xe2, 0xe2, 0x64, 0x64, 0xe4, 0xe4, 0x66, 0x66, 0xe6, 0xe6, 0x68, 0x68, 0xe8, 0xe8, 0x6a, 0x6a, 0xea, 0xea, 0x6c, 0x6c, 0xec, 0xec, 0x6e, 0x6e, 0xee, 0xee, 0x70, 0x70, 0xf0, 0xf0, 0x72, 0x72, 0xf2, 0xf2, 0x74, 0x74, 0xf4, 0xf4, 0x76, 0x76, 0xf6, 0xf6, 0x78, 0x78, 0xf8, 0xf8, 0x7a, 0x7a, 0xfa, 0xfa, 0x7c, 0x7c, 0xfc, 0xfc, 0x7e, 0x7e, 0xfe, 0xfe }; static const u32 pc2[1024] = { 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00040000, 0x00000000, 0x04000000, 0x00100000, 0x00400000, 0x00000008, 0x00000800, 0x40000000, 0x00440000, 0x00000008, 0x04000800, 0x40100000, 0x00000400, 0x00000020, 0x08000000, 0x00000100, 0x00040400, 0x00000020, 0x0c000000, 0x00100100, 0x00400400, 0x00000028, 0x08000800, 0x40000100, 0x00440400, 0x00000028, 0x0c000800, 0x40100100, 0x80000000, 0x00000010, 0x00000000, 0x00800000, 0x80040000, 0x00000010, 0x04000000, 0x00900000, 0x80400000, 0x00000018, 0x00000800, 0x40800000, 0x80440000, 0x00000018, 0x04000800, 0x40900000, 0x80000400, 0x00000030, 0x08000000, 0x00800100, 0x80040400, 0x00000030, 0x0c000000, 0x00900100, 0x80400400, 0x00000038, 0x08000800, 0x40800100, 0x80440400, 0x00000038, 0x0c000800, 0x40900100, 0x10000000, 0x00000000, 0x00200000, 0x00001000, 0x10040000, 0x00000000, 0x04200000, 0x00101000, 0x10400000, 0x00000008, 0x00200800, 0x40001000, 0x10440000, 0x00000008, 0x04200800, 0x40101000, 0x10000400, 0x00000020, 0x08200000, 0x00001100, 0x10040400, 0x00000020, 0x0c200000, 0x00101100, 0x10400400, 0x00000028, 0x08200800, 0x40001100, 0x10440400, 0x00000028, 0x0c200800, 0x40101100, 0x90000000, 0x00000010, 0x00200000, 0x00801000, 0x90040000, 0x00000010, 0x04200000, 0x00901000, 0x90400000, 0x00000018, 0x00200800, 0x40801000, 0x90440000, 0x00000018, 0x04200800, 0x40901000, 0x90000400, 0x00000030, 0x08200000, 0x00801100, 0x90040400, 0x00000030, 0x0c200000, 0x00901100, 0x90400400, 0x00000038, 0x08200800, 0x40801100, 0x90440400, 0x00000038, 0x0c200800, 0x40901100, 0x00000200, 0x00080000, 0x00000000, 0x00000004, 0x00040200, 0x00080000, 0x04000000, 0x00100004, 0x00400200, 0x00080008, 0x00000800, 0x40000004, 0x00440200, 0x00080008, 0x04000800, 0x40100004, 0x00000600, 0x00080020, 0x08000000, 0x00000104, 0x00040600, 0x00080020, 0x0c000000, 0x00100104, 0x00400600, 0x00080028, 0x08000800, 0x40000104, 0x00440600, 0x00080028, 0x0c000800, 0x40100104, 0x80000200, 0x00080010, 0x00000000, 0x00800004, 0x80040200, 0x00080010, 0x04000000, 0x00900004, 0x80400200, 0x00080018, 0x00000800, 0x40800004, 0x80440200, 0x00080018, 0x04000800, 0x40900004, 0x80000600, 0x00080030, 0x08000000, 0x00800104, 0x80040600, 0x00080030, 0x0c000000, 0x00900104, 0x80400600, 0x00080038, 0x08000800, 0x40800104, 0x80440600, 0x00080038, 0x0c000800, 0x40900104, 0x10000200, 0x00080000, 0x00200000, 0x00001004, 0x10040200, 0x00080000, 0x04200000, 0x00101004, 0x10400200, 0x00080008, 0x00200800, 0x40001004, 0x10440200, 0x00080008, 0x04200800, 0x40101004, 0x10000600, 0x00080020, 0x08200000, 0x00001104, 0x10040600, 0x00080020, 0x0c200000, 0x00101104, 0x10400600, 0x00080028, 0x08200800, 0x40001104, 0x10440600, 0x00080028, 0x0c200800, 0x40101104, 0x90000200, 0x00080010, 0x00200000, 0x00801004, 0x90040200, 0x00080010, 0x04200000, 0x00901004, 0x90400200, 0x00080018, 0x00200800, 0x40801004, 0x90440200, 0x00080018, 0x04200800, 0x40901004, 0x90000600, 0x00080030, 0x08200000, 0x00801104, 0x90040600, 0x00080030, 0x0c200000, 0x00901104, 0x90400600, 0x00080038, 0x08200800, 0x40801104, 0x90440600, 0x00080038, 0x0c200800, 0x40901104, 0x00000002, 0x00002000, 0x20000000, 0x00000001, 0x00040002, 0x00002000, 0x24000000, 0x00100001, 0x00400002, 0x00002008, 0x20000800, 0x40000001, 0x00440002, 0x00002008, 0x24000800, 0x40100001, 0x00000402, 0x00002020, 0x28000000, 0x00000101, 0x00040402, 0x00002020, 0x2c000000, 0x00100101, 0x00400402, 0x00002028, 0x28000800, 0x40000101, 0x00440402, 0x00002028, 0x2c000800, 0x40100101, 0x80000002, 0x00002010, 0x20000000, 0x00800001, 0x80040002, 0x00002010, 0x24000000, 0x00900001, 0x80400002, 0x00002018, 0x20000800, 0x40800001, 0x80440002, 0x00002018, 0x24000800, 0x40900001, 0x80000402, 0x00002030, 0x28000000, 0x00800101, 0x80040402, 0x00002030, 0x2c000000, 0x00900101, 0x80400402, 0x00002038, 0x28000800, 0x40800101, 0x80440402, 0x00002038, 0x2c000800, 0x40900101, 0x10000002, 0x00002000, 0x20200000, 0x00001001, 0x10040002, 0x00002000, 0x24200000, 0x00101001, 0x10400002, 0x00002008, 0x20200800, 0x40001001, 0x10440002, 0x00002008, 0x24200800, 0x40101001, 0x10000402, 0x00002020, 0x28200000, 0x00001101, 0x10040402, 0x00002020, 0x2c200000, 0x00101101, 0x10400402, 0x00002028, 0x28200800, 0x40001101, 0x10440402, 0x00002028, 0x2c200800, 0x40101101, 0x90000002, 0x00002010, 0x20200000, 0x00801001, 0x90040002, 0x00002010, 0x24200000, 0x00901001, 0x90400002, 0x00002018, 0x20200800, 0x40801001, 0x90440002, 0x00002018, 0x24200800, 0x40901001, 0x90000402, 0x00002030, 0x28200000, 0x00801101, 0x90040402, 0x00002030, 0x2c200000, 0x00901101, 0x90400402, 0x00002038, 0x28200800, 0x40801101, 0x90440402, 0x00002038, 0x2c200800, 0x40901101, 0x00000202, 0x00082000, 0x20000000, 0x00000005, 0x00040202, 0x00082000, 0x24000000, 0x00100005, 0x00400202, 0x00082008, 0x20000800, 0x40000005, 0x00440202, 0x00082008, 0x24000800, 0x40100005, 0x00000602, 0x00082020, 0x28000000, 0x00000105, 0x00040602, 0x00082020, 0x2c000000, 0x00100105, 0x00400602, 0x00082028, 0x28000800, 0x40000105, 0x00440602, 0x00082028, 0x2c000800, 0x40100105, 0x80000202, 0x00082010, 0x20000000, 0x00800005, 0x80040202, 0x00082010, 0x24000000, 0x00900005, 0x80400202, 0x00082018, 0x20000800, 0x40800005, 0x80440202, 0x00082018, 0x24000800, 0x40900005, 0x80000602, 0x00082030, 0x28000000, 0x00800105, 0x80040602, 0x00082030, 0x2c000000, 0x00900105, 0x80400602, 0x00082038, 0x28000800, 0x40800105, 0x80440602, 0x00082038, 0x2c000800, 0x40900105, 0x10000202, 0x00082000, 0x20200000, 0x00001005, 0x10040202, 0x00082000, 0x24200000, 0x00101005, 0x10400202, 0x00082008, 0x20200800, 0x40001005, 0x10440202, 0x00082008, 0x24200800, 0x40101005, 0x10000602, 0x00082020, 0x28200000, 0x00001105, 0x10040602, 0x00082020, 0x2c200000, 0x00101105, 0x10400602, 0x00082028, 0x28200800, 0x40001105, 0x10440602, 0x00082028, 0x2c200800, 0x40101105, 0x90000202, 0x00082010, 0x20200000, 0x00801005, 0x90040202, 0x00082010, 0x24200000, 0x00901005, 0x90400202, 0x00082018, 0x20200800, 0x40801005, 0x90440202, 0x00082018, 0x24200800, 0x40901005, 0x90000602, 0x00082030, 0x28200000, 0x00801105, 0x90040602, 0x00082030, 0x2c200000, 0x00901105, 0x90400602, 0x00082038, 0x28200800, 0x40801105, 0x90440602, 0x00082038, 0x2c200800, 0x40901105, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000008, 0x00080000, 0x10000000, 0x02000000, 0x00000000, 0x00000080, 0x00001000, 0x02000000, 0x00000008, 0x00080080, 0x10001000, 0x00004000, 0x00000000, 0x00000040, 0x00040000, 0x00004000, 0x00000008, 0x00080040, 0x10040000, 0x02004000, 0x00000000, 0x000000c0, 0x00041000, 0x02004000, 0x00000008, 0x000800c0, 0x10041000, 0x00020000, 0x00008000, 0x08000000, 0x00200000, 0x00020000, 0x00008008, 0x08080000, 0x10200000, 0x02020000, 0x00008000, 0x08000080, 0x00201000, 0x02020000, 0x00008008, 0x08080080, 0x10201000, 0x00024000, 0x00008000, 0x08000040, 0x00240000, 0x00024000, 0x00008008, 0x08080040, 0x10240000, 0x02024000, 0x00008000, 0x080000c0, 0x00241000, 0x02024000, 0x00008008, 0x080800c0, 0x10241000, 0x00000000, 0x01000000, 0x00002000, 0x00000020, 0x00000000, 0x01000008, 0x00082000, 0x10000020, 0x02000000, 0x01000000, 0x00002080, 0x00001020, 0x02000000, 0x01000008, 0x00082080, 0x10001020, 0x00004000, 0x01000000, 0x00002040, 0x00040020, 0x00004000, 0x01000008, 0x00082040, 0x10040020, 0x02004000, 0x01000000, 0x000020c0, 0x00041020, 0x02004000, 0x01000008, 0x000820c0, 0x10041020, 0x00020000, 0x01008000, 0x08002000, 0x00200020, 0x00020000, 0x01008008, 0x08082000, 0x10200020, 0x02020000, 0x01008000, 0x08002080, 0x00201020, 0x02020000, 0x01008008, 0x08082080, 0x10201020, 0x00024000, 0x01008000, 0x08002040, 0x00240020, 0x00024000, 0x01008008, 0x08082040, 0x10240020, 0x02024000, 0x01008000, 0x080020c0, 0x00241020, 0x02024000, 0x01008008, 0x080820c0, 0x10241020, 0x00000400, 0x04000000, 0x00100000, 0x00000004, 0x00000400, 0x04000008, 0x00180000, 0x10000004, 0x02000400, 0x04000000, 0x00100080, 0x00001004, 0x02000400, 0x04000008, 0x00180080, 0x10001004, 0x00004400, 0x04000000, 0x00100040, 0x00040004, 0x00004400, 0x04000008, 0x00180040, 0x10040004, 0x02004400, 0x04000000, 0x001000c0, 0x00041004, 0x02004400, 0x04000008, 0x001800c0, 0x10041004, 0x00020400, 0x04008000, 0x08100000, 0x00200004, 0x00020400, 0x04008008, 0x08180000, 0x10200004, 0x02020400, 0x04008000, 0x08100080, 0x00201004, 0x02020400, 0x04008008, 0x08180080, 0x10201004, 0x00024400, 0x04008000, 0x08100040, 0x00240004, 0x00024400, 0x04008008, 0x08180040, 0x10240004, 0x02024400, 0x04008000, 0x081000c0, 0x00241004, 0x02024400, 0x04008008, 0x081800c0, 0x10241004, 0x00000400, 0x05000000, 0x00102000, 0x00000024, 0x00000400, 0x05000008, 0x00182000, 0x10000024, 0x02000400, 0x05000000, 0x00102080, 0x00001024, 0x02000400, 0x05000008, 0x00182080, 0x10001024, 0x00004400, 0x05000000, 0x00102040, 0x00040024, 0x00004400, 0x05000008, 0x00182040, 0x10040024, 0x02004400, 0x05000000, 0x001020c0, 0x00041024, 0x02004400, 0x05000008, 0x001820c0, 0x10041024, 0x00020400, 0x05008000, 0x08102000, 0x00200024, 0x00020400, 0x05008008, 0x08182000, 0x10200024, 0x02020400, 0x05008000, 0x08102080, 0x00201024, 0x02020400, 0x05008008, 0x08182080, 0x10201024, 0x00024400, 0x05008000, 0x08102040, 0x00240024, 0x00024400, 0x05008008, 0x08182040, 0x10240024, 0x02024400, 0x05008000, 0x081020c0, 0x00241024, 0x02024400, 0x05008008, 0x081820c0, 0x10241024, 0x00000800, 0x00010000, 0x20000000, 0x00000010, 0x00000800, 0x00010008, 0x20080000, 0x10000010, 0x02000800, 0x00010000, 0x20000080, 0x00001010, 0x02000800, 0x00010008, 0x20080080, 0x10001010, 0x00004800, 0x00010000, 0x20000040, 0x00040010, 0x00004800, 0x00010008, 0x20080040, 0x10040010, 0x02004800, 0x00010000, 0x200000c0, 0x00041010, 0x02004800, 0x00010008, 0x200800c0, 0x10041010, 0x00020800, 0x00018000, 0x28000000, 0x00200010, 0x00020800, 0x00018008, 0x28080000, 0x10200010, 0x02020800, 0x00018000, 0x28000080, 0x00201010, 0x02020800, 0x00018008, 0x28080080, 0x10201010, 0x00024800, 0x00018000, 0x28000040, 0x00240010, 0x00024800, 0x00018008, 0x28080040, 0x10240010, 0x02024800, 0x00018000, 0x280000c0, 0x00241010, 0x02024800, 0x00018008, 0x280800c0, 0x10241010, 0x00000800, 0x01010000, 0x20002000, 0x00000030, 0x00000800, 0x01010008, 0x20082000, 0x10000030, 0x02000800, 0x01010000, 0x20002080, 0x00001030, 0x02000800, 0x01010008, 0x20082080, 0x10001030, 0x00004800, 0x01010000, 0x20002040, 0x00040030, 0x00004800, 0x01010008, 0x20082040, 0x10040030, 0x02004800, 0x01010000, 0x200020c0, 0x00041030, 0x02004800, 0x01010008, 0x200820c0, 0x10041030, 0x00020800, 0x01018000, 0x28002000, 0x00200030, 0x00020800, 0x01018008, 0x28082000, 0x10200030, 0x02020800, 0x01018000, 0x28002080, 0x00201030, 0x02020800, 0x01018008, 0x28082080, 0x10201030, 0x00024800, 0x01018000, 0x28002040, 0x00240030, 0x00024800, 0x01018008, 0x28082040, 0x10240030, 0x02024800, 0x01018000, 0x280020c0, 0x00241030, 0x02024800, 0x01018008, 0x280820c0, 0x10241030, 0x00000c00, 0x04010000, 0x20100000, 0x00000014, 0x00000c00, 0x04010008, 0x20180000, 0x10000014, 0x02000c00, 0x04010000, 0x20100080, 0x00001014, 0x02000c00, 0x04010008, 0x20180080, 0x10001014, 0x00004c00, 0x04010000, 0x20100040, 0x00040014, 0x00004c00, 0x04010008, 0x20180040, 0x10040014, 0x02004c00, 0x04010000, 0x201000c0, 0x00041014, 0x02004c00, 0x04010008, 0x201800c0, 0x10041014, 0x00020c00, 0x04018000, 0x28100000, 0x00200014, 0x00020c00, 0x04018008, 0x28180000, 0x10200014, 0x02020c00, 0x04018000, 0x28100080, 0x00201014, 0x02020c00, 0x04018008, 0x28180080, 0x10201014, 0x00024c00, 0x04018000, 0x28100040, 0x00240014, 0x00024c00, 0x04018008, 0x28180040, 0x10240014, 0x02024c00, 0x04018000, 0x281000c0, 0x00241014, 0x02024c00, 0x04018008, 0x281800c0, 0x10241014, 0x00000c00, 0x05010000, 0x20102000, 0x00000034, 0x00000c00, 0x05010008, 0x20182000, 0x10000034, 0x02000c00, 0x05010000, 0x20102080, 0x00001034, 0x02000c00, 0x05010008, 0x20182080, 0x10001034, 0x00004c00, 0x05010000, 0x20102040, 0x00040034, 0x00004c00, 0x05010008, 0x20182040, 0x10040034, 0x02004c00, 0x05010000, 0x201020c0, 0x00041034, 0x02004c00, 0x05010008, 0x201820c0, 0x10041034, 0x00020c00, 0x05018000, 0x28102000, 0x00200034, 0x00020c00, 0x05018008, 0x28182000, 0x10200034, 0x02020c00, 0x05018000, 0x28102080, 0x00201034, 0x02020c00, 0x05018008, 0x28182080, 0x10201034, 0x00024c00, 0x05018000, 0x28102040, 0x00240034, 0x00024c00, 0x05018008, 0x28182040, 0x10240034, 0x02024c00, 0x05018000, 0x281020c0, 0x00241034, 0x02024c00, 0x05018008, 0x281820c0, 0x10241034 }; /* S-box lookup tables */ static const u32 S1[64] = { 0x01010400, 0x00000000, 0x00010000, 0x01010404, 0x01010004, 0x00010404, 0x00000004, 0x00010000, 0x00000400, 0x01010400, 0x01010404, 0x00000400, 0x01000404, 0x01010004, 0x01000000, 0x00000004, 0x00000404, 0x01000400, 0x01000400, 0x00010400, 0x00010400, 0x01010000, 0x01010000, 0x01000404, 0x00010004, 0x01000004, 0x01000004, 0x00010004, 0x00000000, 0x00000404, 0x00010404, 0x01000000, 0x00010000, 0x01010404, 0x00000004, 0x01010000, 0x01010400, 0x01000000, 0x01000000, 0x00000400, 0x01010004, 0x00010000, 0x00010400, 0x01000004, 0x00000400, 0x00000004, 0x01000404, 0x00010404, 0x01010404, 0x00010004, 0x01010000, 0x01000404, 0x01000004, 0x00000404, 0x00010404, 0x01010400, 0x00000404, 0x01000400, 0x01000400, 0x00000000, 0x00010004, 0x00010400, 0x00000000, 0x01010004 }; static const u32 S2[64] = { 0x80108020, 0x80008000, 0x00008000, 0x00108020, 0x00100000, 0x00000020, 0x80100020, 0x80008020, 0x80000020, 0x80108020, 0x80108000, 0x80000000, 0x80008000, 0x00100000, 0x00000020, 0x80100020, 0x00108000, 0x00100020, 0x80008020, 0x00000000, 0x80000000, 0x00008000, 0x00108020, 0x80100000, 0x00100020, 0x80000020, 0x00000000, 0x00108000, 0x00008020, 0x80108000, 0x80100000, 0x00008020, 0x00000000, 0x00108020, 0x80100020, 0x00100000, 0x80008020, 0x80100000, 0x80108000, 0x00008000, 0x80100000, 0x80008000, 0x00000020, 0x80108020, 0x00108020, 0x00000020, 0x00008000, 0x80000000, 0x00008020, 0x80108000, 0x00100000, 0x80000020, 0x00100020, 0x80008020, 0x80000020, 0x00100020, 0x00108000, 0x00000000, 0x80008000, 0x00008020, 0x80000000, 0x80100020, 0x80108020, 0x00108000 }; static const u32 S3[64] = { 0x00000208, 0x08020200, 0x00000000, 0x08020008, 0x08000200, 0x00000000, 0x00020208, 0x08000200, 0x00020008, 0x08000008, 0x08000008, 0x00020000, 0x08020208, 0x00020008, 0x08020000, 0x00000208, 0x08000000, 0x00000008, 0x08020200, 0x00000200, 0x00020200, 0x08020000, 0x08020008, 0x00020208, 0x08000208, 0x00020200, 0x00020000, 0x08000208, 0x00000008, 0x08020208, 0x00000200, 0x08000000, 0x08020200, 0x08000000, 0x00020008, 0x00000208, 0x00020000, 0x08020200, 0x08000200, 0x00000000, 0x00000200, 0x00020008, 0x08020208, 0x08000200, 0x08000008, 0x00000200, 0x00000000, 0x08020008, 0x08000208, 0x00020000, 0x08000000, 0x08020208, 0x00000008, 0x00020208, 0x00020200, 0x08000008, 0x08020000, 0x08000208, 0x00000208, 0x08020000, 0x00020208, 0x00000008, 0x08020008, 0x00020200 }; static const u32 S4[64] = { 0x00802001, 0x00002081, 0x00002081, 0x00000080, 0x00802080, 0x00800081, 0x00800001, 0x00002001, 0x00000000, 0x00802000, 0x00802000, 0x00802081, 0x00000081, 0x00000000, 0x00800080, 0x00800001, 0x00000001, 0x00002000, 0x00800000, 0x00802001, 0x00000080, 0x00800000, 0x00002001, 0x00002080, 0x00800081, 0x00000001, 0x00002080, 0x00800080, 0x00002000, 0x00802080, 0x00802081, 0x00000081, 0x00800080, 0x00800001, 0x00802000, 0x00802081, 0x00000081, 0x00000000, 0x00000000, 0x00802000, 0x00002080, 0x00800080, 0x00800081, 0x00000001, 0x00802001, 0x00002081, 0x00002081, 0x00000080, 0x00802081, 0x00000081, 0x00000001, 0x00002000, 0x00800001, 0x00002001, 0x00802080, 0x00800081, 0x00002001, 0x00002080, 0x00800000, 0x00802001, 0x00000080, 0x00800000, 0x00002000, 0x00802080 }; static const u32 S5[64] = { 0x00000100, 0x02080100, 0x02080000, 0x42000100, 0x00080000, 0x00000100, 0x40000000, 0x02080000, 0x40080100, 0x00080000, 0x02000100, 0x40080100, 0x42000100, 0x42080000, 0x00080100, 0x40000000, 0x02000000, 0x40080000, 0x40080000, 0x00000000, 0x40000100, 0x42080100, 0x42080100, 0x02000100, 0x42080000, 0x40000100, 0x00000000, 0x42000000, 0x02080100, 0x02000000, 0x42000000, 0x00080100, 0x00080000, 0x42000100, 0x00000100, 0x02000000, 0x40000000, 0x02080000, 0x42000100, 0x40080100, 0x02000100, 0x40000000, 0x42080000, 0x02080100, 0x40080100, 0x00000100, 0x02000000, 0x42080000, 0x42080100, 0x00080100, 0x42000000, 0x42080100, 0x02080000, 0x00000000, 0x40080000, 0x42000000, 0x00080100, 0x02000100, 0x40000100, 0x00080000, 0x00000000, 0x40080000, 0x02080100, 0x40000100 }; static const u32 S6[64] = { 0x20000010, 0x20400000, 0x00004000, 0x20404010, 0x20400000, 0x00000010, 0x20404010, 0x00400000, 0x20004000, 0x00404010, 0x00400000, 0x20000010, 0x00400010, 0x20004000, 0x20000000, 0x00004010, 0x00000000, 0x00400010, 0x20004010, 0x00004000, 0x00404000, 0x20004010, 0x00000010, 0x20400010, 0x20400010, 0x00000000, 0x00404010, 0x20404000, 0x00004010, 0x00404000, 0x20404000, 0x20000000, 0x20004000, 0x00000010, 0x20400010, 0x00404000, 0x20404010, 0x00400000, 0x00004010, 0x20000010, 0x00400000, 0x20004000, 0x20000000, 0x00004010, 0x20000010, 0x20404010, 0x00404000, 0x20400000, 0x00404010, 0x20404000, 0x00000000, 0x20400010, 0x00000010, 0x00004000, 0x20400000, 0x00404010, 0x00004000, 0x00400010, 0x20004010, 0x00000000, 0x20404000, 0x20000000, 0x00400010, 0x20004010 }; static const u32 S7[64] = { 0x00200000, 0x04200002, 0x04000802, 0x00000000, 0x00000800, 0x04000802, 0x00200802, 0x04200800, 0x04200802, 0x00200000, 0x00000000, 0x04000002, 0x00000002, 0x04000000, 0x04200002, 0x00000802, 0x04000800, 0x00200802, 0x00200002, 0x04000800, 0x04000002, 0x04200000, 0x04200800, 0x00200002, 0x04200000, 0x00000800, 0x00000802, 0x04200802, 0x00200800, 0x00000002, 0x04000000, 0x00200800, 0x04000000, 0x00200800, 0x00200000, 0x04000802, 0x04000802, 0x04200002, 0x04200002, 0x00000002, 0x00200002, 0x04000000, 0x04000800, 0x00200000, 0x04200800, 0x00000802, 0x00200802, 0x04200800, 0x00000802, 0x04000002, 0x04200802, 0x04200000, 0x00200800, 0x00000000, 0x00000002, 0x04200802, 0x00000000, 0x00200802, 0x04200000, 0x00000800, 0x04000002, 0x04000800, 0x00000800, 0x00200002 }; static const u32 S8[64] = { 0x10001040, 0x00001000, 0x00040000, 0x10041040, 0x10000000, 0x10001040, 0x00000040, 0x10000000, 0x00040040, 0x10040000, 0x10041040, 0x00041000, 0x10041000, 0x00041040, 0x00001000, 0x00000040, 0x10040000, 0x10000040, 0x10001000, 0x00001040, 0x00041000, 0x00040040, 0x10040040, 0x10041000, 0x00001040, 0x00000000, 0x00000000, 0x10040040, 0x10000040, 0x10001000, 0x00041040, 0x00040000, 0x00041040, 0x00040000, 0x10041000, 0x00001000, 0x00000040, 0x10040040, 0x00001000, 0x00041040, 0x10001000, 0x00000040, 0x10000040, 0x10040000, 0x10040040, 0x10000000, 0x00040000, 0x10001040, 0x00000000, 0x10041040, 0x00040040, 0x10000040, 0x10040000, 0x10001000, 0x10001040, 0x00000000, 0x10041040, 0x00041000, 0x00041000, 0x00001040, 0x00001040, 0x00040040, 0x10000000, 0x10041000 }; /* Encryption components: IP, FP, and round function */ #define IP(L, R, T) \ ROL(R, 4); \ T = L; \ L ^= R; \ L &= 0xf0f0f0f0; \ R ^= L; \ L ^= T; \ ROL(R, 12); \ T = L; \ L ^= R; \ L &= 0xffff0000; \ R ^= L; \ L ^= T; \ ROR(R, 14); \ T = L; \ L ^= R; \ L &= 0xcccccccc; \ R ^= L; \ L ^= T; \ ROL(R, 6); \ T = L; \ L ^= R; \ L &= 0xff00ff00; \ R ^= L; \ L ^= T; \ ROR(R, 7); \ T = L; \ L ^= R; \ L &= 0xaaaaaaaa; \ R ^= L; \ L ^= T; \ ROL(L, 1); #define FP(L, R, T) \ ROR(L, 1); \ T = L; \ L ^= R; \ L &= 0xaaaaaaaa; \ R ^= L; \ L ^= T; \ ROL(R, 7); \ T = L; \ L ^= R; \ L &= 0xff00ff00; \ R ^= L; \ L ^= T; \ ROR(R, 6); \ T = L; \ L ^= R; \ L &= 0xcccccccc; \ R ^= L; \ L ^= T; \ ROL(R, 14); \ T = L; \ L ^= R; \ L &= 0xffff0000; \ R ^= L; \ L ^= T; \ ROR(R, 12); \ T = L; \ L ^= R; \ L &= 0xf0f0f0f0; \ R ^= L; \ L ^= T; \ ROR(R, 4); #define ROUND(L, R, A, B, K, d) \ B = K[0]; A = K[1]; K += d; \ B ^= R; A ^= R; \ B &= 0x3f3f3f3f; ROR(A, 4); \ L ^= S8[0xff & B]; A &= 0x3f3f3f3f; \ L ^= S6[0xff & (B >> 8)]; B >>= 16; \ L ^= S7[0xff & A]; \ L ^= S5[0xff & (A >> 8)]; A >>= 16; \ L ^= S4[0xff & B]; \ L ^= S2[0xff & (B >> 8)]; \ L ^= S3[0xff & A]; \ L ^= S1[0xff & (A >> 8)]; /* * PC2 lookup tables are organized as 2 consecutive sets of 4 interleaved * tables of 128 elements. One set is for C_i and the other for D_i, while * the 4 interleaved tables correspond to four 7-bit subsets of C_i or D_i. * * After PC1 each of the variables a,b,c,d contains a 7 bit subset of C_i * or D_i in bits 7-1 (bit 0 being the least significant). */ #define T1(x) pt[2 * (x) + 0] #define T2(x) pt[2 * (x) + 1] #define T3(x) pt[2 * (x) + 2] #define T4(x) pt[2 * (x) + 3] #define DES_PC2(a, b, c, d) (T4(d) | T3(c) | T2(b) | T1(a)) /* * Encryption key expansion * * RFC2451: Weak key checks SHOULD be performed. * * FIPS 74: * * Keys having duals are keys which produce all zeros, all ones, or * alternating zero-one patterns in the C and D registers after Permuted * Choice 1 has operated on the key. * */ static unsigned long des_ekey(u32 *pe, const u8 *k) { /* K&R: long is at least 32 bits */ unsigned long a, b, c, d, w; const u32 *pt = pc2; d = k[4]; d &= 0x0e; d <<= 4; d |= k[0] & 0x1e; d = pc1[d]; c = k[5]; c &= 0x0e; c <<= 4; c |= k[1] & 0x1e; c = pc1[c]; b = k[6]; b &= 0x0e; b <<= 4; b |= k[2] & 0x1e; b = pc1[b]; a = k[7]; a &= 0x0e; a <<= 4; a |= k[3] & 0x1e; a = pc1[a]; pe[15 * 2 + 0] = DES_PC2(a, b, c, d); d = rs[d]; pe[14 * 2 + 0] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[13 * 2 + 0] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[12 * 2 + 0] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[11 * 2 + 0] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[10 * 2 + 0] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[ 9 * 2 + 0] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[ 8 * 2 + 0] = DES_PC2(d, a, b, c); c = rs[c]; pe[ 7 * 2 + 0] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[ 6 * 2 + 0] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[ 5 * 2 + 0] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[ 4 * 2 + 0] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[ 3 * 2 + 0] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[ 2 * 2 + 0] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[ 1 * 2 + 0] = DES_PC2(c, d, a, b); b = rs[b]; pe[ 0 * 2 + 0] = DES_PC2(b, c, d, a); /* Check if first half is weak */ w = (a ^ c) | (b ^ d) | (rs[a] ^ c) | (b ^ rs[d]); /* Skip to next table set */ pt += 512; d = k[0]; d &= 0xe0; d >>= 4; d |= k[4] & 0xf0; d = pc1[d + 1]; c = k[1]; c &= 0xe0; c >>= 4; c |= k[5] & 0xf0; c = pc1[c + 1]; b = k[2]; b &= 0xe0; b >>= 4; b |= k[6] & 0xf0; b = pc1[b + 1]; a = k[3]; a &= 0xe0; a >>= 4; a |= k[7] & 0xf0; a = pc1[a + 1]; /* Check if second half is weak */ w |= (a ^ c) | (b ^ d) | (rs[a] ^ c) | (b ^ rs[d]); pe[15 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; pe[14 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[13 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[12 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[11 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[10 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[ 9 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[ 8 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; pe[ 7 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[ 6 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[ 5 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[ 4 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[ 3 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[ 2 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[ 1 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; pe[ 0 * 2 + 1] = DES_PC2(b, c, d, a); /* Fixup: 2413 5768 -> 1357 2468 */ for (d = 0; d < 16; ++d) { a = pe[2 * d]; b = pe[2 * d + 1]; c = a ^ b; c &= 0xffff0000; a ^= c; b ^= c; ROL(b, 18); pe[2 * d] = a; pe[2 * d + 1] = b; } /* Zero if weak key */ return w; } int des_expand_key(struct des_ctx *ctx, const u8 *key, unsigned int keylen) { if (keylen != DES_KEY_SIZE) return -EINVAL; return des_ekey(ctx->expkey, key) ? 0 : -ENOKEY; } EXPORT_SYMBOL_GPL(des_expand_key); /* * Decryption key expansion * * No weak key checking is performed, as this is only used by triple DES * */ static void dkey(u32 *pe, const u8 *k) { /* K&R: long is at least 32 bits */ unsigned long a, b, c, d; const u32 *pt = pc2; d = k[4]; d &= 0x0e; d <<= 4; d |= k[0] & 0x1e; d = pc1[d]; c = k[5]; c &= 0x0e; c <<= 4; c |= k[1] & 0x1e; c = pc1[c]; b = k[6]; b &= 0x0e; b <<= 4; b |= k[2] & 0x1e; b = pc1[b]; a = k[7]; a &= 0x0e; a <<= 4; a |= k[3] & 0x1e; a = pc1[a]; pe[ 0 * 2] = DES_PC2(a, b, c, d); d = rs[d]; pe[ 1 * 2] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[ 2 * 2] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[ 3 * 2] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[ 4 * 2] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[ 5 * 2] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[ 6 * 2] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[ 7 * 2] = DES_PC2(d, a, b, c); c = rs[c]; pe[ 8 * 2] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[ 9 * 2] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[10 * 2] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[11 * 2] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[12 * 2] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[13 * 2] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[14 * 2] = DES_PC2(c, d, a, b); b = rs[b]; pe[15 * 2] = DES_PC2(b, c, d, a); /* Skip to next table set */ pt += 512; d = k[0]; d &= 0xe0; d >>= 4; d |= k[4] & 0xf0; d = pc1[d + 1]; c = k[1]; c &= 0xe0; c >>= 4; c |= k[5] & 0xf0; c = pc1[c + 1]; b = k[2]; b &= 0xe0; b >>= 4; b |= k[6] & 0xf0; b = pc1[b + 1]; a = k[3]; a &= 0xe0; a >>= 4; a |= k[7] & 0xf0; a = pc1[a + 1]; pe[ 0 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; pe[ 1 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[ 2 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[ 3 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[ 4 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[ 5 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; b = rs[b]; pe[ 6 * 2 + 1] = DES_PC2(b, c, d, a); a = rs[a]; d = rs[d]; pe[ 7 * 2 + 1] = DES_PC2(d, a, b, c); c = rs[c]; pe[ 8 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[ 9 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[10 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[11 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[12 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; a = rs[a]; pe[13 * 2 + 1] = DES_PC2(a, b, c, d); d = rs[d]; c = rs[c]; pe[14 * 2 + 1] = DES_PC2(c, d, a, b); b = rs[b]; pe[15 * 2 + 1] = DES_PC2(b, c, d, a); /* Fixup: 2413 5768 -> 1357 2468 */ for (d = 0; d < 16; ++d) { a = pe[2 * d]; b = pe[2 * d + 1]; c = a ^ b; c &= 0xffff0000; a ^= c; b ^= c; ROL(b, 18); pe[2 * d] = a; pe[2 * d + 1] = b; } } void des_encrypt(const struct des_ctx *ctx, u8 *dst, const u8 *src) { const u32 *K = ctx->expkey; u32 L, R, A, B; int i; L = get_unaligned_le32(src); R = get_unaligned_le32(src + 4); IP(L, R, A); for (i = 0; i < 8; i++) { ROUND(L, R, A, B, K, 2); ROUND(R, L, A, B, K, 2); } FP(R, L, A); put_unaligned_le32(R, dst); put_unaligned_le32(L, dst + 4); } EXPORT_SYMBOL_GPL(des_encrypt); void des_decrypt(const struct des_ctx *ctx, u8 *dst, const u8 *src) { const u32 *K = ctx->expkey + DES_EXPKEY_WORDS - 2; u32 L, R, A, B; int i; L = get_unaligned_le32(src); R = get_unaligned_le32(src + 4); IP(L, R, A); for (i = 0; i < 8; i++) { ROUND(L, R, A, B, K, -2); ROUND(R, L, A, B, K, -2); } FP(R, L, A); put_unaligned_le32(R, dst); put_unaligned_le32(L, dst + 4); } EXPORT_SYMBOL_GPL(des_decrypt); int des3_ede_expand_key(struct des3_ede_ctx *ctx, const u8 *key, unsigned int keylen) { u32 *pe = ctx->expkey; int err; if (keylen != DES3_EDE_KEY_SIZE) return -EINVAL; err = des3_ede_verify_key(key, keylen, true); if (err && err != -ENOKEY) return err; des_ekey(pe, key); pe += DES_EXPKEY_WORDS; key += DES_KEY_SIZE; dkey(pe, key); pe += DES_EXPKEY_WORDS; key += DES_KEY_SIZE; des_ekey(pe, key); return err; } EXPORT_SYMBOL_GPL(des3_ede_expand_key); void des3_ede_encrypt(const struct des3_ede_ctx *dctx, u8 *dst, const u8 *src) { const u32 *K = dctx->expkey; u32 L, R, A, B; int i; L = get_unaligned_le32(src); R = get_unaligned_le32(src + 4); IP(L, R, A); for (i = 0; i < 8; i++) { ROUND(L, R, A, B, K, 2); ROUND(R, L, A, B, K, 2); } for (i = 0; i < 8; i++) { ROUND(R, L, A, B, K, 2); ROUND(L, R, A, B, K, 2); } for (i = 0; i < 8; i++) { ROUND(L, R, A, B, K, 2); ROUND(R, L, A, B, K, 2); } FP(R, L, A); put_unaligned_le32(R, dst); put_unaligned_le32(L, dst + 4); } EXPORT_SYMBOL_GPL(des3_ede_encrypt); void des3_ede_decrypt(const struct des3_ede_ctx *dctx, u8 *dst, const u8 *src) { const u32 *K = dctx->expkey + DES3_EDE_EXPKEY_WORDS - 2; u32 L, R, A, B; int i; L = get_unaligned_le32(src); R = get_unaligned_le32(src + 4); IP(L, R, A); for (i = 0; i < 8; i++) { ROUND(L, R, A, B, K, -2); ROUND(R, L, A, B, K, -2); } for (i = 0; i < 8; i++) { ROUND(R, L, A, B, K, -2); ROUND(L, R, A, B, K, -2); } for (i = 0; i < 8; i++) { ROUND(L, R, A, B, K, -2); ROUND(R, L, A, B, K, -2); } FP(R, L, A); put_unaligned_le32(R, dst); put_unaligned_le32(L, dst + 4); } EXPORT_SYMBOL_GPL(des3_ede_decrypt); MODULE_LICENSE("GPL"); |
| 366 366 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CONTEXT_TRACKING_STATE_H #define _LINUX_CONTEXT_TRACKING_STATE_H #include <linux/percpu.h> #include <linux/static_key.h> #include <linux/context_tracking_irq.h> /* Offset to allow distinguishing irq vs. task-based idle entry/exit. */ #define DYNTICK_IRQ_NONIDLE ((LONG_MAX / 2) + 1) enum ctx_state { CONTEXT_DISABLED = -1, /* returned by ct_state() if unknown */ CONTEXT_KERNEL = 0, CONTEXT_IDLE = 1, CONTEXT_USER = 2, CONTEXT_GUEST = 3, CONTEXT_MAX = 4, }; /* Even value for idle, else odd. */ #define RCU_DYNTICKS_IDX CONTEXT_MAX #define CT_STATE_MASK (CONTEXT_MAX - 1) #define CT_DYNTICKS_MASK (~CT_STATE_MASK) struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING_USER /* * When active is false, probes are unset in order * to minimize overhead: TIF flags are cleared * and calls to user_enter/exit are ignored. This * may be further optimized using static keys. */ bool active; int recursion; #endif #ifdef CONFIG_CONTEXT_TRACKING atomic_t state; #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE long dynticks_nesting; /* Track process nesting level. */ long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ #endif }; #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); #endif #ifdef CONFIG_CONTEXT_TRACKING_USER static __always_inline int __ct_state(void) { return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; } #endif #ifdef CONFIG_CONTEXT_TRACKING_IDLE static __always_inline int ct_dynticks(void) { return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_DYNTICKS_MASK; } static __always_inline int ct_dynticks_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return atomic_read(&ct->state) & CT_DYNTICKS_MASK; } static __always_inline int ct_dynticks_cpu_acquire(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return atomic_read_acquire(&ct->state) & CT_DYNTICKS_MASK; } static __always_inline long ct_dynticks_nesting(void) { return __this_cpu_read(context_tracking.dynticks_nesting); } static __always_inline long ct_dynticks_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return ct->dynticks_nesting; } static __always_inline long ct_dynticks_nmi_nesting(void) { return __this_cpu_read(context_tracking.dynticks_nmi_nesting); } static __always_inline long ct_dynticks_nmi_nesting_cpu(int cpu) { struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu); return ct->dynticks_nmi_nesting; } #endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */ #ifdef CONFIG_CONTEXT_TRACKING_USER extern struct static_key_false context_tracking_key; static __always_inline bool context_tracking_enabled(void) { return static_branch_unlikely(&context_tracking_key); } static __always_inline bool context_tracking_enabled_cpu(int cpu) { return context_tracking_enabled() && per_cpu(context_tracking.active, cpu); } static inline bool context_tracking_enabled_this_cpu(void) { return context_tracking_enabled() && __this_cpu_read(context_tracking.active); } /** * ct_state() - return the current context tracking state if known * * Returns the current cpu's context tracking state if context tracking * is enabled. If context tracking is disabled, returns * CONTEXT_DISABLED. This should be used primarily for debugging. */ static __always_inline int ct_state(void) { int ret; if (!context_tracking_enabled()) return CONTEXT_DISABLED; preempt_disable(); ret = __ct_state(); preempt_enable(); return ret; } #else static __always_inline bool context_tracking_enabled(void) { return false; } static __always_inline bool context_tracking_enabled_cpu(int cpu) { return false; } static __always_inline bool context_tracking_enabled_this_cpu(void) { return false; } #endif /* CONFIG_CONTEXT_TRACKING_USER */ #endif |
| 170 28 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Wound/Wait Mutexes: blocking mutual exclusion locks with deadlock avoidance * * Original mutex implementation started by Ingo Molnar: * * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. * Choice of algorithm: * Copyright (C) 2018 WMWare Inc. * * This file contains the main data structure and API definitions. */ #ifndef __LINUX_WW_MUTEX_H #define __LINUX_WW_MUTEX_H #include <linux/mutex.h> #include <linux/rtmutex.h> #if defined(CONFIG_DEBUG_MUTEXES) || \ (defined(CONFIG_PREEMPT_RT) && defined(CONFIG_DEBUG_RT_MUTEXES)) #define DEBUG_WW_MUTEXES #endif #ifndef CONFIG_PREEMPT_RT #define WW_MUTEX_BASE mutex #define ww_mutex_base_init(l,n,k) __mutex_init(l,n,k) #define ww_mutex_base_is_locked(b) mutex_is_locked((b)) #else #define WW_MUTEX_BASE rt_mutex #define ww_mutex_base_init(l,n,k) __rt_mutex_init(l,n,k) #define ww_mutex_base_is_locked(b) rt_mutex_base_is_locked(&(b)->rtmutex) #endif struct ww_class { atomic_long_t stamp; struct lock_class_key acquire_key; struct lock_class_key mutex_key; const char *acquire_name; const char *mutex_name; unsigned int is_wait_die; }; struct ww_mutex { struct WW_MUTEX_BASE base; struct ww_acquire_ctx *ctx; #ifdef DEBUG_WW_MUTEXES struct ww_class *ww_class; #endif }; struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; unsigned int acquired; unsigned short wounded; unsigned short is_wait_die; #ifdef DEBUG_WW_MUTEXES unsigned int done_acquire; struct ww_class *ww_class; void *contending_lock; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH unsigned int deadlock_inject_interval; unsigned int deadlock_inject_countdown; #endif }; #define __WW_CLASS_INITIALIZER(ww_class, _is_wait_die) \ { .stamp = ATOMIC_LONG_INIT(0) \ , .acquire_name = #ww_class "_acquire" \ , .mutex_name = #ww_class "_mutex" \ , .is_wait_die = _is_wait_die } #define DEFINE_WD_CLASS(classname) \ struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 1) #define DEFINE_WW_CLASS(classname) \ struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 0) /** * ww_mutex_init - initialize the w/w mutex * @lock: the mutex to be initialized * @ww_class: the w/w class the mutex should belong to * * Initialize the w/w mutex to unlocked state and associate it with the given * class. Static define macro for w/w mutex is not provided and this function * is the only way to properly initialize the w/w mutex. * * It is not allowed to initialize an already locked mutex. */ static inline void ww_mutex_init(struct ww_mutex *lock, struct ww_class *ww_class) { ww_mutex_base_init(&lock->base, ww_class->mutex_name, &ww_class->mutex_key); lock->ctx = NULL; #ifdef DEBUG_WW_MUTEXES lock->ww_class = ww_class; #endif } /** * ww_acquire_init - initialize a w/w acquire context * @ctx: w/w acquire context to initialize * @ww_class: w/w class of the context * * Initializes an context to acquire multiple mutexes of the given w/w class. * * Context-based w/w mutex acquiring can be done in any order whatsoever within * a given lock class. Deadlocks will be detected and handled with the * wait/die logic. * * Mixing of context-based w/w mutex acquiring and single w/w mutex locking can * result in undetected deadlocks and is so forbidden. Mixing different contexts * for the same w/w class when acquiring mutexes can also result in undetected * deadlocks, and is hence also forbidden. Both types of abuse will be caught by * enabling CONFIG_PROVE_LOCKING. * * Nesting of acquire contexts for _different_ w/w classes is possible, subject * to the usual locking rules between different lock classes. * * An acquire context must be released with ww_acquire_fini by the same task * before the memory is freed. It is recommended to allocate the context itself * on the stack. */ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, struct ww_class *ww_class) { ctx->task = current; ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp); ctx->acquired = 0; ctx->wounded = false; ctx->is_wait_die = ww_class->is_wait_die; #ifdef DEBUG_WW_MUTEXES ctx->ww_class = ww_class; ctx->done_acquire = 0; ctx->contending_lock = NULL; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC debug_check_no_locks_freed((void *)ctx, sizeof(*ctx)); lockdep_init_map(&ctx->dep_map, ww_class->acquire_name, &ww_class->acquire_key, 0); mutex_acquire(&ctx->dep_map, 0, 0, _RET_IP_); #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH ctx->deadlock_inject_interval = 1; ctx->deadlock_inject_countdown = ctx->stamp & 0xf; #endif } /** * ww_acquire_done - marks the end of the acquire phase * @ctx: the acquire context * * Marks the end of the acquire phase, any further w/w mutex lock calls using * this context are forbidden. * * Calling this function is optional, it is just useful to document w/w mutex * code and clearly designated the acquire phase from actually using the locked * data structures. */ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) { #ifdef DEBUG_WW_MUTEXES lockdep_assert_held(ctx); DEBUG_LOCKS_WARN_ON(ctx->done_acquire); ctx->done_acquire = 1; #endif } /** * ww_acquire_fini - releases a w/w acquire context * @ctx: the acquire context to free * * Releases a w/w acquire context. This must be called _after_ all acquired w/w * mutexes have been released with ww_mutex_unlock. */ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) { #ifdef CONFIG_DEBUG_LOCK_ALLOC mutex_release(&ctx->dep_map, _THIS_IP_); #endif #ifdef DEBUG_WW_MUTEXES DEBUG_LOCKS_WARN_ON(ctx->acquired); if (!IS_ENABLED(CONFIG_PROVE_LOCKING)) /* * lockdep will normally handle this, * but fail without anyway */ ctx->done_acquire = 1; if (!IS_ENABLED(CONFIG_DEBUG_LOCK_ALLOC)) /* ensure ww_acquire_fini will still fail if called twice */ ctx->acquired = ~0U; #endif } /** * ww_mutex_lock - acquire the w/w mutex * @lock: the mutex to be acquired * @ctx: w/w acquire context, or NULL to acquire only a single lock. * * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. * * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow. Alternatively callers can opt to not acquire this * lock and proceed with trying to acquire further w/w mutexes (e.g. when * scanning through lru lists trying to free resources). * * The mutex must later on be released by the same task that * acquired it. The task may not exit without first unlocking the mutex. Also, * kernel memory where the mutex resides must not be freed with the mutex still * locked. The mutex must first be initialized (or statically defined) before it * can be locked. memset()-ing the mutex to 0 is not allowed. The mutex must be * of the same w/w lock class as was used to initialize the acquire context. * * A mutex acquired with this function must be released with ww_mutex_unlock. */ extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx); /** * ww_mutex_lock_interruptible - acquire the w/w mutex, interruptible * @lock: the mutex to be acquired * @ctx: w/w acquire context * * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. If a * signal arrives while waiting for the lock then this function returns -EINTR. * * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow_interruptible. Alternatively callers can opt to * not acquire this lock and proceed with trying to acquire further w/w mutexes * (e.g. when scanning through lru lists trying to free resources). * * The mutex must later on be released by the same task that * acquired it. The task may not exit without first unlocking the mutex. Also, * kernel memory where the mutex resides must not be freed with the mutex still * locked. The mutex must first be initialized (or statically defined) before it * can be locked. memset()-ing the mutex to 0 is not allowed. The mutex must be * of the same w/w lock class as was used to initialize the acquire context. * * A mutex acquired with this function must be released with ww_mutex_unlock. */ extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx); /** * ww_mutex_lock_slow - slowpath acquiring of the w/w mutex * @lock: the mutex to be acquired * @ctx: w/w acquire context * * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available. * * The caller must have released all w/w mutexes already acquired with the * context and then call this function on the contended lock. * * Afterwards the caller may continue to (re)acquire the other w/w mutexes it * needs with ww_mutex_lock. Note that the -EALREADY return code from * ww_mutex_lock can be used to avoid locking this contended mutex twice. * * It is forbidden to call this function with any other w/w mutexes associated * with the context held. It is forbidden to call this on anything else than the * contending mutex. * * Note that the slowpath lock acquiring can also be done by calling * ww_mutex_lock directly. This function here is simply to help w/w mutex * locking code readability by clearly denoting the slowpath. */ static inline void ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { int ret; #ifdef DEBUG_WW_MUTEXES DEBUG_LOCKS_WARN_ON(!ctx->contending_lock); #endif ret = ww_mutex_lock(lock, ctx); (void)ret; } /** * ww_mutex_lock_slow_interruptible - slowpath acquiring of the w/w mutex, interruptible * @lock: the mutex to be acquired * @ctx: w/w acquire context * * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available and returns 0 when the lock has * been acquired. If a signal arrives while waiting for the lock then this * function returns -EINTR. * * The caller must have released all w/w mutexes already acquired with the * context and then call this function on the contended lock. * * Afterwards the caller may continue to (re)acquire the other w/w mutexes it * needs with ww_mutex_lock. Note that the -EALREADY return code from * ww_mutex_lock can be used to avoid locking this contended mutex twice. * * It is forbidden to call this function with any other w/w mutexes associated * with the given context held. It is forbidden to call this on anything else * than the contending mutex. * * Note that the slowpath lock acquiring can also be done by calling * ww_mutex_lock_interruptible directly. This function here is simply to help * w/w mutex locking code readability by clearly denoting the slowpath. */ static inline int __must_check ww_mutex_lock_slow_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { #ifdef DEBUG_WW_MUTEXES DEBUG_LOCKS_WARN_ON(!ctx->contending_lock); #endif return ww_mutex_lock_interruptible(lock, ctx); } extern void ww_mutex_unlock(struct ww_mutex *lock); extern int __must_check ww_mutex_trylock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx); /*** * ww_mutex_destroy - mark a w/w mutex unusable * @lock: the mutex to be destroyed * * This function marks the mutex uninitialized, and any subsequent * use of the mutex is forbidden. The mutex must not be locked when * this function is called. */ static inline void ww_mutex_destroy(struct ww_mutex *lock) { #ifndef CONFIG_PREEMPT_RT mutex_destroy(&lock->base); #endif } /** * ww_mutex_is_locked - is the w/w mutex locked * @lock: the mutex to be queried * * Returns 1 if the mutex is locked, 0 if unlocked. */ static inline bool ww_mutex_is_locked(struct ww_mutex *lock) { return ww_mutex_base_is_locked(&lock->base); } #endif |
| 1 8 1 7 7 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2003-2008 Takahiro Hirofuchi * Copyright (C) 2015-2016 Nobuo Iwata */ #include <linux/kthread.h> #include <linux/file.h> #include <linux/net.h> #include <linux/platform_device.h> #include <linux/slab.h> /* Hardening for Spectre-v1 */ #include <linux/nospec.h> #include "usbip_common.h" #include "vhci.h" /* TODO: refine locking ?*/ /* * output example: * hub port sta spd dev sockfd local_busid * hs 0000 004 000 00000000 000003 1-2.3 * ................................................ * ss 0008 004 000 00000000 000004 2-3.4 * ................................................ * * Output includes socket fd instead of socket pointer address to avoid * leaking kernel memory address in: * /sys/devices/platform/vhci_hcd.0/status and in debug output. * The socket pointer address is not used at the moment and it was made * visible as a convenient way to find IP address from socket pointer * address by looking up /proc/net/{tcp,tcp6}. As this opens a security * hole, the change is made to use sockfd instead. * */ static void port_show_vhci(char **out, int hub, int port, struct vhci_device *vdev) { if (hub == HUB_SPEED_HIGH) *out += sprintf(*out, "hs %04u %03u ", port, vdev->ud.status); else /* hub == HUB_SPEED_SUPER */ *out += sprintf(*out, "ss %04u %03u ", port, vdev->ud.status); if (vdev->ud.status == VDEV_ST_USED) { *out += sprintf(*out, "%03u %08x ", vdev->speed, vdev->devid); *out += sprintf(*out, "%06u %s", vdev->ud.sockfd, dev_name(&vdev->udev->dev)); } else { *out += sprintf(*out, "000 00000000 "); *out += sprintf(*out, "000000 0-0"); } *out += sprintf(*out, "\n"); } /* Sysfs entry to show port status */ static ssize_t status_show_vhci(int pdev_nr, char *out) { struct platform_device *pdev = vhcis[pdev_nr].pdev; struct vhci *vhci; struct usb_hcd *hcd; struct vhci_hcd *vhci_hcd; char *s = out; int i; unsigned long flags; if (!pdev || !out) { usbip_dbg_vhci_sysfs("show status error\n"); return 0; } hcd = platform_get_drvdata(pdev); vhci_hcd = hcd_to_vhci_hcd(hcd); vhci = vhci_hcd->vhci; spin_lock_irqsave(&vhci->lock, flags); for (i = 0; i < VHCI_HC_PORTS; i++) { struct vhci_device *vdev = &vhci->vhci_hcd_hs->vdev[i]; spin_lock(&vdev->ud.lock); port_show_vhci(&out, HUB_SPEED_HIGH, pdev_nr * VHCI_PORTS + i, vdev); spin_unlock(&vdev->ud.lock); } for (i = 0; i < VHCI_HC_PORTS; i++) { struct vhci_device *vdev = &vhci->vhci_hcd_ss->vdev[i]; spin_lock(&vdev->ud.lock); port_show_vhci(&out, HUB_SPEED_SUPER, pdev_nr * VHCI_PORTS + VHCI_HC_PORTS + i, vdev); spin_unlock(&vdev->ud.lock); } spin_unlock_irqrestore(&vhci->lock, flags); return out - s; } static ssize_t status_show_not_ready(int pdev_nr, char *out) { char *s = out; int i = 0; for (i = 0; i < VHCI_HC_PORTS; i++) { out += sprintf(out, "hs %04u %03u ", (pdev_nr * VHCI_PORTS) + i, VDEV_ST_NOTASSIGNED); out += sprintf(out, "000 00000000 0000000000000000 0-0"); out += sprintf(out, "\n"); } for (i = 0; i < VHCI_HC_PORTS; i++) { out += sprintf(out, "ss %04u %03u ", (pdev_nr * VHCI_PORTS) + VHCI_HC_PORTS + i, VDEV_ST_NOTASSIGNED); out += sprintf(out, "000 00000000 0000000000000000 0-0"); out += sprintf(out, "\n"); } return out - s; } static int status_name_to_id(const char *name) { char *c; long val; int ret; c = strchr(name, '.'); if (c == NULL) return 0; ret = kstrtol(c+1, 10, &val); if (ret < 0) return ret; return val; } static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *out) { char *s = out; int pdev_nr; out += sprintf(out, "hub port sta spd dev sockfd local_busid\n"); pdev_nr = status_name_to_id(attr->attr.name); if (pdev_nr < 0) out += status_show_not_ready(pdev_nr, out); else out += status_show_vhci(pdev_nr, out); return out - s; } static ssize_t nports_show(struct device *dev, struct device_attribute *attr, char *out) { char *s = out; /* * Half the ports are for SPEED_HIGH and half for SPEED_SUPER, * thus the * 2. */ out += sprintf(out, "%d\n", VHCI_PORTS * vhci_num_controllers); return out - s; } static DEVICE_ATTR_RO(nports); /* Sysfs entry to shutdown a virtual connection */ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport) { struct vhci_device *vdev = &vhci_hcd->vdev[rhport]; struct vhci *vhci = vhci_hcd->vhci; unsigned long flags; usbip_dbg_vhci_sysfs("enter\n"); mutex_lock(&vdev->ud.sysfs_lock); /* lock */ spin_lock_irqsave(&vhci->lock, flags); spin_lock(&vdev->ud.lock); if (vdev->ud.status == VDEV_ST_NULL) { pr_err("not connected %d\n", vdev->ud.status); /* unlock */ spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); mutex_unlock(&vdev->ud.sysfs_lock); return -EINVAL; } /* unlock */ spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN); mutex_unlock(&vdev->ud.sysfs_lock); return 0; } static int valid_port(__u32 *pdev_nr, __u32 *rhport) { if (*pdev_nr >= vhci_num_controllers) { pr_err("pdev %u\n", *pdev_nr); return 0; } *pdev_nr = array_index_nospec(*pdev_nr, vhci_num_controllers); if (*rhport >= VHCI_HC_PORTS) { pr_err("rhport %u\n", *rhport); return 0; } *rhport = array_index_nospec(*rhport, VHCI_HC_PORTS); return 1; } static ssize_t detach_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { __u32 port = 0, pdev_nr = 0, rhport = 0; struct usb_hcd *hcd; struct vhci_hcd *vhci_hcd; int ret; if (kstrtoint(buf, 10, &port) < 0) return -EINVAL; pdev_nr = port_to_pdev_nr(port); rhport = port_to_rhport(port); if (!valid_port(&pdev_nr, &rhport)) return -EINVAL; hcd = platform_get_drvdata(vhcis[pdev_nr].pdev); if (hcd == NULL) { dev_err(dev, "port is not ready %u\n", port); return -EAGAIN; } usbip_dbg_vhci_sysfs("rhport %d\n", rhport); if ((port / VHCI_HC_PORTS) % 2) vhci_hcd = hcd_to_vhci_hcd(hcd)->vhci->vhci_hcd_ss; else vhci_hcd = hcd_to_vhci_hcd(hcd)->vhci->vhci_hcd_hs; ret = vhci_port_disconnect(vhci_hcd, rhport); if (ret < 0) return -EINVAL; usbip_dbg_vhci_sysfs("Leave\n"); return count; } static DEVICE_ATTR_WO(detach); static int valid_args(__u32 *pdev_nr, __u32 *rhport, enum usb_device_speed speed) { if (!valid_port(pdev_nr, rhport)) { return 0; } switch (speed) { case USB_SPEED_LOW: case USB_SPEED_FULL: case USB_SPEED_HIGH: case USB_SPEED_WIRELESS: case USB_SPEED_SUPER: break; default: pr_err("Failed attach request for unsupported USB speed: %s\n", usb_speed_string(speed)); return 0; } return 1; } /* Sysfs entry to establish a virtual connection */ /* * To start a new USB/IP attachment, a userland program needs to setup a TCP * connection and then write its socket descriptor with remote device * information into this sysfs file. * * A remote device is virtually attached to the root-hub port of @rhport with * @speed. @devid is embedded into a request to specify the remote device in a * server host. * * write() returns 0 on success, else negative errno. */ static ssize_t attach_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct socket *socket; int sockfd = 0; __u32 port = 0, pdev_nr = 0, rhport = 0, devid = 0, speed = 0; struct usb_hcd *hcd; struct vhci_hcd *vhci_hcd; struct vhci_device *vdev; struct vhci *vhci; int err; unsigned long flags; struct task_struct *tcp_rx = NULL; struct task_struct *tcp_tx = NULL; /* * @rhport: port number of vhci_hcd * @sockfd: socket descriptor of an established TCP connection * @devid: unique device identifier in a remote host * @speed: usb device speed in a remote host */ if (sscanf(buf, "%u %u %u %u", &port, &sockfd, &devid, &speed) != 4) return -EINVAL; pdev_nr = port_to_pdev_nr(port); rhport = port_to_rhport(port); usbip_dbg_vhci_sysfs("port(%u) pdev(%d) rhport(%u)\n", port, pdev_nr, rhport); usbip_dbg_vhci_sysfs("sockfd(%u) devid(%u) speed(%u)\n", sockfd, devid, speed); /* check received parameters */ if (!valid_args(&pdev_nr, &rhport, speed)) return -EINVAL; hcd = platform_get_drvdata(vhcis[pdev_nr].pdev); if (hcd == NULL) { dev_err(dev, "port %d is not ready\n", port); return -EAGAIN; } vhci_hcd = hcd_to_vhci_hcd(hcd); vhci = vhci_hcd->vhci; if (speed == USB_SPEED_SUPER) vdev = &vhci->vhci_hcd_ss->vdev[rhport]; else vdev = &vhci->vhci_hcd_hs->vdev[rhport]; mutex_lock(&vdev->ud.sysfs_lock); /* Extract socket from fd. */ socket = sockfd_lookup(sockfd, &err); if (!socket) { dev_err(dev, "failed to lookup sock"); err = -EINVAL; goto unlock_mutex; } if (socket->type != SOCK_STREAM) { dev_err(dev, "Expecting SOCK_STREAM - found %d", socket->type); sockfd_put(socket); err = -EINVAL; goto unlock_mutex; } /* create threads before locking */ tcp_rx = kthread_create(vhci_rx_loop, &vdev->ud, "vhci_rx"); if (IS_ERR(tcp_rx)) { sockfd_put(socket); err = -EINVAL; goto unlock_mutex; } tcp_tx = kthread_create(vhci_tx_loop, &vdev->ud, "vhci_tx"); if (IS_ERR(tcp_tx)) { kthread_stop(tcp_rx); sockfd_put(socket); err = -EINVAL; goto unlock_mutex; } /* get task structs now */ get_task_struct(tcp_rx); get_task_struct(tcp_tx); /* now begin lock until setting vdev status set */ spin_lock_irqsave(&vhci->lock, flags); spin_lock(&vdev->ud.lock); if (vdev->ud.status != VDEV_ST_NULL) { /* end of the lock */ spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); sockfd_put(socket); kthread_stop_put(tcp_rx); kthread_stop_put(tcp_tx); dev_err(dev, "port %d already used\n", rhport); /* * Will be retried from userspace * if there's another free port. */ err = -EBUSY; goto unlock_mutex; } dev_info(dev, "pdev(%u) rhport(%u) sockfd(%d)\n", pdev_nr, rhport, sockfd); dev_info(dev, "devid(%u) speed(%u) speed_str(%s)\n", devid, speed, usb_speed_string(speed)); vdev->devid = devid; vdev->speed = speed; vdev->ud.sockfd = sockfd; vdev->ud.tcp_socket = socket; vdev->ud.tcp_rx = tcp_rx; vdev->ud.tcp_tx = tcp_tx; vdev->ud.status = VDEV_ST_NOTASSIGNED; usbip_kcov_handle_init(&vdev->ud); spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); /* end the lock */ wake_up_process(vdev->ud.tcp_rx); wake_up_process(vdev->ud.tcp_tx); rh_port_connect(vdev, speed); dev_info(dev, "Device attached\n"); mutex_unlock(&vdev->ud.sysfs_lock); return count; unlock_mutex: mutex_unlock(&vdev->ud.sysfs_lock); return err; } static DEVICE_ATTR_WO(attach); #define MAX_STATUS_NAME 16 struct status_attr { struct device_attribute attr; char name[MAX_STATUS_NAME+1]; }; static struct status_attr *status_attrs; static void set_status_attr(int id) { struct status_attr *status; status = status_attrs + id; if (id == 0) strcpy(status->name, "status"); else snprintf(status->name, MAX_STATUS_NAME+1, "status.%d", id); status->attr.attr.name = status->name; status->attr.attr.mode = S_IRUGO; status->attr.show = status_show; sysfs_attr_init(&status->attr.attr); } static int init_status_attrs(void) { int id; status_attrs = kcalloc(vhci_num_controllers, sizeof(struct status_attr), GFP_KERNEL); if (status_attrs == NULL) return -ENOMEM; for (id = 0; id < vhci_num_controllers; id++) set_status_attr(id); return 0; } static void finish_status_attrs(void) { kfree(status_attrs); } struct attribute_group vhci_attr_group = { .attrs = NULL, }; int vhci_init_attr_group(void) { struct attribute **attrs; int ret, i; attrs = kcalloc((vhci_num_controllers + 5), sizeof(struct attribute *), GFP_KERNEL); if (attrs == NULL) return -ENOMEM; ret = init_status_attrs(); if (ret) { kfree(attrs); return ret; } *attrs = &dev_attr_nports.attr; *(attrs + 1) = &dev_attr_detach.attr; *(attrs + 2) = &dev_attr_attach.attr; *(attrs + 3) = &dev_attr_usbip_debug.attr; for (i = 0; i < vhci_num_controllers; i++) *(attrs + i + 4) = &((status_attrs + i)->attr.attr); vhci_attr_group.attrs = attrs; return 0; } void vhci_finish_attr_group(void) { finish_status_attrs(); kfree(vhci_attr_group.attrs); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CFG802154_RDEV_OPS #define __CFG802154_RDEV_OPS #include <net/cfg802154.h> #include "core.h" #include "trace.h" static inline struct net_device * rdev_add_virtual_intf_deprecated(struct cfg802154_registered_device *rdev, const char *name, unsigned char name_assign_type, int type) { return rdev->ops->add_virtual_intf_deprecated(&rdev->wpan_phy, name, name_assign_type, type); } static inline void rdev_del_virtual_intf_deprecated(struct cfg802154_registered_device *rdev, struct net_device *dev) { rdev->ops->del_virtual_intf_deprecated(&rdev->wpan_phy, dev); } static inline int rdev_suspend(struct cfg802154_registered_device *rdev) { int ret; trace_802154_rdev_suspend(&rdev->wpan_phy); ret = rdev->ops->suspend(&rdev->wpan_phy); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_resume(struct cfg802154_registered_device *rdev) { int ret; trace_802154_rdev_resume(&rdev->wpan_phy); ret = rdev->ops->resume(&rdev->wpan_phy); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_add_virtual_intf(struct cfg802154_registered_device *rdev, char *name, unsigned char name_assign_type, enum nl802154_iftype type, __le64 extended_addr) { int ret; trace_802154_rdev_add_virtual_intf(&rdev->wpan_phy, name, type, extended_addr); ret = rdev->ops->add_virtual_intf(&rdev->wpan_phy, name, name_assign_type, type, extended_addr); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_del_virtual_intf(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { int ret; trace_802154_rdev_del_virtual_intf(&rdev->wpan_phy, wpan_dev); ret = rdev->ops->del_virtual_intf(&rdev->wpan_phy, wpan_dev); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_channel(struct cfg802154_registered_device *rdev, u8 page, u8 channel) { int ret; trace_802154_rdev_set_channel(&rdev->wpan_phy, page, channel); ret = rdev->ops->set_channel(&rdev->wpan_phy, page, channel); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_cca_mode(struct cfg802154_registered_device *rdev, const struct wpan_phy_cca *cca) { int ret; trace_802154_rdev_set_cca_mode(&rdev->wpan_phy, cca); ret = rdev->ops->set_cca_mode(&rdev->wpan_phy, cca); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_cca_ed_level(struct cfg802154_registered_device *rdev, s32 ed_level) { int ret; trace_802154_rdev_set_cca_ed_level(&rdev->wpan_phy, ed_level); ret = rdev->ops->set_cca_ed_level(&rdev->wpan_phy, ed_level); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_tx_power(struct cfg802154_registered_device *rdev, s32 power) { int ret; trace_802154_rdev_set_tx_power(&rdev->wpan_phy, power); ret = rdev->ops->set_tx_power(&rdev->wpan_phy, power); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_pan_id(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le16 pan_id) { int ret; trace_802154_rdev_set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id); ret = rdev->ops->set_pan_id(&rdev->wpan_phy, wpan_dev, pan_id); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_short_addr(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le16 short_addr) { int ret; trace_802154_rdev_set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr); ret = rdev->ops->set_short_addr(&rdev->wpan_phy, wpan_dev, short_addr); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_backoff_exponent(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, u8 min_be, u8 max_be) { int ret; trace_802154_rdev_set_backoff_exponent(&rdev->wpan_phy, wpan_dev, min_be, max_be); ret = rdev->ops->set_backoff_exponent(&rdev->wpan_phy, wpan_dev, min_be, max_be); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_max_csma_backoffs(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, u8 max_csma_backoffs) { int ret; trace_802154_rdev_set_csma_backoffs(&rdev->wpan_phy, wpan_dev, max_csma_backoffs); ret = rdev->ops->set_max_csma_backoffs(&rdev->wpan_phy, wpan_dev, max_csma_backoffs); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_max_frame_retries(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, s8 max_frame_retries) { int ret; trace_802154_rdev_set_max_frame_retries(&rdev->wpan_phy, wpan_dev, max_frame_retries); ret = rdev->ops->set_max_frame_retries(&rdev->wpan_phy, wpan_dev, max_frame_retries); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_lbt_mode(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, bool mode) { int ret; trace_802154_rdev_set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode); ret = rdev->ops->set_lbt_mode(&rdev->wpan_phy, wpan_dev, mode); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_set_ackreq_default(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, bool ackreq) { int ret; trace_802154_rdev_set_ackreq_default(&rdev->wpan_phy, wpan_dev, ackreq); ret = rdev->ops->set_ackreq_default(&rdev->wpan_phy, wpan_dev, ackreq); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_trigger_scan(struct cfg802154_registered_device *rdev, struct cfg802154_scan_request *request) { int ret; if (!rdev->ops->trigger_scan) return -EOPNOTSUPP; trace_802154_rdev_trigger_scan(&rdev->wpan_phy, request); ret = rdev->ops->trigger_scan(&rdev->wpan_phy, request); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_abort_scan(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { int ret; if (!rdev->ops->abort_scan) return -EOPNOTSUPP; trace_802154_rdev_abort_scan(&rdev->wpan_phy, wpan_dev); ret = rdev->ops->abort_scan(&rdev->wpan_phy, wpan_dev); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_send_beacons(struct cfg802154_registered_device *rdev, struct cfg802154_beacon_request *request) { int ret; if (!rdev->ops->send_beacons) return -EOPNOTSUPP; trace_802154_rdev_send_beacons(&rdev->wpan_phy, request); ret = rdev->ops->send_beacons(&rdev->wpan_phy, request); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_stop_beacons(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { int ret; if (!rdev->ops->stop_beacons) return -EOPNOTSUPP; trace_802154_rdev_stop_beacons(&rdev->wpan_phy, wpan_dev); ret = rdev->ops->stop_beacons(&rdev->wpan_phy, wpan_dev); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_associate(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, struct ieee802154_addr *coord) { int ret; if (!rdev->ops->associate) return -EOPNOTSUPP; trace_802154_rdev_associate(&rdev->wpan_phy, wpan_dev, coord); ret = rdev->ops->associate(&rdev->wpan_phy, wpan_dev, coord); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } static inline int rdev_disassociate(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, struct ieee802154_addr *target) { int ret; if (!rdev->ops->disassociate) return -EOPNOTSUPP; trace_802154_rdev_disassociate(&rdev->wpan_phy, wpan_dev, target); ret = rdev->ops->disassociate(&rdev->wpan_phy, wpan_dev, target); trace_802154_rdev_return_int(&rdev->wpan_phy, ret); return ret; } #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL /* TODO this is already a nl802154, so move into ieee802154 */ static inline void rdev_get_llsec_table(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, struct ieee802154_llsec_table **table) { rdev->ops->get_llsec_table(&rdev->wpan_phy, wpan_dev, table); } static inline void rdev_lock_llsec_table(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { rdev->ops->lock_llsec_table(&rdev->wpan_phy, wpan_dev); } static inline void rdev_unlock_llsec_table(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev) { rdev->ops->unlock_llsec_table(&rdev->wpan_phy, wpan_dev); } static inline int rdev_get_llsec_params(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, struct ieee802154_llsec_params *params) { return rdev->ops->get_llsec_params(&rdev->wpan_phy, wpan_dev, params); } static inline int rdev_set_llsec_params(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_params *params, u32 changed) { return rdev->ops->set_llsec_params(&rdev->wpan_phy, wpan_dev, params, changed); } static inline int rdev_add_llsec_key(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_key_id *id, const struct ieee802154_llsec_key *key) { return rdev->ops->add_llsec_key(&rdev->wpan_phy, wpan_dev, id, key); } static inline int rdev_del_llsec_key(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_key_id *id) { return rdev->ops->del_llsec_key(&rdev->wpan_phy, wpan_dev, id); } static inline int rdev_add_seclevel(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_seclevel *sl) { return rdev->ops->add_seclevel(&rdev->wpan_phy, wpan_dev, sl); } static inline int rdev_del_seclevel(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_seclevel *sl) { return rdev->ops->del_seclevel(&rdev->wpan_phy, wpan_dev, sl); } static inline int rdev_add_device(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, const struct ieee802154_llsec_device *dev_desc) { return rdev->ops->add_device(&rdev->wpan_phy, wpan_dev, dev_desc); } static inline int rdev_del_device(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le64 extended_addr) { return rdev->ops->del_device(&rdev->wpan_phy, wpan_dev, extended_addr); } static inline int rdev_add_devkey(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le64 extended_addr, const struct ieee802154_llsec_device_key *devkey) { return rdev->ops->add_devkey(&rdev->wpan_phy, wpan_dev, extended_addr, devkey); } static inline int rdev_del_devkey(struct cfg802154_registered_device *rdev, struct wpan_dev *wpan_dev, __le64 extended_addr, const struct ieee802154_llsec_device_key *devkey) { return rdev->ops->del_devkey(&rdev->wpan_phy, wpan_dev, extended_addr, devkey); } #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ #endif /* __CFG802154_RDEV_OPS */ |
| 4 2 3 3 2 1 3 4 12 12 2 2 2 15 1 14 1 14 29 28 20 20 20 20 20 14 1 13 13 11 13 8 7 13 13 12 9 13 11 13 29 29 29 20 1 20 19 20 18 19 19 19 18 29 29 28 29 29 25 28 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Information interface for ALSA driver * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/module.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/info.h> #include <linux/utsname.h> #include <linux/proc_fs.h> #include <linux/mutex.h> int snd_info_check_reserved_words(const char *str) { static const char * const reserved[] = { "version", "meminfo", "memdebug", "detect", "devices", "oss", "cards", "timers", "synth", "pcm", "seq", NULL }; const char * const *xstr = reserved; while (*xstr) { if (!strcmp(*xstr, str)) return 0; xstr++; } if (!strncmp(str, "card", 4)) return 0; return 1; } static DEFINE_MUTEX(info_mutex); struct snd_info_private_data { struct snd_info_buffer *rbuffer; struct snd_info_buffer *wbuffer; struct snd_info_entry *entry; void *file_private_data; }; static int snd_info_version_init(void); static void snd_info_clear_entries(struct snd_info_entry *entry); /* */ static struct snd_info_entry *snd_proc_root; struct snd_info_entry *snd_seq_root; EXPORT_SYMBOL(snd_seq_root); #ifdef CONFIG_SND_OSSEMUL struct snd_info_entry *snd_oss_root; #endif static int alloc_info_private(struct snd_info_entry *entry, struct snd_info_private_data **ret) { struct snd_info_private_data *data; if (!entry || !entry->p) return -ENODEV; if (!try_module_get(entry->module)) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) { module_put(entry->module); return -ENOMEM; } data->entry = entry; *ret = data; return 0; } static bool valid_pos(loff_t pos, size_t count) { if (pos < 0 || (long) pos != pos || (ssize_t) count < 0) return false; if ((unsigned long) pos + (unsigned long) count < (unsigned long) pos) return false; return true; } /* * file ops for binary proc files */ static loff_t snd_info_entry_llseek(struct file *file, loff_t offset, int orig) { struct snd_info_private_data *data; struct snd_info_entry *entry; loff_t size; data = file->private_data; entry = data->entry; guard(mutex)(&entry->access); if (entry->c.ops->llseek) return entry->c.ops->llseek(entry, data->file_private_data, file, offset, orig); size = entry->size; switch (orig) { case SEEK_SET: break; case SEEK_CUR: offset += file->f_pos; break; case SEEK_END: if (!size) return -EINVAL; offset += size; break; default: return -EINVAL; } if (offset < 0) return -EINVAL; if (size && offset > size) offset = size; file->f_pos = offset; return offset; } static ssize_t snd_info_entry_read(struct file *file, char __user *buffer, size_t count, loff_t * offset) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; size_t size; loff_t pos; pos = *offset; if (!valid_pos(pos, count)) return -EIO; if (pos >= entry->size) return 0; size = entry->size - pos; size = min(count, size); size = entry->c.ops->read(entry, data->file_private_data, file, buffer, size, pos); if ((ssize_t) size > 0) *offset = pos + size; return size; } static ssize_t snd_info_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t * offset) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; ssize_t size = 0; loff_t pos; pos = *offset; if (!valid_pos(pos, count)) return -EIO; if (count > 0) { size_t maxsize = entry->size - pos; count = min(count, maxsize); size = entry->c.ops->write(entry, data->file_private_data, file, buffer, count, pos); } if (size > 0) *offset = pos + size; return size; } static __poll_t snd_info_entry_poll(struct file *file, poll_table *wait) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; __poll_t mask = 0; if (entry->c.ops->poll) return entry->c.ops->poll(entry, data->file_private_data, file, wait); if (entry->c.ops->read) mask |= EPOLLIN | EPOLLRDNORM; if (entry->c.ops->write) mask |= EPOLLOUT | EPOLLWRNORM; return mask; } static long snd_info_entry_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; if (!entry->c.ops->ioctl) return -ENOTTY; return entry->c.ops->ioctl(entry, data->file_private_data, file, cmd, arg); } static int snd_info_entry_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); struct snd_info_private_data *data; struct snd_info_entry *entry; data = file->private_data; if (data == NULL) return 0; entry = data->entry; if (!entry->c.ops->mmap) return -ENXIO; return entry->c.ops->mmap(entry, data->file_private_data, inode, file, vma); } static int snd_info_entry_open(struct inode *inode, struct file *file) { struct snd_info_entry *entry = pde_data(inode); struct snd_info_private_data *data; int mode, err; guard(mutex)(&info_mutex); err = alloc_info_private(entry, &data); if (err < 0) return err; mode = file->f_flags & O_ACCMODE; if (((mode == O_RDONLY || mode == O_RDWR) && !entry->c.ops->read) || ((mode == O_WRONLY || mode == O_RDWR) && !entry->c.ops->write)) { err = -ENODEV; goto error; } if (entry->c.ops->open) { err = entry->c.ops->open(entry, mode, &data->file_private_data); if (err < 0) goto error; } file->private_data = data; return 0; error: kfree(data); module_put(entry->module); return err; } static int snd_info_entry_release(struct inode *inode, struct file *file) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; if (entry->c.ops->release) entry->c.ops->release(entry, file->f_flags & O_ACCMODE, data->file_private_data); module_put(entry->module); kfree(data); return 0; } static const struct proc_ops snd_info_entry_operations = { .proc_lseek = snd_info_entry_llseek, .proc_read = snd_info_entry_read, .proc_write = snd_info_entry_write, .proc_poll = snd_info_entry_poll, .proc_ioctl = snd_info_entry_ioctl, .proc_mmap = snd_info_entry_mmap, .proc_open = snd_info_entry_open, .proc_release = snd_info_entry_release, }; /* * file ops for text proc files */ static ssize_t snd_info_text_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *offset) { struct seq_file *m = file->private_data; struct snd_info_private_data *data = m->private; struct snd_info_entry *entry = data->entry; struct snd_info_buffer *buf; loff_t pos; size_t next; if (!entry->c.text.write) return -EIO; pos = *offset; if (!valid_pos(pos, count)) return -EIO; next = pos + count; /* don't handle too large text inputs */ if (next > 16 * 1024) return -EIO; guard(mutex)(&entry->access); buf = data->wbuffer; if (!buf) { data->wbuffer = buf = kzalloc(sizeof(*buf), GFP_KERNEL); if (!buf) return -ENOMEM; } if (next > buf->len) { char *nbuf = kvzalloc(PAGE_ALIGN(next), GFP_KERNEL); if (!nbuf) return -ENOMEM; kvfree(buf->buffer); buf->buffer = nbuf; buf->len = PAGE_ALIGN(next); } if (copy_from_user(buf->buffer + pos, buffer, count)) return -EFAULT; buf->size = next; *offset = next; return count; } static int snd_info_seq_show(struct seq_file *seq, void *p) { struct snd_info_private_data *data = seq->private; struct snd_info_entry *entry = data->entry; if (!entry->c.text.read) { return -EIO; } else { data->rbuffer->buffer = (char *)seq; /* XXX hack! */ entry->c.text.read(entry, data->rbuffer); } return 0; } static int snd_info_text_entry_open(struct inode *inode, struct file *file) { struct snd_info_entry *entry = pde_data(inode); struct snd_info_private_data *data; int err; guard(mutex)(&info_mutex); err = alloc_info_private(entry, &data); if (err < 0) return err; data->rbuffer = kzalloc(sizeof(*data->rbuffer), GFP_KERNEL); if (!data->rbuffer) { err = -ENOMEM; goto error; } if (entry->size) err = single_open_size(file, snd_info_seq_show, data, entry->size); else err = single_open(file, snd_info_seq_show, data); if (err < 0) goto error; return 0; error: kfree(data->rbuffer); kfree(data); module_put(entry->module); return err; } static int snd_info_text_entry_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct snd_info_private_data *data = m->private; struct snd_info_entry *entry = data->entry; if (data->wbuffer && entry->c.text.write) entry->c.text.write(entry, data->wbuffer); single_release(inode, file); kfree(data->rbuffer); if (data->wbuffer) { kvfree(data->wbuffer->buffer); kfree(data->wbuffer); } module_put(entry->module); kfree(data); return 0; } static const struct proc_ops snd_info_text_entry_ops = { .proc_open = snd_info_text_entry_open, .proc_release = snd_info_text_entry_release, .proc_write = snd_info_text_entry_write, .proc_lseek = seq_lseek, .proc_read = seq_read, }; static struct snd_info_entry *create_subdir(struct module *mod, const char *name) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(mod, name, NULL); if (!entry) return NULL; entry->mode = S_IFDIR | 0555; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); return NULL; } return entry; } static struct snd_info_entry * snd_info_create_entry(const char *name, struct snd_info_entry *parent, struct module *module); int __init snd_info_init(void) { snd_proc_root = snd_info_create_entry("asound", NULL, THIS_MODULE); if (!snd_proc_root) return -ENOMEM; snd_proc_root->mode = S_IFDIR | 0555; snd_proc_root->p = proc_mkdir("asound", NULL); if (!snd_proc_root->p) goto error; #ifdef CONFIG_SND_OSSEMUL snd_oss_root = create_subdir(THIS_MODULE, "oss"); if (!snd_oss_root) goto error; #endif #if IS_ENABLED(CONFIG_SND_SEQUENCER) snd_seq_root = create_subdir(THIS_MODULE, "seq"); if (!snd_seq_root) goto error; #endif if (snd_info_version_init() < 0 || snd_minor_info_init() < 0 || snd_minor_info_oss_init() < 0 || snd_card_info_init() < 0 || snd_info_minor_register() < 0) goto error; return 0; error: snd_info_free_entry(snd_proc_root); return -ENOMEM; } int __exit snd_info_done(void) { snd_info_free_entry(snd_proc_root); return 0; } static void snd_card_id_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_card *card = entry->private_data; snd_iprintf(buffer, "%s\n", card->id); } /* * create a card proc file * called from init.c */ int snd_info_card_create(struct snd_card *card) { char str[8]; struct snd_info_entry *entry; if (snd_BUG_ON(!card)) return -ENXIO; sprintf(str, "card%i", card->number); entry = create_subdir(card->module, str); if (!entry) return -ENOMEM; card->proc_root = entry; return snd_card_ro_proc_new(card, "id", card, snd_card_id_read); } /* * register the card proc file * called from init.c * can be called multiple times for reinitialization */ int snd_info_card_register(struct snd_card *card) { struct proc_dir_entry *p; int err; if (snd_BUG_ON(!card)) return -ENXIO; err = snd_info_register(card->proc_root); if (err < 0) return err; if (!strcmp(card->id, card->proc_root->name)) return 0; if (card->proc_root_link) return 0; p = proc_symlink(card->id, snd_proc_root->p, card->proc_root->name); if (!p) return -ENOMEM; card->proc_root_link = p; return 0; } /* * called on card->id change */ void snd_info_card_id_change(struct snd_card *card) { guard(mutex)(&info_mutex); if (card->proc_root_link) { proc_remove(card->proc_root_link); card->proc_root_link = NULL; } if (strcmp(card->id, card->proc_root->name)) card->proc_root_link = proc_symlink(card->id, snd_proc_root->p, card->proc_root->name); } /* * de-register the card proc file * called from init.c */ void snd_info_card_disconnect(struct snd_card *card) { if (!card) return; proc_remove(card->proc_root_link); if (card->proc_root) proc_remove(card->proc_root->p); guard(mutex)(&info_mutex); if (card->proc_root) snd_info_clear_entries(card->proc_root); card->proc_root_link = NULL; card->proc_root = NULL; } /* * release the card proc file resources * called from init.c */ int snd_info_card_free(struct snd_card *card) { if (!card) return 0; snd_info_free_entry(card->proc_root); card->proc_root = NULL; return 0; } /** * snd_info_get_line - read one line from the procfs buffer * @buffer: the procfs buffer * @line: the buffer to store * @len: the max. buffer size * * Reads one line from the buffer and stores the string. * * Return: Zero if successful, or 1 if error or EOF. */ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len) { int c; if (snd_BUG_ON(!buffer)) return 1; if (!buffer->buffer) return 1; if (len <= 0 || buffer->stop || buffer->error) return 1; while (!buffer->stop) { c = buffer->buffer[buffer->curr++]; if (buffer->curr >= buffer->size) buffer->stop = 1; if (c == '\n') break; if (len > 1) { len--; *line++ = c; } } *line = '\0'; return 0; } EXPORT_SYMBOL(snd_info_get_line); /** * snd_info_get_str - parse a string token * @dest: the buffer to store the string token * @src: the original string * @len: the max. length of token - 1 * * Parses the original string and copy a token to the given * string buffer. * * Return: The updated pointer of the original string so that * it can be used for the next call. */ const char *snd_info_get_str(char *dest, const char *src, int len) { int c; while (*src == ' ' || *src == '\t') src++; if (*src == '"' || *src == '\'') { c = *src++; while (--len > 0 && *src && *src != c) { *dest++ = *src++; } if (*src == c) src++; } else { while (--len > 0 && *src && *src != ' ' && *src != '\t') { *dest++ = *src++; } } *dest = 0; while (*src == ' ' || *src == '\t') src++; return src; } EXPORT_SYMBOL(snd_info_get_str); /* * snd_info_create_entry - create an info entry * @name: the proc file name * @parent: the parent directory * * Creates an info entry with the given file name and initializes as * the default state. * * Usually called from other functions such as * snd_info_create_card_entry(). * * Return: The pointer of the new instance, or %NULL on failure. */ static struct snd_info_entry * snd_info_create_entry(const char *name, struct snd_info_entry *parent, struct module *module) { struct snd_info_entry *entry; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry == NULL) return NULL; entry->name = kstrdup(name, GFP_KERNEL); if (entry->name == NULL) { kfree(entry); return NULL; } entry->mode = S_IFREG | 0444; entry->content = SNDRV_INFO_CONTENT_TEXT; mutex_init(&entry->access); INIT_LIST_HEAD(&entry->children); INIT_LIST_HEAD(&entry->list); entry->parent = parent; entry->module = module; if (parent) { guard(mutex)(&parent->access); list_add_tail(&entry->list, &parent->children); } return entry; } /** * snd_info_create_module_entry - create an info entry for the given module * @module: the module pointer * @name: the file name * @parent: the parent directory * * Creates a new info entry and assigns it to the given module. * * Return: The pointer of the new instance, or %NULL on failure. */ struct snd_info_entry *snd_info_create_module_entry(struct module * module, const char *name, struct snd_info_entry *parent) { if (!parent) parent = snd_proc_root; return snd_info_create_entry(name, parent, module); } EXPORT_SYMBOL(snd_info_create_module_entry); /** * snd_info_create_card_entry - create an info entry for the given card * @card: the card instance * @name: the file name * @parent: the parent directory * * Creates a new info entry and assigns it to the given card. * * Return: The pointer of the new instance, or %NULL on failure. */ struct snd_info_entry *snd_info_create_card_entry(struct snd_card *card, const char *name, struct snd_info_entry * parent) { if (!parent) parent = card->proc_root; return snd_info_create_entry(name, parent, card->module); } EXPORT_SYMBOL(snd_info_create_card_entry); static void snd_info_clear_entries(struct snd_info_entry *entry) { struct snd_info_entry *p; if (!entry->p) return; list_for_each_entry(p, &entry->children, list) snd_info_clear_entries(p); entry->p = NULL; } /** * snd_info_free_entry - release the info entry * @entry: the info entry * * Releases the info entry. */ void snd_info_free_entry(struct snd_info_entry * entry) { struct snd_info_entry *p, *n; if (!entry) return; if (entry->p) { proc_remove(entry->p); guard(mutex)(&info_mutex); snd_info_clear_entries(entry); } /* free all children at first */ list_for_each_entry_safe(p, n, &entry->children, list) snd_info_free_entry(p); p = entry->parent; if (p) { guard(mutex)(&p->access); list_del(&entry->list); } kfree(entry->name); if (entry->private_free) entry->private_free(entry); kfree(entry); } EXPORT_SYMBOL(snd_info_free_entry); static int __snd_info_register(struct snd_info_entry *entry) { struct proc_dir_entry *root, *p = NULL; if (snd_BUG_ON(!entry)) return -ENXIO; root = entry->parent == NULL ? snd_proc_root->p : entry->parent->p; guard(mutex)(&info_mutex); if (entry->p || !root) return 0; if (S_ISDIR(entry->mode)) { p = proc_mkdir_mode(entry->name, entry->mode, root); if (!p) return -ENOMEM; } else { const struct proc_ops *ops; if (entry->content == SNDRV_INFO_CONTENT_DATA) ops = &snd_info_entry_operations; else ops = &snd_info_text_entry_ops; p = proc_create_data(entry->name, entry->mode, root, ops, entry); if (!p) return -ENOMEM; proc_set_size(p, entry->size); } entry->p = p; return 0; } /** * snd_info_register - register the info entry * @entry: the info entry * * Registers the proc info entry. * The all children entries are registered recursively. * * Return: Zero if successful, or a negative error code on failure. */ int snd_info_register(struct snd_info_entry *entry) { struct snd_info_entry *p; int err; if (!entry->p) { err = __snd_info_register(entry); if (err < 0) return err; } list_for_each_entry(p, &entry->children, list) { err = snd_info_register(p); if (err < 0) return err; } return 0; } EXPORT_SYMBOL(snd_info_register); /** * snd_card_rw_proc_new - Create a read/write text proc file entry for the card * @card: the card instance * @name: the file name * @private_data: the arbitrary private data * @read: the read callback * @write: the write callback, NULL for read-only * * This proc file entry will be registered via snd_card_register() call, and * it will be removed automatically at the card removal, too. * * Return: zero if successful, or a negative error code */ int snd_card_rw_proc_new(struct snd_card *card, const char *name, void *private_data, void (*read)(struct snd_info_entry *, struct snd_info_buffer *), void (*write)(struct snd_info_entry *entry, struct snd_info_buffer *buffer)) { struct snd_info_entry *entry; entry = snd_info_create_card_entry(card, name, card->proc_root); if (!entry) return -ENOMEM; snd_info_set_text_ops(entry, private_data, read); if (write) { entry->mode |= 0200; entry->c.text.write = write; } return 0; } EXPORT_SYMBOL_GPL(snd_card_rw_proc_new); /* */ static void snd_info_version_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { snd_iprintf(buffer, "Advanced Linux Sound Architecture Driver Version k%s.\n", init_utsname()->release); } static int __init snd_info_version_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "version", NULL); if (entry == NULL) return -ENOMEM; entry->c.text.read = snd_info_version_read; return snd_info_register(entry); /* freed in error path */ } |
| 777 1313 1187 1187 822 823 128 130 86 87 1145 1143 1144 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/interval_tree.c - interval tree for mapping->i_mmap * * Copyright (C) 2012, Michel Lespinasse <walken@google.com> */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/rmap.h> #include <linux/interval_tree_generic.h> static inline unsigned long vma_start_pgoff(struct vm_area_struct *v) { return v->vm_pgoff; } static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) { return v->vm_pgoff + vma_pages(v) - 1; } INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff, /* empty */, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root) { struct rb_node **link; struct vm_area_struct *parent; unsigned long last = vma_last_pgoff(node); VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); if (!prev->shared.rb.rb_right) { parent = prev; link = &prev->shared.rb.rb_right; } else { parent = rb_entry(prev->shared.rb.rb_right, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; while (parent->shared.rb.rb_left) { parent = rb_entry(parent->shared.rb.rb_left, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; } link = &parent->shared.rb.rb_left; } node->shared.rb_subtree_last = last; rb_link_node(&node->shared.rb, &parent->shared.rb, link); rb_insert_augmented(&node->shared.rb, &root->rb_root, &vma_interval_tree_augment); } static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc) { return vma_start_pgoff(avc->vma); } static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc) { return vma_last_pgoff(avc->vma); } INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last, avc_start_pgoff, avc_last_pgoff, static inline, __anon_vma_interval_tree) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root) { #ifdef CONFIG_DEBUG_VM_RB node->cached_vma_start = avc_start_pgoff(node); node->cached_vma_last = avc_last_pgoff(node); #endif __anon_vma_interval_tree_insert(node, root); } void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root) { __anon_vma_interval_tree_remove(node, root); } struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_first(root, first, last); } struct anon_vma_chain * anon_vma_interval_tree_iter_next(struct anon_vma_chain *node, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_next(node, first, last); } #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node) { WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node)); WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node)); } #endif |
| 2 12 8 4 1 14 15 18 1 7 5 5 8 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 | // SPDX-License-Identifier: GPL-2.0-only /* Xtables module to match packets using a BPF filter. * Copyright 2013 Google Inc. * Written by Willem de Bruijn <willemb@google.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/syscalls.h> #include <linux/skbuff.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/netfilter/xt_bpf.h> #include <linux/netfilter/x_tables.h> MODULE_AUTHOR("Willem de Bruijn <willemb@google.com>"); MODULE_DESCRIPTION("Xtables: BPF filter match"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_bpf"); MODULE_ALIAS("ip6t_bpf"); static int __bpf_mt_check_bytecode(struct sock_filter *insns, __u16 len, struct bpf_prog **ret) { struct sock_fprog_kern program; if (len > XT_BPF_MAX_NUM_INSTR) return -EINVAL; program.len = len; program.filter = insns; if (bpf_prog_create(ret, &program)) { pr_info_ratelimited("check failed: parse error\n"); return -EINVAL; } return 0; } static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) { struct bpf_prog *prog; prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) return PTR_ERR(prog); *ret = prog; return 0; } static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) { if (strnlen(path, XT_BPF_PATH_MAX) == XT_BPF_PATH_MAX) return -EINVAL; *ret = bpf_prog_get_type_path(path, BPF_PROG_TYPE_SOCKET_FILTER); return PTR_ERR_OR_ZERO(*ret); } static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); } static int bpf_mt_check_v1(const struct xt_mtchk_param *par) { struct xt_bpf_info_v1 *info = par->matchinfo; if (info->mode == XT_BPF_MODE_BYTECODE) return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); else if (info->mode == XT_BPF_MODE_FD_ELF) return __bpf_mt_check_fd(info->fd, &info->filter); else if (info->mode == XT_BPF_MODE_PATH_PINNED) return __bpf_mt_check_path(info->path, &info->filter); else return -EINVAL; } static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_bpf_info *info = par->matchinfo; return bpf_prog_run(info->filter, skb); } static bool bpf_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_bpf_info_v1 *info = par->matchinfo; return !!bpf_prog_run_save_cb(info->filter, (struct sk_buff *) skb); } static void bpf_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_bpf_info *info = par->matchinfo; bpf_prog_destroy(info->filter); } static void bpf_mt_destroy_v1(const struct xt_mtdtor_param *par) { const struct xt_bpf_info_v1 *info = par->matchinfo; bpf_prog_destroy(info->filter); } static struct xt_match bpf_mt_reg[] __read_mostly = { { .name = "bpf", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = bpf_mt_check, .match = bpf_mt, .destroy = bpf_mt_destroy, .matchsize = sizeof(struct xt_bpf_info), .usersize = offsetof(struct xt_bpf_info, filter), .me = THIS_MODULE, }, { .name = "bpf", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = bpf_mt_check_v1, .match = bpf_mt_v1, .destroy = bpf_mt_destroy_v1, .matchsize = sizeof(struct xt_bpf_info_v1), .usersize = offsetof(struct xt_bpf_info_v1, filter), .me = THIS_MODULE, }, }; static int __init bpf_mt_init(void) { return xt_register_matches(bpf_mt_reg, ARRAY_SIZE(bpf_mt_reg)); } static void __exit bpf_mt_exit(void) { xt_unregister_matches(bpf_mt_reg, ARRAY_SIZE(bpf_mt_reg)); } module_init(bpf_mt_init); module_exit(bpf_mt_exit); |
| 10 10 10 7 10 2 4 12 11 11 10 1 8 5 3 48 1 2 3 3 10 2 17 5 6 10 8 1 21 4 8 6 11 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 | /* * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <net/sock.h> #include <linux/in.h> #include <linux/ipv6.h> #include <linux/if_arp.h> #include <linux/jhash.h> #include <linux/ratelimit.h> #include "rds.h" static struct rhashtable bind_hash_table; static const struct rhashtable_params ht_parms = { .nelem_hint = 768, .key_len = RDS_BOUND_KEY_LEN, .key_offset = offsetof(struct rds_sock, rs_bound_key), .head_offset = offsetof(struct rds_sock, rs_bound_node), .max_size = 16384, .min_size = 1024, }; /* Create a key for the bind hash table manipulation. Port is in network byte * order. */ static inline void __rds_create_bind_key(u8 *key, const struct in6_addr *addr, __be16 port, __u32 scope_id) { memcpy(key, addr, sizeof(*addr)); key += sizeof(*addr); memcpy(key, &port, sizeof(port)); key += sizeof(port); memcpy(key, &scope_id, sizeof(scope_id)); } /* * Return the rds_sock bound at the given local address. * * The rx path can race with rds_release. We notice if rds_release() has * marked this socket and don't return a rs ref to the rx path. */ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __u32 scope_id) { u8 key[RDS_BOUND_KEY_LEN]; struct rds_sock *rs; __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, ntohs(port)); return rs; } /* returns -ve errno or +ve port */ static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr, __be16 *port, __u32 scope_id) { int ret = -EADDRINUSE; u16 rover, last; u8 key[RDS_BOUND_KEY_LEN]; if (*port != 0) { rover = be16_to_cpu(*port); if (rover == RDS_FLAG_PROBE_PORT) return -EINVAL; last = rover; } else { rover = max_t(u16, get_random_u16(), 2); last = rover - 1; } do { if (rover == 0) rover++; if (rover == RDS_FLAG_PROBE_PORT) continue; __rds_create_bind_key(key, addr, cpu_to_be16(rover), scope_id); if (rhashtable_lookup_fast(&bind_hash_table, key, ht_parms)) continue; memcpy(rs->rs_bound_key, key, sizeof(rs->rs_bound_key)); rs->rs_bound_addr = *addr; net_get_random_once(&rs->rs_hash_initval, sizeof(rs->rs_hash_initval)); rs->rs_bound_port = cpu_to_be16(rover); rs->rs_bound_node.next = NULL; rds_sock_addref(rs); if (!rhashtable_insert_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms)) { *port = rs->rs_bound_port; rs->rs_bound_scope_id = scope_id; ret = 0; rdsdebug("rs %p binding to %pI6c:%d\n", rs, addr, (int)ntohs(*port)); break; } else { rs->rs_bound_addr = in6addr_any; rds_sock_put(rs); ret = -ENOMEM; break; } } while (rover++ != last); return ret; } void rds_remove_bound(struct rds_sock *rs) { if (ipv6_addr_any(&rs->rs_bound_addr)) return; rdsdebug("rs %p unbinding from %pI6c:%d\n", rs, &rs->rs_bound_addr, ntohs(rs->rs_bound_port)); rhashtable_remove_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms); rds_sock_put(rs); rs->rs_bound_addr = in6addr_any; } int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); struct in6_addr v6addr, *binding_addr; struct rds_transport *trans; __u32 scope_id = 0; int ret = 0; __be16 port; /* We allow an RDS socket to be bound to either IPv4 or IPv6 * address. */ if (addr_len < offsetofend(struct sockaddr, sa_family)) return -EINVAL; if (uaddr->sa_family == AF_INET) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; if (addr_len < sizeof(struct sockaddr_in) || sin->sin_addr.s_addr == htonl(INADDR_ANY) || sin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || ipv4_is_multicast(sin->sin_addr.s_addr)) return -EINVAL; ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr); binding_addr = &v6addr; port = sin->sin_port; #if IS_ENABLED(CONFIG_IPV6) } else if (uaddr->sa_family == AF_INET6) { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)uaddr; int addr_type; if (addr_len < sizeof(struct sockaddr_in6)) return -EINVAL; addr_type = ipv6_addr_type(&sin6->sin6_addr); if (!(addr_type & IPV6_ADDR_UNICAST)) { __be32 addr4; if (!(addr_type & IPV6_ADDR_MAPPED)) return -EINVAL; /* It is a mapped address. Need to do some sanity * checks. */ addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || ipv4_is_multicast(addr4)) return -EINVAL; } /* The scope ID must be specified for link local address. */ if (addr_type & IPV6_ADDR_LINKLOCAL) { if (sin6->sin6_scope_id == 0) return -EINVAL; scope_id = sin6->sin6_scope_id; } binding_addr = &sin6->sin6_addr; port = sin6->sin6_port; #endif } else { return -EINVAL; } lock_sock(sk); /* RDS socket does not allow re-binding. */ if (!ipv6_addr_any(&rs->rs_bound_addr)) { ret = -EINVAL; goto out; } /* Socket is connected. The binding address should have the same * scope ID as the connected address, except the case when one is * non-link local address (scope_id is 0). */ if (!ipv6_addr_any(&rs->rs_conn_addr) && scope_id && rs->rs_bound_scope_id && scope_id != rs->rs_bound_scope_id) { ret = -EINVAL; goto out; } /* The transport can be set using SO_RDS_TRANSPORT option before the * socket is bound. */ if (rs->rs_transport) { trans = rs->rs_transport; if (!trans->laddr_check || trans->laddr_check(sock_net(sock->sk), binding_addr, scope_id) != 0) { ret = -ENOPROTOOPT; goto out; } } else { trans = rds_trans_get_preferred(sock_net(sock->sk), binding_addr, scope_id); if (!trans) { ret = -EADDRNOTAVAIL; pr_info_ratelimited("RDS: %s could not find a transport for %pI6c, load rds_tcp or rds_rdma?\n", __func__, binding_addr); goto out; } rs->rs_transport = trans; } sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) rs->rs_transport = NULL; out: release_sock(sk); return ret; } void rds_bind_lock_destroy(void) { rhashtable_destroy(&bind_hash_table); } int rds_bind_lock_init(void) { return rhashtable_init(&bind_hash_table, &ht_parms); } |
| 1450 789 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW 0x0001 /* follow links at the end */ #define LOOKUP_DIRECTORY 0x0002 /* require a directory */ #define LOOKUP_AUTOMOUNT 0x0004 /* force terminal automount */ #define LOOKUP_EMPTY 0x4000 /* accept empty path [user_... only] */ #define LOOKUP_DOWN 0x8000 /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT 0x0080 /* follow mounts in the end */ #define LOOKUP_REVAL 0x0020 /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU 0x0040 /* RCU pathwalk mode; semi-internal */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN 0x0100 /* ... in open */ #define LOOKUP_CREATE 0x0200 /* ... in object creation */ #define LOOKUP_EXCL 0x0400 /* ... in exclusive creation */ #define LOOKUP_RENAME_TARGET 0x0800 /* ... in destination of rename() */ /* internal use only */ #define LOOKUP_PARENT 0x0010 /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ #define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); static inline int user_path_at(int dfd, const char __user *name, unsigned flags, struct path *path) { return user_path_at_empty(dfd, name, flags, path, NULL); } struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_TC_MIR_H #define __NET_TC_MIR_H #include <net/act_api.h> #include <linux/tc_act/tc_mirred.h> struct tcf_mirred { struct tc_action common; int tcfm_eaction; u32 tcfm_blockid; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; netdevice_tracker tcfm_dev_tracker; struct list_head tcfm_list; }; #define to_mirred(a) ((struct tcf_mirred *)a) static inline bool is_tcf_mirred_egress_redirect(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_EGRESS_REDIR; #endif return false; } static inline bool is_tcf_mirred_egress_mirror(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_EGRESS_MIRROR; #endif return false; } static inline bool is_tcf_mirred_ingress_redirect(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_INGRESS_REDIR; #endif return false; } static inline bool is_tcf_mirred_ingress_mirror(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_INGRESS_MIRROR; #endif return false; } static inline struct net_device *tcf_mirred_dev(const struct tc_action *a) { return rtnl_dereference(to_mirred(a)->tcfm_dev); } #endif /* __NET_TC_MIR_H */ |
| 21 21 21 19 19 5 5 5 5 14 1 2 1 5 2 4 4 2 13 13 7 3 26 1 25 19 5 18 6 21 3 20 2 2 2 2 2 15 5 2 2 4 35 1 1 4 1 28 2 26 21 21 21 7 2 5 8 7 1 12 3 12 5 3 2 2 3 4 12 12 13 13 1 12 12 12 13 13 21 21 21 21 21 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 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* - * net/sched/act_ct.c Connection Tracking action * * Authors: Paul Blakey <paulb@mellanox.com> * Yossi Kuperman <yossiku@mellanox.com> * Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/pkt_cls.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/rhashtable.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/act_api.h> #include <net/ip.h> #include <net/ipv6_frag.h> #include <uapi/linux/tc_act/tc_ct.h> #include <net/tc_act/tc_ct.h> #include <net/tc_wrapper.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netfilter/nf_conntrack_act_ct.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <uapi/linux/netfilter/nf_nat.h> static struct workqueue_struct *act_ct_wq; static struct rhashtable zones_ht; static DEFINE_MUTEX(zones_mutex); struct tcf_ct_flow_table { struct rhash_head node; /* In zones tables */ struct rcu_work rwork; struct nf_flowtable nf_ft; refcount_t ref; u16 zone; bool dying; }; static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, zone), .key_len = sizeof_field(struct tcf_ct_flow_table, zone), .automatic_shrinking = true, }; static struct flow_action_entry * tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action) { int i = flow_action->num_entries++; return &flow_action->entries[i]; } static void tcf_ct_add_mangle_action(struct flow_action *action, enum flow_action_mangle_base htype, u32 offset, u32 mask, u32 val) { struct flow_action_entry *entry; entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_MANGLE; entry->mangle.htype = htype; entry->mangle.mask = ~mask; entry->mangle.offset = offset; entry->mangle.val = val; } /* The following nat helper functions check if the inverted reverse tuple * (target) is different then the current dir tuple - meaning nat for ports * and/or ip is needed, and add the relevant mangle actions. */ static void tcf_ct_flow_table_add_action_nat_ipv4(const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple target, struct flow_action *action) { if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3))) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offsetof(struct iphdr, saddr), 0xFFFFFFFF, be32_to_cpu(target.src.u3.ip)); if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3))) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4, offsetof(struct iphdr, daddr), 0xFFFFFFFF, be32_to_cpu(target.dst.u3.ip)); } static void tcf_ct_add_ipv6_addr_mangle_action(struct flow_action *action, union nf_inet_addr *addr, u32 offset) { int i; for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP6, i * sizeof(u32) + offset, 0xFFFFFFFF, be32_to_cpu(addr->ip6[i])); } static void tcf_ct_flow_table_add_action_nat_ipv6(const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple target, struct flow_action *action) { if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3))) tcf_ct_add_ipv6_addr_mangle_action(action, &target.src.u3, offsetof(struct ipv6hdr, saddr)); if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3))) tcf_ct_add_ipv6_addr_mangle_action(action, &target.dst.u3, offsetof(struct ipv6hdr, daddr)); } static void tcf_ct_flow_table_add_action_nat_tcp(const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple target, struct flow_action *action) { __be16 target_src = target.src.u.tcp.port; __be16 target_dst = target.dst.u.tcp.port; if (target_src != tuple->src.u.tcp.port) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, offsetof(struct tcphdr, source), 0xFFFF, be16_to_cpu(target_src)); if (target_dst != tuple->dst.u.tcp.port) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP, offsetof(struct tcphdr, dest), 0xFFFF, be16_to_cpu(target_dst)); } static void tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple target, struct flow_action *action) { __be16 target_src = target.src.u.udp.port; __be16 target_dst = target.dst.u.udp.port; if (target_src != tuple->src.u.udp.port) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, offsetof(struct udphdr, source), 0xFFFF, be16_to_cpu(target_src)); if (target_dst != tuple->dst.u.udp.port) tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP, offsetof(struct udphdr, dest), 0xFFFF, be16_to_cpu(target_dst)); } static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, enum ip_conntrack_dir dir, enum ip_conntrack_info ctinfo, struct flow_action *action) { struct nf_conn_labels *ct_labels; struct flow_action_entry *entry; u32 *act_ct_labels; entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_CT_METADATA; #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif /* aligns with the CT reference on the SKB nf_ct_set */ entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL; act_ct_labels = entry->ct_metadata.labels; ct_labels = nf_ct_labels_find(ct); if (ct_labels) memcpy(act_ct_labels, ct_labels->bits, NF_CT_LABELS_MAX_SIZE); else memset(act_ct_labels, 0, NF_CT_LABELS_MAX_SIZE); } static int tcf_ct_flow_table_add_action_nat(struct net *net, struct nf_conn *ct, enum ip_conntrack_dir dir, struct flow_action *action) { const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; struct nf_conntrack_tuple target; if (!(ct->status & IPS_NAT_MASK)) return 0; nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); switch (tuple->src.l3num) { case NFPROTO_IPV4: tcf_ct_flow_table_add_action_nat_ipv4(tuple, target, action); break; case NFPROTO_IPV6: tcf_ct_flow_table_add_action_nat_ipv6(tuple, target, action); break; default: return -EOPNOTSUPP; } switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: tcf_ct_flow_table_add_action_nat_tcp(tuple, target, action); break; case IPPROTO_UDP: tcf_ct_flow_table_add_action_nat_udp(tuple, target, action); break; default: return -EOPNOTSUPP; } return 0; } static int tcf_ct_flow_table_fill_actions(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir tdir, struct nf_flow_rule *flow_rule) { struct flow_action *action = &flow_rule->rule->action; int num_entries = action->num_entries; struct nf_conn *ct = flow->ct; enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; int i, err; switch (tdir) { case FLOW_OFFLOAD_DIR_ORIGINAL: dir = IP_CT_DIR_ORIGINAL; ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? IP_CT_ESTABLISHED : IP_CT_NEW; if (ctinfo == IP_CT_ESTABLISHED) set_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); break; case FLOW_OFFLOAD_DIR_REPLY: dir = IP_CT_DIR_REPLY; ctinfo = IP_CT_ESTABLISHED_REPLY; break; default: return -EOPNOTSUPP; } err = tcf_ct_flow_table_add_action_nat(net, ct, dir, action); if (err) goto err_nat; tcf_ct_flow_table_add_action_meta(ct, dir, ctinfo, action); return 0; err_nat: /* Clear filled actions */ for (i = num_entries; i < action->num_entries; i++) memset(&action->entries[i], 0, sizeof(action->entries[i])); action->num_entries = num_entries; return err; } static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) { return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) && !test_bit(NF_FLOW_HW_PENDING, &flow->flags) && !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); } static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); static void tcf_ct_nf_get(struct nf_flowtable *ft) { struct tcf_ct_flow_table *ct_ft = container_of(ft, struct tcf_ct_flow_table, nf_ft); tcf_ct_flow_table_get_ref(ct_ft); } static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); static void tcf_ct_nf_put(struct nf_flowtable *ft) { struct tcf_ct_flow_table *ct_ft = container_of(ft, struct tcf_ct_flow_table, nf_ft); tcf_ct_flow_table_put(ct_ft); } static struct nf_flowtable_type flowtable_ct = { .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, .get = tcf_ct_nf_get, .put = tcf_ct_nf_put, .owner = THIS_MODULE, }; static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) { struct tcf_ct_flow_table *ct_ft; int err = -ENOMEM; mutex_lock(&zones_mutex); ct_ft = rhashtable_lookup_fast(&zones_ht, ¶ms->zone, zones_params); if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) goto out_unlock; ct_ft = kzalloc(sizeof(*ct_ft), GFP_KERNEL); if (!ct_ft) goto err_alloc; refcount_set(&ct_ft->ref, 1); ct_ft->zone = params->zone; err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params); if (err) goto err_insert; ct_ft->nf_ft.type = &flowtable_ct; ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD | NF_FLOWTABLE_COUNTER; err = nf_flow_table_init(&ct_ft->nf_ft); if (err) goto err_init; write_pnet(&ct_ft->nf_ft.net, net); __module_get(THIS_MODULE); out_unlock: params->ct_ft = ct_ft; params->nf_ft = &ct_ft->nf_ft; mutex_unlock(&zones_mutex); return 0; err_init: rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); err_insert: kfree(ct_ft); err_alloc: mutex_unlock(&zones_mutex); return err; } static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) { refcount_inc(&ct_ft->ref); } static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { struct tcf_ct_flow_table *ct_ft; struct flow_block *block; ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table, rwork); nf_flow_table_free(&ct_ft->nf_ft); block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); module_put(THIS_MODULE); } static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft) { if (refcount_dec_and_test(&ct_ft->ref)) { rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); queue_rcu_work(act_ct_wq, &ct_ft->rwork); } } static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, struct nf_conn_act_ct_ext *act_ct_ext, u8 dir) { entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC; entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir]; } static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry) { struct nf_conn_act_ct_ext *act_ct_ext; act_ct_ext = nf_conn_act_ct_ext_find(entry->ct); if (act_ct_ext) { tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); } } static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, bool tcp, bool bidirectional) { struct nf_conn_act_ct_ext *act_ct_ext; struct flow_offload *entry; int err; if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) return; entry = flow_offload_alloc(ct); if (!entry) { WARN_ON_ONCE(1); goto err_alloc; } if (tcp) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } if (bidirectional) __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &entry->flags); act_ct_ext = nf_conn_act_ct_ext_find(ct); if (act_ct_ext) { tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); } err = flow_offload_add(&ct_ft->nf_ft, entry); if (err) goto err_add; return; err_add: flow_offload_free(entry); err_alloc: clear_bit(IPS_OFFLOAD_BIT, &ct->status); } static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { bool tcp = false, bidirectional = true; switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) || !test_bit(IPS_ASSURED_BIT, &ct->status) || ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) return; tcp = true; break; case IPPROTO_UDP: if (!nf_ct_is_confirmed(ct)) return; if (!test_bit(IPS_ASSURED_BIT, &ct->status)) bidirectional = false; break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) || !test_bit(IPS_ASSURED_BIT, &ct->status) || ct->status & IPS_NAT_MASK) return; tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) return; break; } #endif default: return; } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || ct->status & IPS_SEQ_ADJUST) return; tcf_ct_flow_table_add(ct_ft, ct, tcp, bidirectional); } static bool tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb, struct flow_offload_tuple *tuple, struct tcphdr **tcph) { struct flow_ports *ports; unsigned int thoff; struct iphdr *iph; size_t hdrsize; u8 ipproto; if (!pskb_network_may_pull(skb, sizeof(*iph))) return false; iph = ip_hdr(skb); thoff = iph->ihl * 4; if (ip_is_fragment(iph) || unlikely(thoff != sizeof(struct iphdr))) return false; ipproto = iph->protocol; switch (ipproto) { case IPPROTO_TCP: hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: hdrsize = sizeof(*ports); break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: hdrsize = sizeof(struct gre_base_hdr); break; #endif default: return false; } if (iph->ttl <= 1) return false; if (!pskb_network_may_pull(skb, thoff + hdrsize)) return false; switch (ipproto) { case IPPROTO_TCP: *tcph = (void *)(skb_network_header(skb) + thoff); fallthrough; case IPPROTO_UDP: ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_port = ports->source; tuple->dst_port = ports->dest; break; case IPPROTO_GRE: { struct gre_base_hdr *greh; greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff); if ((greh->flags & GRE_VERSION) != GRE_VERSION_0) return false; break; } } iph = ip_hdr(skb); tuple->src_v4.s_addr = iph->saddr; tuple->dst_v4.s_addr = iph->daddr; tuple->l3proto = AF_INET; tuple->l4proto = ipproto; return true; } static bool tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb, struct flow_offload_tuple *tuple, struct tcphdr **tcph) { struct flow_ports *ports; struct ipv6hdr *ip6h; unsigned int thoff; size_t hdrsize; u8 nexthdr; if (!pskb_network_may_pull(skb, sizeof(*ip6h))) return false; ip6h = ipv6_hdr(skb); thoff = sizeof(*ip6h); nexthdr = ip6h->nexthdr; switch (nexthdr) { case IPPROTO_TCP: hdrsize = sizeof(struct tcphdr); break; case IPPROTO_UDP: hdrsize = sizeof(*ports); break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: hdrsize = sizeof(struct gre_base_hdr); break; #endif default: return false; } if (ip6h->hop_limit <= 1) return false; if (!pskb_network_may_pull(skb, thoff + hdrsize)) return false; switch (nexthdr) { case IPPROTO_TCP: *tcph = (void *)(skb_network_header(skb) + thoff); fallthrough; case IPPROTO_UDP: ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_port = ports->source; tuple->dst_port = ports->dest; break; case IPPROTO_GRE: { struct gre_base_hdr *greh; greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff); if ((greh->flags & GRE_VERSION) != GRE_VERSION_0) return false; break; } } ip6h = ipv6_hdr(skb); tuple->src_v6 = ip6h->saddr; tuple->dst_v6 = ip6h->daddr; tuple->l3proto = AF_INET6; tuple->l4proto = nexthdr; return true; } static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, struct sk_buff *skb, u8 family) { struct nf_flowtable *nf_ft = &p->ct_ft->nf_ft; struct flow_offload_tuple_rhash *tuplehash; struct flow_offload_tuple tuple = {}; enum ip_conntrack_info ctinfo; struct tcphdr *tcph = NULL; bool force_refresh = false; struct flow_offload *flow; struct nf_conn *ct; u8 dir; switch (family) { case NFPROTO_IPV4: if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph)) return false; break; case NFPROTO_IPV6: if (!tcf_ct_flow_table_fill_tuple_ipv6(skb, &tuple, &tcph)) return false; break; default: return false; } tuplehash = flow_offload_lookup(nf_ft, &tuple); if (!tuplehash) return false; dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); ct = flow->ct; if (dir == FLOW_OFFLOAD_DIR_REPLY && !test_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags)) { /* Only offload reply direction after connection became * assured. */ if (test_bit(IPS_ASSURED_BIT, &ct->status)) set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); else if (test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags)) /* If flow_table flow has already been updated to the * established state, then don't refresh. */ return false; force_refresh = true; } if (tcph && (unlikely(tcph->fin || tcph->rst))) { flow_offload_teardown(flow); return false; } if (dir == FLOW_OFFLOAD_DIR_ORIGINAL) ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? IP_CT_ESTABLISHED : IP_CT_NEW; else ctinfo = IP_CT_ESTABLISHED_REPLY; nf_conn_act_ct_ext_fill(skb, ct, ctinfo); tcf_ct_flow_ct_ext_ifidx_update(flow); flow_offload_refresh(nf_ft, flow, force_refresh); if (!test_bit(IPS_ASSURED_BIT, &ct->status)) { /* Process this flow in SW to allow promoting to ASSURED */ return false; } nf_conntrack_get(&ct->ct_general); nf_ct_set(skb, ct, ctinfo); if (nf_ft->flags & NF_FLOWTABLE_COUNTER) nf_ct_acct_update(ct, dir, skb->len); return true; } static int tcf_ct_flow_tables_init(void) { return rhashtable_init(&zones_ht, &zones_params); } static void tcf_ct_flow_tables_uninit(void) { rhashtable_destroy(&zones_ht); } static struct tc_action_ops act_ct_ops; struct tc_ct_action_net { struct tc_action_net tn; /* Must be first */ }; /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, struct tcf_ct_params *p) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); if (!ct) return false; if (!net_eq(net, read_pnet(&ct->ct_net))) goto drop_ct; if (nf_ct_zone(ct)->id != p->zone) goto drop_ct; if (p->helper) { struct nf_conn_help *help; help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); if (help && rcu_access_pointer(help->helper) != p->helper) goto drop_ct; } /* Force conntrack entry direction. */ if ((p->ct_action & TCA_CT_ACT_FORCE) && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { if (nf_ct_is_confirmed(ct)) nf_ct_kill(ct); goto drop_ct; } return true; drop_ct: nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); return false; } static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): family = NFPROTO_IPV4; break; case htons(ETH_P_IPV6): family = NFPROTO_IPV6; break; default: break; } return family; } static int tcf_ct_ipv4_is_fragment(struct sk_buff *skb, bool *frag) { unsigned int len; len = skb_network_offset(skb) + sizeof(struct iphdr); if (unlikely(skb->len < len)) return -EINVAL; if (unlikely(!pskb_may_pull(skb, len))) return -ENOMEM; *frag = ip_is_fragment(ip_hdr(skb)); return 0; } static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag) { unsigned int flags = 0, len, payload_ofs = 0; unsigned short frag_off; int nexthdr; len = skb_network_offset(skb) + sizeof(struct ipv6hdr); if (unlikely(skb->len < len)) return -EINVAL; if (unlikely(!pskb_may_pull(skb, len))) return -ENOMEM; nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags); if (unlikely(nexthdr < 0)) return -EPROTO; *frag = flags & IP6_FH_F_FRAG; return 0; } static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, u8 family, u16 zone, bool *defrag) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; int err = 0; bool frag; u8 proto; u16 mru; /* Previously seen (loopback)? Ignore. */ ct = nf_ct_get(skb, &ctinfo); if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED) return 0; if (family == NFPROTO_IPV4) err = tcf_ct_ipv4_is_fragment(skb, &frag); else err = tcf_ct_ipv6_is_fragment(skb, &frag); if (err || !frag) return err; err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru); if (err) return err; *defrag = true; tc_skb_cb(skb)->mru = mru; return 0; } static void tcf_ct_params_free(struct tcf_ct_params *params) { if (params->helper) { #if IS_ENABLED(CONFIG_NF_NAT) if (params->ct_action & TCA_CT_ACT_NAT) nf_nat_helper_put(params->helper); #endif nf_conntrack_helper_put(params->helper); } if (params->ct_ft) tcf_ct_flow_table_put(params->ct_ft); if (params->tmpl) { if (params->put_labels) nf_connlabels_put(nf_ct_net(params->tmpl)); nf_ct_put(params->tmpl); } kfree(params); } static void tcf_ct_params_free_rcu(struct rcu_head *head) { struct tcf_ct_params *params; params = container_of(head, struct tcf_ct_params, rcu); tcf_ct_params_free(params); } static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; if (!mask) return; new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); if (READ_ONCE(ct->mark) != new_mark) { WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); } #endif } static void tcf_ct_act_set_labels(struct nf_conn *ct, u32 *labels, u32 *labels_m) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) size_t labels_sz = sizeof_field(struct tcf_ct_params, labels); if (!memchr_inv(labels_m, 0, labels_sz)) return; nf_connlabels_replace(ct, labels, labels_m, 4); #endif } static int tcf_ct_act_nat(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, int ct_action, struct nf_nat_range2 *range, bool commit) { #if IS_ENABLED(CONFIG_NF_NAT) int err, action = 0; if (!(ct_action & TCA_CT_ACT_NAT)) return NF_ACCEPT; if (ct_action & TCA_CT_ACT_NAT_SRC) action |= BIT(NF_NAT_MANIP_SRC); if (ct_action & TCA_CT_ACT_NAT_DST) action |= BIT(NF_NAT_MANIP_DST); err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit); if (action & BIT(NF_NAT_MANIP_SRC)) tc_skb_cb(skb)->post_ct_snat = 1; if (action & BIT(NF_NAT_MANIP_DST)) tc_skb_cb(skb)->post_ct_dnat = 1; return err; #else return NF_ACCEPT; #endif } TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct net *net = dev_net(skb->dev); enum ip_conntrack_info ctinfo; struct tcf_ct *c = to_ct(a); struct nf_conn *tmpl = NULL; struct nf_hook_state state; bool cached, commit, clear; int nh_ofs, err, retval; struct tcf_ct_params *p; bool add_helper = false; bool skip_add = false; bool defrag = false; struct nf_conn *ct; u8 family; p = rcu_dereference_bh(c->params); retval = READ_ONCE(c->tcf_action); commit = p->ct_action & TCA_CT_ACT_COMMIT; clear = p->ct_action & TCA_CT_ACT_CLEAR; tmpl = p->tmpl; tcf_lastuse_update(&c->tcf_tm); tcf_action_update_bstats(&c->common, skb); if (clear) { tc_skb_cb(skb)->post_ct = false; ct = nf_ct_get(skb, &ctinfo); if (ct) { nf_ct_put(ct); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } goto out_clear; } family = tcf_ct_skb_nf_family(skb); if (family == NFPROTO_UNSPEC) goto drop; /* The conntrack module expects to be working at L3. * We also try to pull the IPv4/6 header to linear area */ nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag); if (err) goto out_frag; err = nf_ct_skb_network_trim(skb, family); if (err) goto drop; /* If we are recirculating packets to match on ct fields and * committing with a separate ct action, then we don't need to * actually run the packet through conntrack twice unless it's for a * different zone. */ cached = tcf_ct_skb_nfct_cached(net, skb, p); if (!cached) { if (tcf_ct_flow_table_lookup(p, skb, family)) { skip_add = true; goto do_nat; } /* Associate skb with specified zone. */ if (tmpl) { nf_conntrack_put(skb_nfct(skb)); nf_conntrack_get(&tmpl->ct_general); nf_ct_set(skb, tmpl, IP_CT_NEW); } state.hook = NF_INET_PRE_ROUTING; state.net = net; state.pf = family; err = nf_conntrack_in(skb, &state); if (err != NF_ACCEPT) goto out_push; } do_nat: ct = nf_ct_get(skb, &ctinfo); if (!ct) goto out_push; nf_ct_deliver_cached_events(ct); nf_conn_act_ct_ext_fill(skb, ct, ctinfo); err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit); if (err != NF_ACCEPT) goto drop; if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) { err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC); if (err) goto drop; add_helper = true; if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) { if (!nfct_seqadj_ext_add(ct)) goto drop; } } if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) { if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT) goto drop; } if (commit) { tcf_ct_act_set_mark(ct, p->mark, p->mark_mask); tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); if (!nf_ct_is_confirmed(ct)) nf_conn_act_ct_ext_add(skb, ct, ctinfo); /* This will take care of sending queued events * even if the connection is already confirmed. */ if (nf_conntrack_confirm(skb) != NF_ACCEPT) goto drop; } if (!skip_add) tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo); out_push: skb_push_rcsum(skb, nh_ofs); tc_skb_cb(skb)->post_ct = true; tc_skb_cb(skb)->zone = p->zone; out_clear: if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; out_frag: if (err != -EINPROGRESS) tcf_action_inc_drop_qstats(&c->common); return TC_ACT_CONSUMED; drop: tcf_action_inc_drop_qstats(&c->common); return TC_ACT_SHOT; } static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { [TCA_CT_ACTION] = { .type = NLA_U16 }, [TCA_CT_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ct)), [TCA_CT_ZONE] = { .type = NLA_U16 }, [TCA_CT_MARK] = { .type = NLA_U32 }, [TCA_CT_MARK_MASK] = { .type = NLA_U32 }, [TCA_CT_LABELS] = { .type = NLA_BINARY, .len = 128 / BITS_PER_BYTE }, [TCA_CT_LABELS_MASK] = { .type = NLA_BINARY, .len = 128 / BITS_PER_BYTE }, [TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 }, [TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 }, [TCA_CT_NAT_IPV6_MIN] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, [TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN }, [TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 }, [TCA_CT_HELPER_PROTO] = { .type = NLA_U8 }, }; static int tcf_ct_fill_params_nat(struct tcf_ct_params *p, struct tc_ct *parm, struct nlattr **tb, struct netlink_ext_ack *extack) { struct nf_nat_range2 *range; if (!(p->ct_action & TCA_CT_ACT_NAT)) return 0; if (!IS_ENABLED(CONFIG_NF_NAT)) { NL_SET_ERR_MSG_MOD(extack, "Netfilter nat isn't enabled in kernel"); return -EOPNOTSUPP; } if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST))) return 0; if ((p->ct_action & TCA_CT_ACT_NAT_SRC) && (p->ct_action & TCA_CT_ACT_NAT_DST)) { NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time"); return -EOPNOTSUPP; } range = &p->range; if (tb[TCA_CT_NAT_IPV4_MIN]) { struct nlattr *max_attr = tb[TCA_CT_NAT_IPV4_MAX]; p->ipv4_range = true; range->flags |= NF_NAT_RANGE_MAP_IPS; range->min_addr.ip = nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]); range->max_addr.ip = max_attr ? nla_get_in_addr(max_attr) : range->min_addr.ip; } else if (tb[TCA_CT_NAT_IPV6_MIN]) { struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX]; p->ipv4_range = false; range->flags |= NF_NAT_RANGE_MAP_IPS; range->min_addr.in6 = nla_get_in6_addr(tb[TCA_CT_NAT_IPV6_MIN]); range->max_addr.in6 = max_attr ? nla_get_in6_addr(max_attr) : range->min_addr.in6; } if (tb[TCA_CT_NAT_PORT_MIN]) { range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; range->min_proto.all = nla_get_be16(tb[TCA_CT_NAT_PORT_MIN]); range->max_proto.all = tb[TCA_CT_NAT_PORT_MAX] ? nla_get_be16(tb[TCA_CT_NAT_PORT_MAX]) : range->min_proto.all; } return 0; } static void tcf_ct_set_key_val(struct nlattr **tb, void *val, int val_type, void *mask, int mask_type, int len) { if (!tb[val_type]) return; nla_memcpy(val, tb[val_type], len); if (!mask) return; if (mask_type == TCA_CT_UNSPEC || !tb[mask_type]) memset(mask, 0xff, len); else nla_memcpy(mask, tb[mask_type], len); } static int tcf_ct_fill_params(struct net *net, struct tcf_ct_params *p, struct tc_ct *parm, struct nlattr **tb, struct netlink_ext_ack *extack) { struct nf_conntrack_zone zone; int err, family, proto, len; bool put_labels = false; struct nf_conn *tmpl; char *name; p->zone = NF_CT_DEFAULT_ZONE_ID; tcf_ct_set_key_val(tb, &p->ct_action, TCA_CT_ACTION, NULL, TCA_CT_UNSPEC, sizeof(p->ct_action)); if (p->ct_action & TCA_CT_ACT_CLEAR) return 0; err = tcf_ct_fill_params_nat(p, parm, tb, extack); if (err) return err; if (tb[TCA_CT_MARK]) { if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) { NL_SET_ERR_MSG_MOD(extack, "Conntrack mark isn't enabled."); return -EOPNOTSUPP; } tcf_ct_set_key_val(tb, &p->mark, TCA_CT_MARK, &p->mark_mask, TCA_CT_MARK_MASK, sizeof(p->mark)); } if (tb[TCA_CT_LABELS]) { unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) { NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled."); return -EOPNOTSUPP; } if (nf_connlabels_get(net, n_bits - 1)) { NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length"); return -EOPNOTSUPP; } else { put_labels = true; } tcf_ct_set_key_val(tb, p->labels, TCA_CT_LABELS, p->labels_mask, TCA_CT_LABELS_MASK, sizeof(p->labels)); } if (tb[TCA_CT_ZONE]) { if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) { NL_SET_ERR_MSG_MOD(extack, "Conntrack zones isn't enabled."); return -EOPNOTSUPP; } tcf_ct_set_key_val(tb, &p->zone, TCA_CT_ZONE, NULL, TCA_CT_UNSPEC, sizeof(p->zone)); } nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0); tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL); if (!tmpl) { NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template"); return -ENOMEM; } p->tmpl = tmpl; if (tb[TCA_CT_HELPER_NAME]) { name = nla_data(tb[TCA_CT_HELPER_NAME]); len = nla_len(tb[TCA_CT_HELPER_NAME]); if (len > 16 || name[len - 1] != '\0') { NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name."); err = -EINVAL; goto err; } family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET; proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP; err = nf_ct_add_helper(tmpl, name, family, proto, p->ct_action & TCA_CT_ACT_NAT, &p->helper); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to add helper"); goto err; } } p->put_labels = put_labels; if (p->ct_action & TCA_CT_ACT_COMMIT) __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); return 0; err: if (put_labels) nf_connlabels_put(net); nf_ct_put(p->tmpl); p->tmpl = NULL; return err; } static int tcf_ct_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_ct_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_ct_params *params = NULL; struct nlattr *tb[TCA_CT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_ct *parm; struct tcf_ct *c; int err, res = 0; u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed"); return -EINVAL; } err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack); if (err < 0) return err; if (!tb[TCA_CT_PARMS]) { NL_SET_ERR_MSG_MOD(extack, "Missing required ct parameters"); return -EINVAL; } parm = nla_data(tb[TCA_CT_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; if (!err) { err = tcf_idr_create_from_flags(tn, index, est, a, &act_ct_ops, bind, flags); if (err) { tcf_idr_cleanup(tn, index); return err; } res = ACT_P_CREATED; } else { if (bind) return ACT_P_BOUND; if (!(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 cleanup; c = to_ct(*a); params = kzalloc(sizeof(*params), GFP_KERNEL); if (unlikely(!params)) { err = -ENOMEM; goto cleanup; } err = tcf_ct_fill_params(net, params, parm, tb, extack); if (err) goto cleanup; err = tcf_ct_flow_table_get(net, params); if (err) goto cleanup; spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params = rcu_replace_pointer(c->params, params, lockdep_is_held(&c->tcf_lock)); spin_unlock_bh(&c->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); return res; cleanup: if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) tcf_ct_params_free(params); tcf_idr_release(*a, bind); return err; } static void tcf_ct_cleanup(struct tc_action *a) { struct tcf_ct_params *params; struct tcf_ct *c = to_ct(a); params = rcu_dereference_protected(c->params, 1); if (params) call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); } static int tcf_ct_dump_key_val(struct sk_buff *skb, void *val, int val_type, void *mask, int mask_type, int len) { int err; if (mask && !memchr_inv(mask, 0, len)) return 0; err = nla_put(skb, val_type, len, val); if (err) return err; if (mask_type != TCA_CT_UNSPEC) { err = nla_put(skb, mask_type, len, mask); if (err) return err; } return 0; } static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p) { struct nf_nat_range2 *range = &p->range; if (!(p->ct_action & TCA_CT_ACT_NAT)) return 0; if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST))) return 0; if (range->flags & NF_NAT_RANGE_MAP_IPS) { if (p->ipv4_range) { if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MIN, range->min_addr.ip)) return -1; if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MAX, range->max_addr.ip)) return -1; } else { if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MIN, &range->min_addr.in6)) return -1; if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MAX, &range->max_addr.in6)) return -1; } } if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { if (nla_put_be16(skb, TCA_CT_NAT_PORT_MIN, range->min_proto.all)) return -1; if (nla_put_be16(skb, TCA_CT_NAT_PORT_MAX, range->max_proto.all)) return -1; } return 0; } static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper) { if (!helper) return 0; if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) || nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) || nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum)) return -1; return 0; } static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_ct *c = to_ct(a); struct tcf_ct_params *p; struct tc_ct opt = { .index = c->tcf_index, .refcnt = refcount_read(&c->tcf_refcnt) - ref, .bindcnt = atomic_read(&c->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&c->tcf_lock); p = rcu_dereference_protected(c->params, lockdep_is_held(&c->tcf_lock)); opt.action = c->tcf_action; if (tcf_ct_dump_key_val(skb, &p->ct_action, TCA_CT_ACTION, NULL, TCA_CT_UNSPEC, sizeof(p->ct_action))) goto nla_put_failure; if (p->ct_action & TCA_CT_ACT_CLEAR) goto skip_dump; if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) && tcf_ct_dump_key_val(skb, &p->mark, TCA_CT_MARK, &p->mark_mask, TCA_CT_MARK_MASK, sizeof(p->mark))) goto nla_put_failure; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && tcf_ct_dump_key_val(skb, p->labels, TCA_CT_LABELS, p->labels_mask, TCA_CT_LABELS_MASK, sizeof(p->labels))) goto nla_put_failure; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && tcf_ct_dump_key_val(skb, &p->zone, TCA_CT_ZONE, NULL, TCA_CT_UNSPEC, sizeof(p->zone))) goto nla_put_failure; if (tcf_ct_dump_nat(skb, p)) goto nla_put_failure; if (tcf_ct_dump_helper(skb, p->helper)) goto nla_put_failure; skip_dump: if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &c->tcf_tm); if (nla_put_64bit(skb, TCA_CT_TM, sizeof(t), &t, TCA_CT_PAD)) goto nla_put_failure; spin_unlock_bh(&c->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&c->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_ct *c = to_ct(a); tcf_action_update_stats(a, bytes, packets, drops, hw); c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse); } static int tcf_ct_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 (tcf_ct_helper(act)) return -EOPNOTSUPP; entry->id = FLOW_ACTION_CT; entry->ct.action = tcf_ct_action(act); entry->ct.zone = tcf_ct_zone(act); entry->ct.flow_table = tcf_ct_ft(act); *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_CT; } return 0; } static struct tc_action_ops act_ct_ops = { .kind = "ct", .id = TCA_ID_CT, .owner = THIS_MODULE, .act = tcf_ct_act, .dump = tcf_ct_dump, .init = tcf_ct_init, .cleanup = tcf_ct_cleanup, .stats_update = tcf_stats_update, .offload_act_setup = tcf_ct_offload_act_setup, .size = sizeof(struct tcf_ct), }; MODULE_ALIAS_NET_ACT("ct"); static __net_init int ct_init_net(struct net *net) { struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); return tc_action_net_init(net, &tn->tn, &act_ct_ops); } static void __net_exit ct_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_ct_ops.net_id); } static struct pernet_operations ct_net_ops = { .init = ct_init_net, .exit_batch = ct_exit_net, .id = &act_ct_ops.net_id, .size = sizeof(struct tc_ct_action_net), }; static int __init ct_init_module(void) { int err; act_ct_wq = alloc_ordered_workqueue("act_ct_workqueue", 0); if (!act_ct_wq) return -ENOMEM; err = tcf_ct_flow_tables_init(); if (err) goto err_tbl_init; err = tcf_register_action(&act_ct_ops, &ct_net_ops); if (err) goto err_register; static_branch_inc(&tcf_frag_xmit_count); return 0; err_register: tcf_ct_flow_tables_uninit(); err_tbl_init: destroy_workqueue(act_ct_wq); return err; } static void __exit ct_cleanup_module(void) { static_branch_dec(&tcf_frag_xmit_count); tcf_unregister_action(&act_ct_ops, &ct_net_ops); tcf_ct_flow_tables_uninit(); destroy_workqueue(act_ct_wq); } module_init(ct_init_module); module_exit(ct_cleanup_module); MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>"); MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>"); MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>"); MODULE_DESCRIPTION("Connection tracking action"); MODULE_LICENSE("GPL v2"); |
| 7 2 6 5 6 2 5 2 5 6 5 18 18 16 16 16 16 16 3 2 3 3 8 3 2 4 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 | // SPDX-License-Identifier: GPL-2.0-only #include <net/xdp_sock_drv.h> #include "netlink.h" #include "common.h" struct channels_req_info { struct ethnl_req_info base; }; struct channels_reply_data { struct ethnl_reply_data base; struct ethtool_channels channels; }; #define CHANNELS_REPDATA(__reply_base) \ container_of(__reply_base, struct channels_reply_data, base) const struct nla_policy ethnl_channels_get_policy[] = { [ETHTOOL_A_CHANNELS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int channels_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_channels) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; dev->ethtool_ops->get_channels(dev, &data->channels); ethnl_ops_complete(dev); return 0; } static int channels_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u32)) + /* _CHANNELS_RX_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_TX_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_OTHER_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_COMBINED_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_RX_COUNT */ nla_total_size(sizeof(u32)) + /* _CHANNELS_TX_COUNT */ nla_total_size(sizeof(u32)) + /* _CHANNELS_OTHER_COUNT */ nla_total_size(sizeof(u32)); /* _CHANNELS_COMBINED_COUNT */ } static int channels_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); const struct ethtool_channels *channels = &data->channels; if ((channels->max_rx && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_RX_MAX, channels->max_rx) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_RX_COUNT, channels->rx_count))) || (channels->max_tx && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_TX_MAX, channels->max_tx) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_TX_COUNT, channels->tx_count))) || (channels->max_other && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_OTHER_MAX, channels->max_other) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_OTHER_COUNT, channels->other_count))) || (channels->max_combined && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_COMBINED_MAX, channels->max_combined) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_COMBINED_COUNT, channels->combined_count)))) return -EMSGSIZE; return 0; } /* CHANNELS_SET */ const struct nla_policy ethnl_channels_set_policy[] = { [ETHTOOL_A_CHANNELS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_CHANNELS_RX_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_TX_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_COMBINED_COUNT] = { .type = NLA_U32 }, }; static int ethnl_set_channels_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_channels && ops->set_channels ? 1 : -EOPNOTSUPP; } static int ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) { unsigned int from_channel, old_total, i; bool mod = false, mod_combined = false; struct net_device *dev = req_info->dev; struct ethtool_channels channels = {}; struct nlattr **tb = info->attrs; u32 err_attr, max_rxfh_in_use; u64 max_rxnfc_in_use; int ret; dev->ethtool_ops->get_channels(dev, &channels); old_total = channels.combined_count + max(channels.rx_count, channels.tx_count); ethnl_update_u32(&channels.rx_count, tb[ETHTOOL_A_CHANNELS_RX_COUNT], &mod); ethnl_update_u32(&channels.tx_count, tb[ETHTOOL_A_CHANNELS_TX_COUNT], &mod); ethnl_update_u32(&channels.other_count, tb[ETHTOOL_A_CHANNELS_OTHER_COUNT], &mod); ethnl_update_u32(&channels.combined_count, tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT], &mod_combined); mod |= mod_combined; if (!mod) return 0; /* ensure new channel counts are within limits */ if (channels.rx_count > channels.max_rx) err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (channels.tx_count > channels.max_tx) err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else if (channels.other_count > channels.max_other) err_attr = ETHTOOL_A_CHANNELS_OTHER_COUNT; else if (channels.combined_count > channels.max_combined) err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; else err_attr = 0; if (err_attr) { NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], "requested channel count exceeds maximum"); return -EINVAL; } /* ensure there is at least one RX and one TX channel */ if (!channels.combined_count && !channels.rx_count) err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (!channels.combined_count && !channels.tx_count) err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else err_attr = 0; if (err_attr) { if (mod_combined) err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], "requested channel counts would result in no RX or TX channel being configured"); return -EINVAL; } /* ensure the new Rx count fits within the configured Rx flow * indirection table/rxnfc settings */ if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) max_rxnfc_in_use = 0; if (!netif_is_rxfh_configured(dev) || ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use)) max_rxfh_in_use = 0; if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing indirection table settings"); return -EINVAL; } if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); return -EINVAL; } /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); for (i = from_channel; i < old_total; i++) if (xsk_get_pool_from_qid(dev, i)) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); return -EINVAL; } ret = dev->ethtool_ops->set_channels(dev, &channels); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_channels_request_ops = { .request_cmd = ETHTOOL_MSG_CHANNELS_GET, .reply_cmd = ETHTOOL_MSG_CHANNELS_GET_REPLY, .hdr_attr = ETHTOOL_A_CHANNELS_HEADER, .req_info_size = sizeof(struct channels_req_info), .reply_data_size = sizeof(struct channels_reply_data), .prepare_data = channels_prepare_data, .reply_size = channels_reply_size, .fill_reply = channels_fill_reply, .set_validate = ethnl_set_channels_validate, .set = ethnl_set_channels, .set_ntf_cmd = ETHTOOL_MSG_CHANNELS_NTF, }; |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | // SPDX-License-Identifier: GPL-2.0 /* * fs-verity module initialization and logging * * Copyright 2019 Google LLC */ #include "fsverity_private.h" #include <linux/ratelimit.h> #ifdef CONFIG_SYSCTL static struct ctl_table fsverity_sysctl_table[] = { #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES { .procname = "require_signatures", .data = &fsverity_require_signatures, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif }; static void __init fsverity_init_sysctl(void) { register_sysctl_init("fs/verity", fsverity_sysctl_table); } #else /* CONFIG_SYSCTL */ static inline void fsverity_init_sysctl(void) { } #endif /* !CONFIG_SYSCTL */ void fsverity_msg(const struct inode *inode, const char *level, const char *fmt, ...) { static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); struct va_format vaf; va_list args; if (!__ratelimit(&rs)) return; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (inode) printk("%sfs-verity (%s, inode %lu): %pV\n", level, inode->i_sb->s_id, inode->i_ino, &vaf); else printk("%sfs-verity: %pV\n", level, &vaf); va_end(args); } static int __init fsverity_init(void) { fsverity_check_hash_algs(); fsverity_init_info_cache(); fsverity_init_workqueue(); fsverity_init_sysctl(); fsverity_init_signature(); fsverity_init_bpf(); return 0; } late_initcall(fsverity_init) |
| 2 8 6 3 11 11 9 11 11 11 8 11 11 9 1 8 2 8 1 1 8 2 2 1 2 2 1 2 9 9 9 2 11 11 9 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/in.h> #include <linux/inet.h> #include <linux/list.h> #include <linux/module.h> #include <linux/net.h> #include <linux/proc_fs.h> #include <linux/rculist.h> #include <linux/seq_file.h> #include <linux/socket.h> #include <net/inet_sock.h> #include <net/kcm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/tcp.h> #ifdef CONFIG_PROC_FS static struct kcm_mux *kcm_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); return list_first_or_null_rcu(&knet->mux_list, struct kcm_mux, kcm_mux_list); } static struct kcm_mux *kcm_get_next(struct kcm_mux *mux) { struct kcm_net *knet = mux->knet; return list_next_or_null_rcu(&knet->mux_list, &mux->kcm_mux_list, struct kcm_mux, kcm_mux_list); } static struct kcm_mux *kcm_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); struct kcm_mux *m; list_for_each_entry_rcu(m, &knet->mux_list, kcm_mux_list) { if (!pos) return m; --pos; } return NULL; } static void *kcm_seq_next(struct seq_file *seq, void *v, loff_t *pos) { void *p; if (v == SEQ_START_TOKEN) p = kcm_get_first(seq); else p = kcm_get_next(v); ++*pos; return p; } static void *kcm_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; else return kcm_get_idx(seq, *pos - 1); } static void kcm_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { rcu_read_unlock(); } struct kcm_proc_mux_state { struct seq_net_private p; int idx; }; static void kcm_format_mux_header(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct kcm_net *knet = net_generic(net, kcm_net_id); seq_printf(seq, "*** KCM statistics (%d MUX) ****\n", knet->count); seq_printf(seq, "%-14s %-10s %-16s %-10s %-16s %-8s %-8s %-8s %-8s %s", "Object", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "Recv-Q", "Rmem", "Send-Q", "Smem", "Status"); /* XXX: pdsts header stuff here */ seq_puts(seq, "\n"); } static void kcm_format_sock(struct kcm_sock *kcm, struct seq_file *seq, int i, int *len) { seq_printf(seq, " kcm-%-7u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8s ", kcm->index, kcm->stats.rx_msgs, kcm->stats.rx_bytes, kcm->stats.tx_msgs, kcm->stats.tx_bytes, kcm->sk.sk_receive_queue.qlen, sk_rmem_alloc_get(&kcm->sk), kcm->sk.sk_write_queue.qlen, "-"); if (kcm->tx_psock) seq_printf(seq, "Psck-%u ", kcm->tx_psock->index); if (kcm->tx_wait) seq_puts(seq, "TxWait "); if (kcm->tx_wait_more) seq_puts(seq, "WMore "); if (kcm->rx_wait) seq_puts(seq, "RxWait "); seq_puts(seq, "\n"); } static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq, int i, int *len) { seq_printf(seq, " psock-%-5u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8d ", psock->index, psock->strp.stats.msgs, psock->strp.stats.bytes, psock->stats.tx_msgs, psock->stats.tx_bytes, psock->sk->sk_receive_queue.qlen, atomic_read(&psock->sk->sk_rmem_alloc), psock->sk->sk_write_queue.qlen, refcount_read(&psock->sk->sk_wmem_alloc)); if (psock->done) seq_puts(seq, "Done "); if (psock->tx_stopped) seq_puts(seq, "TxStop "); if (psock->strp.stopped) seq_puts(seq, "RxStop "); if (psock->tx_kcm) seq_printf(seq, "Rsvd-%d ", psock->tx_kcm->index); if (!psock->strp.paused && !psock->ready_rx_msg) { if (psock->sk->sk_receive_queue.qlen) { if (psock->strp.need_bytes) seq_printf(seq, "RxWait=%u ", psock->strp.need_bytes); else seq_printf(seq, "RxWait "); } } else { if (psock->strp.paused) seq_puts(seq, "RxPause "); if (psock->ready_rx_msg) seq_puts(seq, "RdyRx "); } seq_puts(seq, "\n"); } static void kcm_format_mux(struct kcm_mux *mux, loff_t idx, struct seq_file *seq) { int i, len; struct kcm_sock *kcm; struct kcm_psock *psock; /* mux information */ seq_printf(seq, "%-6s%-8s %-10llu %-16llu %-10llu %-16llu %-8s %-8s %-8s %-8s ", "mux", "", mux->stats.rx_msgs, mux->stats.rx_bytes, mux->stats.tx_msgs, mux->stats.tx_bytes, "-", "-", "-", "-"); seq_printf(seq, "KCMs: %d, Psocks %d\n", mux->kcm_socks_cnt, mux->psocks_cnt); /* kcm sock information */ i = 0; spin_lock_bh(&mux->lock); list_for_each_entry(kcm, &mux->kcm_socks, kcm_sock_list) { kcm_format_sock(kcm, seq, i, &len); i++; } i = 0; list_for_each_entry(psock, &mux->psocks, psock_list) { kcm_format_psock(psock, seq, i, &len); i++; } spin_unlock_bh(&mux->lock); } static int kcm_seq_show(struct seq_file *seq, void *v) { struct kcm_proc_mux_state *mux_state; mux_state = seq->private; if (v == SEQ_START_TOKEN) { mux_state->idx = 0; kcm_format_mux_header(seq); } else { kcm_format_mux(v, mux_state->idx, seq); mux_state->idx++; } return 0; } static const struct seq_operations kcm_seq_ops = { .show = kcm_seq_show, .start = kcm_seq_start, .next = kcm_seq_next, .stop = kcm_seq_stop, }; static int kcm_stats_seq_show(struct seq_file *seq, void *v) { struct kcm_psock_stats psock_stats; struct kcm_mux_stats mux_stats; struct strp_aggr_stats strp_stats; struct kcm_mux *mux; struct kcm_psock *psock; struct net *net = seq->private; struct kcm_net *knet = net_generic(net, kcm_net_id); memset(&mux_stats, 0, sizeof(mux_stats)); memset(&psock_stats, 0, sizeof(psock_stats)); memset(&strp_stats, 0, sizeof(strp_stats)); mutex_lock(&knet->mutex); aggregate_mux_stats(&knet->aggregate_mux_stats, &mux_stats); aggregate_psock_stats(&knet->aggregate_psock_stats, &psock_stats); aggregate_strp_stats(&knet->aggregate_strp_stats, &strp_stats); list_for_each_entry(mux, &knet->mux_list, kcm_mux_list) { spin_lock_bh(&mux->lock); aggregate_mux_stats(&mux->stats, &mux_stats); aggregate_psock_stats(&mux->aggregate_psock_stats, &psock_stats); aggregate_strp_stats(&mux->aggregate_strp_stats, &strp_stats); list_for_each_entry(psock, &mux->psocks, psock_list) { aggregate_psock_stats(&psock->stats, &psock_stats); save_strp_stats(&psock->strp, &strp_stats); } spin_unlock_bh(&mux->lock); } mutex_unlock(&knet->mutex); seq_printf(seq, "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s\n", "MUX", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "TX-Retries", "Attach", "Unattach", "UnattchRsvd", "RX-RdyDrops"); seq_printf(seq, "%-8s %-10llu %-16llu %-10llu %-16llu %-10u %-10u %-10u %-10u %-10u\n", "", mux_stats.rx_msgs, mux_stats.rx_bytes, mux_stats.tx_msgs, mux_stats.tx_bytes, mux_stats.tx_retries, mux_stats.psock_attach, mux_stats.psock_unattach_rsvd, mux_stats.psock_unattach, mux_stats.rx_ready_drops); seq_printf(seq, "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n", "Psock", "RX-Msgs", "RX-Bytes", "TX-Msgs", "TX-Bytes", "Reserved", "Unreserved", "RX-Aborts", "RX-Intr", "RX-Unrecov", "RX-MemFail", "RX-NeedMor", "RX-BadLen", "RX-TooBig", "RX-Timeout", "TX-Aborts"); seq_printf(seq, "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n", "", strp_stats.msgs, strp_stats.bytes, psock_stats.tx_msgs, psock_stats.tx_bytes, psock_stats.reserved, psock_stats.unreserved, strp_stats.aborts, strp_stats.interrupted, strp_stats.unrecov_intr, strp_stats.mem_fail, strp_stats.need_more_hdr, strp_stats.bad_hdr_len, strp_stats.msg_too_big, strp_stats.msg_timeouts, psock_stats.tx_aborts); return 0; } static int kcm_proc_init_net(struct net *net) { if (!proc_create_net_single("kcm_stats", 0444, net->proc_net, kcm_stats_seq_show, NULL)) goto out_kcm_stats; if (!proc_create_net("kcm", 0444, net->proc_net, &kcm_seq_ops, sizeof(struct kcm_proc_mux_state))) goto out_kcm; return 0; out_kcm: remove_proc_entry("kcm_stats", net->proc_net); out_kcm_stats: return -ENOMEM; } static void kcm_proc_exit_net(struct net *net) { remove_proc_entry("kcm", net->proc_net); remove_proc_entry("kcm_stats", net->proc_net); } static struct pernet_operations kcm_net_ops = { .init = kcm_proc_init_net, .exit = kcm_proc_exit_net, }; int __init kcm_proc_init(void) { return register_pernet_subsys(&kcm_net_ops); } void __exit kcm_proc_exit(void) { unregister_pernet_subsys(&kcm_net_ops); } #endif /* CONFIG_PROC_FS */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2020 Google LLC. */ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/binfmts.h> #include <linux/lsm_hooks.h> #include <linux/bpf_lsm.h> #include <linux/kallsyms.h> #include <linux/bpf_verifier.h> #include <net/bpf_sk_storage.h> #include <linux/bpf_local_storage.h> #include <linux/btf_ids.h> #include <linux/ima.h> #include <linux/bpf-cgroup.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. */ #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ { \ return DEFAULT; \ } #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) BTF_SET_START(bpf_lsm_hooks) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK BTF_SET_END(bpf_lsm_hooks) /* List of LSM hooks that should operate on 'current' cgroup regardless * of function signature. */ BTF_SET_START(bpf_lsm_current_hooks) /* operate on freshly allocated sk without any cgroup association */ #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_sk_alloc_security) BTF_ID(func, bpf_lsm_sk_free_security) #endif BTF_SET_END(bpf_lsm_current_hooks) /* List of LSM hooks that trigger while the socket is properly locked. */ BTF_SET_START(bpf_lsm_locked_sockopt_hooks) #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_sock_graft) BTF_ID(func, bpf_lsm_inet_csk_clone) BTF_ID(func, bpf_lsm_inet_conn_established) #endif BTF_SET_END(bpf_lsm_locked_sockopt_hooks) /* List of LSM hooks that trigger while the socket is _not_ locked, * but it's ok to call bpf_{g,s}etsockopt because the socket is still * in the early init phase. */ BTF_SET_START(bpf_lsm_unlocked_sockopt_hooks) #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_socket_post_create) BTF_ID(func, bpf_lsm_socket_socketpair) #endif BTF_SET_END(bpf_lsm_unlocked_sockopt_hooks) #ifdef CONFIG_CGROUP_BPF void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func) { const struct btf_param *args __maybe_unused; if (btf_type_vlen(prog->aux->attach_func_proto) < 1 || btf_id_set_contains(&bpf_lsm_current_hooks, prog->aux->attach_btf_id)) { *bpf_func = __cgroup_bpf_run_lsm_current; return; } #ifdef CONFIG_NET args = btf_params(prog->aux->attach_func_proto); if (args[0].type == btf_sock_ids[BTF_SOCK_TYPE_SOCKET]) *bpf_func = __cgroup_bpf_run_lsm_socket; else if (args[0].type == btf_sock_ids[BTF_SOCK_TYPE_SOCK]) *bpf_func = __cgroup_bpf_run_lsm_sock; else #endif *bpf_func = __cgroup_bpf_run_lsm_current; } #endif int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) { if (!prog->gpl_compatible) { bpf_log(vlog, "LSM programs must have a GPL compatible license\n"); return -EINVAL; } if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) { bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", prog->aux->attach_btf_id, prog->aux->attach_func_name); return -EINVAL; } return 0; } /* Mask for all the currently supported BPRM option flags */ #define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags) { if (flags & ~BPF_F_BRPM_OPTS_MASK) return -EINVAL; bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC); return 0; } BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm) static const struct bpf_func_proto bpf_bprm_opts_set_proto = { .func = bpf_bprm_opts_set, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0], .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size) { return ima_inode_hash(inode, dst, size); } static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog) { return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); } BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) static const struct bpf_func_proto bpf_ima_inode_hash_proto = { .func = bpf_ima_inode_hash, .gpl_only = false, .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .allowed = bpf_ima_inode_hash_allowed, }; BPF_CALL_3(bpf_ima_file_hash, struct file *, file, void *, dst, u32, size) { return ima_file_hash(file, dst, size); } BTF_ID_LIST_SINGLE(bpf_ima_file_hash_btf_ids, struct, file) static const struct bpf_func_proto bpf_ima_file_hash_proto = { .func = bpf_ima_file_hash, .gpl_only = false, .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_ima_file_hash_btf_ids[0], .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .allowed = bpf_ima_inode_hash_allowed, }; BPF_CALL_1(bpf_get_attach_cookie, void *, ctx) { struct bpf_trace_run_ctx *run_ctx; run_ctx = container_of(current->bpf_ctx, struct bpf_trace_run_ctx, run_ctx); return run_ctx->bpf_cookie; } static const struct bpf_func_proto bpf_get_attach_cookie_proto = { .func = bpf_get_attach_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; if (prog->expected_attach_type == BPF_LSM_CGROUP) { func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; } switch (func_id) { case BPF_FUNC_inode_storage_get: return &bpf_inode_storage_get_proto; case BPF_FUNC_inode_storage_delete: return &bpf_inode_storage_delete_proto; #ifdef CONFIG_NET case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #endif /* CONFIG_NET */ case BPF_FUNC_spin_lock: return &bpf_spin_lock_proto; case BPF_FUNC_spin_unlock: return &bpf_spin_unlock_proto; case BPF_FUNC_bprm_opts_set: return &bpf_bprm_opts_set_proto; case BPF_FUNC_ima_inode_hash: return &bpf_ima_inode_hash_proto; case BPF_FUNC_ima_file_hash: return &bpf_ima_file_hash_proto; case BPF_FUNC_get_attach_cookie: return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL; #ifdef CONFIG_NET case BPF_FUNC_setsockopt: if (prog->expected_attach_type != BPF_LSM_CGROUP) return NULL; if (btf_id_set_contains(&bpf_lsm_locked_sockopt_hooks, prog->aux->attach_btf_id)) return &bpf_sk_setsockopt_proto; if (btf_id_set_contains(&bpf_lsm_unlocked_sockopt_hooks, prog->aux->attach_btf_id)) return &bpf_unlocked_sk_setsockopt_proto; return NULL; case BPF_FUNC_getsockopt: if (prog->expected_attach_type != BPF_LSM_CGROUP) return NULL; if (btf_id_set_contains(&bpf_lsm_locked_sockopt_hooks, prog->aux->attach_btf_id)) return &bpf_sk_getsockopt_proto; if (btf_id_set_contains(&bpf_lsm_unlocked_sockopt_hooks, prog->aux->attach_btf_id)) return &bpf_unlocked_sk_getsockopt_proto; return NULL; #endif default: return tracing_prog_func_proto(func_id, prog); } } /* The set of hooks which are called without pagefaults disabled and are allowed * to "sleep" and thus can be used for sleepable BPF programs. */ BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) BTF_ID(func, bpf_lsm_bpf_map_create) BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) BTF_ID(func, bpf_lsm_bpf_prog_load) BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_bpf_token_create) BTF_ID(func, bpf_lsm_bpf_token_free) BTF_ID(func, bpf_lsm_bpf_token_cmd) BTF_ID(func, bpf_lsm_bpf_token_capable) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) BTF_ID(func, bpf_lsm_bprm_creds_for_exec) BTF_ID(func, bpf_lsm_bprm_creds_from_file) BTF_ID(func, bpf_lsm_capget) BTF_ID(func, bpf_lsm_capset) BTF_ID(func, bpf_lsm_cred_prepare) BTF_ID(func, bpf_lsm_file_ioctl) BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) BTF_ID(func, bpf_lsm_file_receive) BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) BTF_ID(func, bpf_lsm_inode_getxattr) BTF_ID(func, bpf_lsm_inode_mknod) BTF_ID(func, bpf_lsm_inode_need_killpriv) BTF_ID(func, bpf_lsm_inode_post_setxattr) BTF_ID(func, bpf_lsm_inode_readlink) BTF_ID(func, bpf_lsm_inode_rename) BTF_ID(func, bpf_lsm_inode_rmdir) BTF_ID(func, bpf_lsm_inode_setattr) BTF_ID(func, bpf_lsm_inode_setxattr) BTF_ID(func, bpf_lsm_inode_symlink) BTF_ID(func, bpf_lsm_inode_unlink) BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernel_read_file) BTF_ID(func, bpf_lsm_kernfs_init_security) #ifdef CONFIG_SECURITY_PATH BTF_ID(func, bpf_lsm_path_unlink) BTF_ID(func, bpf_lsm_path_mkdir) BTF_ID(func, bpf_lsm_path_rmdir) BTF_ID(func, bpf_lsm_path_truncate) BTF_ID(func, bpf_lsm_path_symlink) BTF_ID(func, bpf_lsm_path_link) BTF_ID(func, bpf_lsm_path_rename) BTF_ID(func, bpf_lsm_path_chmod) BTF_ID(func, bpf_lsm_path_chown) #endif /* CONFIG_SECURITY_PATH */ #ifdef CONFIG_KEYS BTF_ID(func, bpf_lsm_key_free) #endif /* CONFIG_KEYS */ BTF_ID(func, bpf_lsm_mmap_file) BTF_ID(func, bpf_lsm_netlink_send) BTF_ID(func, bpf_lsm_path_notify) BTF_ID(func, bpf_lsm_release_secctx) BTF_ID(func, bpf_lsm_sb_alloc_security) BTF_ID(func, bpf_lsm_sb_eat_lsm_opts) BTF_ID(func, bpf_lsm_sb_kern_mount) BTF_ID(func, bpf_lsm_sb_mount) BTF_ID(func, bpf_lsm_sb_remount) BTF_ID(func, bpf_lsm_sb_set_mnt_opts) BTF_ID(func, bpf_lsm_sb_show_options) BTF_ID(func, bpf_lsm_sb_statfs) BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_inet_conn_established) BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) BTF_ID(func, bpf_lsm_socket_create) BTF_ID(func, bpf_lsm_socket_getpeername) BTF_ID(func, bpf_lsm_socket_getpeersec_dgram) BTF_ID(func, bpf_lsm_socket_getsockname) BTF_ID(func, bpf_lsm_socket_getsockopt) BTF_ID(func, bpf_lsm_socket_listen) BTF_ID(func, bpf_lsm_socket_post_create) BTF_ID(func, bpf_lsm_socket_recvmsg) BTF_ID(func, bpf_lsm_socket_sendmsg) BTF_ID(func, bpf_lsm_socket_shutdown) BTF_ID(func, bpf_lsm_socket_socketpair) #endif /* CONFIG_SECURITY_NETWORK */ BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) BTF_ID(func, bpf_lsm_current_getsecid_subj) BTF_ID(func, bpf_lsm_task_getsecid_obj) BTF_ID(func, bpf_lsm_task_prctl) BTF_ID(func, bpf_lsm_task_setscheduler) BTF_ID(func, bpf_lsm_task_to_inode) BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) #ifdef CONFIG_SECURITY_NETWORK BTF_ID(func, bpf_lsm_sk_alloc_security) BTF_ID(func, bpf_lsm_sk_free_security) #endif /* CONFIG_SECURITY_NETWORK */ BTF_ID(func, bpf_lsm_task_free) BTF_SET_END(untrusted_lsm_hooks) bool bpf_lsm_is_sleepable_hook(u32 btf_id) { return btf_id_set_contains(&sleepable_lsm_hooks, btf_id); } bool bpf_lsm_is_trusted(const struct bpf_prog *prog) { return !btf_id_set_contains(&untrusted_lsm_hooks, prog->aux->attach_btf_id); } const struct bpf_prog_ops lsm_prog_ops = { }; const struct bpf_verifier_ops lsm_verifier_ops = { .get_func_proto = bpf_lsm_func_proto, .is_valid_access = btf_ctx_access, }; |
| 55 3 42 33 39 31 31 35 18 4 2 51 8 6 28 7 1 34 17 4 14 12 5 9 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/bitmap.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handling of allocation file */ #include <linux/pagemap.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" #define PAGE_CACHE_BITS (PAGE_SIZE * 8) int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *max) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct page *page; struct address_space *mapping; __be32 *pptr, *curr, *end; u32 mask, start, len, n; __be32 val; int i; len = *max; if (!len) return size; hfs_dbg(BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len); mutex_lock(&sbi->alloc_mutex); mapping = sbi->alloc_file->i_mapping; page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL); if (IS_ERR(page)) { start = size; goto out; } pptr = kmap_local_page(page); curr = pptr + (offset & (PAGE_CACHE_BITS - 1)) / 32; i = offset % 32; offset &= ~(PAGE_CACHE_BITS - 1); if ((size ^ offset) / PAGE_CACHE_BITS) end = pptr + PAGE_CACHE_BITS / 32; else end = pptr + ((size + 31) & (PAGE_CACHE_BITS - 1)) / 32; /* scan the first partial u32 for zero bits */ val = *curr; if (~val) { n = be32_to_cpu(val); mask = (1U << 31) >> i; for (; i < 32; mask >>= 1, i++) { if (!(n & mask)) goto found; } } curr++; /* scan complete u32s for the first zero bit */ while (1) { while (curr < end) { val = *curr; if (~val) { n = be32_to_cpu(val); mask = 1 << 31; for (i = 0; i < 32; mask >>= 1, i++) { if (!(n & mask)) goto found; } } curr++; } kunmap_local(pptr); offset += PAGE_CACHE_BITS; if (offset >= size) break; page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL); if (IS_ERR(page)) { start = size; goto out; } curr = pptr = kmap_local_page(page); if ((size ^ offset) / PAGE_CACHE_BITS) end = pptr + PAGE_CACHE_BITS / 32; else end = pptr + ((size + 31) & (PAGE_CACHE_BITS - 1)) / 32; } hfs_dbg(BITMAP, "bitmap full\n"); start = size; goto out; found: start = offset + (curr - pptr) * 32 + i; if (start >= size) { hfs_dbg(BITMAP, "bitmap full\n"); goto out; } /* do any partial u32 at the start */ len = min(size - start, len); while (1) { n |= mask; if (++i >= 32) break; mask >>= 1; if (!--len || n & mask) goto done; } if (!--len) goto done; *curr++ = cpu_to_be32(n); /* do full u32s */ while (1) { while (curr < end) { n = be32_to_cpu(*curr); if (len < 32) goto last; if (n) { len = 32; goto last; } *curr++ = cpu_to_be32(0xffffffff); len -= 32; } set_page_dirty(page); kunmap_local(pptr); offset += PAGE_CACHE_BITS; page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL); if (IS_ERR(page)) { start = size; goto out; } pptr = kmap_local_page(page); curr = pptr; end = pptr + PAGE_CACHE_BITS / 32; } last: /* do any partial u32 at end */ mask = 1U << 31; for (i = 0; i < len; i++) { if (n & mask) break; n |= mask; mask >>= 1; } done: *curr = cpu_to_be32(n); set_page_dirty(page); kunmap_local(pptr); *max = offset + (curr - pptr) * 32 + i - start; sbi->free_blocks -= *max; hfsplus_mark_mdb_dirty(sb); hfs_dbg(BITMAP, "-> %u,%u\n", start, *max); out: mutex_unlock(&sbi->alloc_mutex); return start; } int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct page *page; struct address_space *mapping; __be32 *pptr, *curr, *end; u32 mask, len, pnr; int i; /* is there any actual work to be done? */ if (!count) return 0; hfs_dbg(BITMAP, "block_free: %u,%u\n", offset, count); /* are all of the bits in range? */ if ((offset + count) > sbi->total_blocks) return -ENOENT; mutex_lock(&sbi->alloc_mutex); mapping = sbi->alloc_file->i_mapping; pnr = offset / PAGE_CACHE_BITS; page = read_mapping_page(mapping, pnr, NULL); if (IS_ERR(page)) goto kaboom; pptr = kmap_local_page(page); curr = pptr + (offset & (PAGE_CACHE_BITS - 1)) / 32; end = pptr + PAGE_CACHE_BITS / 32; len = count; /* do any partial u32 at the start */ i = offset % 32; if (i) { int j = 32 - i; mask = 0xffffffffU << j; if (j > count) { mask |= 0xffffffffU >> (i + count); *curr++ &= cpu_to_be32(mask); goto out; } *curr++ &= cpu_to_be32(mask); count -= j; } /* do full u32s */ while (1) { while (curr < end) { if (count < 32) goto done; *curr++ = 0; count -= 32; } if (!count) break; set_page_dirty(page); kunmap_local(pptr); page = read_mapping_page(mapping, ++pnr, NULL); if (IS_ERR(page)) goto kaboom; pptr = kmap_local_page(page); curr = pptr; end = pptr + PAGE_CACHE_BITS / 32; } done: /* do any partial u32 at end */ if (count) { mask = 0xffffffffU >> count; *curr &= cpu_to_be32(mask); } out: set_page_dirty(page); kunmap_local(pptr); sbi->free_blocks += len; hfsplus_mark_mdb_dirty(sb); mutex_unlock(&sbi->alloc_mutex); return 0; kaboom: pr_crit("unable to mark blocks free: error %ld\n", PTR_ERR(page)); mutex_unlock(&sbi->alloc_mutex); return -EIO; } |
| 55 28 56 13 19 7 10 595 11 53 622 419 367 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2009-2021 Christoph Hellwig * * 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: * * offset: byte offset into a subcomponent of a file operation * pos: file offset, in bytes * length: length of a file operation, in bytes * ino: inode number * * Numbers describing space allocations should be formatted in hexadecimal. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM iomap #if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define _IOMAP_TRACE_H #include <linux/tracepoint.h> struct inode; DECLARE_EVENT_CLASS(iomap_readpage_class, TP_PROTO(struct inode *inode, int nr_pages), TP_ARGS(inode, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(int, nr_pages) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_pages = nr_pages; ), TP_printk("dev %d:%d ino 0x%llx nr_pages %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->nr_pages) ) #define DEFINE_READPAGE_EVENT(name) \ DEFINE_EVENT(iomap_readpage_class, name, \ TP_PROTO(struct inode *inode, int nr_pages), \ TP_ARGS(inode, nr_pages)) DEFINE_READPAGE_EVENT(iomap_readpage); DEFINE_READPAGE_EVENT(iomap_readahead); DECLARE_EVENT_CLASS(iomap_range_class, TP_PROTO(struct inode *inode, loff_t off, u64 len), TP_ARGS(inode, off, len), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, size) __field(loff_t, offset) __field(u64, length) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->size = i_size_read(inode); __entry->offset = off; __entry->length = len; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx length 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->offset, __entry->length) ) #define DEFINE_RANGE_EVENT(name) \ DEFINE_EVENT(iomap_range_class, name, \ TP_PROTO(struct inode *inode, loff_t off, u64 len),\ TP_ARGS(inode, off, len)) DEFINE_RANGE_EVENT(iomap_writepage); DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); DEFINE_RANGE_EVENT(iomap_dio_rw_queued); #define IOMAP_TYPE_STRINGS \ { IOMAP_HOLE, "HOLE" }, \ { IOMAP_DELALLOC, "DELALLOC" }, \ { IOMAP_MAPPED, "MAPPED" }, \ { IOMAP_UNWRITTEN, "UNWRITTEN" }, \ { IOMAP_INLINE, "INLINE" } #define IOMAP_FLAGS_STRINGS \ { IOMAP_WRITE, "WRITE" }, \ { IOMAP_ZERO, "ZERO" }, \ { IOMAP_REPORT, "REPORT" }, \ { IOMAP_FAULT, "FAULT" }, \ { IOMAP_DIRECT, "DIRECT" }, \ { IOMAP_NOWAIT, "NOWAIT" } #define IOMAP_F_FLAGS_STRINGS \ { IOMAP_F_NEW, "NEW" }, \ { IOMAP_F_DIRTY, "DIRTY" }, \ { IOMAP_F_SHARED, "SHARED" }, \ { IOMAP_F_MERGED, "MERGED" }, \ { IOMAP_F_BUFFER_HEAD, "BH" }, \ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" } #define IOMAP_DIO_STRINGS \ {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" } DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), TP_ARGS(inode, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr 0x%llx offset 0x%llx " "length 0x%llx type %s flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS)) ) #define DEFINE_IOMAP_EVENT(name) \ DEFINE_EVENT(iomap_class, name, \ TP_PROTO(struct inode *inode, struct iomap *iomap), \ TP_ARGS(inode, iomap)) DEFINE_IOMAP_EVENT(iomap_iter_dstmap); DEFINE_IOMAP_EVENT(iomap_iter_srcmap); TRACE_EVENT(iomap_writepage_map, TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len, struct iomap *iomap), TP_ARGS(inode, pos, dirty_len, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, pos) __field(u64, dirty_len) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->dirty_len = dirty_len; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d pos 0x%llx dirty len 0x%llx " "addr 0x%llx offset 0x%llx length 0x%llx type %s flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->pos, __entry->dirty_len, __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS)) ); TRACE_EVENT(iomap_iter, TP_PROTO(struct iomap_iter *iter, const void *ops, unsigned long caller), TP_ARGS(iter, ops, caller), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, pos) __field(u64, length) __field(s64, processed) __field(unsigned int, flags) __field(const void *, ops) __field(unsigned long, caller) ), TP_fast_assign( __entry->dev = iter->inode->i_sb->s_dev; __entry->ino = iter->inode->i_ino; __entry->pos = iter->pos; __entry->length = iomap_length(iter); __entry->processed = iter->processed; __entry->flags = iter->flags; __entry->ops = ops; __entry->caller = caller; ), TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx processed %lld flags %s (0x%x) ops %ps caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->length, __entry->processed, __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS), __entry->flags, __entry->ops, (void *)__entry->caller) ); TRACE_EVENT(iomap_dio_rw_begin, TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, unsigned int dio_flags, size_t done_before), TP_ARGS(iocb, iter, dio_flags, done_before), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, isize) __field(loff_t, pos) __field(size_t, count) __field(size_t, done_before) __field(int, ki_flags) __field(unsigned int, dio_flags) __field(bool, aio) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->isize = file_inode(iocb->ki_filp)->i_size; __entry->pos = iocb->ki_pos; __entry->count = iov_iter_count(iter); __entry->done_before = done_before; __entry->ki_flags = iocb->ki_flags; __entry->dio_flags = dio_flags; __entry->aio = !is_sync_kiocb(iocb); ), TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx length 0x%zx done_before 0x%zx flags %s dio_flags %s aio %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->pos, __entry->count, __entry->done_before, __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), __print_flags(__entry->dio_flags, "|", IOMAP_DIO_STRINGS), __entry->aio) ); TRACE_EVENT(iomap_dio_complete, TP_PROTO(struct kiocb *iocb, int error, ssize_t ret), TP_ARGS(iocb, error, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, isize) __field(loff_t, pos) __field(int, ki_flags) __field(bool, aio) __field(int, error) __field(ssize_t, ret) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->isize = file_inode(iocb->ki_filp)->i_size; __entry->pos = iocb->ki_pos; __entry->ki_flags = iocb->ki_flags; __entry->aio = !is_sync_kiocb(iocb); __entry->error = error; __entry->ret = ret; ), TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx flags %s aio %d error %d ret %zd", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->pos, __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), __entry->aio, __entry->error, __entry->ret) ); #endif /* _IOMAP_TRACE_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 360 360 363 362 363 364 364 363 5 10 5 67 363 10 363 359 69 69 68 10 364 6 364 69 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "mmu_internal.h" #include "tdp_iter.h" #include "spte.h" /* * Recalculates the pointer to the SPTE for the current GFN and level and * reread the SPTE. */ static void tdp_iter_refresh_sptep(struct tdp_iter *iter) { iter->sptep = iter->pt_path[iter->level - 1] + SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level); iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); } /* * Return the TDP iterator to the root PT and allow it to continue its * traversal over the paging structure from there. */ void tdp_iter_restart(struct tdp_iter *iter) { iter->yielded = false; iter->yielded_gfn = iter->next_last_level_gfn; iter->level = iter->root_level; iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); iter->valid = true; } /* * Sets a TDP iterator to walk a pre-order traversal of the paging structure * rooted at root_pt, starting with the walk to translate next_last_level_gfn. */ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, int min_level, gfn_t next_last_level_gfn) { if (WARN_ON_ONCE(!root || (root->role.level < 1) || (root->role.level > PT64_ROOT_MAX_LEVEL))) { iter->valid = false; return; } iter->next_last_level_gfn = next_last_level_gfn; iter->root_level = root->role.level; iter->min_level = min_level; iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt; iter->as_id = kvm_mmu_page_as_id(root); tdp_iter_restart(iter); } /* * Given an SPTE and its level, returns a pointer containing the host virtual * address of the child page table referenced by the SPTE. Returns null if * there is no such entry. */ tdp_ptep_t spte_to_child_pt(u64 spte, int level) { /* * There's no child entry if this entry isn't present or is a * last-level entry. */ if (!is_shadow_present_pte(spte) || is_last_spte(spte, level)) return NULL; return (tdp_ptep_t)__va(spte_to_pfn(spte) << PAGE_SHIFT); } /* * Steps down one level in the paging structure towards the goal GFN. Returns * true if the iterator was able to step down a level, false otherwise. */ static bool try_step_down(struct tdp_iter *iter) { tdp_ptep_t child_pt; if (iter->level == iter->min_level) return false; /* * Reread the SPTE before stepping down to avoid traversing into page * tables that are no longer linked from this entry. */ iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); child_pt = spte_to_child_pt(iter->old_spte, iter->level); if (!child_pt) return false; iter->level--; iter->pt_path[iter->level - 1] = child_pt; iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; } /* * Steps to the next entry in the current page table, at the current page table * level. The next entry could point to a page backing guest memory or another * page table, or it could be non-present. Returns true if the iterator was * able to step to the next entry in the page table, false if the iterator was * already at the end of the current page table. */ static bool try_step_side(struct tdp_iter *iter) { /* * Check if the iterator is already at the end of the current page * table. */ if (SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level) == (SPTE_ENT_PER_PAGE - 1)) return false; iter->gfn += KVM_PAGES_PER_HPAGE(iter->level); iter->next_last_level_gfn = iter->gfn; iter->sptep++; iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); return true; } /* * Tries to traverse back up a level in the paging structure so that the walk * can continue from the next entry in the parent page table. Returns true on a * successful step up, false if already in the root page. */ static bool try_step_up(struct tdp_iter *iter) { if (iter->level == iter->root_level) return false; iter->level++; iter->gfn = gfn_round_for_level(iter->gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; } /* * Step to the next SPTE in a pre-order traversal of the paging structure. * To get to the next SPTE, the iterator either steps down towards the goal * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a * higher GFN. * * The basic algorithm is as follows: * 1. If the current SPTE is a non-last-level SPTE, step down into the page * table it points to. * 2. If the iterator cannot step down, it will try to step to the next SPTE * in the current page of the paging structure. * 3. If the iterator cannot step to the next entry in the current page, it will * try to step up to the parent paging structure page. In this case, that * SPTE will have already been visited, and so the iterator must also step * to the side again. */ void tdp_iter_next(struct tdp_iter *iter) { if (iter->yielded) { tdp_iter_restart(iter); return; } if (try_step_down(iter)) return; do { if (try_step_side(iter)) return; } while (try_step_up(iter)); iter->valid = false; } |
| 141 144 144 138 68 140 5 138 137 139 69 67 137 139 139 134 88 60 139 139 146 145 28 146 146 70 141 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright(c) 2019 Intel Corporation. */ #include <linux/hash.h> #include <linux/bpf.h> #include <linux/filter.h> #include <linux/static_call.h> /* The BPF dispatcher is a multiway branch code generator. The * dispatcher is a mechanism to avoid the performance penalty of an * indirect call, which is expensive when retpolines are enabled. A * dispatch client registers a BPF program into the dispatcher, and if * there is available room in the dispatcher a direct call to the BPF * program will be generated. All calls to the BPF programs called via * the dispatcher will then be a direct call, instead of an * indirect. The dispatcher hijacks a trampoline function it via the * __fentry__ of the trampoline. The trampoline function has the * following signature: * * unsigned int trampoline(const void *ctx, const struct bpf_insn *insnsi, * unsigned int (*bpf_func)(const void *, * const struct bpf_insn *)); */ static struct bpf_dispatcher_prog *bpf_dispatcher_find_prog( struct bpf_dispatcher *d, struct bpf_prog *prog) { int i; for (i = 0; i < BPF_DISPATCHER_MAX; i++) { if (prog == d->progs[i].prog) return &d->progs[i]; } return NULL; } static struct bpf_dispatcher_prog *bpf_dispatcher_find_free( struct bpf_dispatcher *d) { return bpf_dispatcher_find_prog(d, NULL); } static bool bpf_dispatcher_add_prog(struct bpf_dispatcher *d, struct bpf_prog *prog) { struct bpf_dispatcher_prog *entry; if (!prog) return false; entry = bpf_dispatcher_find_prog(d, prog); if (entry) { refcount_inc(&entry->users); return false; } entry = bpf_dispatcher_find_free(d); if (!entry) return false; bpf_prog_inc(prog); entry->prog = prog; refcount_set(&entry->users, 1); d->num_progs++; return true; } static bool bpf_dispatcher_remove_prog(struct bpf_dispatcher *d, struct bpf_prog *prog) { struct bpf_dispatcher_prog *entry; if (!prog) return false; entry = bpf_dispatcher_find_prog(d, prog); if (!entry) return false; if (refcount_dec_and_test(&entry->users)) { entry->prog = NULL; bpf_prog_put(prog); d->num_progs--; return true; } return false; } int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs) { return -ENOTSUPP; } static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf) { s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0]; int i; for (i = 0; i < BPF_DISPATCHER_MAX; i++) { if (d->progs[i].prog) *ipsp++ = (s64)(uintptr_t)d->progs[i].prog->bpf_func; } return arch_prepare_bpf_dispatcher(image, buf, &ips[0], d->num_progs); } static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs) { void *new, *tmp; u32 noff = 0; if (prev_num_progs) noff = d->image_off ^ (PAGE_SIZE / 2); new = d->num_progs ? d->image + noff : NULL; tmp = d->num_progs ? d->rw_image + noff : NULL; if (new) { /* Prepare the dispatcher in d->rw_image. Then use * bpf_arch_text_copy to update d->image, which is RO+X. */ if (bpf_dispatcher_prepare(d, new, tmp)) return; if (IS_ERR(bpf_arch_text_copy(new, tmp, PAGE_SIZE / 2))) return; } __BPF_DISPATCHER_UPDATE(d, new ?: (void *)&bpf_dispatcher_nop_func); /* Make sure all the callers executing the previous/old half of the * image leave it, so following update call can modify it safely. */ synchronize_rcu(); if (new) d->image_off = noff; } void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to) { bool changed = false; int prev_num_progs; if (from == to) return; mutex_lock(&d->mutex); if (!d->image) { d->image = bpf_prog_pack_alloc(PAGE_SIZE, bpf_jit_fill_hole_with_zero); if (!d->image) goto out; d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE); if (!d->rw_image) { bpf_prog_pack_free(d->image, PAGE_SIZE); d->image = NULL; goto out; } bpf_image_ksym_add(d->image, PAGE_SIZE, &d->ksym); } prev_num_progs = d->num_progs; changed |= bpf_dispatcher_remove_prog(d, from); changed |= bpf_dispatcher_add_prog(d, to); if (!changed) goto out; bpf_dispatcher_update(d, prev_num_progs); out: mutex_unlock(&d->mutex); } |
| 1355 1355 1338 15 28 13 38 1 2 1 3 2 1 3 3 3 15 109 23 108 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Event handling for HSR and PRP devices. */ #include <linux/netdevice.h> #include <net/rtnetlink.h> #include <linux/rculist.h> #include <linux/timer.h> #include <linux/etherdevice.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_netlink.h" #include "hsr_framereg.h" #include "hsr_slave.h" static bool hsr_slave_empty(struct hsr_priv *hsr) { struct hsr_port *port; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) return false; return true; } static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, void *ptr) { struct hsr_port *port, *master; struct net_device *dev; struct hsr_priv *hsr; LIST_HEAD(list_kill); int mtu_max; int res; dev = netdev_notifier_info_to_dev(ptr); port = hsr_port_get_rtnl(dev); if (!port) { if (!is_hsr_master(dev)) return NOTIFY_DONE; /* Not an HSR device */ hsr = netdev_priv(dev); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (!port) { /* Resend of notification concerning removed device? */ return NOTIFY_DONE; } } else { hsr = port->hsr; } switch (event) { case NETDEV_UP: /* Administrative state DOWN */ case NETDEV_DOWN: /* Administrative state UP */ case NETDEV_CHANGE: /* Link (carrier) state changes */ hsr_check_carrier_and_operstate(hsr); break; case NETDEV_CHANGENAME: if (is_hsr_master(dev)) hsr_debugfs_rename(dev); break; case NETDEV_CHANGEADDR: if (port->type == HSR_PT_MASTER) { /* This should not happen since there's no * ndo_set_mac_address() for HSR devices - i.e. not * supported. */ break; } master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port->type == HSR_PT_SLAVE_A) { eth_hw_addr_set(master->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, master->dev); } /* Make sure we recognize frames from ourselves in hsr_rcv() */ port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); res = hsr_create_self_node(hsr, master->dev->dev_addr, port ? port->dev->dev_addr : master->dev->dev_addr); if (res) netdev_warn(master->dev, "Could not update HSR node address.\n"); break; case NETDEV_CHANGEMTU: if (port->type == HSR_PT_MASTER) break; /* Handled in ndo_change_mtu() */ mtu_max = hsr_get_max_mtu(port->hsr); master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); WRITE_ONCE(master->dev->mtu, mtu_max); break; case NETDEV_UNREGISTER: if (!is_hsr_master(dev)) { master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); hsr_del_port(port); if (hsr_slave_empty(master->hsr)) { const struct rtnl_link_ops *ops; ops = master->dev->rtnl_link_ops; ops->dellink(master->dev, &list_kill); unregister_netdevice_many(&list_kill); } } break; case NETDEV_PRE_TYPE_CHANGE: /* HSR works only on Ethernet devices. Refuse slave to change * its type. */ return NOTIFY_BAD; } return NOTIFY_DONE; } struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) { struct hsr_port *port; hsr_for_each_port(hsr, port) if (port->type == pt) return port; return NULL; } int hsr_get_version(struct net_device *dev, enum hsr_version *ver) { struct hsr_priv *hsr; hsr = netdev_priv(dev); *ver = hsr->prot_version; return 0; } EXPORT_SYMBOL(hsr_get_version); static struct notifier_block hsr_nb = { .notifier_call = hsr_netdev_notify, /* Slave event notifications */ }; static int __init hsr_init(void) { int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); err = register_netdevice_notifier(&hsr_nb); if (err) return err; err = hsr_netlink_init(); if (err) { unregister_netdevice_notifier(&hsr_nb); return err; } return 0; } static void __exit hsr_exit(void) { hsr_netlink_exit(); hsr_debugfs_remove_root(); unregister_netdevice_notifier(&hsr_nb); } module_init(hsr_init); module_exit(hsr_exit); MODULE_DESCRIPTION("High-availability Seamless Redundancy (HSR) driver"); MODULE_LICENSE("GPL"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /****************************************************************************** * usb_intf.c * * Copyright(c) 2007 - 2010 Realtek Corporation. All rights reserved. * Linux device driver for RTL8192SU * * Modifications for inclusion into the Linux staging tree are * Copyright(c) 2010 Larry Finger. All rights reserved. * * Contact information: * WLAN FAE <wlanfae@realtek.com> * Larry Finger <Larry.Finger@lwfinger.net> * ******************************************************************************/ #define _HCI_INTF_C_ #include <linux/usb.h> #include <linux/module.h> #include <linux/firmware.h> #include "osdep_service.h" #include "drv_types.h" #include "recv_osdep.h" #include "xmit_osdep.h" #include "rtl8712_efuse.h" #include "usb_ops.h" #include "usb_osintf.h" static struct usb_interface *pintf; static int r871xu_drv_init(struct usb_interface *pusb_intf, const struct usb_device_id *pdid); static void r871xu_dev_remove(struct usb_interface *pusb_intf); static const struct usb_device_id rtl871x_usb_id_tbl[] = { /* RTL8188SU */ /* Realtek */ {USB_DEVICE(0x0BDA, 0x8171)}, {USB_DEVICE(0x0bda, 0x8173)}, {USB_DEVICE(0x0bda, 0x8712)}, {USB_DEVICE(0x0bda, 0x8713)}, {USB_DEVICE(0x0bda, 0xC512)}, /* Abocom */ {USB_DEVICE(0x07B8, 0x8188)}, /* ASUS */ {USB_DEVICE(0x0B05, 0x1786)}, {USB_DEVICE(0x0B05, 0x1791)}, /* 11n mode disable */ /* Belkin */ {USB_DEVICE(0x050D, 0x945A)}, /* ISY IWL - Belkin clone */ {USB_DEVICE(0x050D, 0x11F1)}, /* Corega */ {USB_DEVICE(0x07AA, 0x0047)}, /* D-Link */ {USB_DEVICE(0x2001, 0x3306)}, {USB_DEVICE(0x07D1, 0x3306)}, /* 11n mode disable */ /* Edimax */ {USB_DEVICE(0x7392, 0x7611)}, /* EnGenius */ {USB_DEVICE(0x1740, 0x9603)}, /* Hawking */ {USB_DEVICE(0x0E66, 0x0016)}, /* Hercules */ {USB_DEVICE(0x06F8, 0xE034)}, {USB_DEVICE(0x06F8, 0xE032)}, /* Logitec */ {USB_DEVICE(0x0789, 0x0167)}, /* PCI */ {USB_DEVICE(0x2019, 0xAB28)}, {USB_DEVICE(0x2019, 0xED16)}, /* Sitecom */ {USB_DEVICE(0x0DF6, 0x0057)}, {USB_DEVICE(0x0DF6, 0x0045)}, {USB_DEVICE(0x0DF6, 0x0059)}, /* 11n mode disable */ {USB_DEVICE(0x0DF6, 0x004B)}, {USB_DEVICE(0x0DF6, 0x005B)}, {USB_DEVICE(0x0DF6, 0x005D)}, {USB_DEVICE(0x0DF6, 0x0063)}, /* Sweex */ {USB_DEVICE(0x177F, 0x0154)}, /* Thinkware */ {USB_DEVICE(0x0BDA, 0x5077)}, /* Toshiba */ {USB_DEVICE(0x1690, 0x0752)}, /* - */ {USB_DEVICE(0x20F4, 0x646B)}, {USB_DEVICE(0x083A, 0xC512)}, {USB_DEVICE(0x25D4, 0x4CA1)}, {USB_DEVICE(0x25D4, 0x4CAB)}, /* RTL8191SU */ /* Realtek */ {USB_DEVICE(0x0BDA, 0x8172)}, {USB_DEVICE(0x0BDA, 0x8192)}, /* Amigo */ {USB_DEVICE(0x0EB0, 0x9061)}, /* ASUS/EKB */ {USB_DEVICE(0x13D3, 0x3323)}, {USB_DEVICE(0x13D3, 0x3311)}, /* 11n mode disable */ {USB_DEVICE(0x13D3, 0x3342)}, /* ASUS/EKBLenovo */ {USB_DEVICE(0x13D3, 0x3333)}, {USB_DEVICE(0x13D3, 0x3334)}, {USB_DEVICE(0x13D3, 0x3335)}, /* 11n mode disable */ {USB_DEVICE(0x13D3, 0x3336)}, /* 11n mode disable */ /* ASUS/Media BOX */ {USB_DEVICE(0x13D3, 0x3309)}, /* Belkin */ {USB_DEVICE(0x050D, 0x815F)}, /* D-Link */ {USB_DEVICE(0x07D1, 0x3302)}, {USB_DEVICE(0x07D1, 0x3300)}, {USB_DEVICE(0x07D1, 0x3303)}, /* Edimax */ {USB_DEVICE(0x7392, 0x7612)}, /* EnGenius */ {USB_DEVICE(0x1740, 0x9605)}, /* Guillemot */ {USB_DEVICE(0x06F8, 0xE031)}, /* Hawking */ {USB_DEVICE(0x0E66, 0x0015)}, /* Mediao */ {USB_DEVICE(0x13D3, 0x3306)}, /* PCI */ {USB_DEVICE(0x2019, 0xED18)}, {USB_DEVICE(0x2019, 0x4901)}, /* Sitecom */ {USB_DEVICE(0x0DF6, 0x0058)}, {USB_DEVICE(0x0DF6, 0x0049)}, {USB_DEVICE(0x0DF6, 0x004C)}, {USB_DEVICE(0x0DF6, 0x006C)}, {USB_DEVICE(0x0DF6, 0x0064)}, /* Skyworth */ {USB_DEVICE(0x14b2, 0x3300)}, {USB_DEVICE(0x14b2, 0x3301)}, {USB_DEVICE(0x14B2, 0x3302)}, /* - */ {USB_DEVICE(0x04F2, 0xAFF2)}, {USB_DEVICE(0x04F2, 0xAFF5)}, {USB_DEVICE(0x04F2, 0xAFF6)}, {USB_DEVICE(0x13D3, 0x3339)}, {USB_DEVICE(0x13D3, 0x3340)}, /* 11n mode disable */ {USB_DEVICE(0x13D3, 0x3341)}, /* 11n mode disable */ {USB_DEVICE(0x13D3, 0x3310)}, {USB_DEVICE(0x13D3, 0x3325)}, /* RTL8192SU */ /* Realtek */ {USB_DEVICE(0x0BDA, 0x8174)}, /* Belkin */ {USB_DEVICE(0x050D, 0x845A)}, /* Corega */ {USB_DEVICE(0x07AA, 0x0051)}, /* Edimax */ {USB_DEVICE(0x7392, 0x7622)}, /* NEC */ {USB_DEVICE(0x0409, 0x02B6)}, {} }; MODULE_DEVICE_TABLE(usb, rtl871x_usb_id_tbl); static struct specific_device_id specific_device_id_tbl[] = { {.idVendor = 0x0b05, .idProduct = 0x1791, .flags = SPEC_DEV_ID_DISABLE_HT}, {.idVendor = 0x0df6, .idProduct = 0x0059, .flags = SPEC_DEV_ID_DISABLE_HT}, {.idVendor = 0x13d3, .idProduct = 0x3306, .flags = SPEC_DEV_ID_DISABLE_HT}, {.idVendor = 0x13D3, .idProduct = 0x3311, .flags = SPEC_DEV_ID_DISABLE_HT}, {.idVendor = 0x13d3, .idProduct = 0x3335, .flags = SPEC_DEV_ID_DISABLE_HT}, {.idVendor = 0x13d3, .idProduct = 0x3336, .flags = SPEC_DEV_ID_DISABLE_HT}, {.idVendor = 0x13d3, .idProduct = 0x3340, .flags = SPEC_DEV_ID_DISABLE_HT}, {.idVendor = 0x13d3, .idProduct = 0x3341, .flags = SPEC_DEV_ID_DISABLE_HT}, {} }; struct drv_priv { struct usb_driver r871xu_drv; int drv_registered; }; #ifdef CONFIG_PM static int r871x_suspend(struct usb_interface *pusb_intf, pm_message_t state) { struct net_device *pnetdev = usb_get_intfdata(pusb_intf); struct _adapter *padapter = netdev_priv(pnetdev); netdev_info(pnetdev, "Suspending...\n"); padapter->suspended = true; rtl871x_intf_stop(padapter); if (pnetdev->netdev_ops->ndo_stop) pnetdev->netdev_ops->ndo_stop(pnetdev); mdelay(10); netif_device_detach(pnetdev); return 0; } static void rtl871x_intf_resume(struct _adapter *padapter) { if (padapter->dvobjpriv.inirp_init) padapter->dvobjpriv.inirp_init(padapter); } static int r871x_resume(struct usb_interface *pusb_intf) { struct net_device *pnetdev = usb_get_intfdata(pusb_intf); struct _adapter *padapter = netdev_priv(pnetdev); netdev_info(pnetdev, "Resuming...\n"); netif_device_attach(pnetdev); if (pnetdev->netdev_ops->ndo_open) pnetdev->netdev_ops->ndo_open(pnetdev); padapter->suspended = false; rtl871x_intf_resume(padapter); return 0; } #endif static struct drv_priv drvpriv = { .r871xu_drv.name = "r8712u", .r871xu_drv.id_table = rtl871x_usb_id_tbl, .r871xu_drv.probe = r871xu_drv_init, .r871xu_drv.disconnect = r871xu_dev_remove, #ifdef CONFIG_PM .r871xu_drv.suspend = r871x_suspend, .r871xu_drv.resume = r871x_resume, #endif }; static uint r8712_usb_dvobj_init(struct _adapter *padapter) { uint status = _SUCCESS; struct usb_host_interface *phost_iface; struct usb_interface_descriptor *piface_desc; struct dvobj_priv *pdvobjpriv = &padapter->dvobjpriv; struct usb_device *pusbd = pdvobjpriv->pusbdev; pdvobjpriv->padapter = padapter; padapter->eeprom_address_size = 6; phost_iface = pintf->cur_altsetting; piface_desc = &phost_iface->desc; pdvobjpriv->nr_endpoint = piface_desc->bNumEndpoints; if (pusbd->speed == USB_SPEED_HIGH) { pdvobjpriv->ishighspeed = true; dev_info(&pusbd->dev, "r8712u: USB_SPEED_HIGH with %d endpoints\n", pdvobjpriv->nr_endpoint); } else { pdvobjpriv->ishighspeed = false; dev_info(&pusbd->dev, "r8712u: USB_SPEED_LOW with %d endpoints\n", pdvobjpriv->nr_endpoint); } if ((r8712_alloc_io_queue(padapter)) == _FAIL) status = _FAIL; return status; } static void r8712_usb_dvobj_deinit(struct _adapter *padapter) { r8712_free_io_queue(padapter); } void rtl871x_intf_stop(struct _adapter *padapter) { /*disable_hw_interrupt*/ if (!padapter->surprise_removed) { /*device still exists, so driver can do i/o operation * TODO: */ } /* cancel in irp */ if (padapter->dvobjpriv.inirp_deinit) padapter->dvobjpriv.inirp_deinit(padapter); /* cancel out irp */ r8712_usb_write_port_cancel(padapter); /* TODO:cancel other irps */ } void r871x_dev_unload(struct _adapter *padapter) { if (padapter->bup) { /*s1.*/ padapter->driver_stopped = true; /*s3.*/ rtl871x_intf_stop(padapter); /*s4.*/ r8712_stop_drv_threads(padapter); /*s5.*/ if (!padapter->surprise_removed) { padapter->hw_init_completed = false; rtl8712_hal_deinit(padapter); } padapter->bup = false; } } static void disable_ht_for_spec_devid(const struct usb_device_id *pdid, struct _adapter *padapter) { u16 vid, pid; u32 flags; int i; int num = ARRAY_SIZE(specific_device_id_tbl); for (i = 0; i < num; i++) { vid = specific_device_id_tbl[i].idVendor; pid = specific_device_id_tbl[i].idProduct; flags = specific_device_id_tbl[i].flags; if ((pdid->idVendor == vid) && (pdid->idProduct == pid) && (flags & SPEC_DEV_ID_DISABLE_HT)) { padapter->registrypriv.ht_enable = 0; padapter->registrypriv.cbw40_enable = 0; padapter->registrypriv.ampdu_enable = 0; } } } static const struct device_type wlan_type = { .name = "wlan", }; /* * drv_init() - a device potentially for us * * notes: drv_init() is called when the bus driver has located a card for us * to support. We accept the new device by returning 0. */ static int r871xu_drv_init(struct usb_interface *pusb_intf, const struct usb_device_id *pdid) { uint status; struct _adapter *padapter = NULL; struct dvobj_priv *pdvobjpriv; struct net_device *pnetdev; struct usb_device *udev; /* In this probe function, O.S. will provide the usb interface pointer * to driver. We have to increase the reference count of the usb device * structure by using the usb_get_dev function. */ udev = interface_to_usbdev(pusb_intf); usb_get_dev(udev); pintf = pusb_intf; /* step 1. */ pnetdev = r8712_init_netdev(); if (!pnetdev) goto put_dev; padapter = netdev_priv(pnetdev); disable_ht_for_spec_devid(pdid, padapter); pdvobjpriv = &padapter->dvobjpriv; pdvobjpriv->padapter = padapter; padapter->dvobjpriv.pusbdev = udev; padapter->pusb_intf = pusb_intf; usb_set_intfdata(pusb_intf, pnetdev); SET_NETDEV_DEV(pnetdev, &pusb_intf->dev); pnetdev->dev.type = &wlan_type; /* step 2. */ padapter->dvobj_init = r8712_usb_dvobj_init; padapter->dvobj_deinit = r8712_usb_dvobj_deinit; padapter->halpriv.hal_bus_init = r8712_usb_hal_bus_init; padapter->dvobjpriv.inirp_init = r8712_usb_inirp_init; padapter->dvobjpriv.inirp_deinit = r8712_usb_inirp_deinit; /* step 3. * initialize the dvobj_priv */ status = padapter->dvobj_init(padapter); if (status != _SUCCESS) goto free_netdev; /* step 4. */ status = r8712_init_drv_sw(padapter); if (status) goto dvobj_deinit; /* step 5. read efuse/eeprom data and get mac_addr */ { int i, offset; u8 mac[6]; u8 tmpU1b, AutoloadFail, eeprom_CustomerID; u8 *pdata = padapter->eeprompriv.efuse_eeprom_data; tmpU1b = r8712_read8(padapter, EE_9346CR);/*CR9346*/ /* To check system boot selection.*/ dev_info(&udev->dev, "r8712u: Boot from %s: Autoload %s\n", (tmpU1b & _9356SEL) ? "EEPROM" : "EFUSE", (tmpU1b & _EEPROM_EN) ? "OK" : "Failed"); /* To check autoload success or not.*/ if (tmpU1b & _EEPROM_EN) { AutoloadFail = true; /* The following operations prevent Efuse leakage by * turning on 2.5V. */ tmpU1b = r8712_read8(padapter, EFUSE_TEST + 3); r8712_write8(padapter, EFUSE_TEST + 3, tmpU1b | 0x80); msleep(20); r8712_write8(padapter, EFUSE_TEST + 3, (tmpU1b & (~BIT(7)))); /* Retrieve Chip version. * Recognize IC version by Reg0x4 BIT15. */ tmpU1b = (u8)((r8712_read32(padapter, PMC_FSM) >> 15) & 0x1F); if (tmpU1b == 0x3) padapter->registrypriv.chip_version = RTL8712_3rdCUT; else padapter->registrypriv.chip_version = (tmpU1b >> 1) + 1; switch (padapter->registrypriv.chip_version) { case RTL8712_1stCUT: case RTL8712_2ndCUT: case RTL8712_3rdCUT: break; default: padapter->registrypriv.chip_version = RTL8712_2ndCUT; break; } for (i = 0, offset = 0; i < 128; i += 8, offset++) r8712_efuse_pg_packet_read(padapter, offset, &pdata[i]); if (!r8712_initmac || !mac_pton(r8712_initmac, mac)) { /* Use the mac address stored in the Efuse * offset = 0x12 for usb in efuse */ ether_addr_copy(mac, &pdata[0x12]); } eeprom_CustomerID = pdata[0x52]; switch (eeprom_CustomerID) { case EEPROM_CID_ALPHA: padapter->eeprompriv.CustomerID = RT_CID_819x_ALPHA; break; case EEPROM_CID_CAMEO: padapter->eeprompriv.CustomerID = RT_CID_819x_CAMEO; break; case EEPROM_CID_SITECOM: padapter->eeprompriv.CustomerID = RT_CID_819x_Sitecom; break; case EEPROM_CID_COREGA: padapter->eeprompriv.CustomerID = RT_CID_COREGA; break; case EEPROM_CID_Senao: padapter->eeprompriv.CustomerID = RT_CID_819x_Senao; break; case EEPROM_CID_EDIMAX_BELKIN: padapter->eeprompriv.CustomerID = RT_CID_819x_Edimax_Belkin; break; case EEPROM_CID_SERCOMM_BELKIN: padapter->eeprompriv.CustomerID = RT_CID_819x_Sercomm_Belkin; break; case EEPROM_CID_WNC_COREGA: padapter->eeprompriv.CustomerID = RT_CID_819x_WNC_COREGA; break; case EEPROM_CID_WHQL: break; case EEPROM_CID_NetCore: padapter->eeprompriv.CustomerID = RT_CID_819x_Netcore; break; case EEPROM_CID_CAMEO1: padapter->eeprompriv.CustomerID = RT_CID_819x_CAMEO1; break; case EEPROM_CID_CLEVO: padapter->eeprompriv.CustomerID = RT_CID_819x_CLEVO; break; default: padapter->eeprompriv.CustomerID = RT_CID_DEFAULT; break; } dev_info(&udev->dev, "r8712u: CustomerID = 0x%.4x\n", padapter->eeprompriv.CustomerID); /* Led mode */ switch (padapter->eeprompriv.CustomerID) { case RT_CID_DEFAULT: case RT_CID_819x_ALPHA: case RT_CID_819x_CAMEO: padapter->ledpriv.LedStrategy = SW_LED_MODE1; padapter->ledpriv.bRegUseLed = true; break; case RT_CID_819x_Sitecom: padapter->ledpriv.LedStrategy = SW_LED_MODE2; padapter->ledpriv.bRegUseLed = true; break; case RT_CID_COREGA: case RT_CID_819x_Senao: padapter->ledpriv.LedStrategy = SW_LED_MODE3; padapter->ledpriv.bRegUseLed = true; break; case RT_CID_819x_Edimax_Belkin: padapter->ledpriv.LedStrategy = SW_LED_MODE4; padapter->ledpriv.bRegUseLed = true; break; case RT_CID_819x_Sercomm_Belkin: padapter->ledpriv.LedStrategy = SW_LED_MODE5; padapter->ledpriv.bRegUseLed = true; break; case RT_CID_819x_WNC_COREGA: padapter->ledpriv.LedStrategy = SW_LED_MODE6; padapter->ledpriv.bRegUseLed = true; break; default: padapter->ledpriv.LedStrategy = SW_LED_MODE0; padapter->ledpriv.bRegUseLed = false; break; } } else { AutoloadFail = false; } if ((!AutoloadFail) || ((mac[0] == 0xff) && (mac[1] == 0xff) && (mac[2] == 0xff) && (mac[3] == 0xff) && (mac[4] == 0xff) && (mac[5] == 0xff)) || ((mac[0] == 0x00) && (mac[1] == 0x00) && (mac[2] == 0x00) && (mac[3] == 0x00) && (mac[4] == 0x00) && (mac[5] == 0x00))) { mac[0] = 0x00; mac[1] = 0xe0; mac[2] = 0x4c; mac[3] = 0x87; mac[4] = 0x00; mac[5] = 0x00; } if (r8712_initmac) { /* Make sure the user did not select a multicast * address by setting bit 1 of first octet. */ mac[0] &= 0xFE; dev_info(&udev->dev, "r8712u: MAC Address from user = %pM\n", mac); } else { dev_info(&udev->dev, "r8712u: MAC Address from efuse = %pM\n", mac); } eth_hw_addr_set(pnetdev, mac); } /* step 6. Load the firmware asynchronously */ if (rtl871x_load_fw(padapter)) goto deinit_drv_sw; init_completion(&padapter->rx_filter_ready); return 0; deinit_drv_sw: r8712_free_drv_sw(padapter); dvobj_deinit: padapter->dvobj_deinit(padapter); free_netdev: free_netdev(pnetdev); put_dev: usb_put_dev(udev); usb_set_intfdata(pusb_intf, NULL); return -ENODEV; } /* rmmod module & unplug(SurpriseRemoved) will call r871xu_dev_remove() * => how to recognize both */ static void r871xu_dev_remove(struct usb_interface *pusb_intf) { struct net_device *pnetdev = usb_get_intfdata(pusb_intf); struct usb_device *udev = interface_to_usbdev(pusb_intf); struct _adapter *padapter = netdev_priv(pnetdev); /* never exit with a firmware callback pending */ wait_for_completion(&padapter->rtl8712_fw_ready); if (pnetdev->reg_state != NETREG_UNINITIALIZED) unregister_netdev(pnetdev); /* will call netdev_close() */ usb_set_intfdata(pusb_intf, NULL); release_firmware(padapter->fw); if (drvpriv.drv_registered) padapter->surprise_removed = true; r8712_flush_rwctrl_works(padapter); r8712_flush_led_works(padapter); udelay(1); /* Stop driver mlme relation timer */ r8712_stop_drv_timers(padapter); r871x_dev_unload(padapter); if (padapter->dvobj_deinit) padapter->dvobj_deinit(padapter); r8712_free_drv_sw(padapter); free_netdev(pnetdev); /* decrease the reference count of the usb device structure * when disconnect */ usb_put_dev(udev); /* If we didn't unplug usb dongle and remove/insert module, driver * fails on sitesurvey for the first time when device is up. * Reset usb port for sitesurvey fail issue. */ if (udev->state != USB_STATE_NOTATTACHED) usb_reset_device(udev); } static int __init r8712u_drv_entry(void) { drvpriv.drv_registered = true; return usb_register(&drvpriv.r871xu_drv); } static void __exit r8712u_drv_halt(void) { drvpriv.drv_registered = false; usb_deregister(&drvpriv.r871xu_drv); } module_init(r8712u_drv_entry); module_exit(r8712u_drv_halt); |
| 367 141 369 369 369 37 38 38 38 146 146 138 11 8 9 121 103 48 142 141 142 142 142 10 10 10 141 8 1 7 7 7 29 6 165 1 154 6 152 152 150 3 1 1 376 150 366 366 4 3 39 38 122 3 10 131 126 6 1 121 107 107 23 23 2 22 26 26 2 25 12 12 382 65 34 376 3 374 7 375 17 15 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/bnode.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handle basic btree node operations */ #include <linux/string.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/fs.h> #include <linux/swap.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" /* Copy a specified range of bytes from the raw data of a node */ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { struct page **pagep; int l; off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); off &= ~PAGE_MASK; l = min_t(int, len, PAGE_SIZE - off); memcpy_from_page(buf, *pagep, off, l); while ((len -= l) != 0) { buf += l; l = min_t(int, len, PAGE_SIZE); memcpy_from_page(buf, *++pagep, 0, l); } } u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off) { __be16 data; /* TODO: optimize later... */ hfs_bnode_read(node, &data, off, 2); return be16_to_cpu(data); } u8 hfs_bnode_read_u8(struct hfs_bnode *node, int off) { u8 data; /* TODO: optimize later... */ hfs_bnode_read(node, &data, off, 1); return data; } void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off) { struct hfs_btree *tree; int key_len; tree = node->tree; if (node->type == HFS_NODE_LEAF || tree->attributes & HFS_TREE_VARIDXKEYS || node->tree->cnid == HFSPLUS_ATTR_CNID) key_len = hfs_bnode_read_u16(node, off) + 2; else key_len = tree->max_key_len + 2; hfs_bnode_read(node, key, off, key_len); } void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len) { struct page **pagep; int l; off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); off &= ~PAGE_MASK; l = min_t(int, len, PAGE_SIZE - off); memcpy_to_page(*pagep, off, buf, l); set_page_dirty(*pagep); while ((len -= l) != 0) { buf += l; l = min_t(int, len, PAGE_SIZE); memcpy_to_page(*++pagep, 0, buf, l); set_page_dirty(*pagep); } } void hfs_bnode_write_u16(struct hfs_bnode *node, int off, u16 data) { __be16 v = cpu_to_be16(data); /* TODO: optimize later... */ hfs_bnode_write(node, &v, off, 2); } void hfs_bnode_clear(struct hfs_bnode *node, int off, int len) { struct page **pagep; int l; off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); off &= ~PAGE_MASK; l = min_t(int, len, PAGE_SIZE - off); memzero_page(*pagep, off, l); set_page_dirty(*pagep); while ((len -= l) != 0) { l = min_t(int, len, PAGE_SIZE); memzero_page(*++pagep, 0, l); set_page_dirty(*pagep); } } void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst, struct hfs_bnode *src_node, int src, int len) { struct page **src_page, **dst_page; int l; hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); if (!len) return; src += src_node->page_offset; dst += dst_node->page_offset; src_page = src_node->page + (src >> PAGE_SHIFT); src &= ~PAGE_MASK; dst_page = dst_node->page + (dst >> PAGE_SHIFT); dst &= ~PAGE_MASK; if (src == dst) { l = min_t(int, len, PAGE_SIZE - src); memcpy_page(*dst_page, src, *src_page, src, l); set_page_dirty(*dst_page); while ((len -= l) != 0) { l = min_t(int, len, PAGE_SIZE); memcpy_page(*++dst_page, 0, *++src_page, 0, l); set_page_dirty(*dst_page); } } else { void *src_ptr, *dst_ptr; do { dst_ptr = kmap_local_page(*dst_page) + dst; src_ptr = kmap_local_page(*src_page) + src; if (PAGE_SIZE - src < PAGE_SIZE - dst) { l = PAGE_SIZE - src; src = 0; dst += l; } else { l = PAGE_SIZE - dst; src += l; dst = 0; } l = min(len, l); memcpy(dst_ptr, src_ptr, l); kunmap_local(src_ptr); set_page_dirty(*dst_page); kunmap_local(dst_ptr); if (!dst) dst_page++; else src_page++; } while ((len -= l)); } } void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) { struct page **src_page, **dst_page; void *src_ptr, *dst_ptr; int l; hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); if (!len) return; src += node->page_offset; dst += node->page_offset; if (dst > src) { src += len - 1; src_page = node->page + (src >> PAGE_SHIFT); src = (src & ~PAGE_MASK) + 1; dst += len - 1; dst_page = node->page + (dst >> PAGE_SHIFT); dst = (dst & ~PAGE_MASK) + 1; if (src == dst) { while (src < len) { dst_ptr = kmap_local_page(*dst_page); src_ptr = kmap_local_page(*src_page); memmove(dst_ptr, src_ptr, src); kunmap_local(src_ptr); set_page_dirty(*dst_page); kunmap_local(dst_ptr); len -= src; src = PAGE_SIZE; src_page--; dst_page--; } src -= len; dst_ptr = kmap_local_page(*dst_page); src_ptr = kmap_local_page(*src_page); memmove(dst_ptr + src, src_ptr + src, len); kunmap_local(src_ptr); set_page_dirty(*dst_page); kunmap_local(dst_ptr); } else { do { dst_ptr = kmap_local_page(*dst_page) + dst; src_ptr = kmap_local_page(*src_page) + src; if (src < dst) { l = src; src = PAGE_SIZE; dst -= l; } else { l = dst; src -= l; dst = PAGE_SIZE; } l = min(len, l); memmove(dst_ptr - l, src_ptr - l, l); kunmap_local(src_ptr); set_page_dirty(*dst_page); kunmap_local(dst_ptr); if (dst == PAGE_SIZE) dst_page--; else src_page--; } while ((len -= l)); } } else { src_page = node->page + (src >> PAGE_SHIFT); src &= ~PAGE_MASK; dst_page = node->page + (dst >> PAGE_SHIFT); dst &= ~PAGE_MASK; if (src == dst) { l = min_t(int, len, PAGE_SIZE - src); dst_ptr = kmap_local_page(*dst_page) + src; src_ptr = kmap_local_page(*src_page) + src; memmove(dst_ptr, src_ptr, l); kunmap_local(src_ptr); set_page_dirty(*dst_page); kunmap_local(dst_ptr); while ((len -= l) != 0) { l = min_t(int, len, PAGE_SIZE); dst_ptr = kmap_local_page(*++dst_page); src_ptr = kmap_local_page(*++src_page); memmove(dst_ptr, src_ptr, l); kunmap_local(src_ptr); set_page_dirty(*dst_page); kunmap_local(dst_ptr); } } else { do { dst_ptr = kmap_local_page(*dst_page) + dst; src_ptr = kmap_local_page(*src_page) + src; if (PAGE_SIZE - src < PAGE_SIZE - dst) { l = PAGE_SIZE - src; src = 0; dst += l; } else { l = PAGE_SIZE - dst; src += l; dst = 0; } l = min(len, l); memmove(dst_ptr, src_ptr, l); kunmap_local(src_ptr); set_page_dirty(*dst_page); kunmap_local(dst_ptr); if (!dst) dst_page++; else src_page++; } while ((len -= l)); } } } void hfs_bnode_dump(struct hfs_bnode *node) { struct hfs_bnode_desc desc; __be32 cnid; int i, off, key_off; hfs_dbg(BNODE_MOD, "bnode: %d\n", node->this); hfs_bnode_read(node, &desc, 0, sizeof(desc)); hfs_dbg(BNODE_MOD, "%d, %d, %d, %d, %d\n", be32_to_cpu(desc.next), be32_to_cpu(desc.prev), desc.type, desc.height, be16_to_cpu(desc.num_recs)); off = node->tree->node_size - 2; for (i = be16_to_cpu(desc.num_recs); i >= 0; off -= 2, i--) { key_off = hfs_bnode_read_u16(node, off); hfs_dbg(BNODE_MOD, " %d", key_off); if (i && node->type == HFS_NODE_INDEX) { int tmp; if (node->tree->attributes & HFS_TREE_VARIDXKEYS || node->tree->cnid == HFSPLUS_ATTR_CNID) tmp = hfs_bnode_read_u16(node, key_off) + 2; else tmp = node->tree->max_key_len + 2; hfs_dbg_cont(BNODE_MOD, " (%d", tmp); hfs_bnode_read(node, &cnid, key_off + tmp, 4); hfs_dbg_cont(BNODE_MOD, ",%d)", be32_to_cpu(cnid)); } else if (i && node->type == HFS_NODE_LEAF) { int tmp; tmp = hfs_bnode_read_u16(node, key_off); hfs_dbg_cont(BNODE_MOD, " (%d)", tmp); } } hfs_dbg_cont(BNODE_MOD, "\n"); } void hfs_bnode_unlink(struct hfs_bnode *node) { struct hfs_btree *tree; struct hfs_bnode *tmp; __be32 cnid; tree = node->tree; if (node->prev) { tmp = hfs_bnode_find(tree, node->prev); if (IS_ERR(tmp)) return; tmp->next = node->next; cnid = cpu_to_be32(tmp->next); hfs_bnode_write(tmp, &cnid, offsetof(struct hfs_bnode_desc, next), 4); hfs_bnode_put(tmp); } else if (node->type == HFS_NODE_LEAF) tree->leaf_head = node->next; if (node->next) { tmp = hfs_bnode_find(tree, node->next); if (IS_ERR(tmp)) return; tmp->prev = node->prev; cnid = cpu_to_be32(tmp->prev); hfs_bnode_write(tmp, &cnid, offsetof(struct hfs_bnode_desc, prev), 4); hfs_bnode_put(tmp); } else if (node->type == HFS_NODE_LEAF) tree->leaf_tail = node->prev; /* move down? */ if (!node->prev && !node->next) hfs_dbg(BNODE_MOD, "hfs_btree_del_level\n"); if (!node->parent) { tree->root = 0; tree->depth = 0; } set_bit(HFS_BNODE_DELETED, &node->flags); } static inline int hfs_bnode_hash(u32 num) { num = (num >> 16) + num; num += num >> 8; return num & (NODE_HASH_SIZE - 1); } struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid) { struct hfs_bnode *node; if (cnid >= tree->node_count) { pr_err("request for non-existent node %d in B*Tree\n", cnid); return NULL; } for (node = tree->node_hash[hfs_bnode_hash(cnid)]; node; node = node->next_hash) if (node->this == cnid) return node; return NULL; } static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) { struct hfs_bnode *node, *node2; struct address_space *mapping; struct page *page; int size, block, i, hash; loff_t off; if (cnid >= tree->node_count) { pr_err("request for non-existent node %d in B*Tree\n", cnid); return NULL; } size = sizeof(struct hfs_bnode) + tree->pages_per_bnode * sizeof(struct page *); node = kzalloc(size, GFP_KERNEL); if (!node) return NULL; node->tree = tree; node->this = cnid; set_bit(HFS_BNODE_NEW, &node->flags); atomic_set(&node->refcnt, 1); hfs_dbg(BNODE_REFS, "new_node(%d:%d): 1\n", node->tree->cnid, node->this); init_waitqueue_head(&node->lock_wq); spin_lock(&tree->hash_lock); node2 = hfs_bnode_findhash(tree, cnid); if (!node2) { hash = hfs_bnode_hash(cnid); node->next_hash = tree->node_hash[hash]; tree->node_hash[hash] = node; tree->node_hash_cnt++; } else { spin_unlock(&tree->hash_lock); kfree(node); wait_event(node2->lock_wq, !test_bit(HFS_BNODE_NEW, &node2->flags)); return node2; } spin_unlock(&tree->hash_lock); mapping = tree->inode->i_mapping; off = (loff_t)cnid << tree->node_size_shift; block = off >> PAGE_SHIFT; node->page_offset = off & ~PAGE_MASK; for (i = 0; i < tree->pages_per_bnode; block++, i++) { page = read_mapping_page(mapping, block, NULL); if (IS_ERR(page)) goto fail; node->page[i] = page; } return node; fail: set_bit(HFS_BNODE_ERROR, &node->flags); return node; } void hfs_bnode_unhash(struct hfs_bnode *node) { struct hfs_bnode **p; hfs_dbg(BNODE_REFS, "remove_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); for (p = &node->tree->node_hash[hfs_bnode_hash(node->this)]; *p && *p != node; p = &(*p)->next_hash) ; BUG_ON(!*p); *p = node->next_hash; node->tree->node_hash_cnt--; } /* Load a particular node out of a tree */ struct hfs_bnode *hfs_bnode_find(struct hfs_btree *tree, u32 num) { struct hfs_bnode *node; struct hfs_bnode_desc *desc; int i, rec_off, off, next_off; int entry_size, key_size; spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, num); if (node) { hfs_bnode_get(node); spin_unlock(&tree->hash_lock); wait_event(node->lock_wq, !test_bit(HFS_BNODE_NEW, &node->flags)); if (test_bit(HFS_BNODE_ERROR, &node->flags)) goto node_error; return node; } spin_unlock(&tree->hash_lock); node = __hfs_bnode_create(tree, num); if (!node) return ERR_PTR(-ENOMEM); if (test_bit(HFS_BNODE_ERROR, &node->flags)) goto node_error; if (!test_bit(HFS_BNODE_NEW, &node->flags)) return node; desc = (struct hfs_bnode_desc *)(kmap_local_page(node->page[0]) + node->page_offset); node->prev = be32_to_cpu(desc->prev); node->next = be32_to_cpu(desc->next); node->num_recs = be16_to_cpu(desc->num_recs); node->type = desc->type; node->height = desc->height; kunmap_local(desc); switch (node->type) { case HFS_NODE_HEADER: case HFS_NODE_MAP: if (node->height != 0) goto node_error; break; case HFS_NODE_LEAF: if (node->height != 1) goto node_error; break; case HFS_NODE_INDEX: if (node->height <= 1 || node->height > tree->depth) goto node_error; break; default: goto node_error; } rec_off = tree->node_size - 2; off = hfs_bnode_read_u16(node, rec_off); if (off != sizeof(struct hfs_bnode_desc)) goto node_error; for (i = 1; i <= node->num_recs; off = next_off, i++) { rec_off -= 2; next_off = hfs_bnode_read_u16(node, rec_off); if (next_off <= off || next_off > tree->node_size || next_off & 1) goto node_error; entry_size = next_off - off; if (node->type != HFS_NODE_INDEX && node->type != HFS_NODE_LEAF) continue; key_size = hfs_bnode_read_u16(node, off) + 2; if (key_size >= entry_size || key_size & 1) goto node_error; } clear_bit(HFS_BNODE_NEW, &node->flags); wake_up(&node->lock_wq); return node; node_error: set_bit(HFS_BNODE_ERROR, &node->flags); clear_bit(HFS_BNODE_NEW, &node->flags); wake_up(&node->lock_wq); hfs_bnode_put(node); return ERR_PTR(-EIO); } void hfs_bnode_free(struct hfs_bnode *node) { int i; for (i = 0; i < node->tree->pages_per_bnode; i++) if (node->page[i]) put_page(node->page[i]); kfree(node); } struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num) { struct hfs_bnode *node; struct page **pagep; int i; spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, num); spin_unlock(&tree->hash_lock); if (node) { pr_crit("new node %u already hashed?\n", num); WARN_ON(1); return node; } node = __hfs_bnode_create(tree, num); if (!node) return ERR_PTR(-ENOMEM); if (test_bit(HFS_BNODE_ERROR, &node->flags)) { hfs_bnode_put(node); return ERR_PTR(-EIO); } pagep = node->page; memzero_page(*pagep, node->page_offset, min_t(int, PAGE_SIZE, tree->node_size)); set_page_dirty(*pagep); for (i = 1; i < tree->pages_per_bnode; i++) { memzero_page(*++pagep, 0, PAGE_SIZE); set_page_dirty(*pagep); } clear_bit(HFS_BNODE_NEW, &node->flags); wake_up(&node->lock_wq); return node; } void hfs_bnode_get(struct hfs_bnode *node) { if (node) { atomic_inc(&node->refcnt); hfs_dbg(BNODE_REFS, "get_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); } } /* Dispose of resources used by a node */ void hfs_bnode_put(struct hfs_bnode *node) { if (node) { struct hfs_btree *tree = node->tree; int i; hfs_dbg(BNODE_REFS, "put_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); BUG_ON(!atomic_read(&node->refcnt)); if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock)) return; for (i = 0; i < tree->pages_per_bnode; i++) { if (!node->page[i]) continue; mark_page_accessed(node->page[i]); } if (test_bit(HFS_BNODE_DELETED, &node->flags)) { hfs_bnode_unhash(node); spin_unlock(&tree->hash_lock); if (hfs_bnode_need_zeroout(tree)) hfs_bnode_clear(node, 0, tree->node_size); hfs_bmap_free(node); hfs_bnode_free(node); return; } spin_unlock(&tree->hash_lock); } } /* * Unused nodes have to be zeroed if this is the catalog tree and * a corresponding flag in the volume header is set. */ bool hfs_bnode_need_zeroout(struct hfs_btree *tree) { struct super_block *sb = tree->inode->i_sb; struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); const u32 volume_attr = be32_to_cpu(sbi->s_vhdr->attributes); return tree->cnid == HFSPLUS_CAT_CNID && volume_attr & HFSPLUS_VOL_UNUSED_NODE_FIX; } |
| 8 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. */ #ifndef __INODE_DOT_H__ #define __INODE_DOT_H__ #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/mm.h> #include "util.h" bool gfs2_release_folio(struct folio *folio, gfp_t gfp_mask); ssize_t gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, size_t size); void gfs2_set_aops(struct inode *inode); static inline int gfs2_is_stuffed(const struct gfs2_inode *ip) { return !ip->i_height; } static inline int gfs2_is_jdata(const struct gfs2_inode *ip) { return ip->i_diskflags & GFS2_DIF_JDATA; } static inline bool gfs2_is_ordered(const struct gfs2_sbd *sdp) { return sdp->sd_args.ar_data == GFS2_DATA_ORDERED; } static inline bool gfs2_is_writeback(const struct gfs2_sbd *sdp) { return sdp->sd_args.ar_data == GFS2_DATA_WRITEBACK; } static inline int gfs2_is_dir(const struct gfs2_inode *ip) { return S_ISDIR(ip->i_inode.i_mode); } static inline void gfs2_set_inode_blocks(struct inode *inode, u64 blocks) { inode->i_blocks = blocks << (inode->i_blkbits - 9); } static inline u64 gfs2_get_inode_blocks(const struct inode *inode) { return inode->i_blocks >> (inode->i_blkbits - 9); } static inline void gfs2_add_inode_blocks(struct inode *inode, s64 change) { change <<= inode->i_blkbits - 9; gfs2_assert(GFS2_SB(inode), (change >= 0 || inode->i_blocks >= -change)); inode->i_blocks += change; } static inline int gfs2_check_inum(const struct gfs2_inode *ip, u64 no_addr, u64 no_formal_ino) { return ip->i_no_addr == no_addr && ip->i_no_formal_ino == no_formal_ino; } static inline void gfs2_inum_out(const struct gfs2_inode *ip, struct gfs2_dirent *dent) { dent->de_inum.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino); dent->de_inum.no_addr = cpu_to_be64(ip->i_no_addr); } static inline int gfs2_check_internal_file_size(struct inode *inode, u64 minsize, u64 maxsize) { u64 size = i_size_read(inode); if (size < minsize || size > maxsize) goto err; if (size & (BIT(inode->i_blkbits) - 1)) goto err; return 0; err: gfs2_consist_inode(GFS2_I(inode)); return -EIO; } struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, u64 no_addr, u64 no_formal_ino, unsigned int blktype); struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr, u64 no_formal_ino, unsigned int blktype); int gfs2_inode_refresh(struct gfs2_inode *ip); struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name, int is_root); int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask); struct inode *gfs2_lookup_meta(struct inode *dip, const char *name); void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf); int gfs2_open_common(struct inode *inode, struct file *file); loff_t gfs2_seek_data(struct file *file, loff_t offset); loff_t gfs2_seek_hole(struct file *file, loff_t offset); extern const struct file_operations gfs2_file_fops_nolock; extern const struct file_operations gfs2_dir_fops_nolock; int gfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa); int gfs2_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa); void gfs2_set_inode_flags(struct inode *inode); #ifdef CONFIG_GFS2_FS_LOCKING_DLM extern const struct file_operations gfs2_file_fops; extern const struct file_operations gfs2_dir_fops; static inline int gfs2_localflocks(const struct gfs2_sbd *sdp) { return sdp->sd_args.ar_localflocks; } #else /* Single node only */ #define gfs2_file_fops gfs2_file_fops_nolock #define gfs2_dir_fops gfs2_dir_fops_nolock static inline int gfs2_localflocks(const struct gfs2_sbd *sdp) { return 1; } #endif /* CONFIG_GFS2_FS_LOCKING_DLM */ #endif /* __INODE_DOT_H__ */ |
| 106 163 123 126 98 165 116 9 168 103 12 168 168 168 166 166 163 168 163 163 163 163 163 160 163 162 163 101 56 100 52 101 29 29 29 29 29 29 29 74 70 16 69 69 22 21 19 19 14 9 73 74 74 74 74 74 9 160 160 39 10 10 2 123 121 1 168 166 166 168 168 167 168 16 16 10 3 16 16 16 12 12 12 12 12 12 6 12 12 12 4 4 4 168 167 4 166 168 47 47 47 47 47 47 32 123 167 5 168 168 167 168 131 168 168 167 36 135 168 168 168 168 166 57 168 168 168 167 167 81 133 133 133 133 132 133 70 126 45 131 103 34 123 123 123 103 155 147 164 126 69 151 134 109 83 83 83 1 3 166 117 164 153 168 42 69 3 43 14 9 157 160 160 160 160 160 159 160 168 168 122 159 168 167 168 166 161 76 51 100 12 168 163 122 12 12 12 12 165 165 32 166 166 166 133 119 30 110 33 34 62 61 62 23 53 13 61 55 32 45 57 9 9 9 37 37 37 10 34 25 48 49 22 49 8 119 120 32 2 23 23 2 23 23 23 150 106 157 108 162 162 158 22 162 162 37 159 10 39 161 161 161 162 162 39 160 147 142 25 22 38 75 103 147 86 147 85 112 147 161 37 37 23 159 162 136 10 1 9 2 10 10 10 10 10 2 2 9 2 2 2 10 9 9 160 161 162 163 163 104 101 161 162 49 162 162 1 163 126 79 69 57 127 143 143 109 64 163 163 167 168 168 168 167 167 160 168 151 151 164 167 83 82 168 167 168 168 168 23 17 167 168 32 166 61 69 69 101 101 100 101 101 100 45 45 168 38 38 30 2 38 37 37 38 167 168 168 56 33 64 168 167 167 38 167 47 168 89 89 89 168 166 40 46 10 42 7 167 164 28 168 168 168 168 168 167 165 46 168 168 166 167 165 48 48 19 19 19 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "bkey_methods.h" #include "bkey_buf.h" #include "btree_cache.h" #include "btree_iter.h" #include "btree_journal_iter.h" #include "btree_key_cache.h" #include "btree_locking.h" #include "btree_update.h" #include "debug.h" #include "error.h" #include "extents.h" #include "journal.h" #include "journal_io.h" #include "replicas.h" #include "snapshot.h" #include "trace.h" #include <linux/random.h> #include <linux/prefetch.h> static inline void btree_path_list_remove(struct btree_trans *, struct btree_path *); static inline void btree_path_list_add(struct btree_trans *, btree_path_idx_t, btree_path_idx_t); static inline unsigned long btree_iter_ip_allocated(struct btree_iter *iter) { #ifdef TRACK_PATH_ALLOCATED return iter->ip_allocated; #else return 0; #endif } static btree_path_idx_t btree_path_alloc(struct btree_trans *, btree_path_idx_t); static void bch2_trans_srcu_lock(struct btree_trans *); static inline int __btree_path_cmp(const struct btree_path *l, enum btree_id r_btree_id, bool r_cached, struct bpos r_pos, unsigned r_level) { /* * Must match lock ordering as defined by __bch2_btree_node_lock: */ return cmp_int(l->btree_id, r_btree_id) ?: cmp_int((int) l->cached, (int) r_cached) ?: bpos_cmp(l->pos, r_pos) ?: -cmp_int(l->level, r_level); } static inline int btree_path_cmp(const struct btree_path *l, const struct btree_path *r) { return __btree_path_cmp(l, r->btree_id, r->cached, r->pos, r->level); } static inline struct bpos bkey_successor(struct btree_iter *iter, struct bpos p) { /* Are we iterating over keys in all snapshots? */ if (iter->flags & BTREE_ITER_all_snapshots) { p = bpos_successor(p); } else { p = bpos_nosnap_successor(p); p.snapshot = iter->snapshot; } return p; } static inline struct bpos bkey_predecessor(struct btree_iter *iter, struct bpos p) { /* Are we iterating over keys in all snapshots? */ if (iter->flags & BTREE_ITER_all_snapshots) { p = bpos_predecessor(p); } else { p = bpos_nosnap_predecessor(p); p.snapshot = iter->snapshot; } return p; } static inline struct bpos btree_iter_search_key(struct btree_iter *iter) { struct bpos pos = iter->pos; if ((iter->flags & BTREE_ITER_is_extents) && !bkey_eq(pos, POS_MAX)) pos = bkey_successor(iter, pos); return pos; } static inline bool btree_path_pos_before_node(struct btree_path *path, struct btree *b) { return bpos_lt(path->pos, b->data->min_key); } static inline bool btree_path_pos_after_node(struct btree_path *path, struct btree *b) { return bpos_gt(path->pos, b->key.k.p); } static inline bool btree_path_pos_in_node(struct btree_path *path, struct btree *b) { return path->btree_id == b->c.btree_id && !btree_path_pos_before_node(path, b) && !btree_path_pos_after_node(path, b); } /* Btree iterator: */ #ifdef CONFIG_BCACHEFS_DEBUG static void bch2_btree_path_verify_cached(struct btree_trans *trans, struct btree_path *path) { struct bkey_cached *ck; bool locked = btree_node_locked(path, 0); if (!bch2_btree_node_relock(trans, path, 0)) return; ck = (void *) path->l[0].b; BUG_ON(ck->key.btree_id != path->btree_id || !bkey_eq(ck->key.pos, path->pos)); if (!locked) btree_node_unlock(trans, path, 0); } static void bch2_btree_path_verify_level(struct btree_trans *trans, struct btree_path *path, unsigned level) { struct btree_path_level *l; struct btree_node_iter tmp; bool locked; struct bkey_packed *p, *k; struct printbuf buf1 = PRINTBUF; struct printbuf buf2 = PRINTBUF; struct printbuf buf3 = PRINTBUF; const char *msg; if (!bch2_debug_check_iterators) return; l = &path->l[level]; tmp = l->iter; locked = btree_node_locked(path, level); if (path->cached) { if (!level) bch2_btree_path_verify_cached(trans, path); return; } if (!btree_path_node(path, level)) return; if (!bch2_btree_node_relock_notrace(trans, path, level)) return; BUG_ON(!btree_path_pos_in_node(path, l->b)); bch2_btree_node_iter_verify(&l->iter, l->b); /* * For interior nodes, the iterator will have skipped past deleted keys: */ p = level ? bch2_btree_node_iter_prev(&tmp, l->b) : bch2_btree_node_iter_prev_all(&tmp, l->b); k = bch2_btree_node_iter_peek_all(&l->iter, l->b); if (p && bkey_iter_pos_cmp(l->b, p, &path->pos) >= 0) { msg = "before"; goto err; } if (k && bkey_iter_pos_cmp(l->b, k, &path->pos) < 0) { msg = "after"; goto err; } if (!locked) btree_node_unlock(trans, path, level); return; err: bch2_bpos_to_text(&buf1, path->pos); if (p) { struct bkey uk = bkey_unpack_key(l->b, p); bch2_bkey_to_text(&buf2, &uk); } else { prt_printf(&buf2, "(none)"); } if (k) { struct bkey uk = bkey_unpack_key(l->b, k); bch2_bkey_to_text(&buf3, &uk); } else { prt_printf(&buf3, "(none)"); } panic("path should be %s key at level %u:\n" "path pos %s\n" "prev key %s\n" "cur key %s\n", msg, level, buf1.buf, buf2.buf, buf3.buf); } static void bch2_btree_path_verify(struct btree_trans *trans, struct btree_path *path) { struct bch_fs *c = trans->c; unsigned i; EBUG_ON(path->btree_id >= BTREE_ID_NR); for (i = 0; i < (!path->cached ? BTREE_MAX_DEPTH : 1); i++) { if (!path->l[i].b) { BUG_ON(!path->cached && bch2_btree_id_root(c, path->btree_id)->b->c.level > i); break; } bch2_btree_path_verify_level(trans, path, i); } bch2_btree_path_verify_locks(path); } void bch2_trans_verify_paths(struct btree_trans *trans) { struct btree_path *path; unsigned iter; trans_for_each_path(trans, path, iter) bch2_btree_path_verify(trans, path); } static void bch2_btree_iter_verify(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; BUG_ON(iter->btree_id >= BTREE_ID_NR); BUG_ON(!!(iter->flags & BTREE_ITER_cached) != btree_iter_path(trans, iter)->cached); BUG_ON((iter->flags & BTREE_ITER_is_extents) && (iter->flags & BTREE_ITER_all_snapshots)); BUG_ON(!(iter->flags & BTREE_ITER_snapshot_field) && (iter->flags & BTREE_ITER_all_snapshots) && !btree_type_has_snapshot_field(iter->btree_id)); if (iter->update_path) bch2_btree_path_verify(trans, &trans->paths[iter->update_path]); bch2_btree_path_verify(trans, btree_iter_path(trans, iter)); } static void bch2_btree_iter_verify_entry_exit(struct btree_iter *iter) { BUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && !iter->pos.snapshot); BUG_ON(!(iter->flags & BTREE_ITER_all_snapshots) && iter->pos.snapshot != iter->snapshot); BUG_ON(bkey_lt(iter->pos, bkey_start_pos(&iter->k)) || bkey_gt(iter->pos, iter->k.p)); } static int bch2_btree_iter_verify_ret(struct btree_iter *iter, struct bkey_s_c k) { struct btree_trans *trans = iter->trans; struct btree_iter copy; struct bkey_s_c prev; int ret = 0; if (!bch2_debug_check_iterators) return 0; if (!(iter->flags & BTREE_ITER_filter_snapshots)) return 0; if (bkey_err(k) || !k.k) return 0; BUG_ON(!bch2_snapshot_is_ancestor(trans->c, iter->snapshot, k.k->p.snapshot)); bch2_trans_iter_init(trans, ©, iter->btree_id, iter->pos, BTREE_ITER_nopreserve| BTREE_ITER_all_snapshots); prev = bch2_btree_iter_prev(©); if (!prev.k) goto out; ret = bkey_err(prev); if (ret) goto out; if (bkey_eq(prev.k->p, k.k->p) && bch2_snapshot_is_ancestor(trans->c, iter->snapshot, prev.k->p.snapshot) > 0) { struct printbuf buf1 = PRINTBUF, buf2 = PRINTBUF; bch2_bkey_to_text(&buf1, k.k); bch2_bkey_to_text(&buf2, prev.k); panic("iter snap %u\n" "k %s\n" "prev %s\n", iter->snapshot, buf1.buf, buf2.buf); } out: bch2_trans_iter_exit(trans, ©); return ret; } void bch2_assert_pos_locked(struct btree_trans *trans, enum btree_id id, struct bpos pos, bool key_cache) { struct btree_path *path; struct trans_for_each_path_inorder_iter iter; struct printbuf buf = PRINTBUF; btree_trans_sort_paths(trans); trans_for_each_path_inorder(trans, path, iter) { int cmp = cmp_int(path->btree_id, id) ?: cmp_int(path->cached, key_cache); if (cmp > 0) break; if (cmp < 0) continue; if (!btree_node_locked(path, 0) || !path->should_be_locked) continue; if (!key_cache) { if (bkey_ge(pos, path->l[0].b->data->min_key) && bkey_le(pos, path->l[0].b->key.k.p)) return; } else { if (bkey_eq(pos, path->pos)) return; } } bch2_dump_trans_paths_updates(trans); bch2_bpos_to_text(&buf, pos); panic("not locked: %s %s%s\n", bch2_btree_id_str(id), buf.buf, key_cache ? " cached" : ""); } #else static inline void bch2_btree_path_verify_level(struct btree_trans *trans, struct btree_path *path, unsigned l) {} static inline void bch2_btree_path_verify(struct btree_trans *trans, struct btree_path *path) {} static inline void bch2_btree_iter_verify(struct btree_iter *iter) {} static inline void bch2_btree_iter_verify_entry_exit(struct btree_iter *iter) {} static inline int bch2_btree_iter_verify_ret(struct btree_iter *iter, struct bkey_s_c k) { return 0; } #endif /* Btree path: fixups after btree updates */ static void btree_node_iter_set_set_pos(struct btree_node_iter *iter, struct btree *b, struct bset_tree *t, struct bkey_packed *k) { struct btree_node_iter_set *set; btree_node_iter_for_each(iter, set) if (set->end == t->end_offset) { set->k = __btree_node_key_to_offset(b, k); bch2_btree_node_iter_sort(iter, b); return; } bch2_btree_node_iter_push(iter, b, k, btree_bkey_last(b, t)); } static void __bch2_btree_path_fix_key_modified(struct btree_path *path, struct btree *b, struct bkey_packed *where) { struct btree_path_level *l = &path->l[b->c.level]; if (where != bch2_btree_node_iter_peek_all(&l->iter, l->b)) return; if (bkey_iter_pos_cmp(l->b, where, &path->pos) < 0) bch2_btree_node_iter_advance(&l->iter, l->b); } void bch2_btree_path_fix_key_modified(struct btree_trans *trans, struct btree *b, struct bkey_packed *where) { struct btree_path *path; unsigned i; trans_for_each_path_with_node(trans, b, path, i) { __bch2_btree_path_fix_key_modified(path, b, where); bch2_btree_path_verify_level(trans, path, b->c.level); } } static void __bch2_btree_node_iter_fix(struct btree_path *path, struct btree *b, struct btree_node_iter *node_iter, struct bset_tree *t, struct bkey_packed *where, unsigned clobber_u64s, unsigned new_u64s) { const struct bkey_packed *end = btree_bkey_last(b, t); struct btree_node_iter_set *set; unsigned offset = __btree_node_key_to_offset(b, where); int shift = new_u64s - clobber_u64s; unsigned old_end = t->end_offset - shift; unsigned orig_iter_pos = node_iter->data[0].k; bool iter_current_key_modified = orig_iter_pos >= offset && orig_iter_pos <= offset + clobber_u64s; btree_node_iter_for_each(node_iter, set) if (set->end == old_end) goto found; /* didn't find the bset in the iterator - might have to readd it: */ if (new_u64s && bkey_iter_pos_cmp(b, where, &path->pos) >= 0) { bch2_btree_node_iter_push(node_iter, b, where, end); goto fixup_done; } else { /* Iterator is after key that changed */ return; } found: set->end = t->end_offset; /* Iterator hasn't gotten to the key that changed yet: */ if (set->k < offset) return; if (new_u64s && bkey_iter_pos_cmp(b, where, &path->pos) >= 0) { set->k = offset; } else if (set->k < offset + clobber_u64s) { set->k = offset + new_u64s; if (set->k == set->end) bch2_btree_node_iter_set_drop(node_iter, set); } else { /* Iterator is after key that changed */ set->k = (int) set->k + shift; return; } bch2_btree_node_iter_sort(node_iter, b); fixup_done: if (node_iter->data[0].k != orig_iter_pos) iter_current_key_modified = true; /* * When a new key is added, and the node iterator now points to that * key, the iterator might have skipped past deleted keys that should * come after the key the iterator now points to. We have to rewind to * before those deleted keys - otherwise * bch2_btree_node_iter_prev_all() breaks: */ if (!bch2_btree_node_iter_end(node_iter) && iter_current_key_modified && b->c.level) { struct bkey_packed *k, *k2, *p; k = bch2_btree_node_iter_peek_all(node_iter, b); for_each_bset(b, t) { bool set_pos = false; if (node_iter->data[0].end == t->end_offset) continue; k2 = bch2_btree_node_iter_bset_pos(node_iter, b, t); while ((p = bch2_bkey_prev_all(b, t, k2)) && bkey_iter_cmp(b, k, p) < 0) { k2 = p; set_pos = true; } if (set_pos) btree_node_iter_set_set_pos(node_iter, b, t, k2); } } } void bch2_btree_node_iter_fix(struct btree_trans *trans, struct btree_path *path, struct btree *b, struct btree_node_iter *node_iter, struct bkey_packed *where, unsigned clobber_u64s, unsigned new_u64s) { struct bset_tree *t = bch2_bkey_to_bset_inlined(b, where); struct btree_path *linked; unsigned i; if (node_iter != &path->l[b->c.level].iter) { __bch2_btree_node_iter_fix(path, b, node_iter, t, where, clobber_u64s, new_u64s); if (bch2_debug_check_iterators) bch2_btree_node_iter_verify(node_iter, b); } trans_for_each_path_with_node(trans, b, linked, i) { __bch2_btree_node_iter_fix(linked, b, &linked->l[b->c.level].iter, t, where, clobber_u64s, new_u64s); bch2_btree_path_verify_level(trans, linked, b->c.level); } } /* Btree path level: pointer to a particular btree node and node iter */ static inline struct bkey_s_c __btree_iter_unpack(struct bch_fs *c, struct btree_path_level *l, struct bkey *u, struct bkey_packed *k) { if (unlikely(!k)) { /* * signal to bch2_btree_iter_peek_slot() that we're currently at * a hole */ u->type = KEY_TYPE_deleted; return bkey_s_c_null; } return bkey_disassemble(l->b, k, u); } static inline struct bkey_s_c btree_path_level_peek_all(struct bch_fs *c, struct btree_path_level *l, struct bkey *u) { return __btree_iter_unpack(c, l, u, bch2_btree_node_iter_peek_all(&l->iter, l->b)); } static inline struct bkey_s_c btree_path_level_peek(struct btree_trans *trans, struct btree_path *path, struct btree_path_level *l, struct bkey *u) { struct bkey_s_c k = __btree_iter_unpack(trans->c, l, u, bch2_btree_node_iter_peek(&l->iter, l->b)); path->pos = k.k ? k.k->p : l->b->key.k.p; trans->paths_sorted = false; bch2_btree_path_verify_level(trans, path, l - path->l); return k; } static inline struct bkey_s_c btree_path_level_prev(struct btree_trans *trans, struct btree_path *path, struct btree_path_level *l, struct bkey *u) { struct bkey_s_c k = __btree_iter_unpack(trans->c, l, u, bch2_btree_node_iter_prev(&l->iter, l->b)); path->pos = k.k ? k.k->p : l->b->data->min_key; trans->paths_sorted = false; bch2_btree_path_verify_level(trans, path, l - path->l); return k; } static inline bool btree_path_advance_to_pos(struct btree_path *path, struct btree_path_level *l, int max_advance) { struct bkey_packed *k; int nr_advanced = 0; while ((k = bch2_btree_node_iter_peek_all(&l->iter, l->b)) && bkey_iter_pos_cmp(l->b, k, &path->pos) < 0) { if (max_advance > 0 && nr_advanced >= max_advance) return false; bch2_btree_node_iter_advance(&l->iter, l->b); nr_advanced++; } return true; } static inline void __btree_path_level_init(struct btree_path *path, unsigned level) { struct btree_path_level *l = &path->l[level]; bch2_btree_node_iter_init(&l->iter, l->b, &path->pos); /* * Iterators to interior nodes should always be pointed at the first non * whiteout: */ if (level) bch2_btree_node_iter_peek(&l->iter, l->b); } void bch2_btree_path_level_init(struct btree_trans *trans, struct btree_path *path, struct btree *b) { BUG_ON(path->cached); EBUG_ON(!btree_path_pos_in_node(path, b)); path->l[b->c.level].lock_seq = six_lock_seq(&b->c.lock); path->l[b->c.level].b = b; __btree_path_level_init(path, b->c.level); } /* Btree path: fixups after btree node updates: */ static void bch2_trans_revalidate_updates_in_node(struct btree_trans *trans, struct btree *b) { struct bch_fs *c = trans->c; trans_for_each_update(trans, i) if (!i->cached && i->level == b->c.level && i->btree_id == b->c.btree_id && bpos_cmp(i->k->k.p, b->data->min_key) >= 0 && bpos_cmp(i->k->k.p, b->data->max_key) <= 0) { i->old_v = bch2_btree_path_peek_slot(trans->paths + i->path, &i->old_k).v; if (unlikely(trans->journal_replay_not_finished)) { struct bkey_i *j_k = bch2_journal_keys_peek_slot(c, i->btree_id, i->level, i->k->k.p); if (j_k) { i->old_k = j_k->k; i->old_v = &j_k->v; } } } } /* * A btree node is being replaced - update the iterator to point to the new * node: */ void bch2_trans_node_add(struct btree_trans *trans, struct btree_path *path, struct btree *b) { struct btree_path *prev; BUG_ON(!btree_path_pos_in_node(path, b)); while ((prev = prev_btree_path(trans, path)) && btree_path_pos_in_node(prev, b)) path = prev; for (; path && btree_path_pos_in_node(path, b); path = next_btree_path(trans, path)) if (path->uptodate == BTREE_ITER_UPTODATE && !path->cached) { enum btree_node_locked_type t = btree_lock_want(path, b->c.level); if (t != BTREE_NODE_UNLOCKED) { btree_node_unlock(trans, path, b->c.level); six_lock_increment(&b->c.lock, (enum six_lock_type) t); mark_btree_node_locked(trans, path, b->c.level, t); } bch2_btree_path_level_init(trans, path, b); } bch2_trans_revalidate_updates_in_node(trans, b); } /* * A btree node has been modified in such a way as to invalidate iterators - fix * them: */ void bch2_trans_node_reinit_iter(struct btree_trans *trans, struct btree *b) { struct btree_path *path; unsigned i; trans_for_each_path_with_node(trans, b, path, i) __btree_path_level_init(path, b->c.level); bch2_trans_revalidate_updates_in_node(trans, b); } /* Btree path: traverse, set_pos: */ static inline int btree_path_lock_root(struct btree_trans *trans, struct btree_path *path, unsigned depth_want, unsigned long trace_ip) { struct bch_fs *c = trans->c; struct btree *b, **rootp = &bch2_btree_id_root(c, path->btree_id)->b; enum six_lock_type lock_type; unsigned i; int ret; EBUG_ON(path->nodes_locked); while (1) { b = READ_ONCE(*rootp); path->level = READ_ONCE(b->c.level); if (unlikely(path->level < depth_want)) { /* * the root is at a lower depth than the depth we want: * got to the end of the btree, or we're walking nodes * greater than some depth and there are no nodes >= * that depth */ path->level = depth_want; for (i = path->level; i < BTREE_MAX_DEPTH; i++) path->l[i].b = NULL; return 1; } lock_type = __btree_lock_want(path, path->level); ret = btree_node_lock(trans, path, &b->c, path->level, lock_type, trace_ip); if (unlikely(ret)) { if (bch2_err_matches(ret, BCH_ERR_lock_fail_root_changed)) continue; if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) return ret; BUG(); } if (likely(b == READ_ONCE(*rootp) && b->c.level == path->level && !race_fault())) { for (i = 0; i < path->level; i++) path->l[i].b = ERR_PTR(-BCH_ERR_no_btree_node_lock_root); path->l[path->level].b = b; for (i = path->level + 1; i < BTREE_MAX_DEPTH; i++) path->l[i].b = NULL; mark_btree_node_locked(trans, path, path->level, (enum btree_node_locked_type) lock_type); bch2_btree_path_level_init(trans, path, b); return 0; } six_unlock_type(&b->c.lock, lock_type); } } noinline static int btree_path_prefetch(struct btree_trans *trans, struct btree_path *path) { struct bch_fs *c = trans->c; struct btree_path_level *l = path_l(path); struct btree_node_iter node_iter = l->iter; struct bkey_packed *k; struct bkey_buf tmp; unsigned nr = test_bit(BCH_FS_started, &c->flags) ? (path->level > 1 ? 0 : 2) : (path->level > 1 ? 1 : 16); bool was_locked = btree_node_locked(path, path->level); int ret = 0; bch2_bkey_buf_init(&tmp); while (nr-- && !ret) { if (!bch2_btree_node_relock(trans, path, path->level)) break; bch2_btree_node_iter_advance(&node_iter, l->b); k = bch2_btree_node_iter_peek(&node_iter, l->b); if (!k) break; bch2_bkey_buf_unpack(&tmp, c, l->b, k); ret = bch2_btree_node_prefetch(trans, path, tmp.k, path->btree_id, path->level - 1); } if (!was_locked) btree_node_unlock(trans, path, path->level); bch2_bkey_buf_exit(&tmp, c); return ret; } static int btree_path_prefetch_j(struct btree_trans *trans, struct btree_path *path, struct btree_and_journal_iter *jiter) { struct bch_fs *c = trans->c; struct bkey_s_c k; struct bkey_buf tmp; unsigned nr = test_bit(BCH_FS_started, &c->flags) ? (path->level > 1 ? 0 : 2) : (path->level > 1 ? 1 : 16); bool was_locked = btree_node_locked(path, path->level); int ret = 0; bch2_bkey_buf_init(&tmp); while (nr-- && !ret) { if (!bch2_btree_node_relock(trans, path, path->level)) break; bch2_btree_and_journal_iter_advance(jiter); k = bch2_btree_and_journal_iter_peek(jiter); if (!k.k) break; bch2_bkey_buf_reassemble(&tmp, c, k); ret = bch2_btree_node_prefetch(trans, path, tmp.k, path->btree_id, path->level - 1); } if (!was_locked) btree_node_unlock(trans, path, path->level); bch2_bkey_buf_exit(&tmp, c); return ret; } static noinline void btree_node_mem_ptr_set(struct btree_trans *trans, struct btree_path *path, unsigned plevel, struct btree *b) { struct btree_path_level *l = &path->l[plevel]; bool locked = btree_node_locked(path, plevel); struct bkey_packed *k; struct bch_btree_ptr_v2 *bp; if (!bch2_btree_node_relock(trans, path, plevel)) return; k = bch2_btree_node_iter_peek_all(&l->iter, l->b); BUG_ON(k->type != KEY_TYPE_btree_ptr_v2); bp = (void *) bkeyp_val(&l->b->format, k); bp->mem_ptr = (unsigned long)b; if (!locked) btree_node_unlock(trans, path, plevel); } static noinline int btree_node_iter_and_journal_peek(struct btree_trans *trans, struct btree_path *path, unsigned flags, struct bkey_buf *out) { struct bch_fs *c = trans->c; struct btree_path_level *l = path_l(path); struct btree_and_journal_iter jiter; struct bkey_s_c k; int ret = 0; __bch2_btree_and_journal_iter_init_node_iter(trans, &jiter, l->b, l->iter, path->pos); k = bch2_btree_and_journal_iter_peek(&jiter); bch2_bkey_buf_reassemble(out, c, k); if ((flags & BTREE_ITER_prefetch) && c->opts.btree_node_prefetch) ret = btree_path_prefetch_j(trans, path, &jiter); bch2_btree_and_journal_iter_exit(&jiter); return ret; } static __always_inline int btree_path_down(struct btree_trans *trans, struct btree_path *path, unsigned flags, unsigned long trace_ip) { struct bch_fs *c = trans->c; struct btree_path_level *l = path_l(path); struct btree *b; unsigned level = path->level - 1; enum six_lock_type lock_type = __btree_lock_want(path, level); struct bkey_buf tmp; int ret; EBUG_ON(!btree_node_locked(path, path->level)); bch2_bkey_buf_init(&tmp); if (unlikely(trans->journal_replay_not_finished)) { ret = btree_node_iter_and_journal_peek(trans, path, flags, &tmp); if (ret) goto err; } else { struct bkey_packed *k = bch2_btree_node_iter_peek(&l->iter, l->b); if (!k) { struct printbuf buf = PRINTBUF; prt_str(&buf, "node not found at pos "); bch2_bpos_to_text(&buf, path->pos); prt_str(&buf, " within parent node "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&l->b->key)); bch2_fs_fatal_error(c, "%s", buf.buf); printbuf_exit(&buf); ret = -BCH_ERR_btree_need_topology_repair; goto err; } bch2_bkey_buf_unpack(&tmp, c, l->b, k); if ((flags & BTREE_ITER_prefetch) && c->opts.btree_node_prefetch) { ret = btree_path_prefetch(trans, path); if (ret) goto err; } } b = bch2_btree_node_get(trans, path, tmp.k, level, lock_type, trace_ip); ret = PTR_ERR_OR_ZERO(b); if (unlikely(ret)) goto err; if (likely(!trans->journal_replay_not_finished && tmp.k->k.type == KEY_TYPE_btree_ptr_v2) && unlikely(b != btree_node_mem_ptr(tmp.k))) btree_node_mem_ptr_set(trans, path, level + 1, b); if (btree_node_read_locked(path, level + 1)) btree_node_unlock(trans, path, level + 1); mark_btree_node_locked(trans, path, level, (enum btree_node_locked_type) lock_type); path->level = level; bch2_btree_path_level_init(trans, path, b); bch2_btree_path_verify_locks(path); err: bch2_bkey_buf_exit(&tmp, c); return ret; } static int bch2_btree_path_traverse_all(struct btree_trans *trans) { struct bch_fs *c = trans->c; struct btree_path *path; unsigned long trace_ip = _RET_IP_; unsigned i; int ret = 0; if (trans->in_traverse_all) return -BCH_ERR_transaction_restart_in_traverse_all; trans->in_traverse_all = true; retry_all: trans->restarted = 0; trans->last_restarted_ip = 0; trans_for_each_path(trans, path, i) path->should_be_locked = false; btree_trans_sort_paths(trans); bch2_trans_unlock(trans); cond_resched(); trans->locked = true; if (unlikely(trans->memory_allocation_failure)) { struct closure cl; closure_init_stack(&cl); do { ret = bch2_btree_cache_cannibalize_lock(trans, &cl); closure_sync(&cl); } while (ret); } /* Now, redo traversals in correct order: */ i = 0; while (i < trans->nr_sorted) { btree_path_idx_t idx = trans->sorted[i]; /* * Traversing a path can cause another path to be added at about * the same position: */ if (trans->paths[idx].uptodate) { __btree_path_get(&trans->paths[idx], false); ret = bch2_btree_path_traverse_one(trans, idx, 0, _THIS_IP_); __btree_path_put(&trans->paths[idx], false); if (bch2_err_matches(ret, BCH_ERR_transaction_restart) || bch2_err_matches(ret, ENOMEM)) goto retry_all; if (ret) goto err; } else { i++; } } /* * We used to assert that all paths had been traversed here * (path->uptodate < BTREE_ITER_NEED_TRAVERSE); however, since * path->should_be_locked is not set yet, we might have unlocked and * then failed to relock a path - that's fine. */ err: bch2_btree_cache_cannibalize_unlock(trans); trans->in_traverse_all = false; trace_and_count(c, trans_traverse_all, trans, trace_ip); return ret; } static inline bool btree_path_check_pos_in_node(struct btree_path *path, unsigned l, int check_pos) { if (check_pos < 0 && btree_path_pos_before_node(path, path->l[l].b)) return false; if (check_pos > 0 && btree_path_pos_after_node(path, path->l[l].b)) return false; return true; } static inline bool btree_path_good_node(struct btree_trans *trans, struct btree_path *path, unsigned l, int check_pos) { return is_btree_node(path, l) && bch2_btree_node_relock(trans, path, l) && btree_path_check_pos_in_node(path, l, check_pos); } static void btree_path_set_level_down(struct btree_trans *trans, struct btree_path *path, unsigned new_level) { unsigned l; path->level = new_level; for (l = path->level + 1; l < BTREE_MAX_DEPTH; l++) if (btree_lock_want(path, l) == BTREE_NODE_UNLOCKED) btree_node_unlock(trans, path, l); btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE); bch2_btree_path_verify(trans, path); } static noinline unsigned __btree_path_up_until_good_node(struct btree_trans *trans, struct btree_path *path, int check_pos) { unsigned i, l = path->level; again: while (btree_path_node(path, l) && !btree_path_good_node(trans, path, l, check_pos)) __btree_path_set_level_up(trans, path, l++); /* If we need intent locks, take them too: */ for (i = l + 1; i < path->locks_want && btree_path_node(path, i); i++) if (!bch2_btree_node_relock(trans, path, i)) { while (l <= i) __btree_path_set_level_up(trans, path, l++); goto again; } return l; } static inline unsigned btree_path_up_until_good_node(struct btree_trans *trans, struct btree_path *path, int check_pos) { return likely(btree_node_locked(path, path->level) && btree_path_check_pos_in_node(path, path->level, check_pos)) ? path->level : __btree_path_up_until_good_node(trans, path, check_pos); } /* * This is the main state machine for walking down the btree - walks down to a * specified depth * * Returns 0 on success, -EIO on error (error reading in a btree node). * * On error, caller (peek_node()/peek_key()) must return NULL; the error is * stashed in the iterator and returned from bch2_trans_exit(). */ int bch2_btree_path_traverse_one(struct btree_trans *trans, btree_path_idx_t path_idx, unsigned flags, unsigned long trace_ip) { struct btree_path *path = &trans->paths[path_idx]; unsigned depth_want = path->level; int ret = -((int) trans->restarted); if (unlikely(ret)) goto out; if (unlikely(!trans->srcu_held)) bch2_trans_srcu_lock(trans); /* * Ensure we obey path->should_be_locked: if it's set, we can't unlock * and re-traverse the path without a transaction restart: */ if (path->should_be_locked) { ret = bch2_btree_path_relock(trans, path, trace_ip); goto out; } if (path->cached) { ret = bch2_btree_path_traverse_cached(trans, path, flags); goto out; } path = &trans->paths[path_idx]; if (unlikely(path->level >= BTREE_MAX_DEPTH)) goto out_uptodate; path->level = btree_path_up_until_good_node(trans, path, 0); unsigned max_level = path->level; EBUG_ON(btree_path_node(path, path->level) && !btree_node_locked(path, path->level)); /* * Note: path->nodes[path->level] may be temporarily NULL here - that * would indicate to other code that we got to the end of the btree, * here it indicates that relocking the root failed - it's critical that * btree_path_lock_root() comes next and that it can't fail */ while (path->level > depth_want) { ret = btree_path_node(path, path->level) ? btree_path_down(trans, path, flags, trace_ip) : btree_path_lock_root(trans, path, depth_want, trace_ip); if (unlikely(ret)) { if (ret == 1) { /* * No nodes at this level - got to the end of * the btree: */ ret = 0; goto out; } __bch2_btree_path_unlock(trans, path); path->level = depth_want; path->l[path->level].b = ERR_PTR(ret); goto out; } } if (unlikely(max_level > path->level)) { struct btree_path *linked; unsigned iter; trans_for_each_path_with_node(trans, path_l(path)->b, linked, iter) for (unsigned j = path->level + 1; j < max_level; j++) linked->l[j] = path->l[j]; } out_uptodate: path->uptodate = BTREE_ITER_UPTODATE; out: if (bch2_err_matches(ret, BCH_ERR_transaction_restart) != !!trans->restarted) panic("ret %s (%i) trans->restarted %s (%i)\n", bch2_err_str(ret), ret, bch2_err_str(trans->restarted), trans->restarted); bch2_btree_path_verify(trans, path); return ret; } static inline void btree_path_copy(struct btree_trans *trans, struct btree_path *dst, struct btree_path *src) { unsigned i, offset = offsetof(struct btree_path, pos); memcpy((void *) dst + offset, (void *) src + offset, sizeof(struct btree_path) - offset); for (i = 0; i < BTREE_MAX_DEPTH; i++) { unsigned t = btree_node_locked_type(dst, i); if (t != BTREE_NODE_UNLOCKED) six_lock_increment(&dst->l[i].b->c.lock, t); } } static btree_path_idx_t btree_path_clone(struct btree_trans *trans, btree_path_idx_t src, bool intent, unsigned long ip) { btree_path_idx_t new = btree_path_alloc(trans, src); btree_path_copy(trans, trans->paths + new, trans->paths + src); __btree_path_get(trans->paths + new, intent); #ifdef TRACK_PATH_ALLOCATED trans->paths[new].ip_allocated = ip; #endif return new; } __flatten btree_path_idx_t __bch2_btree_path_make_mut(struct btree_trans *trans, btree_path_idx_t path, bool intent, unsigned long ip) { __btree_path_put(trans->paths + path, intent); path = btree_path_clone(trans, path, intent, ip); trans->paths[path].preserve = false; return path; } btree_path_idx_t __must_check __bch2_btree_path_set_pos(struct btree_trans *trans, btree_path_idx_t path_idx, struct bpos new_pos, bool intent, unsigned long ip) { int cmp = bpos_cmp(new_pos, trans->paths[path_idx].pos); bch2_trans_verify_not_in_restart(trans); EBUG_ON(!trans->paths[path_idx].ref); path_idx = bch2_btree_path_make_mut(trans, path_idx, intent, ip); struct btree_path *path = trans->paths + path_idx; path->pos = new_pos; trans->paths_sorted = false; if (unlikely(path->cached)) { btree_node_unlock(trans, path, 0); path->l[0].b = ERR_PTR(-BCH_ERR_no_btree_node_up); btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE); goto out; } unsigned level = btree_path_up_until_good_node(trans, path, cmp); if (btree_path_node(path, level)) { struct btree_path_level *l = &path->l[level]; BUG_ON(!btree_node_locked(path, level)); /* * We might have to skip over many keys, or just a few: try * advancing the node iterator, and if we have to skip over too * many keys just reinit it (or if we're rewinding, since that * is expensive). */ if (cmp < 0 || !btree_path_advance_to_pos(path, l, 8)) bch2_btree_node_iter_init(&l->iter, l->b, &path->pos); /* * Iterators to interior nodes should always be pointed at the first non * whiteout: */ if (unlikely(level)) bch2_btree_node_iter_peek(&l->iter, l->b); } if (unlikely(level != path->level)) { btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE); __bch2_btree_path_unlock(trans, path); } out: bch2_btree_path_verify(trans, path); return path_idx; } /* Btree path: main interface: */ static struct btree_path *have_path_at_pos(struct btree_trans *trans, struct btree_path *path) { struct btree_path *sib; sib = prev_btree_path(trans, path); if (sib && !btree_path_cmp(sib, path)) return sib; sib = next_btree_path(trans, path); if (sib && !btree_path_cmp(sib, path)) return sib; return NULL; } static struct btree_path *have_node_at_pos(struct btree_trans *trans, struct btree_path *path) { struct btree_path *sib; sib = prev_btree_path(trans, path); if (sib && sib->level == path->level && path_l(sib)->b == path_l(path)->b) return sib; sib = next_btree_path(trans, path); if (sib && sib->level == path->level && path_l(sib)->b == path_l(path)->b) return sib; return NULL; } static inline void __bch2_path_free(struct btree_trans *trans, btree_path_idx_t path) { __bch2_btree_path_unlock(trans, trans->paths + path); btree_path_list_remove(trans, trans->paths + path); __clear_bit(path, trans->paths_allocated); } static bool bch2_btree_path_can_relock(struct btree_trans *trans, struct btree_path *path) { unsigned l = path->level; do { if (!btree_path_node(path, l)) break; if (!is_btree_node(path, l)) return false; if (path->l[l].lock_seq != path->l[l].b->c.lock.seq) return false; l++; } while (l < path->locks_want); return true; } void bch2_path_put(struct btree_trans *trans, btree_path_idx_t path_idx, bool intent) { struct btree_path *path = trans->paths + path_idx, *dup; if (!__btree_path_put(path, intent)) return; dup = path->preserve ? have_path_at_pos(trans, path) : have_node_at_pos(trans, path); if (!dup && !(!path->preserve && !is_btree_node(path, path->level))) return; if (path->should_be_locked && !trans->restarted) { if (!dup) return; if (!(trans->locked ? bch2_btree_path_relock_norestart(trans, dup) : bch2_btree_path_can_relock(trans, dup))) return; } if (dup) { dup->preserve |= path->preserve; dup->should_be_locked |= path->should_be_locked; } __bch2_path_free(trans, path_idx); } static void bch2_path_put_nokeep(struct btree_trans *trans, btree_path_idx_t path, bool intent) { if (!__btree_path_put(trans->paths + path, intent)) return; __bch2_path_free(trans, path); } void __noreturn bch2_trans_restart_error(struct btree_trans *trans, u32 restart_count) { panic("trans->restart_count %u, should be %u, last restarted by %pS\n", trans->restart_count, restart_count, (void *) trans->last_begin_ip); } void __noreturn bch2_trans_in_restart_error(struct btree_trans *trans) { panic("in transaction restart: %s, last restarted by %pS\n", bch2_err_str(trans->restarted), (void *) trans->last_restarted_ip); } void __noreturn bch2_trans_unlocked_error(struct btree_trans *trans) { panic("trans should be locked, unlocked by %pS\n", (void *) trans->last_unlock_ip); } noinline __cold void bch2_trans_updates_to_text(struct printbuf *buf, struct btree_trans *trans) { prt_printf(buf, "transaction updates for %s journal seq %llu\n", trans->fn, trans->journal_res.seq); printbuf_indent_add(buf, 2); trans_for_each_update(trans, i) { struct bkey_s_c old = { &i->old_k, i->old_v }; prt_printf(buf, "update: btree=%s cached=%u %pS\n", bch2_btree_id_str(i->btree_id), i->cached, (void *) i->ip_allocated); prt_printf(buf, " old "); bch2_bkey_val_to_text(buf, trans->c, old); prt_newline(buf); prt_printf(buf, " new "); bch2_bkey_val_to_text(buf, trans->c, bkey_i_to_s_c(i->k)); prt_newline(buf); } for (struct jset_entry *e = trans->journal_entries; e != btree_trans_journal_entries_top(trans); e = vstruct_next(e)) bch2_journal_entry_to_text(buf, trans->c, e); printbuf_indent_sub(buf, 2); } noinline __cold void bch2_dump_trans_updates(struct btree_trans *trans) { struct printbuf buf = PRINTBUF; bch2_trans_updates_to_text(&buf, trans); bch2_print_string_as_lines(KERN_ERR, buf.buf); printbuf_exit(&buf); } static void bch2_btree_path_to_text_short(struct printbuf *out, struct btree_trans *trans, btree_path_idx_t path_idx) { struct btree_path *path = trans->paths + path_idx; prt_printf(out, "path: idx %2u ref %u:%u %c %c %c btree=%s l=%u pos ", path_idx, path->ref, path->intent_ref, path->preserve ? 'P' : ' ', path->should_be_locked ? 'S' : ' ', path->cached ? 'C' : 'B', bch2_btree_id_str(path->btree_id), path->level); bch2_bpos_to_text(out, path->pos); #ifdef TRACK_PATH_ALLOCATED prt_printf(out, " %pS", (void *) path->ip_allocated); #endif } static const char *btree_node_locked_str(enum btree_node_locked_type t) { switch (t) { case BTREE_NODE_UNLOCKED: return "unlocked"; case BTREE_NODE_READ_LOCKED: return "read"; case BTREE_NODE_INTENT_LOCKED: return "intent"; case BTREE_NODE_WRITE_LOCKED: return "write"; default: return NULL; } } void bch2_btree_path_to_text(struct printbuf *out, struct btree_trans *trans, btree_path_idx_t path_idx) { bch2_btree_path_to_text_short(out, trans, path_idx); struct btree_path *path = trans->paths + path_idx; prt_printf(out, " uptodate %u locks_want %u", path->uptodate, path->locks_want); prt_newline(out); printbuf_indent_add(out, 2); for (unsigned l = 0; l < BTREE_MAX_DEPTH; l++) { prt_printf(out, "l=%u locks %s seq %u node ", l, btree_node_locked_str(btree_node_locked_type(path, l)), path->l[l].lock_seq); int ret = PTR_ERR_OR_ZERO(path->l[l].b); if (ret) prt_str(out, bch2_err_str(ret)); else prt_printf(out, "%px", path->l[l].b); prt_newline(out); } printbuf_indent_sub(out, 2); } static noinline __cold void __bch2_trans_paths_to_text(struct printbuf *out, struct btree_trans *trans, bool nosort) { struct trans_for_each_path_inorder_iter iter; if (!nosort) btree_trans_sort_paths(trans); trans_for_each_path_idx_inorder(trans, iter) { bch2_btree_path_to_text_short(out, trans, iter.path_idx); prt_newline(out); } } noinline __cold void bch2_trans_paths_to_text(struct printbuf *out, struct btree_trans *trans) { __bch2_trans_paths_to_text(out, trans, false); } static noinline __cold void __bch2_dump_trans_paths_updates(struct btree_trans *trans, bool nosort) { struct printbuf buf = PRINTBUF; __bch2_trans_paths_to_text(&buf, trans, nosort); bch2_trans_updates_to_text(&buf, trans); bch2_print_string_as_lines(KERN_ERR, buf.buf); printbuf_exit(&buf); } noinline __cold void bch2_dump_trans_paths_updates(struct btree_trans *trans) { __bch2_dump_trans_paths_updates(trans, false); } noinline __cold static void bch2_trans_update_max_paths(struct btree_trans *trans) { struct btree_transaction_stats *s = btree_trans_stats(trans); struct printbuf buf = PRINTBUF; size_t nr = bitmap_weight(trans->paths_allocated, trans->nr_paths); bch2_trans_paths_to_text(&buf, trans); if (!buf.allocation_failure) { mutex_lock(&s->lock); if (nr > s->nr_max_paths) { s->nr_max_paths = nr; swap(s->max_paths_text, buf.buf); } mutex_unlock(&s->lock); } printbuf_exit(&buf); trans->nr_paths_max = nr; } noinline __cold int __bch2_btree_trans_too_many_iters(struct btree_trans *trans) { if (trace_trans_restart_too_many_iters_enabled()) { struct printbuf buf = PRINTBUF; bch2_trans_paths_to_text(&buf, trans); trace_trans_restart_too_many_iters(trans, _THIS_IP_, buf.buf); printbuf_exit(&buf); } count_event(trans->c, trans_restart_too_many_iters); return btree_trans_restart(trans, BCH_ERR_transaction_restart_too_many_iters); } static noinline void btree_path_overflow(struct btree_trans *trans) { bch2_dump_trans_paths_updates(trans); bch_err(trans->c, "trans path overflow"); } static noinline void btree_paths_realloc(struct btree_trans *trans) { unsigned nr = trans->nr_paths * 2; void *p = kvzalloc(BITS_TO_LONGS(nr) * sizeof(unsigned long) + sizeof(struct btree_trans_paths) + nr * sizeof(struct btree_path) + nr * sizeof(btree_path_idx_t) + 8 + nr * sizeof(struct btree_insert_entry), GFP_KERNEL|__GFP_NOFAIL); unsigned long *paths_allocated = p; memcpy(paths_allocated, trans->paths_allocated, BITS_TO_LONGS(trans->nr_paths) * sizeof(unsigned long)); p += BITS_TO_LONGS(nr) * sizeof(unsigned long); p += sizeof(struct btree_trans_paths); struct btree_path *paths = p; *trans_paths_nr(paths) = nr; memcpy(paths, trans->paths, trans->nr_paths * sizeof(struct btree_path)); p += nr * sizeof(struct btree_path); btree_path_idx_t *sorted = p; memcpy(sorted, trans->sorted, trans->nr_sorted * sizeof(btree_path_idx_t)); p += nr * sizeof(btree_path_idx_t) + 8; struct btree_insert_entry *updates = p; memcpy(updates, trans->updates, trans->nr_paths * sizeof(struct btree_insert_entry)); unsigned long *old = trans->paths_allocated; rcu_assign_pointer(trans->paths_allocated, paths_allocated); rcu_assign_pointer(trans->paths, paths); rcu_assign_pointer(trans->sorted, sorted); rcu_assign_pointer(trans->updates, updates); trans->nr_paths = nr; if (old != trans->_paths_allocated) kfree_rcu_mightsleep(old); } static inline btree_path_idx_t btree_path_alloc(struct btree_trans *trans, btree_path_idx_t pos) { btree_path_idx_t idx = find_first_zero_bit(trans->paths_allocated, trans->nr_paths); if (unlikely(idx == trans->nr_paths)) { if (trans->nr_paths == BTREE_ITER_MAX) { btree_path_overflow(trans); return 0; } btree_paths_realloc(trans); } /* * Do this before marking the new path as allocated, since it won't be * initialized yet: */ if (unlikely(idx > trans->nr_paths_max)) bch2_trans_update_max_paths(trans); __set_bit(idx, trans->paths_allocated); struct btree_path *path = &trans->paths[idx]; path->ref = 0; path->intent_ref = 0; path->nodes_locked = 0; btree_path_list_add(trans, pos, idx); trans->paths_sorted = false; return idx; } btree_path_idx_t bch2_path_get(struct btree_trans *trans, enum btree_id btree_id, struct bpos pos, unsigned locks_want, unsigned level, unsigned flags, unsigned long ip) { struct btree_path *path; bool cached = flags & BTREE_ITER_cached; bool intent = flags & BTREE_ITER_intent; struct trans_for_each_path_inorder_iter iter; btree_path_idx_t path_pos = 0, path_idx; bch2_trans_verify_not_unlocked(trans); bch2_trans_verify_not_in_restart(trans); bch2_trans_verify_locks(trans); btree_trans_sort_paths(trans); trans_for_each_path_inorder(trans, path, iter) { if (__btree_path_cmp(path, btree_id, cached, pos, level) > 0) break; path_pos = iter.path_idx; } if (path_pos && trans->paths[path_pos].cached == cached && trans->paths[path_pos].btree_id == btree_id && trans->paths[path_pos].level == level) { __btree_path_get(trans->paths + path_pos, intent); path_idx = bch2_btree_path_set_pos(trans, path_pos, pos, intent, ip); path = trans->paths + path_idx; } else { path_idx = btree_path_alloc(trans, path_pos); path = trans->paths + path_idx; __btree_path_get(path, intent); path->pos = pos; path->btree_id = btree_id; path->cached = cached; path->uptodate = BTREE_ITER_NEED_TRAVERSE; path->should_be_locked = false; path->level = level; path->locks_want = locks_want; path->nodes_locked = 0; for (unsigned i = 0; i < ARRAY_SIZE(path->l); i++) path->l[i].b = ERR_PTR(-BCH_ERR_no_btree_node_init); #ifdef TRACK_PATH_ALLOCATED path->ip_allocated = ip; #endif trans->paths_sorted = false; } if (!(flags & BTREE_ITER_nopreserve)) path->preserve = true; if (path->intent_ref) locks_want = max(locks_want, level + 1); /* * If the path has locks_want greater than requested, we don't downgrade * it here - on transaction restart because btree node split needs to * upgrade locks, we might be putting/getting the iterator again. * Downgrading iterators only happens via bch2_trans_downgrade(), after * a successful transaction commit. */ locks_want = min(locks_want, BTREE_MAX_DEPTH); if (locks_want > path->locks_want) bch2_btree_path_upgrade_noupgrade_sibs(trans, path, locks_want, NULL); return path_idx; } btree_path_idx_t bch2_path_get_unlocked_mut(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct bpos pos) { btree_path_idx_t path_idx = bch2_path_get(trans, btree_id, pos, level + 1, level, BTREE_ITER_nopreserve| BTREE_ITER_intent, _RET_IP_); path_idx = bch2_btree_path_make_mut(trans, path_idx, true, _RET_IP_); struct btree_path *path = trans->paths + path_idx; bch2_btree_path_downgrade(trans, path); __bch2_btree_path_unlock(trans, path); return path_idx; } struct bkey_s_c bch2_btree_path_peek_slot(struct btree_path *path, struct bkey *u) { struct btree_path_level *l = path_l(path); struct bkey_packed *_k; struct bkey_s_c k; if (unlikely(!l->b)) return bkey_s_c_null; EBUG_ON(path->uptodate != BTREE_ITER_UPTODATE); EBUG_ON(!btree_node_locked(path, path->level)); if (!path->cached) { _k = bch2_btree_node_iter_peek_all(&l->iter, l->b); k = _k ? bkey_disassemble(l->b, _k, u) : bkey_s_c_null; EBUG_ON(k.k && bkey_deleted(k.k) && bpos_eq(k.k->p, path->pos)); if (!k.k || !bpos_eq(path->pos, k.k->p)) goto hole; } else { struct bkey_cached *ck = (void *) path->l[0].b; EBUG_ON(ck && (path->btree_id != ck->key.btree_id || !bkey_eq(path->pos, ck->key.pos))); if (!ck || !ck->valid) return bkey_s_c_null; *u = ck->k->k; k = bkey_i_to_s_c(ck->k); } return k; hole: bkey_init(u); u->p = path->pos; return (struct bkey_s_c) { u, NULL }; } void bch2_set_btree_iter_dontneed(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; if (!iter->path || trans->restarted) return; struct btree_path *path = btree_iter_path(trans, iter); path->preserve = false; if (path->ref == 1) path->should_be_locked = false; } /* Btree iterators: */ int __must_check __bch2_btree_iter_traverse(struct btree_iter *iter) { return bch2_btree_path_traverse(iter->trans, iter->path, iter->flags); } int __must_check bch2_btree_iter_traverse(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; int ret; bch2_trans_verify_not_unlocked(trans); iter->path = bch2_btree_path_set_pos(trans, iter->path, btree_iter_search_key(iter), iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); ret = bch2_btree_path_traverse(iter->trans, iter->path, iter->flags); if (ret) return ret; struct btree_path *path = btree_iter_path(trans, iter); if (btree_path_node(path, path->level)) btree_path_set_should_be_locked(path); return 0; } /* Iterate across nodes (leaf and interior nodes) */ struct btree *bch2_btree_iter_peek_node(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; struct btree *b = NULL; int ret; EBUG_ON(trans->paths[iter->path].cached); bch2_btree_iter_verify(iter); ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); if (ret) goto err; struct btree_path *path = btree_iter_path(trans, iter); b = btree_path_node(path, path->level); if (!b) goto out; BUG_ON(bpos_lt(b->key.k.p, iter->pos)); bkey_init(&iter->k); iter->k.p = iter->pos = b->key.k.p; iter->path = bch2_btree_path_set_pos(trans, iter->path, b->key.k.p, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); btree_path_set_should_be_locked(btree_iter_path(trans, iter)); out: bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(iter); return b; err: b = ERR_PTR(ret); goto out; } struct btree *bch2_btree_iter_peek_node_and_restart(struct btree_iter *iter) { struct btree *b; while (b = bch2_btree_iter_peek_node(iter), bch2_err_matches(PTR_ERR_OR_ZERO(b), BCH_ERR_transaction_restart)) bch2_trans_begin(iter->trans); return b; } struct btree *bch2_btree_iter_next_node(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; struct btree *b = NULL; int ret; EBUG_ON(trans->paths[iter->path].cached); bch2_trans_verify_not_in_restart(trans); bch2_btree_iter_verify(iter); struct btree_path *path = btree_iter_path(trans, iter); /* already at end? */ if (!btree_path_node(path, path->level)) return NULL; /* got to end? */ if (!btree_path_node(path, path->level + 1)) { btree_path_set_level_up(trans, path); return NULL; } if (!bch2_btree_node_relock(trans, path, path->level + 1)) { __bch2_btree_path_unlock(trans, path); path->l[path->level].b = ERR_PTR(-BCH_ERR_no_btree_node_relock); path->l[path->level + 1].b = ERR_PTR(-BCH_ERR_no_btree_node_relock); btree_path_set_dirty(path, BTREE_ITER_NEED_TRAVERSE); trace_and_count(trans->c, trans_restart_relock_next_node, trans, _THIS_IP_, path); ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_relock); goto err; } b = btree_path_node(path, path->level + 1); if (bpos_eq(iter->pos, b->key.k.p)) { __btree_path_set_level_up(trans, path, path->level++); } else { if (btree_lock_want(path, path->level + 1) == BTREE_NODE_UNLOCKED) btree_node_unlock(trans, path, path->level + 1); /* * Haven't gotten to the end of the parent node: go back down to * the next child node */ iter->path = bch2_btree_path_set_pos(trans, iter->path, bpos_successor(iter->pos), iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); path = btree_iter_path(trans, iter); btree_path_set_level_down(trans, path, iter->min_depth); ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); if (ret) goto err; path = btree_iter_path(trans, iter); b = path->l[path->level].b; } bkey_init(&iter->k); iter->k.p = iter->pos = b->key.k.p; iter->path = bch2_btree_path_set_pos(trans, iter->path, b->key.k.p, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); btree_path_set_should_be_locked(btree_iter_path(trans, iter)); EBUG_ON(btree_iter_path(trans, iter)->uptodate); out: bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(iter); return b; err: b = ERR_PTR(ret); goto out; } /* Iterate across keys (in leaf nodes only) */ inline bool bch2_btree_iter_advance(struct btree_iter *iter) { struct bpos pos = iter->k.p; bool ret = !(iter->flags & BTREE_ITER_all_snapshots ? bpos_eq(pos, SPOS_MAX) : bkey_eq(pos, SPOS_MAX)); if (ret && !(iter->flags & BTREE_ITER_is_extents)) pos = bkey_successor(iter, pos); bch2_btree_iter_set_pos(iter, pos); return ret; } inline bool bch2_btree_iter_rewind(struct btree_iter *iter) { struct bpos pos = bkey_start_pos(&iter->k); bool ret = !(iter->flags & BTREE_ITER_all_snapshots ? bpos_eq(pos, POS_MIN) : bkey_eq(pos, POS_MIN)); if (ret && !(iter->flags & BTREE_ITER_is_extents)) pos = bkey_predecessor(iter, pos); bch2_btree_iter_set_pos(iter, pos); return ret; } static noinline void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c *k) { struct bpos end = path_l(btree_iter_path(trans, iter))->b->data->min_key; trans_for_each_update(trans, i) if (!i->key_cache_already_flushed && i->btree_id == iter->btree_id && bpos_le(i->k->k.p, iter->pos) && bpos_ge(i->k->k.p, k->k ? k->k->p : end)) { iter->k = i->k->k; *k = bkey_i_to_s_c(i->k); } } static noinline void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c *k) { struct btree_path *path = btree_iter_path(trans, iter); struct bpos end = path_l(path)->b->key.k.p; trans_for_each_update(trans, i) if (!i->key_cache_already_flushed && i->btree_id == iter->btree_id && bpos_ge(i->k->k.p, path->pos) && bpos_le(i->k->k.p, k->k ? k->k->p : end)) { iter->k = i->k->k; *k = bkey_i_to_s_c(i->k); } } static noinline void bch2_btree_trans_peek_slot_updates(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c *k) { trans_for_each_update(trans, i) if (!i->key_cache_already_flushed && i->btree_id == iter->btree_id && bpos_eq(i->k->k.p, iter->pos)) { iter->k = i->k->k; *k = bkey_i_to_s_c(i->k); } } static struct bkey_i *bch2_btree_journal_peek(struct btree_trans *trans, struct btree_iter *iter, struct bpos end_pos) { struct btree_path *path = btree_iter_path(trans, iter); return bch2_journal_keys_peek_upto(trans->c, iter->btree_id, path->level, path->pos, end_pos, &iter->journal_idx); } static noinline struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans, struct btree_iter *iter) { struct btree_path *path = btree_iter_path(trans, iter); struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos); if (k) { iter->k = k->k; return bkey_i_to_s_c(k); } else { return bkey_s_c_null; } } static noinline struct bkey_s_c btree_trans_peek_journal(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct btree_path *path = btree_iter_path(trans, iter); struct bkey_i *next_journal = bch2_btree_journal_peek(trans, iter, k.k ? k.k->p : path_l(path)->b->key.k.p); if (next_journal) { iter->k = next_journal->k; k = bkey_i_to_s_c(next_journal); } return k; } /* * Checks btree key cache for key at iter->pos and returns it if present, or * bkey_s_c_null: */ static noinline struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos pos) { struct btree_trans *trans = iter->trans; struct bch_fs *c = trans->c; struct bkey u; struct bkey_s_c k; int ret; bch2_trans_verify_not_in_restart(trans); bch2_trans_verify_not_unlocked(trans); if ((iter->flags & BTREE_ITER_key_cache_fill) && bpos_eq(iter->pos, pos)) return bkey_s_c_null; if (!bch2_btree_key_cache_find(c, iter->btree_id, pos)) return bkey_s_c_null; if (!iter->key_cache_path) iter->key_cache_path = bch2_path_get(trans, iter->btree_id, pos, iter->flags & BTREE_ITER_intent, 0, iter->flags|BTREE_ITER_cached| BTREE_ITER_cached_nofill, _THIS_IP_); iter->key_cache_path = bch2_btree_path_set_pos(trans, iter->key_cache_path, pos, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); ret = bch2_btree_path_traverse(trans, iter->key_cache_path, iter->flags|BTREE_ITER_cached) ?: bch2_btree_path_relock(trans, btree_iter_path(trans, iter), _THIS_IP_); if (unlikely(ret)) return bkey_s_c_err(ret); btree_path_set_should_be_locked(trans->paths + iter->key_cache_path); k = bch2_btree_path_peek_slot(trans->paths + iter->key_cache_path, &u); if (k.k && !bkey_err(k)) { iter->k = u; k.k = &iter->k; } return k; } static struct bkey_s_c __bch2_btree_iter_peek(struct btree_iter *iter, struct bpos search_key) { struct btree_trans *trans = iter->trans; struct bkey_s_c k, k2; int ret; EBUG_ON(btree_iter_path(trans, iter)->cached); bch2_btree_iter_verify(iter); while (1) { struct btree_path_level *l; iter->path = bch2_btree_path_set_pos(trans, iter->path, search_key, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); if (unlikely(ret)) { /* ensure that iter->k is consistent with iter->pos: */ bch2_btree_iter_set_pos(iter, iter->pos); k = bkey_s_c_err(ret); goto out; } struct btree_path *path = btree_iter_path(trans, iter); l = path_l(path); if (unlikely(!l->b)) { /* No btree nodes at requested level: */ bch2_btree_iter_set_pos(iter, SPOS_MAX); k = bkey_s_c_null; goto out; } btree_path_set_should_be_locked(path); k = btree_path_level_peek_all(trans->c, l, &iter->k); if (unlikely(iter->flags & BTREE_ITER_with_key_cache) && k.k && (k2 = btree_trans_peek_key_cache(iter, k.k->p)).k) { k = k2; ret = bkey_err(k); if (ret) { bch2_btree_iter_set_pos(iter, iter->pos); goto out; } } if (unlikely(iter->flags & BTREE_ITER_with_journal)) k = btree_trans_peek_journal(trans, iter, k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) bch2_btree_trans_peek_updates(trans, iter, &k); if (k.k && bkey_deleted(k.k)) { /* * If we've got a whiteout, and it's after the search * key, advance the search key to the whiteout instead * of just after the whiteout - it might be a btree * whiteout, with a real key at the same position, since * in the btree deleted keys sort before non deleted. */ search_key = !bpos_eq(search_key, k.k->p) ? k.k->p : bpos_successor(k.k->p); continue; } if (likely(k.k)) { break; } else if (likely(!bpos_eq(l->b->key.k.p, SPOS_MAX))) { /* Advance to next leaf node: */ search_key = bpos_successor(l->b->key.k.p); } else { /* End of btree: */ bch2_btree_iter_set_pos(iter, SPOS_MAX); k = bkey_s_c_null; goto out; } } out: bch2_btree_iter_verify(iter); return k; } /** * bch2_btree_iter_peek_upto() - returns first key greater than or equal to * iterator's current position * @iter: iterator to peek from * @end: search limit: returns keys less than or equal to @end * * Returns: key if found, or an error extractable with bkey_err(). */ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos end) { struct btree_trans *trans = iter->trans; struct bpos search_key = btree_iter_search_key(iter); struct bkey_s_c k; struct bpos iter_pos; int ret; bch2_trans_verify_not_unlocked(trans); EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bkey_eq(end, POS_MAX)); if (iter->update_path) { bch2_path_put_nokeep(trans, iter->update_path, iter->flags & BTREE_ITER_intent); iter->update_path = 0; } bch2_btree_iter_verify_entry_exit(iter); while (1) { k = __bch2_btree_iter_peek(iter, search_key); if (unlikely(!k.k)) goto end; if (unlikely(bkey_err(k))) goto out_no_locked; /* * We need to check against @end before FILTER_SNAPSHOTS because * if we get to a different inode that requested we might be * seeing keys for a different snapshot tree that will all be * filtered out. * * But we can't do the full check here, because bkey_start_pos() * isn't monotonically increasing before FILTER_SNAPSHOTS, and * that's what we check against in extents mode: */ if (unlikely(!(iter->flags & BTREE_ITER_is_extents) ? bkey_gt(k.k->p, end) : k.k->p.inode > end.inode)) goto end; if (iter->update_path && !bkey_eq(trans->paths[iter->update_path].pos, k.k->p)) { bch2_path_put_nokeep(trans, iter->update_path, iter->flags & BTREE_ITER_intent); iter->update_path = 0; } if ((iter->flags & BTREE_ITER_filter_snapshots) && (iter->flags & BTREE_ITER_intent) && !(iter->flags & BTREE_ITER_is_extents) && !iter->update_path) { struct bpos pos = k.k->p; if (pos.snapshot < iter->snapshot) { search_key = bpos_successor(k.k->p); continue; } pos.snapshot = iter->snapshot; /* * advance, same as on exit for iter->path, but only up * to snapshot */ __btree_path_get(trans->paths + iter->path, iter->flags & BTREE_ITER_intent); iter->update_path = iter->path; iter->update_path = bch2_btree_path_set_pos(trans, iter->update_path, pos, iter->flags & BTREE_ITER_intent, _THIS_IP_); ret = bch2_btree_path_traverse(trans, iter->update_path, iter->flags); if (unlikely(ret)) { k = bkey_s_c_err(ret); goto out_no_locked; } } /* * We can never have a key in a leaf node at POS_MAX, so * we don't have to check these successor() calls: */ if ((iter->flags & BTREE_ITER_filter_snapshots) && !bch2_snapshot_is_ancestor(trans->c, iter->snapshot, k.k->p.snapshot)) { search_key = bpos_successor(k.k->p); continue; } if (bkey_whiteout(k.k) && !(iter->flags & BTREE_ITER_all_snapshots)) { search_key = bkey_successor(iter, k.k->p); continue; } /* * iter->pos should be mononotically increasing, and always be * equal to the key we just returned - except extents can * straddle iter->pos: */ if (!(iter->flags & BTREE_ITER_is_extents)) iter_pos = k.k->p; else iter_pos = bkey_max(iter->pos, bkey_start_pos(k.k)); if (unlikely(!(iter->flags & BTREE_ITER_is_extents) ? bkey_gt(iter_pos, end) : bkey_ge(iter_pos, end))) goto end; break; } iter->pos = iter_pos; iter->path = bch2_btree_path_set_pos(trans, iter->path, k.k->p, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); btree_path_set_should_be_locked(btree_iter_path(trans, iter)); out_no_locked: if (iter->update_path) { ret = bch2_btree_path_relock(trans, trans->paths + iter->update_path, _THIS_IP_); if (unlikely(ret)) k = bkey_s_c_err(ret); else btree_path_set_should_be_locked(trans->paths + iter->update_path); } if (!(iter->flags & BTREE_ITER_all_snapshots)) iter->pos.snapshot = iter->snapshot; ret = bch2_btree_iter_verify_ret(iter, k); if (unlikely(ret)) { bch2_btree_iter_set_pos(iter, iter->pos); k = bkey_s_c_err(ret); } bch2_btree_iter_verify_entry_exit(iter); return k; end: bch2_btree_iter_set_pos(iter, end); k = bkey_s_c_null; goto out_no_locked; } /** * bch2_btree_iter_next() - returns first key greater than iterator's current * position * @iter: iterator to peek from * * Returns: key if found, or an error extractable with bkey_err(). */ struct bkey_s_c bch2_btree_iter_next(struct btree_iter *iter) { if (!bch2_btree_iter_advance(iter)) return bkey_s_c_null; return bch2_btree_iter_peek(iter); } /** * bch2_btree_iter_peek_prev() - returns first key less than or equal to * iterator's current position * @iter: iterator to peek from * * Returns: key if found, or an error extractable with bkey_err(). */ struct bkey_s_c bch2_btree_iter_peek_prev(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; struct bpos search_key = iter->pos; struct bkey_s_c k; struct bkey saved_k; const struct bch_val *saved_v; btree_path_idx_t saved_path = 0; int ret; bch2_trans_verify_not_unlocked(trans); EBUG_ON(btree_iter_path(trans, iter)->cached || btree_iter_path(trans, iter)->level); if (iter->flags & BTREE_ITER_with_journal) return bkey_s_c_err(-BCH_ERR_btree_iter_with_journal_not_supported); bch2_btree_iter_verify(iter); bch2_btree_iter_verify_entry_exit(iter); if (iter->flags & BTREE_ITER_filter_snapshots) search_key.snapshot = U32_MAX; while (1) { iter->path = bch2_btree_path_set_pos(trans, iter->path, search_key, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); if (unlikely(ret)) { /* ensure that iter->k is consistent with iter->pos: */ bch2_btree_iter_set_pos(iter, iter->pos); k = bkey_s_c_err(ret); goto out_no_locked; } struct btree_path *path = btree_iter_path(trans, iter); k = btree_path_level_peek(trans, path, &path->l[0], &iter->k); if (!k.k || ((iter->flags & BTREE_ITER_is_extents) ? bpos_ge(bkey_start_pos(k.k), search_key) : bpos_gt(k.k->p, search_key))) k = btree_path_level_prev(trans, path, &path->l[0], &iter->k); if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) bch2_btree_trans_peek_prev_updates(trans, iter, &k); if (likely(k.k)) { if (iter->flags & BTREE_ITER_filter_snapshots) { if (k.k->p.snapshot == iter->snapshot) goto got_key; /* * If we have a saved candidate, and we're no * longer at the same _key_ (not pos), return * that candidate */ if (saved_path && !bkey_eq(k.k->p, saved_k.p)) { bch2_path_put_nokeep(trans, iter->path, iter->flags & BTREE_ITER_intent); iter->path = saved_path; saved_path = 0; iter->k = saved_k; k.v = saved_v; goto got_key; } if (bch2_snapshot_is_ancestor(trans->c, iter->snapshot, k.k->p.snapshot)) { if (saved_path) bch2_path_put_nokeep(trans, saved_path, iter->flags & BTREE_ITER_intent); saved_path = btree_path_clone(trans, iter->path, iter->flags & BTREE_ITER_intent, _THIS_IP_); path = btree_iter_path(trans, iter); saved_k = *k.k; saved_v = k.v; } search_key = bpos_predecessor(k.k->p); continue; } got_key: if (bkey_whiteout(k.k) && !(iter->flags & BTREE_ITER_all_snapshots)) { search_key = bkey_predecessor(iter, k.k->p); if (iter->flags & BTREE_ITER_filter_snapshots) search_key.snapshot = U32_MAX; continue; } btree_path_set_should_be_locked(path); break; } else if (likely(!bpos_eq(path->l[0].b->data->min_key, POS_MIN))) { /* Advance to previous leaf node: */ search_key = bpos_predecessor(path->l[0].b->data->min_key); } else { /* Start of btree: */ bch2_btree_iter_set_pos(iter, POS_MIN); k = bkey_s_c_null; goto out_no_locked; } } EBUG_ON(bkey_gt(bkey_start_pos(k.k), iter->pos)); /* Extents can straddle iter->pos: */ if (bkey_lt(k.k->p, iter->pos)) iter->pos = k.k->p; if (iter->flags & BTREE_ITER_filter_snapshots) iter->pos.snapshot = iter->snapshot; out_no_locked: if (saved_path) bch2_path_put_nokeep(trans, saved_path, iter->flags & BTREE_ITER_intent); bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(iter); return k; } /** * bch2_btree_iter_prev() - returns first key less than iterator's current * position * @iter: iterator to peek from * * Returns: key if found, or an error extractable with bkey_err(). */ struct bkey_s_c bch2_btree_iter_prev(struct btree_iter *iter) { if (!bch2_btree_iter_rewind(iter)) return bkey_s_c_null; return bch2_btree_iter_peek_prev(iter); } struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) { struct btree_trans *trans = iter->trans; struct bpos search_key; struct bkey_s_c k; int ret; bch2_trans_verify_not_unlocked(trans); bch2_btree_iter_verify(iter); bch2_btree_iter_verify_entry_exit(iter); EBUG_ON(btree_iter_path(trans, iter)->level && (iter->flags & BTREE_ITER_with_key_cache)); /* extents can't span inode numbers: */ if ((iter->flags & BTREE_ITER_is_extents) && unlikely(iter->pos.offset == KEY_OFFSET_MAX)) { if (iter->pos.inode == KEY_INODE_MAX) return bkey_s_c_null; bch2_btree_iter_set_pos(iter, bpos_nosnap_successor(iter->pos)); } search_key = btree_iter_search_key(iter); iter->path = bch2_btree_path_set_pos(trans, iter->path, search_key, iter->flags & BTREE_ITER_intent, btree_iter_ip_allocated(iter)); ret = bch2_btree_path_traverse(trans, iter->path, iter->flags); if (unlikely(ret)) { k = bkey_s_c_err(ret); goto out_no_locked; } if ((iter->flags & BTREE_ITER_cached) || !(iter->flags & (BTREE_ITER_is_extents|BTREE_ITER_filter_snapshots))) { k = bkey_s_c_null; if (unlikely((iter->flags & BTREE_ITER_with_updates) && trans->nr_updates)) { bch2_btree_trans_peek_slot_updates(trans, iter, &k); if (k.k) goto out; } if (unlikely(iter->flags & BTREE_ITER_with_journal) && (k = btree_trans_peek_slot_journal(trans, iter)).k) goto out; if (unlikely(iter->flags & BTREE_ITER_with_key_cache) && (k = btree_trans_peek_key_cache(iter, iter->pos)).k) { if (!bkey_err(k)) iter->k = *k.k; /* We're not returning a key from iter->path: */ goto out_no_locked; } k = bch2_btree_path_peek_slot(trans->paths + iter->path, &iter->k); if (unlikely(!k.k)) goto out_no_locked; } else { struct bpos next; struct bpos end = iter->pos; if (iter->flags & BTREE_ITER_is_extents) end.offset = U64_MAX; EBUG_ON(btree_iter_path(trans, iter)->level); if (iter->flags & BTREE_ITER_intent) { struct btree_iter iter2; bch2_trans_copy_iter(&iter2, iter); k = bch2_btree_iter_peek_upto(&iter2, end); if (k.k && !bkey_err(k)) { swap(iter->key_cache_path, iter2.key_cache_path); iter->k = iter2.k; k.k = &iter->k; } bch2_trans_iter_exit(trans, &iter2); } else { struct bpos pos = iter->pos; k = bch2_btree_iter_peek_upto(iter, end); if (unlikely(bkey_err(k))) bch2_btree_iter_set_pos(iter, pos); else iter->pos = pos; } if (unlikely(bkey_err(k))) goto out_no_locked; next = k.k ? bkey_start_pos(k.k) : POS_MAX; if (bkey_lt(iter->pos, next)) { bkey_init(&iter->k); iter->k.p = iter->pos; if (iter->flags & BTREE_ITER_is_extents) { bch2_key_resize(&iter->k, min_t(u64, KEY_SIZE_MAX, (next.inode == iter->pos.inode ? next.offset : KEY_OFFSET_MAX) - iter->pos.offset)); EBUG_ON(!iter->k.size); } k = (struct bkey_s_c) { &iter->k, NULL }; } } out: btree_path_set_should_be_locked(btree_iter_path(trans, iter)); out_no_locked: bch2_btree_iter_verify_entry_exit(iter); bch2_btree_iter_verify(iter); ret = bch2_btree_iter_verify_ret(iter, k); if (unlikely(ret)) return bkey_s_c_err(ret); return k; } struct bkey_s_c bch2_btree_iter_next_slot(struct btree_iter *iter) { if (!bch2_btree_iter_advance(iter)) return bkey_s_c_null; return bch2_btree_iter_peek_slot(iter); } struct bkey_s_c bch2_btree_iter_prev_slot(struct btree_iter *iter) { if (!bch2_btree_iter_rewind(iter)) return bkey_s_c_null; return bch2_btree_iter_peek_slot(iter); } struct bkey_s_c bch2_btree_iter_peek_and_restart_outlined(struct btree_iter *iter) { struct bkey_s_c k; while (btree_trans_too_many_iters(iter->trans) || (k = bch2_btree_iter_peek_type(iter, iter->flags), bch2_err_matches(bkey_err(k), BCH_ERR_transaction_restart))) bch2_trans_begin(iter->trans); return k; } /* new transactional stuff: */ #ifdef CONFIG_BCACHEFS_DEBUG static void btree_trans_verify_sorted_refs(struct btree_trans *trans) { struct btree_path *path; unsigned i; BUG_ON(trans->nr_sorted != bitmap_weight(trans->paths_allocated, trans->nr_paths) - 1); trans_for_each_path(trans, path, i) { BUG_ON(path->sorted_idx >= trans->nr_sorted); BUG_ON(trans->sorted[path->sorted_idx] != i); } for (i = 0; i < trans->nr_sorted; i++) { unsigned idx = trans->sorted[i]; BUG_ON(!test_bit(idx, trans->paths_allocated)); BUG_ON(trans->paths[idx].sorted_idx != i); } } static void btree_trans_verify_sorted(struct btree_trans *trans) { struct btree_path *path, *prev = NULL; struct trans_for_each_path_inorder_iter iter; if (!bch2_debug_check_iterators) return; trans_for_each_path_inorder(trans, path, iter) { if (prev && btree_path_cmp(prev, path) > 0) { __bch2_dump_trans_paths_updates(trans, true); panic("trans paths out of order!\n"); } prev = path; } } #else static inline void btree_trans_verify_sorted_refs(struct btree_trans *trans) {} static inline void btree_trans_verify_sorted(struct btree_trans *trans) {} #endif void __bch2_btree_trans_sort_paths(struct btree_trans *trans) { int i, l = 0, r = trans->nr_sorted, inc = 1; bool swapped; btree_trans_verify_sorted_refs(trans); if (trans->paths_sorted) goto out; /* * Cocktail shaker sort: this is efficient because iterators will be * mostly sorted. */ do { swapped = false; for (i = inc > 0 ? l : r - 2; i + 1 < r && i >= l; i += inc) { if (btree_path_cmp(trans->paths + trans->sorted[i], trans->paths + trans->sorted[i + 1]) > 0) { swap(trans->sorted[i], trans->sorted[i + 1]); trans->paths[trans->sorted[i]].sorted_idx = i; trans->paths[trans->sorted[i + 1]].sorted_idx = i + 1; swapped = true; } } if (inc > 0) --r; else l++; inc = -inc; } while (swapped); trans->paths_sorted = true; out: btree_trans_verify_sorted(trans); } static inline void btree_path_list_remove(struct btree_trans *trans, struct btree_path *path) { EBUG_ON(path->sorted_idx >= trans->nr_sorted); #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS trans->nr_sorted--; memmove_u64s_down_small(trans->sorted + path->sorted_idx, trans->sorted + path->sorted_idx + 1, DIV_ROUND_UP(trans->nr_sorted - path->sorted_idx, sizeof(u64) / sizeof(btree_path_idx_t))); #else array_remove_item(trans->sorted, trans->nr_sorted, path->sorted_idx); #endif for (unsigned i = path->sorted_idx; i < trans->nr_sorted; i++) trans->paths[trans->sorted[i]].sorted_idx = i; } static inline void btree_path_list_add(struct btree_trans *trans, btree_path_idx_t pos, btree_path_idx_t path_idx) { struct btree_path *path = trans->paths + path_idx; path->sorted_idx = pos ? trans->paths[pos].sorted_idx + 1 : trans->nr_sorted; #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS memmove_u64s_up_small(trans->sorted + path->sorted_idx + 1, trans->sorted + path->sorted_idx, DIV_ROUND_UP(trans->nr_sorted - path->sorted_idx, sizeof(u64) / sizeof(btree_path_idx_t))); trans->nr_sorted++; trans->sorted[path->sorted_idx] = path_idx; #else array_insert_item(trans->sorted, trans->nr_sorted, path->sorted_idx, path_idx); #endif for (unsigned i = path->sorted_idx; i < trans->nr_sorted; i++) trans->paths[trans->sorted[i]].sorted_idx = i; btree_trans_verify_sorted_refs(trans); } void bch2_trans_iter_exit(struct btree_trans *trans, struct btree_iter *iter) { if (iter->update_path) bch2_path_put_nokeep(trans, iter->update_path, iter->flags & BTREE_ITER_intent); if (iter->path) bch2_path_put(trans, iter->path, iter->flags & BTREE_ITER_intent); if (iter->key_cache_path) bch2_path_put(trans, iter->key_cache_path, iter->flags & BTREE_ITER_intent); iter->path = 0; iter->update_path = 0; iter->key_cache_path = 0; iter->trans = NULL; } void bch2_trans_iter_init_outlined(struct btree_trans *trans, struct btree_iter *iter, enum btree_id btree_id, struct bpos pos, unsigned flags) { bch2_trans_iter_init_common(trans, iter, btree_id, pos, 0, 0, bch2_btree_iter_flags(trans, btree_id, flags), _RET_IP_); } void bch2_trans_node_iter_init(struct btree_trans *trans, struct btree_iter *iter, enum btree_id btree_id, struct bpos pos, unsigned locks_want, unsigned depth, unsigned flags) { flags |= BTREE_ITER_not_extents; flags |= BTREE_ITER_snapshot_field; flags |= BTREE_ITER_all_snapshots; bch2_trans_iter_init_common(trans, iter, btree_id, pos, locks_want, depth, __bch2_btree_iter_flags(trans, btree_id, flags), _RET_IP_); iter->min_depth = depth; struct btree_path *path = btree_iter_path(trans, iter); BUG_ON(path->locks_want < min(locks_want, BTREE_MAX_DEPTH)); BUG_ON(path->level != depth); BUG_ON(iter->min_depth != depth); } void bch2_trans_copy_iter(struct btree_iter *dst, struct btree_iter *src) { struct btree_trans *trans = src->trans; *dst = *src; #ifdef TRACK_PATH_ALLOCATED dst->ip_allocated = _RET_IP_; #endif if (src->path) __btree_path_get(trans->paths + src->path, src->flags & BTREE_ITER_intent); if (src->update_path) __btree_path_get(trans->paths + src->update_path, src->flags & BTREE_ITER_intent); dst->key_cache_path = 0; } void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size) { struct bch_fs *c = trans->c; unsigned new_top = trans->mem_top + size; unsigned old_bytes = trans->mem_bytes; unsigned new_bytes = roundup_pow_of_two(new_top); int ret; void *new_mem; void *p; WARN_ON_ONCE(new_bytes > BTREE_TRANS_MEM_MAX); struct btree_transaction_stats *s = btree_trans_stats(trans); s->max_mem = max(s->max_mem, new_bytes); if (trans->used_mempool) { if (trans->mem_bytes >= new_bytes) goto out_change_top; /* No more space from mempool item, need malloc new one */ new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN); if (unlikely(!new_mem)) { bch2_trans_unlock(trans); new_mem = kmalloc(new_bytes, GFP_KERNEL); if (!new_mem) return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); ret = bch2_trans_relock(trans); if (ret) { kfree(new_mem); return ERR_PTR(ret); } } memcpy(new_mem, trans->mem, trans->mem_top); trans->used_mempool = false; mempool_free(trans->mem, &c->btree_trans_mem_pool); goto out_new_mem; } new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN); if (unlikely(!new_mem)) { bch2_trans_unlock(trans); new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL); if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) { new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL); new_bytes = BTREE_TRANS_MEM_MAX; memcpy(new_mem, trans->mem, trans->mem_top); trans->used_mempool = true; kfree(trans->mem); } if (!new_mem) return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc); trans->mem = new_mem; trans->mem_bytes = new_bytes; ret = bch2_trans_relock(trans); if (ret) return ERR_PTR(ret); } out_new_mem: trans->mem = new_mem; trans->mem_bytes = new_bytes; if (old_bytes) { trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes); return ERR_PTR(btree_trans_restart(trans, BCH_ERR_transaction_restart_mem_realloced)); } out_change_top: p = trans->mem + trans->mem_top; trans->mem_top += size; memset(p, 0, size); return p; } static inline void check_srcu_held_too_long(struct btree_trans *trans) { WARN(trans->srcu_held && time_after(jiffies, trans->srcu_lock_time + HZ * 10), "btree trans held srcu lock (delaying memory reclaim) for %lu seconds", (jiffies - trans->srcu_lock_time) / HZ); } void bch2_trans_srcu_unlock(struct btree_trans *trans) { if (trans->srcu_held) { struct bch_fs *c = trans->c; struct btree_path *path; unsigned i; trans_for_each_path(trans, path, i) if (path->cached && !btree_node_locked(path, 0)) path->l[0].b = ERR_PTR(-BCH_ERR_no_btree_node_srcu_reset); check_srcu_held_too_long(trans); srcu_read_unlock(&c->btree_trans_barrier, trans->srcu_idx); trans->srcu_held = false; } } static void bch2_trans_srcu_lock(struct btree_trans *trans) { if (!trans->srcu_held) { trans->srcu_idx = srcu_read_lock(&trans->c->btree_trans_barrier); trans->srcu_lock_time = jiffies; trans->srcu_held = true; } } /** * bch2_trans_begin() - reset a transaction after a interrupted attempt * @trans: transaction to reset * * Returns: current restart counter, to be used with trans_was_restarted() * * While iterating over nodes or updating nodes a attempt to lock a btree node * may return BCH_ERR_transaction_restart when the trylock fails. When this * occurs bch2_trans_begin() should be called and the transaction retried. */ u32 bch2_trans_begin(struct btree_trans *trans) { struct btree_path *path; unsigned i; u64 now; bch2_trans_reset_updates(trans); trans->restart_count++; trans->mem_top = 0; trans->journal_entries = NULL; trans_for_each_path(trans, path, i) { path->should_be_locked = false; /* * If the transaction wasn't restarted, we're presuming to be * doing something new: dont keep iterators excpt the ones that * are in use - except for the subvolumes btree: */ if (!trans->restarted && path->btree_id != BTREE_ID_subvolumes) path->preserve = false; /* * XXX: we probably shouldn't be doing this if the transaction * was restarted, but currently we still overflow transaction * iterators if we do that */ if (!path->ref && !path->preserve) __bch2_path_free(trans, i); else path->preserve = false; } now = local_clock(); if (!IS_ENABLED(CONFIG_BCACHEFS_NO_LATENCY_ACCT) && time_after64(now, trans->last_begin_time + 10)) __bch2_time_stats_update(&btree_trans_stats(trans)->duration, trans->last_begin_time, now); if (!trans->restarted && (need_resched() || time_after64(now, trans->last_begin_time + BTREE_TRANS_MAX_LOCK_HOLD_TIME_NS))) { bch2_trans_unlock(trans); cond_resched(); now = local_clock(); } trans->last_begin_time = now; if (unlikely(trans->srcu_held && time_after(jiffies, trans->srcu_lock_time + msecs_to_jiffies(10)))) bch2_trans_srcu_unlock(trans); trans->last_begin_ip = _RET_IP_; trans->locked = true; if (trans->restarted) { bch2_btree_path_traverse_all(trans); trans->notrace_relock_fail = false; } bch2_trans_verify_not_unlocked(trans); return trans->restart_count; } const char *bch2_btree_transaction_fns[BCH_TRANSACTIONS_NR] = { "(unknown)" }; unsigned bch2_trans_get_fn_idx(const char *fn) { for (unsigned i = 0; i < ARRAY_SIZE(bch2_btree_transaction_fns); i++) if (!bch2_btree_transaction_fns[i] || bch2_btree_transaction_fns[i] == fn) { bch2_btree_transaction_fns[i] = fn; return i; } pr_warn_once("BCH_TRANSACTIONS_NR not big enough!"); return 0; } struct btree_trans *__bch2_trans_get(struct bch_fs *c, unsigned fn_idx) __acquires(&c->btree_trans_barrier) { struct btree_trans *trans; if (IS_ENABLED(__KERNEL__)) { trans = this_cpu_xchg(c->btree_trans_bufs->trans, NULL); if (trans) { memset(trans, 0, offsetof(struct btree_trans, list)); goto got_trans; } } trans = mempool_alloc(&c->btree_trans_pool, GFP_NOFS); memset(trans, 0, sizeof(*trans)); closure_init_stack(&trans->ref); seqmutex_lock(&c->btree_trans_lock); if (IS_ENABLED(CONFIG_BCACHEFS_DEBUG)) { struct btree_trans *pos; pid_t pid = current->pid; trans->locking_wait.task = current; list_for_each_entry(pos, &c->btree_trans_list, list) { struct task_struct *pos_task = READ_ONCE(pos->locking_wait.task); /* * We'd much prefer to be stricter here and completely * disallow multiple btree_trans in the same thread - * but the data move path calls bch2_write when we * already have a btree_trans initialized. */ BUG_ON(pos_task && pid == pos_task->pid && pos->locked); if (pos_task && pid < pos_task->pid) { list_add_tail(&trans->list, &pos->list); goto list_add_done; } } } list_add_tail(&trans->list, &c->btree_trans_list); list_add_done: seqmutex_unlock(&c->btree_trans_lock); got_trans: trans->c = c; trans->last_begin_time = local_clock(); trans->fn_idx = fn_idx; trans->locking_wait.task = current; trans->locked = true; trans->journal_replay_not_finished = unlikely(!test_bit(JOURNAL_replay_done, &c->journal.flags)) && atomic_inc_not_zero(&c->journal_keys.ref); trans->nr_paths = ARRAY_SIZE(trans->_paths); trans->paths_allocated = trans->_paths_allocated; trans->sorted = trans->_sorted; trans->paths = trans->_paths; trans->updates = trans->_updates; *trans_paths_nr(trans->paths) = BTREE_ITER_INITIAL; trans->paths_allocated[0] = 1; if (fn_idx < BCH_TRANSACTIONS_NR) { trans->fn = bch2_btree_transaction_fns[fn_idx]; struct btree_transaction_stats *s = &c->btree_transaction_stats[fn_idx]; if (s->max_mem) { unsigned expected_mem_bytes = roundup_pow_of_two(s->max_mem); trans->mem = kmalloc(expected_mem_bytes, GFP_KERNEL); if (likely(trans->mem)) trans->mem_bytes = expected_mem_bytes; } trans->nr_paths_max = s->nr_max_paths; trans->journal_entries_size = s->journal_entries_size; } trans->srcu_idx = srcu_read_lock(&c->btree_trans_barrier); trans->srcu_lock_time = jiffies; trans->srcu_held = true; return trans; } static void check_btree_paths_leaked(struct btree_trans *trans) { #ifdef CONFIG_BCACHEFS_DEBUG struct bch_fs *c = trans->c; struct btree_path *path; unsigned i; trans_for_each_path(trans, path, i) if (path->ref) goto leaked; return; leaked: bch_err(c, "btree paths leaked from %s!", trans->fn); trans_for_each_path(trans, path, i) if (path->ref) printk(KERN_ERR " btree %s %pS\n", bch2_btree_id_str(path->btree_id), (void *) path->ip_allocated); /* Be noisy about this: */ bch2_fatal_error(c); #endif } void bch2_trans_put(struct btree_trans *trans) __releases(&c->btree_trans_barrier) { struct bch_fs *c = trans->c; bch2_trans_unlock(trans); trans_for_each_update(trans, i) __btree_path_put(trans->paths + i->path, true); trans->nr_updates = 0; trans->locking_wait.task = NULL; check_btree_paths_leaked(trans); if (trans->srcu_held) { check_srcu_held_too_long(trans); srcu_read_unlock(&c->btree_trans_barrier, trans->srcu_idx); } if (trans->fs_usage_deltas) { if (trans->fs_usage_deltas->size + sizeof(trans->fs_usage_deltas) == REPLICAS_DELTA_LIST_MAX) mempool_free(trans->fs_usage_deltas, &c->replicas_delta_pool); else kfree(trans->fs_usage_deltas); } if (unlikely(trans->journal_replay_not_finished)) bch2_journal_keys_put(c); unsigned long *paths_allocated = trans->paths_allocated; trans->paths_allocated = NULL; trans->paths = NULL; if (paths_allocated != trans->_paths_allocated) kvfree_rcu_mightsleep(paths_allocated); if (trans->used_mempool) mempool_free(trans->mem, &c->btree_trans_mem_pool); else kfree(trans->mem); /* Userspace doesn't have a real percpu implementation: */ if (IS_ENABLED(__KERNEL__)) trans = this_cpu_xchg(c->btree_trans_bufs->trans, trans); if (trans) { closure_sync(&trans->ref); seqmutex_lock(&c->btree_trans_lock); list_del(&trans->list); seqmutex_unlock(&c->btree_trans_lock); mempool_free(trans, &c->btree_trans_pool); } } static void __maybe_unused bch2_btree_bkey_cached_common_to_text(struct printbuf *out, struct btree_bkey_cached_common *b) { struct six_lock_count c = six_lock_counts(&b->lock); struct task_struct *owner; pid_t pid; rcu_read_lock(); owner = READ_ONCE(b->lock.owner); pid = owner ? owner->pid : 0; rcu_read_unlock(); prt_printf(out, "\t%px %c l=%u %s:", b, b->cached ? 'c' : 'b', b->level, bch2_btree_id_str(b->btree_id)); bch2_bpos_to_text(out, btree_node_pos(b)); prt_printf(out, "\t locks %u:%u:%u held by pid %u", c.n[0], c.n[1], c.n[2], pid); } void bch2_btree_trans_to_text(struct printbuf *out, struct btree_trans *trans) { struct btree_bkey_cached_common *b; static char lock_types[] = { 'r', 'i', 'w' }; struct task_struct *task = READ_ONCE(trans->locking_wait.task); unsigned l, idx; /* before rcu_read_lock(): */ bch2_printbuf_make_room(out, 4096); if (!out->nr_tabstops) { printbuf_tabstop_push(out, 16); printbuf_tabstop_push(out, 32); } prt_printf(out, "%i %s\n", task ? task->pid : 0, trans->fn); /* trans->paths is rcu protected vs. freeing */ rcu_read_lock(); out->atomic++; struct btree_path *paths = rcu_dereference(trans->paths); if (!paths) goto out; unsigned long *paths_allocated = trans_paths_allocated(paths); trans_for_each_path_idx_from(paths_allocated, *trans_paths_nr(paths), idx, 1) { struct btree_path *path = paths + idx; if (!path->nodes_locked) continue; prt_printf(out, " path %u %c l=%u %s:", idx, path->cached ? 'c' : 'b', path->level, bch2_btree_id_str(path->btree_id)); bch2_bpos_to_text(out, path->pos); prt_newline(out); for (l = 0; l < BTREE_MAX_DEPTH; l++) { if (btree_node_locked(path, l) && !IS_ERR_OR_NULL(b = (void *) READ_ONCE(path->l[l].b))) { prt_printf(out, " %c l=%u ", lock_types[btree_node_locked_type(path, l)], l); bch2_btree_bkey_cached_common_to_text(out, b); prt_newline(out); } } } b = READ_ONCE(trans->locking); if (b) { prt_printf(out, " blocked for %lluus on\n", div_u64(local_clock() - trans->locking_wait.start_time, 1000)); prt_printf(out, " %c", lock_types[trans->locking_wait.lock_want]); bch2_btree_bkey_cached_common_to_text(out, b); prt_newline(out); } out: --out->atomic; rcu_read_unlock(); } void bch2_fs_btree_iter_exit(struct bch_fs *c) { struct btree_transaction_stats *s; struct btree_trans *trans; int cpu; if (c->btree_trans_bufs) for_each_possible_cpu(cpu) { struct btree_trans *trans = per_cpu_ptr(c->btree_trans_bufs, cpu)->trans; if (trans) { closure_sync(&trans->ref); seqmutex_lock(&c->btree_trans_lock); list_del(&trans->list); seqmutex_unlock(&c->btree_trans_lock); } kfree(trans); } free_percpu(c->btree_trans_bufs); trans = list_first_entry_or_null(&c->btree_trans_list, struct btree_trans, list); if (trans) panic("%s leaked btree_trans\n", trans->fn); for (s = c->btree_transaction_stats; s < c->btree_transaction_stats + ARRAY_SIZE(c->btree_transaction_stats); s++) { kfree(s->max_paths_text); bch2_time_stats_exit(&s->lock_hold_times); } if (c->btree_trans_barrier_initialized) cleanup_srcu_struct(&c->btree_trans_barrier); mempool_exit(&c->btree_trans_mem_pool); mempool_exit(&c->btree_trans_pool); } void bch2_fs_btree_iter_init_early(struct bch_fs *c) { struct btree_transaction_stats *s; for (s = c->btree_transaction_stats; s < c->btree_transaction_stats + ARRAY_SIZE(c->btree_transaction_stats); s++) { bch2_time_stats_init(&s->duration); bch2_time_stats_init(&s->lock_hold_times); mutex_init(&s->lock); } INIT_LIST_HEAD(&c->btree_trans_list); seqmutex_init(&c->btree_trans_lock); } int bch2_fs_btree_iter_init(struct bch_fs *c) { int ret; c->btree_trans_bufs = alloc_percpu(struct btree_trans_buf); if (!c->btree_trans_bufs) return -ENOMEM; ret = mempool_init_kmalloc_pool(&c->btree_trans_pool, 1, sizeof(struct btree_trans)) ?: mempool_init_kmalloc_pool(&c->btree_trans_mem_pool, 1, BTREE_TRANS_MEM_MAX) ?: init_srcu_struct(&c->btree_trans_barrier); if (!ret) c->btree_trans_barrier_initialized = true; return ret; } |
| 15 15 15 14 15 15 15 15 5 1 4 4 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/bcd.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/mc146818rtc.h> #ifdef CONFIG_ACPI #include <linux/acpi.h> #endif #define UIP_RECHECK_DELAY 100 /* usec */ #define UIP_RECHECK_DELAY_MS (USEC_PER_MSEC / UIP_RECHECK_DELAY) #define UIP_RECHECK_LOOPS_MS(x) (x / UIP_RECHECK_DELAY_MS) /* * Execute a function while the UIP (Update-in-progress) bit of the RTC is * unset. The timeout is configurable by the caller in ms. * * Warning: callback may be executed more then once. */ bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), int timeout, void *param) { int i; unsigned long flags; unsigned char seconds; for (i = 0; UIP_RECHECK_LOOPS_MS(i) < timeout; i++) { spin_lock_irqsave(&rtc_lock, flags); /* * Check whether there is an update in progress during which the * readout is unspecified. The maximum update time is ~2ms. Poll * for completion. * * Store the second value before checking UIP so a long lasting * NMI which happens to hit after the UIP check cannot make * an update cycle invisible. */ seconds = CMOS_READ(RTC_SECONDS); if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { spin_unlock_irqrestore(&rtc_lock, flags); udelay(UIP_RECHECK_DELAY); continue; } /* Revalidate the above readout */ if (seconds != CMOS_READ(RTC_SECONDS)) { spin_unlock_irqrestore(&rtc_lock, flags); continue; } if (callback) callback(seconds, param); /* * Check for the UIP bit again. If it is set now then * the above values may contain garbage. */ if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { spin_unlock_irqrestore(&rtc_lock, flags); udelay(UIP_RECHECK_DELAY); continue; } /* * A NMI might have interrupted the above sequence so check * whether the seconds value has changed which indicates that * the NMI took longer than the UIP bit was set. Unlikely, but * possible and there is also virt... */ if (seconds != CMOS_READ(RTC_SECONDS)) { spin_unlock_irqrestore(&rtc_lock, flags); continue; } spin_unlock_irqrestore(&rtc_lock, flags); if (UIP_RECHECK_LOOPS_MS(i) >= 100) pr_warn("Reading current time from RTC took around %li ms\n", UIP_RECHECK_LOOPS_MS(i)); return true; } return false; } EXPORT_SYMBOL_GPL(mc146818_avoid_UIP); /* * If the UIP (Update-in-progress) bit of the RTC is set for more then * 10ms, the RTC is apparently broken or not present. */ bool mc146818_does_rtc_work(void) { return mc146818_avoid_UIP(NULL, 1000, NULL); } EXPORT_SYMBOL_GPL(mc146818_does_rtc_work); struct mc146818_get_time_callback_param { struct rtc_time *time; unsigned char ctrl; #ifdef CONFIG_ACPI unsigned char century; #endif #ifdef CONFIG_MACH_DECSTATION unsigned int real_year; #endif }; static void mc146818_get_time_callback(unsigned char seconds, void *param_in) { struct mc146818_get_time_callback_param *p = param_in; /* * Only the values that we read from the RTC are set. We leave * tm_wday, tm_yday and tm_isdst untouched. Even though the * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated * by the RTC when initially set to a non-zero value. */ p->time->tm_sec = seconds; p->time->tm_min = CMOS_READ(RTC_MINUTES); p->time->tm_hour = CMOS_READ(RTC_HOURS); p->time->tm_mday = CMOS_READ(RTC_DAY_OF_MONTH); p->time->tm_mon = CMOS_READ(RTC_MONTH); p->time->tm_year = CMOS_READ(RTC_YEAR); #ifdef CONFIG_MACH_DECSTATION p->real_year = CMOS_READ(RTC_DEC_YEAR); #endif #ifdef CONFIG_ACPI if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && acpi_gbl_FADT.century) { p->century = CMOS_READ(acpi_gbl_FADT.century); } else { p->century = 0; } #endif p->ctrl = CMOS_READ(RTC_CONTROL); } /** * mc146818_get_time - Get the current time from the RTC * @time: pointer to struct rtc_time to store the current time * @timeout: timeout value in ms * * This function reads the current time from the RTC and stores it in the * provided struct rtc_time. The timeout parameter specifies the maximum * time to wait for the RTC to become ready. * * Return: 0 on success, -ETIMEDOUT if the RTC did not become ready within * the specified timeout, or another error code if an error occurred. */ int mc146818_get_time(struct rtc_time *time, int timeout) { struct mc146818_get_time_callback_param p = { .time = time }; if (!mc146818_avoid_UIP(mc146818_get_time_callback, timeout, &p)) { memset(time, 0, sizeof(*time)); return -ETIMEDOUT; } if (!(p.ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { time->tm_sec = bcd2bin(time->tm_sec); time->tm_min = bcd2bin(time->tm_min); time->tm_hour = bcd2bin(time->tm_hour); time->tm_mday = bcd2bin(time->tm_mday); time->tm_mon = bcd2bin(time->tm_mon); time->tm_year = bcd2bin(time->tm_year); #ifdef CONFIG_ACPI p.century = bcd2bin(p.century); #endif } #ifdef CONFIG_MACH_DECSTATION time->tm_year += p.real_year - 72; #endif #ifdef CONFIG_ACPI if (p.century > 19) time->tm_year += (p.century - 19) * 100; #endif /* * Account for differences between how the RTC uses the values * and how they are defined in a struct rtc_time; */ if (time->tm_year <= 69) time->tm_year += 100; time->tm_mon--; return 0; } EXPORT_SYMBOL_GPL(mc146818_get_time); /* AMD systems don't allow access to AltCentury with DV1 */ static bool apply_amd_register_a_behavior(void) { #ifdef CONFIG_X86 if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) return true; #endif return false; } /* Set the current date and time in the real time clock. */ int mc146818_set_time(struct rtc_time *time) { unsigned long flags; unsigned char mon, day, hrs, min, sec; unsigned char save_control, save_freq_select; unsigned int yrs; #ifdef CONFIG_MACH_DECSTATION unsigned int real_yrs, leap_yr; #endif unsigned char century = 0; yrs = time->tm_year; mon = time->tm_mon + 1; /* tm_mon starts at zero */ day = time->tm_mday; hrs = time->tm_hour; min = time->tm_min; sec = time->tm_sec; if (yrs > 255) /* They are unsigned */ return -EINVAL; #ifdef CONFIG_MACH_DECSTATION real_yrs = yrs; leap_yr = ((!((yrs + 1900) % 4) && ((yrs + 1900) % 100)) || !((yrs + 1900) % 400)); yrs = 72; /* * We want to keep the year set to 73 until March * for non-leap years, so that Feb, 29th is handled * correctly. */ if (!leap_yr && mon < 3) { real_yrs--; yrs = 73; } #endif #ifdef CONFIG_ACPI if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && acpi_gbl_FADT.century) { century = (yrs + 1900) / 100; yrs %= 100; } #endif /* These limits and adjustments are independent of * whether the chip is in binary mode or not. */ if (yrs > 169) return -EINVAL; if (yrs >= 100) yrs -= 100; spin_lock_irqsave(&rtc_lock, flags); save_control = CMOS_READ(RTC_CONTROL); spin_unlock_irqrestore(&rtc_lock, flags); if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { sec = bin2bcd(sec); min = bin2bcd(min); hrs = bin2bcd(hrs); day = bin2bcd(day); mon = bin2bcd(mon); yrs = bin2bcd(yrs); century = bin2bcd(century); } spin_lock_irqsave(&rtc_lock, flags); save_control = CMOS_READ(RTC_CONTROL); CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); save_freq_select = CMOS_READ(RTC_FREQ_SELECT); if (apply_amd_register_a_behavior()) CMOS_WRITE((save_freq_select & ~RTC_AMD_BANK_SELECT), RTC_FREQ_SELECT); else CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); #ifdef CONFIG_MACH_DECSTATION CMOS_WRITE(real_yrs, RTC_DEC_YEAR); #endif CMOS_WRITE(yrs, RTC_YEAR); CMOS_WRITE(mon, RTC_MONTH); CMOS_WRITE(day, RTC_DAY_OF_MONTH); CMOS_WRITE(hrs, RTC_HOURS); CMOS_WRITE(min, RTC_MINUTES); CMOS_WRITE(sec, RTC_SECONDS); #ifdef CONFIG_ACPI if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && acpi_gbl_FADT.century) CMOS_WRITE(century, acpi_gbl_FADT.century); #endif CMOS_WRITE(save_control, RTC_CONTROL); CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); spin_unlock_irqrestore(&rtc_lock, flags); return 0; } EXPORT_SYMBOL_GPL(mc146818_set_time); |
| 13 13 13 13 13 13 25 11 5 2 1 6 5 5 13 13 13 13 13 8 5 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 | // SPDX-License-Identifier: GPL-2.0 /* * xfrm_input.c * * Changes: * YOSHIFUJI Hideaki @USAGI * Split up af-specific portion * */ #include <linux/bottom_half.h> #include <linux/cache.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/percpu.h> #include <net/dst.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ip_tunnels.h> #include <net/ip6_tunnel.h> #include <net/dst_metadata.h> #include <net/hotdata.h> #include "xfrm_inout.h" struct xfrm_trans_tasklet { struct work_struct work; spinlock_t queue_lock; struct sk_buff_head queue; }; struct xfrm_trans_cb { union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb); struct net *net; }; #define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0])) static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[2][AF_INET6 + 1]; static struct gro_cells gro_cells; static struct net_device xfrm_napi_dev; static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet); int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo) { int err = 0; if (WARN_ON(afinfo->family > AF_INET6)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_input_afinfo_lock); if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) err = -EEXIST; else rcu_assign_pointer(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], afinfo); spin_unlock_bh(&xfrm_input_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_input_register_afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo) { int err = 0; spin_lock_bh(&xfrm_input_afinfo_lock); if (likely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family])) { if (unlikely(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family] != afinfo)) err = -EINVAL; else RCU_INIT_POINTER(xfrm_input_afinfo[afinfo->is_ipip][afinfo->family], NULL); } spin_unlock_bh(&xfrm_input_afinfo_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL(xfrm_input_unregister_afinfo); static const struct xfrm_input_afinfo *xfrm_input_get_afinfo(u8 family, bool is_ipip) { const struct xfrm_input_afinfo *afinfo; if (WARN_ON_ONCE(family > AF_INET6)) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_input_afinfo[is_ipip][family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } static int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, u8 protocol, int err) { bool is_ipip = (protocol == IPPROTO_IPIP || protocol == IPPROTO_IPV6); const struct xfrm_input_afinfo *afinfo; int ret; afinfo = xfrm_input_get_afinfo(family, is_ipip); if (!afinfo) return -EAFNOSUPPORT; ret = afinfo->callback(skb, protocol, err); rcu_read_unlock(); return ret; } struct sec_path *secpath_set(struct sk_buff *skb) { struct sec_path *sp, *tmp = skb_ext_find(skb, SKB_EXT_SEC_PATH); sp = skb_ext_add(skb, SKB_EXT_SEC_PATH); if (!sp) return NULL; if (tmp) /* reused existing one (was COW'd if needed) */ return sp; /* allocated new secpath */ memset(sp->ovec, 0, sizeof(sp->ovec)); sp->olen = 0; sp->len = 0; sp->verified_cnt = 0; return sp; } EXPORT_SYMBOL(secpath_set); /* Fetch spi and seq from ipsec header */ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) { int offset, offset_seq; int hlen; switch (nexthdr) { case IPPROTO_AH: hlen = sizeof(struct ip_auth_hdr); offset = offsetof(struct ip_auth_hdr, spi); offset_seq = offsetof(struct ip_auth_hdr, seq_no); break; case IPPROTO_ESP: hlen = sizeof(struct ip_esp_hdr); offset = offsetof(struct ip_esp_hdr, spi); offset_seq = offsetof(struct ip_esp_hdr, seq_no); break; case IPPROTO_COMP: if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr))) return -EINVAL; *spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2))); *seq = 0; return 0; default: return 1; } if (!pskb_may_pull(skb, hlen)) return -EINVAL; *spi = *(__be32 *)(skb_transport_header(skb) + offset); *seq = *(__be32 *)(skb_transport_header(skb) + offset_seq); return 0; } EXPORT_SYMBOL(xfrm_parse_spi); static int xfrm4_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) { struct iphdr *iph; int optlen = 0; int err = -EINVAL; skb->protocol = htons(ETH_P_IP); if (unlikely(XFRM_MODE_SKB_CB(skb)->protocol == IPPROTO_BEETPH)) { struct ip_beet_phdr *ph; int phlen; if (!pskb_may_pull(skb, sizeof(*ph))) goto out; ph = (struct ip_beet_phdr *)skb->data; phlen = sizeof(*ph) + ph->padlen; optlen = ph->hdrlen * 8 + (IPV4_BEET_PHMAXLEN - phlen); if (optlen < 0 || optlen & 3 || optlen > 250) goto out; XFRM_MODE_SKB_CB(skb)->protocol = ph->nexthdr; if (!pskb_may_pull(skb, phlen)) goto out; __skb_pull(skb, phlen); } skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); xfrm4_beet_make_header(skb); iph = ip_hdr(skb); iph->ihl += optlen / 4; iph->tot_len = htons(skb->len); iph->daddr = x->sel.daddr.a4; iph->saddr = x->sel.saddr.a4; iph->check = 0; iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl); err = 0; out: return err; } static void ipip_ecn_decapsulate(struct sk_buff *skb) { struct iphdr *inner_iph = ipip_hdr(skb); if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) IP_ECN_set_ce(inner_iph); } static int xfrm4_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; skb->protocol = htons(ETH_P_IP); if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) ipv4_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipip_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip_ecn_decapsulate(skb); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); if (skb->mac_len) eth_hdr(skb)->h_proto = skb->protocol; err = 0; out: return err; } static void ipip6_ecn_decapsulate(struct sk_buff *skb) { struct ipv6hdr *inner_iph = ipipv6_hdr(skb); if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) IP6_ECN_set_ce(skb, inner_iph); } static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; skb->protocol = htons(ETH_P_IPV6); if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); if (skb->mac_len) eth_hdr(skb)->h_proto = skb->protocol; err = 0; out: return err; } static int xfrm6_remove_beet_encap(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *ip6h; int size = sizeof(struct ipv6hdr); int err; skb->protocol = htons(ETH_P_IPV6); err = skb_cow_head(skb, size + skb->mac_len); if (err) goto out; __skb_push(skb, size); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); xfrm6_beet_make_header(skb); ip6h = ipv6_hdr(skb); ip6h->payload_len = htons(skb->len - size); ip6h->daddr = x->sel.daddr.in6; ip6h->saddr = x->sel.saddr.in6; err = 0; out: return err; } /* Remove encapsulation header. * * The IP header will be moved over the top of the encapsulation * header. * * On entry, the transport header shall point to where the IP header * should be and the network header shall be set to where the IP * header currently is. skb->data shall point to the start of the * payload. */ static int xfrm_inner_mode_encap_remove(struct xfrm_state *x, struct sk_buff *skb) { switch (x->props.mode) { case XFRM_MODE_BEET: switch (x->sel.family) { case AF_INET: return xfrm4_remove_beet_encap(x, skb); case AF_INET6: return xfrm6_remove_beet_encap(x, skb); } break; case XFRM_MODE_TUNNEL: switch (XFRM_MODE_SKB_CB(skb)->protocol) { case IPPROTO_IPIP: return xfrm4_remove_tunnel_encap(x, skb); case IPPROTO_IPV6: return xfrm6_remove_tunnel_encap(x, skb); break; } return -EINVAL; } WARN_ON_ONCE(1); return -EOPNOTSUPP; } static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb) { switch (x->props.family) { case AF_INET: xfrm4_extract_header(skb); break; case AF_INET6: xfrm6_extract_header(skb); break; default: WARN_ON_ONCE(1); return -EAFNOSUPPORT; } return xfrm_inner_mode_encap_remove(x, skb); } /* Remove encapsulation header. * * The IP header will be moved over the top of the encapsulation header. * * On entry, skb_transport_header() shall point to where the IP header * should be and skb_network_header() shall be set to where the IP header * currently is. skb->data shall point to the start of the payload. */ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb) { struct xfrm_offload *xo = xfrm_offload(skb); int ihl = skb->data - skb_transport_header(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), skb_network_header(skb), ihl); if (xo) xo->orig_mac_len = skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0; skb->network_header = skb->transport_header; } ip_hdr(skb)->tot_len = htons(skb->len + ihl); skb_reset_transport_header(skb); return 0; } static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) struct xfrm_offload *xo = xfrm_offload(skb); int ihl = skb->data - skb_transport_header(skb); if (skb->transport_header != skb->network_header) { memmove(skb_transport_header(skb), skb_network_header(skb), ihl); if (xo) xo->orig_mac_len = skb_mac_header_was_set(skb) ? skb_mac_header_len(skb) : 0; skb->network_header = skb->transport_header; } ipv6_hdr(skb)->payload_len = htons(skb->len + ihl - sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); return 0; #else WARN_ON_ONCE(1); return -EAFNOSUPPORT; #endif } static int xfrm_inner_mode_input(struct xfrm_state *x, struct sk_buff *skb) { switch (x->props.mode) { case XFRM_MODE_BEET: case XFRM_MODE_TUNNEL: return xfrm_prepare_input(x, skb); case XFRM_MODE_TRANSPORT: if (x->props.family == AF_INET) return xfrm4_transport_input(x, skb); if (x->props.family == AF_INET6) return xfrm6_transport_input(x, skb); break; case XFRM_MODE_ROUTEOPTIMIZATION: WARN_ON_ONCE(1); break; default: WARN_ON_ONCE(1); break; } return -EOPNOTSUPP; } int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { const struct xfrm_state_afinfo *afinfo; struct net *net = dev_net(skb->dev); int err; __be32 seq; __be32 seq_hi; struct xfrm_state *x = NULL; xfrm_address_t *daddr; u32 mark = skb->mark; unsigned int family = AF_UNSPEC; int decaps = 0; int async = 0; bool xfrm_gro = false; bool crypto_done = false; struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; if (encap_type < 0 || (xo && xo->flags & XFRM_GRO)) { x = xfrm_input_state(skb); if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); goto drop; } if (unlikely(x->km.state != XFRM_STATE_VALID)) { if (x->km.state == XFRM_STATE_ACQ) XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); else XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); if (encap_type == -1) dev_put(skb->dev); goto drop; } family = x->props.family; /* An encap_type of -1 indicates async resumption. */ if (encap_type == -1) { async = 1; seq = XFRM_SKB_CB(skb)->seq.input.low; goto resume; } /* GRO call */ seq = XFRM_SPI_SKB_CB(skb)->seq; if (xo && (xo->flags & CRYPTO_DONE)) { crypto_done = true; family = XFRM_SPI_SKB_CB(skb)->family; if (!(xo->status & CRYPTO_SUCCESS)) { if (xo->status & (CRYPTO_TRANSPORT_AH_AUTH_FAILED | CRYPTO_TRANSPORT_ESP_AUTH_FAILED | CRYPTO_TUNNEL_AH_AUTH_FAILED | CRYPTO_TUNNEL_ESP_AUTH_FAILED)) { xfrm_audit_state_icvfail(x, skb, x->type->proto); x->stats.integrity_failed++; XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR); goto drop; } if (xo->status & CRYPTO_INVALID_PROTOCOL) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR); goto drop; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } if (xfrm_parse_spi(skb, nexthdr, &spi, &seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } } goto lock; } family = XFRM_SPI_SKB_CB(skb)->family; /* if tunnel is present override skb->mark value with tunnel i_key */ switch (family) { case AF_INET: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key); break; case AF_INET6: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6) mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key); break; } sp = secpath_set(skb); if (!sp) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; } seq = 0; if (!spi && xfrm_parse_spi(skb, nexthdr, &spi, &seq)) { secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } daddr = (xfrm_address_t *)(skb_network_header(skb) + XFRM_SPI_SKB_CB(skb)->daddroff); do { sp = skb_sec_path(skb); if (sp->len == XFRM_MAX_DEPTH) { secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family); if (x == NULL) { secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); goto drop; } if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); xfrm_state_put(x); goto drop; } skb->mark = xfrm_smark_get(skb->mark, x); sp->xvec[sp->len++] = x; skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; } lock: spin_lock(&x->lock); if (unlikely(x->km.state != XFRM_STATE_VALID)) { if (x->km.state == XFRM_STATE_ACQ) XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); else XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); goto drop_unlock; } if ((x->encap ? x->encap->encap_type : 0) != encap_type) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); goto drop_unlock; } if (xfrm_replay_check(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } if (xfrm_state_check_expire(x)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEEXPIRED); goto drop_unlock; } spin_unlock(&x->lock); if (xfrm_tunnel_check(skb, x, family)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } seq_hi = htonl(xfrm_replay_seqhi(x, seq)); XFRM_SKB_CB(skb)->seq.input.low = seq; XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; dev_hold(skb->dev); if (crypto_done) nexthdr = x->type_offload->input_tail(x, skb); else nexthdr = x->type->input(x, skb); if (nexthdr == -EINPROGRESS) return 0; resume: dev_put(skb->dev); spin_lock(&x->lock); if (nexthdr < 0) { if (nexthdr == -EBADMSG) { xfrm_audit_state_icvfail(x, skb, x->type->proto); x->stats.integrity_failed++; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR); goto drop_unlock; } /* only the first xfrm gets the encap type */ encap_type = 0; if (xfrm_replay_recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } xfrm_replay_advance(x, seq); x->curlft.bytes += skb->len; x->curlft.packets++; x->lastused = ktime_get_real_seconds(); spin_unlock(&x->lock); XFRM_MODE_SKB_CB(skb)->protocol = nexthdr; if (xfrm_inner_mode_input(x, skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL) { decaps = 1; break; } /* * We need the inner address. However, we only get here for * transport mode so the outer address is identical. */ daddr = &x->id.daddr; family = x->props.family; err = xfrm_parse_spi(skb, nexthdr, &spi, &seq); if (err < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } crypto_done = false; } while (!err); err = xfrm_rcv_cb(skb, family, x->type->proto, 0); if (err) goto drop; nf_reset_ct(skb); if (decaps) { sp = skb_sec_path(skb); if (sp) sp->olen = 0; if (skb_valid_dst(skb)) skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return 0; } else { xo = xfrm_offload(skb); if (xo) xfrm_gro = xo->flags & XFRM_GRO; err = -EAFNOSUPPORT; rcu_read_lock(); afinfo = xfrm_state_afinfo_get_rcu(x->props.family); if (likely(afinfo)) err = afinfo->transport_finish(skb, xfrm_gro || async); rcu_read_unlock(); if (xfrm_gro) { sp = skb_sec_path(skb); if (sp) sp->olen = 0; if (skb_valid_dst(skb)) skb_dst_drop(skb); gro_cells_receive(&gro_cells, skb); return err; } return err; } drop_unlock: spin_unlock(&x->lock); drop: xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1); kfree_skb(skb); return 0; } EXPORT_SYMBOL(xfrm_input); int xfrm_input_resume(struct sk_buff *skb, int nexthdr) { return xfrm_input(skb, nexthdr, 0, -1); } EXPORT_SYMBOL(xfrm_input_resume); static void xfrm_trans_reinject(struct work_struct *work) { struct xfrm_trans_tasklet *trans = container_of(work, struct xfrm_trans_tasklet, work); struct sk_buff_head queue; struct sk_buff *skb; __skb_queue_head_init(&queue); spin_lock_bh(&trans->queue_lock); skb_queue_splice_init(&trans->queue, &queue); spin_unlock_bh(&trans->queue_lock); local_bh_disable(); while ((skb = __skb_dequeue(&queue))) XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net, NULL, skb); local_bh_enable(); } int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)) { struct xfrm_trans_tasklet *trans; trans = this_cpu_ptr(&xfrm_trans_tasklet); if (skb_queue_len(&trans->queue) >= READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); XFRM_TRANS_SKB_CB(skb)->finish = finish; XFRM_TRANS_SKB_CB(skb)->net = net; spin_lock_bh(&trans->queue_lock); __skb_queue_tail(&trans->queue, skb); spin_unlock_bh(&trans->queue_lock); schedule_work(&trans->work); return 0; } EXPORT_SYMBOL(xfrm_trans_queue_net); int xfrm_trans_queue(struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)) { return xfrm_trans_queue_net(dev_net(skb->dev), skb, finish); } EXPORT_SYMBOL(xfrm_trans_queue); void __init xfrm_input_init(void) { int err; int i; init_dummy_netdev(&xfrm_napi_dev); err = gro_cells_init(&gro_cells, &xfrm_napi_dev); if (err) gro_cells.cells = NULL; for_each_possible_cpu(i) { struct xfrm_trans_tasklet *trans; trans = &per_cpu(xfrm_trans_tasklet, i); spin_lock_init(&trans->queue_lock); __skb_queue_head_init(&trans->queue); INIT_WORK(&trans->work, xfrm_trans_reinject); } } |
| 1508 1507 1505 1508 1509 6 1495 20 19 1 12 11 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/ipv6.h> #include <linux/in6.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/icmp.h> #include <linux/rcupdate.h> #include <linux/sysctl.h> #include <net/ipv6_frag.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> #endif #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> static DEFINE_MUTEX(defrag6_mutex); static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, struct sk_buff *skb) { u16 zone_id = NF_CT_DEFAULT_ZONE_ID; #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (skb_nfct(skb)) { enum ip_conntrack_info ctinfo; const struct nf_conn *ct = nf_ct_get(skb, &ctinfo); zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); } #endif if (nf_bridge_in_prerouting(skb)) return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id; if (hooknum == NF_INET_PRE_ROUTING) return IP6_DEFRAG_CONNTRACK_IN + zone_id; else return IP6_DEFRAG_CONNTRACK_OUT + zone_id; } static unsigned int ipv6_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int err; #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Previously seen (loopback)? */ if (skb_nfct(skb) && !nf_ct_is_template((struct nf_conn *)skb_nfct(skb))) return NF_ACCEPT; if (skb->_nfct == IP_CT_UNTRACKED) return NF_ACCEPT; #endif err = nf_ct_frag6_gather(state->net, skb, nf_ct6_defrag_user(state->hook, skb)); /* queued */ if (err == -EINPROGRESS) return NF_STOLEN; return err == 0 ? NF_ACCEPT : NF_DROP; } static const struct nf_hook_ops ipv6_defrag_ops[] = { { .hook = ipv6_defrag, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv6_defrag, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, }; static void __net_exit defrag6_net_exit(struct net *net) { if (net->nf.defrag_ipv6_users) { nf_unregister_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); net->nf.defrag_ipv6_users = 0; } } static const struct nf_defrag_hook defrag_hook = { .owner = THIS_MODULE, .enable = nf_defrag_ipv6_enable, .disable = nf_defrag_ipv6_disable, }; static struct pernet_operations defrag6_net_ops = { .exit = defrag6_net_exit, }; static int __init nf_defrag_init(void) { int ret = 0; ret = nf_ct_frag6_init(); if (ret < 0) { pr_err("nf_defrag_ipv6: can't initialize frag6.\n"); return ret; } ret = register_pernet_subsys(&defrag6_net_ops); if (ret < 0) { pr_err("nf_defrag_ipv6: can't register pernet ops\n"); goto cleanup_frag6; } rcu_assign_pointer(nf_defrag_v6_hook, &defrag_hook); return ret; cleanup_frag6: nf_ct_frag6_cleanup(); return ret; } static void __exit nf_defrag_fini(void) { rcu_assign_pointer(nf_defrag_v6_hook, NULL); unregister_pernet_subsys(&defrag6_net_ops); nf_ct_frag6_cleanup(); } int nf_defrag_ipv6_enable(struct net *net) { int err = 0; mutex_lock(&defrag6_mutex); if (net->nf.defrag_ipv6_users == UINT_MAX) { err = -EOVERFLOW; goto out_unlock; } if (net->nf.defrag_ipv6_users) { net->nf.defrag_ipv6_users++; goto out_unlock; } err = nf_register_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); if (err == 0) net->nf.defrag_ipv6_users = 1; out_unlock: mutex_unlock(&defrag6_mutex); return err; } EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable); void nf_defrag_ipv6_disable(struct net *net) { mutex_lock(&defrag6_mutex); if (net->nf.defrag_ipv6_users) { net->nf.defrag_ipv6_users--; if (net->nf.defrag_ipv6_users == 0) nf_unregister_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); } mutex_unlock(&defrag6_mutex); } EXPORT_SYMBOL_GPL(nf_defrag_ipv6_disable); module_init(nf_defrag_init); module_exit(nf_defrag_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IPv6 defragmentation support"); |
| 3 8 2 1 8 7 1 6 2 6 2 6 2 8 7 1 8 7 1 8 6 1 1 8 8 8 8 112 33 112 3 1 2 2 2 2 1 2 1 2 5 3 14 1 1 2 2 2 2 580 294 52 45 15 112 112 96 2 56 42 37 61 25 71 2 65 8 72 52 52 46 46 52 28 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 | // SPDX-License-Identifier: GPL-2.0-only /* * This file contains functions assisting in mapping VFS to 9P2000 * * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/parser.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include "v9fs.h" #include "v9fs_vfs.h" #include "cache.h" static DEFINE_SPINLOCK(v9fs_sessionlist_lock); static LIST_HEAD(v9fs_sessionlist); struct kmem_cache *v9fs_inode_cache; /* * Option Parsing (code inspired by NFS code) * NOTE: each transport will parse its own options */ enum { /* Options that take integer arguments */ Opt_debug, Opt_dfltuid, Opt_dfltgid, Opt_afid, /* String options */ Opt_uname, Opt_remotename, Opt_cache, Opt_cachetag, /* Options that take no arguments */ Opt_nodevmap, Opt_noxattr, Opt_directio, Opt_ignoreqv, /* Access options */ Opt_access, Opt_posixacl, /* Lock timeout option */ Opt_locktimeout, /* Error token */ Opt_err }; static const match_table_t tokens = { {Opt_debug, "debug=%x"}, {Opt_dfltuid, "dfltuid=%u"}, {Opt_dfltgid, "dfltgid=%u"}, {Opt_afid, "afid=%u"}, {Opt_uname, "uname=%s"}, {Opt_remotename, "aname=%s"}, {Opt_nodevmap, "nodevmap"}, {Opt_noxattr, "noxattr"}, {Opt_directio, "directio"}, {Opt_ignoreqv, "ignoreqv"}, {Opt_cache, "cache=%s"}, {Opt_cachetag, "cachetag=%s"}, {Opt_access, "access=%s"}, {Opt_posixacl, "posixacl"}, {Opt_locktimeout, "locktimeout=%u"}, {Opt_err, NULL} }; /* Interpret mount options for cache mode */ static int get_cache_mode(char *s) { int version = -EINVAL; if (!strcmp(s, "loose")) { version = CACHE_SC_LOOSE; p9_debug(P9_DEBUG_9P, "Cache mode: loose\n"); } else if (!strcmp(s, "fscache")) { version = CACHE_SC_FSCACHE; p9_debug(P9_DEBUG_9P, "Cache mode: fscache\n"); } else if (!strcmp(s, "mmap")) { version = CACHE_SC_MMAP; p9_debug(P9_DEBUG_9P, "Cache mode: mmap\n"); } else if (!strcmp(s, "readahead")) { version = CACHE_SC_READAHEAD; p9_debug(P9_DEBUG_9P, "Cache mode: readahead\n"); } else if (!strcmp(s, "none")) { version = CACHE_SC_NONE; p9_debug(P9_DEBUG_9P, "Cache mode: none\n"); } else if (kstrtoint(s, 0, &version) != 0) { version = -EINVAL; pr_info("Unknown Cache mode or invalid value %s\n", s); } return version; } /* * Display the mount options in /proc/mounts. */ int v9fs_show_options(struct seq_file *m, struct dentry *root) { struct v9fs_session_info *v9ses = root->d_sb->s_fs_info; if (v9ses->debug) seq_printf(m, ",debug=%x", v9ses->debug); if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID)) seq_printf(m, ",dfltuid=%u", from_kuid_munged(&init_user_ns, v9ses->dfltuid)); if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID)) seq_printf(m, ",dfltgid=%u", from_kgid_munged(&init_user_ns, v9ses->dfltgid)); if (v9ses->afid != ~0) seq_printf(m, ",afid=%u", v9ses->afid); if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0) seq_printf(m, ",uname=%s", v9ses->uname); if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0) seq_printf(m, ",aname=%s", v9ses->aname); if (v9ses->nodev) seq_puts(m, ",nodevmap"); if (v9ses->cache) seq_printf(m, ",cache=%x", v9ses->cache); #ifdef CONFIG_9P_FSCACHE if (v9ses->cachetag && (v9ses->cache & CACHE_FSCACHE)) seq_printf(m, ",cachetag=%s", v9ses->cachetag); #endif switch (v9ses->flags & V9FS_ACCESS_MASK) { case V9FS_ACCESS_USER: seq_puts(m, ",access=user"); break; case V9FS_ACCESS_ANY: seq_puts(m, ",access=any"); break; case V9FS_ACCESS_CLIENT: seq_puts(m, ",access=client"); break; case V9FS_ACCESS_SINGLE: seq_printf(m, ",access=%u", from_kuid_munged(&init_user_ns, v9ses->uid)); break; } if (v9ses->flags & V9FS_IGNORE_QV) seq_puts(m, ",ignoreqv"); if (v9ses->flags & V9FS_DIRECT_IO) seq_puts(m, ",directio"); if (v9ses->flags & V9FS_POSIX_ACL) seq_puts(m, ",posixacl"); if (v9ses->flags & V9FS_NO_XATTR) seq_puts(m, ",noxattr"); return p9_show_client_options(m, v9ses->clnt); } /** * v9fs_parse_options - parse mount options into session structure * @v9ses: existing v9fs session information * @opts: The mount option string * * Return 0 upon success, -ERRNO upon failure. */ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) { char *options, *tmp_options; substring_t args[MAX_OPT_ARGS]; char *p; int option = 0; char *s; int ret = 0; /* setup defaults */ v9ses->afid = ~0; v9ses->debug = 0; v9ses->cache = CACHE_NONE; #ifdef CONFIG_9P_FSCACHE v9ses->cachetag = NULL; #endif v9ses->session_lock_timeout = P9_LOCK_TIMEOUT; if (!opts) return 0; tmp_options = kstrdup(opts, GFP_KERNEL); if (!tmp_options) { ret = -ENOMEM; goto fail_option_alloc; } options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token, r; if (!*p) continue; token = match_token(p, tokens, args); switch (token) { case Opt_debug: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; } else { v9ses->debug = option; #ifdef CONFIG_NET_9P_DEBUG p9_debug_level = option; #endif } break; case Opt_dfltuid: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } v9ses->dfltuid = make_kuid(current_user_ns(), option); if (!uid_valid(v9ses->dfltuid)) { p9_debug(P9_DEBUG_ERROR, "uid field, but not a uid?\n"); ret = -EINVAL; } break; case Opt_dfltgid: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } v9ses->dfltgid = make_kgid(current_user_ns(), option); if (!gid_valid(v9ses->dfltgid)) { p9_debug(P9_DEBUG_ERROR, "gid field, but not a gid?\n"); ret = -EINVAL; } break; case Opt_afid: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; } else { v9ses->afid = option; } break; case Opt_uname: kfree(v9ses->uname); v9ses->uname = match_strdup(&args[0]); if (!v9ses->uname) { ret = -ENOMEM; goto free_and_return; } break; case Opt_remotename: kfree(v9ses->aname); v9ses->aname = match_strdup(&args[0]); if (!v9ses->aname) { ret = -ENOMEM; goto free_and_return; } break; case Opt_nodevmap: v9ses->nodev = 1; break; case Opt_noxattr: v9ses->flags |= V9FS_NO_XATTR; break; case Opt_directio: v9ses->flags |= V9FS_DIRECT_IO; break; case Opt_ignoreqv: v9ses->flags |= V9FS_IGNORE_QV; break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE kfree(v9ses->cachetag); v9ses->cachetag = match_strdup(&args[0]); if (!v9ses->cachetag) { ret = -ENOMEM; goto free_and_return; } #endif break; case Opt_cache: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of cache arg\n"); goto free_and_return; } r = get_cache_mode(s); if (r < 0) ret = r; else v9ses->cache = r; kfree(s); break; case Opt_access: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of access arg\n"); goto free_and_return; } v9ses->flags &= ~V9FS_ACCESS_MASK; if (strcmp(s, "user") == 0) v9ses->flags |= V9FS_ACCESS_USER; else if (strcmp(s, "any") == 0) v9ses->flags |= V9FS_ACCESS_ANY; else if (strcmp(s, "client") == 0) { v9ses->flags |= V9FS_ACCESS_CLIENT; } else { uid_t uid; v9ses->flags |= V9FS_ACCESS_SINGLE; r = kstrtouint(s, 10, &uid); if (r) { ret = r; pr_info("Unknown access argument %s: %d\n", s, r); kfree(s); continue; } v9ses->uid = make_kuid(current_user_ns(), uid); if (!uid_valid(v9ses->uid)) { ret = -EINVAL; pr_info("Unknown uid %s\n", s); } } kfree(s); break; case Opt_posixacl: #ifdef CONFIG_9P_FS_POSIX_ACL v9ses->flags |= V9FS_POSIX_ACL; #else p9_debug(P9_DEBUG_ERROR, "Not defined CONFIG_9P_FS_POSIX_ACL. Ignoring posixacl option\n"); #endif break; case Opt_locktimeout: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } if (option < 1) { p9_debug(P9_DEBUG_ERROR, "locktimeout must be a greater than zero integer.\n"); ret = -EINVAL; continue; } v9ses->session_lock_timeout = (long)option * HZ; break; default: continue; } } free_and_return: kfree(tmp_options); fail_option_alloc: return ret; } /** * v9fs_session_init - initialize session * @v9ses: session information structure * @dev_name: device being mounted * @data: options * */ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, const char *dev_name, char *data) { struct p9_fid *fid; int rc = -ENOMEM; v9ses->uname = kstrdup(V9FS_DEFUSER, GFP_KERNEL); if (!v9ses->uname) goto err_names; v9ses->aname = kstrdup(V9FS_DEFANAME, GFP_KERNEL); if (!v9ses->aname) goto err_names; init_rwsem(&v9ses->rename_sem); v9ses->uid = INVALID_UID; v9ses->dfltuid = V9FS_DEFUID; v9ses->dfltgid = V9FS_DEFGID; v9ses->clnt = p9_client_create(dev_name, data); if (IS_ERR(v9ses->clnt)) { rc = PTR_ERR(v9ses->clnt); p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n"); goto err_names; } v9ses->flags = V9FS_ACCESS_USER; if (p9_is_proto_dotl(v9ses->clnt)) { v9ses->flags = V9FS_ACCESS_CLIENT; v9ses->flags |= V9FS_PROTO_2000L; } else if (p9_is_proto_dotu(v9ses->clnt)) { v9ses->flags |= V9FS_PROTO_2000U; } rc = v9fs_parse_options(v9ses, data); if (rc < 0) goto err_clnt; v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ; if (!v9fs_proto_dotl(v9ses) && ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) { /* * We support ACCESS_CLIENT only for dotl. * Fall back to ACCESS_USER */ v9ses->flags &= ~V9FS_ACCESS_MASK; v9ses->flags |= V9FS_ACCESS_USER; } /*FIXME !! */ /* for legacy mode, fall back to V9FS_ACCESS_ANY */ if (!(v9fs_proto_dotu(v9ses) || v9fs_proto_dotl(v9ses)) && ((v9ses->flags&V9FS_ACCESS_MASK) == V9FS_ACCESS_USER)) { v9ses->flags &= ~V9FS_ACCESS_MASK; v9ses->flags |= V9FS_ACCESS_ANY; v9ses->uid = INVALID_UID; } if (!v9fs_proto_dotl(v9ses) || !((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_CLIENT)) { /* * We support ACL checks on clinet only if the protocol is * 9P2000.L and access is V9FS_ACCESS_CLIENT. */ v9ses->flags &= ~V9FS_ACL_MASK; } fid = p9_client_attach(v9ses->clnt, NULL, v9ses->uname, INVALID_UID, v9ses->aname); if (IS_ERR(fid)) { rc = PTR_ERR(fid); p9_debug(P9_DEBUG_ERROR, "cannot attach\n"); goto err_clnt; } if ((v9ses->flags & V9FS_ACCESS_MASK) == V9FS_ACCESS_SINGLE) fid->uid = v9ses->uid; else fid->uid = INVALID_UID; #ifdef CONFIG_9P_FSCACHE /* register the session for caching */ if (v9ses->cache & CACHE_FSCACHE) { rc = v9fs_cache_session_get_cookie(v9ses, dev_name); if (rc < 0) goto err_clnt; } #endif spin_lock(&v9fs_sessionlist_lock); list_add(&v9ses->slist, &v9fs_sessionlist); spin_unlock(&v9fs_sessionlist_lock); return fid; err_clnt: #ifdef CONFIG_9P_FSCACHE kfree(v9ses->cachetag); #endif p9_client_destroy(v9ses->clnt); err_names: kfree(v9ses->uname); kfree(v9ses->aname); return ERR_PTR(rc); } /** * v9fs_session_close - shutdown a session * @v9ses: session information structure * */ void v9fs_session_close(struct v9fs_session_info *v9ses) { if (v9ses->clnt) { p9_client_destroy(v9ses->clnt); v9ses->clnt = NULL; } #ifdef CONFIG_9P_FSCACHE fscache_relinquish_volume(v9fs_session_cache(v9ses), NULL, false); kfree(v9ses->cachetag); #endif kfree(v9ses->uname); kfree(v9ses->aname); spin_lock(&v9fs_sessionlist_lock); list_del(&v9ses->slist); spin_unlock(&v9fs_sessionlist_lock); } /** * v9fs_session_cancel - terminate a session * @v9ses: session to terminate * * mark transport as disconnected and cancel all pending requests. */ void v9fs_session_cancel(struct v9fs_session_info *v9ses) { p9_debug(P9_DEBUG_ERROR, "cancel session %p\n", v9ses); p9_client_disconnect(v9ses->clnt); } /** * v9fs_session_begin_cancel - Begin terminate of a session * @v9ses: session to terminate * * After this call we don't allow any request other than clunk. */ void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses) { p9_debug(P9_DEBUG_ERROR, "begin cancel session %p\n", v9ses); p9_client_begin_disconnect(v9ses->clnt); } static struct kobject *v9fs_kobj; #ifdef CONFIG_9P_FSCACHE /* * List caches associated with a session */ static ssize_t caches_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { ssize_t n = 0, count = 0, limit = PAGE_SIZE; struct v9fs_session_info *v9ses; spin_lock(&v9fs_sessionlist_lock); list_for_each_entry(v9ses, &v9fs_sessionlist, slist) { if (v9ses->cachetag) { n = snprintf(buf, limit, "%s\n", v9ses->cachetag); if (n < 0) { count = n; break; } count += n; limit -= n; } } spin_unlock(&v9fs_sessionlist_lock); return count; } static struct kobj_attribute v9fs_attr_cache = __ATTR_RO(caches); #endif /* CONFIG_9P_FSCACHE */ static struct attribute *v9fs_attrs[] = { #ifdef CONFIG_9P_FSCACHE &v9fs_attr_cache.attr, #endif NULL, }; static const struct attribute_group v9fs_attr_group = { .attrs = v9fs_attrs, }; /** * v9fs_sysfs_init - Initialize the v9fs sysfs interface * */ static int __init v9fs_sysfs_init(void) { v9fs_kobj = kobject_create_and_add("9p", fs_kobj); if (!v9fs_kobj) return -ENOMEM; if (sysfs_create_group(v9fs_kobj, &v9fs_attr_group)) { kobject_put(v9fs_kobj); return -ENOMEM; } return 0; } /** * v9fs_sysfs_cleanup - Unregister the v9fs sysfs interface * */ static void v9fs_sysfs_cleanup(void) { sysfs_remove_group(v9fs_kobj, &v9fs_attr_group); kobject_put(v9fs_kobj); } static void v9fs_inode_init_once(void *foo) { struct v9fs_inode *v9inode = (struct v9fs_inode *)foo; memset(&v9inode->qid, 0, sizeof(v9inode->qid)); inode_init_once(&v9inode->netfs.inode); } /** * v9fs_init_inode_cache - initialize a cache for 9P * Returns 0 on success. */ static int v9fs_init_inode_cache(void) { v9fs_inode_cache = kmem_cache_create("v9fs_inode_cache", sizeof(struct v9fs_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), v9fs_inode_init_once); if (!v9fs_inode_cache) return -ENOMEM; return 0; } /** * v9fs_destroy_inode_cache - destroy the cache of 9P inode * */ static void v9fs_destroy_inode_cache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(v9fs_inode_cache); } static int v9fs_cache_register(void) { int ret; ret = v9fs_init_inode_cache(); if (ret < 0) return ret; return ret; } static void v9fs_cache_unregister(void) { v9fs_destroy_inode_cache(); } /** * init_v9fs - Initialize module * */ static int __init init_v9fs(void) { int err; pr_info("Installing v9fs 9p2000 file system support\n"); /* TODO: Setup list of registered trasnport modules */ err = v9fs_cache_register(); if (err < 0) { pr_err("Failed to register v9fs for caching\n"); return err; } err = v9fs_sysfs_init(); if (err < 0) { pr_err("Failed to register with sysfs\n"); goto out_cache; } err = register_filesystem(&v9fs_fs_type); if (err < 0) { pr_err("Failed to register filesystem\n"); goto out_sysfs_cleanup; } return 0; out_sysfs_cleanup: v9fs_sysfs_cleanup(); out_cache: v9fs_cache_unregister(); return err; } /** * exit_v9fs - shutdown module * */ static void __exit exit_v9fs(void) { v9fs_sysfs_cleanup(); v9fs_cache_unregister(); unregister_filesystem(&v9fs_fs_type); } module_init(init_v9fs) module_exit(exit_v9fs) MODULE_AUTHOR("Latchesar Ionkov <lucho@ionkov.net>"); MODULE_AUTHOR("Eric Van Hensbergen <ericvh@gmail.com>"); MODULE_AUTHOR("Ron Minnich <rminnich@lanl.gov>"); MODULE_DESCRIPTION("9P Client File System"); MODULE_LICENSE("GPL"); |
| 2 1 1 6 2 2 1 1 33 33 4 5 5 4 1 3 3 4 4 2 1 1 6 4 3 5 8 3 5 8 3 9 9 9 9 8 10 10 13 10 5 8 8 10 13 4 9 6 10 6 6 6 18 18 18 2 18 18 25 25 16 1 15 15 2 15 15 15 15 15 11 1 9 10 10 3 3 3 3 27 27 11 16 27 18 2 12 1 26 7 1 1 1 1 1 47 69 64 1 4 2 1 52 13 58 6 1 35 8 27 28 1 3 2 42 42 7 35 35 35 4 1 30 32 2 2 32 63 55 2 6 5 1 41 19 2 1 15 44 12 2 4 45 3 50 4 48 6 44 8 2 44 8 40 5 5 39 1 3 7 45 3 1 47 2 6 36 2 3 24 9 7 6 10 30 46 5 17 32 7 3 7 4 3 4 4 3 16 9 7 7 7 7 7 51 104 2 2 88 75 1 1 1 103 1 104 1351 1352 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 | // SPDX-License-Identifier: GPL-2.0-only /* * GENEVE: Generic Network Virtualization Encapsulation * * Copyright (c) 2015 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/hash.h> #include <net/ipv6_stubs.h> #include <net/dst_metadata.h> #include <net/gro_cells.h> #include <net/rtnetlink.h> #include <net/geneve.h> #include <net/gro.h> #include <net/protocol.h> #define GENEVE_NETDEV_VER "0.6" #define GENEVE_N_VID (1u << 24) #define GENEVE_VID_MASK (GENEVE_N_VID - 1) #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) 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"); #define GENEVE_VER 0 #define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr)) #define GENEVE_IPV4_HLEN (ETH_HLEN + sizeof(struct iphdr) + GENEVE_BASE_HLEN) #define GENEVE_IPV6_HLEN (ETH_HLEN + sizeof(struct ipv6hdr) + GENEVE_BASE_HLEN) /* per-network namespace private data for this module */ struct geneve_net { struct list_head geneve_list; struct list_head sock_list; }; static unsigned int geneve_net_id; struct geneve_dev_node { struct hlist_node hlist; struct geneve_dev *geneve; }; struct geneve_config { struct ip_tunnel_info info; bool collect_md; bool use_udp6_rx_checksums; bool ttl_inherit; enum ifla_geneve_df df; bool inner_proto_inherit; }; /* Pseudo network device */ struct geneve_dev { struct geneve_dev_node hlist4; /* vni hash table for IPv4 socket */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_dev_node hlist6; /* vni hash table for IPv6 socket */ #endif struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for geneve tunnel */ struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */ #endif struct list_head next; /* geneve's per namespace list */ struct gro_cells gro_cells; struct geneve_config cfg; }; struct geneve_sock { bool collect_md; struct list_head list; struct socket *sock; struct rcu_head rcu; int refcnt; struct hlist_head vni_list[VNI_HASH_SIZE]; }; static inline __u32 geneve_net_vni_hash(u8 vni[3]) { __u32 vnid; vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2]; return hash_32(vnid, VNI_HASH_BITS); } static __be64 vni_to_tunnel_id(const __u8 *vni) { #ifdef __BIG_ENDIAN return (vni[0] << 16) | (vni[1] << 8) | vni[2]; #else return (__force __be64)(((__force u64)vni[0] << 40) | ((__force u64)vni[1] << 48) | ((__force u64)vni[2] << 56)); #endif } /* Convert 64 bit tunnel ID to 24 bit VNI. */ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) { #ifdef __BIG_ENDIAN vni[0] = (__force __u8)(tun_id >> 16); vni[1] = (__force __u8)(tun_id >> 8); vni[2] = (__force __u8)tun_id; #else vni[0] = (__force __u8)((__force u64)tun_id >> 40); vni[1] = (__force __u8)((__force u64)tun_id >> 48); vni[2] = (__force __u8)((__force u64)tun_id >> 56); #endif } static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni) { return !memcmp(vni, &tun_id[5], 3); } static sa_family_t geneve_get_sk_family(struct geneve_sock *gs) { return gs->sock->sk->sk_family; } static struct geneve_dev *geneve_lookup(struct geneve_sock *gs, __be32 addr, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && addr == node->geneve->cfg.info.key.u.ipv4.dst) return node->geneve; } return NULL; } #if IS_ENABLED(CONFIG_IPV6) static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs, struct in6_addr addr6, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && ipv6_addr_equal(&addr6, &node->geneve->cfg.info.key.u.ipv6.dst)) return node->geneve; } return NULL; } #endif static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) { return (struct genevehdr *)(udp_hdr(skb) + 1); } static struct geneve_dev *geneve_lookup_skb(struct geneve_sock *gs, struct sk_buff *skb) { static u8 zero_vni[3]; u8 *vni; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph; __be32 addr; iph = ip_hdr(skb); /* outer IP header... */ if (gs->collect_md) { vni = zero_vni; addr = 0; } else { vni = geneve_hdr(skb)->vni; addr = iph->saddr; } return geneve_lookup(gs, addr, vni); #if IS_ENABLED(CONFIG_IPV6) } else if (geneve_get_sk_family(gs) == AF_INET6) { static struct in6_addr zero_addr6; struct ipv6hdr *ip6h; struct in6_addr addr6; ip6h = ipv6_hdr(skb); /* outer IPv6 header... */ if (gs->collect_md) { vni = zero_vni; addr6 = zero_addr6; } else { vni = geneve_hdr(skb)->vni; addr6 = ip6h->saddr; } return geneve6_lookup(gs, addr6, vni); #endif } return NULL; } /* geneve receive/decap routine */ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct sk_buff *skb) { struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_KEY_BIT, flags); __assign_bit(IP_TUNNEL_OAM_BIT, flags, gnvh->oam); __assign_bit(IP_TUNNEL_CRIT_OPT_BIT, flags, gnvh->critical); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4); if (!tun_dst) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } /* Update tunnel dst according to Geneve options. */ ip_tunnel_flags_zero(flags); __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, flags); ip_tunnel_info_opts_set(&tun_dst->u.tun_info, gnvh->options, gnvh->opt_len * 4, flags); } else { /* Drop packets w/ critical options, * since we don't support any... */ if (gnvh->critical) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } if (tun_dst) skb_dst_set(skb, &tun_dst->dst); if (gnvh->proto_type == htons(ETH_P_TEB)) { skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, geneve->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } else { skb_reset_mac_header(skb); skb->dev = geneve->dev; skb->pkt_type = PACKET_HOST; } /* 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 (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(geneve->dev, rx_length_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err)) { if (log_ecn_error) { if (geneve_get_sk_family(gs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); #if IS_ENABLED(CONFIG_IPV6) else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); #endif } if (err > 1) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } len = skb->len; err = gro_cells_receive(&geneve->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) dev_sw_netstats_rx_add(geneve->dev, len); return; drop: /* Consume bad packet */ kfree_skb(skb); } /* Setup stats when device is created */ static int geneve_init(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); int err; err = gro_cells_init(&geneve->gro_cells, dev); if (err) return err; err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL); if (err) { gro_cells_destroy(&geneve->gro_cells); return err; } netdev_lockdep_set_classes(dev); return 0; } static void geneve_uninit(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); dst_cache_destroy(&geneve->cfg.info.dst_cache); gro_cells_destroy(&geneve->gro_cells); } /* Callback from net/ipv4/udp.c to receive packets */ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_dev *geneve; struct geneve_sock *gs; __be16 inner_proto; int opts_len; /* Need UDP and Geneve header to be present */ if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN))) goto drop; /* Return packets with reserved bits set */ geneveh = geneve_hdr(skb); if (unlikely(geneveh->ver != GENEVE_VER)) goto drop; gs = rcu_dereference_sk_user_data(sk); if (!gs) goto drop; geneve = geneve_lookup_skb(gs, skb); if (!geneve) goto drop; inner_proto = geneveh->proto_type; if (unlikely((!geneve->cfg.inner_proto_inherit && inner_proto != htons(ETH_P_TEB)))) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } opts_len = geneveh->opt_len * 4; if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto, !net_eq(geneve->net, dev_net(geneve->dev)))) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } geneve_rx(geneve, gs, skb); return 0; drop: /* Consume bad packet */ kfree_skb(skb); return 0; } /* Callback from net/ipv{4,6}/udp.c to check that we have a tunnel for errors */ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_sock *gs; u8 zero_vni[3] = { 0 }; u8 *vni = zero_vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + GENEVE_BASE_HLEN)) return -EINVAL; geneveh = geneve_hdr(skb); if (geneveh->ver != GENEVE_VER) return -EINVAL; if (geneveh->proto_type != htons(ETH_P_TEB)) return -EINVAL; gs = rcu_dereference_sk_user_data(sk); if (!gs) return -ENOENT; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph = ip_hdr(skb); __be32 addr4 = 0; if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr4 = iph->daddr; } return geneve_lookup(gs, addr4, vni) ? 0 : -ENOENT; } #if IS_ENABLED(CONFIG_IPV6) if (geneve_get_sk_family(gs) == AF_INET6) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct in6_addr addr6; memset(&addr6, 0, sizeof(struct in6_addr)); if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr6 = ip6h->daddr; } return geneve6_lookup(gs, addr6, vni) ? 0 : -ENOENT; } #endif return -EPFNOSUPPORT; } static struct socket *geneve_create_sock(struct net *net, bool ipv6, __be16 port, bool ipv6_rx_csum) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.ipv6_v6only = 1; udp_conf.use_udp6_rx_checksums = ipv6_rx_csum; } else { udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = htonl(INADDR_ANY); } udp_conf.local_udp_port = port; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } static int geneve_hlen(struct genevehdr *gh) { return sizeof(*gh) + gh->opt_len * 4; } static struct sk_buff *geneve_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct sk_buff *p; struct genevehdr *gh, *gh2; unsigned int hlen, gh_len, off_gnv; const struct packet_offload *ptype; __be16 type; int flush = 1; off_gnv = skb_gro_offset(skb); hlen = off_gnv + sizeof(*gh); gh = skb_gro_header(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; if (gh->ver != GENEVE_VER || gh->oam) goto out; gh_len = geneve_hlen(gh); hlen = off_gnv + gh_len; if (!skb_gro_may_pull(skb, hlen)) { gh = skb_gro_header_slow(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; } list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; gh2 = (struct genevehdr *)(p->data + off_gnv); if (gh->opt_len != gh2->opt_len || memcmp(gh, gh2, gh_len)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, gh_len); skb_gro_postpull_rcsum(skb, gh, gh_len); type = gh->proto_type; if (likely(type == htons(ETH_P_TEB))) return call_gro_receive(eth_gro_receive, head, skb); ptype = gro_find_receive_by_type(type); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final(skb, pp, flush); return pp; } static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct genevehdr *gh; struct packet_offload *ptype; __be16 type; int gh_len; int err = -ENOSYS; gh = (struct genevehdr *)(skb->data + nhoff); gh_len = geneve_hlen(gh); type = gh->proto_type; /* since skb->encapsulation is set, eth_gro_complete() sets the inner mac header */ if (likely(type == htons(ETH_P_TEB))) return eth_gro_complete(skb, nhoff + gh_len); ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); skb_set_inner_mac_header(skb, nhoff + gh_len); return err; } /* Create new listen socket if needed */ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, bool ipv6, bool ipv6_rx_csum) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; struct socket *sock; struct udp_tunnel_sock_cfg tunnel_cfg; int h; gs = kzalloc(sizeof(*gs), GFP_KERNEL); if (!gs) return ERR_PTR(-ENOMEM); sock = geneve_create_sock(net, ipv6, port, ipv6_rx_csum); if (IS_ERR(sock)) { kfree(gs); return ERR_CAST(sock); } gs->sock = sock; gs->refcnt = 1; for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&gs->vni_list[h]); /* Initialize the geneve udp offloads structure */ udp_tunnel_notify_add_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE); /* Mark socket as an encapsulation socket */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = gs; tunnel_cfg.encap_type = 1; tunnel_cfg.gro_receive = geneve_gro_receive; tunnel_cfg.gro_complete = geneve_gro_complete; tunnel_cfg.encap_rcv = geneve_udp_encap_recv; tunnel_cfg.encap_err_lookup = geneve_udp_encap_err_lookup; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, sock, &tunnel_cfg); list_add(&gs->list, &gn->sock_list); return gs; } static void __geneve_sock_release(struct geneve_sock *gs) { if (!gs || --gs->refcnt) return; list_del(&gs->list); udp_tunnel_notify_del_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE); udp_tunnel_sock_release(gs->sock); kfree_rcu(gs, rcu); } static void geneve_sock_release(struct geneve_dev *geneve) { struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4); #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); #endif rcu_assign_pointer(geneve->sock4, NULL); synchronize_net(); __geneve_sock_release(gs4); #if IS_ENABLED(CONFIG_IPV6) __geneve_sock_release(gs6); #endif } static struct geneve_sock *geneve_find_sock(struct geneve_net *gn, sa_family_t family, __be16 dst_port) { struct geneve_sock *gs; list_for_each_entry(gs, &gn->sock_list, list) { if (inet_sk(gs->sock->sk)->inet_sport == dst_port && geneve_get_sk_family(gs) == family) { return gs; } } return NULL; } static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) { struct net *net = geneve->net; struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev_node *node; struct geneve_sock *gs; __u8 vni[3]; __u32 hash; gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET, geneve->cfg.info.key.tp_dst); if (gs) { gs->refcnt++; goto out; } gs = geneve_socket_create(net, geneve->cfg.info.key.tp_dst, ipv6, geneve->cfg.use_udp6_rx_checksums); if (IS_ERR(gs)) return PTR_ERR(gs); out: gs->collect_md = geneve->cfg.collect_md; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(geneve->sock6, gs); node = &geneve->hlist6; } else #endif { rcu_assign_pointer(geneve->sock4, gs); node = &geneve->hlist4; } node->geneve = geneve; tunnel_id_to_vni(geneve->cfg.info.key.tun_id, vni); hash = geneve_net_vni_hash(vni); hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]); return 0; } static int geneve_open(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); bool metadata = geneve->cfg.collect_md; bool ipv4, ipv6; int ret = 0; ipv6 = geneve->cfg.info.mode & IP_TUNNEL_INFO_IPV6 || metadata; ipv4 = !ipv6 || metadata; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { ret = geneve_sock_add(geneve, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = geneve_sock_add(geneve, false); if (ret < 0) geneve_sock_release(geneve); return ret; } static int geneve_stop(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); hlist_del_init_rcu(&geneve->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&geneve->hlist6.hlist); #endif geneve_sock_release(geneve); return 0; } static void geneve_build_header(struct genevehdr *geneveh, const struct ip_tunnel_info *info, __be16 inner_proto) { geneveh->ver = GENEVE_VER; geneveh->opt_len = info->options_len / 4; geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, info->key.tun_flags); geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, info->key.tun_flags); geneveh->rsvd1 = 0; tunnel_id_to_vni(info->key.tun_id, geneveh->vni); geneveh->proto_type = inner_proto; geneveh->rsvd2 = 0; if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) ip_tunnel_info_opts_get(geneveh->options, info); } static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, const struct ip_tunnel_info *info, bool xnet, int ip_hdr_len, bool inner_proto_inherit) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); struct genevehdr *gnvh; __be16 inner_proto; int min_headroom; int err; skb_reset_mac_header(skb); skb_scrub_packet(skb, xnet); min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + GENEVE_BASE_HLEN + info->options_len + ip_hdr_len; err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; gnvh = __skb_push(skb, sizeof(*gnvh) + info->options_len); inner_proto = inner_proto_inherit ? skb->protocol : htons(ETH_P_TEB); geneve_build_header(gnvh, info, inner_proto); skb_set_inner_protocol(skb, inner_proto); return 0; free_dst: dst_release(dst); return err; } static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev, const struct ip_tunnel_info *info, bool *use_cache) { struct geneve_dev *geneve = netdev_priv(dev); u8 dsfield; dsfield = info->key.tos; if (dsfield == 1 && !geneve->cfg.collect_md) { dsfield = ip_tunnel_get_dsfield(ip_hdr(skb), skb); *use_cache = false; } return dsfield; } static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; bool use_cache; __u8 tos, ttl; __be16 df = 0; __be32 saddr; __be16 sport; int err; if (!skb_vlan_inet_prepare(skb)) return -EINVAL; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); err = skb_tunnel_check_pmtu(skb, &rt->dst, GENEVE_IPV4_HLEN + info->options_len, netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(&rt->dst); return err; } else if (err) { struct ip_tunnel_info *info; info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(&rt->dst); return -ENOMEM; } unclone->key.u.ipv4.dst = saddr; unclone->key.u.ipv4.src = info->key.u.ipv4.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(&rt->dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(&rt->dst); return -EMSGSIZE; } tos = ip_tunnel_ecn_encap(tos, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? htons(IP_DF) : 0; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); if (geneve->cfg.df == GENEVE_DF_SET) { df = htons(IP_DF); } else if (geneve->cfg.df == GENEVE_DF_INHERIT) { struct ethhdr *eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6) { df = htons(IP_DF); } else if (ntohs(eth->h_proto) == ETH_P_IP) { struct iphdr *iph = ip_hdr(skb); if (iph->frag_off & htons(IP_DF)) df = htons(IP_DF); } } } err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr), geneve->cfg.inner_proto_inherit); if (unlikely(err)) return err; udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, geneve->cfg.info.key.tp_dst, !net_eq(geneve->net, dev_net(geneve->dev)), !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; } #if IS_ENABLED(CONFIG_IPV6) static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr; bool use_cache; __u8 prio, ttl; __be16 sport; int err; if (!skb_vlan_inet_prepare(skb)) return -EINVAL; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, &saddr, key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); err = skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len, netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(dst); return err; } else if (err) { struct ip_tunnel_info *info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(dst); return -ENOMEM; } unclone->key.u.ipv6.dst = saddr; unclone->key.u.ipv6.src = info->key.u.ipv6.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(dst); return -EMSGSIZE; } prio = ip_tunnel_ecn_encap(prio, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr), geneve->cfg.inner_proto_inherit); if (unlikely(err)) return err; udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; } #endif static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; if (geneve->cfg.collect_md) { info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { netdev_dbg(dev, "no tunnel metadata\n"); dev_kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } } else { info = &geneve->cfg.info; } rcu_read_lock(); #if IS_ENABLED(CONFIG_IPV6) if (info->mode & IP_TUNNEL_INFO_IPV6) err = geneve6_xmit_skb(skb, dev, geneve, info); else #endif err = geneve_xmit_skb(skb, dev, geneve, info); rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; if (err != -EMSGSIZE) dev_kfree_skb(skb); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static int geneve_change_mtu(struct net_device *dev, int new_mtu) { if (new_mtu > dev->max_mtu) new_mtu = dev->max_mtu; else if (new_mtu < dev->min_mtu) new_mtu = dev->min_mtu; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); struct geneve_dev *geneve = netdev_priv(dev); __be16 sport; if (ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); bool use_cache; __be32 saddr; u8 tos; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? &info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = saddr; #if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); struct in6_addr saddr; bool use_cache; u8 prio; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); dst_release(dst); info->key.u.ipv6.src = saddr; #endif } else { return -EINVAL; } info->key.tp_src = sport; info->key.tp_dst = geneve->cfg.info.key.tp_dst; return 0; } static const struct net_device_ops geneve_netdev_ops = { .ndo_init = geneve_init, .ndo_uninit = geneve_uninit, .ndo_open = geneve_open, .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_xmit, .ndo_change_mtu = geneve_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fill_metadata_dst = geneve_fill_metadata_dst, }; static void geneve_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver)); } static const struct ethtool_ops geneve_ethtool_ops = { .get_drvinfo = geneve_get_drvinfo, .get_link = ethtool_op_get_link, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type geneve_type = { .name = "geneve", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening GENEVE udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void geneve_offload_rx_ports(struct net_device *dev, bool push) { struct net *net = dev_net(dev); struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; rcu_read_lock(); list_for_each_entry_rcu(gs, &gn->sock_list, list) { if (push) { udp_tunnel_push_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); } else { udp_tunnel_drop_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); } } rcu_read_unlock(); } /* Initialize the device structure. */ static void geneve_setup(struct net_device *dev) { ether_setup(dev); dev->netdev_ops = &geneve_netdev_ops; dev->ethtool_ops = &geneve_ethtool_ops; dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &geneve_type); dev->features |= NETIF_F_LLTX; dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; /* MTU range: 68 - (something less than 65535) */ dev->min_mtu = ETH_MIN_MTU; /* The max_mtu calculation does not take account of GENEVE * options, to avoid excluding potentially valid * configurations. This will be further reduced by IPvX hdr size. */ dev->max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len; netif_keep_dst(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; eth_hw_addr_random(dev); } static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_UNSPEC] = { .strict_start_type = IFLA_GENEVE_INNER_PROTO_INHERIT }, [IFLA_GENEVE_ID] = { .type = NLA_U32 }, [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, [IFLA_GENEVE_LABEL] = { .type = NLA_U32 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, [IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_GENEVE_TTL_INHERIT] = { .type = NLA_U8 }, [IFLA_GENEVE_DF] = { .type = NLA_U8 }, [IFLA_GENEVE_INNER_PROTO_INHERIT] = { .type = NLA_FLAG }, }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (!data) { NL_SET_ERR_MSG(extack, "Not enough attributes provided to perform the operation"); return -EINVAL; } if (data[IFLA_GENEVE_ID]) { __u32 vni = nla_get_u32(data[IFLA_GENEVE_ID]); if (vni >= GENEVE_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_ID], "Geneve ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_GENEVE_DF]) { enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]); if (df < 0 || df > GENEVE_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF], "Invalid DF attribute"); return -EINVAL; } } return 0; } static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, const struct ip_tunnel_info *info, bool *tun_on_same_port, bool *tun_collect_md) { struct geneve_dev *geneve, *t = NULL; *tun_on_same_port = false; *tun_collect_md = false; list_for_each_entry(geneve, &gn->geneve_list, next) { if (info->key.tp_dst == geneve->cfg.info.key.tp_dst) { *tun_collect_md = geneve->cfg.collect_md; *tun_on_same_port = true; } if (info->key.tun_id == geneve->cfg.info.key.tun_id && info->key.tp_dst == geneve->cfg.info.key.tp_dst && !memcmp(&info->key.u, &geneve->cfg.info.key.u, sizeof(info->key.u))) t = geneve; } return t; } static bool is_tnl_info_zero(const struct ip_tunnel_info *info) { return !(info->key.tun_id || info->key.tos || !ip_tunnel_flags_empty(info->key.tun_flags) || info->key.ttl || info->key.label || info->key.tp_src || memchr_inv(&info->key.u, 0, sizeof(info->key.u))); } static bool geneve_dst_addr_equal(struct ip_tunnel_info *a, struct ip_tunnel_info *b) { if (ip_tunnel_info_af(a) == AF_INET) return a->key.u.ipv4.dst == b->key.u.ipv4.dst; else return ipv6_addr_equal(&a->key.u.ipv6.dst, &b->key.u.ipv6.dst); } static int geneve_configure(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack, const struct geneve_config *cfg) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); const struct ip_tunnel_info *info = &cfg->info; bool tun_collect_md, tun_on_same_port; int err, encap_len; if (cfg->collect_md && !is_tnl_info_zero(info)) { NL_SET_ERR_MSG(extack, "Device is externally controlled, so attributes (VNI, Port, and so on) must not be specified"); return -EINVAL; } geneve->net = net; geneve->dev = dev; t = geneve_find_dev(gn, info, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; /* make enough headroom for basic scenario */ encap_len = GENEVE_BASE_HLEN + ETH_HLEN; if (!cfg->collect_md && ip_tunnel_info_af(info) == AF_INET) { encap_len += sizeof(struct iphdr); dev->max_mtu -= sizeof(struct iphdr); } else { encap_len += sizeof(struct ipv6hdr); dev->max_mtu -= sizeof(struct ipv6hdr); } dev->needed_headroom = encap_len + ETH_HLEN; if (cfg->collect_md) { if (tun_on_same_port) { NL_SET_ERR_MSG(extack, "There can be only one externally controlled device on a destination port"); return -EPERM; } } else { if (tun_collect_md) { NL_SET_ERR_MSG(extack, "There already exists an externally controlled device on this destination port"); return -EPERM; } } dst_cache_reset(&geneve->cfg.info.dst_cache); memcpy(&geneve->cfg, cfg, sizeof(*cfg)); if (geneve->cfg.inner_proto_inherit) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP; } err = register_netdevice(dev); if (err) return err; list_add(&geneve->next, &gn->geneve_list); return 0; } static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port) { memset(info, 0, sizeof(*info)); info->key.tp_dst = htons(dst_port); } static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack, struct geneve_config *cfg, bool changelink) { struct ip_tunnel_info *info = &cfg->info; int attrtype; if (data[IFLA_GENEVE_REMOTE] && data[IFLA_GENEVE_REMOTE6]) { NL_SET_ERR_MSG(extack, "Cannot specify both IPv4 and IPv6 Remote addresses"); return -EINVAL; } if (data[IFLA_GENEVE_REMOTE]) { if (changelink && (ip_tunnel_info_af(info) == AF_INET6)) { attrtype = IFLA_GENEVE_REMOTE; goto change_notsup; } info->key.u.ipv4.dst = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); if (ipv4_is_multicast(info->key.u.ipv4.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE], "Remote IPv4 address cannot be Multicast"); return -EINVAL; } } if (data[IFLA_GENEVE_REMOTE6]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink && (ip_tunnel_info_af(info) == AF_INET)) { attrtype = IFLA_GENEVE_REMOTE6; goto change_notsup; } info->mode = IP_TUNNEL_INFO_IPV6; info->key.u.ipv6.dst = nla_get_in6_addr(data[IFLA_GENEVE_REMOTE6]); if (ipv6_addr_type(&info->key.u.ipv6.dst) & IPV6_ADDR_LINKLOCAL) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be link-local"); return -EINVAL; } if (ipv6_addr_is_multicast(&info->key.u.ipv6.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be Multicast"); return -EINVAL; } __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); cfg->use_udp6_rx_checksums = true; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_ID]) { __u32 vni; __u8 tvni[3]; __be64 tunid; vni = nla_get_u32(data[IFLA_GENEVE_ID]); tvni[0] = (vni & 0x00ff0000) >> 16; tvni[1] = (vni & 0x0000ff00) >> 8; tvni[2] = vni & 0x000000ff; tunid = vni_to_tunnel_id(tvni); if (changelink && (tunid != info->key.tun_id)) { attrtype = IFLA_GENEVE_ID; goto change_notsup; } info->key.tun_id = tunid; } if (data[IFLA_GENEVE_TTL_INHERIT]) { if (nla_get_u8(data[IFLA_GENEVE_TTL_INHERIT])) cfg->ttl_inherit = true; else cfg->ttl_inherit = false; } else if (data[IFLA_GENEVE_TTL]) { info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); cfg->ttl_inherit = false; } if (data[IFLA_GENEVE_TOS]) info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]); if (data[IFLA_GENEVE_DF]) cfg->df = nla_get_u8(data[IFLA_GENEVE_DF]); if (data[IFLA_GENEVE_LABEL]) { info->key.label = nla_get_be32(data[IFLA_GENEVE_LABEL]) & IPV6_FLOWLABEL_MASK; if (info->key.label && (!(info->mode & IP_TUNNEL_INFO_IPV6))) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LABEL], "Label attribute only applies for IPv6 Geneve devices"); return -EINVAL; } } if (data[IFLA_GENEVE_PORT]) { if (changelink) { attrtype = IFLA_GENEVE_PORT; goto change_notsup; } info->key.tp_dst = nla_get_be16(data[IFLA_GENEVE_PORT]); } if (data[IFLA_GENEVE_COLLECT_METADATA]) { if (changelink) { attrtype = IFLA_GENEVE_COLLECT_METADATA; goto change_notsup; } cfg->collect_md = true; } if (data[IFLA_GENEVE_UDP_CSUM]) { if (changelink) { attrtype = IFLA_GENEVE_UDP_CSUM; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_TX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) __clear_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_RX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) cfg->use_udp6_rx_checksums = false; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_INNER_PROTO_INHERIT]) { if (changelink) { attrtype = IFLA_GENEVE_INNER_PROTO_INHERIT; goto change_notsup; } cfg->inner_proto_inherit = true; } return 0; change_notsup: NL_SET_ERR_MSG_ATTR(extack, data[attrtype], "Changing VNI, Port, endpoint IP address family, external, inner_proto_inherit, and UDP checksum attributes are not supported"); return -EOPNOTSUPP; } static void geneve_link_config(struct net_device *dev, struct ip_tunnel_info *info, struct nlattr *tb[]) { struct geneve_dev *geneve = netdev_priv(dev); int ldev_mtu = 0; if (tb[IFLA_MTU]) { geneve_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); return; } switch (ip_tunnel_info_af(info)) { case AF_INET: { struct flowi4 fl4 = { .daddr = info->key.u.ipv4.dst }; struct rtable *rt = ip_route_output_key(geneve->net, &fl4); if (!IS_ERR(rt) && rt->dst.dev) { ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV4_HLEN; ip_rt_put(rt); } break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct rt6_info *rt; if (!__in6_dev_get(dev)) break; rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; ip6_rt_put(rt); break; } #endif } if (ldev_mtu <= 0) return; geneve_change_mtu(dev, ldev_mtu - info->options_len); } static int geneve_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = false, .ttl_inherit = false, .collect_md = false, }; int err; init_tnl_info(&cfg.info, GENEVE_UDP_PORT); err = geneve_nl2info(tb, data, extack, &cfg, false); if (err) return err; err = geneve_configure(net, dev, extack, &cfg); if (err) return err; geneve_link_config(dev, &cfg.info, tb); return 0; } /* Quiesces the geneve device data path for both TX and RX. * * On transmit geneve checks for non-NULL geneve_sock before it proceeds. * So, if we set that socket to NULL under RCU and wait for synchronize_net() * to complete for the existing set of in-flight packets to be transmitted, * then we would have quiesced the transmit data path. All the future packets * will get dropped until we unquiesce the data path. * * On receive geneve dereference the geneve_sock stashed in the socket. So, * if we set that to NULL under RCU and wait for synchronize_net() to * complete, then we would have quiesced the receive data path. */ static void geneve_quiesce(struct geneve_dev *geneve, struct geneve_sock **gs4, struct geneve_sock **gs6) { *gs4 = rtnl_dereference(geneve->sock4); rcu_assign_pointer(geneve->sock4, NULL); if (*gs4) rcu_assign_sk_user_data((*gs4)->sock->sk, NULL); #if IS_ENABLED(CONFIG_IPV6) *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); if (*gs6) rcu_assign_sk_user_data((*gs6)->sock->sk, NULL); #else *gs6 = NULL; #endif synchronize_net(); } /* Resumes the geneve device data path for both TX and RX. */ static void geneve_unquiesce(struct geneve_dev *geneve, struct geneve_sock *gs4, struct geneve_sock __maybe_unused *gs6) { rcu_assign_pointer(geneve->sock4, gs4); if (gs4) rcu_assign_sk_user_data(gs4->sock->sk, gs4); #if IS_ENABLED(CONFIG_IPV6) rcu_assign_pointer(geneve->sock6, gs6); if (gs6) rcu_assign_sk_user_data(gs6->sock->sk, gs6); #endif synchronize_net(); } static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs4, *gs6; struct geneve_config cfg; int err; /* If the geneve device is configured for metadata (or externally * controlled, for example, OVS), then nothing can be changed. */ if (geneve->cfg.collect_md) return -EOPNOTSUPP; /* Start with the existing info. */ memcpy(&cfg, &geneve->cfg, sizeof(cfg)); err = geneve_nl2info(tb, data, extack, &cfg, true); if (err) return err; if (!geneve_dst_addr_equal(&geneve->cfg.info, &cfg.info)) { dst_cache_reset(&cfg.info.dst_cache); geneve_link_config(dev, &cfg.info, tb); } geneve_quiesce(geneve, &gs4, &gs6); memcpy(&geneve->cfg, &cfg, sizeof(cfg)); geneve_unquiesce(geneve, gs4, gs6); return 0; } static void geneve_dellink(struct net_device *dev, struct list_head *head) { struct geneve_dev *geneve = netdev_priv(dev); list_del(&geneve->next); unregister_netdevice_queue(dev, head); } static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_GENEVE_LABEL */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */ nla_total_size(0) + /* IFLA_GENEVE_INNER_PROTO_INHERIT */ 0; } static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = &geneve->cfg.info; bool ttl_inherit = geneve->cfg.ttl_inherit; bool metadata = geneve->cfg.collect_md; __u8 tmp_vni[3]; __u32 vni; tunnel_id_to_vni(info->key.tun_id, tmp_vni); vni = (tmp_vni[0] << 16) | (tmp_vni[1] << 8) | tmp_vni[2]; if (nla_put_u32(skb, IFLA_GENEVE_ID, vni)) goto nla_put_failure; if (!metadata && ip_tunnel_info_af(info) == AF_INET) { if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, info->key.u.ipv4.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else if (!metadata) { if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6, &info->key.u.ipv6.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #endif } if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) || nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) || nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_DF, geneve->cfg.df)) goto nla_put_failure; if (nla_put_be16(skb, IFLA_GENEVE_PORT, info->key.tp_dst)) goto nla_put_failure; if (metadata && nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, !geneve->cfg.use_udp6_rx_checksums)) goto nla_put_failure; #endif if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit)) goto nla_put_failure; if (geneve->cfg.inner_proto_inherit && nla_put_flag(skb, IFLA_GENEVE_INNER_PROTO_INHERIT)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops geneve_link_ops __read_mostly = { .kind = "geneve", .maxtype = IFLA_GENEVE_MAX, .policy = geneve_policy, .priv_size = sizeof(struct geneve_dev), .setup = geneve_setup, .validate = geneve_validate, .newlink = geneve_newlink, .changelink = geneve_changelink, .dellink = geneve_dellink, .get_size = geneve_get_size, .fill_info = geneve_fill_info, }; struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); int err; struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = true, .ttl_inherit = false, .collect_md = true, }; memset(tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &geneve_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; init_tnl_info(&cfg.info, dst_port); err = geneve_configure(net, dev, NULL, &cfg); if (err) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = geneve_change_mtu(dev, IP_MAX_MTU); if (err) goto err; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto err; return dev; err: geneve_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(geneve_dev_create_fb); static int geneve_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) geneve_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) geneve_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block geneve_notifier_block __read_mostly = { .notifier_call = geneve_netdevice_event, }; static __net_init int geneve_init_net(struct net *net) { struct geneve_net *gn = net_generic(net, geneve_net_id); INIT_LIST_HEAD(&gn->geneve_list); INIT_LIST_HEAD(&gn->sock_list); return 0; } static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; struct net_device *dev, *aux; /* gather any geneve devices that were moved into this ns */ for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &geneve_link_ops) unregister_netdevice_queue(dev, head); /* now gather any other geneve devices that were created in this ns */ list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) { /* If geneve->dev is in the same netns, it was already added * to the list by the previous loop. */ if (!net_eq(dev_net(geneve->dev), net)) unregister_netdevice_queue(geneve->dev, head); } } static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; list_for_each_entry(net, net_list, exit_list) geneve_destroy_tunnels(net, dev_to_kill); } static void __net_exit geneve_exit_net(struct net *net) { const struct geneve_net *gn = net_generic(net, geneve_net_id); WARN_ON_ONCE(!list_empty(&gn->sock_list)); } static struct pernet_operations geneve_net_ops = { .init = geneve_init_net, .exit_batch_rtnl = geneve_exit_batch_rtnl, .exit = geneve_exit_net, .id = &geneve_net_id, .size = sizeof(struct geneve_net), }; static int __init geneve_init_module(void) { int rc; rc = register_pernet_subsys(&geneve_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&geneve_notifier_block); if (rc) goto out2; rc = rtnl_link_register(&geneve_link_ops); if (rc) goto out3; return 0; out3: unregister_netdevice_notifier(&geneve_notifier_block); out2: unregister_pernet_subsys(&geneve_net_ops); out1: return rc; } late_initcall(geneve_init_module); static void __exit geneve_cleanup_module(void) { rtnl_link_unregister(&geneve_link_ops); unregister_netdevice_notifier(&geneve_notifier_block); unregister_pernet_subsys(&geneve_net_ops); } module_exit(geneve_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(GENEVE_NETDEV_VER); MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>"); MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("geneve"); |
| 151 151 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | // SPDX-License-Identifier: GPL-2.0-only /* * crc16.c */ #include <linux/types.h> #include <linux/module.h> #include <linux/crc16.h> /** CRC table for the CRC-16. The poly is 0x8005 (x^16 + x^15 + x^2 + 1) */ u16 const crc16_table[256] = { 0x0000, 0xC0C1, 0xC181, 0x0140, 0xC301, 0x03C0, 0x0280, 0xC241, 0xC601, 0x06C0, 0x0780, 0xC741, 0x0500, 0xC5C1, 0xC481, 0x0440, 0xCC01, 0x0CC0, 0x0D80, 0xCD41, 0x0F00, 0xCFC1, 0xCE81, 0x0E40, 0x0A00, 0xCAC1, 0xCB81, 0x0B40, 0xC901, 0x09C0, 0x0880, 0xC841, 0xD801, 0x18C0, 0x1980, 0xD941, 0x1B00, 0xDBC1, 0xDA81, 0x1A40, 0x1E00, 0xDEC1, 0xDF81, 0x1F40, 0xDD01, 0x1DC0, 0x1C80, 0xDC41, 0x1400, 0xD4C1, 0xD581, 0x1540, 0xD701, 0x17C0, 0x1680, 0xD641, 0xD201, 0x12C0, 0x1380, 0xD341, 0x1100, 0xD1C1, 0xD081, 0x1040, 0xF001, 0x30C0, 0x3180, 0xF141, 0x3300, 0xF3C1, 0xF281, 0x3240, 0x3600, 0xF6C1, 0xF781, 0x3740, 0xF501, 0x35C0, 0x3480, 0xF441, 0x3C00, 0xFCC1, 0xFD81, 0x3D40, 0xFF01, 0x3FC0, 0x3E80, 0xFE41, 0xFA01, 0x3AC0, 0x3B80, 0xFB41, 0x3900, 0xF9C1, 0xF881, 0x3840, 0x2800, 0xE8C1, 0xE981, 0x2940, 0xEB01, 0x2BC0, 0x2A80, 0xEA41, 0xEE01, 0x2EC0, 0x2F80, 0xEF41, 0x2D00, 0xEDC1, 0xEC81, 0x2C40, 0xE401, 0x24C0, 0x2580, 0xE541, 0x2700, 0xE7C1, 0xE681, 0x2640, 0x2200, 0xE2C1, 0xE381, 0x2340, 0xE101, 0x21C0, 0x2080, 0xE041, 0xA001, 0x60C0, 0x6180, 0xA141, 0x6300, 0xA3C1, 0xA281, 0x6240, 0x6600, 0xA6C1, 0xA781, 0x6740, 0xA501, 0x65C0, 0x6480, 0xA441, 0x6C00, 0xACC1, 0xAD81, 0x6D40, 0xAF01, 0x6FC0, 0x6E80, 0xAE41, 0xAA01, 0x6AC0, 0x6B80, 0xAB41, 0x6900, 0xA9C1, 0xA881, 0x6840, 0x7800, 0xB8C1, 0xB981, 0x7940, 0xBB01, 0x7BC0, 0x7A80, 0xBA41, 0xBE01, 0x7EC0, 0x7F80, 0xBF41, 0x7D00, 0xBDC1, 0xBC81, 0x7C40, 0xB401, 0x74C0, 0x7580, 0xB541, 0x7700, 0xB7C1, 0xB681, 0x7640, 0x7200, 0xB2C1, 0xB381, 0x7340, 0xB101, 0x71C0, 0x7080, 0xB041, 0x5000, 0x90C1, 0x9181, 0x5140, 0x9301, 0x53C0, 0x5280, 0x9241, 0x9601, 0x56C0, 0x5780, 0x9741, 0x5500, 0x95C1, 0x9481, 0x5440, 0x9C01, 0x5CC0, 0x5D80, 0x9D41, 0x5F00, 0x9FC1, 0x9E81, 0x5E40, 0x5A00, 0x9AC1, 0x9B81, 0x5B40, 0x9901, 0x59C0, 0x5880, 0x9841, 0x8801, 0x48C0, 0x4980, 0x8941, 0x4B00, 0x8BC1, 0x8A81, 0x4A40, 0x4E00, 0x8EC1, 0x8F81, 0x4F40, 0x8D01, 0x4DC0, 0x4C80, 0x8C41, 0x4400, 0x84C1, 0x8581, 0x4540, 0x8701, 0x47C0, 0x4680, 0x8641, 0x8201, 0x42C0, 0x4380, 0x8341, 0x4100, 0x81C1, 0x8081, 0x4040 }; EXPORT_SYMBOL(crc16_table); /** * crc16 - compute the CRC-16 for the data buffer * @crc: previous CRC value * @buffer: data pointer * @len: number of bytes in the buffer * * Returns the updated CRC value. */ u16 crc16(u16 crc, u8 const *buffer, size_t len) { while (len--) crc = crc16_byte(crc, *buffer++); return crc; } EXPORT_SYMBOL(crc16); MODULE_DESCRIPTION("CRC16 calculations"); MODULE_LICENSE("GPL"); |
| 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 | #ifndef _NET_FLOW_OFFLOAD_H #define _NET_FLOW_OFFLOAD_H #include <linux/kernel.h> #include <linux/list.h> #include <linux/netlink.h> #include <net/flow_dissector.h> struct flow_match { struct flow_dissector *dissector; void *mask; void *key; }; struct flow_match_meta { struct flow_dissector_key_meta *key, *mask; }; struct flow_match_basic { struct flow_dissector_key_basic *key, *mask; }; struct flow_match_control { struct flow_dissector_key_control *key, *mask; }; struct flow_match_eth_addrs { struct flow_dissector_key_eth_addrs *key, *mask; }; struct flow_match_vlan { struct flow_dissector_key_vlan *key, *mask; }; struct flow_match_arp { struct flow_dissector_key_arp *key, *mask; }; struct flow_match_ipv4_addrs { struct flow_dissector_key_ipv4_addrs *key, *mask; }; struct flow_match_ipv6_addrs { struct flow_dissector_key_ipv6_addrs *key, *mask; }; struct flow_match_ip { struct flow_dissector_key_ip *key, *mask; }; struct flow_match_ports { struct flow_dissector_key_ports *key, *mask; }; struct flow_match_ports_range { struct flow_dissector_key_ports_range *key, *mask; }; struct flow_match_icmp { struct flow_dissector_key_icmp *key, *mask; }; struct flow_match_tcp { struct flow_dissector_key_tcp *key, *mask; }; struct flow_match_ipsec { struct flow_dissector_key_ipsec *key, *mask; }; struct flow_match_mpls { struct flow_dissector_key_mpls *key, *mask; }; struct flow_match_enc_keyid { struct flow_dissector_key_keyid *key, *mask; }; struct flow_match_enc_opts { struct flow_dissector_key_enc_opts *key, *mask; }; struct flow_match_ct { struct flow_dissector_key_ct *key, *mask; }; struct flow_match_pppoe { struct flow_dissector_key_pppoe *key, *mask; }; struct flow_match_l2tpv3 { struct flow_dissector_key_l2tpv3 *key, *mask; }; struct flow_rule; void flow_rule_match_meta(const struct flow_rule *rule, struct flow_match_meta *out); void flow_rule_match_basic(const struct flow_rule *rule, struct flow_match_basic *out); void flow_rule_match_control(const struct flow_rule *rule, struct flow_match_control *out); void flow_rule_match_eth_addrs(const struct flow_rule *rule, struct flow_match_eth_addrs *out); void flow_rule_match_vlan(const struct flow_rule *rule, struct flow_match_vlan *out); void flow_rule_match_cvlan(const struct flow_rule *rule, struct flow_match_vlan *out); void flow_rule_match_arp(const struct flow_rule *rule, struct flow_match_arp *out); void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out); void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, struct flow_match_ipv6_addrs *out); void flow_rule_match_ip(const struct flow_rule *rule, struct flow_match_ip *out); void flow_rule_match_ports(const struct flow_rule *rule, struct flow_match_ports *out); void flow_rule_match_ports_range(const struct flow_rule *rule, struct flow_match_ports_range *out); void flow_rule_match_tcp(const struct flow_rule *rule, struct flow_match_tcp *out); void flow_rule_match_ipsec(const struct flow_rule *rule, struct flow_match_ipsec *out); void flow_rule_match_icmp(const struct flow_rule *rule, struct flow_match_icmp *out); void flow_rule_match_mpls(const struct flow_rule *rule, struct flow_match_mpls *out); void flow_rule_match_enc_control(const struct flow_rule *rule, struct flow_match_control *out); void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out); void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule, struct flow_match_ipv6_addrs *out); void flow_rule_match_enc_ip(const struct flow_rule *rule, struct flow_match_ip *out); void flow_rule_match_enc_ports(const struct flow_rule *rule, struct flow_match_ports *out); void flow_rule_match_enc_keyid(const struct flow_rule *rule, struct flow_match_enc_keyid *out); void flow_rule_match_enc_opts(const struct flow_rule *rule, struct flow_match_enc_opts *out); void flow_rule_match_ct(const struct flow_rule *rule, struct flow_match_ct *out); void flow_rule_match_pppoe(const struct flow_rule *rule, struct flow_match_pppoe *out); void flow_rule_match_l2tpv3(const struct flow_rule *rule, struct flow_match_l2tpv3 *out); enum flow_action_id { FLOW_ACTION_ACCEPT = 0, FLOW_ACTION_DROP, FLOW_ACTION_TRAP, FLOW_ACTION_GOTO, FLOW_ACTION_REDIRECT, FLOW_ACTION_MIRRED, FLOW_ACTION_REDIRECT_INGRESS, FLOW_ACTION_MIRRED_INGRESS, FLOW_ACTION_VLAN_PUSH, FLOW_ACTION_VLAN_POP, FLOW_ACTION_VLAN_MANGLE, FLOW_ACTION_TUNNEL_ENCAP, FLOW_ACTION_TUNNEL_DECAP, FLOW_ACTION_MANGLE, FLOW_ACTION_ADD, FLOW_ACTION_CSUM, FLOW_ACTION_MARK, FLOW_ACTION_PTYPE, FLOW_ACTION_PRIORITY, FLOW_ACTION_RX_QUEUE_MAPPING, FLOW_ACTION_WAKE, FLOW_ACTION_QUEUE, FLOW_ACTION_SAMPLE, FLOW_ACTION_POLICE, FLOW_ACTION_CT, FLOW_ACTION_CT_METADATA, FLOW_ACTION_MPLS_PUSH, FLOW_ACTION_MPLS_POP, FLOW_ACTION_MPLS_MANGLE, FLOW_ACTION_GATE, FLOW_ACTION_PPPOE_PUSH, FLOW_ACTION_JUMP, FLOW_ACTION_PIPE, FLOW_ACTION_VLAN_PUSH_ETH, FLOW_ACTION_VLAN_POP_ETH, FLOW_ACTION_CONTINUE, NUM_FLOW_ACTIONS, }; /* This is mirroring enum pedit_header_type definition for easy mapping between * tc pedit action. Legacy TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK is mapped to * FLOW_ACT_MANGLE_UNSPEC, which is supported by no driver. */ enum flow_action_mangle_base { FLOW_ACT_MANGLE_UNSPEC = 0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, FLOW_ACT_MANGLE_HDR_TYPE_IP4, FLOW_ACT_MANGLE_HDR_TYPE_IP6, FLOW_ACT_MANGLE_HDR_TYPE_TCP, FLOW_ACT_MANGLE_HDR_TYPE_UDP, }; enum flow_action_hw_stats_bit { FLOW_ACTION_HW_STATS_IMMEDIATE_BIT, FLOW_ACTION_HW_STATS_DELAYED_BIT, FLOW_ACTION_HW_STATS_DISABLED_BIT, FLOW_ACTION_HW_STATS_NUM_BITS }; enum flow_action_hw_stats { FLOW_ACTION_HW_STATS_IMMEDIATE = BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT), FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT), FLOW_ACTION_HW_STATS_ANY = FLOW_ACTION_HW_STATS_IMMEDIATE | FLOW_ACTION_HW_STATS_DELAYED, FLOW_ACTION_HW_STATS_DISABLED = BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT), FLOW_ACTION_HW_STATS_DONT_CARE = BIT(FLOW_ACTION_HW_STATS_NUM_BITS) - 1, }; typedef void (*action_destr)(void *priv); struct flow_action_cookie { u32 cookie_len; u8 cookie[]; }; struct flow_action_cookie *flow_action_cookie_create(void *data, unsigned int len, gfp_t gfp); void flow_action_cookie_destroy(struct flow_action_cookie *cookie); struct flow_action_entry { enum flow_action_id id; u32 hw_index; unsigned long cookie; u64 miss_cookie; enum flow_action_hw_stats hw_stats; action_destr destructor; void *destructor_priv; union { u32 chain_index; /* FLOW_ACTION_GOTO */ struct net_device *dev; /* FLOW_ACTION_REDIRECT */ struct { /* FLOW_ACTION_VLAN */ u16 vid; __be16 proto; u8 prio; } vlan; struct { /* FLOW_ACTION_VLAN_PUSH_ETH */ unsigned char dst[ETH_ALEN]; unsigned char src[ETH_ALEN]; } vlan_push_eth; struct { /* FLOW_ACTION_MANGLE */ /* FLOW_ACTION_ADD */ enum flow_action_mangle_base htype; u32 offset; u32 mask; u32 val; } mangle; struct ip_tunnel_info *tunnel; /* FLOW_ACTION_TUNNEL_ENCAP */ u32 csum_flags; /* FLOW_ACTION_CSUM */ u32 mark; /* FLOW_ACTION_MARK */ u16 ptype; /* FLOW_ACTION_PTYPE */ u16 rx_queue; /* FLOW_ACTION_RX_QUEUE_MAPPING */ u32 priority; /* FLOW_ACTION_PRIORITY */ struct { /* FLOW_ACTION_QUEUE */ u32 ctx; u32 index; u8 vf; } queue; struct { /* FLOW_ACTION_SAMPLE */ struct psample_group *psample_group; u32 rate; u32 trunc_size; bool truncate; } sample; struct { /* FLOW_ACTION_POLICE */ u32 burst; u64 rate_bytes_ps; u64 peakrate_bytes_ps; u32 avrate; u16 overhead; u64 burst_pkt; u64 rate_pkt_ps; u32 mtu; struct { enum flow_action_id act_id; u32 extval; } exceed, notexceed; } police; struct { /* FLOW_ACTION_CT */ int action; u16 zone; struct nf_flowtable *flow_table; } ct; struct { unsigned long cookie; u32 mark; u32 labels[4]; bool orig_dir; } ct_metadata; struct { /* FLOW_ACTION_MPLS_PUSH */ u32 label; __be16 proto; u8 tc; u8 bos; u8 ttl; } mpls_push; struct { /* FLOW_ACTION_MPLS_POP */ __be16 proto; } mpls_pop; struct { /* FLOW_ACTION_MPLS_MANGLE */ u32 label; u8 tc; u8 bos; u8 ttl; } mpls_mangle; struct { s32 prio; u64 basetime; u64 cycletime; u64 cycletimeext; u32 num_entries; struct action_gate_entry *entries; } gate; struct { /* FLOW_ACTION_PPPOE_PUSH */ u16 sid; } pppoe; }; struct flow_action_cookie *user_cookie; /* user defined action cookie */ }; struct flow_action { unsigned int num_entries; struct flow_action_entry entries[] __counted_by(num_entries); }; static inline bool flow_action_has_entries(const struct flow_action *action) { return action->num_entries; } /** * flow_offload_has_one_action() - check if exactly one action is present * @action: tc filter flow offload action * * Return: true if exactly one action is present. */ static inline bool flow_offload_has_one_action(const struct flow_action *action) { return action->num_entries == 1; } static inline bool flow_action_is_last_entry(const struct flow_action *action, const struct flow_action_entry *entry) { return entry == &action->entries[action->num_entries - 1]; } #define flow_action_for_each(__i, __act, __actions) \ for (__i = 0, __act = &(__actions)->entries[0]; \ __i < (__actions)->num_entries; \ __act = &(__actions)->entries[++__i]) static inline bool flow_action_mixed_hw_stats_check(const struct flow_action *action, struct netlink_ext_ack *extack) { const struct flow_action_entry *action_entry; u8 last_hw_stats; int i; if (flow_offload_has_one_action(action)) return true; flow_action_for_each(i, action_entry, action) { if (i && action_entry->hw_stats != last_hw_stats) { NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported"); return false; } last_hw_stats = action_entry->hw_stats; } return true; } static inline const struct flow_action_entry * flow_action_first_entry_get(const struct flow_action *action) { WARN_ON(!flow_action_has_entries(action)); return &action->entries[0]; } static inline bool __flow_action_hw_stats_check(const struct flow_action *action, struct netlink_ext_ack *extack, bool check_allow_bit, enum flow_action_hw_stats_bit allow_bit) { const struct flow_action_entry *action_entry; if (!flow_action_has_entries(action)) return true; if (!flow_action_mixed_hw_stats_check(action, extack)) return false; action_entry = flow_action_first_entry_get(action); /* Zero is not a legal value for hw_stats, catch anyone passing it */ WARN_ON_ONCE(!action_entry->hw_stats); if (!check_allow_bit && ~action_entry->hw_stats & FLOW_ACTION_HW_STATS_ANY) { NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\""); return false; } else if (check_allow_bit && !(action_entry->hw_stats & BIT(allow_bit))) { NL_SET_ERR_MSG_MOD(extack, "Driver does not support selected HW stats type"); return false; } return true; } static inline bool flow_action_hw_stats_check(const struct flow_action *action, struct netlink_ext_ack *extack, enum flow_action_hw_stats_bit allow_bit) { return __flow_action_hw_stats_check(action, extack, true, allow_bit); } static inline bool flow_action_basic_hw_stats_check(const struct flow_action *action, struct netlink_ext_ack *extack) { return __flow_action_hw_stats_check(action, extack, false, 0); } struct flow_rule { struct flow_match match; struct flow_action action; }; struct flow_rule *flow_rule_alloc(unsigned int num_actions); static inline bool flow_rule_match_key(const struct flow_rule *rule, enum flow_dissector_key_id key) { return dissector_uses_key(rule->match.dissector, key); } /** * flow_rule_is_supp_control_flags() - check for supported control flags * @supp_flags: control flags supported by driver * @ctrl_flags: control flags present in rule * @extack: The netlink extended ACK for reporting errors. * * Return: true if only supported control flags are set, false otherwise. */ static inline bool flow_rule_is_supp_control_flags(const u32 supp_flags, const u32 ctrl_flags, struct netlink_ext_ack *extack) { if (likely((ctrl_flags & ~supp_flags) == 0)) return true; NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported match on control.flags %#x", ctrl_flags); return false; } /** * flow_rule_has_control_flags() - check for presence of any control flags * @ctrl_flags: control flags present in rule * @extack: The netlink extended ACK for reporting errors. * * Return: true if control flags are set, false otherwise. */ static inline bool flow_rule_has_control_flags(const u32 ctrl_flags, struct netlink_ext_ack *extack) { return !flow_rule_is_supp_control_flags(0, ctrl_flags, extack); } /** * flow_rule_match_has_control_flags() - match and check for any control flags * @rule: The flow_rule under evaluation. * @extack: The netlink extended ACK for reporting errors. * * Return: true if control flags are set, false otherwise. */ static inline bool flow_rule_match_has_control_flags(struct flow_rule *rule, struct netlink_ext_ack *extack) { struct flow_match_control match; if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) return false; flow_rule_match_control(rule, &match); return flow_rule_has_control_flags(match.mask->flags, extack); } struct flow_stats { u64 pkts; u64 bytes; u64 drops; u64 lastused; enum flow_action_hw_stats used_hw_stats; bool used_hw_stats_valid; }; static inline void flow_stats_update(struct flow_stats *flow_stats, u64 bytes, u64 pkts, u64 drops, u64 lastused, enum flow_action_hw_stats used_hw_stats) { flow_stats->pkts += pkts; flow_stats->bytes += bytes; flow_stats->drops += drops; flow_stats->lastused = max_t(u64, flow_stats->lastused, lastused); /* The driver should pass value with a maximum of one bit set. * Passing FLOW_ACTION_HW_STATS_ANY is invalid. */ WARN_ON(used_hw_stats == FLOW_ACTION_HW_STATS_ANY); flow_stats->used_hw_stats |= used_hw_stats; flow_stats->used_hw_stats_valid = true; } enum flow_block_command { FLOW_BLOCK_BIND, FLOW_BLOCK_UNBIND, }; enum flow_block_binder_type { FLOW_BLOCK_BINDER_TYPE_UNSPEC, FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS, FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, FLOW_BLOCK_BINDER_TYPE_RED_MARK, }; struct flow_block { struct list_head cb_list; }; struct netlink_ext_ack; struct flow_block_offload { enum flow_block_command command; enum flow_block_binder_type binder_type; bool block_shared; bool unlocked_driver_cb; struct net *net; struct flow_block *block; struct list_head cb_list; struct list_head *driver_block_list; struct netlink_ext_ack *extack; struct Qdisc *sch; struct list_head *cb_list_head; }; enum tc_setup_type; typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data, void *cb_priv); struct flow_block_cb; struct flow_block_indr { struct list_head list; struct net_device *dev; struct Qdisc *sch; enum flow_block_binder_type binder_type; void *data; void *cb_priv; void (*cleanup)(struct flow_block_cb *block_cb); }; struct flow_block_cb { struct list_head driver_list; struct list_head list; flow_setup_cb_t *cb; void *cb_ident; void *cb_priv; void (*release)(void *cb_priv); struct flow_block_indr indr; unsigned int refcnt; }; struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)); struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv), struct flow_block_offload *bo, struct net_device *dev, struct Qdisc *sch, void *data, void *indr_cb_priv, void (*cleanup)(struct flow_block_cb *block_cb)); void flow_block_cb_free(struct flow_block_cb *block_cb); struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, flow_setup_cb_t *cb, void *cb_ident); void *flow_block_cb_priv(struct flow_block_cb *block_cb); void flow_block_cb_incref(struct flow_block_cb *block_cb); unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb); static inline void flow_block_cb_add(struct flow_block_cb *block_cb, struct flow_block_offload *offload) { list_add_tail(&block_cb->list, &offload->cb_list); } static inline void flow_block_cb_remove(struct flow_block_cb *block_cb, struct flow_block_offload *offload) { list_move(&block_cb->list, &offload->cb_list); } static inline void flow_indr_block_cb_remove(struct flow_block_cb *block_cb, struct flow_block_offload *offload) { list_del(&block_cb->indr.list); list_move(&block_cb->list, &offload->cb_list); } bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list); int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_list, flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only); enum flow_cls_command { FLOW_CLS_REPLACE, FLOW_CLS_DESTROY, FLOW_CLS_STATS, FLOW_CLS_TMPLT_CREATE, FLOW_CLS_TMPLT_DESTROY, }; struct flow_cls_common_offload { u32 chain_index; __be16 protocol; u32 prio; struct netlink_ext_ack *extack; }; struct flow_cls_offload { struct flow_cls_common_offload common; enum flow_cls_command command; bool use_act_stats; unsigned long cookie; struct flow_rule *rule; struct flow_stats stats; u32 classid; }; enum offload_act_command { FLOW_ACT_REPLACE, FLOW_ACT_DESTROY, FLOW_ACT_STATS, }; struct flow_offload_action { struct netlink_ext_ack *extack; /* NULL in FLOW_ACT_STATS process*/ enum offload_act_command command; enum flow_action_id id; u32 index; unsigned long cookie; struct flow_stats stats; struct flow_action action; }; struct flow_offload_action *offload_action_alloc(unsigned int num_actions); static inline struct flow_rule * flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) { return flow_cmd->rule; } static inline void flow_block_init(struct flow_block *flow_block) { INIT_LIST_HEAD(&flow_block->cb_list); } typedef int flow_indr_block_bind_cb_t(struct net_device *dev, struct Qdisc *sch, void *cb_priv, enum tc_setup_type type, void *type_data, void *data, void (*cleanup)(struct flow_block_cb *block_cb)); int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv); void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv, void (*release)(void *cb_priv)); int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, enum tc_setup_type type, void *data, struct flow_block_offload *bo, void (*cleanup)(struct flow_block_cb *block_cb)); bool flow_indr_dev_exists(void); #endif /* _NET_FLOW_OFFLOAD_H */ |
| 15 16 20 11 141 138 2 9 136 2 2 124 124 124 15 15 4 3 4 4 136 135 11 85 52 122 15 20 20 6 6 6 132 141 8 8 1 11 140 141 141 141 140 138 125 11 8 5 2 6 6 6 11 1 1 11 31 1 11 11 20 20 20 20 20 20 20 20 2 19 95 95 95 95 6 1 5 5 13 13 3 14 13 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * Basic worker thread pool for io_uring * * Copyright (C) 2019 Jens Axboe * */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/rculist_nulls.h> #include <linux/cpu.h> #include <linux/task_work.h> #include <linux/audit.h> #include <linux/mmu_context.h> #include <uapi/linux/io_uring.h> #include "io-wq.h" #include "slist.h" #include "io_uring.h" #define WORKER_IDLE_TIMEOUT (5 * HZ) enum { IO_WORKER_F_UP = 0, /* up and active */ IO_WORKER_F_RUNNING = 1, /* account as running */ IO_WORKER_F_FREE = 2, /* worker on free list */ IO_WORKER_F_BOUND = 3, /* is doing bounded work */ }; enum { IO_WQ_BIT_EXIT = 0, /* wq exiting */ }; enum { IO_ACCT_STALLED_BIT = 0, /* stalled on hash */ }; /* * One for each thread in a wq pool */ struct io_worker { refcount_t ref; int create_index; unsigned long flags; struct hlist_nulls_node nulls_node; struct list_head all_list; struct task_struct *task; struct io_wq *wq; struct io_wq_work *cur_work; raw_spinlock_t lock; struct completion ref_done; unsigned long create_state; struct callback_head create_work; union { struct rcu_head rcu; struct work_struct work; }; }; #if BITS_PER_LONG == 64 #define IO_WQ_HASH_ORDER 6 #else #define IO_WQ_HASH_ORDER 5 #endif #define IO_WQ_NR_HASH_BUCKETS (1u << IO_WQ_HASH_ORDER) struct io_wq_acct { unsigned nr_workers; unsigned max_workers; int index; atomic_t nr_running; raw_spinlock_t lock; struct io_wq_work_list work_list; unsigned long flags; }; enum { IO_WQ_ACCT_BOUND, IO_WQ_ACCT_UNBOUND, IO_WQ_ACCT_NR, }; /* * Per io_wq state */ struct io_wq { unsigned long state; free_work_fn *free_work; io_wq_work_fn *do_work; struct io_wq_hash *hash; atomic_t worker_refs; struct completion worker_done; struct hlist_node cpuhp_node; struct task_struct *task; struct io_wq_acct acct[IO_WQ_ACCT_NR]; /* lock protects access to elements below */ raw_spinlock_t lock; struct hlist_nulls_head free_list; struct list_head all_list; struct wait_queue_entry wait; struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS]; cpumask_var_t cpu_mask; }; static enum cpuhp_state io_wq_online; struct io_cb_cancel_data { work_cancel_fn *fn; void *data; int nr_running; int nr_pending; bool cancel_all; }; static bool create_io_worker(struct io_wq *wq, int index); static void io_wq_dec_running(struct io_worker *worker); static bool io_acct_cancel_pending_work(struct io_wq *wq, struct io_wq_acct *acct, struct io_cb_cancel_data *match); static void create_worker_cb(struct callback_head *cb); static void io_wq_cancel_tw_create(struct io_wq *wq); static bool io_worker_get(struct io_worker *worker) { return refcount_inc_not_zero(&worker->ref); } static void io_worker_release(struct io_worker *worker) { if (refcount_dec_and_test(&worker->ref)) complete(&worker->ref_done); } static inline struct io_wq_acct *io_get_acct(struct io_wq *wq, bool bound) { return &wq->acct[bound ? IO_WQ_ACCT_BOUND : IO_WQ_ACCT_UNBOUND]; } static inline struct io_wq_acct *io_work_get_acct(struct io_wq *wq, struct io_wq_work *work) { return io_get_acct(wq, !(work->flags & IO_WQ_WORK_UNBOUND)); } static inline struct io_wq_acct *io_wq_get_acct(struct io_worker *worker) { return io_get_acct(worker->wq, test_bit(IO_WORKER_F_BOUND, &worker->flags)); } static void io_worker_ref_put(struct io_wq *wq) { if (atomic_dec_and_test(&wq->worker_refs)) complete(&wq->worker_done); } bool io_wq_worker_stopped(void) { struct io_worker *worker = current->worker_private; if (WARN_ON_ONCE(!io_wq_current_is_worker())) return true; return test_bit(IO_WQ_BIT_EXIT, &worker->wq->state); } static void io_worker_cancel_cb(struct io_worker *worker) { struct io_wq_acct *acct = io_wq_get_acct(worker); struct io_wq *wq = worker->wq; atomic_dec(&acct->nr_running); raw_spin_lock(&wq->lock); acct->nr_workers--; raw_spin_unlock(&wq->lock); io_worker_ref_put(wq); clear_bit_unlock(0, &worker->create_state); io_worker_release(worker); } static bool io_task_worker_match(struct callback_head *cb, void *data) { struct io_worker *worker; if (cb->func != create_worker_cb) return false; worker = container_of(cb, struct io_worker, create_work); return worker == data; } static void io_worker_exit(struct io_worker *worker) { struct io_wq *wq = worker->wq; while (1) { struct callback_head *cb = task_work_cancel_match(wq->task, io_task_worker_match, worker); if (!cb) break; io_worker_cancel_cb(worker); } io_worker_release(worker); wait_for_completion(&worker->ref_done); raw_spin_lock(&wq->lock); if (test_bit(IO_WORKER_F_FREE, &worker->flags)) hlist_nulls_del_rcu(&worker->nulls_node); list_del_rcu(&worker->all_list); raw_spin_unlock(&wq->lock); io_wq_dec_running(worker); /* * this worker is a goner, clear ->worker_private to avoid any * inc/dec running calls that could happen as part of exit from * touching 'worker'. */ current->worker_private = NULL; kfree_rcu(worker, rcu); io_worker_ref_put(wq); do_exit(0); } static inline bool __io_acct_run_queue(struct io_wq_acct *acct) { return !test_bit(IO_ACCT_STALLED_BIT, &acct->flags) && !wq_list_empty(&acct->work_list); } /* * If there's work to do, returns true with acct->lock acquired. If not, * returns false with no lock held. */ static inline bool io_acct_run_queue(struct io_wq_acct *acct) __acquires(&acct->lock) { raw_spin_lock(&acct->lock); if (__io_acct_run_queue(acct)) return true; raw_spin_unlock(&acct->lock); return false; } /* * Check head of free list for an available worker. If one isn't available, * caller must create one. */ static bool io_wq_activate_free_worker(struct io_wq *wq, struct io_wq_acct *acct) __must_hold(RCU) { struct hlist_nulls_node *n; struct io_worker *worker; /* * Iterate free_list and see if we can find an idle worker to * activate. If a given worker is on the free_list but in the process * of exiting, keep trying. */ hlist_nulls_for_each_entry_rcu(worker, n, &wq->free_list, nulls_node) { if (!io_worker_get(worker)) continue; if (io_wq_get_acct(worker) != acct) { io_worker_release(worker); continue; } /* * If the worker is already running, it's either already * starting work or finishing work. In either case, if it does * to go sleep, we'll kick off a new task for this work anyway. */ wake_up_process(worker->task); io_worker_release(worker); return true; } return false; } /* * We need a worker. If we find a free one, we're good. If not, and we're * below the max number of workers, create one. */ static bool io_wq_create_worker(struct io_wq *wq, struct io_wq_acct *acct) { /* * Most likely an attempt to queue unbounded work on an io_wq that * wasn't setup with any unbounded workers. */ if (unlikely(!acct->max_workers)) pr_warn_once("io-wq is not configured for unbound workers"); raw_spin_lock(&wq->lock); if (acct->nr_workers >= acct->max_workers) { raw_spin_unlock(&wq->lock); return true; } acct->nr_workers++; raw_spin_unlock(&wq->lock); atomic_inc(&acct->nr_running); atomic_inc(&wq->worker_refs); return create_io_worker(wq, acct->index); } static void io_wq_inc_running(struct io_worker *worker) { struct io_wq_acct *acct = io_wq_get_acct(worker); atomic_inc(&acct->nr_running); } static void create_worker_cb(struct callback_head *cb) { struct io_worker *worker; struct io_wq *wq; struct io_wq_acct *acct; bool do_create = false; worker = container_of(cb, struct io_worker, create_work); wq = worker->wq; acct = &wq->acct[worker->create_index]; raw_spin_lock(&wq->lock); if (acct->nr_workers < acct->max_workers) { acct->nr_workers++; do_create = true; } raw_spin_unlock(&wq->lock); if (do_create) { create_io_worker(wq, worker->create_index); } else { atomic_dec(&acct->nr_running); io_worker_ref_put(wq); } clear_bit_unlock(0, &worker->create_state); io_worker_release(worker); } static bool io_queue_worker_create(struct io_worker *worker, struct io_wq_acct *acct, task_work_func_t func) { struct io_wq *wq = worker->wq; /* raced with exit, just ignore create call */ if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) goto fail; if (!io_worker_get(worker)) goto fail; /* * create_state manages ownership of create_work/index. We should * only need one entry per worker, as the worker going to sleep * will trigger the condition, and waking will clear it once it * runs the task_work. */ if (test_bit(0, &worker->create_state) || test_and_set_bit_lock(0, &worker->create_state)) goto fail_release; atomic_inc(&wq->worker_refs); init_task_work(&worker->create_work, func); worker->create_index = acct->index; if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) { /* * EXIT may have been set after checking it above, check after * adding the task_work and remove any creation item if it is * now set. wq exit does that too, but we can have added this * work item after we canceled in io_wq_exit_workers(). */ if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) io_wq_cancel_tw_create(wq); io_worker_ref_put(wq); return true; } io_worker_ref_put(wq); clear_bit_unlock(0, &worker->create_state); fail_release: io_worker_release(worker); fail: atomic_dec(&acct->nr_running); io_worker_ref_put(wq); return false; } static void io_wq_dec_running(struct io_worker *worker) { struct io_wq_acct *acct = io_wq_get_acct(worker); struct io_wq *wq = worker->wq; if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; if (!atomic_dec_and_test(&acct->nr_running)) return; if (!io_acct_run_queue(acct)) return; raw_spin_unlock(&acct->lock); atomic_inc(&acct->nr_running); atomic_inc(&wq->worker_refs); io_queue_worker_create(worker, acct, create_worker_cb); } /* * Worker will start processing some work. Move it to the busy list, if * it's currently on the freelist */ static void __io_worker_busy(struct io_wq *wq, struct io_worker *worker) { if (test_bit(IO_WORKER_F_FREE, &worker->flags)) { clear_bit(IO_WORKER_F_FREE, &worker->flags); raw_spin_lock(&wq->lock); hlist_nulls_del_init_rcu(&worker->nulls_node); raw_spin_unlock(&wq->lock); } } /* * No work, worker going to sleep. Move to freelist. */ static void __io_worker_idle(struct io_wq *wq, struct io_worker *worker) __must_hold(wq->lock) { if (!test_bit(IO_WORKER_F_FREE, &worker->flags)) { set_bit(IO_WORKER_F_FREE, &worker->flags); hlist_nulls_add_head_rcu(&worker->nulls_node, &wq->free_list); } } static inline unsigned int io_get_work_hash(struct io_wq_work *work) { return work->flags >> IO_WQ_HASH_SHIFT; } static bool io_wait_on_hash(struct io_wq *wq, unsigned int hash) { bool ret = false; spin_lock_irq(&wq->hash->wait.lock); if (list_empty(&wq->wait.entry)) { __add_wait_queue(&wq->hash->wait, &wq->wait); if (!test_bit(hash, &wq->hash->map)) { __set_current_state(TASK_RUNNING); list_del_init(&wq->wait.entry); ret = true; } } spin_unlock_irq(&wq->hash->wait.lock); return ret; } static struct io_wq_work *io_get_next_work(struct io_wq_acct *acct, struct io_worker *worker) __must_hold(acct->lock) { struct io_wq_work_node *node, *prev; struct io_wq_work *work, *tail; unsigned int stall_hash = -1U; struct io_wq *wq = worker->wq; wq_list_for_each(node, prev, &acct->work_list) { unsigned int hash; work = container_of(node, struct io_wq_work, list); /* not hashed, can run anytime */ if (!io_wq_is_hashed(work)) { wq_list_del(&acct->work_list, node, prev); return work; } hash = io_get_work_hash(work); /* all items with this hash lie in [work, tail] */ tail = wq->hash_tail[hash]; /* hashed, can run if not already running */ if (!test_and_set_bit(hash, &wq->hash->map)) { wq->hash_tail[hash] = NULL; wq_list_cut(&acct->work_list, &tail->list, prev); return work; } if (stall_hash == -1U) stall_hash = hash; /* fast forward to a next hash, for-each will fix up @prev */ node = &tail->list; } if (stall_hash != -1U) { bool unstalled; /* * Set this before dropping the lock to avoid racing with new * work being added and clearing the stalled bit. */ set_bit(IO_ACCT_STALLED_BIT, &acct->flags); raw_spin_unlock(&acct->lock); unstalled = io_wait_on_hash(wq, stall_hash); raw_spin_lock(&acct->lock); if (unstalled) { clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); if (wq_has_sleeper(&wq->hash->wait)) wake_up(&wq->hash->wait); } } return NULL; } static void io_assign_current_work(struct io_worker *worker, struct io_wq_work *work) { if (work) { io_run_task_work(); cond_resched(); } raw_spin_lock(&worker->lock); worker->cur_work = work; raw_spin_unlock(&worker->lock); } /* * Called with acct->lock held, drops it before returning */ static void io_worker_handle_work(struct io_wq_acct *acct, struct io_worker *worker) __releases(&acct->lock) { struct io_wq *wq = worker->wq; bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); do { struct io_wq_work *work; /* * If we got some work, mark us as busy. If we didn't, but * the list isn't empty, it means we stalled on hashed work. * Mark us stalled so we don't keep looking for work when we * can't make progress, any work completion or insertion will * clear the stalled flag. */ work = io_get_next_work(acct, worker); if (work) { /* * Make sure cancelation can find this, even before * it becomes the active work. That avoids a window * where the work has been removed from our general * work list, but isn't yet discoverable as the * current work item for this worker. */ raw_spin_lock(&worker->lock); worker->cur_work = work; raw_spin_unlock(&worker->lock); } raw_spin_unlock(&acct->lock); if (!work) break; __io_worker_busy(wq, worker); io_assign_current_work(worker, work); __set_current_state(TASK_RUNNING); /* handle a whole dependent link */ do { struct io_wq_work *next_hashed, *linked; unsigned int hash = io_get_work_hash(work); next_hashed = wq_next_work(work); if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND)) work->flags |= IO_WQ_WORK_CANCEL; wq->do_work(work); io_assign_current_work(worker, NULL); linked = wq->free_work(work); work = next_hashed; if (!work && linked && !io_wq_is_hashed(linked)) { work = linked; linked = NULL; } io_assign_current_work(worker, work); if (linked) io_wq_enqueue(wq, linked); if (hash != -1U && !next_hashed) { /* serialize hash clear with wake_up() */ spin_lock_irq(&wq->hash->wait.lock); clear_bit(hash, &wq->hash->map); clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); spin_unlock_irq(&wq->hash->wait.lock); if (wq_has_sleeper(&wq->hash->wait)) wake_up(&wq->hash->wait); } } while (work); if (!__io_acct_run_queue(acct)) break; raw_spin_lock(&acct->lock); } while (1); } static int io_wq_worker(void *data) { struct io_worker *worker = data; struct io_wq_acct *acct = io_wq_get_acct(worker); struct io_wq *wq = worker->wq; bool exit_mask = false, last_timeout = false; char buf[TASK_COMM_LEN]; set_mask_bits(&worker->flags, 0, BIT(IO_WORKER_F_UP) | BIT(IO_WORKER_F_RUNNING)); snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); set_task_comm(current, buf); while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { long ret; set_current_state(TASK_INTERRUPTIBLE); /* * If we have work to do, io_acct_run_queue() returns with * the acct->lock held. If not, it will drop it. */ while (io_acct_run_queue(acct)) io_worker_handle_work(acct, worker); raw_spin_lock(&wq->lock); /* * Last sleep timed out. Exit if we're not the last worker, * or if someone modified our affinity. */ if (last_timeout && (exit_mask || acct->nr_workers > 1)) { acct->nr_workers--; raw_spin_unlock(&wq->lock); __set_current_state(TASK_RUNNING); break; } last_timeout = false; __io_worker_idle(wq, worker); raw_spin_unlock(&wq->lock); if (io_run_task_work()) continue; ret = schedule_timeout(WORKER_IDLE_TIMEOUT); if (signal_pending(current)) { struct ksignal ksig; if (!get_signal(&ksig)) continue; break; } if (!ret) { last_timeout = true; exit_mask = !cpumask_test_cpu(raw_smp_processor_id(), wq->cpu_mask); } } if (test_bit(IO_WQ_BIT_EXIT, &wq->state) && io_acct_run_queue(acct)) io_worker_handle_work(acct, worker); io_worker_exit(worker); return 0; } /* * Called when a worker is scheduled in. Mark us as currently running. */ void io_wq_worker_running(struct task_struct *tsk) { struct io_worker *worker = tsk->worker_private; if (!worker) return; if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; if (test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; set_bit(IO_WORKER_F_RUNNING, &worker->flags); io_wq_inc_running(worker); } /* * Called when worker is going to sleep. If there are no workers currently * running and we have work pending, wake up a free one or create a new one. */ void io_wq_worker_sleeping(struct task_struct *tsk) { struct io_worker *worker = tsk->worker_private; if (!worker) return; if (!test_bit(IO_WORKER_F_UP, &worker->flags)) return; if (!test_bit(IO_WORKER_F_RUNNING, &worker->flags)) return; clear_bit(IO_WORKER_F_RUNNING, &worker->flags); io_wq_dec_running(worker); } static void io_init_new_worker(struct io_wq *wq, struct io_worker *worker, struct task_struct *tsk) { tsk->worker_private = worker; worker->task = tsk; set_cpus_allowed_ptr(tsk, wq->cpu_mask); raw_spin_lock(&wq->lock); hlist_nulls_add_head_rcu(&worker->nulls_node, &wq->free_list); list_add_tail_rcu(&worker->all_list, &wq->all_list); set_bit(IO_WORKER_F_FREE, &worker->flags); raw_spin_unlock(&wq->lock); wake_up_new_task(tsk); } static bool io_wq_work_match_all(struct io_wq_work *work, void *data) { return true; } static inline bool io_should_retry_thread(long err) { /* * Prevent perpetual task_work retry, if the task (or its group) is * exiting. */ if (fatal_signal_pending(current)) return false; switch (err) { case -EAGAIN: case -ERESTARTSYS: case -ERESTARTNOINTR: case -ERESTARTNOHAND: return true; default: return false; } } static void create_worker_cont(struct callback_head *cb) { struct io_worker *worker; struct task_struct *tsk; struct io_wq *wq; worker = container_of(cb, struct io_worker, create_work); clear_bit_unlock(0, &worker->create_state); wq = worker->wq; tsk = create_io_thread(io_wq_worker, worker, NUMA_NO_NODE); if (!IS_ERR(tsk)) { io_init_new_worker(wq, worker, tsk); io_worker_release(worker); return; } else if (!io_should_retry_thread(PTR_ERR(tsk))) { struct io_wq_acct *acct = io_wq_get_acct(worker); atomic_dec(&acct->nr_running); raw_spin_lock(&wq->lock); acct->nr_workers--; if (!acct->nr_workers) { struct io_cb_cancel_data match = { .fn = io_wq_work_match_all, .cancel_all = true, }; raw_spin_unlock(&wq->lock); while (io_acct_cancel_pending_work(wq, acct, &match)) ; } else { raw_spin_unlock(&wq->lock); } io_worker_ref_put(wq); kfree(worker); return; } /* re-create attempts grab a new worker ref, drop the existing one */ io_worker_release(worker); schedule_work(&worker->work); } static void io_workqueue_create(struct work_struct *work) { struct io_worker *worker = container_of(work, struct io_worker, work); struct io_wq_acct *acct = io_wq_get_acct(worker); if (!io_queue_worker_create(worker, acct, create_worker_cont)) kfree(worker); } static bool create_io_worker(struct io_wq *wq, int index) { struct io_wq_acct *acct = &wq->acct[index]; struct io_worker *worker; struct task_struct *tsk; __set_current_state(TASK_RUNNING); worker = kzalloc(sizeof(*worker), GFP_KERNEL); if (!worker) { fail: atomic_dec(&acct->nr_running); raw_spin_lock(&wq->lock); acct->nr_workers--; raw_spin_unlock(&wq->lock); io_worker_ref_put(wq); return false; } refcount_set(&worker->ref, 1); worker->wq = wq; raw_spin_lock_init(&worker->lock); init_completion(&worker->ref_done); if (index == IO_WQ_ACCT_BOUND) set_bit(IO_WORKER_F_BOUND, &worker->flags); tsk = create_io_thread(io_wq_worker, worker, NUMA_NO_NODE); if (!IS_ERR(tsk)) { io_init_new_worker(wq, worker, tsk); } else if (!io_should_retry_thread(PTR_ERR(tsk))) { kfree(worker); goto fail; } else { INIT_WORK(&worker->work, io_workqueue_create); schedule_work(&worker->work); } return true; } /* * Iterate the passed in list and call the specific function for each * worker that isn't exiting */ static bool io_wq_for_each_worker(struct io_wq *wq, bool (*func)(struct io_worker *, void *), void *data) { struct io_worker *worker; bool ret = false; list_for_each_entry_rcu(worker, &wq->all_list, all_list) { if (io_worker_get(worker)) { /* no task if node is/was offline */ if (worker->task) ret = func(worker, data); io_worker_release(worker); if (ret) break; } } return ret; } static bool io_wq_worker_wake(struct io_worker *worker, void *data) { __set_notify_signal(worker->task); wake_up_process(worker->task); return false; } static void io_run_cancel(struct io_wq_work *work, struct io_wq *wq) { do { work->flags |= IO_WQ_WORK_CANCEL; wq->do_work(work); work = wq->free_work(work); } while (work); } static void io_wq_insert_work(struct io_wq *wq, struct io_wq_work *work) { struct io_wq_acct *acct = io_work_get_acct(wq, work); unsigned int hash; struct io_wq_work *tail; if (!io_wq_is_hashed(work)) { append: wq_list_add_tail(&work->list, &acct->work_list); return; } hash = io_get_work_hash(work); tail = wq->hash_tail[hash]; wq->hash_tail[hash] = work; if (!tail) goto append; wq_list_add_after(&work->list, &tail->list, &acct->work_list); } static bool io_wq_work_match_item(struct io_wq_work *work, void *data) { return work == data; } void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work) { struct io_wq_acct *acct = io_work_get_acct(wq, work); unsigned long work_flags = work->flags; struct io_cb_cancel_data match; bool do_create; /* * If io-wq is exiting for this task, or if the request has explicitly * been marked as one that should not get executed, cancel it here. */ if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || (work->flags & IO_WQ_WORK_CANCEL)) { io_run_cancel(work, wq); return; } raw_spin_lock(&acct->lock); io_wq_insert_work(wq, work); clear_bit(IO_ACCT_STALLED_BIT, &acct->flags); raw_spin_unlock(&acct->lock); rcu_read_lock(); do_create = !io_wq_activate_free_worker(wq, acct); rcu_read_unlock(); if (do_create && ((work_flags & IO_WQ_WORK_CONCURRENT) || !atomic_read(&acct->nr_running))) { bool did_create; did_create = io_wq_create_worker(wq, acct); if (likely(did_create)) return; raw_spin_lock(&wq->lock); if (acct->nr_workers) { raw_spin_unlock(&wq->lock); return; } raw_spin_unlock(&wq->lock); /* fatal condition, failed to create the first worker */ match.fn = io_wq_work_match_item, match.data = work, match.cancel_all = false, io_acct_cancel_pending_work(wq, acct, &match); } } /* * Work items that hash to the same value will not be done in parallel. * Used to limit concurrent writes, generally hashed by inode. */ void io_wq_hash_work(struct io_wq_work *work, void *val) { unsigned int bit; bit = hash_ptr(val, IO_WQ_HASH_ORDER); work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT)); } static bool __io_wq_worker_cancel(struct io_worker *worker, struct io_cb_cancel_data *match, struct io_wq_work *work) { if (work && match->fn(work, match->data)) { work->flags |= IO_WQ_WORK_CANCEL; __set_notify_signal(worker->task); return true; } return false; } static bool io_wq_worker_cancel(struct io_worker *worker, void *data) { struct io_cb_cancel_data *match = data; /* * Hold the lock to avoid ->cur_work going out of scope, caller * may dereference the passed in work. */ raw_spin_lock(&worker->lock); if (__io_wq_worker_cancel(worker, match, worker->cur_work)) match->nr_running++; raw_spin_unlock(&worker->lock); return match->nr_running && !match->cancel_all; } static inline void io_wq_remove_pending(struct io_wq *wq, struct io_wq_work *work, struct io_wq_work_node *prev) { struct io_wq_acct *acct = io_work_get_acct(wq, work); unsigned int hash = io_get_work_hash(work); struct io_wq_work *prev_work = NULL; if (io_wq_is_hashed(work) && work == wq->hash_tail[hash]) { if (prev) prev_work = container_of(prev, struct io_wq_work, list); if (prev_work && io_get_work_hash(prev_work) == hash) wq->hash_tail[hash] = prev_work; else wq->hash_tail[hash] = NULL; } wq_list_del(&acct->work_list, &work->list, prev); } static bool io_acct_cancel_pending_work(struct io_wq *wq, struct io_wq_acct *acct, struct io_cb_cancel_data *match) { struct io_wq_work_node *node, *prev; struct io_wq_work *work; raw_spin_lock(&acct->lock); wq_list_for_each(node, prev, &acct->work_list) { work = container_of(node, struct io_wq_work, list); if (!match->fn(work, match->data)) continue; io_wq_remove_pending(wq, work, prev); raw_spin_unlock(&acct->lock); io_run_cancel(work, wq); match->nr_pending++; /* not safe to continue after unlock */ return true; } raw_spin_unlock(&acct->lock); return false; } static void io_wq_cancel_pending_work(struct io_wq *wq, struct io_cb_cancel_data *match) { int i; retry: for (i = 0; i < IO_WQ_ACCT_NR; i++) { struct io_wq_acct *acct = io_get_acct(wq, i == 0); if (io_acct_cancel_pending_work(wq, acct, match)) { if (match->cancel_all) goto retry; break; } } } static void io_wq_cancel_running_work(struct io_wq *wq, struct io_cb_cancel_data *match) { rcu_read_lock(); io_wq_for_each_worker(wq, io_wq_worker_cancel, match); rcu_read_unlock(); } enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel, void *data, bool cancel_all) { struct io_cb_cancel_data match = { .fn = cancel, .data = data, .cancel_all = cancel_all, }; /* * First check pending list, if we're lucky we can just remove it * from there. CANCEL_OK means that the work is returned as-new, * no completion will be posted for it. * * Then check if a free (going busy) or busy worker has the work * currently running. If we find it there, we'll return CANCEL_RUNNING * as an indication that we attempt to signal cancellation. The * completion will run normally in this case. * * Do both of these while holding the wq->lock, to ensure that * we'll find a work item regardless of state. */ io_wq_cancel_pending_work(wq, &match); if (match.nr_pending && !match.cancel_all) return IO_WQ_CANCEL_OK; raw_spin_lock(&wq->lock); io_wq_cancel_running_work(wq, &match); raw_spin_unlock(&wq->lock); if (match.nr_running && !match.cancel_all) return IO_WQ_CANCEL_RUNNING; if (match.nr_running) return IO_WQ_CANCEL_RUNNING; if (match.nr_pending) return IO_WQ_CANCEL_OK; return IO_WQ_CANCEL_NOTFOUND; } static int io_wq_hash_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct io_wq *wq = container_of(wait, struct io_wq, wait); int i; list_del_init(&wait->entry); rcu_read_lock(); for (i = 0; i < IO_WQ_ACCT_NR; i++) { struct io_wq_acct *acct = &wq->acct[i]; if (test_and_clear_bit(IO_ACCT_STALLED_BIT, &acct->flags)) io_wq_activate_free_worker(wq, acct); } rcu_read_unlock(); return 1; } struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) { int ret, i; struct io_wq *wq; if (WARN_ON_ONCE(!data->free_work || !data->do_work)) return ERR_PTR(-EINVAL); if (WARN_ON_ONCE(!bounded)) return ERR_PTR(-EINVAL); wq = kzalloc(sizeof(struct io_wq), GFP_KERNEL); if (!wq) return ERR_PTR(-ENOMEM); refcount_inc(&data->hash->refs); wq->hash = data->hash; wq->free_work = data->free_work; wq->do_work = data->do_work; ret = -ENOMEM; if (!alloc_cpumask_var(&wq->cpu_mask, GFP_KERNEL)) goto err; cpumask_copy(wq->cpu_mask, cpu_possible_mask); wq->acct[IO_WQ_ACCT_BOUND].max_workers = bounded; wq->acct[IO_WQ_ACCT_UNBOUND].max_workers = task_rlimit(current, RLIMIT_NPROC); INIT_LIST_HEAD(&wq->wait.entry); wq->wait.func = io_wq_hash_wake; for (i = 0; i < IO_WQ_ACCT_NR; i++) { struct io_wq_acct *acct = &wq->acct[i]; acct->index = i; atomic_set(&acct->nr_running, 0); INIT_WQ_LIST(&acct->work_list); raw_spin_lock_init(&acct->lock); } raw_spin_lock_init(&wq->lock); INIT_HLIST_NULLS_HEAD(&wq->free_list, 0); INIT_LIST_HEAD(&wq->all_list); wq->task = get_task_struct(data->task); atomic_set(&wq->worker_refs, 1); init_completion(&wq->worker_done); ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); if (ret) goto err; return wq; err: io_wq_put_hash(data->hash); free_cpumask_var(wq->cpu_mask); kfree(wq); return ERR_PTR(ret); } static bool io_task_work_match(struct callback_head *cb, void *data) { struct io_worker *worker; if (cb->func != create_worker_cb && cb->func != create_worker_cont) return false; worker = container_of(cb, struct io_worker, create_work); return worker->wq == data; } void io_wq_exit_start(struct io_wq *wq) { set_bit(IO_WQ_BIT_EXIT, &wq->state); } static void io_wq_cancel_tw_create(struct io_wq *wq) { struct callback_head *cb; while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { struct io_worker *worker; worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); /* * Only the worker continuation helper has worker allocated and * hence needs freeing. */ if (cb->func == create_worker_cont) kfree(worker); } } static void io_wq_exit_workers(struct io_wq *wq) { if (!wq->task) return; io_wq_cancel_tw_create(wq); rcu_read_lock(); io_wq_for_each_worker(wq, io_wq_worker_wake, NULL); rcu_read_unlock(); io_worker_ref_put(wq); wait_for_completion(&wq->worker_done); spin_lock_irq(&wq->hash->wait.lock); list_del_init(&wq->wait.entry); spin_unlock_irq(&wq->hash->wait.lock); put_task_struct(wq->task); wq->task = NULL; } static void io_wq_destroy(struct io_wq *wq) { struct io_cb_cancel_data match = { .fn = io_wq_work_match_all, .cancel_all = true, }; cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); io_wq_cancel_pending_work(wq, &match); free_cpumask_var(wq->cpu_mask); io_wq_put_hash(wq->hash); kfree(wq); } void io_wq_put_and_exit(struct io_wq *wq) { WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state)); io_wq_exit_workers(wq); io_wq_destroy(wq); } struct online_data { unsigned int cpu; bool online; }; static bool io_wq_worker_affinity(struct io_worker *worker, void *data) { struct online_data *od = data; if (od->online) cpumask_set_cpu(od->cpu, worker->wq->cpu_mask); else cpumask_clear_cpu(od->cpu, worker->wq->cpu_mask); return false; } static int __io_wq_cpu_online(struct io_wq *wq, unsigned int cpu, bool online) { struct online_data od = { .cpu = cpu, .online = online }; rcu_read_lock(); io_wq_for_each_worker(wq, io_wq_worker_affinity, &od); rcu_read_unlock(); return 0; } static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node) { struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); return __io_wq_cpu_online(wq, cpu, true); } static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node) { struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); return __io_wq_cpu_online(wq, cpu, false); } int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask) { if (!tctx || !tctx->io_wq) return -EINVAL; rcu_read_lock(); if (mask) cpumask_copy(tctx->io_wq->cpu_mask, mask); else cpumask_copy(tctx->io_wq->cpu_mask, cpu_possible_mask); rcu_read_unlock(); return 0; } /* * Set max number of unbounded workers, returns old value. If new_count is 0, * then just return the old value. */ int io_wq_max_workers(struct io_wq *wq, int *new_count) { struct io_wq_acct *acct; int prev[IO_WQ_ACCT_NR]; int i; BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND); BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND); BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2); for (i = 0; i < IO_WQ_ACCT_NR; i++) { if (new_count[i] > task_rlimit(current, RLIMIT_NPROC)) new_count[i] = task_rlimit(current, RLIMIT_NPROC); } for (i = 0; i < IO_WQ_ACCT_NR; i++) prev[i] = 0; rcu_read_lock(); raw_spin_lock(&wq->lock); for (i = 0; i < IO_WQ_ACCT_NR; i++) { acct = &wq->acct[i]; prev[i] = max_t(int, acct->max_workers, prev[i]); if (new_count[i]) acct->max_workers = new_count[i]; } raw_spin_unlock(&wq->lock); rcu_read_unlock(); for (i = 0; i < IO_WQ_ACCT_NR; i++) new_count[i] = prev[i]; return 0; } static __init int io_wq_init(void) { int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online", io_wq_cpu_online, io_wq_cpu_offline); if (ret < 0) return ret; io_wq_online = ret; return 0; } subsys_initcall(io_wq_init); |
| 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/common.c - Common device power management code. * * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp. */ #include <linux/kernel.h> #include <linux/device.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/pm_clock.h> #include <linux/acpi.h> #include <linux/pm_domain.h> #include "power.h" /** * dev_pm_get_subsys_data - Create or refcount power.subsys_data for device. * @dev: Device to handle. * * If power.subsys_data is NULL, point it to a new object, otherwise increment * its reference counter. Return 0 if new object has been created or refcount * increased, otherwise negative error code. */ int dev_pm_get_subsys_data(struct device *dev) { struct pm_subsys_data *psd; psd = kzalloc(sizeof(*psd), GFP_KERNEL); if (!psd) return -ENOMEM; spin_lock_irq(&dev->power.lock); if (dev->power.subsys_data) { dev->power.subsys_data->refcount++; } else { spin_lock_init(&psd->lock); psd->refcount = 1; dev->power.subsys_data = psd; pm_clk_init(dev); psd = NULL; } spin_unlock_irq(&dev->power.lock); /* kfree() verifies that its argument is nonzero. */ kfree(psd); return 0; } EXPORT_SYMBOL_GPL(dev_pm_get_subsys_data); /** * dev_pm_put_subsys_data - Drop reference to power.subsys_data. * @dev: Device to handle. * * If the reference counter of power.subsys_data is zero after dropping the * reference, power.subsys_data is removed. */ void dev_pm_put_subsys_data(struct device *dev) { struct pm_subsys_data *psd; spin_lock_irq(&dev->power.lock); psd = dev_to_psd(dev); if (!psd) goto out; if (--psd->refcount == 0) dev->power.subsys_data = NULL; else psd = NULL; out: spin_unlock_irq(&dev->power.lock); kfree(psd); } EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data); /** * dev_pm_domain_attach - Attach a device to its PM domain. * @dev: Device to attach. * @power_on: Used to indicate whether we should power on the device. * * The @dev may only be attached to a single PM domain. By iterating through * the available alternatives we try to find a valid PM domain for the device. * As attachment succeeds, the ->detach() callback in the struct dev_pm_domain * should be assigned by the corresponding attach function. * * This function should typically be invoked from subsystem level code during * the probe phase. Especially for those that holds devices which requires * power management through PM domains. * * Callers must ensure proper synchronization of this function with power * management callbacks. * * Returns 0 on successfully attached PM domain, or when it is found that the * device doesn't need a PM domain, else a negative error code. */ int dev_pm_domain_attach(struct device *dev, bool power_on) { int ret; if (dev->pm_domain) return 0; ret = acpi_dev_pm_attach(dev, power_on); if (!ret) ret = genpd_dev_pm_attach(dev); return ret < 0 ? ret : 0; } EXPORT_SYMBOL_GPL(dev_pm_domain_attach); /** * dev_pm_domain_attach_by_id - Associate a device with one of its PM domains. * @dev: The device used to lookup the PM domain. * @index: The index of the PM domain. * * As @dev may only be attached to a single PM domain, the backend PM domain * provider creates a virtual device to attach instead. If attachment succeeds, * the ->detach() callback in the struct dev_pm_domain are assigned by the * corresponding backend attach function, as to deal with detaching of the * created virtual device. * * This function should typically be invoked by a driver during the probe phase, * in case its device requires power management through multiple PM domains. The * driver may benefit from using the received device, to configure device-links * towards its original device. Depending on the use-case and if needed, the * links may be dynamically changed by the driver, which allows it to control * the power to the PM domains independently from each other. * * Callers must ensure proper synchronization of this function with power * management callbacks. * * Returns the virtual created device when successfully attached to its PM * domain, NULL in case @dev don't need a PM domain, else an ERR_PTR(). * Note that, to detach the returned virtual device, the driver shall call * dev_pm_domain_detach() on it, typically during the remove phase. */ struct device *dev_pm_domain_attach_by_id(struct device *dev, unsigned int index) { if (dev->pm_domain) return ERR_PTR(-EEXIST); return genpd_dev_pm_attach_by_id(dev, index); } EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id); /** * dev_pm_domain_attach_by_name - Associate a device with one of its PM domains. * @dev: The device used to lookup the PM domain. * @name: The name of the PM domain. * * For a detailed function description, see dev_pm_domain_attach_by_id(). */ struct device *dev_pm_domain_attach_by_name(struct device *dev, const char *name) { if (dev->pm_domain) return ERR_PTR(-EEXIST); return genpd_dev_pm_attach_by_name(dev, name); } EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name); /** * dev_pm_domain_attach_list - Associate a device with its PM domains. * @dev: The device used to lookup the PM domains for. * @data: The data used for attaching to the PM domains. * @list: An out-parameter with an allocated list of attached PM domains. * * This function helps to attach a device to its multiple PM domains. The * caller, which is typically a driver's probe function, may provide a list of * names for the PM domains that we should try to attach the device to, but it * may also provide an empty list, in case the attach should be done for all of * the available PM domains. * * Callers must ensure proper synchronization of this function with power * management callbacks. * * Returns the number of attached PM domains or a negative error code in case of * a failure. Note that, to detach the list of PM domains, the driver shall call * dev_pm_domain_detach_list(), typically during the remove phase. */ int dev_pm_domain_attach_list(struct device *dev, const struct dev_pm_domain_attach_data *data, struct dev_pm_domain_list **list) { struct device_node *np = dev->of_node; struct dev_pm_domain_list *pds; struct device *pd_dev = NULL; int ret, i, num_pds = 0; bool by_id = true; u32 pd_flags = data ? data->pd_flags : 0; u32 link_flags = pd_flags & PD_FLAG_NO_DEV_LINK ? 0 : DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME; if (dev->pm_domain) return -EEXIST; /* For now this is limited to OF based platforms. */ if (!np) return 0; if (data && data->pd_names) { num_pds = data->num_pd_names; by_id = false; } else { num_pds = of_count_phandle_with_args(np, "power-domains", "#power-domain-cells"); } if (num_pds <= 0) return 0; pds = devm_kzalloc(dev, sizeof(*pds), GFP_KERNEL); if (!pds) return -ENOMEM; pds->pd_devs = devm_kcalloc(dev, num_pds, sizeof(*pds->pd_devs), GFP_KERNEL); if (!pds->pd_devs) return -ENOMEM; pds->pd_links = devm_kcalloc(dev, num_pds, sizeof(*pds->pd_links), GFP_KERNEL); if (!pds->pd_links) return -ENOMEM; if (link_flags && pd_flags & PD_FLAG_DEV_LINK_ON) link_flags |= DL_FLAG_RPM_ACTIVE; for (i = 0; i < num_pds; i++) { if (by_id) pd_dev = dev_pm_domain_attach_by_id(dev, i); else pd_dev = dev_pm_domain_attach_by_name(dev, data->pd_names[i]); if (IS_ERR_OR_NULL(pd_dev)) { ret = pd_dev ? PTR_ERR(pd_dev) : -ENODEV; goto err_attach; } if (link_flags) { struct device_link *link; link = device_link_add(dev, pd_dev, link_flags); if (!link) { ret = -ENODEV; goto err_link; } pds->pd_links[i] = link; } pds->pd_devs[i] = pd_dev; } pds->num_pds = num_pds; *list = pds; return num_pds; err_link: dev_pm_domain_detach(pd_dev, true); err_attach: while (--i >= 0) { if (pds->pd_links[i]) device_link_del(pds->pd_links[i]); dev_pm_domain_detach(pds->pd_devs[i], true); } return ret; } EXPORT_SYMBOL_GPL(dev_pm_domain_attach_list); /** * dev_pm_domain_detach - Detach a device from its PM domain. * @dev: Device to detach. * @power_off: Used to indicate whether we should power off the device. * * This functions will reverse the actions from dev_pm_domain_attach(), * dev_pm_domain_attach_by_id() and dev_pm_domain_attach_by_name(), thus it * detaches @dev from its PM domain. Typically it should be invoked during the * remove phase, either from subsystem level code or from drivers. * * Callers must ensure proper synchronization of this function with power * management callbacks. */ void dev_pm_domain_detach(struct device *dev, bool power_off) { if (dev->pm_domain && dev->pm_domain->detach) dev->pm_domain->detach(dev, power_off); } EXPORT_SYMBOL_GPL(dev_pm_domain_detach); /** * dev_pm_domain_detach_list - Detach a list of PM domains. * @list: The list of PM domains to detach. * * This function reverse the actions from dev_pm_domain_attach_list(). * Typically it should be invoked during the remove phase from drivers. * * Callers must ensure proper synchronization of this function with power * management callbacks. */ void dev_pm_domain_detach_list(struct dev_pm_domain_list *list) { int i; if (!list) return; for (i = 0; i < list->num_pds; i++) { if (list->pd_links[i]) device_link_del(list->pd_links[i]); dev_pm_domain_detach(list->pd_devs[i], true); } } EXPORT_SYMBOL_GPL(dev_pm_domain_detach_list); /** * dev_pm_domain_start - Start the device through its PM domain. * @dev: Device to start. * * This function should typically be called during probe by a subsystem/driver, * when it needs to start its device from the PM domain's perspective. Note * that, it's assumed that the PM domain is already powered on when this * function is called. * * Returns 0 on success and negative error values on failures. */ int dev_pm_domain_start(struct device *dev) { if (dev->pm_domain && dev->pm_domain->start) return dev->pm_domain->start(dev); return 0; } EXPORT_SYMBOL_GPL(dev_pm_domain_start); /** * dev_pm_domain_set - Set PM domain of a device. * @dev: Device whose PM domain is to be set. * @pd: PM domain to be set, or NULL. * * Sets the PM domain the device belongs to. The PM domain of a device needs * to be set before its probe finishes (it's bound to a driver). * * This function must be called with the device lock held. */ void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd) { if (dev->pm_domain == pd) return; WARN(pd && device_is_bound(dev), "PM domains can only be changed for unbound devices\n"); dev->pm_domain = pd; device_pm_check_callbacks(dev); } EXPORT_SYMBOL_GPL(dev_pm_domain_set); /** * dev_pm_domain_set_performance_state - Request a new performance state. * @dev: The device to make the request for. * @state: Target performance state for the device. * * This function should be called when a new performance state needs to be * requested for a device that is attached to a PM domain. Note that, the * support for performance scaling for PM domains is optional. * * Returns 0 on success and when performance scaling isn't supported, negative * error code on failure. */ int dev_pm_domain_set_performance_state(struct device *dev, unsigned int state) { if (dev->pm_domain && dev->pm_domain->set_performance_state) return dev->pm_domain->set_performance_state(dev, state); return 0; } EXPORT_SYMBOL_GPL(dev_pm_domain_set_performance_state); |
| 4 10 1 4 4 5 1 6 2 4 6 2 3 1 2 15 15 12 2 2 2 3 7 4 10 11 1 2 1 2 3 3 3 2 1 1 2 1 1 3 3 2 1 1 2 2 2 1 1 1 82 81 80 14 17 2 9 29 51 39 39 25 9 20 2 5 2 5 2 6 4 4 24 24 18 5 4 13 1 1 25 24 1 1 1 1 24 24 2 2 2 25 2 2 2 2 2 2 13 62 62 43 25 2 2 24 25 24 13 25 24 25 48 2 46 1 6 15 4 6 4 4 10 10 10 6 5 10 2 9 10 17 14 18 66 66 42 25 10 1 1 1 1 1 1 1 10 10 1 1 1 1 49 43 27 1 1 51 3 8 2 10 3 8 39 2 5 39 2 5 2 1 1 1 2 11 51 2 2 49 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 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2017 - 2019, Intel Corporation. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> #include <crypto/sha2.h> #include <net/tcp.h> #include <net/mptcp.h> #include "protocol.h" #include "mib.h" #include <trace/events/mptcp.h> static bool mptcp_cap_flag_sha256(u8 flags) { return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256; } static void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, int opsize, struct mptcp_options_received *mp_opt) { u8 subtype = *ptr >> 4; int expected_opsize; u16 subopt; u8 version; u8 flags; u8 i; switch (subtype) { case MPTCPOPT_MP_CAPABLE: /* strict size checking */ if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { if (skb->len > tcp_hdr(skb)->doff << 2) expected_opsize = TCPOLEN_MPTCP_MPC_ACK_DATA; else expected_opsize = TCPOLEN_MPTCP_MPC_ACK; subopt = OPTION_MPTCP_MPC_ACK; } else { if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK) { expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK; subopt = OPTION_MPTCP_MPC_SYNACK; } else { expected_opsize = TCPOLEN_MPTCP_MPC_SYN; subopt = OPTION_MPTCP_MPC_SYN; } } /* Cfr RFC 8684 Section 3.3.0: * If a checksum is present but its use had * not been negotiated in the MP_CAPABLE handshake, the receiver MUST * close the subflow with a RST, as it is not behaving as negotiated. * If a checksum is not present when its use has been negotiated, the * receiver MUST close the subflow with a RST, as it is considered * broken * We parse even option with mismatching csum presence, so that * later in subflow_data_ready we can trigger the reset. */ if (opsize != expected_opsize && (expected_opsize != TCPOLEN_MPTCP_MPC_ACK_DATA || opsize != TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM)) break; /* try to be gentle vs future versions on the initial syn */ version = *ptr++ & MPTCP_VERSION_MASK; if (opsize != TCPOLEN_MPTCP_MPC_SYN) { if (version != MPTCP_SUPPORTED_VERSION) break; } else if (version < MPTCP_SUPPORTED_VERSION) { break; } flags = *ptr++; if (!mptcp_cap_flag_sha256(flags) || (flags & MPTCP_CAP_EXTENSIBILITY)) break; /* RFC 6824, Section 3.1: * "For the Checksum Required bit (labeled "A"), if either * host requires the use of checksums, checksums MUST be used. * In other words, the only way for checksums not to be used * is if both hosts in their SYNs set A=0." */ if (flags & MPTCP_CAP_CHECKSUM_REQD) mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; mp_opt->deny_join_id0 = !!(flags & MPTCP_CAP_DENY_JOIN_ID0); mp_opt->suboptions |= subopt; if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) { mp_opt->sndr_key = get_unaligned_be64(ptr); ptr += 8; } if (opsize >= TCPOLEN_MPTCP_MPC_ACK) { mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; } if (opsize >= TCPOLEN_MPTCP_MPC_ACK_DATA) { /* Section 3.1.: * "the data parameters in a MP_CAPABLE are semantically * equivalent to those in a DSS option and can be used * interchangeably." */ mp_opt->suboptions |= OPTION_MPTCP_DSS; mp_opt->use_map = 1; mp_opt->mpc_map = 1; mp_opt->use_ack = 0; mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; } if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { mp_opt->csum = get_unaligned((__force __sum16 *)ptr); mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u", version, flags, opsize, mp_opt->sndr_key, mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum); break; case MPTCPOPT_MP_JOIN: if (opsize == TCPOLEN_MPTCP_MPJ_SYN) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; mp_opt->token = get_unaligned_be32(ptr); ptr += 4; mp_opt->nonce = get_unaligned_be32(ptr); ptr += 4; pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u", mp_opt->backup, mp_opt->join_id, mp_opt->token, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYNACK; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; mp_opt->join_id = *ptr++; mp_opt->thmac = get_unaligned_be64(ptr); ptr += 8; mp_opt->nonce = get_unaligned_be32(ptr); ptr += 4; pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u", mp_opt->backup, mp_opt->join_id, mp_opt->thmac, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK; ptr += 2; memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); pr_debug("MP_JOIN hmac"); } break; case MPTCPOPT_DSS: pr_debug("DSS"); ptr++; /* we must clear 'mpc_map' be able to detect MP_CAPABLE * map vs DSS map in mptcp_incoming_options(), and reconstruct * map info accordingly */ mp_opt->mpc_map = 0; flags = (*ptr++) & MPTCP_DSS_FLAG_MASK; mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0; mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0; mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0; mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0; mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK); pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d", mp_opt->data_fin, mp_opt->dsn64, mp_opt->use_map, mp_opt->ack64, mp_opt->use_ack); expected_opsize = TCPOLEN_MPTCP_DSS_BASE; if (mp_opt->use_ack) { if (mp_opt->ack64) expected_opsize += TCPOLEN_MPTCP_DSS_ACK64; else expected_opsize += TCPOLEN_MPTCP_DSS_ACK32; } if (mp_opt->use_map) { if (mp_opt->dsn64) expected_opsize += TCPOLEN_MPTCP_DSS_MAP64; else expected_opsize += TCPOLEN_MPTCP_DSS_MAP32; } /* Always parse any csum presence combination, we will enforce * RFC 8684 Section 3.3.0 checks later in subflow_data_ready */ if (opsize != expected_opsize && opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) break; mp_opt->suboptions |= OPTION_MPTCP_DSS; if (mp_opt->use_ack) { if (mp_opt->ack64) { mp_opt->data_ack = get_unaligned_be64(ptr); ptr += 8; } else { mp_opt->data_ack = get_unaligned_be32(ptr); ptr += 4; } pr_debug("data_ack=%llu", mp_opt->data_ack); } if (mp_opt->use_map) { if (mp_opt->dsn64) { mp_opt->data_seq = get_unaligned_be64(ptr); ptr += 8; } else { mp_opt->data_seq = get_unaligned_be32(ptr); ptr += 4; } mp_opt->subflow_seq = get_unaligned_be32(ptr); ptr += 4; mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; mp_opt->csum = get_unaligned((__force __sum16 *)ptr); ptr += 2; } pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", mp_opt->data_seq, mp_opt->subflow_seq, mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD), mp_opt->csum); } break; case MPTCPOPT_ADD_ADDR: mp_opt->echo = (*ptr++) & MPTCP_ADDR_ECHO; if (!mp_opt->echo) { if (opsize == TCPOLEN_MPTCP_ADD_ADDR || opsize == TCPOLEN_MPTCP_ADD_ADDR_PORT) mp_opt->addr.family = AF_INET; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (opsize == TCPOLEN_MPTCP_ADD_ADDR6 || opsize == TCPOLEN_MPTCP_ADD_ADDR6_PORT) mp_opt->addr.family = AF_INET6; #endif else break; } else { if (opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE || opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT) mp_opt->addr.family = AF_INET; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE || opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT) mp_opt->addr.family = AF_INET6; #endif else break; } mp_opt->suboptions |= OPTION_MPTCP_ADD_ADDR; mp_opt->addr.id = *ptr++; mp_opt->addr.port = 0; mp_opt->ahmac = 0; if (mp_opt->addr.family == AF_INET) { memcpy((u8 *)&mp_opt->addr.addr.s_addr, (u8 *)ptr, 4); ptr += 4; if (opsize == TCPOLEN_MPTCP_ADD_ADDR_PORT || opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT) { mp_opt->addr.port = htons(get_unaligned_be16(ptr)); ptr += 2; } } #if IS_ENABLED(CONFIG_MPTCP_IPV6) else { memcpy(mp_opt->addr.addr6.s6_addr, (u8 *)ptr, 16); ptr += 16; if (opsize == TCPOLEN_MPTCP_ADD_ADDR6_PORT || opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT) { mp_opt->addr.port = htons(get_unaligned_be16(ptr)); ptr += 2; } } #endif if (!mp_opt->echo) { mp_opt->ahmac = get_unaligned_be64(ptr); ptr += 8; } pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d", (mp_opt->addr.family == AF_INET6) ? "6" : "", mp_opt->addr.id, mp_opt->ahmac, mp_opt->echo, ntohs(mp_opt->addr.port)); break; case MPTCPOPT_RM_ADDR: if (opsize < TCPOLEN_MPTCP_RM_ADDR_BASE + 1 || opsize > TCPOLEN_MPTCP_RM_ADDR_BASE + MPTCP_RM_IDS_MAX) break; ptr++; mp_opt->suboptions |= OPTION_MPTCP_RM_ADDR; mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE; for (i = 0; i < mp_opt->rm_list.nr; i++) mp_opt->rm_list.ids[i] = *ptr++; pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr); break; case MPTCPOPT_MP_PRIO: if (opsize != TCPOLEN_MPTCP_PRIO) break; mp_opt->suboptions |= OPTION_MPTCP_PRIO; mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP; pr_debug("MP_PRIO: prio=%d", mp_opt->backup); break; case MPTCPOPT_MP_FASTCLOSE: if (opsize != TCPOLEN_MPTCP_FASTCLOSE) break; ptr += 2; mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE; pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key); break; case MPTCPOPT_RST: if (opsize != TCPOLEN_MPTCP_RST) break; if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) break; mp_opt->suboptions |= OPTION_MPTCP_RST; flags = *ptr++; mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT; mp_opt->reset_reason = *ptr; pr_debug("MP_RST: transient=%u reason=%u", mp_opt->reset_transient, mp_opt->reset_reason); break; case MPTCPOPT_MP_FAIL: if (opsize != TCPOLEN_MPTCP_FAIL) break; ptr += 2; mp_opt->suboptions |= OPTION_MPTCP_FAIL; mp_opt->fail_seq = get_unaligned_be64(ptr); pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq); break; default: break; } } void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt) { const struct tcphdr *th = tcp_hdr(skb); const unsigned char *ptr; int length; /* initialize option status */ mp_opt->suboptions = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); while (length > 0) { int opcode = *ptr++; int opsize; switch (opcode) { case TCPOPT_EOL: return; case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ length--; continue; default: if (length < 2) return; opsize = *ptr++; if (opsize < 2) /* "silly options" */ return; if (opsize > length) return; /* don't parse partial options */ if (opcode == TCPOPT_MPTCP) mptcp_parse_option(skb, ptr, opsize, mp_opt); ptr += opsize - 2; length -= opsize; } } } bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); /* we will use snd_isn to detect first pkt [re]transmission * in mptcp_established_options_mp() */ subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; if (subflow->request_mptcp) { opts->suboptions = OPTION_MPTCP_MPC_SYN; opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk)); opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { pr_debug("remote_token=%u, nonce=%u", subflow->remote_token, subflow->local_nonce); opts->suboptions = OPTION_MPTCP_MPJ_SYN; opts->join_id = subflow->local_id; opts->token = subflow->remote_token; opts->nonce = subflow->local_nonce; opts->backup = subflow->request_bkup; *size = TCPOLEN_MPTCP_MPJ_SYN; return true; } return false; } static void clear_3rdack_retransmission(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); sk_stop_timer(sk, &icsk->icsk_delack_timer); icsk->icsk_ack.timeout = 0; icsk->icsk_ack.ato = 0; icsk->icsk_ack.pending &= ~(ICSK_ACK_SCHED | ICSK_ACK_TIMER); } static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, bool snd_data_fin_enable, unsigned int *size, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_ext *mpext; unsigned int data_len; u8 len; /* When skb is not available, we better over-estimate the emitted * options len. A full DSS option (28 bytes) is longer than * TCPOLEN_MPTCP_MPC_ACK_DATA(22) or TCPOLEN_MPTCP_MPJ_ACK(24), so * tell the caller to defer the estimate to * mptcp_established_options_dss(), which will reserve enough space. */ if (!skb) return false; /* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */ if (subflow->fully_established || snd_data_fin_enable || subflow->snd_isn != TCP_SKB_CB(skb)->seq || sk->sk_state != TCP_ESTABLISHED) return false; if (subflow->mp_capable) { mpext = mptcp_get_ext(skb); data_len = mpext ? mpext->data_len : 0; /* we will check ops->data_len in mptcp_write_options() to * discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and * TCPOLEN_MPTCP_MPC_ACK */ opts->data_len = data_len; opts->suboptions = OPTION_MPTCP_MPC_ACK; opts->sndr_key = subflow->local_key; opts->rcvr_key = subflow->remote_key; opts->csum_reqd = READ_ONCE(msk->csum_enabled); opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); /* Section 3.1. * The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK * packets that start the first subflow of an MPTCP connection, * as well as the first packet that carries data */ if (data_len > 0) { len = TCPOLEN_MPTCP_MPC_ACK_DATA; if (opts->csum_reqd) { /* we need to propagate more info to csum the pseudo hdr */ opts->data_seq = mpext->data_seq; opts->subflow_seq = mpext->subflow_seq; opts->csum = mpext->csum; len += TCPOLEN_MPTCP_DSS_CHECKSUM; } *size = ALIGN(len, 4); } else { *size = TCPOLEN_MPTCP_MPC_ACK; } pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d", subflow, subflow->local_key, subflow->remote_key, data_len); return true; } else if (subflow->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_ACK; memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN); *size = TCPOLEN_MPTCP_MPJ_ACK; pr_debug("subflow=%p", subflow); /* we can use the full delegate action helper only from BH context * If we are in process context - sk is flushing the backlog at * socket lock release time - just set the appropriate flag, will * be handled by the release callback */ if (sock_owned_by_user(sk)) set_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status); else mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_ACK); return true; } return false; } static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, struct sk_buff *skb, struct mptcp_ext *ext) { /* The write_seq value has already been incremented, so the actual * sequence number for the DATA_FIN is one less. */ u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq) - 1; if (!ext->use_map || !skb->len) { /* RFC6824 requires a DSS mapping with specific values * if DATA_FIN is set but no data payload is mapped */ ext->data_fin = 1; ext->use_map = 1; ext->dsn64 = 1; ext->data_seq = data_fin_tx_seq; ext->subflow_seq = 0; ext->data_len = 1; } else if (ext->data_seq + ext->data_len == data_fin_tx_seq) { /* If there's an existing DSS mapping and it is the * final mapping, DATA_FIN consumes 1 additional byte of * mapping space. */ ext->data_fin = 1; ext->data_len++; } } static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, bool snd_data_fin_enable, unsigned int *size, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); unsigned int dss_size = 0; struct mptcp_ext *mpext; unsigned int ack_size; bool ret = false; u64 ack_seq; opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; if (mpext) { if (opts->csum_reqd) map_size += TCPOLEN_MPTCP_DSS_CHECKSUM; opts->ext_copy = *mpext; } dss_size = map_size; if (skb && snd_data_fin_enable) mptcp_write_data_fin(subflow, skb, &opts->ext_copy); opts->suboptions = OPTION_MPTCP_DSS; ret = true; } /* passive sockets msk will set the 'can_ack' after accept(), even * if the first subflow may have the already the remote key handy */ opts->ext_copy.use_ack = 0; if (!READ_ONCE(msk->can_ack)) { *size = ALIGN(dss_size, 4); return ret; } ack_seq = READ_ONCE(msk->ack_seq); if (READ_ONCE(msk->use_64bit_ack)) { ack_size = TCPOLEN_MPTCP_DSS_ACK64; opts->ext_copy.data_ack = ack_seq; opts->ext_copy.ack64 = 1; } else { ack_size = TCPOLEN_MPTCP_DSS_ACK32; opts->ext_copy.data_ack32 = (uint32_t)ack_seq; opts->ext_copy.ack64 = 0; } opts->ext_copy.use_ack = 1; opts->suboptions = OPTION_MPTCP_DSS; WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk)); /* Add kind/length/subtype/flag overhead if mapping is not populated */ if (dss_size == 0) ack_size += TCPOLEN_MPTCP_DSS_BASE; dss_size += ack_size; *size = ALIGN(dss_size, 4); return true; } static u64 add_addr_generate_hmac(u64 key1, u64 key2, struct mptcp_addr_info *addr) { u16 port = ntohs(addr->port); u8 hmac[SHA256_DIGEST_SIZE]; u8 msg[19]; int i = 0; msg[i++] = addr->id; if (addr->family == AF_INET) { memcpy(&msg[i], &addr->addr.s_addr, 4); i += 4; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->family == AF_INET6) { memcpy(&msg[i], &addr->addr6.s6_addr, 16); i += 16; } #endif msg[i++] = port >> 8; msg[i++] = port & 0xFF; mptcp_crypto_hmac_sha(key1, key2, msg, i, hmac); return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]); } static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); bool drop_other_suboptions = false; unsigned int opt_size = *size; bool echo; int len; /* add addr will strip the existing options, be sure to avoid breaking * MPC/MPJ handshakes */ if (!mptcp_pm_should_add_signal(msk) || (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) || !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr, &echo, &drop_other_suboptions)) return false; if (drop_other_suboptions) remaining += opt_size; len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); if (remaining < len) return false; *size = len; if (drop_other_suboptions) { pr_debug("drop other suboptions"); opts->suboptions = 0; /* note that e.g. DSS could have written into the memory * aliased by ahmac, we must reset the field here * to avoid appending the hmac even for ADD_ADDR echo * options */ opts->ahmac = 0; *size -= opt_size; } opts->suboptions |= OPTION_MPTCP_ADD_ADDR; if (!echo) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX); opts->ahmac = add_addr_generate_hmac(READ_ONCE(msk->local_key), READ_ONCE(msk->remote_key), &opts->addr); } else { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); } pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d", opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port)); return true; } static bool mptcp_established_options_rm_addr(struct sock *sk, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_rm_list rm_list; int i, len; if (!mptcp_pm_should_rm_signal(msk) || !(mptcp_pm_rm_addr_signal(msk, remaining, &rm_list))) return false; len = mptcp_rm_addr_len(&rm_list); if (len < 0) return false; if (remaining < len) return false; *size = len; opts->suboptions |= OPTION_MPTCP_RM_ADDR; opts->rm_list = rm_list; for (i = 0; i < opts->rm_list.nr; i++) pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]); MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr); return true; } static bool mptcp_established_options_mp_prio(struct sock *sk, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); /* can't send MP_PRIO with MPC, as they share the same option space: * 'backup'. Also it makes no sense at all */ if (!subflow->send_mp_prio || (opts->suboptions & OPTIONS_MPTCP_MPC)) return false; /* account for the trailing 'nop' option */ if (remaining < TCPOLEN_MPTCP_PRIO_ALIGN) return false; *size = TCPOLEN_MPTCP_PRIO_ALIGN; opts->suboptions |= OPTION_MPTCP_PRIO; opts->backup = subflow->request_bkup; pr_debug("prio=%d", opts->backup); return true; } static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); if (remaining < TCPOLEN_MPTCP_RST) return false; *size = TCPOLEN_MPTCP_RST; opts->suboptions |= OPTION_MPTCP_RST; opts->reset_transient = subflow->reset_transient; opts->reset_reason = subflow->reset_reason; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX); return true; } static bool mptcp_established_options_fastclose(struct sock *sk, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); if (likely(!subflow->send_fastclose)) return false; if (remaining < TCPOLEN_MPTCP_FASTCLOSE) return false; *size = TCPOLEN_MPTCP_FASTCLOSE; opts->suboptions |= OPTION_MPTCP_FASTCLOSE; opts->rcvr_key = READ_ONCE(msk->remote_key); pr_debug("FASTCLOSE key=%llu", opts->rcvr_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); return true; } static bool mptcp_established_options_mp_fail(struct sock *sk, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); if (likely(!subflow->send_mp_fail)) return false; if (remaining < TCPOLEN_MPTCP_FAIL) return false; *size = TCPOLEN_MPTCP_FAIL; opts->suboptions |= OPTION_MPTCP_FAIL; opts->fail_seq = subflow->map_seq; pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX); return true; } bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); unsigned int opt_size = 0; bool snd_data_fin; bool ret = false; opts->suboptions = 0; if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb))) return false; if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) { if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) || mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; } /* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */ if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; } return true; } snd_data_fin = mptcp_data_fin_enabled(msk); if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, opts)) ret = true; else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, opts)) { unsigned int mp_fail_size; ret = true; if (mptcp_established_options_mp_fail(sk, &mp_fail_size, remaining - opt_size, opts)) { *size += opt_size + mp_fail_size; remaining -= opt_size - mp_fail_size; return true; } } /* we reserved enough space for the above options, and exceeding the * TCP option space would be fatal */ if (WARN_ON_ONCE(opt_size > remaining)) return false; *size += opt_size; remaining -= opt_size; if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; ret = true; } else if (mptcp_established_options_rm_addr(sk, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; ret = true; } if (mptcp_established_options_mp_prio(sk, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; ret = true; } return ret; } bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, struct mptcp_out_options *opts) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); if (subflow_req->mp_capable) { opts->suboptions = OPTION_MPTCP_MPC_SYNACK; opts->sndr_key = subflow_req->local_key; opts->csum_reqd = subflow_req->csum_reqd; opts->allow_join_id0 = subflow_req->allow_join_id0; *size = TCPOLEN_MPTCP_MPC_SYNACK; pr_debug("subflow_req=%p, local_key=%llu", subflow_req, subflow_req->local_key); return true; } else if (subflow_req->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_SYNACK; opts->backup = subflow_req->backup; opts->join_id = subflow_req->local_id; opts->thmac = subflow_req->thmac; opts->nonce = subflow_req->local_nonce; pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u", subflow_req, opts->backup, opts->join_id, opts->thmac, opts->nonce); *size = TCPOLEN_MPTCP_MPJ_SYNACK; return true; } return false; } static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_subflow_context *subflow, struct sk_buff *skb, struct mptcp_options_received *mp_opt) { /* here we can process OoO, in-window pkts, only in-sequence 4th ack * will make the subflow fully established */ if (likely(subflow->fully_established)) { /* on passive sockets, check for 3rd ack retransmission * note that msk is always set by subflow_syn_recv_sock() * for mp_join subflows */ if (TCP_SKB_CB(skb)->seq == subflow->ssn_offset + 1 && TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq && subflow->mp_join && (mp_opt->suboptions & OPTIONS_MPTCP_MPJ) && !subflow->request_join) tcp_send_ack(ssk); goto check_notify; } /* we must process OoO packets before the first subflow is fully * established. OoO packets are instead a protocol violation * for MP_JOIN subflows as the peer must not send any data * before receiving the forth ack - cfr. RFC 8684 section 3.2. */ if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) { if (subflow->mp_join) goto reset; if (subflow->is_mptfo && mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) goto set_fully_established; return subflow->mp_capable; } if (subflow->remote_key_valid && (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) { /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ goto set_fully_established; } /* If the first established packet does not contain MP_CAPABLE + data * then fallback to TCP. Fallback scenarios requires a reset for * MP_JOIN subflows. */ if (!(mp_opt->suboptions & OPTIONS_MPTCP_MPC)) { if (subflow->mp_join) goto reset; subflow->mp_capable = 0; pr_fallback(msk); mptcp_do_fallback(ssk); return false; } if (mp_opt->deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); set_fully_established: mptcp_data_lock((struct sock *)msk); __mptcp_subflow_fully_established(msk, subflow, mp_opt); mptcp_data_unlock((struct sock *)msk); check_notify: /* if the subflow is not already linked into the conn_list, we can't * notify the PM: this subflow is still on the listener queue * and the PM possibly acquiring the subflow lock could race with * the listener close */ if (likely(subflow->pm_notified) || list_empty(&subflow->node)) return true; subflow->pm_notified = 1; if (subflow->mp_join) { clear_3rdack_retransmission(ssk); mptcp_pm_subflow_established(msk); } else { mptcp_pm_fully_established(msk, ssk); } return true; reset: mptcp_subflow_reset(ssk); return false; } u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq) { u32 old_seq32, cur_seq32; old_seq32 = (u32)old_seq; cur_seq32 = (u32)cur_seq; cur_seq = (old_seq & GENMASK_ULL(63, 32)) + cur_seq32; if (unlikely(cur_seq32 < old_seq32 && before(old_seq32, cur_seq32))) return cur_seq + (1LL << 32); /* reverse wrap could happen, too */ if (unlikely(cur_seq32 > old_seq32 && after(old_seq32, cur_seq32))) return cur_seq - (1LL << 32); return cur_seq; } static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una) { msk->bytes_acked += new_snd_una - msk->snd_una; WRITE_ONCE(msk->snd_una, new_snd_una); } static void ack_update_msk(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_options_received *mp_opt) { u64 new_wnd_end, new_snd_una, snd_nxt = READ_ONCE(msk->snd_nxt); struct sock *sk = (struct sock *)msk; u64 old_snd_una; mptcp_data_lock(sk); /* avoid ack expansion on update conflict, to reduce the risk of * wrongly expanding to a future ack sequence number, which is way * more dangerous than missing an ack */ old_snd_una = msk->snd_una; new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64); /* ACK for data not even sent yet? Ignore.*/ if (unlikely(after64(new_snd_una, snd_nxt))) new_snd_una = old_snd_una; new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd; if (after64(new_wnd_end, msk->wnd_end)) WRITE_ONCE(msk->wnd_end, new_wnd_end); /* this assumes mptcp_incoming_options() is invoked after tcp_ack() */ if (after64(msk->wnd_end, snd_nxt)) __mptcp_check_push(sk, ssk); if (after64(new_snd_una, old_snd_una)) { __mptcp_snd_una_update(msk, new_snd_una); __mptcp_data_acked(sk); } msk->last_ack_recv = tcp_jiffies32; mptcp_data_unlock(sk); trace_ack_update_msk(mp_opt->data_ack, old_snd_una, new_snd_una, new_wnd_end, READ_ONCE(msk->wnd_end)); } bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit) { /* Skip if DATA_FIN was already received. * If updating simultaneously with the recvmsg loop, values * should match. If they mismatch, the peer is misbehaving and * we will prefer the most recent information. */ if (READ_ONCE(msk->rcv_data_fin)) return false; WRITE_ONCE(msk->rcv_data_fin_seq, mptcp_expand_seq(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); WRITE_ONCE(msk->rcv_data_fin, 1); return true; } static bool add_addr_hmac_valid(struct mptcp_sock *msk, struct mptcp_options_received *mp_opt) { u64 hmac = 0; if (mp_opt->echo) return true; hmac = add_addr_generate_hmac(READ_ONCE(msk->remote_key), READ_ONCE(msk->local_key), &mp_opt->addr); pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n", msk, hmac, mp_opt->ahmac); return hmac == mp_opt->ahmac; } /* Return false if a subflow has been reset, else return true */ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_options_received mp_opt; struct mptcp_ext *mpext; if (__mptcp_check_fallback(msk)) { /* Keep it simple and unconditionally trigger send data cleanup and * pending queue spooling. We will need to acquire the data lock * for more accurate checks, and once the lock is acquired, such * helpers are cheap. */ mptcp_data_lock(subflow->conn); if (sk_stream_memory_free(sk)) __mptcp_check_push(subflow->conn, sk); /* on fallback we just need to ignore the msk-level snd_una, as * this is really plain TCP */ __mptcp_snd_una_update(msk, READ_ONCE(msk->snd_nxt)); __mptcp_data_acked(subflow->conn); mptcp_data_unlock(subflow->conn); return true; } mptcp_get_options(skb, &mp_opt); /* The subflow can be in close state only if check_fully_established() * just sent a reset. If so, tell the caller to ignore the current packet. */ if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return sk->sk_state != TCP_CLOSE; if (unlikely(mp_opt.suboptions != OPTION_MPTCP_DSS)) { if ((mp_opt.suboptions & OPTION_MPTCP_FASTCLOSE) && READ_ONCE(msk->local_key) == mp_opt.rcvr_key) { WRITE_ONCE(msk->rcv_fastclose, true); mptcp_schedule_work((struct sock *)msk); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSERX); } if ((mp_opt.suboptions & OPTION_MPTCP_ADD_ADDR) && add_addr_hmac_valid(msk, &mp_opt)) { if (!mp_opt.echo) { mptcp_pm_add_addr_received(sk, &mp_opt.addr); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR); } else { mptcp_pm_add_addr_echoed(msk, &mp_opt.addr); mptcp_pm_del_add_timer(msk, &mp_opt.addr, true); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD); } if (mp_opt.addr.port) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_PORTADD); } if (mp_opt.suboptions & OPTION_MPTCP_RM_ADDR) mptcp_pm_rm_addr_received(msk, &mp_opt.rm_list); if (mp_opt.suboptions & OPTION_MPTCP_PRIO) { mptcp_pm_mp_prio_received(sk, mp_opt.backup); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIORX); } if (mp_opt.suboptions & OPTION_MPTCP_FAIL) { mptcp_pm_mp_fail_received(sk, mp_opt.fail_seq); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILRX); } if (mp_opt.suboptions & OPTION_MPTCP_RST) { subflow->reset_seen = 1; subflow->reset_reason = mp_opt.reset_reason; subflow->reset_transient = mp_opt.reset_transient; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTRX); } if (!(mp_opt.suboptions & OPTION_MPTCP_DSS)) return true; } /* we can't wait for recvmsg() to update the ack_seq, otherwise * monodirectional flows will stuck */ if (mp_opt.use_ack) ack_update_msk(msk, sk, &mp_opt); /* Zero-data-length packets are dropped by the caller and not * propagated to the MPTCP layer, so the skb extension does not * need to be allocated or populated. DATA_FIN information, if * present, needs to be updated here before the skb is freed. */ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { if (mp_opt.data_fin && mp_opt.data_len == 1 && mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64)) mptcp_schedule_work((struct sock *)msk); return true; } mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) return true; memset(mpext, 0, sizeof(*mpext)); if (likely(mp_opt.use_map)) { if (mp_opt.mpc_map) { /* this is an MP_CAPABLE carrying MPTCP data * we know this map the first chunk of data */ mptcp_crypto_key_sha(subflow->remote_key, NULL, &mpext->data_seq); mpext->data_seq++; mpext->subflow_seq = 1; mpext->dsn64 = 1; mpext->mpc_map = 1; mpext->data_fin = 0; } else { mpext->data_seq = mp_opt.data_seq; mpext->subflow_seq = mp_opt.subflow_seq; mpext->dsn64 = mp_opt.dsn64; mpext->data_fin = mp_opt.data_fin; } mpext->data_len = mp_opt.data_len; mpext->use_map = 1; mpext->csum_reqd = !!(mp_opt.suboptions & OPTION_MPTCP_CSUMREQD); if (mpext->csum_reqd) mpext->csum = mp_opt.csum; } return true; } static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) { const struct sock *ssk = (const struct sock *)tp; struct mptcp_subflow_context *subflow; u64 ack_seq, rcv_wnd_old, rcv_wnd_new; struct mptcp_sock *msk; u32 new_win; u64 win; subflow = mptcp_subflow_ctx(ssk); msk = mptcp_sk(subflow->conn); ack_seq = READ_ONCE(msk->ack_seq); rcv_wnd_new = ack_seq + tp->rcv_wnd; rcv_wnd_old = atomic64_read(&msk->rcv_wnd_sent); if (after64(rcv_wnd_new, rcv_wnd_old)) { u64 rcv_wnd; for (;;) { rcv_wnd = atomic64_cmpxchg(&msk->rcv_wnd_sent, rcv_wnd_old, rcv_wnd_new); if (rcv_wnd == rcv_wnd_old) break; rcv_wnd_old = rcv_wnd; if (before64(rcv_wnd_new, rcv_wnd_old)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICTUPDATE); goto raise_win; } MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); } return; } if (rcv_wnd_new != rcv_wnd_old) { raise_win: win = rcv_wnd_old - ack_seq; tp->rcv_wnd = min_t(u64, win, U32_MAX); new_win = tp->rcv_wnd; /* Make sure we do not exceed the maximum possible * scaled window. */ if (unlikely(th->syn)) new_win = min(new_win, 65535U) << tp->rx_opt.rcv_wscale; if (!tp->rx_opt.rcv_wscale && READ_ONCE(sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows)) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); /* RFC1323 scaling applied */ new_win >>= tp->rx_opt.rcv_wscale; th->window = htons(new_win); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED); } } __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) { struct csum_pseudo_header header; __wsum csum; /* cfr RFC 8684 3.3.1.: * the data sequence number used in the pseudo-header is * always the 64-bit value, irrespective of what length is used in the * DSS option itself. */ header.data_seq = cpu_to_be64(data_seq); header.subflow_seq = htonl(subflow_seq); header.data_len = htons(data_len); header.csum = 0; csum = csum_partial(&header, sizeof(header), sum); return csum_fold(csum); } static __sum16 mptcp_make_csum(const struct mptcp_ext *mpext) { return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len, ~csum_unfold(mpext->csum)); } static void put_len_csum(u16 len, __sum16 csum, void *data) { __sum16 *sumptr = data + 2; __be16 *ptr = data; put_unaligned_be16(len, ptr); put_unaligned(csum, sumptr); } void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct mptcp_out_options *opts) { const struct sock *ssk = (const struct sock *)tp; struct mptcp_subflow_context *subflow; /* Which options can be used together? * * X: mutually exclusive * O: often used together * C: can be used together in some cases * P: could be used together but we prefer not to (optimisations) * * Opt: | MPC | MPJ | DSS | ADD | RM | PRIO | FAIL | FC | * ------|------|------|------|------|------|------|------|------| * MPC |------|------|------|------|------|------|------|------| * MPJ | X |------|------|------|------|------|------|------| * DSS | X | X |------|------|------|------|------|------| * ADD | X | X | P |------|------|------|------|------| * RM | C | C | C | P |------|------|------|------| * PRIO | X | C | C | C | C |------|------|------| * FAIL | X | X | C | X | X | X |------|------| * FC | X | X | X | X | X | X | X |------| * RST | X | X | X | X | X | X | O | O | * ------|------|------|------|------|------|------|------|------| * * The same applies in mptcp_established_options() function. */ if (likely(OPTION_MPTCP_DSS & opts->suboptions)) { struct mptcp_ext *mpext = &opts->ext_copy; u8 len = TCPOLEN_MPTCP_DSS_BASE; u8 flags = 0; if (mpext->use_ack) { flags = MPTCP_DSS_HAS_ACK; if (mpext->ack64) { len += TCPOLEN_MPTCP_DSS_ACK64; flags |= MPTCP_DSS_ACK64; } else { len += TCPOLEN_MPTCP_DSS_ACK32; } } if (mpext->use_map) { len += TCPOLEN_MPTCP_DSS_MAP64; /* Use only 64-bit mapping flags for now, add * support for optional 32-bit mappings later. */ flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; if (mpext->data_fin) flags |= MPTCP_DSS_DATA_FIN; if (opts->csum_reqd) len += TCPOLEN_MPTCP_DSS_CHECKSUM; } *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); if (mpext->use_ack) { if (mpext->ack64) { put_unaligned_be64(mpext->data_ack, ptr); ptr += 2; } else { put_unaligned_be32(mpext->data_ack32, ptr); ptr += 1; } } if (mpext->use_map) { put_unaligned_be64(mpext->data_seq, ptr); ptr += 2; put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; if (opts->csum_reqd) { /* data_len == 0 is reserved for the infinite mapping, * the checksum will also be set to 0. */ put_len_csum(mpext->data_len, (mpext->data_len ? mptcp_make_csum(mpext) : 0), ptr); } else { put_unaligned_be32(mpext->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); } ptr += 1; } /* We might need to add MP_FAIL options in rare cases */ if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) goto mp_fail; } else if (OPTIONS_MPTCP_MPC & opts->suboptions) { u8 len, flag = MPTCP_CAP_HMAC_SHA256; if (OPTION_MPTCP_MPC_SYN & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYN; } else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYNACK; } else if (opts->data_len) { len = TCPOLEN_MPTCP_MPC_ACK_DATA; if (opts->csum_reqd) len += TCPOLEN_MPTCP_DSS_CHECKSUM; } else { len = TCPOLEN_MPTCP_MPC_ACK; } if (opts->csum_reqd) flag |= MPTCP_CAP_CHECKSUM_REQD; if (!opts->allow_join_id0) flag |= MPTCP_CAP_DENY_JOIN_ID0; *ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len, MPTCP_SUPPORTED_VERSION, flag); if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) & opts->suboptions)) goto mp_capable_done; put_unaligned_be64(opts->sndr_key, ptr); ptr += 2; if (!((OPTION_MPTCP_MPC_ACK) & opts->suboptions)) goto mp_capable_done; put_unaligned_be64(opts->rcvr_key, ptr); ptr += 2; if (!opts->data_len) goto mp_capable_done; if (opts->csum_reqd) { put_len_csum(opts->data_len, __mptcp_make_csum(opts->data_seq, opts->subflow_seq, opts->data_len, ~csum_unfold(opts->csum)), ptr); } else { put_unaligned_be32(opts->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); } ptr += 1; /* MPC is additionally mutually exclusive with MP_PRIO */ goto mp_capable_done; } else if (OPTIONS_MPTCP_MPJ & opts->suboptions) { if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) { *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, TCPOLEN_MPTCP_MPJ_SYN, opts->backup, opts->join_id); put_unaligned_be32(opts->token, ptr); ptr += 1; put_unaligned_be32(opts->nonce, ptr); ptr += 1; } else if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) { *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, TCPOLEN_MPTCP_MPJ_SYNACK, opts->backup, opts->join_id); put_unaligned_be64(opts->thmac, ptr); ptr += 2; put_unaligned_be32(opts->nonce, ptr); ptr += 1; } else { *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, TCPOLEN_MPTCP_MPJ_ACK, 0, 0); memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN); ptr += 5; } } else if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) { u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE; u8 echo = MPTCP_ADDR_ECHO; #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (opts->addr.family == AF_INET6) len = TCPOLEN_MPTCP_ADD_ADDR6_BASE; #endif if (opts->addr.port) len += TCPOLEN_MPTCP_PORT_LEN; if (opts->ahmac) { len += sizeof(opts->ahmac); echo = 0; } *ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR, len, echo, opts->addr.id); if (opts->addr.family == AF_INET) { memcpy((u8 *)ptr, (u8 *)&opts->addr.addr.s_addr, 4); ptr += 1; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (opts->addr.family == AF_INET6) { memcpy((u8 *)ptr, opts->addr.addr6.s6_addr, 16); ptr += 4; } #endif if (!opts->addr.port) { if (opts->ahmac) { put_unaligned_be64(opts->ahmac, ptr); ptr += 2; } } else { u16 port = ntohs(opts->addr.port); if (opts->ahmac) { u8 *bptr = (u8 *)ptr; put_unaligned_be16(port, bptr); bptr += 2; put_unaligned_be64(opts->ahmac, bptr); bptr += 8; put_unaligned_be16(TCPOPT_NOP << 8 | TCPOPT_NOP, bptr); ptr += 3; } else { put_unaligned_be32(port << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); ptr += 1; } } } else if (unlikely(OPTION_MPTCP_FASTCLOSE & opts->suboptions)) { /* FASTCLOSE is mutually exclusive with others except RST */ *ptr++ = mptcp_option(MPTCPOPT_MP_FASTCLOSE, TCPOLEN_MPTCP_FASTCLOSE, 0, 0); put_unaligned_be64(opts->rcvr_key, ptr); ptr += 2; if (OPTION_MPTCP_RST & opts->suboptions) goto mp_rst; return; } else if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { mp_fail: /* MP_FAIL is mutually exclusive with others except RST */ subflow = mptcp_subflow_ctx(ssk); subflow->send_mp_fail = 0; *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, TCPOLEN_MPTCP_FAIL, 0, 0); put_unaligned_be64(opts->fail_seq, ptr); ptr += 2; if (OPTION_MPTCP_RST & opts->suboptions) goto mp_rst; return; } else if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) { mp_rst: *ptr++ = mptcp_option(MPTCPOPT_RST, TCPOLEN_MPTCP_RST, opts->reset_transient, opts->reset_reason); return; } if (OPTION_MPTCP_PRIO & opts->suboptions) { subflow = mptcp_subflow_ctx(ssk); subflow->send_mp_prio = 0; *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO, TCPOLEN_MPTCP_PRIO, opts->backup, TCPOPT_NOP); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPPRIOTX); } mp_capable_done: if (OPTION_MPTCP_RM_ADDR & opts->suboptions) { u8 i = 1; *ptr++ = mptcp_option(MPTCPOPT_RM_ADDR, TCPOLEN_MPTCP_RM_ADDR_BASE + opts->rm_list.nr, 0, opts->rm_list.ids[0]); while (i < opts->rm_list.nr) { u8 id1, id2, id3, id4; id1 = opts->rm_list.ids[i]; id2 = i + 1 < opts->rm_list.nr ? opts->rm_list.ids[i + 1] : TCPOPT_NOP; id3 = i + 2 < opts->rm_list.nr ? opts->rm_list.ids[i + 2] : TCPOPT_NOP; id4 = i + 3 < opts->rm_list.nr ? opts->rm_list.ids[i + 3] : TCPOPT_NOP; put_unaligned_be32(id1 << 24 | id2 << 16 | id3 << 8 | id4, ptr); ptr += 1; i += 4; } } if (tp) mptcp_set_rwin(tp, th); } __be32 mptcp_get_reset_option(const struct sk_buff *skb) { const struct mptcp_ext *ext = mptcp_get_ext(skb); u8 flags, reason; if (ext) { flags = ext->reset_transient; reason = ext->reset_reason; return mptcp_option(MPTCPOPT_RST, TCPOLEN_MPTCP_RST, flags, reason); } return htonl(0u); } EXPORT_SYMBOL_GPL(mptcp_get_reset_option); |
| 41 30 29 25 131 5 34 3 35 16 53 51 72 39 16 1 27 41 9 10 10 76 79 21 2 124 52 26 8 141 51 2 2 148 273 54 50 14 212 201 212 212 2 1 1 311 304 99 30 2 4 3 1 4 42 1 9 9 6 3 9 116 2 5 301 262 106 54 349 222 222 349 28 273 88 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM btrfs #if !defined(_TRACE_BTRFS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BTRFS_H #include <linux/writeback.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> struct btrfs_root; struct btrfs_fs_info; struct btrfs_inode; struct extent_map; struct btrfs_file_extent_item; struct btrfs_ordered_extent; struct btrfs_delayed_ref_node; struct btrfs_delayed_ref_head; struct btrfs_block_group; struct btrfs_free_cluster; struct btrfs_chunk_map; struct extent_buffer; struct btrfs_work; struct btrfs_workqueue; struct btrfs_qgroup_extent_record; struct btrfs_qgroup; struct extent_io_tree; struct prelim_ref; struct btrfs_space_info; struct btrfs_raid_bio; struct raid56_bio_trace_info; struct find_free_extent_ctl; #define show_ref_type(type) \ __print_symbolic(type, \ { BTRFS_TREE_BLOCK_REF_KEY, "TREE_BLOCK_REF" }, \ { BTRFS_EXTENT_DATA_REF_KEY, "EXTENT_DATA_REF" }, \ { BTRFS_SHARED_BLOCK_REF_KEY, "SHARED_BLOCK_REF" }, \ { BTRFS_SHARED_DATA_REF_KEY, "SHARED_DATA_REF" }) #define __show_root_type(obj) \ __print_symbolic_u64(obj, \ { BTRFS_ROOT_TREE_OBJECTID, "ROOT_TREE" }, \ { BTRFS_EXTENT_TREE_OBJECTID, "EXTENT_TREE" }, \ { BTRFS_CHUNK_TREE_OBJECTID, "CHUNK_TREE" }, \ { BTRFS_DEV_TREE_OBJECTID, "DEV_TREE" }, \ { BTRFS_FS_TREE_OBJECTID, "FS_TREE" }, \ { BTRFS_ROOT_TREE_DIR_OBJECTID, "ROOT_TREE_DIR" }, \ { BTRFS_CSUM_TREE_OBJECTID, "CSUM_TREE" }, \ { BTRFS_TREE_LOG_OBJECTID, "TREE_LOG" }, \ { BTRFS_QUOTA_TREE_OBJECTID, "QUOTA_TREE" }, \ { BTRFS_TREE_RELOC_OBJECTID, "TREE_RELOC" }, \ { BTRFS_UUID_TREE_OBJECTID, "UUID_TREE" }, \ { BTRFS_FREE_SPACE_TREE_OBJECTID, "FREE_SPACE_TREE" }, \ { BTRFS_BLOCK_GROUP_TREE_OBJECTID, "BLOCK_GROUP_TREE" },\ { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }) #define show_root_type(obj) \ obj, ((obj >= BTRFS_DATA_RELOC_TREE_OBJECTID) || \ (obj >= BTRFS_ROOT_TREE_OBJECTID && \ obj <= BTRFS_QUOTA_TREE_OBJECTID)) ? __show_root_type(obj) : "-" #define FLUSH_ACTIONS \ EM( BTRFS_RESERVE_NO_FLUSH, "BTRFS_RESERVE_NO_FLUSH") \ EM( BTRFS_RESERVE_FLUSH_LIMIT, "BTRFS_RESERVE_FLUSH_LIMIT") \ EM( BTRFS_RESERVE_FLUSH_ALL, "BTRFS_RESERVE_FLUSH_ALL") \ EMe(BTRFS_RESERVE_FLUSH_ALL_STEAL, "BTRFS_RESERVE_FLUSH_ALL_STEAL") #define FI_TYPES \ EM( BTRFS_FILE_EXTENT_INLINE, "INLINE") \ EM( BTRFS_FILE_EXTENT_REG, "REG") \ EMe(BTRFS_FILE_EXTENT_PREALLOC, "PREALLOC") #define QGROUP_RSV_TYPES \ EM( BTRFS_QGROUP_RSV_DATA, "DATA") \ EM( BTRFS_QGROUP_RSV_META_PERTRANS, "META_PERTRANS") \ EMe(BTRFS_QGROUP_RSV_META_PREALLOC, "META_PREALLOC") #define IO_TREE_OWNER \ EM( IO_TREE_FS_PINNED_EXTENTS, "PINNED_EXTENTS") \ EM( IO_TREE_FS_EXCLUDED_EXTENTS, "EXCLUDED_EXTENTS") \ EM( IO_TREE_BTREE_INODE_IO, "BTREE_INODE_IO") \ EM( IO_TREE_INODE_IO, "INODE_IO") \ EM( IO_TREE_RELOC_BLOCKS, "RELOC_BLOCKS") \ EM( IO_TREE_TRANS_DIRTY_PAGES, "TRANS_DIRTY_PAGES") \ EM( IO_TREE_ROOT_DIRTY_LOG_PAGES, "ROOT_DIRTY_LOG_PAGES") \ EM( IO_TREE_INODE_FILE_EXTENT, "INODE_FILE_EXTENT") \ EM( IO_TREE_LOG_CSUM_RANGE, "LOG_CSUM_RANGE") \ EMe(IO_TREE_SELFTEST, "SELFTEST") #define FLUSH_STATES \ EM( FLUSH_DELAYED_ITEMS_NR, "FLUSH_DELAYED_ITEMS_NR") \ EM( FLUSH_DELAYED_ITEMS, "FLUSH_DELAYED_ITEMS") \ EM( FLUSH_DELALLOC, "FLUSH_DELALLOC") \ EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \ EM( FLUSH_DELALLOC_FULL, "FLUSH_DELALLOC_FULL") \ EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \ EM( FLUSH_DELAYED_REFS, "FLUSH_DELAYED_REFS") \ EM( ALLOC_CHUNK, "ALLOC_CHUNK") \ EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \ EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \ EMe(COMMIT_TRANS, "COMMIT_TRANS") /* * First define the enums in the above macros to be exported to userspace via * TRACE_DEFINE_ENUM(). */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); FLUSH_ACTIONS FI_TYPES QGROUP_RSV_TYPES IO_TREE_OWNER FLUSH_STATES /* * Now redefine the EM and EMe macros to map the enums to the strings that will * be printed in the output */ #undef EM #undef EMe #define EM(a, b) {a, b}, #define EMe(a, b) {a, b} #define BTRFS_GROUP_FLAGS \ { BTRFS_BLOCK_GROUP_DATA, "DATA"}, \ { BTRFS_BLOCK_GROUP_SYSTEM, "SYSTEM"}, \ { BTRFS_BLOCK_GROUP_METADATA, "METADATA"}, \ { BTRFS_BLOCK_GROUP_RAID0, "RAID0"}, \ { BTRFS_BLOCK_GROUP_RAID1, "RAID1"}, \ { BTRFS_BLOCK_GROUP_DUP, "DUP"}, \ { BTRFS_BLOCK_GROUP_RAID10, "RAID10"}, \ { BTRFS_BLOCK_GROUP_RAID5, "RAID5"}, \ { BTRFS_BLOCK_GROUP_RAID6, "RAID6"} #define EXTENT_FLAGS \ { EXTENT_DIRTY, "DIRTY"}, \ { EXTENT_UPTODATE, "UPTODATE"}, \ { EXTENT_LOCKED, "LOCKED"}, \ { EXTENT_NEW, "NEW"}, \ { EXTENT_DELALLOC, "DELALLOC"}, \ { EXTENT_DEFRAG, "DEFRAG"}, \ { EXTENT_BOUNDARY, "BOUNDARY"}, \ { EXTENT_NODATASUM, "NODATASUM"}, \ { EXTENT_CLEAR_META_RESV, "CLEAR_META_RESV"}, \ { EXTENT_NEED_WAIT, "NEED_WAIT"}, \ { EXTENT_NORESERVE, "NORESERVE"}, \ { EXTENT_QGROUP_RESERVED, "QGROUP_RESERVED"}, \ { EXTENT_CLEAR_DATA_RESV, "CLEAR_DATA_RESV"}, \ { EXTENT_DELALLOC_NEW, "DELALLOC_NEW"} #define BTRFS_FSID_SIZE 16 #define TP_STRUCT__entry_fsid __array(u8, fsid, BTRFS_FSID_SIZE) #define TP_fast_assign_fsid(fs_info) \ ({ \ if (fs_info) \ memcpy(__entry->fsid, fs_info->fs_devices->fsid, \ BTRFS_FSID_SIZE); \ else \ memset(__entry->fsid, 0, BTRFS_FSID_SIZE); \ }) #define TP_STRUCT__entry_btrfs(args...) \ TP_STRUCT__entry( \ TP_STRUCT__entry_fsid \ args) #define TP_fast_assign_btrfs(fs_info, args...) \ TP_fast_assign( \ TP_fast_assign_fsid(fs_info); \ args) #define TP_printk_btrfs(fmt, args...) \ TP_printk("%pU: " fmt, __entry->fsid, args) TRACE_EVENT(btrfs_transaction_commit, TP_PROTO(const struct btrfs_fs_info *fs_info), TP_ARGS(fs_info), TP_STRUCT__entry_btrfs( __field( u64, generation ) __field( u64, root_objectid ) ), TP_fast_assign_btrfs(fs_info, __entry->generation = fs_info->generation; __entry->root_objectid = BTRFS_ROOT_TREE_OBJECTID; ), TP_printk_btrfs("root=%llu(%s) gen=%llu", show_root_type(__entry->root_objectid), __entry->generation) ); DECLARE_EVENT_CLASS(btrfs__inode, TP_PROTO(const struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry_btrfs( __field( u64, ino ) __field( u64, blocks ) __field( u64, disk_i_size ) __field( u64, generation ) __field( u64, last_trans ) __field( u64, logged_trans ) __field( u64, root_objectid ) ), TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->blocks = inode->i_blocks; __entry->disk_i_size = BTRFS_I(inode)->disk_i_size; __entry->generation = BTRFS_I(inode)->generation; __entry->last_trans = BTRFS_I(inode)->last_trans; __entry->logged_trans = BTRFS_I(inode)->logged_trans; __entry->root_objectid = BTRFS_I(inode)->root->root_key.objectid; ), TP_printk_btrfs("root=%llu(%s) gen=%llu ino=%llu blocks=%llu " "disk_i_size=%llu last_trans=%llu logged_trans=%llu", show_root_type(__entry->root_objectid), __entry->generation, __entry->ino, __entry->blocks, __entry->disk_i_size, __entry->last_trans, __entry->logged_trans) ); DEFINE_EVENT(btrfs__inode, btrfs_inode_new, TP_PROTO(const struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(btrfs__inode, btrfs_inode_request, TP_PROTO(const struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(btrfs__inode, btrfs_inode_evict, TP_PROTO(const struct inode *inode), TP_ARGS(inode) ); #define __show_map_type(type) \ __print_symbolic_u64(type, \ { EXTENT_MAP_LAST_BYTE, "LAST_BYTE" }, \ { EXTENT_MAP_HOLE, "HOLE" }, \ { EXTENT_MAP_INLINE, "INLINE" }) #define show_map_type(type) \ type, (type >= EXTENT_MAP_LAST_BYTE) ? "-" : __show_map_type(type) #define show_map_flags(flag) \ __print_flags(flag, "|", \ { EXTENT_FLAG_PINNED, "PINNED" },\ { EXTENT_FLAG_COMPRESS_ZLIB, "COMPRESS_ZLIB" },\ { EXTENT_FLAG_COMPRESS_LZO, "COMPRESS_LZO" },\ { EXTENT_FLAG_COMPRESS_ZSTD, "COMPRESS_ZSTD" },\ { EXTENT_FLAG_PREALLOC, "PREALLOC" },\ { EXTENT_FLAG_LOGGING, "LOGGING" }) TRACE_EVENT_CONDITION(btrfs_get_extent, TP_PROTO(const struct btrfs_root *root, const struct btrfs_inode *inode, const struct extent_map *map), TP_ARGS(root, inode, map), TP_CONDITION(map), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, ino ) __field( u64, start ) __field( u64, len ) __field( u64, orig_start ) __field( u64, block_start ) __field( u64, block_len ) __field( u32, flags ) __field( int, refs ) ), TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->ino = btrfs_ino(inode); __entry->start = map->start; __entry->len = map->len; __entry->orig_start = map->orig_start; __entry->block_start = map->block_start; __entry->block_len = map->block_len; __entry->flags = map->flags; __entry->refs = refcount_read(&map->refs); ), TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu len=%llu " "orig_start=%llu block_start=%llu(%s) " "block_len=%llu flags=%s refs=%u", show_root_type(__entry->root_objectid), __entry->ino, __entry->start, __entry->len, __entry->orig_start, show_map_type(__entry->block_start), __entry->block_len, show_map_flags(__entry->flags), __entry->refs) ); TRACE_EVENT(btrfs_handle_em_exist, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct extent_map *existing, const struct extent_map *map, u64 start, u64 len), TP_ARGS(fs_info, existing, map, start, len), TP_STRUCT__entry_btrfs( __field( u64, e_start ) __field( u64, e_len ) __field( u64, map_start ) __field( u64, map_len ) __field( u64, start ) __field( u64, len ) ), TP_fast_assign_btrfs(fs_info, __entry->e_start = existing->start; __entry->e_len = existing->len; __entry->map_start = map->start; __entry->map_len = map->len; __entry->start = start; __entry->len = len; ), TP_printk_btrfs("start=%llu len=%llu " "existing(start=%llu len=%llu) " "em(start=%llu len=%llu)", __entry->start, __entry->len, __entry->e_start, __entry->e_len, __entry->map_start, __entry->map_len) ); /* file extent item */ DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular, TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, const struct btrfs_file_extent_item *fi, u64 start), TP_ARGS(bi, l, fi, start), TP_STRUCT__entry_btrfs( __field( u64, root_obj ) __field( u64, ino ) __field( loff_t, isize ) __field( u64, disk_isize ) __field( u64, num_bytes ) __field( u64, ram_bytes ) __field( u64, disk_bytenr ) __field( u64, disk_num_bytes ) __field( u64, extent_offset ) __field( u8, extent_type ) __field( u8, compression ) __field( u64, extent_start ) __field( u64, extent_end ) ), TP_fast_assign_btrfs(bi->root->fs_info, __entry->root_obj = bi->root->root_key.objectid; __entry->ino = btrfs_ino(bi); __entry->isize = bi->vfs_inode.i_size; __entry->disk_isize = bi->disk_i_size; __entry->num_bytes = btrfs_file_extent_num_bytes(l, fi); __entry->ram_bytes = btrfs_file_extent_ram_bytes(l, fi); __entry->disk_bytenr = btrfs_file_extent_disk_bytenr(l, fi); __entry->disk_num_bytes = btrfs_file_extent_disk_num_bytes(l, fi); __entry->extent_offset = btrfs_file_extent_offset(l, fi); __entry->extent_type = btrfs_file_extent_type(l, fi); __entry->compression = btrfs_file_extent_compression(l, fi); __entry->extent_start = start; __entry->extent_end = (start + __entry->num_bytes); ), TP_printk_btrfs( "root=%llu(%s) inode=%llu size=%llu disk_isize=%llu " "file extent range=[%llu %llu] " "(num_bytes=%llu ram_bytes=%llu disk_bytenr=%llu " "disk_num_bytes=%llu extent_offset=%llu type=%s " "compression=%u", show_root_type(__entry->root_obj), __entry->ino, __entry->isize, __entry->disk_isize, __entry->extent_start, __entry->extent_end, __entry->num_bytes, __entry->ram_bytes, __entry->disk_bytenr, __entry->disk_num_bytes, __entry->extent_offset, __print_symbolic(__entry->extent_type, FI_TYPES), __entry->compression) ); DECLARE_EVENT_CLASS( btrfs__file_extent_item_inline, TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, const struct btrfs_file_extent_item *fi, int slot, u64 start), TP_ARGS(bi, l, fi, slot, start), TP_STRUCT__entry_btrfs( __field( u64, root_obj ) __field( u64, ino ) __field( loff_t, isize ) __field( u64, disk_isize ) __field( u8, extent_type ) __field( u8, compression ) __field( u64, extent_start ) __field( u64, extent_end ) ), TP_fast_assign_btrfs( bi->root->fs_info, __entry->root_obj = bi->root->root_key.objectid; __entry->ino = btrfs_ino(bi); __entry->isize = bi->vfs_inode.i_size; __entry->disk_isize = bi->disk_i_size; __entry->extent_type = btrfs_file_extent_type(l, fi); __entry->compression = btrfs_file_extent_compression(l, fi); __entry->extent_start = start; __entry->extent_end = (start + btrfs_file_extent_ram_bytes(l, fi)); ), TP_printk_btrfs( "root=%llu(%s) inode=%llu size=%llu disk_isize=%llu " "file extent range=[%llu %llu] " "extent_type=%s compression=%u", show_root_type(__entry->root_obj), __entry->ino, __entry->isize, __entry->disk_isize, __entry->extent_start, __entry->extent_end, __print_symbolic(__entry->extent_type, FI_TYPES), __entry->compression) ); DEFINE_EVENT( btrfs__file_extent_item_regular, btrfs_get_extent_show_fi_regular, TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, const struct btrfs_file_extent_item *fi, u64 start), TP_ARGS(bi, l, fi, start) ); DEFINE_EVENT( btrfs__file_extent_item_regular, btrfs_truncate_show_fi_regular, TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, const struct btrfs_file_extent_item *fi, u64 start), TP_ARGS(bi, l, fi, start) ); DEFINE_EVENT( btrfs__file_extent_item_inline, btrfs_get_extent_show_fi_inline, TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, const struct btrfs_file_extent_item *fi, int slot, u64 start), TP_ARGS(bi, l, fi, slot, start) ); DEFINE_EVENT( btrfs__file_extent_item_inline, btrfs_truncate_show_fi_inline, TP_PROTO(const struct btrfs_inode *bi, const struct extent_buffer *l, const struct btrfs_file_extent_item *fi, int slot, u64 start), TP_ARGS(bi, l, fi, slot, start) ); #define show_ordered_flags(flags) \ __print_flags(flags, "|", \ { (1 << BTRFS_ORDERED_REGULAR), "REGULAR" }, \ { (1 << BTRFS_ORDERED_NOCOW), "NOCOW" }, \ { (1 << BTRFS_ORDERED_PREALLOC), "PREALLOC" }, \ { (1 << BTRFS_ORDERED_COMPRESSED), "COMPRESSED" }, \ { (1 << BTRFS_ORDERED_DIRECT), "DIRECT" }, \ { (1 << BTRFS_ORDERED_IO_DONE), "IO_DONE" }, \ { (1 << BTRFS_ORDERED_COMPLETE), "COMPLETE" }, \ { (1 << BTRFS_ORDERED_IOERR), "IOERR" }, \ { (1 << BTRFS_ORDERED_TRUNCATED), "TRUNCATED" }) DECLARE_EVENT_CLASS(btrfs__ordered_extent, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered), TP_STRUCT__entry_btrfs( __field( u64, ino ) __field( u64, file_offset ) __field( u64, start ) __field( u64, len ) __field( u64, disk_len ) __field( u64, bytes_left ) __field( unsigned long, flags ) __field( int, compress_type ) __field( int, refs ) __field( u64, root_objectid ) __field( u64, truncated_len ) ), TP_fast_assign_btrfs(inode->root->fs_info, __entry->ino = btrfs_ino(inode); __entry->file_offset = ordered->file_offset; __entry->start = ordered->disk_bytenr; __entry->len = ordered->num_bytes; __entry->disk_len = ordered->disk_num_bytes; __entry->bytes_left = ordered->bytes_left; __entry->flags = ordered->flags; __entry->compress_type = ordered->compress_type; __entry->refs = refcount_read(&ordered->refs); __entry->root_objectid = inode->root->root_key.objectid; __entry->truncated_len = ordered->truncated_len; ), TP_printk_btrfs("root=%llu(%s) ino=%llu file_offset=%llu " "start=%llu len=%llu disk_len=%llu " "truncated_len=%llu " "bytes_left=%llu flags=%s compress_type=%d " "refs=%d", show_root_type(__entry->root_objectid), __entry->ino, __entry->file_offset, __entry->start, __entry->len, __entry->disk_len, __entry->truncated_len, __entry->bytes_left, show_ordered_flags(__entry->flags), __entry->compress_type, __entry->refs) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_add, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_remove, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_start, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_put, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_lookup, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_lookup_range, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_lookup_first_range, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_lookup_for_logging, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_lookup_first, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_split, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_dec_test_pending, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_mark_finished, TP_PROTO(const struct btrfs_inode *inode, const struct btrfs_ordered_extent *ordered), TP_ARGS(inode, ordered) ); TRACE_EVENT(btrfs_finish_ordered_extent, TP_PROTO(const struct btrfs_inode *inode, u64 start, u64 len, bool uptodate), TP_ARGS(inode, start, len, uptodate), TP_STRUCT__entry_btrfs( __field( u64, ino ) __field( u64, start ) __field( u64, len ) __field( bool, uptodate ) __field( u64, root_objectid ) ), TP_fast_assign_btrfs(inode->root->fs_info, __entry->ino = btrfs_ino(inode); __entry->start = start; __entry->len = len; __entry->uptodate = uptodate; __entry->root_objectid = inode->root->root_key.objectid; ), TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu len=%llu uptodate=%d", show_root_type(__entry->root_objectid), __entry->ino, __entry->start, __entry->len, !!__entry->uptodate) ); DECLARE_EVENT_CLASS(btrfs__writepage, TP_PROTO(const struct page *page, const struct inode *inode, const struct writeback_control *wbc), TP_ARGS(page, inode, wbc), TP_STRUCT__entry_btrfs( __field( u64, ino ) __field( pgoff_t, index ) __field( long, nr_to_write ) __field( long, pages_skipped ) __field( loff_t, range_start ) __field( loff_t, range_end ) __field( char, for_kupdate ) __field( char, for_reclaim ) __field( char, range_cyclic ) __field( unsigned long, writeback_index ) __field( u64, root_objectid ) ), TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->index = page->index; __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->range_start = wbc->range_start; __entry->range_end = wbc->range_end; __entry->for_kupdate = wbc->for_kupdate; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->root_objectid = BTRFS_I(inode)->root->root_key.objectid; ), TP_printk_btrfs("root=%llu(%s) ino=%llu page_index=%lu " "nr_to_write=%ld pages_skipped=%ld range_start=%llu " "range_end=%llu for_kupdate=%d " "for_reclaim=%d range_cyclic=%d writeback_index=%lu", show_root_type(__entry->root_objectid), __entry->ino, __entry->index, __entry->nr_to_write, __entry->pages_skipped, __entry->range_start, __entry->range_end, __entry->for_kupdate, __entry->for_reclaim, __entry->range_cyclic, __entry->writeback_index) ); DEFINE_EVENT(btrfs__writepage, __extent_writepage, TP_PROTO(const struct page *page, const struct inode *inode, const struct writeback_control *wbc), TP_ARGS(page, inode, wbc) ); TRACE_EVENT(btrfs_writepage_end_io_hook, TP_PROTO(const struct btrfs_inode *inode, u64 start, u64 end, int uptodate), TP_ARGS(inode, start, end, uptodate), TP_STRUCT__entry_btrfs( __field( u64, ino ) __field( u64, start ) __field( u64, end ) __field( int, uptodate ) __field( u64, root_objectid ) ), TP_fast_assign_btrfs(inode->root->fs_info, __entry->ino = btrfs_ino(inode); __entry->start = start; __entry->end = end; __entry->uptodate = uptodate; __entry->root_objectid = inode->root->root_key.objectid; ), TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu end=%llu uptodate=%d", show_root_type(__entry->root_objectid), __entry->ino, __entry->start, __entry->end, __entry->uptodate) ); TRACE_EVENT(btrfs_sync_file, TP_PROTO(const struct file *file, int datasync), TP_ARGS(file, datasync), TP_STRUCT__entry_btrfs( __field( u64, ino ) __field( u64, parent ) __field( int, datasync ) __field( u64, root_objectid ) ), TP_fast_assign( const struct dentry *dentry = file->f_path.dentry; const struct inode *inode = d_inode(dentry); TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb)); __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->parent = btrfs_ino(BTRFS_I(d_inode(dentry->d_parent))); __entry->datasync = datasync; __entry->root_objectid = BTRFS_I(inode)->root->root_key.objectid; ), TP_printk_btrfs("root=%llu(%s) ino=%llu parent=%llu datasync=%d", show_root_type(__entry->root_objectid), __entry->ino, __entry->parent, __entry->datasync) ); TRACE_EVENT(btrfs_sync_fs, TP_PROTO(const struct btrfs_fs_info *fs_info, int wait), TP_ARGS(fs_info, wait), TP_STRUCT__entry_btrfs( __field( int, wait ) ), TP_fast_assign_btrfs(fs_info, __entry->wait = wait; ), TP_printk_btrfs("wait=%d", __entry->wait) ); TRACE_EVENT(btrfs_add_block_group, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_block_group *block_group, int create), TP_ARGS(fs_info, block_group, create), TP_STRUCT__entry_btrfs( __field( u64, offset ) __field( u64, size ) __field( u64, flags ) __field( u64, bytes_used ) __field( u64, bytes_super ) __field( int, create ) ), TP_fast_assign_btrfs(fs_info, __entry->offset = block_group->start; __entry->size = block_group->length; __entry->flags = block_group->flags; __entry->bytes_used = block_group->used; __entry->bytes_super = block_group->bytes_super; __entry->create = create; ), TP_printk_btrfs("block_group offset=%llu size=%llu " "flags=%llu(%s) bytes_used=%llu bytes_super=%llu " "create=%d", __entry->offset, __entry->size, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->bytes_used, __entry->bytes_super, __entry->create) ); #define show_ref_action(action) \ __print_symbolic(action, \ { BTRFS_ADD_DELAYED_REF, "ADD_DELAYED_REF" }, \ { BTRFS_DROP_DELAYED_REF, "DROP_DELAYED_REF" }, \ { BTRFS_ADD_DELAYED_EXTENT, "ADD_DELAYED_EXTENT" }, \ { BTRFS_UPDATE_DELAYED_HEAD, "UPDATE_DELAYED_HEAD" }) DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_node *ref), TP_ARGS(fs_info, ref), TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) __field( u64, parent ) __field( u64, ref_root ) __field( int, level ) __field( int, type ) __field( u64, seq ) ), TP_fast_assign_btrfs(fs_info, __entry->bytenr = ref->bytenr; __entry->num_bytes = ref->num_bytes; __entry->action = ref->action; __entry->parent = ref->parent; __entry->ref_root = ref->ref_root; __entry->level = ref->tree_ref.level; __entry->type = ref->type; __entry->seq = ref->seq; ), TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s " "parent=%llu(%s) ref_root=%llu(%s) level=%d " "type=%s seq=%llu", __entry->bytenr, __entry->num_bytes, show_ref_action(__entry->action), show_root_type(__entry->parent), show_root_type(__entry->ref_root), __entry->level, show_ref_type(__entry->type), __entry->seq) ); DEFINE_EVENT(btrfs_delayed_tree_ref, add_delayed_tree_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_node *ref), TP_ARGS(fs_info, ref) ); DEFINE_EVENT(btrfs_delayed_tree_ref, run_delayed_tree_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_node *ref), TP_ARGS(fs_info, ref) ); DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_node *ref), TP_ARGS(fs_info, ref), TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) __field( u64, parent ) __field( u64, ref_root ) __field( u64, owner ) __field( u64, offset ) __field( int, type ) __field( u64, seq ) ), TP_fast_assign_btrfs(fs_info, __entry->bytenr = ref->bytenr; __entry->num_bytes = ref->num_bytes; __entry->action = ref->action; __entry->parent = ref->parent; __entry->ref_root = ref->ref_root; __entry->owner = ref->data_ref.objectid; __entry->offset = ref->data_ref.offset; __entry->type = ref->type; __entry->seq = ref->seq; ), TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s " "parent=%llu(%s) ref_root=%llu(%s) owner=%llu " "offset=%llu type=%s seq=%llu", __entry->bytenr, __entry->num_bytes, show_ref_action(__entry->action), show_root_type(__entry->parent), show_root_type(__entry->ref_root), __entry->owner, __entry->offset, show_ref_type(__entry->type), __entry->seq) ); DEFINE_EVENT(btrfs_delayed_data_ref, add_delayed_data_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_node *ref), TP_ARGS(fs_info, ref) ); DEFINE_EVENT(btrfs_delayed_data_ref, run_delayed_data_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_node *ref), TP_ARGS(fs_info, ref) ); DECLARE_EVENT_CLASS(btrfs_delayed_ref_head, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_head *head_ref, int action), TP_ARGS(fs_info, head_ref, action), TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) __field( int, is_data ) ), TP_fast_assign_btrfs(fs_info, __entry->bytenr = head_ref->bytenr; __entry->num_bytes = head_ref->num_bytes; __entry->action = action; __entry->is_data = head_ref->is_data; ), TP_printk_btrfs("bytenr=%llu num_bytes=%llu action=%s is_data=%d", __entry->bytenr, __entry->num_bytes, show_ref_action(__entry->action), __entry->is_data) ); DEFINE_EVENT(btrfs_delayed_ref_head, add_delayed_ref_head, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_head *head_ref, int action), TP_ARGS(fs_info, head_ref, action) ); DEFINE_EVENT(btrfs_delayed_ref_head, run_delayed_ref_head, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_delayed_ref_head *head_ref, int action), TP_ARGS(fs_info, head_ref, action) ); #define show_chunk_type(type) \ __print_flags(type, "|", \ { BTRFS_BLOCK_GROUP_DATA, "DATA" }, \ { BTRFS_BLOCK_GROUP_SYSTEM, "SYSTEM"}, \ { BTRFS_BLOCK_GROUP_METADATA, "METADATA"}, \ { BTRFS_BLOCK_GROUP_RAID0, "RAID0" }, \ { BTRFS_BLOCK_GROUP_RAID1, "RAID1" }, \ { BTRFS_BLOCK_GROUP_DUP, "DUP" }, \ { BTRFS_BLOCK_GROUP_RAID10, "RAID10"}, \ { BTRFS_BLOCK_GROUP_RAID5, "RAID5" }, \ { BTRFS_BLOCK_GROUP_RAID6, "RAID6" }) DECLARE_EVENT_CLASS(btrfs__chunk, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_chunk_map *map, u64 offset, u64 size), TP_ARGS(fs_info, map, offset, size), TP_STRUCT__entry_btrfs( __field( int, num_stripes ) __field( u64, type ) __field( int, sub_stripes ) __field( u64, offset ) __field( u64, size ) __field( u64, root_objectid ) ), TP_fast_assign_btrfs(fs_info, __entry->num_stripes = map->num_stripes; __entry->type = map->type; __entry->sub_stripes = map->sub_stripes; __entry->offset = offset; __entry->size = size; __entry->root_objectid = fs_info->chunk_root->root_key.objectid; ), TP_printk_btrfs("root=%llu(%s) offset=%llu size=%llu " "num_stripes=%d sub_stripes=%d type=%s", show_root_type(__entry->root_objectid), __entry->offset, __entry->size, __entry->num_stripes, __entry->sub_stripes, show_chunk_type(__entry->type)) ); DEFINE_EVENT(btrfs__chunk, btrfs_chunk_alloc, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_chunk_map *map, u64 offset, u64 size), TP_ARGS(fs_info, map, offset, size) ); DEFINE_EVENT(btrfs__chunk, btrfs_chunk_free, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_chunk_map *map, u64 offset, u64 size), TP_ARGS(fs_info, map, offset, size) ); TRACE_EVENT(btrfs_cow_block, TP_PROTO(const struct btrfs_root *root, const struct extent_buffer *buf, const struct extent_buffer *cow), TP_ARGS(root, buf, cow), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, buf_start ) __field( int, refs ) __field( u64, cow_start ) __field( int, buf_level ) __field( int, cow_level ) ), TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->buf_start = buf->start; __entry->refs = atomic_read(&buf->refs); __entry->cow_start = cow->start; __entry->buf_level = btrfs_header_level(buf); __entry->cow_level = btrfs_header_level(cow); ), TP_printk_btrfs("root=%llu(%s) refs=%d orig_buf=%llu " "(orig_level=%d) cow_buf=%llu (cow_level=%d)", show_root_type(__entry->root_objectid), __entry->refs, __entry->buf_start, __entry->buf_level, __entry->cow_start, __entry->cow_level) ); TRACE_EVENT(btrfs_space_reservation, TP_PROTO(const struct btrfs_fs_info *fs_info, const char *type, u64 val, u64 bytes, int reserve), TP_ARGS(fs_info, type, val, bytes, reserve), TP_STRUCT__entry_btrfs( __string( type, type ) __field( u64, val ) __field( u64, bytes ) __field( int, reserve ) ), TP_fast_assign_btrfs(fs_info, __assign_str(type, type); __entry->val = val; __entry->bytes = bytes; __entry->reserve = reserve; ), TP_printk_btrfs("%s: %llu %s %llu", __get_str(type), __entry->val, __entry->reserve ? "reserve" : "release", __entry->bytes) ); TRACE_EVENT(btrfs_trigger_flush, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 bytes, int flush, const char *reason), TP_ARGS(fs_info, flags, bytes, flush, reason), TP_STRUCT__entry_btrfs( __field( u64, flags ) __field( u64, bytes ) __field( int, flush ) __string( reason, reason ) ), TP_fast_assign_btrfs(fs_info, __entry->flags = flags; __entry->bytes = bytes; __entry->flush = flush; __assign_str(reason, reason); ), TP_printk_btrfs("%s: flush=%d(%s) flags=%llu(%s) bytes=%llu", __get_str(reason), __entry->flush, __print_symbolic(__entry->flush, FLUSH_ACTIONS), __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->bytes) ); TRACE_EVENT(btrfs_flush_space, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 num_bytes, int state, int ret, bool for_preempt), TP_ARGS(fs_info, flags, num_bytes, state, ret, for_preempt), TP_STRUCT__entry_btrfs( __field( u64, flags ) __field( u64, num_bytes ) __field( int, state ) __field( int, ret ) __field( bool, for_preempt ) ), TP_fast_assign_btrfs(fs_info, __entry->flags = flags; __entry->num_bytes = num_bytes; __entry->state = state; __entry->ret = ret; __entry->for_preempt = for_preempt; ), TP_printk_btrfs("state=%d(%s) flags=%llu(%s) num_bytes=%llu ret=%d for_preempt=%d", __entry->state, __print_symbolic(__entry->state, FLUSH_STATES), __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->num_bytes, __entry->ret, __entry->for_preempt) ); DECLARE_EVENT_CLASS(btrfs__reserved_extent, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 start, u64 len), TP_ARGS(fs_info, start, len), TP_STRUCT__entry_btrfs( __field( u64, start ) __field( u64, len ) ), TP_fast_assign_btrfs(fs_info, __entry->start = start; __entry->len = len; ), TP_printk_btrfs("root=%llu(%s) start=%llu len=%llu", show_root_type(BTRFS_EXTENT_TREE_OBJECTID), __entry->start, __entry->len) ); DEFINE_EVENT(btrfs__reserved_extent, btrfs_reserved_extent_alloc, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 start, u64 len), TP_ARGS(fs_info, start, len) ); DEFINE_EVENT(btrfs__reserved_extent, btrfs_reserved_extent_free, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 start, u64 len), TP_ARGS(fs_info, start, len) ); TRACE_EVENT(find_free_extent, TP_PROTO(const struct btrfs_root *root, const struct find_free_extent_ctl *ffe_ctl), TP_ARGS(root, ffe_ctl), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, num_bytes ) __field( u64, empty_size ) __field( u64, flags ) ), TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->num_bytes = ffe_ctl->num_bytes; __entry->empty_size = ffe_ctl->empty_size; __entry->flags = ffe_ctl->flags; ), TP_printk_btrfs("root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s)", show_root_type(__entry->root_objectid), __entry->num_bytes, __entry->empty_size, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS)) ); TRACE_EVENT(find_free_extent_search_loop, TP_PROTO(const struct btrfs_root *root, const struct find_free_extent_ctl *ffe_ctl), TP_ARGS(root, ffe_ctl), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, num_bytes ) __field( u64, empty_size ) __field( u64, flags ) __field( u64, loop ) ), TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->num_bytes = ffe_ctl->num_bytes; __entry->empty_size = ffe_ctl->empty_size; __entry->flags = ffe_ctl->flags; __entry->loop = ffe_ctl->loop; ), TP_printk_btrfs("root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s) loop=%llu", show_root_type(__entry->root_objectid), __entry->num_bytes, __entry->empty_size, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->loop) ); TRACE_EVENT(find_free_extent_have_block_group, TP_PROTO(const struct btrfs_root *root, const struct find_free_extent_ctl *ffe_ctl, const struct btrfs_block_group *block_group), TP_ARGS(root, ffe_ctl, block_group), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, num_bytes ) __field( u64, empty_size ) __field( u64, flags ) __field( u64, loop ) __field( bool, hinted ) __field( u64, bg_start ) __field( u64, bg_flags ) ), TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->num_bytes = ffe_ctl->num_bytes; __entry->empty_size = ffe_ctl->empty_size; __entry->flags = ffe_ctl->flags; __entry->loop = ffe_ctl->loop; __entry->hinted = ffe_ctl->hinted; __entry->bg_start = block_group->start; __entry->bg_flags = block_group->flags; ), TP_printk_btrfs( "root=%llu(%s) len=%llu empty_size=%llu flags=%llu(%s) loop=%llu hinted=%d block_group=%llu bg_flags=%llu(%s)", show_root_type(__entry->root_objectid), __entry->num_bytes, __entry->empty_size, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->loop, __entry->hinted, __entry->bg_start, __entry->bg_flags, __print_flags((unsigned long)__entry->bg_flags, "|", BTRFS_GROUP_FLAGS)) ); DECLARE_EVENT_CLASS(btrfs__reserve_extent, TP_PROTO(const struct btrfs_block_group *block_group, const struct find_free_extent_ctl *ffe_ctl), TP_ARGS(block_group, ffe_ctl), TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) __field( u64, flags ) __field( int, bg_size_class ) __field( u64, start ) __field( u64, len ) __field( u64, loop ) __field( bool, hinted ) __field( int, size_class ) ), TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->start; __entry->flags = block_group->flags; __entry->bg_size_class = block_group->size_class; __entry->start = ffe_ctl->search_start; __entry->len = ffe_ctl->num_bytes; __entry->loop = ffe_ctl->loop; __entry->hinted = ffe_ctl->hinted; __entry->size_class = ffe_ctl->size_class; ), TP_printk_btrfs( "root=%llu(%s) block_group=%llu flags=%llu(%s) bg_size_class=%d start=%llu len=%llu loop=%llu hinted=%d size_class=%d", show_root_type(BTRFS_EXTENT_TREE_OBJECTID), __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->bg_size_class, __entry->start, __entry->len, __entry->loop, __entry->hinted, __entry->size_class) ); DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent, TP_PROTO(const struct btrfs_block_group *block_group, const struct find_free_extent_ctl *ffe_ctl), TP_ARGS(block_group, ffe_ctl) ); DEFINE_EVENT(btrfs__reserve_extent, btrfs_reserve_extent_cluster, TP_PROTO(const struct btrfs_block_group *block_group, const struct find_free_extent_ctl *ffe_ctl), TP_ARGS(block_group, ffe_ctl) ); TRACE_EVENT(btrfs_find_cluster, TP_PROTO(const struct btrfs_block_group *block_group, u64 start, u64 bytes, u64 empty_size, u64 min_bytes), TP_ARGS(block_group, start, bytes, empty_size, min_bytes), TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) __field( u64, flags ) __field( u64, start ) __field( u64, bytes ) __field( u64, empty_size ) __field( u64, min_bytes ) ), TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->start; __entry->flags = block_group->flags; __entry->start = start; __entry->bytes = bytes; __entry->empty_size = empty_size; __entry->min_bytes = min_bytes; ), TP_printk_btrfs("block_group=%llu flags=%llu(%s) start=%llu len=%llu " "empty_size=%llu min_bytes=%llu", __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->start, __entry->bytes, __entry->empty_size, __entry->min_bytes) ); TRACE_EVENT(btrfs_failed_cluster_setup, TP_PROTO(const struct btrfs_block_group *block_group), TP_ARGS(block_group), TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) ), TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->start; ), TP_printk_btrfs("block_group=%llu", __entry->bg_objectid) ); TRACE_EVENT(btrfs_setup_cluster, TP_PROTO(const struct btrfs_block_group *block_group, const struct btrfs_free_cluster *cluster, u64 size, int bitmap), TP_ARGS(block_group, cluster, size, bitmap), TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) __field( u64, flags ) __field( u64, start ) __field( u64, max_size ) __field( u64, size ) __field( int, bitmap ) ), TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->start; __entry->flags = block_group->flags; __entry->start = cluster->window_start; __entry->max_size = cluster->max_size; __entry->size = size; __entry->bitmap = bitmap; ), TP_printk_btrfs("block_group=%llu flags=%llu(%s) window_start=%llu " "size=%llu max_size=%llu bitmap=%d", __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->start, __entry->size, __entry->max_size, __entry->bitmap) ); struct extent_state; TRACE_EVENT(alloc_extent_state, TP_PROTO(const struct extent_state *state, gfp_t mask, unsigned long IP), TP_ARGS(state, mask, IP), TP_STRUCT__entry( __field(const struct extent_state *, state) __field(unsigned long, mask) __field(const void*, ip) ), TP_fast_assign( __entry->state = state, __entry->mask = (__force unsigned long)mask, __entry->ip = (const void *)IP ), TP_printk("state=%p mask=%s caller=%pS", __entry->state, show_gfp_flags(__entry->mask), __entry->ip) ); TRACE_EVENT(free_extent_state, TP_PROTO(const struct extent_state *state, unsigned long IP), TP_ARGS(state, IP), TP_STRUCT__entry( __field(const struct extent_state *, state) __field(const void*, ip) ), TP_fast_assign( __entry->state = state, __entry->ip = (const void *)IP ), TP_printk("state=%p caller=%pS", __entry->state, __entry->ip) ); DECLARE_EVENT_CLASS(btrfs__work, TP_PROTO(const struct btrfs_work *work), TP_ARGS(work), TP_STRUCT__entry_btrfs( __field( const void *, work ) __field( const void *, wq ) __field( const void *, func ) __field( const void *, ordered_func ) __field( const void *, normal_work ) ), TP_fast_assign_btrfs(btrfs_work_owner(work), __entry->work = work; __entry->wq = work->wq; __entry->func = work->func; __entry->ordered_func = work->ordered_func; __entry->normal_work = &work->normal_work; ), TP_printk_btrfs("work=%p (normal_work=%p) wq=%p func=%ps ordered_func=%p", __entry->work, __entry->normal_work, __entry->wq, __entry->func, __entry->ordered_func) ); /* * For situations when the work is freed, we pass fs_info and a tag that matches * the address of the work structure so it can be paired with the scheduling * event. DO NOT add anything here that dereferences wtag. */ DECLARE_EVENT_CLASS(btrfs__work__done, TP_PROTO(const struct btrfs_fs_info *fs_info, const void *wtag), TP_ARGS(fs_info, wtag), TP_STRUCT__entry_btrfs( __field( const void *, wtag ) ), TP_fast_assign_btrfs(fs_info, __entry->wtag = wtag; ), TP_printk_btrfs("work->%p", __entry->wtag) ); DEFINE_EVENT(btrfs__work, btrfs_work_queued, TP_PROTO(const struct btrfs_work *work), TP_ARGS(work) ); DEFINE_EVENT(btrfs__work, btrfs_work_sched, TP_PROTO(const struct btrfs_work *work), TP_ARGS(work) ); DEFINE_EVENT(btrfs__work__done, btrfs_all_work_done, TP_PROTO(const struct btrfs_fs_info *fs_info, const void *wtag), TP_ARGS(fs_info, wtag) ); DEFINE_EVENT(btrfs__work, btrfs_ordered_sched, TP_PROTO(const struct btrfs_work *work), TP_ARGS(work) ); DECLARE_EVENT_CLASS(btrfs_workqueue, TP_PROTO(const struct btrfs_workqueue *wq, const char *name), TP_ARGS(wq, name), TP_STRUCT__entry_btrfs( __field( const void *, wq ) __string( name, name ) ), TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; __assign_str(name, name); ), TP_printk_btrfs("name=%s wq=%p", __get_str(name), __entry->wq) ); DEFINE_EVENT(btrfs_workqueue, btrfs_workqueue_alloc, TP_PROTO(const struct btrfs_workqueue *wq, const char *name), TP_ARGS(wq, name) ); DECLARE_EVENT_CLASS(btrfs_workqueue_done, TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq), TP_STRUCT__entry_btrfs( __field( const void *, wq ) ), TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; ), TP_printk_btrfs("wq=%p", __entry->wq) ); DEFINE_EVENT(btrfs_workqueue_done, btrfs_workqueue_destroy, TP_PROTO(const struct btrfs_workqueue *wq), TP_ARGS(wq) ); #define BTRFS_QGROUP_OPERATIONS \ { QGROUP_RESERVE, "reserve" }, \ { QGROUP_RELEASE, "release" }, \ { QGROUP_FREE, "free" } DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, TP_PROTO(const struct inode *inode, u64 start, u64 len, u64 reserved, int op), TP_ARGS(inode, start, len, reserved, op), TP_STRUCT__entry_btrfs( __field( u64, rootid ) __field( u64, ino ) __field( u64, start ) __field( u64, len ) __field( u64, reserved ) __field( int, op ) ), TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->rootid = BTRFS_I(inode)->root->root_key.objectid; __entry->ino = btrfs_ino(BTRFS_I(inode)); __entry->start = start; __entry->len = len; __entry->reserved = reserved; __entry->op = op; ), TP_printk_btrfs("root=%llu ino=%llu start=%llu len=%llu reserved=%llu op=%s", __entry->rootid, __entry->ino, __entry->start, __entry->len, __entry->reserved, __print_flags((unsigned long)__entry->op, "", BTRFS_QGROUP_OPERATIONS) ) ); DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_reserve_data, TP_PROTO(const struct inode *inode, u64 start, u64 len, u64 reserved, int op), TP_ARGS(inode, start, len, reserved, op) ); DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_release_data, TP_PROTO(const struct inode *inode, u64 start, u64 len, u64 reserved, int op), TP_ARGS(inode, start, len, reserved, op) ); DECLARE_EVENT_CLASS(btrfs_qgroup_extent, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_qgroup_extent_record *rec), TP_ARGS(fs_info, rec), TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) ), TP_fast_assign_btrfs(fs_info, __entry->bytenr = rec->bytenr, __entry->num_bytes = rec->num_bytes; ), TP_printk_btrfs("bytenr=%llu num_bytes=%llu", __entry->bytenr, __entry->num_bytes) ); DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_account_extents, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_qgroup_extent_record *rec), TP_ARGS(fs_info, rec) ); DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_trace_extent, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_qgroup_extent_record *rec), TP_ARGS(fs_info, rec) ); TRACE_EVENT(qgroup_num_dirty_extents, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 transid, u64 num_dirty_extents), TP_ARGS(fs_info, transid, num_dirty_extents), TP_STRUCT__entry_btrfs( __field( u64, transid ) __field( u64, num_dirty_extents ) ), TP_fast_assign_btrfs(fs_info, __entry->transid = transid; __entry->num_dirty_extents = num_dirty_extents; ), TP_printk_btrfs("transid=%llu num_dirty_extents=%llu", __entry->transid, __entry->num_dirty_extents) ); TRACE_EVENT(btrfs_qgroup_account_extent, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 transid, u64 bytenr, u64 num_bytes, u64 nr_old_roots, u64 nr_new_roots), TP_ARGS(fs_info, transid, bytenr, num_bytes, nr_old_roots, nr_new_roots), TP_STRUCT__entry_btrfs( __field( u64, transid ) __field( u64, bytenr ) __field( u64, num_bytes ) __field( u64, nr_old_roots ) __field( u64, nr_new_roots ) ), TP_fast_assign_btrfs(fs_info, __entry->transid = transid; __entry->bytenr = bytenr; __entry->num_bytes = num_bytes; __entry->nr_old_roots = nr_old_roots; __entry->nr_new_roots = nr_new_roots; ), TP_printk_btrfs( "transid=%llu bytenr=%llu num_bytes=%llu nr_old_roots=%llu nr_new_roots=%llu", __entry->transid, __entry->bytenr, __entry->num_bytes, __entry->nr_old_roots, __entry->nr_new_roots) ); TRACE_EVENT(qgroup_update_counters, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_qgroup *qgroup, u64 cur_old_count, u64 cur_new_count), TP_ARGS(fs_info, qgroup, cur_old_count, cur_new_count), TP_STRUCT__entry_btrfs( __field( u64, qgid ) __field( u64, old_rfer ) __field( u64, old_excl ) __field( u64, cur_old_count ) __field( u64, cur_new_count ) ), TP_fast_assign_btrfs(fs_info, __entry->qgid = qgroup->qgroupid; __entry->old_rfer = qgroup->rfer; __entry->old_excl = qgroup->excl; __entry->cur_old_count = cur_old_count; __entry->cur_new_count = cur_new_count; ), TP_printk_btrfs("qgid=%llu old_rfer=%llu old_excl=%llu cur_old_count=%llu cur_new_count=%llu", __entry->qgid, __entry->old_rfer, __entry->old_excl, __entry->cur_old_count, __entry->cur_new_count) ); TRACE_EVENT(qgroup_update_reserve, TP_PROTO(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup, s64 diff, int type), TP_ARGS(fs_info, qgroup, diff, type), TP_STRUCT__entry_btrfs( __field( u64, qgid ) __field( u64, cur_reserved ) __field( s64, diff ) __field( int, type ) ), TP_fast_assign_btrfs(fs_info, __entry->qgid = qgroup->qgroupid; __entry->cur_reserved = qgroup->rsv.values[type]; __entry->diff = diff; __entry->type = type; ), TP_printk_btrfs("qgid=%llu type=%s cur_reserved=%llu diff=%lld", __entry->qgid, __print_symbolic(__entry->type, QGROUP_RSV_TYPES), __entry->cur_reserved, __entry->diff) ); TRACE_EVENT(qgroup_meta_reserve, TP_PROTO(struct btrfs_root *root, s64 diff, int type), TP_ARGS(root, diff, type), TP_STRUCT__entry_btrfs( __field( u64, refroot ) __field( s64, diff ) __field( int, type ) ), TP_fast_assign_btrfs(root->fs_info, __entry->refroot = root->root_key.objectid; __entry->diff = diff; __entry->type = type; ), TP_printk_btrfs("refroot=%llu(%s) type=%s diff=%lld", show_root_type(__entry->refroot), __print_symbolic(__entry->type, QGROUP_RSV_TYPES), __entry->diff) ); TRACE_EVENT(qgroup_meta_convert, TP_PROTO(struct btrfs_root *root, s64 diff), TP_ARGS(root, diff), TP_STRUCT__entry_btrfs( __field( u64, refroot ) __field( s64, diff ) ), TP_fast_assign_btrfs(root->fs_info, __entry->refroot = root->root_key.objectid; __entry->diff = diff; ), TP_printk_btrfs("refroot=%llu(%s) type=%s->%s diff=%lld", show_root_type(__entry->refroot), __print_symbolic(BTRFS_QGROUP_RSV_META_PREALLOC, QGROUP_RSV_TYPES), __print_symbolic(BTRFS_QGROUP_RSV_META_PERTRANS, QGROUP_RSV_TYPES), __entry->diff) ); TRACE_EVENT(qgroup_meta_free_all_pertrans, TP_PROTO(struct btrfs_root *root), TP_ARGS(root), TP_STRUCT__entry_btrfs( __field( u64, refroot ) __field( s64, diff ) __field( int, type ) ), TP_fast_assign_btrfs(root->fs_info, __entry->refroot = root->root_key.objectid; spin_lock(&root->qgroup_meta_rsv_lock); __entry->diff = -(s64)root->qgroup_meta_rsv_pertrans; spin_unlock(&root->qgroup_meta_rsv_lock); __entry->type = BTRFS_QGROUP_RSV_META_PERTRANS; ), TP_printk_btrfs("refroot=%llu(%s) type=%s diff=%lld", show_root_type(__entry->refroot), __print_symbolic(__entry->type, QGROUP_RSV_TYPES), __entry->diff) ); DECLARE_EVENT_CLASS(btrfs__prelim_ref, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct prelim_ref *oldref, const struct prelim_ref *newref, u64 tree_size), TP_ARGS(fs_info, newref, oldref, tree_size), TP_STRUCT__entry_btrfs( __field( u64, root_id ) __field( u64, objectid ) __field( u8, type ) __field( u64, offset ) __field( int, level ) __field( int, old_count ) __field( u64, parent ) __field( u64, bytenr ) __field( int, mod_count ) __field( u64, tree_size ) ), TP_fast_assign_btrfs(fs_info, __entry->root_id = oldref->root_id; __entry->objectid = oldref->key_for_search.objectid; __entry->type = oldref->key_for_search.type; __entry->offset = oldref->key_for_search.offset; __entry->level = oldref->level; __entry->old_count = oldref->count; __entry->parent = oldref->parent; __entry->bytenr = oldref->wanted_disk_byte; __entry->mod_count = newref ? newref->count : 0; __entry->tree_size = tree_size; ), TP_printk_btrfs("root_id=%llu key=[%llu,%u,%llu] level=%d count=[%d+%d=%d] parent=%llu wanted_disk_byte=%llu nodes=%llu", __entry->root_id, __entry->objectid, __entry->type, __entry->offset, __entry->level, __entry->old_count, __entry->mod_count, __entry->old_count + __entry->mod_count, __entry->parent, __entry->bytenr, __entry->tree_size) ); DEFINE_EVENT(btrfs__prelim_ref, btrfs_prelim_ref_merge, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct prelim_ref *oldref, const struct prelim_ref *newref, u64 tree_size), TP_ARGS(fs_info, oldref, newref, tree_size) ); DEFINE_EVENT(btrfs__prelim_ref, btrfs_prelim_ref_insert, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct prelim_ref *oldref, const struct prelim_ref *newref, u64 tree_size), TP_ARGS(fs_info, oldref, newref, tree_size) ); TRACE_EVENT(btrfs_inode_mod_outstanding_extents, TP_PROTO(const struct btrfs_root *root, u64 ino, int mod, unsigned outstanding), TP_ARGS(root, ino, mod, outstanding), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, ino ) __field( int, mod ) __field( unsigned, outstanding ) ), TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->ino = ino; __entry->mod = mod; __entry->outstanding = outstanding; ), TP_printk_btrfs("root=%llu(%s) ino=%llu mod=%d outstanding=%u", show_root_type(__entry->root_objectid), __entry->ino, __entry->mod, __entry->outstanding) ); DECLARE_EVENT_CLASS(btrfs__block_group, TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache), TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, len ) __field( u64, used ) __field( u64, flags ) ), TP_fast_assign_btrfs(bg_cache->fs_info, __entry->bytenr = bg_cache->start, __entry->len = bg_cache->length, __entry->used = bg_cache->used; __entry->flags = bg_cache->flags; ), TP_printk_btrfs("bg bytenr=%llu len=%llu used=%llu flags=%llu(%s)", __entry->bytenr, __entry->len, __entry->used, __entry->flags, __print_flags(__entry->flags, "|", BTRFS_GROUP_FLAGS)) ); DEFINE_EVENT(btrfs__block_group, btrfs_remove_block_group, TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache) ); DEFINE_EVENT(btrfs__block_group, btrfs_add_unused_block_group, TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache) ); DEFINE_EVENT(btrfs__block_group, btrfs_add_reclaim_block_group, TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache) ); DEFINE_EVENT(btrfs__block_group, btrfs_reclaim_block_group, TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache) ); DEFINE_EVENT(btrfs__block_group, btrfs_skip_unused_block_group, TP_PROTO(const struct btrfs_block_group *bg_cache), TP_ARGS(bg_cache) ); TRACE_EVENT(btrfs_set_extent_bit, TP_PROTO(const struct extent_io_tree *tree, u64 start, u64 len, unsigned set_bits), TP_ARGS(tree, start, len, set_bits), TP_STRUCT__entry_btrfs( __field( unsigned, owner ) __field( u64, ino ) __field( u64, rootid ) __field( u64, start ) __field( u64, len ) __field( unsigned, set_bits) ), TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree), const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree); __entry->owner = tree->owner; __entry->ino = inode ? btrfs_ino(inode) : 0; __entry->rootid = inode ? inode->root->root_key.objectid : 0; __entry->start = start; __entry->len = len; __entry->set_bits = set_bits; ), TP_printk_btrfs( "io_tree=%s ino=%llu root=%llu start=%llu len=%llu set_bits=%s", __print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino, __entry->rootid, __entry->start, __entry->len, __print_flags(__entry->set_bits, "|", EXTENT_FLAGS)) ); TRACE_EVENT(btrfs_clear_extent_bit, TP_PROTO(const struct extent_io_tree *tree, u64 start, u64 len, unsigned clear_bits), TP_ARGS(tree, start, len, clear_bits), TP_STRUCT__entry_btrfs( __field( unsigned, owner ) __field( u64, ino ) __field( u64, rootid ) __field( u64, start ) __field( u64, len ) __field( unsigned, clear_bits) ), TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree), const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree); __entry->owner = tree->owner; __entry->ino = inode ? btrfs_ino(inode) : 0; __entry->rootid = inode ? inode->root->root_key.objectid : 0; __entry->start = start; __entry->len = len; __entry->clear_bits = clear_bits; ), TP_printk_btrfs( "io_tree=%s ino=%llu root=%llu start=%llu len=%llu clear_bits=%s", __print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino, __entry->rootid, __entry->start, __entry->len, __print_flags(__entry->clear_bits, "|", EXTENT_FLAGS)) ); TRACE_EVENT(btrfs_convert_extent_bit, TP_PROTO(const struct extent_io_tree *tree, u64 start, u64 len, unsigned set_bits, unsigned clear_bits), TP_ARGS(tree, start, len, set_bits, clear_bits), TP_STRUCT__entry_btrfs( __field( unsigned, owner ) __field( u64, ino ) __field( u64, rootid ) __field( u64, start ) __field( u64, len ) __field( unsigned, set_bits) __field( unsigned, clear_bits) ), TP_fast_assign_btrfs(extent_io_tree_to_fs_info(tree), const struct btrfs_inode *inode = extent_io_tree_to_inode_const(tree); __entry->owner = tree->owner; __entry->ino = inode ? btrfs_ino(inode) : 0; __entry->rootid = inode ? inode->root->root_key.objectid : 0; __entry->start = start; __entry->len = len; __entry->set_bits = set_bits; __entry->clear_bits = clear_bits; ), TP_printk_btrfs( "io_tree=%s ino=%llu root=%llu start=%llu len=%llu set_bits=%s clear_bits=%s", __print_symbolic(__entry->owner, IO_TREE_OWNER), __entry->ino, __entry->rootid, __entry->start, __entry->len, __print_flags(__entry->set_bits , "|", EXTENT_FLAGS), __print_flags(__entry->clear_bits, "|", EXTENT_FLAGS)) ); DECLARE_EVENT_CLASS(btrfs_dump_space_info, TP_PROTO(struct btrfs_fs_info *fs_info, const struct btrfs_space_info *sinfo), TP_ARGS(fs_info, sinfo), TP_STRUCT__entry_btrfs( __field( u64, flags ) __field( u64, total_bytes ) __field( u64, bytes_used ) __field( u64, bytes_pinned ) __field( u64, bytes_reserved ) __field( u64, bytes_may_use ) __field( u64, bytes_readonly ) __field( u64, reclaim_size ) __field( int, clamp ) __field( u64, global_reserved ) __field( u64, trans_reserved ) __field( u64, delayed_refs_reserved ) __field( u64, delayed_reserved ) __field( u64, free_chunk_space ) __field( u64, delalloc_bytes ) __field( u64, ordered_bytes ) ), TP_fast_assign_btrfs(fs_info, __entry->flags = sinfo->flags; __entry->total_bytes = sinfo->total_bytes; __entry->bytes_used = sinfo->bytes_used; __entry->bytes_pinned = sinfo->bytes_pinned; __entry->bytes_reserved = sinfo->bytes_reserved; __entry->bytes_may_use = sinfo->bytes_may_use; __entry->bytes_readonly = sinfo->bytes_readonly; __entry->reclaim_size = sinfo->reclaim_size; __entry->clamp = sinfo->clamp; __entry->global_reserved = fs_info->global_block_rsv.reserved; __entry->trans_reserved = fs_info->trans_block_rsv.reserved; __entry->delayed_refs_reserved = fs_info->delayed_refs_rsv.reserved; __entry->delayed_reserved = fs_info->delayed_block_rsv.reserved; __entry->free_chunk_space = atomic64_read(&fs_info->free_chunk_space); __entry->delalloc_bytes = percpu_counter_sum_positive(&fs_info->delalloc_bytes); __entry->ordered_bytes = percpu_counter_sum_positive(&fs_info->ordered_bytes); ), TP_printk_btrfs("flags=%s total_bytes=%llu bytes_used=%llu " "bytes_pinned=%llu bytes_reserved=%llu " "bytes_may_use=%llu bytes_readonly=%llu " "reclaim_size=%llu clamp=%d global_reserved=%llu " "trans_reserved=%llu delayed_refs_reserved=%llu " "delayed_reserved=%llu chunk_free_space=%llu " "delalloc_bytes=%llu ordered_bytes=%llu", __print_flags(__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->total_bytes, __entry->bytes_used, __entry->bytes_pinned, __entry->bytes_reserved, __entry->bytes_may_use, __entry->bytes_readonly, __entry->reclaim_size, __entry->clamp, __entry->global_reserved, __entry->trans_reserved, __entry->delayed_refs_reserved, __entry->delayed_reserved, __entry->free_chunk_space, __entry->delalloc_bytes, __entry->ordered_bytes) ); DEFINE_EVENT(btrfs_dump_space_info, btrfs_done_preemptive_reclaim, TP_PROTO(struct btrfs_fs_info *fs_info, const struct btrfs_space_info *sinfo), TP_ARGS(fs_info, sinfo) ); DEFINE_EVENT(btrfs_dump_space_info, btrfs_fail_all_tickets, TP_PROTO(struct btrfs_fs_info *fs_info, const struct btrfs_space_info *sinfo), TP_ARGS(fs_info, sinfo) ); TRACE_EVENT(btrfs_reserve_ticket, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 flags, u64 bytes, u64 start_ns, int flush, int error), TP_ARGS(fs_info, flags, bytes, start_ns, flush, error), TP_STRUCT__entry_btrfs( __field( u64, flags ) __field( u64, bytes ) __field( u64, start_ns ) __field( int, flush ) __field( int, error ) ), TP_fast_assign_btrfs(fs_info, __entry->flags = flags; __entry->bytes = bytes; __entry->start_ns = start_ns; __entry->flush = flush; __entry->error = error; ), TP_printk_btrfs("flags=%s bytes=%llu start_ns=%llu flush=%s error=%d", __print_flags(__entry->flags, "|", BTRFS_GROUP_FLAGS), __entry->bytes, __entry->start_ns, __print_symbolic(__entry->flush, FLUSH_ACTIONS), __entry->error) ); DECLARE_EVENT_CLASS(btrfs_sleep_tree_lock, TP_PROTO(const struct extent_buffer *eb, u64 start_ns), TP_ARGS(eb, start_ns), TP_STRUCT__entry_btrfs( __field( u64, block ) __field( u64, generation ) __field( u64, start_ns ) __field( u64, end_ns ) __field( u64, diff_ns ) __field( u64, owner ) __field( int, is_log_tree ) ), TP_fast_assign_btrfs(eb->fs_info, __entry->block = eb->start; __entry->generation = btrfs_header_generation(eb); __entry->start_ns = start_ns; __entry->end_ns = ktime_get_ns(); __entry->diff_ns = __entry->end_ns - start_ns; __entry->owner = btrfs_header_owner(eb); __entry->is_log_tree = (eb->log_index >= 0); ), TP_printk_btrfs( "block=%llu generation=%llu start_ns=%llu end_ns=%llu diff_ns=%llu owner=%llu is_log_tree=%d", __entry->block, __entry->generation, __entry->start_ns, __entry->end_ns, __entry->diff_ns, __entry->owner, __entry->is_log_tree) ); DEFINE_EVENT(btrfs_sleep_tree_lock, btrfs_tree_read_lock, TP_PROTO(const struct extent_buffer *eb, u64 start_ns), TP_ARGS(eb, start_ns) ); DEFINE_EVENT(btrfs_sleep_tree_lock, btrfs_tree_lock, TP_PROTO(const struct extent_buffer *eb, u64 start_ns), TP_ARGS(eb, start_ns) ); DECLARE_EVENT_CLASS(btrfs_locking_events, TP_PROTO(const struct extent_buffer *eb), TP_ARGS(eb), TP_STRUCT__entry_btrfs( __field( u64, block ) __field( u64, generation ) __field( u64, owner ) __field( int, is_log_tree ) ), TP_fast_assign_btrfs(eb->fs_info, __entry->block = eb->start; __entry->generation = btrfs_header_generation(eb); __entry->owner = btrfs_header_owner(eb); __entry->is_log_tree = (eb->log_index >= 0); ), TP_printk_btrfs("block=%llu generation=%llu owner=%llu is_log_tree=%d", __entry->block, __entry->generation, __entry->owner, __entry->is_log_tree) ); #define DEFINE_BTRFS_LOCK_EVENT(name) \ DEFINE_EVENT(btrfs_locking_events, name, \ TP_PROTO(const struct extent_buffer *eb), \ \ TP_ARGS(eb) \ ) DEFINE_BTRFS_LOCK_EVENT(btrfs_tree_unlock); DEFINE_BTRFS_LOCK_EVENT(btrfs_tree_read_unlock); DEFINE_BTRFS_LOCK_EVENT(btrfs_tree_read_unlock_blocking); DEFINE_BTRFS_LOCK_EVENT(btrfs_set_lock_blocking_read); DEFINE_BTRFS_LOCK_EVENT(btrfs_set_lock_blocking_write); DEFINE_BTRFS_LOCK_EVENT(btrfs_try_tree_read_lock); DEFINE_BTRFS_LOCK_EVENT(btrfs_try_tree_write_lock); DEFINE_BTRFS_LOCK_EVENT(btrfs_tree_read_lock_atomic); DECLARE_EVENT_CLASS(btrfs__space_info_update, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_space_info *sinfo, u64 old, s64 diff), TP_ARGS(fs_info, sinfo, old, diff), TP_STRUCT__entry_btrfs( __field( u64, type ) __field( u64, old ) __field( s64, diff ) ), TP_fast_assign_btrfs(fs_info, __entry->type = sinfo->flags; __entry->old = old; __entry->diff = diff; ), TP_printk_btrfs("type=%s old=%llu diff=%lld", __print_flags(__entry->type, "|", BTRFS_GROUP_FLAGS), __entry->old, __entry->diff) ); DEFINE_EVENT(btrfs__space_info_update, update_bytes_may_use, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_space_info *sinfo, u64 old, s64 diff), TP_ARGS(fs_info, sinfo, old, diff) ); DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned, TP_PROTO(const struct btrfs_fs_info *fs_info, const struct btrfs_space_info *sinfo, u64 old, s64 diff), TP_ARGS(fs_info, sinfo, old, diff) ); DECLARE_EVENT_CLASS(btrfs_raid56_bio, TP_PROTO(const struct btrfs_raid_bio *rbio, const struct bio *bio, const struct raid56_bio_trace_info *trace_info), TP_ARGS(rbio, bio, trace_info), TP_STRUCT__entry_btrfs( __field( u64, full_stripe ) __field( u64, physical ) __field( u64, devid ) __field( u32, offset ) __field( u32, len ) __field( u8, opf ) __field( u8, total_stripes ) __field( u8, real_stripes ) __field( u8, nr_data ) __field( u8, stripe_nr ) ), TP_fast_assign_btrfs(rbio->bioc->fs_info, __entry->full_stripe = rbio->bioc->full_stripe_logical; __entry->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; __entry->len = bio->bi_iter.bi_size; __entry->opf = bio_op(bio); __entry->devid = trace_info->devid; __entry->offset = trace_info->offset; __entry->stripe_nr = trace_info->stripe_nr; __entry->total_stripes = rbio->bioc->num_stripes; __entry->real_stripes = rbio->real_stripes; __entry->nr_data = rbio->nr_data; ), /* * For type output, we need to output things like "DATA1" * (the first data stripe), "DATA2" (the second data stripe), * "PQ1" (P stripe),"PQ2" (Q stripe), "REPLACE0" (replace target device). */ TP_printk_btrfs( "full_stripe=%llu devid=%lld type=%s%d offset=%d opf=0x%x physical=%llu len=%u", __entry->full_stripe, __entry->devid, (__entry->stripe_nr < __entry->nr_data) ? "DATA" : ((__entry->stripe_nr < __entry->real_stripes) ? "PQ" : "REPLACE"), (__entry->stripe_nr < __entry->nr_data) ? (__entry->stripe_nr + 1) : ((__entry->stripe_nr < __entry->real_stripes) ? (__entry->stripe_nr - __entry->nr_data + 1) : 0), __entry->offset, __entry->opf, __entry->physical, __entry->len) ); DEFINE_EVENT(btrfs_raid56_bio, raid56_read, TP_PROTO(const struct btrfs_raid_bio *rbio, const struct bio *bio, const struct raid56_bio_trace_info *trace_info), TP_ARGS(rbio, bio, trace_info) ); DEFINE_EVENT(btrfs_raid56_bio, raid56_write, TP_PROTO(const struct btrfs_raid_bio *rbio, const struct bio *bio, const struct raid56_bio_trace_info *trace_info), TP_ARGS(rbio, bio, trace_info) ); TRACE_EVENT(btrfs_insert_one_raid_extent, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 logical, u64 length, int num_stripes), TP_ARGS(fs_info, logical, length, num_stripes), TP_STRUCT__entry_btrfs( __field( u64, logical ) __field( u64, length ) __field( int, num_stripes ) ), TP_fast_assign_btrfs(fs_info, __entry->logical = logical; __entry->length = length; __entry->num_stripes = num_stripes; ), TP_printk_btrfs("logical=%llu length=%llu num_stripes=%d", __entry->logical, __entry->length, __entry->num_stripes) ); TRACE_EVENT(btrfs_raid_extent_delete, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 start, u64 end, u64 found_start, u64 found_end), TP_ARGS(fs_info, start, end, found_start, found_end), TP_STRUCT__entry_btrfs( __field( u64, start ) __field( u64, end ) __field( u64, found_start ) __field( u64, found_end ) ), TP_fast_assign_btrfs(fs_info, __entry->start = start; __entry->end = end; __entry->found_start = found_start; __entry->found_end = found_end; ), TP_printk_btrfs("start=%llu end=%llu found_start=%llu found_end=%llu", __entry->start, __entry->end, __entry->found_start, __entry->found_end) ); TRACE_EVENT(btrfs_get_raid_extent_offset, TP_PROTO(const struct btrfs_fs_info *fs_info, u64 logical, u64 length, u64 physical, u64 devid), TP_ARGS(fs_info, logical, length, physical, devid), TP_STRUCT__entry_btrfs( __field( u64, logical ) __field( u64, length ) __field( u64, physical ) __field( u64, devid ) ), TP_fast_assign_btrfs(fs_info, __entry->logical = logical; __entry->length = length; __entry->physical = physical; __entry->devid = devid; ), TP_printk_btrfs("logical=%llu length=%llu physical=%llu devid=%llu", __entry->logical, __entry->length, __entry->physical, __entry->devid) ); TRACE_EVENT(btrfs_extent_map_shrinker_count, TP_PROTO(const struct btrfs_fs_info *fs_info, long nr), TP_ARGS(fs_info, nr), TP_STRUCT__entry_btrfs( __field( long, nr ) ), TP_fast_assign_btrfs(fs_info, __entry->nr = nr; ), TP_printk_btrfs("nr=%ld", __entry->nr) ); TRACE_EVENT(btrfs_extent_map_shrinker_scan_enter, TP_PROTO(const struct btrfs_fs_info *fs_info, long nr_to_scan, long nr), TP_ARGS(fs_info, nr_to_scan, nr), TP_STRUCT__entry_btrfs( __field( long, nr_to_scan ) __field( long, nr ) __field( u64, last_root_id ) __field( u64, last_ino ) ), TP_fast_assign_btrfs(fs_info, __entry->nr_to_scan = nr_to_scan; __entry->nr = nr; __entry->last_root_id = fs_info->extent_map_shrinker_last_root; __entry->last_ino = fs_info->extent_map_shrinker_last_ino; ), TP_printk_btrfs("nr_to_scan=%ld nr=%ld last_root=%llu(%s) last_ino=%llu", __entry->nr_to_scan, __entry->nr, show_root_type(__entry->last_root_id), __entry->last_ino) ); TRACE_EVENT(btrfs_extent_map_shrinker_scan_exit, TP_PROTO(const struct btrfs_fs_info *fs_info, long nr_dropped, long nr), TP_ARGS(fs_info, nr_dropped, nr), TP_STRUCT__entry_btrfs( __field( long, nr_dropped ) __field( long, nr ) __field( u64, last_root_id ) __field( u64, last_ino ) ), TP_fast_assign_btrfs(fs_info, __entry->nr_dropped = nr_dropped; __entry->nr = nr; __entry->last_root_id = fs_info->extent_map_shrinker_last_root; __entry->last_ino = fs_info->extent_map_shrinker_last_ino; ), TP_printk_btrfs("nr_dropped=%ld nr=%ld last_root=%llu(%s) last_ino=%llu", __entry->nr_dropped, __entry->nr, show_root_type(__entry->last_root_id), __entry->last_ino) ); TRACE_EVENT(btrfs_extent_map_shrinker_remove_em, TP_PROTO(const struct btrfs_inode *inode, const struct extent_map *em), TP_ARGS(inode, em), TP_STRUCT__entry_btrfs( __field( u64, ino ) __field( u64, root_id ) __field( u64, start ) __field( u64, len ) __field( u64, block_start ) __field( u32, flags ) ), TP_fast_assign_btrfs(inode->root->fs_info, __entry->ino = btrfs_ino(inode); __entry->root_id = inode->root->root_key.objectid; __entry->start = em->start; __entry->len = em->len; __entry->block_start = em->block_start; __entry->flags = em->flags; ), TP_printk_btrfs( "ino=%llu root=%llu(%s) start=%llu len=%llu block_start=%llu(%s) flags=%s", __entry->ino, show_root_type(__entry->root_id), __entry->start, __entry->len, show_map_type(__entry->block_start), show_map_flags(__entry->flags)) ); #endif /* _TRACE_BTRFS_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 15 15 15 15 15 15 70 10 79 1 2 11 17 14 1 15 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 | // SPDX-License-Identifier: GPL-2.0 #include <linux/anon_inodes.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/magic.h> #include <linux/mount.h> #include <linux/pid.h> #include <linux/pidfs.h> #include <linux/pid_namespace.h> #include <linux/poll.h> #include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/pseudo_fs.h> #include <linux/seq_file.h> #include <uapi/linux/pidfd.h> #include "internal.h" #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd * @m: proc fdinfo file * @f: file referencing a pidfd * * Pid: * This function will print the pid that a given pidfd refers to in the * pid namespace of the procfs instance. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its pid. This is * similar to calling getppid() on a process whose parent is outside of * its pid namespace. * * NSpid: * If pid namespaces are supported then this function will also print * the pid of a given pidfd refers to for all descendant pid namespaces * starting from the current pid namespace of the instance, i.e. the * Pid field and the first entry in the NSpid field will be identical. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its first NSpid * entry and no others will be shown. * Note that this differs from the Pid and NSpid fields in * /proc/<pid>/status where Pid and NSpid are always shown relative to * the pid namespace of the procfs instance. The difference becomes * obvious when sending around a pidfd between pid namespaces from a * different branch of the tree, i.e. where no ancestral relation is * present between the pid namespaces: * - create two new pid namespaces ns1 and ns2 in the initial pid * namespace (also take care to create new mount namespaces in the * new pid namespace and mount procfs) * - create a process with a pidfd in ns1 * - send pidfd from ns1 to ns2 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid * have exactly one entry, which is 0 */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { struct pid *pid = pidfd_pid(f); struct pid_namespace *ns; pid_t nr = -1; if (likely(pid_has_task(pid, PIDTYPE_PID))) { ns = proc_pid_ns(file_inode(m->file)->i_sb); nr = pid_nr_ns(pid, ns); } seq_put_decimal_ll(m, "Pid:\t", nr); #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { int i; /* If nr is non-zero it means that 'pid' is valid and that * ns, i.e. the pid namespace associated with the procfs * instance, is in the pid namespace hierarchy of pid. * Start at one below the already printed level. */ for (i = ns->level + 1; i <= pid->level; i++) seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); } #endif seq_putc(m, '\n'); } #endif /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = pidfd_pid(file); bool thread = file->f_flags & PIDFD_THREAD; struct task_struct *task; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); /* * Depending on PIDFD_THREAD, inform pollers when the thread * or the whole thread-group exits. */ guard(rcu)(); task = pid_task(pid, PIDTYPE_PID); if (!task) poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP; else if (task->exit_state && (thread || thread_group_empty(task))) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; } static const struct file_operations pidfs_file_operations = { .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif }; struct pid *pidfd_pid(const struct file *file) { if (file->f_op != &pidfs_file_operations) return ERR_PTR(-EBADF); return file_inode(file)->i_private; } static struct vfsmount *pidfs_mnt __ro_after_init; #if BITS_PER_LONG == 32 /* * Provide a fallback mechanism for 32-bit systems so processes remain * reliably comparable by inode number even on those systems. */ static DEFINE_IDA(pidfd_inum_ida); static int pidfs_inum(struct pid *pid, unsigned long *ino) { int ret; ret = ida_alloc_range(&pidfd_inum_ida, RESERVED_PIDS + 1, UINT_MAX, GFP_ATOMIC); if (ret < 0) return -ENOSPC; *ino = ret; return 0; } static inline void pidfs_free_inum(unsigned long ino) { if (ino > 0) ida_free(&pidfd_inum_ida, ino); } #else static inline int pidfs_inum(struct pid *pid, unsigned long *ino) { *ino = pid->ino; return 0; } #define pidfs_free_inum(ino) ((void)(ino)) #endif /* * The vfs falls back to simple_setattr() if i_op->setattr() isn't * implemented. Let's reject it completely until we have a clean * permission concept for pidfds. */ static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EOPNOTSUPP; } static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); return 0; } static const struct inode_operations pidfs_inode_operations = { .getattr = pidfs_getattr, .setattr = pidfs_setattr, }; static void pidfs_evict_inode(struct inode *inode) { struct pid *pid = inode->i_private; clear_inode(inode); put_pid(pid); pidfs_free_inum(inode->i_ino); } static const struct super_operations pidfs_sops = { .drop_inode = generic_delete_inode, .evict_inode = pidfs_evict_inode, .statfs = simple_statfs, }; static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen) { struct inode *inode = d_inode(dentry); struct pid *pid = inode->i_private; return dynamic_dname(buffer, buflen, "pidfd:[%llu]", pid->ino); } static const struct dentry_operations pidfs_dentry_operations = { .d_delete = always_delete_dentry, .d_dname = pidfs_dname, .d_prune = stashed_dentry_prune, }; static int pidfs_init_inode(struct inode *inode, void *data) { inode->i_private = data; inode->i_flags |= S_PRIVATE; inode->i_mode |= S_IRWXU; inode->i_op = &pidfs_inode_operations; inode->i_fop = &pidfs_file_operations; /* * Inode numbering for pidfs start at RESERVED_PIDS + 1. This * avoids collisions with the root inode which is 1 for pseudo * filesystems. */ return pidfs_inum(data, &inode->i_ino); } static void pidfs_put_data(void *data) { struct pid *pid = data; put_pid(pid); } static const struct stashed_operations pidfs_stashed_ops = { .init_inode = pidfs_init_inode, .put_data = pidfs_put_data, }; static int pidfs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx; ctx = init_pseudo(fc, PID_FS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pidfs_sops; ctx->dops = &pidfs_dentry_operations; fc->s_fs_info = (void *)&pidfs_stashed_ops; return 0; } static struct file_system_type pidfs_type = { .name = "pidfs", .init_fs_context = pidfs_init_fs_context, .kill_sb = kill_anon_super, }; struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) { struct file *pidfd_file; struct path path; int ret; ret = path_from_stashed(&pid->stashed, pidfs_mnt, get_pid(pid), &path); if (ret < 0) return ERR_PTR(ret); pidfd_file = dentry_open(&path, flags, current_cred()); path_put(&path); return pidfd_file; } void __init pidfs_init(void) { pidfs_mnt = kern_mount(&pidfs_type); if (IS_ERR(pidfs_mnt)) panic("Failed to mount pidfs pseudo filesystem"); } |
| 77 77 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/isofs/util.c */ #include <linux/time.h> #include "isofs.h" /* * We have to convert from a MM/DD/YY format to the Unix ctime format. * We have to take into account leap years and all of that good stuff. * Unfortunately, the kernel does not have the information on hand to * take into account daylight savings time, but it shouldn't matter. * The time stored should be localtime (with or without DST in effect), * and the timezone offset should hold the offset required to get back * to GMT. Thus we should always be correct. */ int iso_date(u8 *p, int flag) { int year, month, day, hour, minute, second, tz; int crtime; year = p[0]; month = p[1]; day = p[2]; hour = p[3]; minute = p[4]; second = p[5]; if (flag == 0) tz = p[6]; /* High sierra has no time zone */ else tz = 0; if (year < 0) { crtime = 0; } else { crtime = mktime64(year+1900, month, day, hour, minute, second); /* sign extend */ if (tz & 0x80) tz |= (-1 << 8); /* * The timezone offset is unreliable on some disks, * so we make a sanity check. In no case is it ever * more than 13 hours from GMT, which is 52*15min. * The time is always stored in localtime with the * timezone offset being what get added to GMT to * get to localtime. Thus we need to subtract the offset * to get to true GMT, which is what we store the time * as internally. On the local system, the user may set * their timezone any way they wish, of course, so GMT * gets converted back to localtime on the receiving * system. * * NOTE: mkisofs in versions prior to mkisofs-1.10 had * the sign wrong on the timezone offset. This has now * been corrected there too, but if you are getting screwy * results this may be the explanation. If enough people * complain, a user configuration option could be added * to add the timezone offset in with the wrong sign * for 'compatibility' with older discs, but I cannot see how * it will matter that much. * * Thanks to kuhlmav@elec.canterbury.ac.nz (Volker Kuhlmann) * for pointing out the sign error. */ if (-52 <= tz && tz <= 52) crtime -= tz * 15 * 60; } return crtime; } |
| 47 8 47 59 58 2 116 14 118 8 79 36 31 15 116 14 92 92 93 94 94 92 35 39 113 19 105 105 73 55 55 35 31 24 92 91 92 14 21 4 4 14 14 14 70 70 70 11 70 11 70 12 2 12 12 12 3 158 123 51 79 79 116 116 162 161 151 118 116 116 116 65 24 70 97 34 123 151 48 48 43 21 19 19 19 1 21 17 7 11 40 6 33 16 39 7 34 19 2 2 5 4 100 14 13 7 8 61 62 14 7 4 12 3 1 2 14 3 58 57 9 2 1 7 2 1 2 1 9 2 2 57 32 6 24 4 9 32 4 15 57 2573 2466 126 73 126 89 29 73 89 88 12 77 2550 59 50 9 43 43 1132 89 1132 903 4 14 12 1960 1938 652 1340 42 41 42 42 2 40 42 42 1714 1681 49 45 49 2 2 2 49 49 666 666 666 1180 1153 70 1107 31 31 31 31 1 30 1 30 31 31 920 897 28 28 28 28 28 28 28 18 4 14 18 18 18 16 16 18 18 16 16 16 16 16 18 18 18 18 18 16 52 33 8 11 2 9 8 2 3 3 10 10 5 5 1128 217 931 15 19 24 2 15 80 80 59 24 19 6 5 19 19 21 21 21 21 24 5 5 19 62 4 1 56 1 55 53 2 60 60 60 2 1 58 58 58 5 54 8 48 48 48 59 60 43 15 3 3 3 3 3 7 1 6 13 11 9 5 4 3 2 3 3 4 3 4 1 3 3 10 5 5 14 7 1 6 30 26 18 11 18 10 19 10 18 8 11 15 11 15 11 11 15 10 16 10 16 10 11 15 19 7 7 14 3 2 6 12 4 4 23 3 33 4 30 4 4 4 2 1 1 2 1 1 4 9 9 6 3 3 3 1 3 1 3 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the diskquota system for the LINUX operating system. QUOTA * is implemented using the BSD system call interface as the means of * communication with the user level. This file contains the generic routines * called by the different filesystems on allocation of an inode or block. * These routines take care of the administration needed to have a consistent * diskquota tracking system. The ideas of both user and group quotas are based * on the Melbourne quota system as used on BSD derived systems. The internal * implementation is based on one of the several variants of the LINUX * inode-subsystem with added complexity of the diskquota system. * * Author: Marco van Wieringen <mvw@planets.elm.net> * * Fixes: Dmitry Gorodchanin <pgmdsg@ibi.com>, 11 Feb 96 * * Revised list management to avoid races * -- Bill Hawes, <whawes@star.net>, 9/98 * * Fixed races in dquot_transfer(), dqget() and dquot_alloc_...(). * As the consequence the locking was moved from dquot_decr_...(), * dquot_incr_...() to calling functions. * invalidate_dquots() now writes modified dquots. * Serialized quota_off() and quota_on() for mount point. * Fixed a few bugs in grow_dquots(). * Fixed deadlock in write_dquot() - we no longer account quotas on * quota files * remove_dquot_ref() moved to inode.c - it now traverses through inodes * add_dquot_ref() restarts after blocking * Added check for bogus uid and fixed check for group in quotactl. * Jan Kara, <jack@suse.cz>, sponsored by SuSE CR, 10-11/99 * * Used struct list_head instead of own list struct * Invalidation of referenced dquots is no longer possible * Improved free_dquots list management * Quota and i_blocks are now updated in one place to avoid races * Warnings are now delayed so we won't block in critical section * Write updated not to require dquot lock * Jan Kara, <jack@suse.cz>, 9/2000 * * Added dynamic quota structure allocation * Jan Kara <jack@suse.cz> 12/2000 * * Rewritten quota interface. Implemented new quota format and * formats registering. * Jan Kara, <jack@suse.cz>, 2001,2002 * * New SMP locking. * Jan Kara, <jack@suse.cz>, 10/2002 * * Added journalled quota support, fix lock inversion problems * Jan Kara, <jack@suse.cz>, 2003,2004 * * (C) Copyright 1994 - 1997 Marco van Wieringen */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/mm.h> #include <linux/time.h> #include <linux/types.h> #include <linux/string.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/tty.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/init.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/kmod.h> #include <linux/namei.h> #include <linux/capability.h> #include <linux/quotaops.h> #include <linux/blkdev.h> #include <linux/sched/mm.h> #include "../internal.h" /* ugh */ #include <linux/uaccess.h> /* * There are five quota SMP locks: * * dq_list_lock protects all lists with quotas and quota formats. * * dquot->dq_dqb_lock protects data from dq_dqb * * inode->i_lock protects inode->i_blocks, i_bytes and also guards * consistency of dquot->dq_dqb with inode->i_blocks, i_bytes so that * dquot_transfer() can stabilize amount it transfers * * dq_data_lock protects mem_dqinfo structures and modifications of dquot * pointers in the inode * * dq_state_lock protects modifications of quota state (on quotaon and * quotaoff) and readers who care about latest values take it as well. * * The spinlock ordering is hence: * dq_data_lock > dq_list_lock > i_lock > dquot->dq_dqb_lock, * dq_list_lock > dq_state_lock * * Note that some things (eg. sb pointer, type, id) doesn't change during * the life of the dquot structure and so needn't to be protected by a lock * * Operation accessing dquots via inode pointers are protected by dquot_srcu. * Operation of reading pointer needs srcu_read_lock(&dquot_srcu), and * synchronize_srcu(&dquot_srcu) is called after clearing pointers from * inode and before dropping dquot references to avoid use of dquots after * they are freed. dq_data_lock is used to serialize the pointer setting and * clearing operations. * Special care needs to be taken about S_NOQUOTA inode flag (marking that * inode is a quota file). Functions adding pointers from inode to dquots have * to check this flag under dq_data_lock and then (if S_NOQUOTA is not set) they * have to do all pointer modifications before dropping dq_data_lock. This makes * sure they cannot race with quotaon which first sets S_NOQUOTA flag and * then drops all pointers to dquots from an inode. * * Each dquot has its dq_lock mutex. Dquot is locked when it is being read to * memory (or space for it is being allocated) on the first dqget(), when it is * being written out, and when it is being released on the last dqput(). The * allocation and release operations are serialized by the dq_lock and by * checking the use count in dquot_release(). * * Lock ordering (including related VFS locks) is the following: * s_umount > i_mutex > journal_lock > dquot->dq_lock > dqio_sem */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_list_lock); static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_state_lock); __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_data_lock); EXPORT_SYMBOL(dq_data_lock); DEFINE_STATIC_SRCU(dquot_srcu); static DECLARE_WAIT_QUEUE_HEAD(dquot_ref_wq); void __quota_error(struct super_block *sb, const char *func, const char *fmt, ...) { if (printk_ratelimit()) { va_list args; struct va_format vaf; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_ERR "Quota error (device %s): %s: %pV\n", sb->s_id, func, &vaf); va_end(args); } } EXPORT_SYMBOL(__quota_error); #if defined(CONFIG_QUOTA_DEBUG) || defined(CONFIG_PRINT_QUOTA_WARNING) static char *quotatypes[] = INITQFNAMES; #endif static struct quota_format_type *quota_formats; /* List of registered formats */ static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES; /* SLAB cache for dquot structures */ static struct kmem_cache *dquot_cachep; int register_quota_format(struct quota_format_type *fmt) { spin_lock(&dq_list_lock); fmt->qf_next = quota_formats; quota_formats = fmt; spin_unlock(&dq_list_lock); return 0; } EXPORT_SYMBOL(register_quota_format); void unregister_quota_format(struct quota_format_type *fmt) { struct quota_format_type **actqf; spin_lock(&dq_list_lock); for (actqf = "a_formats; *actqf && *actqf != fmt; actqf = &(*actqf)->qf_next) ; if (*actqf) *actqf = (*actqf)->qf_next; spin_unlock(&dq_list_lock); } EXPORT_SYMBOL(unregister_quota_format); static struct quota_format_type *find_quota_format(int id) { struct quota_format_type *actqf; spin_lock(&dq_list_lock); for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id; actqf = actqf->qf_next) ; if (!actqf || !try_module_get(actqf->qf_owner)) { int qm; spin_unlock(&dq_list_lock); for (qm = 0; module_names[qm].qm_fmt_id && module_names[qm].qm_fmt_id != id; qm++) ; if (!module_names[qm].qm_fmt_id || request_module(module_names[qm].qm_mod_name)) return NULL; spin_lock(&dq_list_lock); for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id; actqf = actqf->qf_next) ; if (actqf && !try_module_get(actqf->qf_owner)) actqf = NULL; } spin_unlock(&dq_list_lock); return actqf; } static void put_quota_format(struct quota_format_type *fmt) { module_put(fmt->qf_owner); } /* * Dquot List Management: * The quota code uses five lists for dquot management: the inuse_list, * releasing_dquots, free_dquots, dqi_dirty_list, and dquot_hash[] array. * A single dquot structure may be on some of those lists, depending on * its current state. * * All dquots are placed to the end of inuse_list when first created, and this * list is used for invalidate operation, which must look at every dquot. * * When the last reference of a dquot is dropped, the dquot is added to * releasing_dquots. We'll then queue work item which will call * synchronize_srcu() and after that perform the final cleanup of all the * dquots on the list. Each cleaned up dquot is moved to free_dquots list. * Both releasing_dquots and free_dquots use the dq_free list_head in the dquot * struct. * * Unused and cleaned up dquots are in the free_dquots list and this list is * searched whenever we need an available dquot. Dquots are removed from the * list as soon as they are used again and dqstats.free_dquots gives the number * of dquots on the list. When dquot is invalidated it's completely released * from memory. * * Dirty dquots are added to the dqi_dirty_list of quota_info when mark * dirtied, and this list is searched when writing dirty dquots back to * quota file. Note that some filesystems do dirty dquot tracking on their * own (e.g. in a journal) and thus don't use dqi_dirty_list. * * Dquots with a specific identity (device, type and id) are placed on * one of the dquot_hash[] hash chains. The provides an efficient search * mechanism to locate a specific dquot. */ static LIST_HEAD(inuse_list); static LIST_HEAD(free_dquots); static LIST_HEAD(releasing_dquots); static unsigned int dq_hash_bits, dq_hash_mask; static struct hlist_head *dquot_hash; struct dqstats dqstats; EXPORT_SYMBOL(dqstats); static qsize_t inode_get_rsv_space(struct inode *inode); static qsize_t __inode_get_rsv_space(struct inode *inode); static int __dquot_initialize(struct inode *inode, int type); static void quota_release_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(quota_release_work, quota_release_workfn); static inline unsigned int hashfn(const struct super_block *sb, struct kqid qid) { unsigned int id = from_kqid(&init_user_ns, qid); int type = qid.type; unsigned long tmp; tmp = (((unsigned long)sb>>L1_CACHE_SHIFT) ^ id) * (MAXQUOTAS - type); return (tmp + (tmp >> dq_hash_bits)) & dq_hash_mask; } /* * Following list functions expect dq_list_lock to be held */ static inline void insert_dquot_hash(struct dquot *dquot) { struct hlist_head *head; head = dquot_hash + hashfn(dquot->dq_sb, dquot->dq_id); hlist_add_head(&dquot->dq_hash, head); } static inline void remove_dquot_hash(struct dquot *dquot) { hlist_del_init(&dquot->dq_hash); } static struct dquot *find_dquot(unsigned int hashent, struct super_block *sb, struct kqid qid) { struct dquot *dquot; hlist_for_each_entry(dquot, dquot_hash+hashent, dq_hash) if (dquot->dq_sb == sb && qid_eq(dquot->dq_id, qid)) return dquot; return NULL; } /* Add a dquot to the tail of the free list */ static inline void put_dquot_last(struct dquot *dquot) { list_add_tail(&dquot->dq_free, &free_dquots); dqstats_inc(DQST_FREE_DQUOTS); } static inline void put_releasing_dquots(struct dquot *dquot) { list_add_tail(&dquot->dq_free, &releasing_dquots); set_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void remove_free_dquot(struct dquot *dquot) { if (list_empty(&dquot->dq_free)) return; list_del_init(&dquot->dq_free); if (!test_bit(DQ_RELEASING_B, &dquot->dq_flags)) dqstats_dec(DQST_FREE_DQUOTS); else clear_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void put_inuse(struct dquot *dquot) { /* We add to the back of inuse list so we don't have to restart * when traversing this list and we block */ list_add_tail(&dquot->dq_inuse, &inuse_list); dqstats_inc(DQST_ALLOC_DQUOTS); } static inline void remove_inuse(struct dquot *dquot) { dqstats_dec(DQST_ALLOC_DQUOTS); list_del(&dquot->dq_inuse); } /* * End of list functions needing dq_list_lock */ static void wait_on_dquot(struct dquot *dquot) { mutex_lock(&dquot->dq_lock); mutex_unlock(&dquot->dq_lock); } static inline int dquot_active(struct dquot *dquot) { return test_bit(DQ_ACTIVE_B, &dquot->dq_flags); } static inline int dquot_dirty(struct dquot *dquot) { return test_bit(DQ_MOD_B, &dquot->dq_flags); } static inline int mark_dquot_dirty(struct dquot *dquot) { return dquot->dq_sb->dq_op->mark_dirty(dquot); } /* Mark dquot dirty in atomic manner, and return it's old dirty flag state */ int dquot_mark_dquot_dirty(struct dquot *dquot) { int ret = 1; if (!dquot_active(dquot)) return 0; if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags); /* If quota is dirty already, we don't have to acquire dq_list_lock */ if (dquot_dirty(dquot)) return 1; spin_lock(&dq_list_lock); if (!test_and_set_bit(DQ_MOD_B, &dquot->dq_flags)) { list_add(&dquot->dq_dirty, &sb_dqopt(dquot->dq_sb)-> info[dquot->dq_id.type].dqi_dirty_list); ret = 0; } spin_unlock(&dq_list_lock); return ret; } EXPORT_SYMBOL(dquot_mark_dquot_dirty); /* Dirtify all the dquots - this can block when journalling */ static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots) { int ret, err, cnt; struct dquot *dquot; ret = err = 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (dquot) /* Even in case of error we have to continue */ ret = mark_dquot_dirty(dquot); if (!err && ret < 0) err = ret; } return err; } static inline void dqput_all(struct dquot **dquot) { unsigned int cnt; for (cnt = 0; cnt < MAXQUOTAS; cnt++) dqput(dquot[cnt]); } static inline int clear_dquot_dirty(struct dquot *dquot) { if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) return test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags); spin_lock(&dq_list_lock); if (!test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags)) { spin_unlock(&dq_list_lock); return 0; } list_del_init(&dquot->dq_dirty); spin_unlock(&dq_list_lock); return 1; } void mark_info_dirty(struct super_block *sb, int type) { spin_lock(&dq_data_lock); sb_dqopt(sb)->info[type].dqi_flags |= DQF_INFO_DIRTY; spin_unlock(&dq_data_lock); } EXPORT_SYMBOL(mark_info_dirty); /* * Read dquot from disk and alloc space for it */ int dquot_acquire(struct dquot *dquot) { int ret = 0, ret2 = 0; unsigned int memalloc; struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); mutex_lock(&dquot->dq_lock); memalloc = memalloc_nofs_save(); if (!test_bit(DQ_READ_B, &dquot->dq_flags)) { ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot); if (ret < 0) goto out_iolock; } /* Make sure flags update is visible after dquot has been filled */ smp_mb__before_atomic(); set_bit(DQ_READ_B, &dquot->dq_flags); /* Instantiate dquot if needed */ if (!dquot_active(dquot) && !dquot->dq_off) { ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); /* Write the info if needed */ if (info_dirty(&dqopt->info[dquot->dq_id.type])) { ret2 = dqopt->ops[dquot->dq_id.type]->write_file_info( dquot->dq_sb, dquot->dq_id.type); } if (ret < 0) goto out_iolock; if (ret2 < 0) { ret = ret2; goto out_iolock; } } /* * Make sure flags update is visible after on-disk struct has been * allocated. Paired with smp_rmb() in dqget(). */ smp_mb__before_atomic(); set_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_iolock: memalloc_nofs_restore(memalloc); mutex_unlock(&dquot->dq_lock); return ret; } EXPORT_SYMBOL(dquot_acquire); /* * Write dquot to disk */ int dquot_commit(struct dquot *dquot) { int ret = 0; unsigned int memalloc; struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); mutex_lock(&dquot->dq_lock); memalloc = memalloc_nofs_save(); if (!clear_dquot_dirty(dquot)) goto out_lock; /* Inactive dquot can be only if there was error during read/init * => we have better not writing it */ if (dquot_active(dquot)) ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); else ret = -EIO; out_lock: memalloc_nofs_restore(memalloc); mutex_unlock(&dquot->dq_lock); return ret; } EXPORT_SYMBOL(dquot_commit); /* * Release dquot */ int dquot_release(struct dquot *dquot) { int ret = 0, ret2 = 0; unsigned int memalloc; struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); mutex_lock(&dquot->dq_lock); memalloc = memalloc_nofs_save(); /* Check whether we are not racing with some other dqget() */ if (dquot_is_busy(dquot)) goto out_dqlock; if (dqopt->ops[dquot->dq_id.type]->release_dqblk) { ret = dqopt->ops[dquot->dq_id.type]->release_dqblk(dquot); /* Write the info */ if (info_dirty(&dqopt->info[dquot->dq_id.type])) { ret2 = dqopt->ops[dquot->dq_id.type]->write_file_info( dquot->dq_sb, dquot->dq_id.type); } if (ret >= 0) ret = ret2; } clear_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_dqlock: memalloc_nofs_restore(memalloc); mutex_unlock(&dquot->dq_lock); return ret; } EXPORT_SYMBOL(dquot_release); void dquot_destroy(struct dquot *dquot) { kmem_cache_free(dquot_cachep, dquot); } EXPORT_SYMBOL(dquot_destroy); static inline void do_destroy_dquot(struct dquot *dquot) { dquot->dq_sb->dq_op->destroy_dquot(dquot); } /* Invalidate all dquots on the list. Note that this function is called after * quota is disabled and pointers from inodes removed so there cannot be new * quota users. There can still be some users of quotas due to inodes being * just deleted or pruned by prune_icache() (those are not attached to any * list) or parallel quotactl call. We have to wait for such users. */ static void invalidate_dquots(struct super_block *sb, int type) { struct dquot *dquot, *tmp; restart: flush_delayed_work("a_release_work); spin_lock(&dq_list_lock); list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) { if (dquot->dq_sb != sb) continue; if (dquot->dq_id.type != type) continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* * Once dqput() wakes us up, we know it's time to free * the dquot. * IMPORTANT: we rely on the fact that there is always * at most one process waiting for dquot to free. * Otherwise dq_count would be > 1 and we would never * wake up. */ wait_event(dquot_ref_wq, atomic_read(&dquot->dq_count) == 1); dqput(dquot); /* At this moment dquot() need not exist (it could be * reclaimed by prune_dqcache(). Hence we must * restart. */ goto restart; } /* * The last user already dropped its reference but dquot didn't * get fully cleaned up yet. Restart the scan which flushes the * work cleaning up released dquots. */ if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { spin_unlock(&dq_list_lock); goto restart; } /* * Quota now has no users and it has been written on last * dqput() */ remove_dquot_hash(dquot); remove_free_dquot(dquot); remove_inuse(dquot); do_destroy_dquot(dquot); } spin_unlock(&dq_list_lock); } /* Call callback for every active dquot on given filesystem */ int dquot_scan_active(struct super_block *sb, int (*fn)(struct dquot *dquot, unsigned long priv), unsigned long priv) { struct dquot *dquot, *old_dquot = NULL; int ret = 0; WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount)); spin_lock(&dq_list_lock); list_for_each_entry(dquot, &inuse_list, dq_inuse) { if (!dquot_active(dquot)) continue; if (dquot->dq_sb != sb) continue; /* Now we have active dquot so we can just increase use count */ atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); dqput(old_dquot); old_dquot = dquot; /* * ->release_dquot() can be racing with us. Our reference * protects us from new calls to it so just wait for any * outstanding call and recheck the DQ_ACTIVE_B after that. */ wait_on_dquot(dquot); if (dquot_active(dquot)) { ret = fn(dquot, priv); if (ret < 0) goto out; } spin_lock(&dq_list_lock); /* We are safe to continue now because our dquot could not * be moved out of the inuse list while we hold the reference */ } spin_unlock(&dq_list_lock); out: dqput(old_dquot); return ret; } EXPORT_SYMBOL(dquot_scan_active); static inline int dquot_write_dquot(struct dquot *dquot) { int ret = dquot->dq_sb->dq_op->write_dquot(dquot); if (ret < 0) { quota_error(dquot->dq_sb, "Can't write quota structure " "(error %d). Quota may get out of sync!", ret); /* Clear dirty bit anyway to avoid infinite loop. */ clear_dquot_dirty(dquot); } return ret; } /* Write all dquot structures to quota files */ int dquot_writeback_dquots(struct super_block *sb, int type) { struct list_head dirty; struct dquot *dquot; struct quota_info *dqopt = sb_dqopt(sb); int cnt; int err, ret = 0; WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount)); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; spin_lock(&dq_list_lock); /* Move list away to avoid livelock. */ list_replace_init(&dqopt->info[cnt].dqi_dirty_list, &dirty); while (!list_empty(&dirty)) { dquot = list_first_entry(&dirty, struct dquot, dq_dirty); WARN_ON(!dquot_active(dquot)); /* If the dquot is releasing we should not touch it */ if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { spin_unlock(&dq_list_lock); flush_delayed_work("a_release_work); spin_lock(&dq_list_lock); continue; } /* Now we have active dquot from which someone is * holding reference so we can safely just increase * use count */ dqgrab(dquot); spin_unlock(&dq_list_lock); err = dquot_write_dquot(dquot); if (err && !ret) ret = err; dqput(dquot); spin_lock(&dq_list_lock); } spin_unlock(&dq_list_lock); } for (cnt = 0; cnt < MAXQUOTAS; cnt++) if ((cnt == type || type == -1) && sb_has_quota_active(sb, cnt) && info_dirty(&dqopt->info[cnt])) sb->dq_op->write_info(sb, cnt); dqstats_inc(DQST_SYNCS); return ret; } EXPORT_SYMBOL(dquot_writeback_dquots); /* Write all dquot structures to disk and make them visible from userspace */ int dquot_quota_sync(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); int cnt; int ret; ret = dquot_writeback_dquots(sb, type); if (ret) return ret; if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) return 0; /* This is not very clever (and fast) but currently I don't know about * any other simple way of getting quota data to disk and we must get * them there for userspace to be visible... */ if (sb->s_op->sync_fs) { ret = sb->s_op->sync_fs(sb, 1); if (ret) return ret; } ret = sync_blockdev(sb->s_bdev); if (ret) return ret; /* * Now when everything is written we can discard the pagecache so * that userspace sees the changes. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; inode_lock(dqopt->files[cnt]); truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); inode_unlock(dqopt->files[cnt]); } return 0; } EXPORT_SYMBOL(dquot_quota_sync); static unsigned long dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct dquot *dquot; unsigned long freed = 0; spin_lock(&dq_list_lock); while (!list_empty(&free_dquots) && sc->nr_to_scan) { dquot = list_first_entry(&free_dquots, struct dquot, dq_free); remove_dquot_hash(dquot); remove_free_dquot(dquot); remove_inuse(dquot); do_destroy_dquot(dquot); sc->nr_to_scan--; freed++; } spin_unlock(&dq_list_lock); return freed; } static unsigned long dqcache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { return vfs_pressure_ratio( percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS])); } /* * Safely release dquot and put reference to dquot. */ static void quota_release_workfn(struct work_struct *work) { struct dquot *dquot; struct list_head rls_head; spin_lock(&dq_list_lock); /* Exchange the list head to avoid livelock. */ list_replace_init(&releasing_dquots, &rls_head); spin_unlock(&dq_list_lock); synchronize_srcu(&dquot_srcu); restart: spin_lock(&dq_list_lock); while (!list_empty(&rls_head)) { dquot = list_first_entry(&rls_head, struct dquot, dq_free); WARN_ON_ONCE(atomic_read(&dquot->dq_count)); /* * Note that DQ_RELEASING_B protects us from racing with * invalidate_dquots() calls so we are safe to work with the * dquot even after we drop dq_list_lock. */ if (dquot_dirty(dquot)) { spin_unlock(&dq_list_lock); /* Commit dquot before releasing */ dquot_write_dquot(dquot); goto restart; } if (dquot_active(dquot)) { spin_unlock(&dq_list_lock); dquot->dq_sb->dq_op->release_dquot(dquot); goto restart; } /* Dquot is inactive and clean, now move it to free list */ remove_free_dquot(dquot); put_dquot_last(dquot); } spin_unlock(&dq_list_lock); } /* * Put reference to dquot */ void dqput(struct dquot *dquot) { if (!dquot) return; #ifdef CONFIG_QUOTA_DEBUG if (!atomic_read(&dquot->dq_count)) { quota_error(dquot->dq_sb, "trying to free free dquot of %s %d", quotatypes[dquot->dq_id.type], from_kqid(&init_user_ns, dquot->dq_id)); BUG(); } #endif dqstats_inc(DQST_DROPS); spin_lock(&dq_list_lock); if (atomic_read(&dquot->dq_count) > 1) { /* We have more than one user... nothing to do */ atomic_dec(&dquot->dq_count); /* Releasing dquot during quotaoff phase? */ if (!sb_has_quota_active(dquot->dq_sb, dquot->dq_id.type) && atomic_read(&dquot->dq_count) == 1) wake_up(&dquot_ref_wq); spin_unlock(&dq_list_lock); return; } /* Need to release dquot? */ WARN_ON_ONCE(!list_empty(&dquot->dq_free)); put_releasing_dquots(dquot); atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); queue_delayed_work(system_unbound_wq, "a_release_work, 1); } EXPORT_SYMBOL(dqput); struct dquot *dquot_alloc(struct super_block *sb, int type) { return kmem_cache_zalloc(dquot_cachep, GFP_NOFS); } EXPORT_SYMBOL(dquot_alloc); static struct dquot *get_empty_dquot(struct super_block *sb, int type) { struct dquot *dquot; dquot = sb->dq_op->alloc_dquot(sb, type); if(!dquot) return NULL; mutex_init(&dquot->dq_lock); INIT_LIST_HEAD(&dquot->dq_free); INIT_LIST_HEAD(&dquot->dq_inuse); INIT_HLIST_NODE(&dquot->dq_hash); INIT_LIST_HEAD(&dquot->dq_dirty); dquot->dq_sb = sb; dquot->dq_id = make_kqid_invalid(type); atomic_set(&dquot->dq_count, 1); spin_lock_init(&dquot->dq_dqb_lock); return dquot; } /* * Get reference to dquot * * Locking is slightly tricky here. We are guarded from parallel quotaoff() * destroying our dquot by: * a) checking for quota flags under dq_list_lock and * b) getting a reference to dquot before we release dq_list_lock */ struct dquot *dqget(struct super_block *sb, struct kqid qid) { unsigned int hashent = hashfn(sb, qid); struct dquot *dquot, *empty = NULL; if (!qid_has_mapping(sb->s_user_ns, qid)) return ERR_PTR(-EINVAL); if (!sb_has_quota_active(sb, qid.type)) return ERR_PTR(-ESRCH); we_slept: spin_lock(&dq_list_lock); spin_lock(&dq_state_lock); if (!sb_has_quota_active(sb, qid.type)) { spin_unlock(&dq_state_lock); spin_unlock(&dq_list_lock); dquot = ERR_PTR(-ESRCH); goto out; } spin_unlock(&dq_state_lock); dquot = find_dquot(hashent, sb, qid); if (!dquot) { if (!empty) { spin_unlock(&dq_list_lock); empty = get_empty_dquot(sb, qid.type); if (!empty) schedule(); /* Try to wait for a moment... */ goto we_slept; } dquot = empty; empty = NULL; dquot->dq_id = qid; /* all dquots go on the inuse_list */ put_inuse(dquot); /* hash it first so it can be found */ insert_dquot_hash(dquot); spin_unlock(&dq_list_lock); dqstats_inc(DQST_LOOKUPS); } else { if (!atomic_read(&dquot->dq_count)) remove_free_dquot(dquot); atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); dqstats_inc(DQST_CACHE_HITS); dqstats_inc(DQST_LOOKUPS); } /* Wait for dq_lock - after this we know that either dquot_release() is * already finished or it will be canceled due to dq_count > 0 test */ wait_on_dquot(dquot); /* Read the dquot / allocate space in quota file */ if (!dquot_active(dquot)) { int err; err = sb->dq_op->acquire_dquot(dquot); if (err < 0) { dqput(dquot); dquot = ERR_PTR(err); goto out; } } /* * Make sure following reads see filled structure - paired with * smp_mb__before_atomic() in dquot_acquire(). */ smp_rmb(); /* Has somebody invalidated entry under us? */ WARN_ON_ONCE(hlist_unhashed(&dquot->dq_hash)); out: if (empty) do_destroy_dquot(empty); return dquot; } EXPORT_SYMBOL(dqget); static inline struct dquot __rcu **i_dquot(struct inode *inode) { return inode->i_sb->s_op->get_dquots(inode); } static int dqinit_needed(struct inode *inode, int type) { struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) return 0; dquots = i_dquot(inode); if (type != -1) return !dquots[type]; for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (!dquots[cnt]) return 1; return 0; } /* This routine is guarded by s_umount semaphore */ static int add_dquot_ref(struct super_block *sb, int type) { struct inode *inode, *old_inode = NULL; #ifdef CONFIG_QUOTA_DEBUG int reserved = 0; #endif int err = 0; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || !atomic_read(&inode->i_writecount) || !dqinit_needed(inode, type)) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif iput(old_inode); err = __dquot_initialize(inode, type); if (err) { iput(inode); goto out; } /* * We hold a reference to 'inode' so it couldn't have been * removed from s_inodes list while we dropped the * s_inode_list_lock. We cannot iput the inode now as we can be * holding the last reference and we cannot iput it under * s_inode_list_lock. So we keep the reference and iput it * later. */ old_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(old_inode); out: #ifdef CONFIG_QUOTA_DEBUG if (reserved) { quota_error(sb, "Writes happened before quota was turned on " "thus quota information is probably inconsistent. " "Please run quotacheck(8)"); } #endif return err; } static void remove_dquot_ref(struct super_block *sb, int type) { struct inode *inode; #ifdef CONFIG_QUOTA_DEBUG int reserved = 0; #endif spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { /* * We have to scan also I_NEW inodes because they can already * have quota pointer initialized. Luckily, we need to touch * only quota pointers and these have separate locking * (dq_data_lock). */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { struct dquot __rcu **dquots = i_dquot(inode); struct dquot *dquot = srcu_dereference_check( dquots[type], &dquot_srcu, lockdep_is_held(&dq_data_lock)); #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif rcu_assign_pointer(dquots[type], NULL); if (dquot) dqput(dquot); } spin_unlock(&dq_data_lock); } spin_unlock(&sb->s_inode_list_lock); #ifdef CONFIG_QUOTA_DEBUG if (reserved) { printk(KERN_WARNING "VFS (%s): Writes happened after quota" " was disabled thus quota information is probably " "inconsistent. Please run quotacheck(8).\n", sb->s_id); } #endif } /* Gather all references from inodes and drop them */ static void drop_dquot_ref(struct super_block *sb, int type) { if (sb->dq_op) remove_dquot_ref(sb, type); } static inline void dquot_free_reserved_space(struct dquot *dquot, qsize_t number) { if (dquot->dq_dqb.dqb_rsvspace >= number) dquot->dq_dqb.dqb_rsvspace -= number; else { WARN_ON_ONCE(1); dquot->dq_dqb.dqb_rsvspace = 0; } if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <= dquot->dq_dqb.dqb_bsoftlimit) dquot->dq_dqb.dqb_btime = (time64_t) 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } static void dquot_decr_inodes(struct dquot *dquot, qsize_t number) { if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE || dquot->dq_dqb.dqb_curinodes >= number) dquot->dq_dqb.dqb_curinodes -= number; else dquot->dq_dqb.dqb_curinodes = 0; if (dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit) dquot->dq_dqb.dqb_itime = (time64_t) 0; clear_bit(DQ_INODES_B, &dquot->dq_flags); } static void dquot_decr_space(struct dquot *dquot, qsize_t number) { if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE || dquot->dq_dqb.dqb_curspace >= number) dquot->dq_dqb.dqb_curspace -= number; else dquot->dq_dqb.dqb_curspace = 0; if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <= dquot->dq_dqb.dqb_bsoftlimit) dquot->dq_dqb.dqb_btime = (time64_t) 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } struct dquot_warn { struct super_block *w_sb; struct kqid w_dq_id; short w_type; }; static int warning_issued(struct dquot *dquot, const int warntype) { int flag = (warntype == QUOTA_NL_BHARDWARN || warntype == QUOTA_NL_BSOFTLONGWARN) ? DQ_BLKS_B : ((warntype == QUOTA_NL_IHARDWARN || warntype == QUOTA_NL_ISOFTLONGWARN) ? DQ_INODES_B : 0); if (!flag) return 0; return test_and_set_bit(flag, &dquot->dq_flags); } #ifdef CONFIG_PRINT_QUOTA_WARNING static int flag_print_warnings = 1; static int need_print_warning(struct dquot_warn *warn) { if (!flag_print_warnings) return 0; switch (warn->w_dq_id.type) { case USRQUOTA: return uid_eq(current_fsuid(), warn->w_dq_id.uid); case GRPQUOTA: return in_group_p(warn->w_dq_id.gid); case PRJQUOTA: return 1; } return 0; } /* Print warning to user which exceeded quota */ static void print_warning(struct dquot_warn *warn) { char *msg = NULL; struct tty_struct *tty; int warntype = warn->w_type; if (warntype == QUOTA_NL_IHARDBELOW || warntype == QUOTA_NL_ISOFTBELOW || warntype == QUOTA_NL_BHARDBELOW || warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(warn)) return; tty = get_current_tty(); if (!tty) return; tty_write_message(tty, warn->w_sb->s_id); if (warntype == QUOTA_NL_ISOFTWARN || warntype == QUOTA_NL_BSOFTWARN) tty_write_message(tty, ": warning, "); else tty_write_message(tty, ": write failed, "); tty_write_message(tty, quotatypes[warn->w_dq_id.type]); switch (warntype) { case QUOTA_NL_IHARDWARN: msg = " file limit reached.\r\n"; break; case QUOTA_NL_ISOFTLONGWARN: msg = " file quota exceeded too long.\r\n"; break; case QUOTA_NL_ISOFTWARN: msg = " file quota exceeded.\r\n"; break; case QUOTA_NL_BHARDWARN: msg = " block limit reached.\r\n"; break; case QUOTA_NL_BSOFTLONGWARN: msg = " block quota exceeded too long.\r\n"; break; case QUOTA_NL_BSOFTWARN: msg = " block quota exceeded.\r\n"; break; } tty_write_message(tty, msg); tty_kref_put(tty); } #endif static void prepare_warning(struct dquot_warn *warn, struct dquot *dquot, int warntype) { if (warning_issued(dquot, warntype)) return; warn->w_type = warntype; warn->w_sb = dquot->dq_sb; warn->w_dq_id = dquot->dq_id; } /* * Write warnings to the console and send warning messages over netlink. * * Note that this function can call into tty and networking code. */ static void flush_warnings(struct dquot_warn *warn) { int i; for (i = 0; i < MAXQUOTAS; i++) { if (warn[i].w_type == QUOTA_NL_NOWARN) continue; #ifdef CONFIG_PRINT_QUOTA_WARNING print_warning(&warn[i]); #endif quota_send_warning(warn[i].w_dq_id, warn[i].w_sb->s_dev, warn[i].w_type); } } static int ignore_hardlimit(struct dquot *dquot) { struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; return capable(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || !(info->dqi_flags & DQF_ROOT_SQUASH)); } static int dquot_add_inodes(struct dquot *dquot, qsize_t inodes, struct dquot_warn *warn) { qsize_t newinodes; int ret = 0; spin_lock(&dquot->dq_dqb_lock); newinodes = dquot->dq_dqb.dqb_curinodes + inodes; if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_id.type) || test_bit(DQ_FAKE_B, &dquot->dq_flags)) goto add; if (dquot->dq_dqb.dqb_ihardlimit && newinodes > dquot->dq_dqb.dqb_ihardlimit && !ignore_hardlimit(dquot)) { prepare_warning(warn, dquot, QUOTA_NL_IHARDWARN); ret = -EDQUOT; goto out; } if (dquot->dq_dqb.dqb_isoftlimit && newinodes > dquot->dq_dqb.dqb_isoftlimit && dquot->dq_dqb.dqb_itime && ktime_get_real_seconds() >= dquot->dq_dqb.dqb_itime && !ignore_hardlimit(dquot)) { prepare_warning(warn, dquot, QUOTA_NL_ISOFTLONGWARN); ret = -EDQUOT; goto out; } if (dquot->dq_dqb.dqb_isoftlimit && newinodes > dquot->dq_dqb.dqb_isoftlimit && dquot->dq_dqb.dqb_itime == 0) { prepare_warning(warn, dquot, QUOTA_NL_ISOFTWARN); dquot->dq_dqb.dqb_itime = ktime_get_real_seconds() + sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type].dqi_igrace; } add: dquot->dq_dqb.dqb_curinodes = newinodes; out: spin_unlock(&dquot->dq_dqb_lock); return ret; } static int dquot_add_space(struct dquot *dquot, qsize_t space, qsize_t rsv_space, unsigned int flags, struct dquot_warn *warn) { qsize_t tspace; struct super_block *sb = dquot->dq_sb; int ret = 0; spin_lock(&dquot->dq_dqb_lock); if (!sb_has_quota_limits_enabled(sb, dquot->dq_id.type) || test_bit(DQ_FAKE_B, &dquot->dq_flags)) goto finish; tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace + space + rsv_space; if (dquot->dq_dqb.dqb_bhardlimit && tspace > dquot->dq_dqb.dqb_bhardlimit && !ignore_hardlimit(dquot)) { if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN); ret = -EDQUOT; goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && tspace > dquot->dq_dqb.dqb_bsoftlimit && dquot->dq_dqb.dqb_btime && ktime_get_real_seconds() >= dquot->dq_dqb.dqb_btime && !ignore_hardlimit(dquot)) { if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN); ret = -EDQUOT; goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && tspace > dquot->dq_dqb.dqb_bsoftlimit && dquot->dq_dqb.dqb_btime == 0) { if (flags & DQUOT_SPACE_WARN) { prepare_warning(warn, dquot, QUOTA_NL_BSOFTWARN); dquot->dq_dqb.dqb_btime = ktime_get_real_seconds() + sb_dqopt(sb)->info[dquot->dq_id.type].dqi_bgrace; } else { /* * We don't allow preallocation to exceed softlimit so exceeding will * be always printed */ ret = -EDQUOT; goto finish; } } finish: /* * We have to be careful and go through warning generation & grace time * setting even if DQUOT_SPACE_NOFAIL is set. That's why we check it * only here... */ if (flags & DQUOT_SPACE_NOFAIL) ret = 0; if (!ret) { dquot->dq_dqb.dqb_rsvspace += rsv_space; dquot->dq_dqb.dqb_curspace += space; } spin_unlock(&dquot->dq_dqb_lock); return ret; } static int info_idq_free(struct dquot *dquot, qsize_t inodes) { qsize_t newinodes; if (test_bit(DQ_FAKE_B, &dquot->dq_flags) || dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit || !sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_id.type)) return QUOTA_NL_NOWARN; newinodes = dquot->dq_dqb.dqb_curinodes - inodes; if (newinodes <= dquot->dq_dqb.dqb_isoftlimit) return QUOTA_NL_ISOFTBELOW; if (dquot->dq_dqb.dqb_curinodes >= dquot->dq_dqb.dqb_ihardlimit && newinodes < dquot->dq_dqb.dqb_ihardlimit) return QUOTA_NL_IHARDBELOW; return QUOTA_NL_NOWARN; } static int info_bdq_free(struct dquot *dquot, qsize_t space) { qsize_t tspace; tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace; if (test_bit(DQ_FAKE_B, &dquot->dq_flags) || tspace <= dquot->dq_dqb.dqb_bsoftlimit) return QUOTA_NL_NOWARN; if (tspace - space <= dquot->dq_dqb.dqb_bsoftlimit) return QUOTA_NL_BSOFTBELOW; if (tspace >= dquot->dq_dqb.dqb_bhardlimit && tspace - space < dquot->dq_dqb.dqb_bhardlimit) return QUOTA_NL_BHARDBELOW; return QUOTA_NL_NOWARN; } static int inode_quota_active(const struct inode *inode) { struct super_block *sb = inode->i_sb; if (IS_NOQUOTA(inode)) return 0; return sb_any_quota_loaded(sb) & ~sb_any_quota_suspended(sb); } /* * Initialize quota pointers in inode * * It is better to call this function outside of any transaction as it * might need a lot of space in journal for dquot structure allocation. */ static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; struct dquot __rcu **dquots; struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; if (!inode_quota_active(inode)) return 0; dquots = i_dquot(inode); /* First get references to structures we might need. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { struct kqid qid; kprojid_t projid; int rc; struct dquot *dquot; if (type != -1 && cnt != type) continue; /* * The i_dquot should have been initialized in most cases, * we check it without locking here to avoid unnecessary * dqget()/dqput() calls. */ if (dquots[cnt]) continue; if (!sb_has_quota_active(sb, cnt)) continue; init_needed = 1; switch (cnt) { case USRQUOTA: qid = make_kqid_uid(inode->i_uid); break; case GRPQUOTA: qid = make_kqid_gid(inode->i_gid); break; case PRJQUOTA: rc = inode->i_sb->dq_op->get_projid(inode, &projid); if (rc) continue; qid = make_kqid_projid(projid); break; } dquot = dqget(sb, qid); if (IS_ERR(dquot)) { /* We raced with somebody turning quotas off... */ if (PTR_ERR(dquot) != -ESRCH) { ret = PTR_ERR(dquot); goto out_put; } dquot = NULL; } got[cnt] = dquot; } /* All required i_dquot has been initialized */ if (!init_needed) return 0; spin_lock(&dq_data_lock); if (IS_NOQUOTA(inode)) goto out_lock; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; /* Avoid races with quotaoff() */ if (!sb_has_quota_active(sb, cnt)) continue; /* We could race with quotaon or dqget() could have failed */ if (!got[cnt]) continue; if (!dquots[cnt]) { rcu_assign_pointer(dquots[cnt], got[cnt]); got[cnt] = NULL; /* * Make quota reservation system happy if someone * did a write before quota was turned on */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { struct dquot *dquot = srcu_dereference_check( dquots[cnt], &dquot_srcu, lockdep_is_held(&dq_data_lock)); spin_lock(&inode->i_lock); /* Get reservation again under proper lock */ rsv = __inode_get_rsv_space(inode); spin_lock(&dquot->dq_dqb_lock); dquot->dq_dqb.dqb_rsvspace += rsv; spin_unlock(&dquot->dq_dqb_lock); spin_unlock(&inode->i_lock); } } } out_lock: spin_unlock(&dq_data_lock); out_put: /* Drop unused references */ dqput_all(got); return ret; } int dquot_initialize(struct inode *inode) { return __dquot_initialize(inode, -1); } EXPORT_SYMBOL(dquot_initialize); bool dquot_initialize_needed(struct inode *inode) { struct dquot __rcu **dquots; int i; if (!inode_quota_active(inode)) return false; dquots = i_dquot(inode); for (i = 0; i < MAXQUOTAS; i++) if (!dquots[i] && sb_has_quota_active(inode->i_sb, i)) return true; return false; } EXPORT_SYMBOL(dquot_initialize_needed); /* * Release all quotas referenced by inode. * * This function only be called on inode free or converting * a file to quota file, no other users for the i_dquot in * both cases, so we needn't call synchronize_srcu() after * clearing i_dquot. */ static void __dquot_drop(struct inode *inode) { int cnt; struct dquot __rcu **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, lockdep_is_held(&dq_data_lock)); rcu_assign_pointer(dquots[cnt], NULL); } spin_unlock(&dq_data_lock); dqput_all(put); } void dquot_drop(struct inode *inode) { struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) return; /* * Test before calling to rule out calls from proc and such * where we are not allowed to block. Note that this is * actually reliable test even without the lock - the caller * must assure that nobody can come after the DQUOT_DROP and * add quota pointers back anyway. */ dquots = i_dquot(inode); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (dquots[cnt]) break; } if (cnt < MAXQUOTAS) __dquot_drop(inode); } EXPORT_SYMBOL(dquot_drop); /* * inode_reserved_space is managed internally by quota, and protected by * i_lock similar to i_blocks+i_bytes. */ static qsize_t *inode_reserved_space(struct inode * inode) { /* Filesystem must explicitly define it's own method in order to use * quota reservation interface */ BUG_ON(!inode->i_sb->dq_op->get_reserved_space); return inode->i_sb->dq_op->get_reserved_space(inode); } static qsize_t __inode_get_rsv_space(struct inode *inode) { if (!inode->i_sb->dq_op->get_reserved_space) return 0; return *inode_reserved_space(inode); } static qsize_t inode_get_rsv_space(struct inode *inode) { qsize_t ret; if (!inode->i_sb->dq_op->get_reserved_space) return 0; spin_lock(&inode->i_lock); ret = __inode_get_rsv_space(inode); spin_unlock(&inode->i_lock); return ret; } /* * This functions updates i_blocks+i_bytes fields and quota information * (together with appropriate checks). * * NOTE: We absolutely rely on the fact that caller dirties the inode * (usually helpers in quotaops.h care about this) and holds a handle for * the current transaction so that dquot write and inode write go into the * same transaction. */ /* * This operation can block, but only after everything is updated */ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; int reserve = flags & DQUOT_SPACE_RESERVE; struct dquot __rcu **dquots; struct dquot *dquot; if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; spin_unlock(&inode->i_lock); } else { inode_add_bytes(inode, number); } goto out; } for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; if (reserve) { ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]); } else { ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]); } if (ret) { /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; spin_lock(&dquot->dq_dqb_lock); if (reserve) dquot_free_reserved_space(dquot, number); else dquot_decr_space(dquot, number); spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); goto out_flush_warn; } } if (reserve) *inode_reserved_space(inode) += number; else __inode_add_bytes(inode, number); spin_unlock(&inode->i_lock); if (reserve) goto out_flush_warn; ret = mark_all_dquot_dirty(dquots); out_flush_warn: srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); out: return ret; } EXPORT_SYMBOL(__dquot_alloc_space); /* * This operation can block, but only after everything is updated */ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; struct dquot __rcu * const *dquots; struct dquot *dquot; if (!inode_quota_active(inode)) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; ret = dquot_add_inodes(dquot, 1, &warn[cnt]); if (ret) { for (cnt--; cnt >= 0; cnt--) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; /* Back out changes we already did */ spin_lock(&dquot->dq_dqb_lock); dquot_decr_inodes(dquot, 1); spin_unlock(&dquot->dq_dqb_lock); } goto warn_put_all; } } warn_put_all: spin_unlock(&inode->i_lock); if (ret == 0) ret = mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); return ret; } EXPORT_SYMBOL(dquot_alloc_inode); /* * Convert in-memory reserved quotas to real consumed quotas */ void dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { struct dquot __rcu **dquots; struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; __inode_add_bytes(inode, number); spin_unlock(&inode->i_lock); return; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) number = dquot->dq_dqb.dqb_rsvspace; dquot->dq_dqb.dqb_curspace += number; dquot->dq_dqb.dqb_rsvspace -= number; spin_unlock(&dquot->dq_dqb_lock); } } /* Update inode bytes */ *inode_reserved_space(inode) -= number; __inode_add_bytes(inode, number); spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); return; } EXPORT_SYMBOL(dquot_claim_space_nodirty); /* * Convert allocated space back to in-memory reserved quotas */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { struct dquot __rcu **dquots; struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; __inode_sub_bytes(inode, number); spin_unlock(&inode->i_lock); return; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) number = dquot->dq_dqb.dqb_curspace; dquot->dq_dqb.dqb_rsvspace += number; dquot->dq_dqb.dqb_curspace -= number; spin_unlock(&dquot->dq_dqb_lock); } } /* Update inode bytes */ *inode_reserved_space(inode) += number; __inode_sub_bytes(inode, number); spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); return; } EXPORT_SYMBOL(dquot_reclaim_space_nodirty); /* * This operation can block, but only after everything is updated */ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; struct dquot __rcu **dquots; struct dquot *dquot; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; spin_unlock(&inode->i_lock); } else { inode_sub_bytes(inode, number); } return; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; spin_lock(&dquot->dq_dqb_lock); wtype = info_bdq_free(dquot, number); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn[cnt], dquot, wtype); if (reserve) dquot_free_reserved_space(dquot, number); else dquot_decr_space(dquot, number); spin_unlock(&dquot->dq_dqb_lock); } if (reserve) *inode_reserved_space(inode) -= number; else __inode_sub_bytes(inode, number); spin_unlock(&inode->i_lock); if (reserve) goto out_unlock; mark_all_dquot_dirty(dquots); out_unlock: srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); } EXPORT_SYMBOL(__dquot_free_space); /* * This operation can block, but only after everything is updated */ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; struct dquot __rcu * const *dquots; struct dquot *dquot; int index; if (!inode_quota_active(inode)) return; dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; spin_lock(&dquot->dq_dqb_lock); wtype = info_idq_free(dquot, 1); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn[cnt], dquot, wtype); dquot_decr_inodes(dquot, 1); spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); } EXPORT_SYMBOL(dquot_free_inode); /* * Transfer the number of inode and blocks from one diskquota to an other. * On success, dquot references in transfer_to are consumed and references * to original dquots that need to be released are placed there. On failure, * references are kept untouched. * * This operation can block, but only after everything is updated * A transaction must be started when entering this function. * * We are holding reference on transfer_from & transfer_to, no need to * protect them by srcu_read_lock(). */ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) { qsize_t cur_space; qsize_t rsv_space = 0; qsize_t inode_usage = 1; struct dquot __rcu **dquots; struct dquot *transfer_from[MAXQUOTAS] = {}; int cnt, index, ret = 0, err; char is_valid[MAXQUOTAS] = {}; struct dquot_warn warn_to[MAXQUOTAS]; struct dquot_warn warn_from_inodes[MAXQUOTAS]; struct dquot_warn warn_from_space[MAXQUOTAS]; if (IS_NOQUOTA(inode)) return 0; if (inode->i_sb->dq_op->get_inode_usage) { ret = inode->i_sb->dq_op->get_inode_usage(inode, &inode_usage); if (ret) return ret; } /* Initialize the arrays */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { warn_to[cnt].w_type = QUOTA_NL_NOWARN; warn_from_inodes[cnt].w_type = QUOTA_NL_NOWARN; warn_from_space[cnt].w_type = QUOTA_NL_NOWARN; } spin_lock(&dq_data_lock); spin_lock(&inode->i_lock); if (IS_NOQUOTA(inode)) { /* File without quota accounting? */ spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); return 0; } cur_space = __inode_get_bytes(inode); rsv_space = __inode_get_rsv_space(inode); dquots = i_dquot(inode); /* * Build the transfer_from list, check limits, and update usage in * the target structures. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { /* * Skip changes for same uid or gid or for turned off quota-type. */ if (!transfer_to[cnt]) continue; /* Avoid races with quotaoff() */ if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; transfer_from[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, lockdep_is_held(&dq_data_lock)); ret = dquot_add_inodes(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) goto over_quota; ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, DQUOT_SPACE_WARN, &warn_to[cnt]); if (ret) { spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); spin_unlock(&transfer_to[cnt]->dq_dqb_lock); goto over_quota; } } /* Decrease usage for source structures and update quota pointers */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (!is_valid[cnt]) continue; /* Due to IO error we might not have transfer_from[] structure */ if (transfer_from[cnt]) { int wtype; spin_lock(&transfer_from[cnt]->dq_dqb_lock); wtype = info_idq_free(transfer_from[cnt], inode_usage); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn_from_inodes[cnt], transfer_from[cnt], wtype); wtype = info_bdq_free(transfer_from[cnt], cur_space + rsv_space); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn_from_space[cnt], transfer_from[cnt], wtype); dquot_decr_inodes(transfer_from[cnt], inode_usage); dquot_decr_space(transfer_from[cnt], cur_space); dquot_free_reserved_space(transfer_from[cnt], rsv_space); spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } rcu_assign_pointer(dquots[cnt], transfer_to[cnt]); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); /* * These arrays are local and we hold dquot references so we don't need * the srcu protection but still take dquot_srcu to avoid warning in * mark_all_dquot_dirty(). */ index = srcu_read_lock(&dquot_srcu); err = mark_all_dquot_dirty((struct dquot __rcu **)transfer_from); if (err < 0) ret = err; err = mark_all_dquot_dirty((struct dquot __rcu **)transfer_to); if (err < 0) ret = err; srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn_to); flush_warnings(warn_from_inodes); flush_warnings(warn_from_space); /* Pass back references to put */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (is_valid[cnt]) transfer_to[cnt] = transfer_from[cnt]; return ret; over_quota: /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { if (!is_valid[cnt]) continue; spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); dquot_decr_space(transfer_to[cnt], cur_space); dquot_free_reserved_space(transfer_to[cnt], rsv_space); spin_unlock(&transfer_to[cnt]->dq_dqb_lock); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); flush_warnings(warn_to); return ret; } EXPORT_SYMBOL(__dquot_transfer); /* Wrapper for transferring ownership of an inode for uid/gid only * Called from FSXXX_setattr() */ int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr) { struct dquot *transfer_to[MAXQUOTAS] = {}; struct dquot *dquot; struct super_block *sb = inode->i_sb; int ret; if (!inode_quota_active(inode)) return 0; if (i_uid_needs_update(idmap, iattr, inode)) { kuid_t kuid = from_vfsuid(idmap, i_user_ns(inode), iattr->ia_vfsuid); dquot = dqget(sb, make_kqid_uid(kuid)); if (IS_ERR(dquot)) { if (PTR_ERR(dquot) != -ESRCH) { ret = PTR_ERR(dquot); goto out_put; } dquot = NULL; } transfer_to[USRQUOTA] = dquot; } if (i_gid_needs_update(idmap, iattr, inode)) { kgid_t kgid = from_vfsgid(idmap, i_user_ns(inode), iattr->ia_vfsgid); dquot = dqget(sb, make_kqid_gid(kgid)); if (IS_ERR(dquot)) { if (PTR_ERR(dquot) != -ESRCH) { ret = PTR_ERR(dquot); goto out_put; } dquot = NULL; } transfer_to[GRPQUOTA] = dquot; } ret = __dquot_transfer(inode, transfer_to); out_put: dqput_all(transfer_to); return ret; } EXPORT_SYMBOL(dquot_transfer); /* * Write info of quota file to disk */ int dquot_commit_info(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); return dqopt->ops[type]->write_file_info(sb, type); } EXPORT_SYMBOL(dquot_commit_info); int dquot_get_next_id(struct super_block *sb, struct kqid *qid) { struct quota_info *dqopt = sb_dqopt(sb); if (!sb_has_quota_active(sb, qid->type)) return -ESRCH; if (!dqopt->ops[qid->type]->get_next_id) return -ENOSYS; return dqopt->ops[qid->type]->get_next_id(sb, qid); } EXPORT_SYMBOL(dquot_get_next_id); /* * Definitions of diskquota operations. */ const struct dquot_operations dquot_operations = { .write_dquot = dquot_commit, .acquire_dquot = dquot_acquire, .release_dquot = dquot_release, .mark_dirty = dquot_mark_dquot_dirty, .write_info = dquot_commit_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_next_id = dquot_get_next_id, }; EXPORT_SYMBOL(dquot_operations); /* * Generic helper for ->open on filesystems supporting disk quotas. */ int dquot_file_open(struct inode *inode, struct file *file) { int error; error = generic_file_open(inode, file); if (!error && (file->f_mode & FMODE_WRITE)) error = dquot_initialize(inode); return error; } EXPORT_SYMBOL(dquot_file_open); static void vfs_cleanup_quota_inode(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); struct inode *inode = dqopt->files[type]; if (!inode) return; if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { inode_lock(inode); inode->i_flags &= ~S_NOQUOTA; inode_unlock(inode); } dqopt->files[type] = NULL; iput(inode); } /* * Turn quota off on a device. type == -1 ==> quotaoff for all types (umount) */ int dquot_disable(struct super_block *sb, int type, unsigned int flags) { int cnt; struct quota_info *dqopt = sb_dqopt(sb); /* s_umount should be held in exclusive mode */ if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount))) up_read(&sb->s_umount); /* Cannot turn off usage accounting without turning off limits, or * suspend quotas and simultaneously turn quotas off. */ if ((flags & DQUOT_USAGE_ENABLED && !(flags & DQUOT_LIMITS_ENABLED)) || (flags & DQUOT_SUSPENDED && flags & (DQUOT_LIMITS_ENABLED | DQUOT_USAGE_ENABLED))) return -EINVAL; /* * Skip everything if there's nothing to do. We have to do this because * sometimes we are called when fill_super() failed and calling * sync_fs() in such cases does no good. */ if (!sb_any_quota_loaded(sb)) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_loaded(sb, cnt)) continue; if (flags & DQUOT_SUSPENDED) { spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(DQUOT_SUSPENDED, cnt); spin_unlock(&dq_state_lock); } else { spin_lock(&dq_state_lock); dqopt->flags &= ~dquot_state_flag(flags, cnt); /* Turning off suspended quotas? */ if (!sb_has_quota_loaded(sb, cnt) && sb_has_quota_suspended(sb, cnt)) { dqopt->flags &= ~dquot_state_flag( DQUOT_SUSPENDED, cnt); spin_unlock(&dq_state_lock); vfs_cleanup_quota_inode(sb, cnt); continue; } spin_unlock(&dq_state_lock); } /* We still have to keep quota loaded? */ if (sb_has_quota_loaded(sb, cnt) && !(flags & DQUOT_SUSPENDED)) continue; /* Note: these are blocking operations */ drop_dquot_ref(sb, cnt); invalidate_dquots(sb, cnt); /* * Now all dquots should be invalidated, all writes done so we * should be only users of the info. No locks needed. */ if (info_dirty(&dqopt->info[cnt])) sb->dq_op->write_info(sb, cnt); if (dqopt->ops[cnt]->free_file_info) dqopt->ops[cnt]->free_file_info(sb, cnt); put_quota_format(dqopt->info[cnt].dqi_format); dqopt->info[cnt].dqi_flags = 0; dqopt->info[cnt].dqi_igrace = 0; dqopt->info[cnt].dqi_bgrace = 0; dqopt->ops[cnt] = NULL; } /* Skip syncing and setting flags if quota files are hidden */ if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) goto put_inodes; /* Sync the superblock so that buffers with quota data are written to * disk (and so userspace sees correct data afterwards). */ if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, 1); sync_blockdev(sb->s_bdev); /* Now the quota files are just ordinary files and we can set the * inode flags back. Moreover we discard the pagecache so that * userspace sees the writes we did bypassing the pagecache. We * must also discard the blockdev buffers so that we see the * changes done by userspace on the next quotaon() */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (!sb_has_quota_loaded(sb, cnt) && dqopt->files[cnt]) { inode_lock(dqopt->files[cnt]); truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); inode_unlock(dqopt->files[cnt]); } if (sb->s_bdev) invalidate_bdev(sb->s_bdev); put_inodes: /* We are done when suspending quotas */ if (flags & DQUOT_SUSPENDED) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (!sb_has_quota_loaded(sb, cnt)) vfs_cleanup_quota_inode(sb, cnt); return 0; } EXPORT_SYMBOL(dquot_disable); int dquot_quota_off(struct super_block *sb, int type) { return dquot_disable(sb, type, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); } EXPORT_SYMBOL(dquot_quota_off); /* * Turn quotas on on a device */ static int vfs_setup_quota_inode(struct inode *inode, int type) { struct super_block *sb = inode->i_sb; struct quota_info *dqopt = sb_dqopt(sb); if (is_bad_inode(inode)) return -EUCLEAN; if (!S_ISREG(inode->i_mode)) return -EACCES; if (IS_RDONLY(inode)) return -EROFS; if (sb_has_quota_loaded(sb, type)) return -EBUSY; /* * Quota files should never be encrypted. They should be thought of as * filesystem metadata, not user data. New-style internal quota files * cannot be encrypted by users anyway, but old-style external quota * files could potentially be incorrectly created in an encrypted * directory, hence this explicit check. Some reasons why encrypted * quota files don't work include: (1) some filesystems that support * encryption don't handle it in their quota_read and quota_write, and * (2) cleaning up encrypted quota files at unmount would need special * consideration, as quota files are cleaned up later than user files. */ if (IS_ENCRYPTED(inode)) return -EINVAL; dqopt->files[type] = igrab(inode); if (!dqopt->files[type]) return -EIO; if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { /* We don't want quota and atime on quota files (deadlocks * possible) Also nobody should write to the file - we use * special IO operations which ignore the immutable bit. */ inode_lock(inode); inode->i_flags |= S_NOQUOTA; inode_unlock(inode); /* * When S_NOQUOTA is set, remove dquot references as no more * references can be added */ __dquot_drop(inode); } return 0; } int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags) { struct quota_format_type *fmt = find_quota_format(format_id); struct quota_info *dqopt = sb_dqopt(sb); int error; lockdep_assert_held_write(&sb->s_umount); /* Just unsuspend quotas? */ if (WARN_ON_ONCE(flags & DQUOT_SUSPENDED)) return -EINVAL; if (!fmt) return -ESRCH; if (!sb->dq_op || !sb->s_qcop || (type == PRJQUOTA && sb->dq_op->get_projid == NULL)) { error = -EINVAL; goto out_fmt; } /* Filesystems outside of init_user_ns not yet supported */ if (sb->s_user_ns != &init_user_ns) { error = -EINVAL; goto out_fmt; } /* Usage always has to be set... */ if (!(flags & DQUOT_USAGE_ENABLED)) { error = -EINVAL; goto out_fmt; } if (sb_has_quota_loaded(sb, type)) { error = -EBUSY; goto out_fmt; } if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { /* As we bypass the pagecache we must now flush all the * dirty data and invalidate caches so that kernel sees * changes from userspace. It is not enough to just flush * the quota file since if blocksize < pagesize, invalidation * of the cache could fail because of other unrelated dirty * data */ sync_filesystem(sb); invalidate_bdev(sb->s_bdev); } error = -EINVAL; if (!fmt->qf_ops->check_quota_file(sb, type)) goto out_fmt; dqopt->ops[type] = fmt->qf_ops; dqopt->info[type].dqi_format = fmt; dqopt->info[type].dqi_fmt_id = format_id; INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list); error = dqopt->ops[type]->read_file_info(sb, type); if (error < 0) goto out_fmt; if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) { spin_lock(&dq_data_lock); dqopt->info[type].dqi_flags |= DQF_SYS_FILE; spin_unlock(&dq_data_lock); } spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(flags, type); spin_unlock(&dq_state_lock); error = add_dquot_ref(sb, type); if (error) dquot_disable(sb, type, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); return error; out_fmt: put_quota_format(fmt); return error; } EXPORT_SYMBOL(dquot_load_quota_sb); /* * More powerful function for turning on quotas on given quota inode allowing * setting of individual quota flags */ int dquot_load_quota_inode(struct inode *inode, int type, int format_id, unsigned int flags) { int err; err = vfs_setup_quota_inode(inode, type); if (err < 0) return err; err = dquot_load_quota_sb(inode->i_sb, type, format_id, flags); if (err < 0) vfs_cleanup_quota_inode(inode->i_sb, type); return err; } EXPORT_SYMBOL(dquot_load_quota_inode); /* Reenable quotas on remount RW */ int dquot_resume(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); int ret = 0, cnt; unsigned int flags; /* s_umount should be held in exclusive mode */ if (WARN_ON_ONCE(down_read_trylock(&sb->s_umount))) up_read(&sb->s_umount); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_suspended(sb, cnt)) continue; spin_lock(&dq_state_lock); flags = dqopt->flags & dquot_state_flag(DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED, cnt); dqopt->flags &= ~dquot_state_flag(DQUOT_STATE_FLAGS, cnt); spin_unlock(&dq_state_lock); flags = dquot_generic_flag(flags, cnt); ret = dquot_load_quota_sb(sb, cnt, dqopt->info[cnt].dqi_fmt_id, flags); if (ret < 0) vfs_cleanup_quota_inode(sb, cnt); } return ret; } EXPORT_SYMBOL(dquot_resume); int dquot_quota_on(struct super_block *sb, int type, int format_id, const struct path *path) { int error = security_quota_on(path->dentry); if (error) return error; /* Quota file not on the same filesystem? */ if (path->dentry->d_sb != sb) error = -EXDEV; else error = dquot_load_quota_inode(d_inode(path->dentry), type, format_id, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); return error; } EXPORT_SYMBOL(dquot_quota_on); /* * This function is used when filesystem needs to initialize quotas * during mount time. */ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type) { struct dentry *dentry; int error; dentry = lookup_positive_unlocked(qf_name, sb->s_root, strlen(qf_name)); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_quota_on(dentry); if (!error) error = dquot_load_quota_inode(d_inode(dentry), type, format_id, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); dput(dentry); return error; } EXPORT_SYMBOL(dquot_quota_on_mount); static int dquot_quota_enable(struct super_block *sb, unsigned int flags) { int ret; int type; struct quota_info *dqopt = sb_dqopt(sb); if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) return -ENOSYS; /* Accounting cannot be turned on while fs is mounted */ flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT); if (!flags) return -EINVAL; for (type = 0; type < MAXQUOTAS; type++) { if (!(flags & qtype_enforce_flag(type))) continue; /* Can't enforce without accounting */ if (!sb_has_quota_usage_enabled(sb, type)) { ret = -EINVAL; goto out_err; } if (sb_has_quota_limits_enabled(sb, type)) { ret = -EBUSY; goto out_err; } spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(DQUOT_LIMITS_ENABLED, type); spin_unlock(&dq_state_lock); } return 0; out_err: /* Backout enforcement enablement we already did */ for (type--; type >= 0; type--) { if (flags & qtype_enforce_flag(type)) dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); } /* Error code translation for better compatibility with XFS */ if (ret == -EBUSY) ret = -EEXIST; return ret; } static int dquot_quota_disable(struct super_block *sb, unsigned int flags) { int ret; int type; struct quota_info *dqopt = sb_dqopt(sb); if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) return -ENOSYS; /* * We don't support turning off accounting via quotactl. In principle * quota infrastructure can do this but filesystems don't expect * userspace to be able to do it. */ if (flags & (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT)) return -EOPNOTSUPP; /* Filter out limits not enabled */ for (type = 0; type < MAXQUOTAS; type++) if (!sb_has_quota_limits_enabled(sb, type)) flags &= ~qtype_enforce_flag(type); /* Nothing left? */ if (!flags) return -EEXIST; for (type = 0; type < MAXQUOTAS; type++) { if (flags & qtype_enforce_flag(type)) { ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); if (ret < 0) goto out_err; } } return 0; out_err: /* Backout enforcement disabling we already did */ for (type--; type >= 0; type--) { if (flags & qtype_enforce_flag(type)) { spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(DQUOT_LIMITS_ENABLED, type); spin_unlock(&dq_state_lock); } } return ret; } /* Generic routine for getting common part of quota structure */ static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; memset(di, 0, sizeof(*di)); spin_lock(&dquot->dq_dqb_lock); di->d_spc_hardlimit = dm->dqb_bhardlimit; di->d_spc_softlimit = dm->dqb_bsoftlimit; di->d_ino_hardlimit = dm->dqb_ihardlimit; di->d_ino_softlimit = dm->dqb_isoftlimit; di->d_space = dm->dqb_curspace + dm->dqb_rsvspace; di->d_ino_count = dm->dqb_curinodes; di->d_spc_timer = dm->dqb_btime; di->d_ino_timer = dm->dqb_itime; spin_unlock(&dquot->dq_dqb_lock); } int dquot_get_dqblk(struct super_block *sb, struct kqid qid, struct qc_dqblk *di) { struct dquot *dquot; dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); do_get_dqblk(dquot, di); dqput(dquot); return 0; } EXPORT_SYMBOL(dquot_get_dqblk); int dquot_get_next_dqblk(struct super_block *sb, struct kqid *qid, struct qc_dqblk *di) { struct dquot *dquot; int err; if (!sb->dq_op->get_next_id) return -ENOSYS; err = sb->dq_op->get_next_id(sb, qid); if (err < 0) return err; dquot = dqget(sb, *qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); do_get_dqblk(dquot, di); dqput(dquot); return 0; } EXPORT_SYMBOL(dquot_get_next_dqblk); #define VFS_QC_MASK \ (QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \ QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \ QC_SPC_TIMER | QC_INO_TIMER) /* Generic routine for setting common part of quota structure */ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; int check_blim = 0, check_ilim = 0; struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; int ret; if (di->d_fieldmask & ~VFS_QC_MASK) return -EINVAL; if (((di->d_fieldmask & QC_SPC_SOFT) && di->d_spc_softlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_SPC_HARD) && di->d_spc_hardlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_INO_SOFT) && (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) || ((di->d_fieldmask & QC_INO_HARD) && (di->d_ino_hardlimit > dqi->dqi_max_ino_limit))) return -ERANGE; spin_lock(&dquot->dq_dqb_lock); if (di->d_fieldmask & QC_SPACE) { dm->dqb_curspace = di->d_space - dm->dqb_rsvspace; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_SPC_SOFT) dm->dqb_bsoftlimit = di->d_spc_softlimit; if (di->d_fieldmask & QC_SPC_HARD) dm->dqb_bhardlimit = di->d_spc_hardlimit; if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) { check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_INO_COUNT) { dm->dqb_curinodes = di->d_ino_count; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_INO_SOFT) dm->dqb_isoftlimit = di->d_ino_softlimit; if (di->d_fieldmask & QC_INO_HARD) dm->dqb_ihardlimit = di->d_ino_hardlimit; if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) { check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_SPC_TIMER) { dm->dqb_btime = di->d_spc_timer; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_INO_TIMER) { dm->dqb_itime = di->d_ino_timer; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags); } if (check_blim) { if (!dm->dqb_bsoftlimit || dm->dqb_curspace + dm->dqb_rsvspace <= dm->dqb_bsoftlimit) { dm->dqb_btime = 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } else if (!(di->d_fieldmask & QC_SPC_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_btime = ktime_get_real_seconds() + dqi->dqi_bgrace; } if (check_ilim) { if (!dm->dqb_isoftlimit || dm->dqb_curinodes <= dm->dqb_isoftlimit) { dm->dqb_itime = 0; clear_bit(DQ_INODES_B, &dquot->dq_flags); } else if (!(di->d_fieldmask & QC_INO_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_itime = ktime_get_real_seconds() + dqi->dqi_igrace; } if (dm->dqb_bhardlimit || dm->dqb_bsoftlimit || dm->dqb_ihardlimit || dm->dqb_isoftlimit) clear_bit(DQ_FAKE_B, &dquot->dq_flags); else set_bit(DQ_FAKE_B, &dquot->dq_flags); spin_unlock(&dquot->dq_dqb_lock); ret = mark_dquot_dirty(dquot); if (ret < 0) return ret; return 0; } int dquot_set_dqblk(struct super_block *sb, struct kqid qid, struct qc_dqblk *di) { struct dquot *dquot; int rc; dquot = dqget(sb, qid); if (IS_ERR(dquot)) { rc = PTR_ERR(dquot); goto out; } rc = do_set_dqblk(dquot, di); dqput(dquot); out: return rc; } EXPORT_SYMBOL(dquot_set_dqblk); /* Generic routine for getting common part of quota file information */ int dquot_get_state(struct super_block *sb, struct qc_state *state) { struct mem_dqinfo *mi; struct qc_type_state *tstate; struct quota_info *dqopt = sb_dqopt(sb); int type; memset(state, 0, sizeof(*state)); for (type = 0; type < MAXQUOTAS; type++) { if (!sb_has_quota_active(sb, type)) continue; tstate = state->s_state + type; mi = sb_dqopt(sb)->info + type; tstate->flags = QCI_ACCT_ENABLED; spin_lock(&dq_data_lock); if (mi->dqi_flags & DQF_SYS_FILE) tstate->flags |= QCI_SYSFILE; if (mi->dqi_flags & DQF_ROOT_SQUASH) tstate->flags |= QCI_ROOT_SQUASH; if (sb_has_quota_limits_enabled(sb, type)) tstate->flags |= QCI_LIMITS_ENFORCED; tstate->spc_timelimit = mi->dqi_bgrace; tstate->ino_timelimit = mi->dqi_igrace; if (dqopt->files[type]) { tstate->ino = dqopt->files[type]->i_ino; tstate->blocks = dqopt->files[type]->i_blocks; } tstate->nextents = 1; /* We don't know... */ spin_unlock(&dq_data_lock); } return 0; } EXPORT_SYMBOL(dquot_get_state); /* Generic routine for setting common part of quota file information */ int dquot_set_dqinfo(struct super_block *sb, int type, struct qc_info *ii) { struct mem_dqinfo *mi; if ((ii->i_fieldmask & QC_WARNS_MASK) || (ii->i_fieldmask & QC_RT_SPC_TIMER)) return -EINVAL; if (!sb_has_quota_active(sb, type)) return -ESRCH; mi = sb_dqopt(sb)->info + type; if (ii->i_fieldmask & QC_FLAGS) { if ((ii->i_flags & QCI_ROOT_SQUASH && mi->dqi_format->qf_fmt_id != QFMT_VFS_OLD)) return -EINVAL; } spin_lock(&dq_data_lock); if (ii->i_fieldmask & QC_SPC_TIMER) mi->dqi_bgrace = ii->i_spc_timelimit; if (ii->i_fieldmask & QC_INO_TIMER) mi->dqi_igrace = ii->i_ino_timelimit; if (ii->i_fieldmask & QC_FLAGS) { if (ii->i_flags & QCI_ROOT_SQUASH) mi->dqi_flags |= DQF_ROOT_SQUASH; else mi->dqi_flags &= ~DQF_ROOT_SQUASH; } spin_unlock(&dq_data_lock); mark_info_dirty(sb, type); /* Force write to disk */ return sb->dq_op->write_info(sb, type); } EXPORT_SYMBOL(dquot_set_dqinfo); const struct quotactl_ops dquot_quotactl_sysfile_ops = { .quota_enable = dquot_quota_enable, .quota_disable = dquot_quota_disable, .quota_sync = dquot_quota_sync, .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .get_nextdqblk = dquot_get_next_dqblk, .set_dqblk = dquot_set_dqblk }; EXPORT_SYMBOL(dquot_quotactl_sysfile_ops); static int do_proc_dqstats(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned int type = (unsigned long *)table->data - dqstats.stat; s64 value = percpu_counter_sum(&dqstats.counter[type]); /* Filter negative values for non-monotonic counters */ if (value < 0 && (type == DQST_ALLOC_DQUOTS || type == DQST_FREE_DQUOTS)) value = 0; /* Update global table */ dqstats.stat[type] = value; return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_dqstats_table[] = { { .procname = "lookups", .data = &dqstats.stat[DQST_LOOKUPS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "drops", .data = &dqstats.stat[DQST_DROPS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "reads", .data = &dqstats.stat[DQST_READS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "writes", .data = &dqstats.stat[DQST_WRITES], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "cache_hits", .data = &dqstats.stat[DQST_CACHE_HITS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "allocated_dquots", .data = &dqstats.stat[DQST_ALLOC_DQUOTS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "free_dquots", .data = &dqstats.stat[DQST_FREE_DQUOTS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "syncs", .data = &dqstats.stat[DQST_SYNCS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, #ifdef CONFIG_PRINT_QUOTA_WARNING { .procname = "warnings", .data = &flag_print_warnings, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif }; static int __init dquot_init(void) { int i, ret; unsigned long nr_hash, order; struct shrinker *dqcache_shrinker; printk(KERN_NOTICE "VFS: Disk quotas %s\n", __DQUOT_VERSION__); register_sysctl_init("fs/quota", fs_dqstats_table); dquot_cachep = kmem_cache_create("dquot", sizeof(struct dquot), sizeof(unsigned long) * 4, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| SLAB_PANIC), NULL); order = 0; dquot_hash = (struct hlist_head *)__get_free_pages(GFP_KERNEL, order); if (!dquot_hash) panic("Cannot create dquot hash table"); ret = percpu_counter_init_many(dqstats.counter, 0, GFP_KERNEL, _DQST_DQSTAT_LAST); if (ret) panic("Cannot create dquot stat counters"); /* Find power-of-two hlist_heads which can fit into allocation */ nr_hash = (1UL << order) * PAGE_SIZE / sizeof(struct hlist_head); dq_hash_bits = ilog2(nr_hash); nr_hash = 1UL << dq_hash_bits; dq_hash_mask = nr_hash - 1; for (i = 0; i < nr_hash; i++) INIT_HLIST_HEAD(dquot_hash + i); pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld," " %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); dqcache_shrinker = shrinker_alloc(0, "dquota-cache"); if (!dqcache_shrinker) panic("Cannot allocate dquot shrinker"); dqcache_shrinker->count_objects = dqcache_shrink_count; dqcache_shrinker->scan_objects = dqcache_shrink_scan; shrinker_register(dqcache_shrinker); return 0; } fs_initcall(dquot_init); |
| 1 1 16 16 2 16 4 4 4 2 2 2 2 2 2 12 12 7 7 7 2 4 2 2 12 2 2 8 8 1 6 8 1 7 7 1 7 17 17 13 12 7 2 8 8 3 1 7 2 1 1 12 5 7 8 5 36 36 36 35 29 2 2 7 26 30 30 30 3 5 5 5 5 25 25 1 16 16 22 5 10 5 13 7 2 12 2 11 12 3 2 2 5 8 1 2 1 1 7 2 1 1 1 1 3 5 1 1 1 2 2 1 1 12 2 1 9 2 3 2 11 1 2 3 2 1 13 12 3 13 9 2 1 3 3 3 3 2 4 9 2 2 2 2 2 2 2 2 1 1 2 31 4 14 5 2 5 7 7 7 10 10 10 3 7 10 10 11 1 10 8 2 10 10 10 9 6 3 2 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel Connection Multiplexor * * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> */ #include <linux/bpf.h> #include <linux/errno.h> #include <linux/errqueue.h> #include <linux/file.h> #include <linux/filter.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/uaccess.h> #include <linux/workqueue.h> #include <linux/syscalls.h> #include <linux/sched/signal.h> #include <net/kcm.h> #include <net/netns/generic.h> #include <net/sock.h> #include <uapi/linux/kcm.h> #include <trace/events/sock.h> unsigned int kcm_net_id; static struct kmem_cache *kcm_psockp __read_mostly; static struct kmem_cache *kcm_muxp __read_mostly; static struct workqueue_struct *kcm_wq; static inline struct kcm_sock *kcm_sk(const struct sock *sk) { return (struct kcm_sock *)sk; } static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) { return (struct kcm_tx_msg *)skb->cb; } static void report_csk_error(struct sock *csk, int err) { csk->sk_err = EPIPE; sk_error_report(csk); } static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, bool wakeup_kcm) { struct sock *csk = psock->sk; struct kcm_mux *mux = psock->mux; /* Unrecoverable error in transmit */ spin_lock_bh(&mux->lock); if (psock->tx_stopped) { spin_unlock_bh(&mux->lock); return; } psock->tx_stopped = 1; KCM_STATS_INCR(psock->stats.tx_aborts); if (!psock->tx_kcm) { /* Take off psocks_avail list */ list_del(&psock->psock_avail_list); } else if (wakeup_kcm) { /* In this case psock is being aborted while outside of * write_msgs and psock is reserved. Schedule tx_work * to handle the failure there. Need to commit tx_stopped * before queuing work. */ smp_mb(); queue_work(kcm_wq, &psock->tx_kcm->tx_work); } spin_unlock_bh(&mux->lock); /* Report error on lower socket */ report_csk_error(csk, err); } /* RX mux lock held. */ static void kcm_update_rx_mux_stats(struct kcm_mux *mux, struct kcm_psock *psock) { STRP_STATS_ADD(mux->stats.rx_bytes, psock->strp.stats.bytes - psock->saved_rx_bytes); mux->stats.rx_msgs += psock->strp.stats.msgs - psock->saved_rx_msgs; psock->saved_rx_msgs = psock->strp.stats.msgs; psock->saved_rx_bytes = psock->strp.stats.bytes; } static void kcm_update_tx_mux_stats(struct kcm_mux *mux, struct kcm_psock *psock) { KCM_STATS_ADD(mux->stats.tx_bytes, psock->stats.tx_bytes - psock->saved_tx_bytes); mux->stats.tx_msgs += psock->stats.tx_msgs - psock->saved_tx_msgs; psock->saved_tx_msgs = psock->stats.tx_msgs; psock->saved_tx_bytes = psock->stats.tx_bytes; } static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); /* KCM is ready to receive messages on its queue-- either the KCM is new or * has become unblocked after being blocked on full socket buffer. Queue any * pending ready messages on a psock. RX mux lock held. */ static void kcm_rcv_ready(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; struct sk_buff *skb; if (unlikely(kcm->rx_wait || kcm->rx_psock || kcm->rx_disabled)) return; while (unlikely((skb = __skb_dequeue(&mux->rx_hold_queue)))) { if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Assuming buffer limit has been reached */ skb_queue_head(&mux->rx_hold_queue, skb); WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); return; } } while (!list_empty(&mux->psocks_ready)) { psock = list_first_entry(&mux->psocks_ready, struct kcm_psock, psock_ready_list); if (kcm_queue_rcv_skb(&kcm->sk, psock->ready_rx_msg)) { /* Assuming buffer limit has been reached */ WARN_ON(!sk_rmem_alloc_get(&kcm->sk)); return; } /* Consumed the ready message on the psock. Schedule rx_work to * get more messages. */ list_del(&psock->psock_ready_list); psock->ready_rx_msg = NULL; /* Commit clearing of ready_rx_msg for queuing work */ smp_mb(); strp_unpause(&psock->strp); strp_check_rcv(&psock->strp); } /* Buffer limit is okay now, add to ready list */ list_add_tail(&kcm->wait_rx_list, &kcm->mux->kcm_rx_waiters); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, true); } static void kcm_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct kcm_sock *kcm = kcm_sk(sk); struct kcm_mux *mux = kcm->mux; unsigned int len = skb->truesize; sk_mem_uncharge(sk, len); atomic_sub(len, &sk->sk_rmem_alloc); /* For reading rx_wait and rx_psock without holding lock */ smp_mb__after_atomic(); if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) && sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } } static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct sk_buff_head *list = &sk->sk_receive_queue; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) return -ENOMEM; if (!sk_rmem_schedule(sk, skb, skb->truesize)) return -ENOBUFS; skb->dev = NULL; skb_orphan(skb); skb->sk = sk; skb->destructor = kcm_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); skb_queue_tail(list, skb); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk); return 0; } /* Requeue received messages for a kcm socket to other kcm sockets. This is * called with a kcm socket is receive disabled. * RX mux lock held. */ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) { struct sk_buff *skb; struct kcm_sock *kcm; while ((skb = skb_dequeue(head))) { /* Reset destructor to avoid calling kcm_rcv_ready */ skb->destructor = sock_rfree; skb_orphan(skb); try_again: if (list_empty(&mux->kcm_rx_waiters)) { skb_queue_tail(&mux->rx_hold_queue, skb); continue; } kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); /* Commit rx_wait to read in kcm_free */ smp_wmb(); goto try_again; } } } /* Lower sock lock held */ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, struct sk_buff *head) { struct kcm_mux *mux = psock->mux; struct kcm_sock *kcm; WARN_ON(psock->ready_rx_msg); if (psock->rx_kcm) return psock->rx_kcm; spin_lock_bh(&mux->rx_lock); if (psock->rx_kcm) { spin_unlock_bh(&mux->rx_lock); return psock->rx_kcm; } kcm_update_rx_mux_stats(mux, psock); if (list_empty(&mux->kcm_rx_waiters)) { psock->ready_rx_msg = head; strp_pause(&psock->strp); list_add_tail(&psock->psock_ready_list, &mux->psocks_ready); spin_unlock_bh(&mux->rx_lock); return NULL; } kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); psock->rx_kcm = kcm; /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_psock, psock); spin_unlock_bh(&mux->rx_lock); return kcm; } static void kcm_done(struct kcm_sock *kcm); static void kcm_done_work(struct work_struct *w) { kcm_done(container_of(w, struct kcm_sock, done_work)); } /* Lower sock held */ static void unreserve_rx_kcm(struct kcm_psock *psock, bool rcv_ready) { struct kcm_sock *kcm = psock->rx_kcm; struct kcm_mux *mux = psock->mux; if (!kcm) return; spin_lock_bh(&mux->rx_lock); psock->rx_kcm = NULL; /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_psock, NULL); /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with * kcm_rfree */ smp_mb(); if (unlikely(kcm->done)) { spin_unlock_bh(&mux->rx_lock); /* Need to run kcm_done in a task since we need to qcquire * callback locks which may already be held here. */ INIT_WORK(&kcm->done_work, kcm_done_work); schedule_work(&kcm->done_work); return; } if (unlikely(kcm->rx_disabled)) { requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); } else if (rcv_ready || unlikely(!sk_rmem_alloc_get(&kcm->sk))) { /* Check for degenerative race with rx_wait that all * data was dequeued (accounted for in kcm_rfree). */ kcm_rcv_ready(kcm); } spin_unlock_bh(&mux->rx_lock); } /* Lower sock lock held */ static void psock_data_ready(struct sock *sk) { struct kcm_psock *psock; trace_sk_data_ready(sk); read_lock_bh(&sk->sk_callback_lock); psock = (struct kcm_psock *)sk->sk_user_data; if (likely(psock)) strp_data_ready(&psock->strp); read_unlock_bh(&sk->sk_callback_lock); } /* Called with lower sock held */ static void kcm_rcv_strparser(struct strparser *strp, struct sk_buff *skb) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); struct kcm_sock *kcm; try_queue: kcm = reserve_rx_kcm(psock, skb); if (!kcm) { /* Unable to reserve a KCM, message is held in psock and strp * is paused. */ return; } if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ unreserve_rx_kcm(psock, false); goto try_queue; } } static int kcm_parse_func_strparser(struct strparser *strp, struct sk_buff *skb) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); struct bpf_prog *prog = psock->bpf_prog; int res; res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } static int kcm_read_sock_done(struct strparser *strp, int err) { struct kcm_psock *psock = container_of(strp, struct kcm_psock, strp); unreserve_rx_kcm(psock, true); return err; } static void psock_state_change(struct sock *sk) { /* TCP only does a EPOLLIN for a half close. Do a EPOLLHUP here * since application will normally not poll with EPOLLIN * on the TCP sockets. */ report_csk_error(sk, EPIPE); } static void psock_write_space(struct sock *sk) { struct kcm_psock *psock; struct kcm_mux *mux; struct kcm_sock *kcm; read_lock_bh(&sk->sk_callback_lock); psock = (struct kcm_psock *)sk->sk_user_data; if (unlikely(!psock)) goto out; mux = psock->mux; spin_lock_bh(&mux->lock); /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; if (kcm && !unlikely(kcm->tx_stopped)) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); out: read_unlock_bh(&sk->sk_callback_lock); } static void unreserve_psock(struct kcm_sock *kcm); /* kcm sock is locked. */ static struct kcm_psock *reserve_psock(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; psock = kcm->tx_psock; smp_rmb(); /* Must read tx_psock before tx_wait */ if (psock) { WARN_ON(kcm->tx_wait); if (unlikely(psock->tx_stopped)) unreserve_psock(kcm); else return kcm->tx_psock; } spin_lock_bh(&mux->lock); /* Check again under lock to see if psock was reserved for this * psock via psock_unreserve. */ psock = kcm->tx_psock; if (unlikely(psock)) { WARN_ON(kcm->tx_wait); spin_unlock_bh(&mux->lock); return kcm->tx_psock; } if (!list_empty(&mux->psocks_avail)) { psock = list_first_entry(&mux->psocks_avail, struct kcm_psock, psock_avail_list); list_del(&psock->psock_avail_list); if (kcm->tx_wait) { list_del(&kcm->wait_psock_list); kcm->tx_wait = false; } kcm->tx_psock = psock; psock->tx_kcm = kcm; KCM_STATS_INCR(psock->stats.reserved); } else if (!kcm->tx_wait) { list_add_tail(&kcm->wait_psock_list, &mux->kcm_tx_waiters); kcm->tx_wait = true; } spin_unlock_bh(&mux->lock); return psock; } /* mux lock held */ static void psock_now_avail(struct kcm_psock *psock) { struct kcm_mux *mux = psock->mux; struct kcm_sock *kcm; if (list_empty(&mux->kcm_tx_waiters)) { list_add_tail(&psock->psock_avail_list, &mux->psocks_avail); } else { kcm = list_first_entry(&mux->kcm_tx_waiters, struct kcm_sock, wait_psock_list); list_del(&kcm->wait_psock_list); kcm->tx_wait = false; psock->tx_kcm = kcm; /* Commit before changing tx_psock since that is read in * reserve_psock before queuing work. */ smp_mb(); kcm->tx_psock = psock; KCM_STATS_INCR(psock->stats.reserved); queue_work(kcm_wq, &kcm->tx_work); } } /* kcm sock is locked. */ static void unreserve_psock(struct kcm_sock *kcm) { struct kcm_psock *psock; struct kcm_mux *mux = kcm->mux; spin_lock_bh(&mux->lock); psock = kcm->tx_psock; if (WARN_ON(!psock)) { spin_unlock_bh(&mux->lock); return; } smp_rmb(); /* Read tx_psock before tx_wait */ kcm_update_tx_mux_stats(mux, psock); WARN_ON(kcm->tx_wait); kcm->tx_psock = NULL; psock->tx_kcm = NULL; KCM_STATS_INCR(psock->stats.unreserved); if (unlikely(psock->tx_stopped)) { if (psock->done) { /* Deferred free */ list_del(&psock->psock_list); mux->psocks_cnt--; sock_put(psock->sk); fput(psock->sk->sk_socket->file); kmem_cache_free(kcm_psockp, psock); } /* Don't put back on available list */ spin_unlock_bh(&mux->lock); return; } psock_now_avail(psock); spin_unlock_bh(&mux->lock); } static void kcm_report_tx_retry(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; spin_lock_bh(&mux->lock); KCM_STATS_INCR(mux->stats.tx_retries); spin_unlock_bh(&mux->lock); } /* Write any messages ready on the kcm socket. Called with kcm sock lock * held. Return bytes actually sent or error. */ static int kcm_write_msgs(struct kcm_sock *kcm) { unsigned int total_sent = 0; struct sock *sk = &kcm->sk; struct kcm_psock *psock; struct sk_buff *head; int ret = 0; kcm->tx_wait_more = false; psock = kcm->tx_psock; if (unlikely(psock && psock->tx_stopped)) { /* A reserved psock was aborted asynchronously. Unreserve * it and we'll retry the message. */ unreserve_psock(kcm); kcm_report_tx_retry(kcm); if (skb_queue_empty(&sk->sk_write_queue)) return 0; kcm_tx_msg(skb_peek(&sk->sk_write_queue))->started_tx = false; } retry: while ((head = skb_peek(&sk->sk_write_queue))) { struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES, }; struct kcm_tx_msg *txm = kcm_tx_msg(head); struct sk_buff *skb; unsigned int msize; int i; if (!txm->started_tx) { psock = reserve_psock(kcm); if (!psock) goto out; skb = head; txm->frag_offset = 0; txm->sent = 0; txm->started_tx = true; } else { if (WARN_ON(!psock)) { ret = -EINVAL; goto out; } skb = txm->frag_skb; } if (WARN_ON(!skb_shinfo(skb)->nr_frags) || WARN_ON_ONCE(!skb_frag_page(&skb_shinfo(skb)->frags[0]))) { ret = -EINVAL; goto out; } msize = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) msize += skb_frag_size(&skb_shinfo(skb)->frags[i]); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, (const struct bio_vec *)skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags, msize); iov_iter_advance(&msg.msg_iter, txm->frag_offset); do { ret = sock_sendmsg(psock->sk->sk_socket, &msg); if (ret <= 0) { if (ret == -EAGAIN) { /* Save state to try again when there's * write space on the socket */ txm->frag_skb = skb; ret = 0; goto out; } /* Hard failure in sending message, abort this * psock since it has lost framing * synchronization and retry sending the * message from the beginning. */ kcm_abort_tx_psock(psock, ret ? -ret : EPIPE, true); unreserve_psock(kcm); psock = NULL; txm->started_tx = false; kcm_report_tx_retry(kcm); ret = 0; goto retry; } txm->sent += ret; txm->frag_offset += ret; KCM_STATS_ADD(psock->stats.tx_bytes, ret); } while (msg.msg_iter.count > 0); if (skb == head) { if (skb_has_frag_list(skb)) { txm->frag_skb = skb_shinfo(skb)->frag_list; txm->frag_offset = 0; continue; } } else if (skb->next) { txm->frag_skb = skb->next; txm->frag_offset = 0; continue; } /* Successfully sent the whole packet, account for it. */ sk->sk_wmem_queued -= txm->sent; total_sent += txm->sent; skb_dequeue(&sk->sk_write_queue); kfree_skb(head); KCM_STATS_INCR(psock->stats.tx_msgs); } out: if (!head) { /* Done with all queued messages. */ WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); if (psock) unreserve_psock(kcm); } /* Check if write space is available */ sk->sk_write_space(sk); return total_sent ? : ret; } static void kcm_tx_work(struct work_struct *w) { struct kcm_sock *kcm = container_of(w, struct kcm_sock, tx_work); struct sock *sk = &kcm->sk; int err; lock_sock(sk); /* Primarily for SOCK_DGRAM sockets, also handle asynchronous tx * aborts */ err = kcm_write_msgs(kcm); if (err < 0) { /* Hard failure in write, report error on KCM socket */ pr_warn("KCM: Hard failure on kcm_write_msgs %d\n", err); report_csk_error(&kcm->sk, -err); goto out; } /* Primarily for SOCK_SEQPACKET sockets */ if (likely(sk->sk_socket) && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_space(sk); } out: release_sock(sk); } static void kcm_push(struct kcm_sock *kcm) { if (kcm->tx_wait_more) kcm_write_msgs(kcm); } static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); struct sk_buff *skb = NULL, *head = NULL; size_t copy, copied = 0; long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); int eor = (sock->type == SOCK_DGRAM) ? !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err) goto out_error; if (kcm->seq_skb) { /* Previously opened message */ head = kcm->seq_skb; skb = kcm_tx_msg(head)->last_skb; goto start; } /* Call the sk_stream functions to manage the sndbuf mem. */ if (!sk_stream_memory_free(sk)) { kcm_push(kcm); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } if (msg_data_left(msg)) { /* New message, alloc head skb */ head = alloc_skb(0, sk->sk_allocation); while (!head) { kcm_push(kcm); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; head = alloc_skb(0, sk->sk_allocation); } skb = head; /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling * csum_and_copy_from_iter from skb_do_copy_data_nocache. */ skb->ip_summed = CHECKSUM_UNNECESSARY; } start: while (msg_data_left(msg)) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) goto wait_for_memory; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { if (i == MAX_SKB_FRAGS) { struct sk_buff *tskb; tskb = alloc_skb(0, sk->sk_allocation); if (!tskb) goto wait_for_memory; if (head == skb) skb_shinfo(head)->frag_list = tskb; else skb->next = tskb; skb = tskb; skb->ip_summed = CHECKSUM_UNNECESSARY; continue; } merge = false; } if (msg->msg_flags & MSG_SPLICE_PAGES) { copy = msg_data_left(msg); if (!sk_wmem_schedule(sk, copy)) goto wait_for_memory; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) { if (err == -EMSGSIZE) goto wait_for_memory; goto out_error; } copy = err; skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); if (head != skb) head->truesize += copy; } else { copy = min_t(int, msg_data_left(msg), pfrag->size - pfrag->offset); if (!sk_wmem_schedule(sk, copy)) goto wait_for_memory; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, pfrag->offset, copy); if (err) goto out_error; /* Update the skb. */ if (merge) { skb_frag_size_add( &skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy); get_page(pfrag->page); } pfrag->offset += copy; } copied += copy; if (head != skb) { head->len += copy; head->data_len += copy; } continue; wait_for_memory: kcm_push(kcm); err = sk_stream_wait_memory(sk, &timeo); if (err) goto out_error; } if (eor) { bool not_busy = skb_queue_empty(&sk->sk_write_queue); if (head) { /* Message complete, queue it on send buffer */ __skb_queue_tail(&sk->sk_write_queue, head); kcm->seq_skb = NULL; KCM_STATS_INCR(kcm->stats.tx_msgs); } if (msg->msg_flags & MSG_BATCH) { kcm->tx_wait_more = true; } else if (kcm->tx_wait_more || not_busy) { err = kcm_write_msgs(kcm); if (err < 0) { /* We got a hard error in write_msgs but have * already queued this message. Report an error * in the socket, but don't affect return value * from sendmsg */ pr_warn("KCM: Hard failure on kcm_write_msgs\n"); report_csk_error(&kcm->sk, -err); } } } else { /* Message not complete, save state */ partial_message: if (head) { kcm->seq_skb = head; kcm_tx_msg(head)->last_skb = skb; } } KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); return copied; out_error: kcm_push(kcm); if (sock->type == SOCK_SEQPACKET) { /* Wrote some bytes before encountering an * error, return partial success. */ if (copied) goto partial_message; if (head != kcm->seq_skb) kfree_skb(head); } else { kfree_skb(head); kcm->seq_skb = NULL; } err = sk_stream_error(sk, msg->msg_flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN)) sk->sk_write_space(sk); release_sock(sk); return err; } static void kcm_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); if (skb_queue_empty_lockless(&sk->sk_write_queue)) return; lock_sock(sk); kcm_write_msgs(kcm); release_sock(sk); } static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); int err = 0; struct strp_msg *stm; int copied = 0; struct sk_buff *skb; skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; /* Okay, have a message on the receive queue */ stm = strp_msg(skb); if (len > stm->full_len) len = stm->full_len; err = skb_copy_datagram_msg(skb, stm->offset, msg, len); if (err < 0) goto out; copied = len; if (likely(!(flags & MSG_PEEK))) { KCM_STATS_ADD(kcm->stats.rx_bytes, copied); if (copied < stm->full_len) { if (sock->type == SOCK_DGRAM) { /* Truncated message */ msg->msg_flags |= MSG_TRUNC; goto msg_finished; } stm->offset += copied; stm->full_len -= copied; } else { msg_finished: /* Finished with message */ msg->msg_flags |= MSG_EOR; KCM_STATS_INCR(kcm->stats.rx_msgs); } } out: skb_free_datagram(sk, skb); return copied ? : err; } static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); struct strp_msg *stm; int err = 0; ssize_t copied; struct sk_buff *skb; /* Only support splice for SOCKSEQPACKET */ skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto err_out; /* Okay, have a message on the receive queue */ stm = strp_msg(skb); if (len > stm->full_len) len = stm->full_len; copied = skb_splice_bits(skb, sk, stm->offset, pipe, len, flags); if (copied < 0) { err = copied; goto err_out; } KCM_STATS_ADD(kcm->stats.rx_bytes, copied); stm->offset += copied; stm->full_len -= copied; /* We have no way to return MSG_EOR. If all the bytes have been * read we still leave the message in the receive socket buffer. * A subsequent recvmsg needs to be done to return MSG_EOR and * finish reading the message. */ skb_free_datagram(sk, skb); return copied; err_out: skb_free_datagram(sk, skb); return err; } /* kcm sock lock held */ static void kcm_recv_disable(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; if (kcm->rx_disabled) return; spin_lock_bh(&mux->rx_lock); kcm->rx_disabled = 1; /* If a psock is reserved we'll do cleanup in unreserve */ if (!kcm->rx_psock) { if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); } requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); } spin_unlock_bh(&mux->rx_lock); } /* kcm sock lock held */ static void kcm_recv_enable(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; if (!kcm->rx_disabled) return; spin_lock_bh(&mux->rx_lock); kcm->rx_disabled = 0; kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } static int kcm_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct kcm_sock *kcm = kcm_sk(sock->sk); int val, valbool; int err = 0; if (level != SOL_KCM) return -ENOPROTOOPT; if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(int))) return -EFAULT; valbool = val ? 1 : 0; switch (optname) { case KCM_RECV_DISABLE: lock_sock(&kcm->sk); if (valbool) kcm_recv_disable(kcm); else kcm_recv_enable(kcm); release_sock(&kcm->sk); break; default: err = -ENOPROTOOPT; } return err; } static int kcm_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct kcm_sock *kcm = kcm_sk(sock->sk); int val, len; if (level != SOL_KCM) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) { struct kcm_sock *tkcm; struct list_head *head; int index = 0; /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so * we set sk_state, otherwise epoll_wait always returns right away with * EPOLLHUP */ kcm->sk.sk_state = TCP_ESTABLISHED; /* Add to mux's kcm sockets list */ kcm->mux = mux; spin_lock_bh(&mux->lock); head = &mux->kcm_socks; list_for_each_entry(tkcm, &mux->kcm_socks, kcm_sock_list) { if (tkcm->index != index) break; head = &tkcm->kcm_sock_list; index++; } list_add(&kcm->kcm_sock_list, head); kcm->index = index; mux->kcm_socks_cnt++; spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); spin_unlock_bh(&mux->rx_lock); } static int kcm_attach(struct socket *sock, struct socket *csock, struct bpf_prog *prog) { struct kcm_sock *kcm = kcm_sk(sock->sk); struct kcm_mux *mux = kcm->mux; struct sock *csk; struct kcm_psock *psock = NULL, *tpsock; struct list_head *head; int index = 0; static const struct strp_callbacks cb = { .rcv_msg = kcm_rcv_strparser, .parse_msg = kcm_parse_func_strparser, .read_sock_done = kcm_read_sock_done, }; int err = 0; csk = csock->sk; if (!csk) return -EINVAL; lock_sock(csk); /* Only allow TCP sockets to be attached for now */ if ((csk->sk_family != AF_INET && csk->sk_family != AF_INET6) || csk->sk_protocol != IPPROTO_TCP) { err = -EOPNOTSUPP; goto out; } /* Don't allow listeners or closed sockets */ if (csk->sk_state == TCP_LISTEN || csk->sk_state == TCP_CLOSE) { err = -EOPNOTSUPP; goto out; } psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); if (!psock) { err = -ENOMEM; goto out; } psock->mux = mux; psock->sk = csk; psock->bpf_prog = prog; write_lock_bh(&csk->sk_callback_lock); /* Check if sk_user_data is already by KCM or someone else. * Must be done under lock to prevent race conditions. */ if (csk->sk_user_data) { write_unlock_bh(&csk->sk_callback_lock); kmem_cache_free(kcm_psockp, psock); err = -EALREADY; goto out; } err = strp_init(&psock->strp, csk, &cb); if (err) { write_unlock_bh(&csk->sk_callback_lock); kmem_cache_free(kcm_psockp, psock); goto out; } psock->save_data_ready = csk->sk_data_ready; psock->save_write_space = csk->sk_write_space; psock->save_state_change = csk->sk_state_change; csk->sk_user_data = psock; csk->sk_data_ready = psock_data_ready; csk->sk_write_space = psock_write_space; csk->sk_state_change = psock_state_change; write_unlock_bh(&csk->sk_callback_lock); sock_hold(csk); /* Finished initialization, now add the psock to the MUX. */ spin_lock_bh(&mux->lock); head = &mux->psocks; list_for_each_entry(tpsock, &mux->psocks, psock_list) { if (tpsock->index != index) break; head = &tpsock->psock_list; index++; } list_add(&psock->psock_list, head); psock->index = index; KCM_STATS_INCR(mux->stats.psock_attach); mux->psocks_cnt++; psock_now_avail(psock); spin_unlock_bh(&mux->lock); /* Schedule RX work in case there are already bytes queued */ strp_check_rcv(&psock->strp); out: release_sock(csk); return err; } static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info) { struct socket *csock; struct bpf_prog *prog; int err; csock = sockfd_lookup(info->fd, &err); if (!csock) return -ENOENT; prog = bpf_prog_get_type(info->bpf_fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(prog)) { err = PTR_ERR(prog); goto out; } err = kcm_attach(sock, csock, prog); if (err) { bpf_prog_put(prog); goto out; } /* Keep reference on file also */ return 0; out: sockfd_put(csock); return err; } static void kcm_unattach(struct kcm_psock *psock) { struct sock *csk = psock->sk; struct kcm_mux *mux = psock->mux; lock_sock(csk); /* Stop getting callbacks from TCP socket. After this there should * be no way to reserve a kcm for this psock. */ write_lock_bh(&csk->sk_callback_lock); csk->sk_user_data = NULL; csk->sk_data_ready = psock->save_data_ready; csk->sk_write_space = psock->save_write_space; csk->sk_state_change = psock->save_state_change; strp_stop(&psock->strp); if (WARN_ON(psock->rx_kcm)) { write_unlock_bh(&csk->sk_callback_lock); release_sock(csk); return; } spin_lock_bh(&mux->rx_lock); /* Stop receiver activities. After this point psock should not be * able to get onto ready list either through callbacks or work. */ if (psock->ready_rx_msg) { list_del(&psock->psock_ready_list); kfree_skb(psock->ready_rx_msg); psock->ready_rx_msg = NULL; KCM_STATS_INCR(mux->stats.rx_ready_drops); } spin_unlock_bh(&mux->rx_lock); write_unlock_bh(&csk->sk_callback_lock); /* Call strp_done without sock lock */ release_sock(csk); strp_done(&psock->strp); lock_sock(csk); bpf_prog_put(psock->bpf_prog); spin_lock_bh(&mux->lock); aggregate_psock_stats(&psock->stats, &mux->aggregate_psock_stats); save_strp_stats(&psock->strp, &mux->aggregate_strp_stats); KCM_STATS_INCR(mux->stats.psock_unattach); if (psock->tx_kcm) { /* psock was reserved. Just mark it finished and we will clean * up in the kcm paths, we need kcm lock which can not be * acquired here. */ KCM_STATS_INCR(mux->stats.psock_unattach_rsvd); spin_unlock_bh(&mux->lock); /* We are unattaching a socket that is reserved. Abort the * socket since we may be out of sync in sending on it. We need * to do this without the mux lock. */ kcm_abort_tx_psock(psock, EPIPE, false); spin_lock_bh(&mux->lock); if (!psock->tx_kcm) { /* psock now unreserved in window mux was unlocked */ goto no_reserved; } psock->done = 1; /* Commit done before queuing work to process it */ smp_mb(); /* Queue tx work to make sure psock->done is handled */ queue_work(kcm_wq, &psock->tx_kcm->tx_work); spin_unlock_bh(&mux->lock); } else { no_reserved: if (!psock->tx_stopped) list_del(&psock->psock_avail_list); list_del(&psock->psock_list); mux->psocks_cnt--; spin_unlock_bh(&mux->lock); sock_put(csk); fput(csk->sk_socket->file); kmem_cache_free(kcm_psockp, psock); } release_sock(csk); } static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info) { struct kcm_sock *kcm = kcm_sk(sock->sk); struct kcm_mux *mux = kcm->mux; struct kcm_psock *psock; struct socket *csock; struct sock *csk; int err; csock = sockfd_lookup(info->fd, &err); if (!csock) return -ENOENT; csk = csock->sk; if (!csk) { err = -EINVAL; goto out; } err = -ENOENT; spin_lock_bh(&mux->lock); list_for_each_entry(psock, &mux->psocks, psock_list) { if (psock->sk != csk) continue; /* Found the matching psock */ if (psock->unattaching || WARN_ON(psock->done)) { err = -EALREADY; break; } psock->unattaching = 1; spin_unlock_bh(&mux->lock); /* Lower socket lock should already be held */ kcm_unattach(psock); err = 0; goto out; } spin_unlock_bh(&mux->lock); out: sockfd_put(csock); return err; } static struct proto kcm_proto = { .name = "KCM", .owner = THIS_MODULE, .obj_size = sizeof(struct kcm_sock), }; /* Clone a kcm socket. */ static struct file *kcm_clone(struct socket *osock) { struct socket *newsock; struct sock *newsk; newsock = sock_alloc(); if (!newsock) return ERR_PTR(-ENFILE); newsock->type = osock->type; newsock->ops = osock->ops; __module_get(newsock->ops->owner); newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL, &kcm_proto, false); if (!newsk) { sock_release(newsock); return ERR_PTR(-ENOMEM); } sock_init_data(newsock, newsk); init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux); return sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name); } static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int err; switch (cmd) { case SIOCKCMATTACH: { struct kcm_attach info; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; err = kcm_attach_ioctl(sock, &info); break; } case SIOCKCMUNATTACH: { struct kcm_unattach info; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; err = kcm_unattach_ioctl(sock, &info); break; } case SIOCKCMCLONE: { struct kcm_clone info; struct file *file; info.fd = get_unused_fd_flags(0); if (unlikely(info.fd < 0)) return info.fd; file = kcm_clone(sock); if (IS_ERR(file)) { put_unused_fd(info.fd); return PTR_ERR(file); } if (copy_to_user((void __user *)arg, &info, sizeof(info))) { put_unused_fd(info.fd); fput(file); return -EFAULT; } fd_install(info.fd, file); err = 0; break; } default: err = -ENOIOCTLCMD; break; } return err; } static void free_mux(struct rcu_head *rcu) { struct kcm_mux *mux = container_of(rcu, struct kcm_mux, rcu); kmem_cache_free(kcm_muxp, mux); } static void release_mux(struct kcm_mux *mux) { struct kcm_net *knet = mux->knet; struct kcm_psock *psock, *tmp_psock; /* Release psocks */ list_for_each_entry_safe(psock, tmp_psock, &mux->psocks, psock_list) { if (!WARN_ON(psock->unattaching)) kcm_unattach(psock); } if (WARN_ON(mux->psocks_cnt)) return; __skb_queue_purge(&mux->rx_hold_queue); mutex_lock(&knet->mutex); aggregate_mux_stats(&mux->stats, &knet->aggregate_mux_stats); aggregate_psock_stats(&mux->aggregate_psock_stats, &knet->aggregate_psock_stats); aggregate_strp_stats(&mux->aggregate_strp_stats, &knet->aggregate_strp_stats); list_del_rcu(&mux->kcm_mux_list); knet->count--; mutex_unlock(&knet->mutex); call_rcu(&mux->rcu, free_mux); } static void kcm_done(struct kcm_sock *kcm) { struct kcm_mux *mux = kcm->mux; struct sock *sk = &kcm->sk; int socks_cnt; spin_lock_bh(&mux->rx_lock); if (kcm->rx_psock) { /* Cleanup in unreserve_rx_kcm */ WARN_ON(kcm->done); kcm->rx_disabled = 1; kcm->done = 1; spin_unlock_bh(&mux->rx_lock); return; } if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); /* paired with lockless reads in kcm_rfree() */ WRITE_ONCE(kcm->rx_wait, false); } /* Move any pending receive messages to other kcm sockets */ requeue_rx_msgs(mux, &sk->sk_receive_queue); spin_unlock_bh(&mux->rx_lock); if (WARN_ON(sk_rmem_alloc_get(sk))) return; /* Detach from MUX */ spin_lock_bh(&mux->lock); list_del(&kcm->kcm_sock_list); mux->kcm_socks_cnt--; socks_cnt = mux->kcm_socks_cnt; spin_unlock_bh(&mux->lock); if (!socks_cnt) { /* We are done with the mux now. */ release_mux(mux); } WARN_ON(kcm->rx_wait); sock_put(&kcm->sk); } /* Called by kcm_release to close a KCM socket. * If this is the last KCM socket on the MUX, destroy the MUX. */ static int kcm_release(struct socket *sock) { struct sock *sk = sock->sk; struct kcm_sock *kcm; struct kcm_mux *mux; struct kcm_psock *psock; if (!sk) return 0; kcm = kcm_sk(sk); mux = kcm->mux; lock_sock(sk); sock_orphan(sk); kfree_skb(kcm->seq_skb); /* Purge queue under lock to avoid race condition with tx_work trying * to act when queue is nonempty. If tx_work runs after this point * it will just return. */ __skb_queue_purge(&sk->sk_write_queue); /* Set tx_stopped. This is checked when psock is bound to a kcm and we * get a writespace callback. This prevents further work being queued * from the callback (unbinding the psock occurs after canceling work. */ kcm->tx_stopped = 1; release_sock(sk); spin_lock_bh(&mux->lock); if (kcm->tx_wait) { /* Take of tx_wait list, after this point there should be no way * that a psock will be assigned to this kcm. */ list_del(&kcm->wait_psock_list); kcm->tx_wait = false; } spin_unlock_bh(&mux->lock); /* Cancel work. After this point there should be no outside references * to the kcm socket. */ cancel_work_sync(&kcm->tx_work); lock_sock(sk); psock = kcm->tx_psock; if (psock) { /* A psock was reserved, so we need to kill it since it * may already have some bytes queued from a message. We * need to do this after removing kcm from tx_wait list. */ kcm_abort_tx_psock(psock, EPIPE, false); unreserve_psock(kcm); } release_sock(sk); WARN_ON(kcm->tx_wait); WARN_ON(kcm->tx_psock); sock->sk = NULL; kcm_done(kcm); return 0; } static const struct proto_ops kcm_dgram_ops = { .family = PF_KCM, .owner = THIS_MODULE, .release = kcm_release, .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = kcm_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = kcm_setsockopt, .getsockopt = kcm_getsockopt, .sendmsg = kcm_sendmsg, .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, .splice_eof = kcm_splice_eof, }; static const struct proto_ops kcm_seqpacket_ops = { .family = PF_KCM, .owner = THIS_MODULE, .release = kcm_release, .bind = sock_no_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = kcm_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = kcm_setsockopt, .getsockopt = kcm_getsockopt, .sendmsg = kcm_sendmsg, .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, .splice_eof = kcm_splice_eof, .splice_read = kcm_splice_read, }; /* Create proto operation for kcm sockets */ static int kcm_create(struct net *net, struct socket *sock, int protocol, int kern) { struct kcm_net *knet = net_generic(net, kcm_net_id); struct sock *sk; struct kcm_mux *mux; switch (sock->type) { case SOCK_DGRAM: sock->ops = &kcm_dgram_ops; break; case SOCK_SEQPACKET: sock->ops = &kcm_seqpacket_ops; break; default: return -ESOCKTNOSUPPORT; } if (protocol != KCMPROTO_CONNECTED) return -EPROTONOSUPPORT; sk = sk_alloc(net, PF_KCM, GFP_KERNEL, &kcm_proto, kern); if (!sk) return -ENOMEM; /* Allocate a kcm mux, shared between KCM sockets */ mux = kmem_cache_zalloc(kcm_muxp, GFP_KERNEL); if (!mux) { sk_free(sk); return -ENOMEM; } spin_lock_init(&mux->lock); spin_lock_init(&mux->rx_lock); INIT_LIST_HEAD(&mux->kcm_socks); INIT_LIST_HEAD(&mux->kcm_rx_waiters); INIT_LIST_HEAD(&mux->kcm_tx_waiters); INIT_LIST_HEAD(&mux->psocks); INIT_LIST_HEAD(&mux->psocks_ready); INIT_LIST_HEAD(&mux->psocks_avail); mux->knet = knet; /* Add new MUX to list */ mutex_lock(&knet->mutex); list_add_rcu(&mux->kcm_mux_list, &knet->mux_list); knet->count++; mutex_unlock(&knet->mutex); skb_queue_head_init(&mux->rx_hold_queue); /* Init KCM socket */ sock_init_data(sock, sk); init_kcm_sock(kcm_sk(sk), mux); return 0; } static const struct net_proto_family kcm_family_ops = { .family = PF_KCM, .create = kcm_create, .owner = THIS_MODULE, }; static __net_init int kcm_init_net(struct net *net) { struct kcm_net *knet = net_generic(net, kcm_net_id); INIT_LIST_HEAD_RCU(&knet->mux_list); mutex_init(&knet->mutex); return 0; } static __net_exit void kcm_exit_net(struct net *net) { struct kcm_net *knet = net_generic(net, kcm_net_id); /* All KCM sockets should be closed at this point, which should mean * that all multiplexors and psocks have been destroyed. */ WARN_ON(!list_empty(&knet->mux_list)); mutex_destroy(&knet->mutex); } static struct pernet_operations kcm_net_ops = { .init = kcm_init_net, .exit = kcm_exit_net, .id = &kcm_net_id, .size = sizeof(struct kcm_net), }; static int __init kcm_init(void) { int err = -ENOMEM; kcm_muxp = KMEM_CACHE(kcm_mux, SLAB_HWCACHE_ALIGN); if (!kcm_muxp) goto fail; kcm_psockp = KMEM_CACHE(kcm_psock, SLAB_HWCACHE_ALIGN); if (!kcm_psockp) goto fail; kcm_wq = create_singlethread_workqueue("kkcmd"); if (!kcm_wq) goto fail; err = proto_register(&kcm_proto, 1); if (err) goto fail; err = register_pernet_device(&kcm_net_ops); if (err) goto net_ops_fail; err = sock_register(&kcm_family_ops); if (err) goto sock_register_fail; err = kcm_proc_init(); if (err) goto proc_init_fail; return 0; proc_init_fail: sock_unregister(PF_KCM); sock_register_fail: unregister_pernet_device(&kcm_net_ops); net_ops_fail: proto_unregister(&kcm_proto); fail: kmem_cache_destroy(kcm_muxp); kmem_cache_destroy(kcm_psockp); if (kcm_wq) destroy_workqueue(kcm_wq); return err; } static void __exit kcm_exit(void) { kcm_proc_exit(); sock_unregister(PF_KCM); unregister_pernet_device(&kcm_net_ops); proto_unregister(&kcm_proto); destroy_workqueue(kcm_wq); kmem_cache_destroy(kcm_muxp); kmem_cache_destroy(kcm_psockp); } module_init(kcm_init); module_exit(kcm_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("KCM (Kernel Connection Multiplexor) sockets"); MODULE_ALIAS_NETPROTO(PF_KCM); |
| 3920 6349 16695 124 6424 6698 571 6431 31 31 2020 16790 16772 1990 4656 2039 2732 4652 4 4893 4901 4892 4892 1 1 1 1 394 394 3917 15939 2548 2548 2543 98 1 40 130 34 139 4 2396 949 288 4 13 15 13 4 16 6998 6950 5479 3293 1701 742 30 1997 772 716 643 433 175 167 624 685 684 21 21 21 21 3 682 716 719 685 683 103 365 14379 877 3310 14080 363 364 13404 13440 363 6998 1 6349 6345 6349 6347 6354 6345 6338 2725 2227 1456 1 124 123 35 124 124 124 124 124 6641 1689 6641 6424 6440 78 110 109 22 108 109 109 110 6345 364 361 363 1 360 363 6376 1084 1080 1028 1026 934 247 247 242 31 31 124 209 31 155 196 196 183 249 217 31 249 30 30 27 99 99 33 2980 267 2730 2980 7 5 6 3002 3008 2978 29 288 127 128 4590 4595 6349 6349 4985 6349 2459 3788 4944 6349 4992 1990 1990 2 1987 1987 6349 6349 98 97 21 301 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset = 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 1728 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib6 #if !defined(_TRACE_FIB6_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB6_H #include <linux/in6.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib6_table_lookup, TP_PROTO(const struct net *net, const struct fib6_result *res, struct fib6_table *table, const struct flowi6 *flp), TP_ARGS(net, res, table, flp), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 16 ) __array( __u8, dst, 16 ) __field( u16, sport ) __field( u16, dport ) __field( u8, proto ) __field( u8, rt_type ) __array( char, name, IFNAMSIZ ) __array( __u8, gw, 16 ) ), TP_fast_assign( struct in6_addr *in6; __entry->tb_id = table->tb6_id; __entry->err = ip6_rt_type_to_error(res->fib6_type); __entry->oif = flp->flowi6_oif; __entry->iif = flp->flowi6_iif; __entry->tos = ip6_tclass(flp->flowlabel); __entry->scope = flp->flowi6_scope; __entry->flags = flp->flowi6_flags; in6 = (struct in6_addr *)__entry->src; *in6 = flp->saddr; in6 = (struct in6_addr *)__entry->dst; *in6 = flp->daddr; __entry->proto = flp->flowi6_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl6_sport); __entry->dport = ntohs(flp->fl6_dport); } else { __entry->sport = 0; __entry->dport = 0; } if (res->nh && res->nh->fib_nh_dev) { strscpy(__entry->name, res->nh->fib_nh_dev->name, IFNAMSIZ); } else { strcpy(__entry->name, "-"); } if (res->f6i == net->ipv6.fib6_null_entry) { in6 = (struct in6_addr *)__entry->gw; *in6 = in6addr_any; } else if (res->nh) { in6 = (struct in6_addr *)__entry->gw; *in6 = res->nh->fib_nh_gw6; } ), TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u tos %d scope %d flags %x ==> dev %s gw %pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->tos, __entry->scope, __entry->flags, __entry->name, __entry->gw, __entry->err) ); #endif /* _TRACE_FIB6_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 39 48 12 2 36 1 4 5 4 4 5 3 5 2 4 2 1 1 4 4 3 4 1 10 2 2 6 5 1 1 8 2 2 4 1 41 2 2 1 1 34 1 1 4 2 2 1 76 1 72 3 3 3 1 68 76 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Crypto user configuration API. * * Copyright (C) 2011 secunet Security Networks AG * Copyright (C) 2011 Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/module.h> #include <linux/crypto.h> #include <linux/cryptouser.h> #include <linux/sched.h> #include <linux/security.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <crypto/internal/skcipher.h> #include <crypto/internal/rng.h> #include <crypto/akcipher.h> #include <crypto/kpp.h> #include "internal.h" #define null_terminated(x) (strnlen(x, sizeof(x)) < sizeof(x)) static DEFINE_MUTEX(crypto_cfg_mutex); struct crypto_dump_info { struct sk_buff *in_skb; struct sk_buff *out_skb; u32 nlmsg_seq; u16 nlmsg_flags; }; static struct crypto_alg *crypto_alg_match(struct crypto_user_alg *p, int exact) { struct crypto_alg *q, *alg = NULL; down_read(&crypto_alg_sem); list_for_each_entry(q, &crypto_alg_list, cra_list) { int match = 0; if (crypto_is_larval(q)) continue; if ((q->cra_flags ^ p->cru_type) & p->cru_mask) continue; if (strlen(p->cru_driver_name)) match = !strcmp(q->cra_driver_name, p->cru_driver_name); else if (!exact) match = !strcmp(q->cra_name, p->cru_name); if (!match) continue; if (unlikely(!crypto_mod_get(q))) continue; alg = q; break; } up_read(&crypto_alg_sem); return alg; } static int crypto_report_cipher(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_cipher rcipher; memset(&rcipher, 0, sizeof(rcipher)); strscpy(rcipher.type, "cipher", sizeof(rcipher.type)); rcipher.blocksize = alg->cra_blocksize; rcipher.min_keysize = alg->cra_cipher.cia_min_keysize; rcipher.max_keysize = alg->cra_cipher.cia_max_keysize; return nla_put(skb, CRYPTOCFGA_REPORT_CIPHER, sizeof(rcipher), &rcipher); } static int crypto_report_comp(struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_comp rcomp; memset(&rcomp, 0, sizeof(rcomp)); strscpy(rcomp.type, "compression", sizeof(rcomp.type)); return nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS, sizeof(rcomp), &rcomp); } static int crypto_report_one(struct crypto_alg *alg, struct crypto_user_alg *ualg, struct sk_buff *skb) { memset(ualg, 0, sizeof(*ualg)); strscpy(ualg->cru_name, alg->cra_name, sizeof(ualg->cru_name)); strscpy(ualg->cru_driver_name, alg->cra_driver_name, sizeof(ualg->cru_driver_name)); strscpy(ualg->cru_module_name, module_name(alg->cra_module), sizeof(ualg->cru_module_name)); ualg->cru_type = 0; ualg->cru_mask = 0; ualg->cru_flags = alg->cra_flags; ualg->cru_refcnt = refcount_read(&alg->cra_refcnt); if (nla_put_u32(skb, CRYPTOCFGA_PRIORITY_VAL, alg->cra_priority)) goto nla_put_failure; if (alg->cra_flags & CRYPTO_ALG_LARVAL) { struct crypto_report_larval rl; memset(&rl, 0, sizeof(rl)); strscpy(rl.type, "larval", sizeof(rl.type)); if (nla_put(skb, CRYPTOCFGA_REPORT_LARVAL, sizeof(rl), &rl)) goto nla_put_failure; goto out; } if (alg->cra_type && alg->cra_type->report) { if (alg->cra_type->report(skb, alg)) goto nla_put_failure; goto out; } switch (alg->cra_flags & (CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_LARVAL)) { case CRYPTO_ALG_TYPE_CIPHER: if (crypto_report_cipher(skb, alg)) goto nla_put_failure; break; case CRYPTO_ALG_TYPE_COMPRESS: if (crypto_report_comp(skb, alg)) goto nla_put_failure; break; } out: return 0; nla_put_failure: return -EMSGSIZE; } static int crypto_report_alg(struct crypto_alg *alg, struct crypto_dump_info *info) { struct sk_buff *in_skb = info->in_skb; struct sk_buff *skb = info->out_skb; struct nlmsghdr *nlh; struct crypto_user_alg *ualg; int err = 0; nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, info->nlmsg_seq, CRYPTO_MSG_GETALG, sizeof(*ualg), info->nlmsg_flags); if (!nlh) { err = -EMSGSIZE; goto out; } ualg = nlmsg_data(nlh); err = crypto_report_one(alg, ualg, skb); if (err) { nlmsg_cancel(skb, nlh); goto out; } nlmsg_end(skb, nlh); out: return err; } static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, struct nlattr **attrs) { struct net *net = sock_net(in_skb->sk); struct crypto_user_alg *p = nlmsg_data(in_nlh); struct crypto_alg *alg; struct sk_buff *skb; struct crypto_dump_info info; int err; if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) return -EINVAL; alg = crypto_alg_match(p, 0); if (!alg) return -ENOENT; err = -ENOMEM; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) goto drop_alg; info.in_skb = in_skb; info.out_skb = skb; info.nlmsg_seq = in_nlh->nlmsg_seq; info.nlmsg_flags = 0; err = crypto_report_alg(alg, &info); drop_alg: crypto_mod_put(alg); if (err) { kfree_skb(skb); return err; } return nlmsg_unicast(net->crypto_nlsk, skb, NETLINK_CB(in_skb).portid); } static int crypto_dump_report(struct sk_buff *skb, struct netlink_callback *cb) { const size_t start_pos = cb->args[0]; size_t pos = 0; struct crypto_dump_info info; struct crypto_alg *alg; int res; info.in_skb = cb->skb; info.out_skb = skb; info.nlmsg_seq = cb->nlh->nlmsg_seq; info.nlmsg_flags = NLM_F_MULTI; down_read(&crypto_alg_sem); list_for_each_entry(alg, &crypto_alg_list, cra_list) { if (pos >= start_pos) { res = crypto_report_alg(alg, &info); if (res == -EMSGSIZE) break; if (res) goto out; } pos++; } cb->args[0] = pos; res = skb->len; out: up_read(&crypto_alg_sem); return res; } static int crypto_dump_report_done(struct netlink_callback *cb) { return 0; } static int crypto_update_alg(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { struct crypto_alg *alg; struct crypto_user_alg *p = nlmsg_data(nlh); struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; LIST_HEAD(list); if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) return -EINVAL; if (priority && !strlen(p->cru_driver_name)) return -EINVAL; alg = crypto_alg_match(p, 1); if (!alg) return -ENOENT; down_write(&crypto_alg_sem); crypto_remove_spawns(alg, &list, NULL); if (priority) alg->cra_priority = nla_get_u32(priority); up_write(&crypto_alg_sem); crypto_mod_put(alg); crypto_remove_final(&list); return 0; } static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { struct crypto_alg *alg; struct crypto_user_alg *p = nlmsg_data(nlh); int err; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) return -EINVAL; alg = crypto_alg_match(p, 1); if (!alg) return -ENOENT; /* We can not unregister core algorithms such as aes-generic. * We would loose the reference in the crypto_alg_list to this algorithm * if we try to unregister. Unregistering such an algorithm without * removing the module is not possible, so we restrict to crypto * instances that are build from templates. */ err = -EINVAL; if (!(alg->cra_flags & CRYPTO_ALG_INSTANCE)) goto drop_alg; err = -EBUSY; if (refcount_read(&alg->cra_refcnt) > 2) goto drop_alg; crypto_unregister_instance((struct crypto_instance *)alg); err = 0; drop_alg: crypto_mod_put(alg); return err; } static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { int exact = 0; const char *name; struct crypto_alg *alg; struct crypto_user_alg *p = nlmsg_data(nlh); struct nlattr *priority = attrs[CRYPTOCFGA_PRIORITY_VAL]; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!null_terminated(p->cru_name) || !null_terminated(p->cru_driver_name)) return -EINVAL; if (strlen(p->cru_driver_name)) exact = 1; if (priority && !exact) return -EINVAL; alg = crypto_alg_match(p, exact); if (alg) { crypto_mod_put(alg); return -EEXIST; } if (strlen(p->cru_driver_name)) name = p->cru_driver_name; else name = p->cru_name; alg = crypto_alg_mod_lookup(name, p->cru_type, p->cru_mask); if (IS_ERR(alg)) return PTR_ERR(alg); down_write(&crypto_alg_sem); if (priority) alg->cra_priority = nla_get_u32(priority); up_write(&crypto_alg_sem); crypto_mod_put(alg); return 0; } static int crypto_del_rng(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; return crypto_del_default_rng(); } static int crypto_reportstat(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, struct nlattr **attrs) { /* No longer supported */ return -ENOTSUPP; } #define MSGSIZE(type) sizeof(struct type) static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = { [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0, [CRYPTO_MSG_GETSTAT - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), }; static const struct nla_policy crypto_policy[CRYPTOCFGA_MAX+1] = { [CRYPTOCFGA_PRIORITY_VAL] = { .type = NLA_U32}, }; #undef MSGSIZE static const struct crypto_link { int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **); int (*dump)(struct sk_buff *, struct netlink_callback *); int (*done)(struct netlink_callback *); } crypto_dispatch[CRYPTO_NR_MSGTYPES] = { [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = { .doit = crypto_add_alg}, [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = { .doit = crypto_del_alg}, [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = { .doit = crypto_update_alg}, [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = { .doit = crypto_report, .dump = crypto_dump_report, .done = crypto_dump_report_done}, [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = { .doit = crypto_del_rng }, [CRYPTO_MSG_GETSTAT - CRYPTO_MSG_BASE] = { .doit = crypto_reportstat}, }; static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *attrs[CRYPTOCFGA_MAX+1]; const struct crypto_link *link; int type, err; type = nlh->nlmsg_type; if (type > CRYPTO_MSG_MAX) return -EINVAL; type -= CRYPTO_MSG_BASE; link = &crypto_dispatch[type]; if ((type == (CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE) && (nlh->nlmsg_flags & NLM_F_DUMP))) { struct crypto_alg *alg; unsigned long dump_alloc = 0; if (link->dump == NULL) return -EINVAL; down_read(&crypto_alg_sem); list_for_each_entry(alg, &crypto_alg_list, cra_list) dump_alloc += CRYPTO_REPORT_MAXSIZE; up_read(&crypto_alg_sem); { struct netlink_dump_control c = { .dump = link->dump, .done = link->done, .min_dump_alloc = min(dump_alloc, 65535UL), }; err = netlink_dump_start(net->crypto_nlsk, skb, nlh, &c); } return err; } err = nlmsg_parse_deprecated(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX, crypto_policy, extack); if (err < 0) return err; if (link->doit == NULL) return -EINVAL; return link->doit(skb, nlh, attrs); } static void crypto_netlink_rcv(struct sk_buff *skb) { mutex_lock(&crypto_cfg_mutex); netlink_rcv_skb(skb, &crypto_user_rcv_msg); mutex_unlock(&crypto_cfg_mutex); } static int __net_init crypto_netlink_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = crypto_netlink_rcv, }; net->crypto_nlsk = netlink_kernel_create(net, NETLINK_CRYPTO, &cfg); return net->crypto_nlsk == NULL ? -ENOMEM : 0; } static void __net_exit crypto_netlink_exit(struct net *net) { netlink_kernel_release(net->crypto_nlsk); net->crypto_nlsk = NULL; } static struct pernet_operations crypto_netlink_net_ops = { .init = crypto_netlink_init, .exit = crypto_netlink_exit, }; static int __init crypto_user_init(void) { return register_pernet_subsys(&crypto_netlink_net_ops); } static void __exit crypto_user_exit(void) { unregister_pernet_subsys(&crypto_netlink_net_ops); } module_init(crypto_user_init); module_exit(crypto_user_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_DESCRIPTION("Crypto userspace configuration API"); MODULE_ALIAS("net-pf-16-proto-21"); |
| 5 3 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * connector.c * * 2004+ Copyright (c) Evgeniy Polyakov <zbr@ioremap.net> * All rights reserved. */ #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/list.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <linux/moduleparam.h> #include <linux/connector.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/spinlock.h> #include <net/sock.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>"); MODULE_DESCRIPTION("Generic userspace <-> kernelspace connector."); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_CONNECTOR); static struct cn_dev cdev; static int cn_already_initialized; /* * Sends mult (multiple) cn_msg at a time. * * msg->seq and msg->ack are used to determine message genealogy. * When someone sends message it puts there locally unique sequence * and random acknowledge numbers. Sequence number may be copied into * nlmsghdr->nlmsg_seq too. * * Sequence number is incremented with each message to be sent. * * If we expect a reply to our message then the sequence number in * received message MUST be the same as in original message, and * acknowledge number MUST be the same + 1. * * If we receive a message and its sequence number is not equal to the * one we are expecting then it is a new message. * * If we receive a message and its sequence number is the same as one * we are expecting but it's acknowledgement number is not equal to * the acknowledgement number in the original message + 1, then it is * a new message. * * If msg->len != len, then additional cn_msg messages are expected following * the first msg. * * The message is sent to, the portid if given, the group if given, both if * both, or if both are zero then the group is looked up and sent there. */ int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 __group, gfp_t gfp_mask, netlink_filter_fn filter, void *filter_data) { struct cn_callback_entry *__cbq; unsigned int size; struct sk_buff *skb; struct nlmsghdr *nlh; struct cn_msg *data; struct cn_dev *dev = &cdev; u32 group = 0; int found = 0; if (portid || __group) { group = __group; } else { spin_lock_bh(&dev->cbdev->queue_lock); list_for_each_entry(__cbq, &dev->cbdev->queue_list, callback_entry) { if (cn_cb_equal(&__cbq->id.id, &msg->id)) { found = 1; group = __cbq->group; break; } } spin_unlock_bh(&dev->cbdev->queue_lock); if (!found) return -ENODEV; } if (!portid && !netlink_has_listeners(dev->nls, group)) return -ESRCH; size = sizeof(*msg) + len; skb = nlmsg_new(size, gfp_mask); if (!skb) return -ENOMEM; nlh = nlmsg_put(skb, 0, msg->seq, NLMSG_DONE, size, 0); if (!nlh) { kfree_skb(skb); return -EMSGSIZE; } data = nlmsg_data(nlh); memcpy(data, msg, size); NETLINK_CB(skb).dst_group = group; if (group) return netlink_broadcast_filtered(dev->nls, skb, portid, group, gfp_mask, filter, (void *)filter_data); return netlink_unicast(dev->nls, skb, portid, !gfpflags_allow_blocking(gfp_mask)); } EXPORT_SYMBOL_GPL(cn_netlink_send_mult); /* same as cn_netlink_send_mult except msg->len is used for len */ int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 __group, gfp_t gfp_mask) { return cn_netlink_send_mult(msg, msg->len, portid, __group, gfp_mask, NULL, NULL); } EXPORT_SYMBOL_GPL(cn_netlink_send); /* * Callback helper - queues work and setup destructor for given data. */ static int cn_call_callback(struct sk_buff *skb) { struct nlmsghdr *nlh; struct cn_callback_entry *i, *cbq = NULL; struct cn_dev *dev = &cdev; struct cn_msg *msg = nlmsg_data(nlmsg_hdr(skb)); struct netlink_skb_parms *nsp = &NETLINK_CB(skb); int err = -ENODEV; /* verify msg->len is within skb */ nlh = nlmsg_hdr(skb); if (nlh->nlmsg_len < NLMSG_HDRLEN + sizeof(struct cn_msg) + msg->len) return -EINVAL; spin_lock_bh(&dev->cbdev->queue_lock); list_for_each_entry(i, &dev->cbdev->queue_list, callback_entry) { if (cn_cb_equal(&i->id.id, &msg->id)) { refcount_inc(&i->refcnt); cbq = i; break; } } spin_unlock_bh(&dev->cbdev->queue_lock); if (cbq != NULL) { cbq->callback(msg, nsp); kfree_skb(skb); cn_queue_release_callback(cbq); err = 0; } return err; } /* * Allow non-root access for NETLINK_CONNECTOR family having CN_IDX_PROC * multicast group. */ static int cn_bind(struct net *net, int group) { unsigned long groups = (unsigned long) group; if (ns_capable(net->user_ns, CAP_NET_ADMIN)) return 0; if (test_bit(CN_IDX_PROC - 1, &groups)) return 0; return -EPERM; } static void cn_release(struct sock *sk, unsigned long *groups) { if (groups && test_bit(CN_IDX_PROC - 1, groups)) { kfree(sk->sk_user_data); sk->sk_user_data = NULL; } } /* * Main netlink receiving function. * * It checks skb, netlink header and msg sizes, and calls callback helper. */ static void cn_rx_skb(struct sk_buff *skb) { struct nlmsghdr *nlh; int len, err; if (skb->len >= NLMSG_HDRLEN) { nlh = nlmsg_hdr(skb); len = nlmsg_len(nlh); if (len < (int)sizeof(struct cn_msg) || skb->len < nlh->nlmsg_len || len > CONNECTOR_MAX_MSG_SIZE) return; err = cn_call_callback(skb_get(skb)); if (err < 0) kfree_skb(skb); } } /* * Callback add routing - adds callback with given ID and name. * If there is registered callback with the same ID it will not be added. * * May sleep. */ int cn_add_callback(const struct cb_id *id, const char *name, void (*callback)(struct cn_msg *, struct netlink_skb_parms *)) { struct cn_dev *dev = &cdev; if (!cn_already_initialized) return -EAGAIN; return cn_queue_add_callback(dev->cbdev, name, id, callback); } EXPORT_SYMBOL_GPL(cn_add_callback); /* * Callback remove routing - removes callback * with given ID. * If there is no registered callback with given * ID nothing happens. * * May sleep while waiting for reference counter to become zero. */ void cn_del_callback(const struct cb_id *id) { struct cn_dev *dev = &cdev; cn_queue_del_callback(dev->cbdev, id); } EXPORT_SYMBOL_GPL(cn_del_callback); static int __maybe_unused cn_proc_show(struct seq_file *m, void *v) { struct cn_queue_dev *dev = cdev.cbdev; struct cn_callback_entry *cbq; seq_printf(m, "Name ID\n"); spin_lock_bh(&dev->queue_lock); list_for_each_entry(cbq, &dev->queue_list, callback_entry) { seq_printf(m, "%-15s %u:%u\n", cbq->id.name, cbq->id.id.idx, cbq->id.id.val); } spin_unlock_bh(&dev->queue_lock); return 0; } static int cn_init(void) { struct cn_dev *dev = &cdev; struct netlink_kernel_cfg cfg = { .groups = CN_NETLINK_USERS + 0xf, .input = cn_rx_skb, .flags = NL_CFG_F_NONROOT_RECV, .bind = cn_bind, .release = cn_release, }; dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, &cfg); if (!dev->nls) return -EIO; dev->cbdev = cn_queue_alloc_dev("cqueue", dev->nls); if (!dev->cbdev) { netlink_kernel_release(dev->nls); return -EINVAL; } cn_already_initialized = 1; proc_create_single("connector", S_IRUGO, init_net.proc_net, cn_proc_show); return 0; } static void cn_fini(void) { struct cn_dev *dev = &cdev; cn_already_initialized = 0; remove_proc_entry("connector", init_net.proc_net); cn_queue_free_dev(dev->cbdev); netlink_kernel_release(dev->nls); } subsys_initcall(cn_init); module_exit(cn_fini); |
| 4 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 | /* * Copyright (c) 2006 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/percpu.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include "rds.h" #include "ib.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_ib_statistics, rds_ib_stats); static const char *const rds_ib_stat_names[] = { "ib_connect_raced", "ib_listen_closed_stale", "ib_evt_handler_call", "ib_tasklet_call", "ib_tx_cq_event", "ib_tx_ring_full", "ib_tx_throttle", "ib_tx_sg_mapping_failure", "ib_tx_stalled", "ib_tx_credit_updates", "ib_rx_cq_event", "ib_rx_ring_empty", "ib_rx_refill_from_cq", "ib_rx_refill_from_thread", "ib_rx_alloc_limit", "ib_rx_total_frags", "ib_rx_total_incs", "ib_rx_credit_updates", "ib_ack_sent", "ib_ack_send_failure", "ib_ack_send_delayed", "ib_ack_send_piggybacked", "ib_ack_received", "ib_rdma_mr_8k_alloc", "ib_rdma_mr_8k_free", "ib_rdma_mr_8k_used", "ib_rdma_mr_8k_pool_flush", "ib_rdma_mr_8k_pool_wait", "ib_rdma_mr_8k_pool_depleted", "ib_rdma_mr_1m_alloc", "ib_rdma_mr_1m_free", "ib_rdma_mr_1m_used", "ib_rdma_mr_1m_pool_flush", "ib_rdma_mr_1m_pool_wait", "ib_rdma_mr_1m_pool_depleted", "ib_rdma_mr_8k_reused", "ib_rdma_mr_1m_reused", "ib_atomic_cswp", "ib_atomic_fadd", }; unsigned int rds_ib_stats_info_copy(struct rds_info_iterator *iter, unsigned int avail) { struct rds_ib_statistics stats = {0, }; uint64_t *src; uint64_t *sum; size_t i; int cpu; if (avail < ARRAY_SIZE(rds_ib_stat_names)) goto out; for_each_online_cpu(cpu) { src = (uint64_t *)&(per_cpu(rds_ib_stats, cpu)); sum = (uint64_t *)&stats; for (i = 0; i < sizeof(stats) / sizeof(uint64_t); i++) *(sum++) += *(src++); } rds_stats_info_copy(iter, (uint64_t *)&stats, rds_ib_stat_names, ARRAY_SIZE(rds_ib_stat_names)); out: return ARRAY_SIZE(rds_ib_stat_names); } |
| 9 6 4 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | // SPDX-License-Identifier: GPL-2.0 /* * Implement the manual drop-all-pagecache function */ #include <linux/pagemap.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/writeback.h> #include <linux/sysctl.h> #include <linux/gfp.h> #include <linux/swap.h> #include "internal.h" /* A global variable is a bit ugly, but it keeps the code simple */ int sysctl_drop_caches; static void drop_pagecache_sb(struct super_block *sb, void *unused) { struct inode *inode, *toput_inode = NULL; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); /* * We must skip inodes in unusual state. We may also skip * inodes without pages but we deliberately won't in case * we need to reschedule to avoid softlockups. */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || (mapping_empty(inode->i_mapping) && !need_resched())) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(toput_inode); } int drop_caches_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (ret) return ret; if (write) { static int stfu; if (sysctl_drop_caches & 1) { lru_add_drain_all(); iterate_supers(drop_pagecache_sb, NULL); count_vm_event(DROP_PAGECACHE); } if (sysctl_drop_caches & 2) { drop_slab(); count_vm_event(DROP_SLAB); } if (!stfu) { pr_info("%s (%d): drop_caches: %d\n", current->comm, task_pid_nr(current), sysctl_drop_caches); } stfu |= sysctl_drop_caches & 4; } return 0; } |
| 3 2 18 22 119 109 5 5 110 5 4 109 5 1 99 2 11 34 113 11 31 114 5 11 20 21 1 23 1 23 24 7 7 5 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_STR_HASH_H #define _BCACHEFS_STR_HASH_H #include "btree_iter.h" #include "btree_update.h" #include "checksum.h" #include "error.h" #include "inode.h" #include "siphash.h" #include "subvolume.h" #include "super.h" #include <linux/crc32c.h> #include <crypto/hash.h> #include <crypto/sha2.h> static inline enum bch_str_hash_type bch2_str_hash_opt_to_type(struct bch_fs *c, enum bch_str_hash_opts opt) { switch (opt) { case BCH_STR_HASH_OPT_crc32c: return BCH_STR_HASH_crc32c; case BCH_STR_HASH_OPT_crc64: return BCH_STR_HASH_crc64; case BCH_STR_HASH_OPT_siphash: return c->sb.features & (1ULL << BCH_FEATURE_new_siphash) ? BCH_STR_HASH_siphash : BCH_STR_HASH_siphash_old; default: BUG(); } } struct bch_hash_info { u8 type; /* * For crc32 or crc64 string hashes the first key value of * the siphash_key (k0) is used as the key. */ SIPHASH_KEY siphash_key; }; static inline struct bch_hash_info bch2_hash_info_init(struct bch_fs *c, const struct bch_inode_unpacked *bi) { /* XXX ick */ struct bch_hash_info info = { .type = (bi->bi_flags >> INODE_STR_HASH_OFFSET) & ~(~0U << INODE_STR_HASH_BITS), .siphash_key = { .k0 = bi->bi_hash_seed } }; if (unlikely(info.type == BCH_STR_HASH_siphash_old)) { SHASH_DESC_ON_STACK(desc, c->sha256); u8 digest[SHA256_DIGEST_SIZE]; desc->tfm = c->sha256; crypto_shash_digest(desc, (void *) &bi->bi_hash_seed, sizeof(bi->bi_hash_seed), digest); memcpy(&info.siphash_key, digest, sizeof(info.siphash_key)); } return info; } struct bch_str_hash_ctx { union { u32 crc32c; u64 crc64; SIPHASH_CTX siphash; }; }; static inline void bch2_str_hash_init(struct bch_str_hash_ctx *ctx, const struct bch_hash_info *info) { switch (info->type) { case BCH_STR_HASH_crc32c: ctx->crc32c = crc32c(~0, &info->siphash_key.k0, sizeof(info->siphash_key.k0)); break; case BCH_STR_HASH_crc64: ctx->crc64 = crc64_be(~0, &info->siphash_key.k0, sizeof(info->siphash_key.k0)); break; case BCH_STR_HASH_siphash_old: case BCH_STR_HASH_siphash: SipHash24_Init(&ctx->siphash, &info->siphash_key); break; default: BUG(); } } static inline void bch2_str_hash_update(struct bch_str_hash_ctx *ctx, const struct bch_hash_info *info, const void *data, size_t len) { switch (info->type) { case BCH_STR_HASH_crc32c: ctx->crc32c = crc32c(ctx->crc32c, data, len); break; case BCH_STR_HASH_crc64: ctx->crc64 = crc64_be(ctx->crc64, data, len); break; case BCH_STR_HASH_siphash_old: case BCH_STR_HASH_siphash: SipHash24_Update(&ctx->siphash, data, len); break; default: BUG(); } } static inline u64 bch2_str_hash_end(struct bch_str_hash_ctx *ctx, const struct bch_hash_info *info) { switch (info->type) { case BCH_STR_HASH_crc32c: return ctx->crc32c; case BCH_STR_HASH_crc64: return ctx->crc64 >> 1; case BCH_STR_HASH_siphash_old: case BCH_STR_HASH_siphash: return SipHash24_End(&ctx->siphash) >> 1; default: BUG(); } } struct bch_hash_desc { enum btree_id btree_id; u8 key_type; u64 (*hash_key)(const struct bch_hash_info *, const void *); u64 (*hash_bkey)(const struct bch_hash_info *, struct bkey_s_c); bool (*cmp_key)(struct bkey_s_c, const void *); bool (*cmp_bkey)(struct bkey_s_c, struct bkey_s_c); bool (*is_visible)(subvol_inum inum, struct bkey_s_c); }; static inline bool is_visible_key(struct bch_hash_desc desc, subvol_inum inum, struct bkey_s_c k) { return k.k->type == desc.key_type && (!desc.is_visible || !inum.inum || desc.is_visible(inum, k)); } static __always_inline struct bkey_s_c bch2_hash_lookup_in_snapshot(struct btree_trans *trans, struct btree_iter *iter, const struct bch_hash_desc desc, const struct bch_hash_info *info, subvol_inum inum, const void *key, enum btree_iter_update_trigger_flags flags, u32 snapshot) { struct bkey_s_c k; int ret; for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id, SPOS(inum.inum, desc.hash_key(info, key), snapshot), POS(inum.inum, U64_MAX), BTREE_ITER_slots|flags, k, ret) { if (is_visible_key(desc, inum, k)) { if (!desc.cmp_key(k, key)) return k; } else if (k.k->type == KEY_TYPE_hash_whiteout) { ; } else { /* hole, not found */ break; } } bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret ?: -BCH_ERR_ENOENT_str_hash_lookup); } static __always_inline struct bkey_s_c bch2_hash_lookup(struct btree_trans *trans, struct btree_iter *iter, const struct bch_hash_desc desc, const struct bch_hash_info *info, subvol_inum inum, const void *key, enum btree_iter_update_trigger_flags flags) { u32 snapshot; int ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot); if (ret) return bkey_s_c_err(ret); return bch2_hash_lookup_in_snapshot(trans, iter, desc, info, inum, key, flags, snapshot); } static __always_inline int bch2_hash_hole(struct btree_trans *trans, struct btree_iter *iter, const struct bch_hash_desc desc, const struct bch_hash_info *info, subvol_inum inum, const void *key) { struct bkey_s_c k; u32 snapshot; int ret; ret = bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot); if (ret) return ret; for_each_btree_key_upto_norestart(trans, *iter, desc.btree_id, SPOS(inum.inum, desc.hash_key(info, key), snapshot), POS(inum.inum, U64_MAX), BTREE_ITER_slots|BTREE_ITER_intent, k, ret) if (!is_visible_key(desc, inum, k)) return 0; bch2_trans_iter_exit(trans, iter); return ret ?: -BCH_ERR_ENOSPC_str_hash_create; } static __always_inline int bch2_hash_needs_whiteout(struct btree_trans *trans, const struct bch_hash_desc desc, const struct bch_hash_info *info, struct btree_iter *start) { struct btree_iter iter; struct bkey_s_c k; int ret; bch2_trans_copy_iter(&iter, start); bch2_btree_iter_advance(&iter); for_each_btree_key_continue_norestart(iter, BTREE_ITER_slots, k, ret) { if (k.k->type != desc.key_type && k.k->type != KEY_TYPE_hash_whiteout) break; if (k.k->type == desc.key_type && desc.hash_bkey(info, k) <= start->pos.offset) { ret = 1; break; } } bch2_trans_iter_exit(trans, &iter); return ret; } static __always_inline int bch2_hash_set_in_snapshot(struct btree_trans *trans, const struct bch_hash_desc desc, const struct bch_hash_info *info, subvol_inum inum, u32 snapshot, struct bkey_i *insert, enum btree_iter_update_trigger_flags flags) { struct btree_iter iter, slot = { NULL }; struct bkey_s_c k; bool found = false; int ret; for_each_btree_key_upto_norestart(trans, iter, desc.btree_id, SPOS(insert->k.p.inode, desc.hash_bkey(info, bkey_i_to_s_c(insert)), snapshot), POS(insert->k.p.inode, U64_MAX), BTREE_ITER_slots|BTREE_ITER_intent, k, ret) { if (is_visible_key(desc, inum, k)) { if (!desc.cmp_bkey(k, bkey_i_to_s_c(insert))) goto found; /* hash collision: */ continue; } if (!slot.path && !(flags & STR_HASH_must_replace)) bch2_trans_copy_iter(&slot, &iter); if (k.k->type != KEY_TYPE_hash_whiteout) goto not_found; } if (!ret) ret = -BCH_ERR_ENOSPC_str_hash_create; out: bch2_trans_iter_exit(trans, &slot); bch2_trans_iter_exit(trans, &iter); return ret; found: found = true; not_found: if (!found && (flags & STR_HASH_must_replace)) { ret = -BCH_ERR_ENOENT_str_hash_set_must_replace; } else if (found && (flags & STR_HASH_must_create)) { ret = -EEXIST; } else { if (!found && slot.path) swap(iter, slot); insert->k.p = iter.pos; ret = bch2_trans_update(trans, &iter, insert, flags); } goto out; } static __always_inline int bch2_hash_set(struct btree_trans *trans, const struct bch_hash_desc desc, const struct bch_hash_info *info, subvol_inum inum, struct bkey_i *insert, enum btree_iter_update_trigger_flags flags) { insert->k.p.inode = inum.inum; u32 snapshot; return bch2_subvolume_get_snapshot(trans, inum.subvol, &snapshot) ?: bch2_hash_set_in_snapshot(trans, desc, info, inum, snapshot, insert, flags); } static __always_inline int bch2_hash_delete_at(struct btree_trans *trans, const struct bch_hash_desc desc, const struct bch_hash_info *info, struct btree_iter *iter, enum btree_iter_update_trigger_flags flags) { struct bkey_i *delete; int ret; delete = bch2_trans_kmalloc(trans, sizeof(*delete)); ret = PTR_ERR_OR_ZERO(delete); if (ret) return ret; ret = bch2_hash_needs_whiteout(trans, desc, info, iter); if (ret < 0) return ret; bkey_init(&delete->k); delete->k.p = iter->pos; delete->k.type = ret ? KEY_TYPE_hash_whiteout : KEY_TYPE_deleted; return bch2_trans_update(trans, iter, delete, flags); } static __always_inline int bch2_hash_delete(struct btree_trans *trans, const struct bch_hash_desc desc, const struct bch_hash_info *info, subvol_inum inum, const void *key) { struct btree_iter iter; struct bkey_s_c k = bch2_hash_lookup(trans, &iter, desc, info, inum, key, BTREE_ITER_intent); int ret = bkey_err(k) ?: bch2_hash_delete_at(trans, desc, info, &iter, 0); bch2_trans_iter_exit(trans, &iter); return ret; } #endif /* _BCACHEFS_STR_HASH_H */ |
| 60 43 23 74 23 55 55 58 58 14 2 2 2 56 56 56 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_ALLOC_FOREGROUND_H #define _BCACHEFS_ALLOC_FOREGROUND_H #include "bcachefs.h" #include "alloc_types.h" #include "extents.h" #include "sb-members.h" #include <linux/hash.h> struct bkey; struct bch_dev; struct bch_fs; struct bch_devs_List; extern const char * const bch2_watermarks[]; void bch2_reset_alloc_cursors(struct bch_fs *); struct dev_alloc_list { unsigned nr; u8 devs[BCH_SB_MEMBERS_MAX]; }; struct dev_alloc_list bch2_dev_alloc_list(struct bch_fs *, struct dev_stripe_state *, struct bch_devs_mask *); void bch2_dev_stripe_increment(struct bch_dev *, struct dev_stripe_state *); long bch2_bucket_alloc_new_fs(struct bch_dev *); static inline struct bch_dev *ob_dev(struct bch_fs *c, struct open_bucket *ob) { return bch2_dev_have_ref(c, ob->dev); } struct open_bucket *bch2_bucket_alloc(struct bch_fs *, struct bch_dev *, enum bch_watermark, enum bch_data_type, struct closure *); static inline void ob_push(struct bch_fs *c, struct open_buckets *obs, struct open_bucket *ob) { BUG_ON(obs->nr >= ARRAY_SIZE(obs->v)); obs->v[obs->nr++] = ob - c->open_buckets; } #define open_bucket_for_each(_c, _obs, _ob, _i) \ for ((_i) = 0; \ (_i) < (_obs)->nr && \ ((_ob) = (_c)->open_buckets + (_obs)->v[_i], true); \ (_i)++) static inline struct open_bucket *ec_open_bucket(struct bch_fs *c, struct open_buckets *obs) { struct open_bucket *ob; unsigned i; open_bucket_for_each(c, obs, ob, i) if (ob->ec) return ob; return NULL; } void bch2_open_bucket_write_error(struct bch_fs *, struct open_buckets *, unsigned); void __bch2_open_bucket_put(struct bch_fs *, struct open_bucket *); static inline void bch2_open_bucket_put(struct bch_fs *c, struct open_bucket *ob) { if (atomic_dec_and_test(&ob->pin)) __bch2_open_bucket_put(c, ob); } static inline void bch2_open_buckets_put(struct bch_fs *c, struct open_buckets *ptrs) { struct open_bucket *ob; unsigned i; open_bucket_for_each(c, ptrs, ob, i) bch2_open_bucket_put(c, ob); ptrs->nr = 0; } static inline void bch2_alloc_sectors_done_inlined(struct bch_fs *c, struct write_point *wp) { struct open_buckets ptrs = { .nr = 0 }, keep = { .nr = 0 }; struct open_bucket *ob; unsigned i; open_bucket_for_each(c, &wp->ptrs, ob, i) ob_push(c, !ob->sectors_free ? &ptrs : &keep, ob); wp->ptrs = keep; mutex_unlock(&wp->lock); bch2_open_buckets_put(c, &ptrs); } static inline void bch2_open_bucket_get(struct bch_fs *c, struct write_point *wp, struct open_buckets *ptrs) { struct open_bucket *ob; unsigned i; open_bucket_for_each(c, &wp->ptrs, ob, i) { ob->data_type = wp->data_type; atomic_inc(&ob->pin); ob_push(c, ptrs, ob); } } static inline open_bucket_idx_t *open_bucket_hashslot(struct bch_fs *c, unsigned dev, u64 bucket) { return c->open_buckets_hash + (jhash_3words(dev, bucket, bucket >> 32, 0) & (OPEN_BUCKETS_COUNT - 1)); } static inline bool bch2_bucket_is_open(struct bch_fs *c, unsigned dev, u64 bucket) { open_bucket_idx_t slot = *open_bucket_hashslot(c, dev, bucket); while (slot) { struct open_bucket *ob = &c->open_buckets[slot]; if (ob->dev == dev && ob->bucket == bucket) return true; slot = ob->hash; } return false; } static inline bool bch2_bucket_is_open_safe(struct bch_fs *c, unsigned dev, u64 bucket) { bool ret; if (bch2_bucket_is_open(c, dev, bucket)) return true; spin_lock(&c->freelist_lock); ret = bch2_bucket_is_open(c, dev, bucket); spin_unlock(&c->freelist_lock); return ret; } int bch2_bucket_alloc_set_trans(struct btree_trans *, struct open_buckets *, struct dev_stripe_state *, struct bch_devs_mask *, unsigned, unsigned *, bool *, unsigned, enum bch_data_type, enum bch_watermark, struct closure *); int bch2_alloc_sectors_start_trans(struct btree_trans *, unsigned, unsigned, struct write_point_specifier, struct bch_devs_list *, unsigned, unsigned, enum bch_watermark, unsigned, struct closure *, struct write_point **); struct bch_extent_ptr bch2_ob_ptr(struct bch_fs *, struct open_bucket *); /* * Append pointers to the space we just allocated to @k, and mark @sectors space * as allocated out of @ob */ static inline void bch2_alloc_sectors_append_ptrs_inlined(struct bch_fs *c, struct write_point *wp, struct bkey_i *k, unsigned sectors, bool cached) { struct open_bucket *ob; unsigned i; BUG_ON(sectors > wp->sectors_free); wp->sectors_free -= sectors; wp->sectors_allocated += sectors; open_bucket_for_each(c, &wp->ptrs, ob, i) { struct bch_dev *ca = ob_dev(c, ob); struct bch_extent_ptr ptr = bch2_ob_ptr(c, ob); ptr.cached = cached || (!ca->mi.durability && wp->data_type == BCH_DATA_user); bch2_bkey_append_ptr(k, ptr); BUG_ON(sectors > ob->sectors_free); ob->sectors_free -= sectors; } } void bch2_alloc_sectors_append_ptrs(struct bch_fs *, struct write_point *, struct bkey_i *, unsigned, bool); void bch2_alloc_sectors_done(struct bch_fs *, struct write_point *); void bch2_open_buckets_stop(struct bch_fs *c, struct bch_dev *, bool); static inline struct write_point_specifier writepoint_hashed(unsigned long v) { return (struct write_point_specifier) { .v = v | 1 }; } static inline struct write_point_specifier writepoint_ptr(struct write_point *wp) { return (struct write_point_specifier) { .v = (unsigned long) wp }; } void bch2_fs_allocator_foreground_init(struct bch_fs *); void bch2_open_buckets_to_text(struct printbuf *, struct bch_fs *); void bch2_open_buckets_partial_to_text(struct printbuf *, struct bch_fs *); void bch2_write_points_to_text(struct printbuf *, struct bch_fs *); void bch2_fs_alloc_debug_to_text(struct printbuf *, struct bch_fs *); void bch2_dev_alloc_debug_to_text(struct printbuf *, struct bch_dev *); void bch2_print_allocator_stuck(struct bch_fs *); #endif /* _BCACHEFS_ALLOC_FOREGROUND_H */ |
| 11 5 6 2 2 1 7 7 1 15 14 9 6 15 2 13 1 1 1 14 14 1 2 1 8 2 8 2 10 2 8 6 2 3 1 2 1 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | // SPDX-License-Identifier: GPL-2.0 #include <net/xsk_buff_pool.h> #include <net/xdp_sock.h> #include <net/xdp_sock_drv.h> #include "xsk_queue.h" #include "xdp_umem.h" #include "xsk.h" void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) { unsigned long flags; if (!xs->tx) return; spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); list_add_rcu(&xs->tx_list, &pool->xsk_tx_list); spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); } void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) { unsigned long flags; if (!xs->tx) return; spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); list_del_rcu(&xs->tx_list); spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); } void xp_destroy(struct xsk_buff_pool *pool) { if (!pool) return; kvfree(pool->tx_descs); kvfree(pool->heads); kvfree(pool); } int xp_alloc_tx_descs(struct xsk_buff_pool *pool, struct xdp_sock *xs) { pool->tx_descs = kvcalloc(xs->tx->nentries, sizeof(*pool->tx_descs), GFP_KERNEL); if (!pool->tx_descs) return -ENOMEM; return 0; } struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, struct xdp_umem *umem) { bool unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; struct xsk_buff_pool *pool; struct xdp_buff_xsk *xskb; u32 i, entries; entries = unaligned ? umem->chunks : 0; pool = kvzalloc(struct_size(pool, free_heads, entries), GFP_KERNEL); if (!pool) goto out; pool->heads = kvcalloc(umem->chunks, sizeof(*pool->heads), GFP_KERNEL); if (!pool->heads) goto out; if (xs->tx) if (xp_alloc_tx_descs(pool, xs)) goto out; pool->chunk_mask = ~((u64)umem->chunk_size - 1); pool->addrs_cnt = umem->size; pool->heads_cnt = umem->chunks; pool->free_heads_cnt = umem->chunks; pool->headroom = umem->headroom; pool->chunk_size = umem->chunk_size; pool->chunk_shift = ffs(umem->chunk_size) - 1; pool->unaligned = unaligned; pool->frame_len = umem->chunk_size - umem->headroom - XDP_PACKET_HEADROOM; pool->umem = umem; pool->addrs = umem->addrs; pool->tx_metadata_len = umem->tx_metadata_len; pool->tx_sw_csum = umem->flags & XDP_UMEM_TX_SW_CSUM; INIT_LIST_HEAD(&pool->free_list); INIT_LIST_HEAD(&pool->xskb_list); INIT_LIST_HEAD(&pool->xsk_tx_list); spin_lock_init(&pool->xsk_tx_list_lock); spin_lock_init(&pool->cq_lock); refcount_set(&pool->users, 1); pool->fq = xs->fq_tmp; pool->cq = xs->cq_tmp; for (i = 0; i < pool->free_heads_cnt; i++) { xskb = &pool->heads[i]; xskb->pool = pool; xskb->xdp.frame_sz = umem->chunk_size - umem->headroom; INIT_LIST_HEAD(&xskb->free_list_node); INIT_LIST_HEAD(&xskb->xskb_list_node); if (pool->unaligned) pool->free_heads[i] = xskb; else xp_init_xskb_addr(xskb, pool, i * pool->chunk_size); } return pool; out: xp_destroy(pool); return NULL; } void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { u32 i; for (i = 0; i < pool->heads_cnt; i++) pool->heads[i].xdp.rxq = rxq; } EXPORT_SYMBOL(xp_set_rxq_info); void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc) { u32 i; for (i = 0; i < pool->heads_cnt; i++) { struct xdp_buff_xsk *xskb = &pool->heads[i]; memcpy(xskb->cb + desc->off, desc->src, desc->bytes); } } EXPORT_SYMBOL(xp_fill_cb); static void xp_disable_drv_zc(struct xsk_buff_pool *pool) { struct netdev_bpf bpf; int err; ASSERT_RTNL(); if (pool->umem->zc) { bpf.command = XDP_SETUP_XSK_POOL; bpf.xsk.pool = NULL; bpf.xsk.queue_id = pool->queue_id; err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf); if (err) WARN(1, "Failed to disable zero-copy!\n"); } } #define NETDEV_XDP_ACT_ZC (NETDEV_XDP_ACT_BASIC | \ NETDEV_XDP_ACT_REDIRECT | \ NETDEV_XDP_ACT_XSK_ZEROCOPY) int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, u16 queue_id, u16 flags) { bool force_zc, force_copy; struct netdev_bpf bpf; int err = 0; ASSERT_RTNL(); force_zc = flags & XDP_ZEROCOPY; force_copy = flags & XDP_COPY; if (force_zc && force_copy) return -EINVAL; if (xsk_get_pool_from_qid(netdev, queue_id)) return -EBUSY; pool->netdev = netdev; pool->queue_id = queue_id; err = xsk_reg_pool_at_qid(netdev, pool, queue_id); if (err) return err; if (flags & XDP_USE_SG) pool->umem->flags |= XDP_UMEM_SG_FLAG; if (flags & XDP_USE_NEED_WAKEUP) pool->uses_need_wakeup = true; /* Tx needs to be explicitly woken up the first time. Also * for supporting drivers that do not implement this * feature. They will always have to call sendto() or poll(). */ pool->cached_need_wakeup = XDP_WAKEUP_TX; dev_hold(netdev); if (force_copy) /* For copy-mode, we are done. */ return 0; if ((netdev->xdp_features & NETDEV_XDP_ACT_ZC) != NETDEV_XDP_ACT_ZC) { err = -EOPNOTSUPP; goto err_unreg_pool; } if (netdev->xdp_zc_max_segs == 1 && (flags & XDP_USE_SG)) { err = -EOPNOTSUPP; goto err_unreg_pool; } bpf.command = XDP_SETUP_XSK_POOL; bpf.xsk.pool = pool; bpf.xsk.queue_id = queue_id; err = netdev->netdev_ops->ndo_bpf(netdev, &bpf); if (err) goto err_unreg_pool; if (!pool->dma_pages) { WARN(1, "Driver did not DMA map zero-copy buffers"); err = -EINVAL; goto err_unreg_xsk; } pool->umem->zc = true; return 0; err_unreg_xsk: xp_disable_drv_zc(pool); err_unreg_pool: if (!force_zc) err = 0; /* fallback to copy mode */ if (err) { xsk_clear_pool_at_qid(netdev, queue_id); dev_put(netdev); } return err; } int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_sock *umem_xs, struct net_device *dev, u16 queue_id) { u16 flags; struct xdp_umem *umem = umem_xs->umem; /* One fill and completion ring required for each queue id. */ if (!pool->fq || !pool->cq) return -EINVAL; flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY; if (umem_xs->pool->uses_need_wakeup) flags |= XDP_USE_NEED_WAKEUP; return xp_assign_dev(pool, dev, queue_id, flags); } void xp_clear_dev(struct xsk_buff_pool *pool) { if (!pool->netdev) return; xp_disable_drv_zc(pool); xsk_clear_pool_at_qid(pool->netdev, pool->queue_id); dev_put(pool->netdev); pool->netdev = NULL; } static void xp_release_deferred(struct work_struct *work) { struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool, work); rtnl_lock(); xp_clear_dev(pool); rtnl_unlock(); if (pool->fq) { xskq_destroy(pool->fq); pool->fq = NULL; } if (pool->cq) { xskq_destroy(pool->cq); pool->cq = NULL; } xdp_put_umem(pool->umem, false); xp_destroy(pool); } void xp_get_pool(struct xsk_buff_pool *pool) { refcount_inc(&pool->users); } bool xp_put_pool(struct xsk_buff_pool *pool) { if (!pool) return false; if (refcount_dec_and_test(&pool->users)) { INIT_WORK(&pool->work, xp_release_deferred); schedule_work(&pool->work); return true; } return false; } static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool) { struct xsk_dma_map *dma_map; list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) { if (dma_map->netdev == pool->netdev) return dma_map; } return NULL; } static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev, u32 nr_pages, struct xdp_umem *umem) { struct xsk_dma_map *dma_map; dma_map = kzalloc(sizeof(*dma_map), GFP_KERNEL); if (!dma_map) return NULL; dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL); if (!dma_map->dma_pages) { kfree(dma_map); return NULL; } dma_map->netdev = netdev; dma_map->dev = dev; dma_map->dma_pages_cnt = nr_pages; refcount_set(&dma_map->users, 1); list_add(&dma_map->list, &umem->xsk_dma_list); return dma_map; } static void xp_destroy_dma_map(struct xsk_dma_map *dma_map) { list_del(&dma_map->list); kvfree(dma_map->dma_pages); kfree(dma_map); } static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs) { dma_addr_t *dma; u32 i; for (i = 0; i < dma_map->dma_pages_cnt; i++) { dma = &dma_map->dma_pages[i]; if (*dma) { *dma &= ~XSK_NEXT_PG_CONTIG_MASK; dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); *dma = 0; } } xp_destroy_dma_map(dma_map); } void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { struct xsk_dma_map *dma_map; if (!pool->dma_pages) return; dma_map = xp_find_dma_map(pool); if (!dma_map) { WARN(1, "Could not find dma_map for device"); return; } if (!refcount_dec_and_test(&dma_map->users)) return; __xp_dma_unmap(dma_map, attrs); kvfree(pool->dma_pages); pool->dma_pages = NULL; pool->dma_pages_cnt = 0; pool->dev = NULL; } EXPORT_SYMBOL(xp_dma_unmap); static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map) { u32 i; for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) { if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1]) dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK; else dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK; } } static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map) { if (!pool->unaligned) { u32 i; for (i = 0; i < pool->heads_cnt; i++) { struct xdp_buff_xsk *xskb = &pool->heads[i]; xp_init_xskb_dma(xskb, pool, dma_map->dma_pages, xskb->orig_addr); } } pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL); if (!pool->dma_pages) return -ENOMEM; pool->dev = dma_map->dev; pool->dma_pages_cnt = dma_map->dma_pages_cnt; memcpy(pool->dma_pages, dma_map->dma_pages, pool->dma_pages_cnt * sizeof(*pool->dma_pages)); return 0; } int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages) { struct xsk_dma_map *dma_map; dma_addr_t dma; int err; u32 i; dma_map = xp_find_dma_map(pool); if (dma_map) { err = xp_init_dma_info(pool, dma_map); if (err) return err; refcount_inc(&dma_map->users); return 0; } dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem); if (!dma_map) return -ENOMEM; for (i = 0; i < dma_map->dma_pages_cnt; i++) { dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); if (dma_mapping_error(dev, dma)) { __xp_dma_unmap(dma_map, attrs); return -ENOMEM; } dma_map->dma_pages[i] = dma; } if (pool->unaligned) xp_check_dma_contiguity(dma_map); err = xp_init_dma_info(pool, dma_map); if (err) { __xp_dma_unmap(dma_map, attrs); return err; } return 0; } EXPORT_SYMBOL(xp_dma_map); static bool xp_addr_crosses_non_contig_pg(struct xsk_buff_pool *pool, u64 addr) { return xp_desc_crosses_non_contig_pg(pool, addr, pool->chunk_size); } static bool xp_check_unaligned(struct xsk_buff_pool *pool, u64 *addr) { *addr = xp_unaligned_extract_addr(*addr); if (*addr >= pool->addrs_cnt || *addr + pool->chunk_size > pool->addrs_cnt || xp_addr_crosses_non_contig_pg(pool, *addr)) return false; return true; } static bool xp_check_aligned(struct xsk_buff_pool *pool, u64 *addr) { *addr = xp_aligned_extract_addr(pool, *addr); return *addr < pool->addrs_cnt; } static struct xdp_buff_xsk *__xp_alloc(struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb; u64 addr; bool ok; if (pool->free_heads_cnt == 0) return NULL; for (;;) { if (!xskq_cons_peek_addr_unchecked(pool->fq, &addr)) { pool->fq->queue_empty_descs++; return NULL; } ok = pool->unaligned ? xp_check_unaligned(pool, &addr) : xp_check_aligned(pool, &addr); if (!ok) { pool->fq->invalid_descs++; xskq_cons_release(pool->fq); continue; } break; } if (pool->unaligned) { xskb = pool->free_heads[--pool->free_heads_cnt]; xp_init_xskb_addr(xskb, pool, addr); if (pool->dma_pages) xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr); } else { xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)]; } xskq_cons_release(pool->fq); return xskb; } struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) { struct xdp_buff_xsk *xskb; if (!pool->free_list_cnt) { xskb = __xp_alloc(pool); if (!xskb) return NULL; } else { pool->free_list_cnt--; xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node); list_del_init(&xskb->free_list_node); } xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM; xskb->xdp.data_meta = xskb->xdp.data; xskb->xdp.flags = 0; if (pool->dev) xp_dma_sync_for_device(pool, xskb->dma, pool->frame_len); return &xskb->xdp; } EXPORT_SYMBOL(xp_alloc); static u32 xp_alloc_new_from_fq(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) { u32 i, cached_cons, nb_entries; if (max > pool->free_heads_cnt) max = pool->free_heads_cnt; max = xskq_cons_nb_entries(pool->fq, max); cached_cons = pool->fq->cached_cons; nb_entries = max; i = max; while (i--) { struct xdp_buff_xsk *xskb; u64 addr; bool ok; __xskq_cons_read_addr_unchecked(pool->fq, cached_cons++, &addr); ok = pool->unaligned ? xp_check_unaligned(pool, &addr) : xp_check_aligned(pool, &addr); if (unlikely(!ok)) { pool->fq->invalid_descs++; nb_entries--; continue; } if (pool->unaligned) { xskb = pool->free_heads[--pool->free_heads_cnt]; xp_init_xskb_addr(xskb, pool, addr); if (pool->dma_pages) xp_init_xskb_dma(xskb, pool, pool->dma_pages, addr); } else { xskb = &pool->heads[xp_aligned_extract_idx(pool, addr)]; } *xdp = &xskb->xdp; xdp++; } xskq_cons_release_n(pool->fq, max); return nb_entries; } static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 nb_entries) { struct xdp_buff_xsk *xskb; u32 i; nb_entries = min_t(u32, nb_entries, pool->free_list_cnt); i = nb_entries; while (i--) { xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node); list_del_init(&xskb->free_list_node); *xdp = &xskb->xdp; xdp++; } pool->free_list_cnt -= nb_entries; return nb_entries; } u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) { u32 nb_entries1 = 0, nb_entries2; if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) { struct xdp_buff *buff; /* Slow path */ buff = xp_alloc(pool); if (buff) *xdp = buff; return !!buff; } if (unlikely(pool->free_list_cnt)) { nb_entries1 = xp_alloc_reused(pool, xdp, max); if (nb_entries1 == max) return nb_entries1; max -= nb_entries1; xdp += nb_entries1; } nb_entries2 = xp_alloc_new_from_fq(pool, xdp, max); if (!nb_entries2) pool->fq->queue_empty_descs++; return nb_entries1 + nb_entries2; } EXPORT_SYMBOL(xp_alloc_batch); bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count) { if (pool->free_list_cnt >= count) return true; return xskq_cons_has_entries(pool->fq, count - pool->free_list_cnt); } EXPORT_SYMBOL(xp_can_alloc); void xp_free(struct xdp_buff_xsk *xskb) { if (!list_empty(&xskb->free_list_node)) return; xskb->pool->free_list_cnt++; list_add(&xskb->free_list_node, &xskb->pool->free_list); } EXPORT_SYMBOL(xp_free); void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr) { addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr; return pool->addrs + addr; } EXPORT_SYMBOL(xp_raw_get_data); dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr) { addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr; return (pool->dma_pages[addr >> PAGE_SHIFT] & ~XSK_NEXT_PG_CONTIG_MASK) + (addr & ~PAGE_MASK); } EXPORT_SYMBOL(xp_raw_get_dma); |
| 89 89 89 88 89 89 3 1 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * binfmt_misc.c * * Copyright (C) 1997 Richard Günther * * binfmt_misc detects binaries via a magic or filename extension and invokes * a specified wrapper. See Documentation/admin-guide/binfmt-misc.rst for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/magic.h> #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/string_helpers.h> #include <linux/file.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/uaccess.h> #include "internal.h" #ifdef DEBUG # define USE_DEBUG 1 #else # define USE_DEBUG 0 #endif enum { VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */ }; enum {Enabled, Magic}; #define MISC_FMT_PRESERVE_ARGV0 (1UL << 31) #define MISC_FMT_OPEN_BINARY (1UL << 30) #define MISC_FMT_CREDENTIALS (1UL << 29) #define MISC_FMT_OPEN_FILE (1UL << 28) typedef struct { struct list_head list; unsigned long flags; /* type, status, etc. */ int offset; /* offset of magic */ int size; /* size of magic/mask */ char *magic; /* magic or filename extension */ char *mask; /* mask, NULL for exact match */ const char *interpreter; /* filename of interpreter */ char *name; struct dentry *dentry; struct file *interp_file; refcount_t users; /* sync removal with load_misc_binary() */ } Node; static struct file_system_type bm_fs_type; /* * Max length of the register string. Determined by: * - 7 delimiters * - name: ~50 bytes * - type: 1 byte * - offset: 3 bytes (has to be smaller than BINPRM_BUF_SIZE) * - magic: 128 bytes (512 in escaped form) * - mask: 128 bytes (512 in escaped form) * - interp: ~50 bytes * - flags: 5 bytes * Round that up a bit, and then back off to hold the internal data * (like struct Node). */ #define MAX_REGISTER_LENGTH 1920 /** * search_binfmt_handler - search for a binary handler for @bprm * @misc: handle to binfmt_misc instance * @bprm: binary for which we are looking for a handler * * Search for a binary type handler for @bprm in the list of registered binary * type handlers. * * Return: binary type list entry on success, NULL on failure */ static Node *search_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm) { char *p = strrchr(bprm->interp, '.'); Node *e; /* Walk all the registered handlers. */ list_for_each_entry(e, &misc->entries, list) { char *s; int j; /* Make sure this one is currently enabled. */ if (!test_bit(Enabled, &e->flags)) continue; /* Do matching based on extension if applicable. */ if (!test_bit(Magic, &e->flags)) { if (p && !strcmp(e->magic, p + 1)) return e; continue; } /* Do matching based on magic & mask. */ s = bprm->buf + e->offset; if (e->mask) { for (j = 0; j < e->size; j++) if ((*s++ ^ e->magic[j]) & e->mask[j]) break; } else { for (j = 0; j < e->size; j++) if ((*s++ ^ e->magic[j])) break; } if (j == e->size) return e; } return NULL; } /** * get_binfmt_handler - try to find a binary type handler * @misc: handle to binfmt_misc instance * @bprm: binary for which we are looking for a handler * * Try to find a binfmt handler for the binary type. If one is found take a * reference to protect against removal via bm_{entry,status}_write(). * * Return: binary type list entry on success, NULL on failure */ static Node *get_binfmt_handler(struct binfmt_misc *misc, struct linux_binprm *bprm) { Node *e; read_lock(&misc->entries_lock); e = search_binfmt_handler(misc, bprm); if (e) refcount_inc(&e->users); read_unlock(&misc->entries_lock); return e; } /** * put_binfmt_handler - put binary handler node * @e: node to put * * Free node syncing with load_misc_binary() and defer final free to * load_misc_binary() in case it is using the binary type handler we were * requested to remove. */ static void put_binfmt_handler(Node *e) { if (refcount_dec_and_test(&e->users)) { if (e->flags & MISC_FMT_OPEN_FILE) filp_close(e->interp_file, NULL); kfree(e); } } /** * load_binfmt_misc - load the binfmt_misc of the caller's user namespace * * To be called in load_misc_binary() to load the relevant struct binfmt_misc. * If a user namespace doesn't have its own binfmt_misc mount it can make use * of its ancestor's binfmt_misc handlers. This mimicks the behavior of * pre-namespaced binfmt_misc where all registered binfmt_misc handlers where * available to all user and user namespaces on the system. * * Return: the binfmt_misc instance of the caller's user namespace */ static struct binfmt_misc *load_binfmt_misc(void) { const struct user_namespace *user_ns; struct binfmt_misc *misc; user_ns = current_user_ns(); while (user_ns) { /* Pairs with smp_store_release() in bm_fill_super(). */ misc = smp_load_acquire(&user_ns->binfmt_misc); if (misc) return misc; user_ns = user_ns->parent; } return &init_binfmt_misc; } /* * the loader itself */ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; int retval = -ENOEXEC; struct binfmt_misc *misc; misc = load_binfmt_misc(); if (!misc->enabled) return retval; fmt = get_binfmt_handler(misc, bprm); if (!fmt) return retval; /* Need to be able to load the file after exec */ retval = -ENOENT; if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) goto ret; if (fmt->flags & MISC_FMT_PRESERVE_ARGV0) { bprm->interp_flags |= BINPRM_FLAGS_PRESERVE_ARGV0; } else { retval = remove_arg_zero(bprm); if (retval) goto ret; } if (fmt->flags & MISC_FMT_OPEN_BINARY) bprm->have_execfd = 1; /* make argv[1] be the path to the binary */ retval = copy_string_kernel(bprm->interp, bprm); if (retval < 0) goto ret; bprm->argc++; /* add the interp as argv[0] */ retval = copy_string_kernel(fmt->interpreter, bprm); if (retval < 0) goto ret; bprm->argc++; /* Update interp in case binfmt_script needs it. */ retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) goto ret; if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = file_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { interp_file = open_exec(fmt->interpreter); } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) goto ret; bprm->interpreter = interp_file; if (fmt->flags & MISC_FMT_CREDENTIALS) bprm->execfd_creds = 1; retval = 0; ret: /* * If we actually put the node here all concurrent calls to * load_misc_binary() will have finished. We also know * that for the refcount to be zero someone must have concurently * removed the binary type handler from the list and it's our job to * free it. */ put_binfmt_handler(fmt); return retval; } /* Command parsers */ /* * parses and copies one argument enclosed in del from *sp to *dp, * recognising the \x special. * returns pointer to the copied argument or NULL in case of an * error (and sets err) or null argument length. */ static char *scanarg(char *s, char del) { char c; while ((c = *s++) != del) { if (c == '\\' && *s == 'x') { s++; if (!isxdigit(*s++)) return NULL; if (!isxdigit(*s++)) return NULL; } } s[-1] ='\0'; return s; } static char *check_special_flags(char *sfs, Node *e) { char *p = sfs; int cont = 1; /* special flags */ while (cont) { switch (*p) { case 'P': pr_debug("register: flag: P (preserve argv0)\n"); p++; e->flags |= MISC_FMT_PRESERVE_ARGV0; break; case 'O': pr_debug("register: flag: O (open binary)\n"); p++; e->flags |= MISC_FMT_OPEN_BINARY; break; case 'C': pr_debug("register: flag: C (preserve creds)\n"); p++; /* this flags also implies the open-binary flag */ e->flags |= (MISC_FMT_CREDENTIALS | MISC_FMT_OPEN_BINARY); break; case 'F': pr_debug("register: flag: F: open interpreter file now\n"); p++; e->flags |= MISC_FMT_OPEN_FILE; break; default: cont = 0; } } return p; } /* * This registers a new binary format, it recognises the syntax * ':name:type:offset:magic:mask:interpreter:flags' * where the ':' is the IFS, that can be chosen with the first char */ static Node *create_entry(const char __user *buffer, size_t count) { Node *e; int memsize, err; char *buf, *p; char del; pr_debug("register: received %zu bytes\n", count); /* some sanity checks */ err = -EINVAL; if ((count < 11) || (count > MAX_REGISTER_LENGTH)) goto out; err = -ENOMEM; memsize = sizeof(Node) + count + 8; e = kmalloc(memsize, GFP_KERNEL_ACCOUNT); if (!e) goto out; p = buf = (char *)e + sizeof(Node); memset(e, 0, sizeof(Node)); if (copy_from_user(buf, buffer, count)) goto efault; del = *p++; /* delimeter */ pr_debug("register: delim: %#x {%c}\n", del, del); /* Pad the buffer with the delim to simplify parsing below. */ memset(buf + count, del, 8); /* Parse the 'name' field. */ e->name = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->name[0] || !strcmp(e->name, ".") || !strcmp(e->name, "..") || strchr(e->name, '/')) goto einval; pr_debug("register: name: {%s}\n", e->name); /* Parse the 'type' field. */ switch (*p++) { case 'E': pr_debug("register: type: E (extension)\n"); e->flags = 1 << Enabled; break; case 'M': pr_debug("register: type: M (magic)\n"); e->flags = (1 << Enabled) | (1 << Magic); break; default: goto einval; } if (*p++ != del) goto einval; if (test_bit(Magic, &e->flags)) { /* Handle the 'M' (magic) format. */ char *s; /* Parse the 'offset' field. */ s = strchr(p, del); if (!s) goto einval; *s = '\0'; if (p != s) { int r = kstrtoint(p, 10, &e->offset); if (r != 0 || e->offset < 0) goto einval; } p = s; if (*p++) goto einval; pr_debug("register: offset: %#x\n", e->offset); /* Parse the 'magic' field. */ e->magic = p; p = scanarg(p, del); if (!p) goto einval; if (!e->magic[0]) goto einval; if (USE_DEBUG) print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[raw]: ", DUMP_PREFIX_NONE, e->magic, p - e->magic); /* Parse the 'mask' field. */ e->mask = p; p = scanarg(p, del); if (!p) goto einval; if (!e->mask[0]) { e->mask = NULL; pr_debug("register: mask[raw]: none\n"); } else if (USE_DEBUG) print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[raw]: ", DUMP_PREFIX_NONE, e->mask, p - e->mask); /* * Decode the magic & mask fields. * Note: while we might have accepted embedded NUL bytes from * above, the unescape helpers here will stop at the first one * it encounters. */ e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX); if (e->mask && string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size) goto einval; if (e->size > BINPRM_BUF_SIZE || BINPRM_BUF_SIZE - e->size < e->offset) goto einval; pr_debug("register: magic/mask length: %i\n", e->size); if (USE_DEBUG) { print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[decoded]: ", DUMP_PREFIX_NONE, e->magic, e->size); if (e->mask) { int i; char *masked = kmalloc(e->size, GFP_KERNEL_ACCOUNT); print_hex_dump_bytes( KBUILD_MODNAME ": register: mask[decoded]: ", DUMP_PREFIX_NONE, e->mask, e->size); if (masked) { for (i = 0; i < e->size; ++i) masked[i] = e->magic[i] & e->mask[i]; print_hex_dump_bytes( KBUILD_MODNAME ": register: magic[masked]: ", DUMP_PREFIX_NONE, masked, e->size); kfree(masked); } } } } else { /* Handle the 'E' (extension) format. */ /* Skip the 'offset' field. */ p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; /* Parse the 'magic' field. */ e->magic = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->magic[0] || strchr(e->magic, '/')) goto einval; pr_debug("register: extension: {%s}\n", e->magic); /* Skip the 'mask' field. */ p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; } /* Parse the 'interpreter' field. */ e->interpreter = p; p = strchr(p, del); if (!p) goto einval; *p++ = '\0'; if (!e->interpreter[0]) goto einval; pr_debug("register: interpreter: {%s}\n", e->interpreter); /* Parse the 'flags' field. */ p = check_special_flags(p, e); if (*p == '\n') p++; if (p != buf + count) goto einval; return e; out: return ERR_PTR(err); efault: kfree(e); return ERR_PTR(-EFAULT); einval: kfree(e); return ERR_PTR(-EINVAL); } /* * Set status of entry/binfmt_misc: * '1' enables, '0' disables and '-1' clears entry/binfmt_misc */ static int parse_command(const char __user *buffer, size_t count) { char s[4]; if (count > 3) return -EINVAL; if (copy_from_user(s, buffer, count)) return -EFAULT; if (!count) return 0; if (s[count - 1] == '\n') count--; if (count == 1 && s[0] == '0') return 1; if (count == 1 && s[0] == '1') return 2; if (count == 2 && s[0] == '-' && s[1] == '1') return 3; return -EINVAL; } /* generic stuff */ static void entry_status(Node *e, char *page) { char *dp = page; const char *status = "disabled"; if (test_bit(Enabled, &e->flags)) status = "enabled"; if (!VERBOSE_STATUS) { sprintf(page, "%s\n", status); return; } dp += sprintf(dp, "%s\ninterpreter %s\n", status, e->interpreter); /* print the special flags */ dp += sprintf(dp, "flags: "); if (e->flags & MISC_FMT_PRESERVE_ARGV0) *dp++ = 'P'; if (e->flags & MISC_FMT_OPEN_BINARY) *dp++ = 'O'; if (e->flags & MISC_FMT_CREDENTIALS) *dp++ = 'C'; if (e->flags & MISC_FMT_OPEN_FILE) *dp++ = 'F'; *dp++ = '\n'; if (!test_bit(Magic, &e->flags)) { sprintf(dp, "extension .%s\n", e->magic); } else { dp += sprintf(dp, "offset %i\nmagic ", e->offset); dp = bin2hex(dp, e->magic, e->size); if (e->mask) { dp += sprintf(dp, "\nmask "); dp = bin2hex(dp, e->mask, e->size); } *dp++ = '\n'; *dp = '\0'; } } static struct inode *bm_get_inode(struct super_block *sb, int mode) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = mode; simple_inode_init_ts(inode); } return inode; } /** * i_binfmt_misc - retrieve struct binfmt_misc from a binfmt_misc inode * @inode: inode of the relevant binfmt_misc instance * * This helper retrieves struct binfmt_misc from a binfmt_misc inode. This can * be done without any memory barriers because we are guaranteed that * user_ns->binfmt_misc is fully initialized. It was fully initialized when the * binfmt_misc mount was first created. * * Return: struct binfmt_misc of the relevant binfmt_misc instance */ static struct binfmt_misc *i_binfmt_misc(struct inode *inode) { return inode->i_sb->s_user_ns->binfmt_misc; } /** * bm_evict_inode - cleanup data associated with @inode * @inode: inode to which the data is attached * * Cleanup the binary type handler data associated with @inode if a binary type * entry is removed or the filesystem is unmounted and the super block is * shutdown. * * If the ->evict call was not caused by a super block shutdown but by a write * to remove the entry or all entries via bm_{entry,status}_write() the entry * will have already been removed from the list. We keep the list_empty() check * to make that explicit. */ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private; clear_inode(inode); if (e) { struct binfmt_misc *misc; misc = i_binfmt_misc(inode); write_lock(&misc->entries_lock); if (!list_empty(&e->list)) list_del_init(&e->list); write_unlock(&misc->entries_lock); put_binfmt_handler(e); } } /** * unlink_binfmt_dentry - remove the dentry for the binary type handler * @dentry: dentry associated with the binary type handler * * Do the actual filesystem work to remove a dentry for a registered binary * type handler. Since binfmt_misc only allows simple files to be created * directly under the root dentry of the filesystem we ensure that we are * indeed passed a dentry directly beneath the root dentry, that the inode * associated with the root dentry is locked, and that it is a regular file we * are asked to remove. */ static void unlink_binfmt_dentry(struct dentry *dentry) { struct dentry *parent = dentry->d_parent; struct inode *inode, *parent_inode; /* All entries are immediate descendants of the root dentry. */ if (WARN_ON_ONCE(dentry->d_sb->s_root != parent)) return; /* We only expect to be called on regular files. */ inode = d_inode(dentry); if (WARN_ON_ONCE(!S_ISREG(inode->i_mode))) return; /* The parent inode must be locked. */ parent_inode = d_inode(parent); if (WARN_ON_ONCE(!inode_is_locked(parent_inode))) return; if (simple_positive(dentry)) { dget(dentry); simple_unlink(parent_inode, dentry); d_delete(dentry); dput(dentry); } } /** * remove_binfmt_handler - remove a binary type handler * @misc: handle to binfmt_misc instance * @e: binary type handler to remove * * Remove a binary type handler from the list of binary type handlers and * remove its associated dentry. This is called from * binfmt_{entry,status}_write(). In the future, we might want to think about * adding a proper ->unlink() method to binfmt_misc instead of forcing caller's * to use writes to files in order to delete binary type handlers. But it has * worked for so long that it's not a pressing issue. */ static void remove_binfmt_handler(struct binfmt_misc *misc, Node *e) { write_lock(&misc->entries_lock); list_del_init(&e->list); write_unlock(&misc->entries_lock); unlink_binfmt_dentry(e->dentry); } /* /<entry> */ static ssize_t bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { Node *e = file_inode(file)->i_private; ssize_t res; char *page; page = (char *) __get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; entry_status(e, page); res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page)); free_page((unsigned long) page); return res; } static ssize_t bm_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); Node *e = inode->i_private; int res = parse_command(buffer, count); switch (res) { case 1: /* Disable this handler. */ clear_bit(Enabled, &e->flags); break; case 2: /* Enable this handler. */ set_bit(Enabled, &e->flags); break; case 3: /* Delete this handler. */ inode = d_inode(inode->i_sb->s_root); inode_lock(inode); /* * In order to add new element or remove elements from the list * via bm_{entry,register,status}_write() inode_lock() on the * root inode must be held. * The lock is exclusive ensuring that the list can't be * modified. Only load_misc_binary() can access but does so * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ if (!list_empty(&e->list)) remove_binfmt_handler(i_binfmt_misc(inode), e); inode_unlock(inode); break; default: return res; } return count; } static const struct file_operations bm_entry_operations = { .read = bm_entry_read, .write = bm_entry_write, .llseek = default_llseek, }; /* /register */ static ssize_t bm_register_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { Node *e; struct inode *inode; struct super_block *sb = file_inode(file)->i_sb; struct dentry *root = sb->s_root, *dentry; struct binfmt_misc *misc; int err = 0; struct file *f = NULL; e = create_entry(buffer, count); if (IS_ERR(e)) return PTR_ERR(e); if (e->flags & MISC_FMT_OPEN_FILE) { const struct cred *old_cred; /* * Now that we support unprivileged binfmt_misc mounts make * sure we use the credentials that the register @file was * opened with to also open the interpreter. Before that this * didn't matter much as only a privileged process could open * the register file. */ old_cred = override_creds(file->f_cred); f = open_exec(e->interpreter); revert_creds(old_cred); if (IS_ERR(f)) { pr_notice("register: failed to install interpreter file %s\n", e->interpreter); kfree(e); return PTR_ERR(f); } e->interp_file = f; } inode_lock(d_inode(root)); dentry = lookup_one_len(e->name, root, strlen(e->name)); err = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out; err = -EEXIST; if (d_really_is_positive(dentry)) goto out2; inode = bm_get_inode(sb, S_IFREG | 0644); err = -ENOMEM; if (!inode) goto out2; refcount_set(&e->users, 1); e->dentry = dget(dentry); inode->i_private = e; inode->i_fop = &bm_entry_operations; d_instantiate(dentry, inode); misc = i_binfmt_misc(inode); write_lock(&misc->entries_lock); list_add(&e->list, &misc->entries); write_unlock(&misc->entries_lock); err = 0; out2: dput(dentry); out: inode_unlock(d_inode(root)); if (err) { if (f) filp_close(f, NULL); kfree(e); return err; } return count; } static const struct file_operations bm_register_operations = { .write = bm_register_write, .llseek = noop_llseek, }; /* /status */ static ssize_t bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { struct binfmt_misc *misc; char *s; misc = i_binfmt_misc(file_inode(file)); s = misc->enabled ? "enabled\n" : "disabled\n"; return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s)); } static ssize_t bm_status_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct binfmt_misc *misc; int res = parse_command(buffer, count); Node *e, *next; struct inode *inode; misc = i_binfmt_misc(file_inode(file)); switch (res) { case 1: /* Disable all handlers. */ misc->enabled = false; break; case 2: /* Enable all handlers. */ misc->enabled = true; break; case 3: /* Delete all handlers. */ inode = d_inode(file_inode(file)->i_sb->s_root); inode_lock(inode); /* * In order to add new element or remove elements from the list * via bm_{entry,register,status}_write() inode_lock() on the * root inode must be held. * The lock is exclusive ensuring that the list can't be * modified. Only load_misc_binary() can access but does so * read-only. So we only need to take the write lock when we * actually remove the entry from the list. */ list_for_each_entry_safe(e, next, &misc->entries, list) remove_binfmt_handler(misc, e); inode_unlock(inode); break; default: return res; } return count; } static const struct file_operations bm_status_operations = { .read = bm_status_read, .write = bm_status_write, .llseek = default_llseek, }; /* Superblock handling */ static void bm_put_super(struct super_block *sb) { struct user_namespace *user_ns = sb->s_fs_info; sb->s_fs_info = NULL; put_user_ns(user_ns); } static const struct super_operations s_ops = { .statfs = simple_statfs, .evict_inode = bm_evict_inode, .put_super = bm_put_super, }; static int bm_fill_super(struct super_block *sb, struct fs_context *fc) { int err; struct user_namespace *user_ns = sb->s_user_ns; struct binfmt_misc *misc; static const struct tree_descr bm_files[] = { [2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO}, [3] = {"register", &bm_register_operations, S_IWUSR}, /* last one */ {""} }; if (WARN_ON(user_ns != current_user_ns())) return -EINVAL; /* * Lazily allocate a new binfmt_misc instance for this namespace, i.e. * do it here during the first mount of binfmt_misc. We don't need to * waste memory for every user namespace allocation. It's likely much * more common to not mount a separate binfmt_misc instance than it is * to mount one. * * While multiple superblocks can exist they are keyed by userns in * s_fs_info for binfmt_misc. Hence, the vfs guarantees that * bm_fill_super() is called exactly once whenever a binfmt_misc * superblock for a userns is created. This in turn lets us conclude * that when a binfmt_misc superblock is created for the first time for * a userns there's no one racing us. Therefore we don't need any * barriers when we dereference binfmt_misc. */ misc = user_ns->binfmt_misc; if (!misc) { /* * If it turns out that most user namespaces actually want to * register their own binary type handler and therefore all * create their own separate binfm_misc mounts we should * consider turning this into a kmem cache. */ misc = kzalloc(sizeof(struct binfmt_misc), GFP_KERNEL); if (!misc) return -ENOMEM; INIT_LIST_HEAD(&misc->entries); rwlock_init(&misc->entries_lock); /* Pairs with smp_load_acquire() in load_binfmt_misc(). */ smp_store_release(&user_ns->binfmt_misc, misc); } /* * When the binfmt_misc superblock for this userns is shutdown * ->enabled might have been set to false and we don't reinitialize * ->enabled again in put_super() as someone might already be mounting * binfmt_misc again. It also would be pointless since by the time * ->put_super() is called we know that the binary type list for this * bintfmt_misc mount is empty making load_misc_binary() return * -ENOEXEC independent of whether ->enabled is true. Instead, if * someone mounts binfmt_misc for the first time or again we simply * reset ->enabled to true. */ misc->enabled = true; err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files); if (!err) sb->s_op = &s_ops; return err; } static void bm_free(struct fs_context *fc) { if (fc->s_fs_info) put_user_ns(fc->s_fs_info); } static int bm_get_tree(struct fs_context *fc) { return get_tree_keyed(fc, bm_fill_super, get_user_ns(fc->user_ns)); } static const struct fs_context_operations bm_context_ops = { .free = bm_free, .get_tree = bm_get_tree, }; static int bm_init_fs_context(struct fs_context *fc) { fc->ops = &bm_context_ops; return 0; } static struct linux_binfmt misc_format = { .module = THIS_MODULE, .load_binary = load_misc_binary, }; static struct file_system_type bm_fs_type = { .owner = THIS_MODULE, .name = "binfmt_misc", .init_fs_context = bm_init_fs_context, .fs_flags = FS_USERNS_MOUNT, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("binfmt_misc"); static int __init init_misc_binfmt(void) { int err = register_filesystem(&bm_fs_type); if (!err) insert_binfmt(&misc_format); return err; } static void __exit exit_misc_binfmt(void) { unregister_binfmt(&misc_format); unregister_filesystem(&bm_fs_type); } core_initcall(init_misc_binfmt); module_exit(exit_misc_binfmt); MODULE_LICENSE("GPL"); |
| 23 12 22 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 | /* * linux/fs/nls/nls_cp1251.c * * Charset cp1251 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0402, 0x0403, 0x201a, 0x0453, 0x201e, 0x2026, 0x2020, 0x2021, 0x20ac, 0x2030, 0x0409, 0x2039, 0x040a, 0x040c, 0x040b, 0x040f, /* 0x90*/ 0x0452, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014, 0x0000, 0x2122, 0x0459, 0x203a, 0x045a, 0x045c, 0x045b, 0x045f, /* 0xa0*/ 0x00a0, 0x040e, 0x045e, 0x0408, 0x00a4, 0x0490, 0x00a6, 0x00a7, 0x0401, 0x00a9, 0x0404, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x0407, /* 0xb0*/ 0x00b0, 0x00b1, 0x0406, 0x0456, 0x0491, 0x00b5, 0x00b6, 0x00b7, 0x0451, 0x2116, 0x0454, 0x00bb, 0x0458, 0x0405, 0x0455, 0x0457, /* 0xc0*/ 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, 0x041f, /* 0xd0*/ 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, 0x0428, 0x0429, 0x042a, 0x042b, 0x042c, 0x042d, 0x042e, 0x042f, /* 0xe0*/ 0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, 0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e, 0x043f, /* 0xf0*/ 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447, 0x0448, 0x0449, 0x044a, 0x044b, 0x044c, 0x044d, 0x044e, 0x044f, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0x00, 0xa9, 0x00, 0xab, 0xac, 0xad, 0xae, 0x00, /* 0xa8-0xaf */ 0xb0, 0xb1, 0x00, 0x00, 0x00, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page04[256] = { 0x00, 0xa8, 0x80, 0x81, 0xaa, 0xbd, 0xb2, 0xaf, /* 0x00-0x07 */ 0xa3, 0x8a, 0x8c, 0x8e, 0x8d, 0x00, 0xa1, 0x8f, /* 0x08-0x0f */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0x10-0x17 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0x18-0x1f */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0x20-0x27 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0x28-0x2f */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0x30-0x37 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0x38-0x3f */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0x40-0x47 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0x48-0x4f */ 0x00, 0xb8, 0x90, 0x83, 0xba, 0xbe, 0xb3, 0xbf, /* 0x50-0x57 */ 0xbc, 0x9a, 0x9c, 0x9e, 0x9d, 0x00, 0xa2, 0x9f, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0xa5, 0xb4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x96, 0x97, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x91, 0x92, 0x82, 0x00, 0x93, 0x94, 0x84, 0x00, /* 0x18-0x1f */ 0x86, 0x87, 0x95, 0x00, 0x00, 0x00, 0x85, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x89, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x8b, 0x9b, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ }; static const unsigned char page21[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb9, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x99, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, page04, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, page21, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x90, 0x83, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x9a, 0x8b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa2, 0xa2, 0xbc, 0xa4, 0xb4, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xb8, 0xa9, 0xba, 0xab, 0xac, 0xad, 0xae, 0xbf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb3, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbe, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xc0-0xc7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xc8-0xcf */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xd0-0xd7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x81, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x80, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x8a, 0x9b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa1, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb2, 0xa5, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xa8, 0xb9, 0xaa, 0xbb, 0xa3, 0xbd, 0xbd, 0xaf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xe0-0xe7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xe8-0xef */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xf0-0xf7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp1251", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp1251(void) { return register_nls(&table); } static void __exit exit_nls_cp1251(void) { unregister_nls(&table); } module_init(init_nls_cp1251) module_exit(exit_nls_cp1251) MODULE_LICENSE("Dual BSD/GPL"); |
| 126 218 2208 219 219 219 217 4 893 2 893 892 891 890 891 890 2 890 889 890 39 35 4 39 39 39 38 39 4 4 4 614 614 185 4594 4771 4773 4778 4775 3726 1218 2 2 2 2 4773 4771 4769 1 3546 185 1216 1217 4773 1402 3545 4771 4774 2 2 1401 3545 4779 185 184 185 292 256 37 292 290 292 98 194 102 190 291 291 292 292 292 291 291 103 103 103 1 1 103 103 103 102 1 102 1 103 103 103 103 103 103 103 103 102 102 103 103 4711 4722 125 4593 4595 4591 103 103 103 103 103 103 101 102 106 5 5 5 106 106 106 101 5 106 5 101 4542 4548 125 4417 4417 4543 4543 4544 4500 4500 4504 379 681 4500 2 3724 1214 34 34 34 34 91 91 91 91 91 613 1317 1319 1320 1318 4444 3 1195 126 2 126 1317 3 1318 1319 1320 1320 1318 1317 1320 2 2 2 2 2 2 1317 10 10 271 12 3 2 2 12 12 282 282 2420 2423 2201 2423 2422 1510 1320 46 916 876 42 916 915 4 4 4 3 3 44 81 219 2 2 219 219 125 124 4129 1000 4594 3270 1 3271 3266 3273 3269 3274 3271 3269 3268 656 3267 3268 1 3268 1 100 249 1390 249 1210 220 5821 2562 1391 3364 3265 100 100 3272 1391 1391 2 2 2 3720 259 1337 4591 4592 4594 4594 4592 4594 4598 4595 1585 4593 4596 4595 4597 4597 4593 4597 4593 4590 4591 4499 261 8 9 2 2 2 2 11 11 7 4 4 11 11 11 2 1 8 8 8 8 8 8 1 6 2 7 1 8 8 8 8 8 8 8 5 2 6 6 7 6 1 6 7 7 7 7 5 6 2 8 8 8 7 7 6 6 6 8 8 8 9 9 8 8 8 7 8 8 8 8 8 8 8 8 8 8 8 8 8 5 5 6 6 6 6 6 6 6 6 8 7 2 7 8 8 8 8 8 6 6 6 6 6 5 5 5 6 6 6 6 6 6 9 8 1 1 1 1 1 1 7 7 6 1 7 7 7 7 7 6 9 9 9 9 9 9 2 2 10 10 2 2 2 2 2 2 2 2 1 2 1 1 1 10 10 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 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 | // SPDX-License-Identifier: GPL-2.0 /* * Block multiqueue core code * * Copyright (C) 2013-2014 Jens Axboe * Copyright (C) 2013-2014 Christoph Hellwig */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-integrity.h> #include <linux/kmemleak.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/llist.h> #include <linux/cpu.h> #include <linux/cache.h> #include <linux/sched/topology.h> #include <linux/sched/signal.h> #include <linux/delay.h> #include <linux/crash_dump.h> #include <linux/prefetch.h> #include <linux/blk-crypto.h> #include <linux/part_stat.h> #include <linux/sched/isolation.h> #include <trace/events/block.h> #include <linux/t10-pi.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-pm.h" #include "blk-stat.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd); static void blk_mq_insert_request(struct request *rq, blk_insert_t flags); static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags); static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob, unsigned int flags); /* * Check if any of the ctx, dispatch list or elevator * have pending work in this hardware queue. */ static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx) { return !list_empty_careful(&hctx->dispatch) || sbitmap_any_bit_set(&hctx->ctx_map) || blk_mq_sched_has_work(hctx); } /* * Mark this ctx as having pending work in this hardware queue */ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; if (!sbitmap_test_bit(&hctx->ctx_map, bit)) sbitmap_set_bit(&hctx->ctx_map, bit); } static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx) { const int bit = ctx->index_hw[hctx->type]; sbitmap_clear_bit(&hctx->ctx_map, bit); } struct mq_inflight { struct block_device *part; unsigned int inflight[2]; }; static bool blk_mq_check_inflight(struct request *rq, void *priv) { struct mq_inflight *mi = priv; if (rq->part && blk_do_io_stat(rq) && (!bdev_is_partition(mi->part) || rq->part == mi->part) && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) mi->inflight[rq_data_dir(rq)]++; return true; } unsigned int blk_mq_in_flight(struct request_queue *q, struct block_device *part) { struct mq_inflight mi = { .part = part }; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); return mi.inflight[0] + mi.inflight[1]; } void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, unsigned int inflight[2]) { struct mq_inflight mi = { .part = part }; blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi); inflight[0] = mi.inflight[0]; inflight[1] = mi.inflight[1]; } void blk_freeze_queue_start(struct request_queue *q) { mutex_lock(&q->mq_freeze_lock); if (++q->mq_freeze_depth == 1) { percpu_ref_kill(&q->q_usage_counter); mutex_unlock(&q->mq_freeze_lock); if (queue_is_mq(q)) blk_mq_run_hw_queues(q, false); } else { mutex_unlock(&q->mq_freeze_lock); } } EXPORT_SYMBOL_GPL(blk_freeze_queue_start); void blk_mq_freeze_queue_wait(struct request_queue *q) { wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter)); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout) { return wait_event_timeout(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter), timeout); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout); /* * Guarantee no request is in use, so we can change any data structure of * the queue afterward. */ void blk_freeze_queue(struct request_queue *q) { /* * In the !blk_mq case we are only calling this to kill the * q_usage_counter, otherwise this increases the freeze depth * and waits for it to return to zero. For this reason there is * no blk_unfreeze_queue(), and blk_freeze_queue() is not * exported to drivers as the only user for unfreeze is blk_mq. */ blk_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); } void blk_mq_freeze_queue(struct request_queue *q) { /* * ...just an alias to keep freeze and unfreeze actions balanced * in the blk_mq_* namespace */ blk_freeze_queue(q); } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue); void __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic) { mutex_lock(&q->mq_freeze_lock); if (force_atomic) q->q_usage_counter.data->force_atomic = true; q->mq_freeze_depth--; WARN_ON_ONCE(q->mq_freeze_depth < 0); if (!q->mq_freeze_depth) { percpu_ref_resurrect(&q->q_usage_counter); wake_up_all(&q->mq_freeze_wq); } mutex_unlock(&q->mq_freeze_lock); } void blk_mq_unfreeze_queue(struct request_queue *q) { __blk_mq_unfreeze_queue(q, false); } EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); /* * FIXME: replace the scsi_internal_device_*block_nowait() calls in the * mpt3sas driver such that this function can be removed. */ void blk_mq_quiesce_queue_nowait(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->queue_lock, flags); if (!q->quiesce_depth++) blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q); spin_unlock_irqrestore(&q->queue_lock, flags); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); /** * blk_mq_wait_quiesce_done() - wait until in-progress quiesce is done * @set: tag_set to wait on * * Note: it is driver's responsibility for making sure that quiesce has * been started on or more of the request_queues of the tag_set. This * function only waits for the quiesce on those request_queues that had * the quiesce flag set using blk_mq_quiesce_queue_nowait. */ void blk_mq_wait_quiesce_done(struct blk_mq_tag_set *set) { if (set->flags & BLK_MQ_F_BLOCKING) synchronize_srcu(set->srcu); else synchronize_rcu(); } EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done); /** * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished * @q: request queue. * * Note: this function does not prevent that the struct request end_io() * callback function is invoked. Once this function is returned, we make * sure no dispatch can happen until the queue is unquiesced via * blk_mq_unquiesce_queue(). */ void blk_mq_quiesce_queue(struct request_queue *q) { blk_mq_quiesce_queue_nowait(q); /* nothing to wait for non-mq queues */ if (queue_is_mq(q)) blk_mq_wait_quiesce_done(q->tag_set); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); /* * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue() * @q: request queue. * * This function recovers queue into the state before quiescing * which is done by blk_mq_quiesce_queue. */ void blk_mq_unquiesce_queue(struct request_queue *q) { unsigned long flags; bool run_queue = false; spin_lock_irqsave(&q->queue_lock, flags); if (WARN_ON_ONCE(q->quiesce_depth <= 0)) { ; } else if (!--q->quiesce_depth) { blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q); run_queue = true; } spin_unlock_irqrestore(&q->queue_lock, flags); /* dispatch requests which are inserted during quiescing */ if (run_queue) blk_mq_run_hw_queues(q, true); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue); void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; mutex_lock(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_quiesce_queue_nowait(q); } blk_mq_wait_quiesce_done(set); mutex_unlock(&set->tag_list_lock); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_tagset); void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set) { struct request_queue *q; mutex_lock(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { if (!blk_queue_skip_tagset_quiesce(q)) blk_mq_unquiesce_queue(q); } mutex_unlock(&set->tag_list_lock); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset); void blk_mq_wake_waiters(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_wakeup_all(hctx->tags, true); } void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); rq->q = q; rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = BLK_MQ_NO_TAG; rq->start_time_ns = blk_time_get_ns(); rq->part = NULL; blk_crypto_rq_set_defaults(rq); } EXPORT_SYMBOL(blk_rq_init); /* Set start and alloc time when the allocated request is actually used */ static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns) { if (blk_mq_need_time_stamp(rq)) rq->start_time_ns = blk_time_get_ns(); else rq->start_time_ns = 0; #ifdef CONFIG_BLK_RQ_ALLOC_TIME if (blk_queue_rq_alloc_time(rq->q)) rq->alloc_time_ns = alloc_time_ns ?: rq->start_time_ns; else rq->alloc_time_ns = 0; #endif } static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, struct blk_mq_tags *tags, unsigned int tag) { struct blk_mq_ctx *ctx = data->ctx; struct blk_mq_hw_ctx *hctx = data->hctx; struct request_queue *q = data->q; struct request *rq = tags->static_rqs[tag]; rq->q = q; rq->mq_ctx = ctx; rq->mq_hctx = hctx; rq->cmd_flags = data->cmd_flags; if (data->flags & BLK_MQ_REQ_PM) data->rq_flags |= RQF_PM; if (blk_queue_io_stat(q)) data->rq_flags |= RQF_IO_STAT; rq->rq_flags = data->rq_flags; if (data->rq_flags & RQF_SCHED_TAGS) { rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; } else { rq->tag = tag; rq->internal_tag = BLK_MQ_NO_TAG; } rq->timeout = 0; rq->part = NULL; rq->io_start_time_ns = 0; rq->stats_sectors = 0; rq->nr_phys_segments = 0; #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; #endif rq->end_io = NULL; rq->end_io_data = NULL; blk_crypto_rq_set_defaults(rq); INIT_LIST_HEAD(&rq->queuelist); /* tag was already set */ WRITE_ONCE(rq->deadline, 0); req_ref_set(rq, 1); if (rq->rq_flags & RQF_USE_SCHED) { struct elevator_queue *e = data->q->elevator; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); if (e->type->ops.prepare_request) e->type->ops.prepare_request(rq); } return rq; } static inline struct request * __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data) { unsigned int tag, tag_offset; struct blk_mq_tags *tags; struct request *rq; unsigned long tag_mask; int i, nr = 0; tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset); if (unlikely(!tag_mask)) return NULL; tags = blk_mq_tags_from_data(data); for (i = 0; tag_mask; i++) { if (!(tag_mask & (1UL << i))) continue; tag = tag_offset + i; prefetch(tags->static_rqs[tag]); tag_mask &= ~(1UL << i); rq = blk_mq_rq_ctx_init(data, tags, tag); rq_list_add(data->cached_rq, rq); nr++; } if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_add_active_requests(data->hctx, nr); /* caller already holds a reference, add for remainder */ percpu_ref_get_many(&data->q->q_usage_counter, nr - 1); data->nr_tags -= nr; return rq_list_pop(data->cached_rq); } static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) { struct request_queue *q = data->q; u64 alloc_time_ns = 0; struct request *rq; unsigned int tag; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = blk_time_get_ns(); if (data->cmd_flags & REQ_NOWAIT) data->flags |= BLK_MQ_REQ_NOWAIT; if (q->elevator) { /* * All requests use scheduler tags when an I/O scheduler is * enabled for the queue. */ data->rq_flags |= RQF_SCHED_TAGS; /* * Flush/passthrough requests are special and go directly to the * dispatch list. */ if ((data->cmd_flags & REQ_OP_MASK) != REQ_OP_FLUSH && !blk_op_is_passthrough(data->cmd_flags)) { struct elevator_mq_ops *ops = &q->elevator->type->ops; WARN_ON_ONCE(data->flags & BLK_MQ_REQ_RESERVED); data->rq_flags |= RQF_USE_SCHED; if (ops->limit_depth) ops->limit_depth(data->cmd_flags, data); } } retry: data->ctx = blk_mq_get_ctx(q); data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx); if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_tag_busy(data->hctx); if (data->flags & BLK_MQ_REQ_RESERVED) data->rq_flags |= RQF_RESV; /* * Try batched alloc if we want more than 1 tag. */ if (data->nr_tags > 1) { rq = __blk_mq_alloc_requests_batch(data); if (rq) { blk_mq_rq_time_init(rq, alloc_time_ns); return rq; } data->nr_tags = 1; } /* * Waiting allocations only fail because of an inactive hctx. In that * case just retry the hctx assignment and tag allocation as CPU hotplug * should have migrated us to an online CPU by now. */ tag = blk_mq_get_tag(data); if (tag == BLK_MQ_NO_TAG) { if (data->flags & BLK_MQ_REQ_NOWAIT) return NULL; /* * Give up the CPU and sleep for a random short time to * ensure that thread using a realtime scheduling class * are migrated off the CPU, and thus off the hctx that * is going away. */ msleep(3); goto retry; } if (!(data->rq_flags & RQF_SCHED_TAGS)) blk_mq_inc_active_requests(data->hctx); rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag); blk_mq_rq_time_init(rq, alloc_time_ns); return rq; } static struct request *blk_mq_rq_cache_fill(struct request_queue *q, struct blk_plug *plug, blk_opf_t opf, blk_mq_req_flags_t flags) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .cmd_flags = opf, .nr_tags = plug->nr_ios, .cached_rq = &plug->cached_rq, }; struct request *rq; if (blk_queue_enter(q, flags)) return NULL; plug->nr_ios = 1; rq = __blk_mq_alloc_requests(&data); if (unlikely(!rq)) blk_queue_exit(q); return rq; } static struct request *blk_mq_alloc_cached_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags) { struct blk_plug *plug = current->plug; struct request *rq; if (!plug) return NULL; if (rq_list_empty(plug->cached_rq)) { if (plug->nr_ios == 1) return NULL; rq = blk_mq_rq_cache_fill(q, plug, opf, flags); if (!rq) return NULL; } else { rq = rq_list_peek(&plug->cached_rq); if (!rq || rq->q != q) return NULL; if (blk_mq_get_hctx_type(opf) != rq->mq_hctx->type) return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush(opf)) return NULL; plug->cached_rq = rq_list_next(rq); blk_mq_rq_time_init(rq, 0); } rq->cmd_flags = opf; INIT_LIST_HEAD(&rq->queuelist); return rq; } struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags) { struct request *rq; rq = blk_mq_alloc_cached_request(q, opf, flags); if (!rq) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .cmd_flags = opf, .nr_tags = 1, }; int ret; ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); rq = __blk_mq_alloc_requests(&data); if (!rq) goto out_queue_exit; } rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; out_queue_exit: blk_queue_exit(q); return ERR_PTR(-EWOULDBLOCK); } EXPORT_SYMBOL(blk_mq_alloc_request); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, .cmd_flags = opf, .nr_tags = 1, }; u64 alloc_time_ns = 0; struct request *rq; unsigned int cpu; unsigned int tag; int ret; /* alloc_time includes depth and tag waits */ if (blk_queue_rq_alloc_time(q)) alloc_time_ns = blk_time_get_ns(); /* * If the tag allocator sleeps we could get an allocation for a * different hardware context. No need to complicate the low level * allocator for this for the rare use case of a command tied to * a specific queue. */ if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)) || WARN_ON_ONCE(!(flags & BLK_MQ_REQ_RESERVED))) return ERR_PTR(-EINVAL); if (hctx_idx >= q->nr_hw_queues) return ERR_PTR(-EIO); ret = blk_queue_enter(q, flags); if (ret) return ERR_PTR(ret); /* * Check if the hardware context is actually mapped to anything. * If not tell the caller that it should skip this queue. */ ret = -EXDEV; data.hctx = xa_load(&q->hctx_table, hctx_idx); if (!blk_mq_hw_queue_mapped(data.hctx)) goto out_queue_exit; cpu = cpumask_first_and(data.hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) goto out_queue_exit; data.ctx = __blk_mq_get_ctx(q, cpu); if (q->elevator) data.rq_flags |= RQF_SCHED_TAGS; else blk_mq_tag_busy(data.hctx); if (flags & BLK_MQ_REQ_RESERVED) data.rq_flags |= RQF_RESV; ret = -EWOULDBLOCK; tag = blk_mq_get_tag(&data); if (tag == BLK_MQ_NO_TAG) goto out_queue_exit; if (!(data.rq_flags & RQF_SCHED_TAGS)) blk_mq_inc_active_requests(data.hctx); rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag); blk_mq_rq_time_init(rq, alloc_time_ns); rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; return rq; out_queue_exit: blk_queue_exit(q); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); static void blk_mq_finish_request(struct request *rq) { struct request_queue *q = rq->q; blk_zone_finish_request(rq); if (rq->rq_flags & RQF_USE_SCHED) { q->elevator->type->ops.finish_request(rq); /* * For postflush request that may need to be * completed twice, we should clear this flag * to avoid double finish_request() on the rq. */ rq->rq_flags &= ~RQF_USE_SCHED; } } static void __blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; const int sched_tag = rq->internal_tag; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); rq->mq_hctx = NULL; if (rq->tag != BLK_MQ_NO_TAG) { blk_mq_dec_active_requests(hctx); blk_mq_put_tag(hctx->tags, ctx, rq->tag); } if (sched_tag != BLK_MQ_NO_TAG) blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag); blk_mq_sched_restart(hctx); blk_queue_exit(q); } void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; blk_mq_finish_request(rq); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->disk->bdi); rq_qos_done(q, rq); WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (req_ref_put_and_test(rq)) __blk_mq_free_request(rq); } EXPORT_SYMBOL_GPL(blk_mq_free_request); void blk_mq_free_plug_rqs(struct blk_plug *plug) { struct request *rq; while ((rq = rq_list_pop(&plug->cached_rq)) != NULL) blk_mq_free_request(rq); } void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, rq->q->disk ? rq->q->disk->disk_name : "?", (__force unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); printk(KERN_INFO " bio %p, biotail %p, len %u\n", rq->bio, rq->biotail, blk_rq_bytes(rq)); } EXPORT_SYMBOL(blk_dump_rq_flags); static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); part_stat_lock(); part_stat_add(req->part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } static void blk_print_req_error(struct request *req, blk_status_t status) { printk_ratelimited(KERN_ERR "%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x " "phys_seg %u prio class %u\n", blk_status_to_str(status), req->q->disk ? req->q->disk->disk_name : "?", blk_rq_pos(req), (__force u32)req_op(req), blk_op_str(req_op(req)), (__force u32)(req->cmd_flags & ~REQ_OP_MASK), req->nr_phys_segments, IOPRIO_PRIO_CLASS(req->ioprio)); } /* * Fully end IO on a request. Does not support partial completions, or * errors. */ static void blk_complete_request(struct request *req) { const bool is_flush = (req->rq_flags & RQF_FLUSH_SEQ) != 0; int total_bytes = blk_rq_bytes(req); struct bio *bio = req->bio; trace_block_rq_complete(req, BLK_STS_OK, total_bytes); if (!bio) return; #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ) req->q->integrity.profile->complete_fn(req, total_bytes); #endif /* * Upper layers may call blk_crypto_evict_key() anytime after the last * bio_endio(). Therefore, the keyslot must be released before that. */ blk_crypto_rq_put_keyslot(req); blk_account_io_completion(req, total_bytes); do { struct bio *next = bio->bi_next; /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); blk_zone_update_request_bio(req, bio); if (!is_flush) bio_endio(bio); bio = next; } while (bio); /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ if (!req->end_io) { req->bio = NULL; req->__data_len = 0; } } /** * blk_update_request - Complete multiple bytes without completing the request * @req: the request being processed * @error: block status code * @nr_bytes: number of bytes to complete for @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function * except in the consistency check at the end of this function. * * Return: * %false - this request doesn't have any more data * %true - this request has more data **/ bool blk_update_request(struct request *req, blk_status_t error, unsigned int nr_bytes) { bool is_flush = req->rq_flags & RQF_FLUSH_SEQ; bool quiet = req->rq_flags & RQF_QUIET; int total_bytes; trace_block_rq_complete(req, error, nr_bytes); if (!req->bio) return false; #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && error == BLK_STS_OK) req->q->integrity.profile->complete_fn(req, nr_bytes); #endif /* * Upper layers may call blk_crypto_evict_key() anytime after the last * bio_endio(). Therefore, the keyslot must be released before that. */ if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req)) __blk_crypto_rq_put_keyslot(req); if (unlikely(error && !blk_rq_is_passthrough(req) && !quiet) && !test_bit(GD_DEAD, &req->q->disk->state)) { blk_print_req_error(req, error); trace_block_rq_error(req, error, nr_bytes); } blk_account_io_completion(req, nr_bytes); total_bytes = 0; while (req->bio) { struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); if (unlikely(error)) bio->bi_status = error; if (bio_bytes == bio->bi_iter.bi_size) { req->bio = bio->bi_next; } else if (bio_is_zone_append(bio) && error == BLK_STS_OK) { /* * Partial zone append completions cannot be supported * as the BIO fragments may end up not being written * sequentially. */ bio->bi_status = BLK_STS_IOERR; } /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); if (unlikely(quiet)) bio_set_flag(bio, BIO_QUIET); bio_advance(bio, bio_bytes); /* Don't actually finish bio if it's part of flush sequence */ if (!bio->bi_iter.bi_size) { blk_zone_update_request_bio(req, bio); if (!is_flush) bio_endio(bio); } total_bytes += bio_bytes; nr_bytes -= bio_bytes; if (!nr_bytes) break; } /* * completely done */ if (!req->bio) { /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ req->__data_len = 0; return false; } req->__data_len -= total_bytes; /* update sector only for requests with clear definition of sector */ if (!blk_rq_is_passthrough(req)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ if (req->rq_flags & RQF_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) { /* * If total number of sectors is less than the first segment * size, something has gone terribly wrong. */ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) { blk_dump_rq_flags(req, "request botched"); req->__data_len = blk_rq_cur_bytes(req); } /* recalculate the number of segments */ req->nr_phys_segments = blk_recalc_rq_segments(req); } return true; } EXPORT_SYMBOL_GPL(blk_update_request); static inline void blk_account_io_done(struct request *req, u64 now) { trace_block_io_done(req); /* * Account IO completion. flush_rq isn't accounted as a * normal IO on queueing nor completion. Accounting the * containing request is enough. */ if (blk_do_io_stat(req) && req->part && !(req->rq_flags & RQF_FLUSH_SEQ)) { const int sgrp = op_stat_group(req_op(req)); part_stat_lock(); update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); part_stat_local_dec(req->part, in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } static inline void blk_account_io_start(struct request *req) { trace_block_io_start(req); if (blk_do_io_stat(req)) { /* * All non-passthrough requests are created from a bio with one * exception: when a flush command that is part of a flush sequence * generated by the state machine in blk-flush.c is cloned onto the * lower device by dm-multipath we can get here without a bio. */ if (req->bio) req->part = req->bio->bi_bdev; else req->part = req->q->disk->part0; part_stat_lock(); update_io_ticks(req->part, jiffies, false); part_stat_local_inc(req->part, in_flight[op_is_write(req_op(req))]); part_stat_unlock(); } } static inline void __blk_mq_end_request_acct(struct request *rq, u64 now) { if (rq->rq_flags & RQF_STATS) blk_stat_add(rq, now); blk_mq_sched_completed_request(rq, now); blk_account_io_done(rq, now); } inline void __blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_mq_need_time_stamp(rq)) __blk_mq_end_request_acct(rq, blk_time_get_ns()); blk_mq_finish_request(rq); if (rq->end_io) { rq_qos_done(rq->q, rq); if (rq->end_io(rq, error) == RQ_END_IO_FREE) blk_mq_free_request(rq); } else { blk_mq_free_request(rq); } } EXPORT_SYMBOL(__blk_mq_end_request); void blk_mq_end_request(struct request *rq, blk_status_t error) { if (blk_update_request(rq, error, blk_rq_bytes(rq))) BUG(); __blk_mq_end_request(rq, error); } EXPORT_SYMBOL(blk_mq_end_request); #define TAG_COMP_BATCH 32 static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx, int *tag_array, int nr_tags) { struct request_queue *q = hctx->queue; blk_mq_sub_active_requests(hctx, nr_tags); blk_mq_put_tags(hctx->tags, tag_array, nr_tags); percpu_ref_put_many(&q->q_usage_counter, nr_tags); } void blk_mq_end_request_batch(struct io_comp_batch *iob) { int tags[TAG_COMP_BATCH], nr_tags = 0; struct blk_mq_hw_ctx *cur_hctx = NULL; struct request *rq; u64 now = 0; if (iob->need_ts) now = blk_time_get_ns(); while ((rq = rq_list_pop(&iob->req_list)) != NULL) { prefetch(rq->bio); prefetch(rq->rq_next); blk_complete_request(rq); if (iob->need_ts) __blk_mq_end_request_acct(rq, now); blk_mq_finish_request(rq); rq_qos_done(rq->q, rq); /* * If end_io handler returns NONE, then it still has * ownership of the request. */ if (rq->end_io && rq->end_io(rq, 0) == RQ_END_IO_NONE) continue; WRITE_ONCE(rq->state, MQ_RQ_IDLE); if (!req_ref_put_and_test(rq)) continue; blk_crypto_free_request(rq); blk_pm_mark_last_busy(rq); if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) { if (cur_hctx) blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags); nr_tags = 0; cur_hctx = rq->mq_hctx; } tags[nr_tags++] = rq->tag; } if (nr_tags) blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags); } EXPORT_SYMBOL_GPL(blk_mq_end_request_batch); static void blk_complete_reqs(struct llist_head *list) { struct llist_node *entry = llist_reverse_order(llist_del_all(list)); struct request *rq, *next; llist_for_each_entry_safe(rq, next, entry, ipi_list) rq->q->mq_ops->complete(rq); } static __latent_entropy void blk_done_softirq(struct softirq_action *h) { blk_complete_reqs(this_cpu_ptr(&blk_cpu_done)); } static int blk_softirq_cpu_dead(unsigned int cpu) { blk_complete_reqs(&per_cpu(blk_cpu_done, cpu)); return 0; } static void __blk_mq_complete_request_remote(void *data) { __raise_softirq_irqoff(BLOCK_SOFTIRQ); } static inline bool blk_mq_complete_need_ipi(struct request *rq) { int cpu = raw_smp_processor_id(); if (!IS_ENABLED(CONFIG_SMP) || !test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) return false; /* * With force threaded interrupts enabled, raising softirq from an SMP * function call will always result in waking the ksoftirqd thread. * This is probably worse than completing the request on a different * cache domain. */ if (force_irqthreads()) return false; /* same CPU or cache domain and capacity? Complete locally */ if (cpu == rq->mq_ctx->cpu || (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags) && cpus_share_cache(cpu, rq->mq_ctx->cpu) && cpus_equal_capacity(cpu, rq->mq_ctx->cpu))) return false; /* don't try to IPI to an offline CPU */ return cpu_online(rq->mq_ctx->cpu); } static void blk_mq_complete_send_ipi(struct request *rq) { unsigned int cpu; cpu = rq->mq_ctx->cpu; if (llist_add(&rq->ipi_list, &per_cpu(blk_cpu_done, cpu))) smp_call_function_single_async(cpu, &per_cpu(blk_cpu_csd, cpu)); } static void blk_mq_raise_softirq(struct request *rq) { struct llist_head *list; preempt_disable(); list = this_cpu_ptr(&blk_cpu_done); if (llist_add(&rq->ipi_list, list)) raise_softirq(BLOCK_SOFTIRQ); preempt_enable(); } bool blk_mq_complete_request_remote(struct request *rq) { WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); /* * For request which hctx has only one ctx mapping, * or a polled request, always complete locally, * it's pointless to redirect the completion. */ if ((rq->mq_hctx->nr_ctx == 1 && rq->mq_ctx->cpu == raw_smp_processor_id()) || rq->cmd_flags & REQ_POLLED) return false; if (blk_mq_complete_need_ipi(rq)) { blk_mq_complete_send_ipi(rq); return true; } if (rq->q->nr_hw_queues == 1) { blk_mq_raise_softirq(rq); return true; } return false; } EXPORT_SYMBOL_GPL(blk_mq_complete_request_remote); /** * blk_mq_complete_request - end I/O on a request * @rq: the request being processed * * Description: * Complete a request by scheduling the ->complete_rq operation. **/ void blk_mq_complete_request(struct request *rq) { if (!blk_mq_complete_request_remote(rq)) rq->q->mq_ops->complete(rq); } EXPORT_SYMBOL(blk_mq_complete_request); /** * blk_mq_start_request - Start processing a request * @rq: Pointer to request to be started * * Function used by device drivers to notify the block layer that a request * is going to be processed now, so blk layer can do proper initializations * such as starting the timeout timer. */ void blk_mq_start_request(struct request *rq) { struct request_queue *q = rq->q; trace_block_rq_issue(rq); if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) && !blk_rq_is_passthrough(rq)) { rq->io_start_time_ns = blk_time_get_ns(); rq->stats_sectors = blk_rq_sectors(rq); rq->rq_flags |= RQF_STATS; rq_qos_issue(q, rq); } WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE); blk_add_timer(rq); WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT); rq->mq_hctx->tags->rqs[rq->tag] = rq; #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE) q->integrity.profile->prepare_fn(rq); #endif if (rq->bio && rq->bio->bi_opf & REQ_POLLED) WRITE_ONCE(rq->bio->bi_cookie, rq->mq_hctx->queue_num); } EXPORT_SYMBOL(blk_mq_start_request); /* * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple * queues. This is important for md arrays to benefit from merging * requests. */ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) { if (plug->multiple_queues) return BLK_MAX_REQUEST_COUNT * 2; return BLK_MAX_REQUEST_COUNT; } static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) { struct request *last = rq_list_peek(&plug->mq_list); if (!plug->rq_count) { trace_block_plug(rq->q); } else if (plug->rq_count >= blk_plug_max_rq_count(plug) || (!blk_queue_nomerges(rq->q) && blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { blk_mq_flush_plug_list(plug, false); last = NULL; trace_block_plug(rq->q); } if (!plug->multiple_queues && last && last->q != rq->q) plug->multiple_queues = true; /* * Any request allocated from sched tags can't be issued to * ->queue_rqs() directly */ if (!plug->has_elevator && (rq->rq_flags & RQF_SCHED_TAGS)) plug->has_elevator = true; rq->rq_next = NULL; rq_list_add(&plug->mq_list, rq); plug->rq_count++; } /** * blk_execute_rq_nowait - insert a request to I/O scheduler for execution * @rq: request to insert * @at_head: insert request at head or tail of queue * * Description: * Insert a fully prepared request at the back of the I/O scheduler queue * for execution. Don't wait for completion. * * Note: * This function will invoke @done directly if the queue is dead. */ void blk_execute_rq_nowait(struct request *rq, bool at_head) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); blk_account_io_start(rq); if (current->plug && !at_head) { blk_add_rq_to_plug(current->plug, rq); return; } blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0); blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING); } EXPORT_SYMBOL_GPL(blk_execute_rq_nowait); struct blk_rq_wait { struct completion done; blk_status_t ret; }; static enum rq_end_io_ret blk_end_sync_rq(struct request *rq, blk_status_t ret) { struct blk_rq_wait *wait = rq->end_io_data; wait->ret = ret; complete(&wait->done); return RQ_END_IO_NONE; } bool blk_rq_is_poll(struct request *rq) { if (!rq->mq_hctx) return false; if (rq->mq_hctx->type != HCTX_TYPE_POLL) return false; return true; } EXPORT_SYMBOL_GPL(blk_rq_is_poll); static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { blk_hctx_poll(rq->q, rq->mq_hctx, NULL, 0); cond_resched(); } while (!completion_done(wait)); } /** * blk_execute_rq - insert a request into queue for execution * @rq: request to insert * @at_head: insert request at head or tail of queue * * Description: * Insert a fully prepared request at the back of the I/O scheduler queue * for execution and wait for completion. * Return: The blk_status_t result provided to blk_mq_end_request(). */ blk_status_t blk_execute_rq(struct request *rq, bool at_head) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct blk_rq_wait wait = { .done = COMPLETION_INITIALIZER_ONSTACK(wait.done), }; WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); rq->end_io_data = &wait; rq->end_io = blk_end_sync_rq; blk_account_io_start(rq); blk_mq_insert_request(rq, at_head ? BLK_MQ_INSERT_AT_HEAD : 0); blk_mq_run_hw_queue(hctx, false); if (blk_rq_is_poll(rq)) blk_rq_poll_completion(rq, &wait.done); else blk_wait_io(&wait.done); return wait.ret; } EXPORT_SYMBOL(blk_execute_rq); static void __blk_mq_requeue_request(struct request *rq) { struct request_queue *q = rq->q; blk_mq_put_driver_tag(rq); trace_block_rq_requeue(rq); rq_qos_requeue(q, rq); if (blk_mq_request_started(rq)) { WRITE_ONCE(rq->state, MQ_RQ_IDLE); rq->rq_flags &= ~RQF_TIMED_OUT; } } void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) { struct request_queue *q = rq->q; unsigned long flags; __blk_mq_requeue_request(rq); /* this request will be re-inserted to io scheduler queue */ blk_mq_sched_requeue_request(rq); spin_lock_irqsave(&q->requeue_lock, flags); list_add_tail(&rq->queuelist, &q->requeue_list); spin_unlock_irqrestore(&q->requeue_lock, flags); if (kick_requeue_list) blk_mq_kick_requeue_list(q); } EXPORT_SYMBOL(blk_mq_requeue_request); static void blk_mq_requeue_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, requeue_work.work); LIST_HEAD(rq_list); LIST_HEAD(flush_list); struct request *rq; spin_lock_irq(&q->requeue_lock); list_splice_init(&q->requeue_list, &rq_list); list_splice_init(&q->flush_list, &flush_list); spin_unlock_irq(&q->requeue_lock); while (!list_empty(&rq_list)) { rq = list_entry(rq_list.next, struct request, queuelist); /* * If RQF_DONTPREP ist set, the request has been started by the * driver already and might have driver-specific data allocated * already. Insert it into the hctx dispatch list to avoid * block layer merges for the request. */ if (rq->rq_flags & RQF_DONTPREP) { list_del_init(&rq->queuelist); blk_mq_request_bypass_insert(rq, 0); } else { list_del_init(&rq->queuelist); blk_mq_insert_request(rq, BLK_MQ_INSERT_AT_HEAD); } } while (!list_empty(&flush_list)) { rq = list_entry(flush_list.next, struct request, queuelist); list_del_init(&rq->queuelist); blk_mq_insert_request(rq, 0); } blk_mq_run_hw_queues(q, false); } void blk_mq_kick_requeue_list(struct request_queue *q) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0); } EXPORT_SYMBOL(blk_mq_kick_requeue_list); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs) { kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); static bool blk_is_flush_data_rq(struct request *rq) { return (rq->rq_flags & RQF_FLUSH_SEQ) && !is_flush_rq(rq); } static bool blk_mq_rq_inflight(struct request *rq, void *priv) { /* * If we find a request that isn't idle we know the queue is busy * as it's checked in the iter. * Return false to stop the iteration. * * In case of queue quiesce, if one flush data request is completed, * don't count it as inflight given the flush sequence is suspended, * and the original flush data request is invisible to driver, just * like other pending requests because of quiesce */ if (blk_mq_request_started(rq) && !(blk_queue_quiesced(rq->q) && blk_is_flush_data_rq(rq) && blk_mq_request_completed(rq))) { bool *busy = priv; *busy = true; return false; } return true; } bool blk_mq_queue_inflight(struct request_queue *q) { bool busy = false; blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy); return busy; } EXPORT_SYMBOL_GPL(blk_mq_queue_inflight); static void blk_mq_rq_timed_out(struct request *req) { req->rq_flags |= RQF_TIMED_OUT; if (req->q->mq_ops->timeout) { enum blk_eh_timer_return ret; ret = req->q->mq_ops->timeout(req); if (ret == BLK_EH_DONE) return; WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER); } blk_add_timer(req); } struct blk_expired_data { bool has_timedout_rq; unsigned long next; unsigned long timeout_start; }; static bool blk_mq_req_expired(struct request *rq, struct blk_expired_data *expired) { unsigned long deadline; if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT) return false; if (rq->rq_flags & RQF_TIMED_OUT) return false; deadline = READ_ONCE(rq->deadline); if (time_after_eq(expired->timeout_start, deadline)) return true; if (expired->next == 0) expired->next = deadline; else if (time_after(expired->next, deadline)) expired->next = deadline; return false; } void blk_mq_put_rq_ref(struct request *rq) { if (is_flush_rq(rq)) { if (rq->end_io(rq, 0) == RQ_END_IO_FREE) blk_mq_free_request(rq); } else if (req_ref_put_and_test(rq)) { __blk_mq_free_request(rq); } } static bool blk_mq_check_expired(struct request *rq, void *priv) { struct blk_expired_data *expired = priv; /* * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot * be reallocated underneath the timeout handler's processing, then * the expire check is reliable. If the request is not expired, then * it was completed and reallocated as a new request after returning * from blk_mq_check_expired(). */ if (blk_mq_req_expired(rq, expired)) { expired->has_timedout_rq = true; return false; } return true; } static bool blk_mq_handle_expired(struct request *rq, void *priv) { struct blk_expired_data *expired = priv; if (blk_mq_req_expired(rq, expired)) blk_mq_rq_timed_out(rq); return true; } static void blk_mq_timeout_work(struct work_struct *work) { struct request_queue *q = container_of(work, struct request_queue, timeout_work); struct blk_expired_data expired = { .timeout_start = jiffies, }; struct blk_mq_hw_ctx *hctx; unsigned long i; /* A deadlock might occur if a request is stuck requiring a * timeout at the same time a queue freeze is waiting * completion, since the timeout code would not be able to * acquire the queue reference here. * * That's why we don't use blk_queue_enter here; instead, we use * percpu_ref_tryget directly, because we need to be able to * obtain a reference even in the short window between the queue * starting to freeze, by dropping the first reference in * blk_freeze_queue_start, and the moment the last request is * consumed, marked by the instant q_usage_counter reaches * zero. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; /* check if there is any timed-out request */ blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &expired); if (expired.has_timedout_rq) { /* * Before walking tags, we must ensure any submit started * before the current time has finished. Since the submit * uses srcu or rcu, wait for a synchronization point to * ensure all running submits have finished */ blk_mq_wait_quiesce_done(q->tag_set); expired.next = 0; blk_mq_queue_tag_busy_iter(q, blk_mq_handle_expired, &expired); } if (expired.next != 0) { mod_timer(&q->timeout, expired.next); } else { /* * Request timeouts are handled as a forward rolling timer. If * we end up here it means that no requests are pending and * also that no request has been pending for a while. Mark * each hctx as idle. */ queue_for_each_hw_ctx(q, hctx, i) { /* the hctx may be unmapped, so check it here */ if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); } } blk_queue_exit(q); } struct flush_busy_ctx_data { struct blk_mq_hw_ctx *hctx; struct list_head *list; }; static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct flush_busy_ctx_data *flush_data = data; struct blk_mq_hw_ctx *hctx = flush_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); list_splice_tail_init(&ctx->rq_lists[type], flush_data->list); sbitmap_clear_bit(sb, bitnr); spin_unlock(&ctx->lock); return true; } /* * Process software queues that have been marked busy, splicing them * to the for-dispatch */ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list) { struct flush_busy_ctx_data data = { .hctx = hctx, .list = list, }; sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data); } EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs); struct dispatch_rq_data { struct blk_mq_hw_ctx *hctx; struct request *rq; }; static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr, void *data) { struct dispatch_rq_data *dispatch_data = data; struct blk_mq_hw_ctx *hctx = dispatch_data->hctx; struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; enum hctx_type type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { dispatch_data->rq = list_entry_rq(ctx->rq_lists[type].next); list_del_init(&dispatch_data->rq->queuelist); if (list_empty(&ctx->rq_lists[type])) sbitmap_clear_bit(sb, bitnr); } spin_unlock(&ctx->lock); return !dispatch_data->rq; } struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start) { unsigned off = start ? start->index_hw[hctx->type] : 0; struct dispatch_rq_data data = { .hctx = hctx, .rq = NULL, }; __sbitmap_for_each_set(&hctx->ctx_map, off, dispatch_rq_from_ctx, &data); return data.rq; } bool __blk_mq_alloc_driver_tag(struct request *rq) { struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags; unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags; int tag; blk_mq_tag_busy(rq->mq_hctx); if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) { bt = &rq->mq_hctx->tags->breserved_tags; tag_offset = 0; } else { if (!hctx_may_queue(rq->mq_hctx, bt)) return false; } tag = __sbitmap_queue_get(bt); if (tag == BLK_MQ_NO_TAG) return false; rq->tag = tag + tag_offset; blk_mq_inc_active_requests(rq->mq_hctx); return true; } static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key) { struct blk_mq_hw_ctx *hctx; hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { struct sbitmap_queue *sbq; list_del_init(&wait->entry); sbq = &hctx->tags->bitmap_tags; atomic_dec(&sbq->ws_active); } spin_unlock(&hctx->dispatch_wait_lock); blk_mq_run_hw_queue(hctx, true); return 1; } /* * Mark us waiting for a tag. For shared tags, this involves hooking us into * the tag wakeups. For non-shared tags, we can simply mark us needing a * restart. For both cases, take care to check the condition again after * marking us as waiting. */ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { struct sbitmap_queue *sbq; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && !(blk_mq_is_shared_tags(hctx->flags))) { blk_mq_sched_mark_restart_hctx(hctx); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. * * Don't clear RESTART here, someone else could have set it. * At most this will cost an extra queue run. */ return blk_mq_get_driver_tag(rq); } wait = &hctx->dispatch_wait; if (!list_empty_careful(&wait->entry)) return false; if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) sbq = &hctx->tags->breserved_tags; else sbq = &hctx->tags->bitmap_tags; wq = &bt_wait_ptr(sbq, hctx)->wait; spin_lock_irq(&wq->lock); spin_lock(&hctx->dispatch_wait_lock); if (!list_empty(&wait->entry)) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } atomic_inc(&sbq->ws_active); wait->flags &= ~WQ_FLAG_EXCLUSIVE; __add_wait_queue(wq, wait); /* * Add one explicit barrier since blk_mq_get_driver_tag() may * not imply barrier in case of failure. * * Order adding us to wait queue and allocating driver tag. * * The pair is the one implied in sbitmap_queue_wake_up() which * orders clearing sbitmap tag bits and waitqueue_active() in * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless * * Otherwise, re-order of adding wait queue and getting driver tag * may cause __sbitmap_queue_wake_up() to wake up nothing because * the waitqueue_active() may not observe us in wait queue. */ smp_mb(); /* * It's possible that a tag was freed in the window between the * allocation failure and adding the hardware queue to the wait * queue. */ ret = blk_mq_get_driver_tag(rq); if (!ret) { spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return false; } /* * We got a tag, remove ourselves from the wait queue to ensure * someone else gets the wakeup. */ list_del_init(&wait->entry); atomic_dec(&sbq->ws_active); spin_unlock(&hctx->dispatch_wait_lock); spin_unlock_irq(&wq->lock); return true; } #define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT 8 #define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR 4 /* * Update dispatch busy with the Exponential Weighted Moving Average(EWMA): * - EWMA is one simple way to compute running average value * - weight(7/8 and 1/8) is applied so that it can decrease exponentially * - take 4 as factor for avoiding to get too small(0) result, and this * factor doesn't matter because EWMA decreases exponentially */ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) { unsigned int ewma; ewma = hctx->dispatch_busy; if (!ewma && !busy) return; ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1; if (busy) ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR; ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT; hctx->dispatch_busy = ewma; } #define BLK_MQ_RESOURCE_DELAY 3 /* ms units */ static void blk_mq_handle_dev_resource(struct request *rq, struct list_head *list) { list_add(&rq->queuelist, list); __blk_mq_requeue_request(rq); } enum prep_dispatch { PREP_DISPATCH_OK, PREP_DISPATCH_NO_TAG, PREP_DISPATCH_NO_BUDGET, }; static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq, bool need_budget) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; int budget_token = -1; if (need_budget) { budget_token = blk_mq_get_dispatch_budget(rq->q); if (budget_token < 0) { blk_mq_put_driver_tag(rq); return PREP_DISPATCH_NO_BUDGET; } blk_mq_set_rq_budget_token(rq, budget_token); } if (!blk_mq_get_driver_tag(rq)) { /* * The initial allocation attempt failed, so we need to * rerun the hardware queue when a tag is freed. The * waitqueue takes care of that. If the queue is run * before we add this entry back on the dispatch list, * we'll re-run it below. */ if (!blk_mq_mark_tag_wait(hctx, rq)) { /* * All budgets not got from this function will be put * together during handling partial dispatch */ if (need_budget) blk_mq_put_dispatch_budget(rq->q, budget_token); return PREP_DISPATCH_NO_TAG; } } return PREP_DISPATCH_OK; } /* release all allocated budgets before calling to blk_mq_dispatch_rq_list */ static void blk_mq_release_budgets(struct request_queue *q, struct list_head *list) { struct request *rq; list_for_each_entry(rq, list, queuelist) { int budget_token = blk_mq_get_rq_budget_token(rq); if (budget_token >= 0) blk_mq_put_dispatch_budget(q, budget_token); } } /* * blk_mq_commit_rqs will notify driver using bd->last that there is no * more requests. (See comment in struct blk_mq_ops for commit_rqs for * details) * Attention, we should explicitly call this in unusual cases: * 1) did not queue everything initially scheduled to queue * 2) the last attempt to queue a request failed */ static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int queued, bool from_schedule) { if (hctx->queue->mq_ops->commit_rqs && queued) { trace_block_unplug(hctx->queue, queued, !from_schedule); hctx->queue->mq_ops->commit_rqs(hctx); } } /* * Returns true if we did some work AND can potentially do more. */ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list, unsigned int nr_budgets) { enum prep_dispatch prep; struct request_queue *q = hctx->queue; struct request *rq; int queued; blk_status_t ret = BLK_STS_OK; bool needs_resource = false; if (list_empty(list)) return false; /* * Now process all the entries, sending them to the driver. */ queued = 0; do { struct blk_mq_queue_data bd; rq = list_first_entry(list, struct request, queuelist); WARN_ON_ONCE(hctx != rq->mq_hctx); prep = blk_mq_prep_dispatch_rq(rq, !nr_budgets); if (prep != PREP_DISPATCH_OK) break; list_del_init(&rq->queuelist); bd.rq = rq; bd.last = list_empty(list); /* * once the request is queued to lld, no need to cover the * budget any more */ if (nr_budgets) nr_budgets--; ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: needs_resource = true; fallthrough; case BLK_STS_DEV_RESOURCE: blk_mq_handle_dev_resource(rq, list); goto out; default: blk_mq_end_request(rq, ret); } } while (!list_empty(list)); out: /* If we didn't flush the entire list, we could have told the driver * there was more coming, but that turned out to be a lie. */ if (!list_empty(list) || ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. */ if (!list_empty(list)) { bool needs_restart; /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) || blk_mq_is_shared_tags(hctx->flags)); if (nr_budgets) blk_mq_release_budgets(q, list); spin_lock(&hctx->lock); list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); /* * Order adding requests to hctx->dispatch and checking * SCHED_RESTART flag. The pair of this smp_mb() is the one * in blk_mq_sched_restart(). Avoid restart code path to * miss the new added requests to hctx->dispatch, meantime * SCHED_RESTART is observed here. */ smp_mb(); /* * If SCHED_RESTART was set by the caller of this function and * it is no longer set that means that it was cleared by another * thread and hence that a queue rerun is needed. * * If 'no_tag' is set, that means that we failed getting * a driver tag with an I/O scheduler attached. If our dispatch * waitqueue is no longer active, ensure that we run the queue * AFTER adding our entries back to the list. * * If no I/O scheduler has been configured it is possible that * the hardware queue got stopped and restarted before requests * were pushed back onto the dispatch list. Rerun the queue to * avoid starvation. Notes: * - blk_mq_run_hw_queue() checks whether or not a queue has * been stopped before rerunning a queue. * - Some but not all block drivers stop a queue before * returning BLK_STS_RESOURCE. Two exceptions are scsi-mq * and dm-rq. * * If driver returns BLK_STS_RESOURCE and SCHED_RESTART * bit is set, run queue after a delay to avoid IO stalls * that could otherwise occur if the queue is idle. We'll do * similar if we couldn't get budget or couldn't lock a zone * and SCHED_RESTART is set. */ needs_restart = blk_mq_sched_needs_restart(hctx); if (prep == PREP_DISPATCH_NO_BUDGET) needs_resource = true; if (!needs_restart || (no_tag && list_empty_careful(&hctx->dispatch_wait.entry))) blk_mq_run_hw_queue(hctx, true); else if (needs_resource) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); blk_mq_update_dispatch_busy(hctx, true); return false; } blk_mq_update_dispatch_busy(hctx, false); return true; } static inline int blk_mq_first_mapped_cpu(struct blk_mq_hw_ctx *hctx) { int cpu = cpumask_first_and(hctx->cpumask, cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(hctx->cpumask); return cpu; } /* * ->next_cpu is always calculated from hctx->cpumask, so simply use * it for speeding up the check */ static bool blk_mq_hctx_empty_cpumask(struct blk_mq_hw_ctx *hctx) { return hctx->next_cpu >= nr_cpu_ids; } /* * It'd be great if the workqueue API had a way to pass * in a mask and had some smarts for more clever placement. * For now we just round-robin here, switching for every * BLK_MQ_CPU_WORK_BATCH queued items. */ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx) { bool tried = false; int next_cpu = hctx->next_cpu; /* Switch to unbound if no allowable CPUs in this hctx */ if (hctx->queue->nr_hw_queues == 1 || blk_mq_hctx_empty_cpumask(hctx)) return WORK_CPU_UNBOUND; if (--hctx->next_cpu_batch <= 0) { select_cpu: next_cpu = cpumask_next_and(next_cpu, hctx->cpumask, cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } /* * Do unbound schedule if we can't find a online CPU for this hctx, * and it should only happen in the path of handling CPU DEAD. */ if (!cpu_online(next_cpu)) { if (!tried) { tried = true; goto select_cpu; } /* * Make sure to re-select CPU next time once after CPUs * in hctx->cpumask become online again. */ hctx->next_cpu = next_cpu; hctx->next_cpu_batch = 1; return WORK_CPU_UNBOUND; } hctx->next_cpu = next_cpu; return next_cpu; } /** * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously. * @hctx: Pointer to the hardware queue to run. * @msecs: Milliseconds of delay to wait before running the queue. * * Run a hardware queue asynchronously with a delay of @msecs. */ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) { if (unlikely(blk_mq_hctx_stopped(hctx))) return; kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, msecs_to_jiffies(msecs)); } EXPORT_SYMBOL(blk_mq_delay_run_hw_queue); /** * blk_mq_run_hw_queue - Start to run a hardware queue. * @hctx: Pointer to the hardware queue to run. * @async: If we want to run the queue asynchronously. * * Check if the request queue is not in a quiesced state and if there are * pending requests to be sent. If this is true, run the queue to send requests * to hardware. */ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { bool need_run; /* * We can't run the queue inline with interrupts disabled. */ WARN_ON_ONCE(!async && in_interrupt()); might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING); /* * When queue is quiesced, we may be switching io scheduler, or * updating nr_hw_queues, or other things, and we can't run queue * any more, even __blk_mq_hctx_has_pending() can't be called safely. * * And queue will be rerun in blk_mq_unquiesce_queue() if it is * quiesced. */ __blk_mq_run_dispatch_ops(hctx->queue, false, need_run = !blk_queue_quiesced(hctx->queue) && blk_mq_hctx_has_pending(hctx)); if (!need_run) return; if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) { blk_mq_delay_run_hw_queue(hctx, 0); return; } blk_mq_run_dispatch_ops(hctx->queue, blk_mq_sched_dispatch_requests(hctx)); } EXPORT_SYMBOL(blk_mq_run_hw_queue); /* * Return prefered queue to dispatch from (if any) for non-mq aware IO * scheduler. */ static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q) { struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); /* * If the IO scheduler does not respect hardware queues when * dispatching, we just don't bother with multiple HW queues and * dispatch from hctx for the current CPU since running multiple queues * just causes lock contention inside the scheduler and pointless cache * bouncing. */ struct blk_mq_hw_ctx *hctx = ctx->hctxs[HCTX_TYPE_DEFAULT]; if (!blk_mq_hctx_stopped(hctx)) return hctx; return NULL; } /** * blk_mq_run_hw_queues - Run all hardware queues in a request queue. * @q: Pointer to the request queue to run. * @async: If we want to run the queue asynchronously. */ void blk_mq_run_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx, *sq_hctx; unsigned long i; sq_hctx = NULL; if (blk_queue_sq_sched(q)) sq_hctx = blk_mq_get_sq_hctx(q); queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; /* * Dispatch from this hctx either if there's no hctx preferred * by IO scheduler or if it has requests that bypass the * scheduler. */ if (!sq_hctx || sq_hctx == hctx || !list_empty_careful(&hctx->dispatch)) blk_mq_run_hw_queue(hctx, async); } } EXPORT_SYMBOL(blk_mq_run_hw_queues); /** * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously. * @q: Pointer to the request queue to run. * @msecs: Milliseconds of delay to wait before running the queues. */ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs) { struct blk_mq_hw_ctx *hctx, *sq_hctx; unsigned long i; sq_hctx = NULL; if (blk_queue_sq_sched(q)) sq_hctx = blk_mq_get_sq_hctx(q); queue_for_each_hw_ctx(q, hctx, i) { if (blk_mq_hctx_stopped(hctx)) continue; /* * If there is already a run_work pending, leave the * pending delay untouched. Otherwise, a hctx can stall * if another hctx is re-delaying the other's work * before the work executes. */ if (delayed_work_pending(&hctx->run_work)) continue; /* * Dispatch from this hctx either if there's no hctx preferred * by IO scheduler or if it has requests that bypass the * scheduler. */ if (!sq_hctx || sq_hctx == hctx || !list_empty_careful(&hctx->dispatch)) blk_mq_delay_run_hw_queue(hctx, msecs); } } EXPORT_SYMBOL(blk_mq_delay_run_hw_queues); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queue() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx) { cancel_delayed_work(&hctx->run_work); set_bit(BLK_MQ_S_STOPPED, &hctx->state); } EXPORT_SYMBOL(blk_mq_stop_hw_queue); /* * This function is often used for pausing .queue_rq() by driver when * there isn't enough resource or some conditions aren't satisfied, and * BLK_STS_RESOURCE is usually returned. * * We do not guarantee that dispatch can be drained or blocked * after blk_mq_stop_hw_queues() returns. Please use * blk_mq_quiesce_queue() for that requirement. */ void blk_mq_stop_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_stop_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_stop_hw_queues); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx) { clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, hctx->flags & BLK_MQ_F_BLOCKING); } EXPORT_SYMBOL(blk_mq_start_hw_queue); void blk_mq_start_hw_queues(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_hw_queue(hctx); } EXPORT_SYMBOL(blk_mq_start_hw_queues); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async) { if (!blk_mq_hctx_stopped(hctx)) return; clear_bit(BLK_MQ_S_STOPPED, &hctx->state); blk_mq_run_hw_queue(hctx, async); } EXPORT_SYMBOL_GPL(blk_mq_start_stopped_hw_queue); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) blk_mq_start_stopped_hw_queue(hctx, async || (hctx->flags & BLK_MQ_F_BLOCKING)); } EXPORT_SYMBOL(blk_mq_start_stopped_hw_queues); static void blk_mq_run_work_fn(struct work_struct *work) { struct blk_mq_hw_ctx *hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work); blk_mq_run_dispatch_ops(hctx->queue, blk_mq_sched_dispatch_requests(hctx)); } /** * blk_mq_request_bypass_insert - Insert a request at dispatch list. * @rq: Pointer to request to be inserted. * @flags: BLK_MQ_INSERT_* * * Should only be used carefully, when the caller knows we want to * bypass a potential IO scheduler on the target device. */ static void blk_mq_request_bypass_insert(struct request *rq, blk_insert_t flags) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; spin_lock(&hctx->lock); if (flags & BLK_MQ_INSERT_AT_HEAD) list_add(&rq->queuelist, &hctx->dispatch); else list_add_tail(&rq->queuelist, &hctx->dispatch); spin_unlock(&hctx->lock); } static void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list, bool run_queue_async) { struct request *rq; enum hctx_type type = hctx->type; /* * Try to issue requests directly if the hw queue isn't busy to save an * extra enqueue & dequeue to the sw queue. */ if (!hctx->dispatch_busy && !run_queue_async) { blk_mq_run_dispatch_ops(hctx->queue, blk_mq_try_issue_list_directly(hctx, list)); if (list_empty(list)) goto out; } /* * preemption doesn't flush plug list, so it's possible ctx->cpu is * offline now */ list_for_each_entry(rq, list, queuelist) { BUG_ON(rq->mq_ctx != ctx); trace_block_rq_insert(rq); if (rq->cmd_flags & REQ_NOWAIT) run_queue_async = true; } spin_lock(&ctx->lock); list_splice_tail_init(list, &ctx->rq_lists[type]); blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); out: blk_mq_run_hw_queue(hctx, run_queue_async); } static void blk_mq_insert_request(struct request *rq, blk_insert_t flags) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (blk_rq_is_passthrough(rq)) { /* * Passthrough request have to be added to hctx->dispatch * directly. The device may be in a situation where it can't * handle FS request, and always returns BLK_STS_RESOURCE for * them, which gets them added to hctx->dispatch. * * If a passthrough request is required to unblock the queues, * and it is added to the scheduler queue, there is no chance to * dispatch it given we prioritize requests in hctx->dispatch. */ blk_mq_request_bypass_insert(rq, flags); } else if (req_op(rq) == REQ_OP_FLUSH) { /* * Firstly normal IO request is inserted to scheduler queue or * sw queue, meantime we add flush request to dispatch queue( * hctx->dispatch) directly and there is at most one in-flight * flush request for each hw queue, so it doesn't matter to add * flush request to tail or front of the dispatch queue. * * Secondly in case of NCQ, flush request belongs to non-NCQ * command, and queueing it will fail when there is any * in-flight normal IO request(NCQ command). When adding flush * rq to the front of hctx->dispatch, it is easier to introduce * extra time to flush rq's latency because of S_SCHED_RESTART * compared with adding to the tail of dispatch queue, then * chance of flush merge is increased, and less flush requests * will be issued to controller. It is observed that ~10% time * is saved in blktests block/004 on disk attached to AHCI/NCQ * drive when adding flush rq to the front of hctx->dispatch. * * Simply queue flush rq to the front of hctx->dispatch so that * intensive flush workloads can benefit in case of NCQ HW. */ blk_mq_request_bypass_insert(rq, BLK_MQ_INSERT_AT_HEAD); } else if (q->elevator) { LIST_HEAD(list); WARN_ON_ONCE(rq->tag != BLK_MQ_NO_TAG); list_add(&rq->queuelist, &list); q->elevator->type->ops.insert_requests(hctx, &list, flags); } else { trace_block_rq_insert(rq); spin_lock(&ctx->lock); if (flags & BLK_MQ_INSERT_AT_HEAD) list_add(&rq->queuelist, &ctx->rq_lists[hctx->type]); else list_add_tail(&rq->queuelist, &ctx->rq_lists[hctx->type]); blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); } } static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, unsigned int nr_segs) { int err; if (bio->bi_opf & REQ_RAHEAD) rq->cmd_flags |= REQ_FAILFAST_MASK; rq->__sector = bio->bi_iter.bi_sector; rq->write_hint = bio->bi_write_hint; blk_rq_bio_prep(rq, bio, nr_segs); /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */ err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO); WARN_ON_ONCE(err); blk_account_io_start(rq); } static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, bool last) { struct request_queue *q = rq->q; struct blk_mq_queue_data bd = { .rq = rq, .last = last, }; blk_status_t ret; /* * For OK queue, we are done. For error, caller may kill it. * Any other error (busy), just add it to our list as we * previously would have done. */ ret = q->mq_ops->queue_rq(hctx, &bd); switch (ret) { case BLK_STS_OK: blk_mq_update_dispatch_busy(hctx, false); break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_update_dispatch_busy(hctx, true); __blk_mq_requeue_request(rq); break; default: blk_mq_update_dispatch_busy(hctx, false); break; } return ret; } static bool blk_mq_get_budget_and_tag(struct request *rq) { int budget_token; budget_token = blk_mq_get_dispatch_budget(rq->q); if (budget_token < 0) return false; blk_mq_set_rq_budget_token(rq, budget_token); if (!blk_mq_get_driver_tag(rq)) { blk_mq_put_dispatch_budget(rq->q, budget_token); return false; } return true; } /** * blk_mq_try_issue_directly - Try to send a request directly to device driver. * @hctx: Pointer of the associated hardware queue. * @rq: Pointer to request to be sent. * * If the device has enough resources to accept a new request now, send the * request directly to device driver. Else, insert at hctx->dispatch queue, so * we can try send it another time in the future. Requests inserted at this * queue have higher priority. */ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_status_t ret; if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) { blk_mq_insert_request(rq, 0); return; } if ((rq->rq_flags & RQF_USE_SCHED) || !blk_mq_get_budget_and_tag(rq)) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, rq->cmd_flags & REQ_NOWAIT); return; } ret = __blk_mq_issue_directly(hctx, rq, true); switch (ret) { case BLK_STS_OK: break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); blk_mq_run_hw_queue(hctx, false); break; default: blk_mq_end_request(rq, ret); break; } } static blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(rq->q)) { blk_mq_insert_request(rq, 0); return BLK_STS_OK; } if (!blk_mq_get_budget_and_tag(rq)) return BLK_STS_RESOURCE; return __blk_mq_issue_directly(hctx, rq, last); } static void blk_mq_plug_issue_direct(struct blk_plug *plug) { struct blk_mq_hw_ctx *hctx = NULL; struct request *rq; int queued = 0; blk_status_t ret = BLK_STS_OK; while ((rq = rq_list_pop(&plug->mq_list))) { bool last = rq_list_empty(plug->mq_list); if (hctx != rq->mq_hctx) { if (hctx) { blk_mq_commit_rqs(hctx, queued, false); queued = 0; } hctx = rq->mq_hctx; } ret = blk_mq_request_issue_directly(rq, last); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); blk_mq_run_hw_queue(hctx, false); goto out; default: blk_mq_end_request(rq, ret); break; } } out: if (ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); } static void __blk_mq_flush_plug_list(struct request_queue *q, struct blk_plug *plug) { if (blk_queue_quiesced(q)) return; q->mq_ops->queue_rqs(&plug->mq_list); } static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) { struct blk_mq_hw_ctx *this_hctx = NULL; struct blk_mq_ctx *this_ctx = NULL; struct request *requeue_list = NULL; struct request **requeue_lastp = &requeue_list; unsigned int depth = 0; bool is_passthrough = false; LIST_HEAD(list); do { struct request *rq = rq_list_pop(&plug->mq_list); if (!this_hctx) { this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; is_passthrough = blk_rq_is_passthrough(rq); } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx || is_passthrough != blk_rq_is_passthrough(rq)) { rq_list_add_tail(&requeue_lastp, rq); continue; } list_add(&rq->queuelist, &list); depth++; } while (!rq_list_empty(plug->mq_list)); plug->mq_list = requeue_list; trace_block_unplug(this_hctx->queue, depth, !from_sched); percpu_ref_get(&this_hctx->queue->q_usage_counter); /* passthrough requests should never be issued to the I/O scheduler */ if (is_passthrough) { spin_lock(&this_hctx->lock); list_splice_tail_init(&list, &this_hctx->dispatch); spin_unlock(&this_hctx->lock); blk_mq_run_hw_queue(this_hctx, from_sched); } else if (this_hctx->queue->elevator) { this_hctx->queue->elevator->type->ops.insert_requests(this_hctx, &list, 0); blk_mq_run_hw_queue(this_hctx, from_sched); } else { blk_mq_insert_requests(this_hctx, this_ctx, &list, from_sched); } percpu_ref_put(&this_hctx->queue->q_usage_counter); } void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct request *rq; /* * We may have been called recursively midway through handling * plug->mq_list via a schedule() in the driver's queue_rq() callback. * To avoid mq_list changing under our feet, clear rq_count early and * bail out specifically if rq_count is 0 rather than checking * whether the mq_list is empty. */ if (plug->rq_count == 0) return; plug->rq_count = 0; if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) { struct request_queue *q; rq = rq_list_peek(&plug->mq_list); q = rq->q; /* * Peek first request and see if we have a ->queue_rqs() hook. * If we do, we can dispatch the whole plug list in one go. We * already know at this point that all requests belong to the * same queue, caller must ensure that's the case. */ if (q->mq_ops->queue_rqs) { blk_mq_run_dispatch_ops(q, __blk_mq_flush_plug_list(q, plug)); if (rq_list_empty(plug->mq_list)) return; } blk_mq_run_dispatch_ops(q, blk_mq_plug_issue_direct(plug)); if (rq_list_empty(plug->mq_list)) return; } do { blk_mq_dispatch_plug_list(plug, from_schedule); } while (!rq_list_empty(plug->mq_list)); } static void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { int queued = 0; blk_status_t ret = BLK_STS_OK; while (!list_empty(list)) { struct request *rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq, list_empty(list)); switch (ret) { case BLK_STS_OK: queued++; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: blk_mq_request_bypass_insert(rq, 0); if (list_empty(list)) blk_mq_run_hw_queue(hctx, false); goto out; default: blk_mq_end_request(rq, ret); break; } } out: if (ret != BLK_STS_OK) blk_mq_commit_rqs(hctx, queued, false); } static bool blk_mq_attempt_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { if (!blk_queue_nomerges(q) && bio_mergeable(bio)) { if (blk_attempt_plug_merge(q, bio, nr_segs)) return true; if (blk_mq_sched_bio_merge(q, bio, nr_segs)) return true; } return false; } static struct request *blk_mq_get_new_requests(struct request_queue *q, struct blk_plug *plug, struct bio *bio, unsigned int nsegs) { struct blk_mq_alloc_data data = { .q = q, .nr_tags = 1, .cmd_flags = bio->bi_opf, }; struct request *rq; rq_qos_throttle(q, bio); if (plug) { data.nr_tags = plug->nr_ios; plug->nr_ios = 1; data.cached_rq = &plug->cached_rq; } rq = __blk_mq_alloc_requests(&data); if (rq) return rq; rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); return NULL; } /* * Check if there is a suitable cached request and return it. */ static struct request *blk_mq_peek_cached_request(struct blk_plug *plug, struct request_queue *q, blk_opf_t opf) { enum hctx_type type = blk_mq_get_hctx_type(opf); struct request *rq; if (!plug) return NULL; rq = rq_list_peek(&plug->cached_rq); if (!rq || rq->q != q) return NULL; if (type != rq->mq_hctx->type && (type != HCTX_TYPE_READ || rq->mq_hctx->type != HCTX_TYPE_DEFAULT)) return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush(opf)) return NULL; return rq; } static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug, struct bio *bio) { WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq); /* * If any qos ->throttle() end up blocking, we will have flushed the * plug and hence killed the cached_rq list as well. Pop this entry * before we throttle. */ plug->cached_rq = rq_list_next(rq); rq_qos_throttle(rq->q, bio); blk_mq_rq_time_init(rq, 0); rq->cmd_flags = bio->bi_opf; INIT_LIST_HEAD(&rq->queuelist); } /** * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. * * Builds up a request structure from @q and @bio and send to the device. The * request may not be queued directly to hardware if: * * This request can be merged with another one * * We want to place request at plug queue for possible future merging * * There is an IO scheduler active at this queue * * It will not queue the request if there is an error with the bio, or at the * request creation. */ void blk_mq_submit_bio(struct bio *bio) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct blk_plug *plug = current->plug; const int is_sync = op_is_sync(bio->bi_opf); struct blk_mq_hw_ctx *hctx; unsigned int nr_segs = 1; struct request *rq; blk_status_t ret; /* * If the plug has a cached request for this queue, try to use it. */ rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf); /* * A BIO that was released from a zone write plug has already been * through the preparation in this function, already holds a reference * on the queue usage counter, and is the only write BIO in-flight for * the target zone. Go straight to preparing a request for it. */ if (bio_zone_write_plugging(bio)) { nr_segs = bio->__bi_nr_segments; if (rq) blk_queue_exit(q); goto new_request; } bio = blk_queue_bounce(bio, q); /* * The cached request already holds a q_usage_counter reference and we * don't have to acquire a new one if we use it. */ if (!rq) { if (unlikely(bio_queue_enter(bio))) return; } if (unlikely(bio_may_exceed_limits(bio, &q->limits))) { bio = __bio_split_to_limits(bio, &q->limits, &nr_segs); if (!bio) goto queue_exit; } if (!bio_integrity_prep(bio)) goto queue_exit; if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) goto queue_exit; if (blk_queue_is_zoned(q) && blk_zone_plug_bio(bio, nr_segs)) goto queue_exit; new_request: if (!rq) { rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); if (unlikely(!rq)) goto queue_exit; } else { blk_mq_use_cached_rq(rq, plug, bio); } trace_block_getrq(bio); rq_qos_track(q, rq, bio); blk_mq_bio_to_request(rq, bio, nr_segs); ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) { bio->bi_status = ret; bio_endio(bio); blk_mq_free_request(rq); return; } if (bio_zone_write_plugging(bio)) blk_zone_write_plug_init_request(rq); if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq)) return; if (plug) { blk_add_rq_to_plug(plug, rq); return; } hctx = rq->mq_hctx; if ((rq->rq_flags & RQF_USE_SCHED) || (hctx->dispatch_busy && (q->nr_hw_queues == 1 || !is_sync))) { blk_mq_insert_request(rq, 0); blk_mq_run_hw_queue(hctx, true); } else { blk_mq_run_dispatch_ops(q, blk_mq_try_issue_directly(hctx, rq)); } return; queue_exit: /* * Don't drop the queue reference if we were trying to use a cached * request and thus didn't acquire one. */ if (!rq) blk_queue_exit(q); } #ifdef CONFIG_BLK_MQ_STACKING /** * blk_insert_cloned_request - Helper for stacking drivers to submit a request * @rq: the request being queued */ blk_status_t blk_insert_cloned_request(struct request *rq) { struct request_queue *q = rq->q; unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); unsigned int max_segments = blk_rq_get_max_segments(rq); blk_status_t ret; if (blk_rq_sectors(rq) > max_sectors) { /* * SCSI device does not have a good way to return if * Write Same/Zero is actually supported. If a device rejects * a non-read/write command (discard, write same,etc.) the * low-level device driver will set the relevant queue limit to * 0 to prevent blk-lib from issuing more of the offending * operations. Commands queued prior to the queue limit being * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O * errors being propagated to upper layers. */ if (max_sectors == 0) return BLK_STS_NOTSUPP; printk(KERN_ERR "%s: over max size limit. (%u > %u)\n", __func__, blk_rq_sectors(rq), max_sectors); return BLK_STS_IOERR; } /* * The queue settings related to segment counting may differ from the * original queue. */ rq->nr_phys_segments = blk_recalc_rq_segments(rq); if (rq->nr_phys_segments > max_segments) { printk(KERN_ERR "%s: over max segments limit. (%u > %u)\n", __func__, rq->nr_phys_segments, max_segments); return BLK_STS_IOERR; } if (q->disk && should_fail_request(q->disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; ret = blk_crypto_rq_get_keyslot(rq); if (ret != BLK_STS_OK) return ret; blk_account_io_start(rq); /* * Since we have a scheduler attached on the top device, * bypass a potential scheduler on the bottom device for * insert. */ blk_mq_run_dispatch_ops(q, ret = blk_mq_request_issue_directly(rq, true)); if (ret) blk_account_io_done(rq, blk_time_get_ns()); return ret; } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); /** * blk_rq_unprep_clone - Helper function to free all bios in a cloned request * @rq: the clone request to be cleaned up * * Description: * Free all bios in @rq for a cloned request. */ void blk_rq_unprep_clone(struct request *rq) { struct bio *bio; while ((bio = rq->bio) != NULL) { rq->bio = bio->bi_next; bio_put(bio); } } EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); /** * blk_rq_prep_clone - Helper function to setup clone request * @rq: the request to be setup * @rq_src: original request to be cloned * @bs: bio_set that bios for clone are allocated from * @gfp_mask: memory allocation mask for bio * @bio_ctr: setup function to be called for each clone bio. * Returns %0 for success, non %0 for failure. * @data: private data to be passed to @bio_ctr * * Description: * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. * Also, pages which the original bios are pointing to are not copied * and the cloned bios just point same pages. * So cloned bios must be completed before original bios, which means * the caller must complete @rq before @rq_src. */ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data) { struct bio *bio, *bio_src; if (!bs) bs = &fs_bio_set; __rq_for_each_bio(bio_src, rq_src) { bio = bio_alloc_clone(rq->q->disk->part0, bio_src, gfp_mask, bs); if (!bio) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) goto free_and_out; if (rq->bio) { rq->biotail->bi_next = bio; rq->biotail = bio; } else { rq->bio = rq->biotail = bio; } bio = NULL; } /* Copy attributes of the original request to the clone request. */ rq->__sector = blk_rq_pos(rq_src); rq->__data_len = blk_rq_bytes(rq_src); if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) { rq->rq_flags |= RQF_SPECIAL_PAYLOAD; rq->special_vec = rq_src->special_vec; } rq->nr_phys_segments = rq_src->nr_phys_segments; rq->ioprio = rq_src->ioprio; rq->write_hint = rq_src->write_hint; if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0) goto free_and_out; return 0; free_and_out: if (bio) bio_put(bio); blk_rq_unprep_clone(rq); return -ENOMEM; } EXPORT_SYMBOL_GPL(blk_rq_prep_clone); #endif /* CONFIG_BLK_MQ_STACKING */ /* * Steal bios from a request and add them to a bio list. * The request must not have been partially completed before. */ void blk_steal_bios(struct bio_list *list, struct request *rq) { if (rq->bio) { if (list->tail) list->tail->bi_next = rq->bio; else list->head = rq->bio; list->tail = rq->biotail; rq->bio = NULL; rq->biotail = NULL; } rq->__data_len = 0; } EXPORT_SYMBOL_GPL(blk_steal_bios); static size_t order_to_size(unsigned int order) { return (size_t)PAGE_SIZE << order; } /* called before freeing request pool in @tags */ static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags, struct blk_mq_tags *tags) { struct page *page; unsigned long flags; /* * There is no need to clear mapping if driver tags is not initialized * or the mapping belongs to the driver tags. */ if (!drv_tags || drv_tags == tags) return; list_for_each_entry(page, &tags->page_list, lru) { unsigned long start = (unsigned long)page_address(page); unsigned long end = start + order_to_size(page->private); int i; for (i = 0; i < drv_tags->nr_tags; i++) { struct request *rq = drv_tags->rqs[i]; unsigned long rq_addr = (unsigned long)rq; if (rq_addr >= start && rq_addr < end) { WARN_ON_ONCE(req_ref_read(rq) != 0); cmpxchg(&drv_tags->rqs[i], rq, NULL); } } } /* * Wait until all pending iteration is done. * * Request reference is cleared and it is guaranteed to be observed * after the ->lock is released. */ spin_lock_irqsave(&drv_tags->lock, flags); spin_unlock_irqrestore(&drv_tags->lock, flags); } void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { struct blk_mq_tags *drv_tags; struct page *page; if (list_empty(&tags->page_list)) return; if (blk_mq_is_shared_tags(set->flags)) drv_tags = set->shared_tags; else drv_tags = set->tags[hctx_idx]; if (tags->static_rqs && set->ops->exit_request) { int i; for (i = 0; i < tags->nr_tags; i++) { struct request *rq = tags->static_rqs[i]; if (!rq) continue; set->ops->exit_request(set, rq, hctx_idx); tags->static_rqs[i] = NULL; } } blk_mq_clear_rq_mapping(drv_tags, tags); while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); /* * Remove kmemleak object previously allocated in * blk_mq_alloc_rqs(). */ kmemleak_free(page_address(page)); __free_pages(page, page->private); } } void blk_mq_free_rq_map(struct blk_mq_tags *tags) { kfree(tags->rqs); tags->rqs = NULL; kfree(tags->static_rqs); tags->static_rqs = NULL; blk_mq_free_tags(tags); } static enum hctx_type hctx_idx_to_type(struct blk_mq_tag_set *set, unsigned int hctx_idx) { int i; for (i = 0; i < set->nr_maps; i++) { unsigned int start = set->map[i].queue_offset; unsigned int end = start + set->map[i].nr_queues; if (hctx_idx >= start && hctx_idx < end) break; } if (i >= set->nr_maps) i = HCTX_TYPE_DEFAULT; return i; } static int blk_mq_get_hctx_node(struct blk_mq_tag_set *set, unsigned int hctx_idx) { enum hctx_type type = hctx_idx_to_type(set, hctx_idx); return blk_mq_hw_queue_to_node(&set->map[type], hctx_idx); } static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, unsigned int reserved_tags) { int node = blk_mq_get_hctx_node(set, hctx_idx); struct blk_mq_tags *tags; if (node == NUMA_NO_NODE) node = set->numa_node; tags = blk_mq_init_tags(nr_tags, reserved_tags, node, BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags)); if (!tags) return NULL; tags->rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->rqs) goto err_free_tags; tags->static_rqs = kcalloc_node(nr_tags, sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->static_rqs) goto err_free_rqs; return tags; err_free_rqs: kfree(tags->rqs); err_free_tags: blk_mq_free_tags(tags); return NULL; } static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, int node) { int ret; if (set->ops->init_request) { ret = set->ops->init_request(set, rq, hctx_idx, node); if (ret) return ret; } WRITE_ONCE(rq->state, MQ_RQ_IDLE); return 0; } static int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth) { unsigned int i, j, entries_per_page, max_order = 4; int node = blk_mq_get_hctx_node(set, hctx_idx); size_t rq_size, left; if (node == NUMA_NO_NODE) node = set->numa_node; INIT_LIST_HEAD(&tags->page_list); /* * rq_size is the size of the request plus driver payload, rounded * to the cacheline size */ rq_size = round_up(sizeof(struct request) + set->cmd_size, cache_line_size()); left = rq_size * depth; for (i = 0; i < depth; ) { int this_order = max_order; struct page *page; int to_do; void *p; while (this_order && left < order_to_size(this_order - 1)) this_order--; do { page = alloc_pages_node(node, GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; if (!this_order--) break; if (order_to_size(this_order) < rq_size) break; } while (1); if (!page) goto fail; page->private = this_order; list_add_tail(&page->lru, &tags->page_list); p = page_address(page); /* * Allow kmemleak to scan these pages as they contain pointers * to additional allocations like via ops->init_request(). */ kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, depth - i); left -= to_do * rq_size; for (j = 0; j < to_do; j++) { struct request *rq = p; tags->static_rqs[i] = rq; if (blk_mq_init_request(set, rq, hctx_idx, node)) { tags->static_rqs[i] = NULL; goto fail; } p += rq_size; i++; } } return 0; fail: blk_mq_free_rqs(set, tags, hctx_idx); return -ENOMEM; } struct rq_iter_data { struct blk_mq_hw_ctx *hctx; bool has_rq; }; static bool blk_mq_has_request(struct request *rq, void *data) { struct rq_iter_data *iter_data = data; if (rq->mq_hctx != iter_data->hctx) return true; iter_data->has_rq = true; return false; } static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->sched_tags ? hctx->sched_tags : hctx->tags; struct rq_iter_data data = { .hctx = hctx, }; blk_mq_all_tag_iter(tags, blk_mq_has_request, &data); return data.has_rq; } static bool blk_mq_hctx_has_online_cpu(struct blk_mq_hw_ctx *hctx, unsigned int this_cpu) { enum hctx_type type = hctx->type; int cpu; /* * hctx->cpumask has to rule out isolated CPUs, but userspace still * might submit IOs on these isolated CPUs, so use the queue map to * check if all CPUs mapped to this hctx are offline */ for_each_online_cpu(cpu) { struct blk_mq_hw_ctx *h = blk_mq_map_queue_type(hctx->queue, type, cpu); if (h != hctx) continue; /* this hctx has at least one online CPU */ if (this_cpu != cpu) return true; } return false; } static int blk_mq_hctx_notify_offline(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); if (blk_mq_hctx_has_online_cpu(hctx, cpu)) return 0; /* * Prevent new request from being allocated on the current hctx. * * The smp_mb__after_atomic() Pairs with the implied barrier in * test_and_set_bit_lock in sbitmap_get(). Ensures the inactive flag is * seen once we return from the tag allocator. */ set_bit(BLK_MQ_S_INACTIVE, &hctx->state); smp_mb__after_atomic(); /* * Try to grab a reference to the queue and wait for any outstanding * requests. If we could not grab a reference the queue has been * frozen and there are no requests. */ if (percpu_ref_tryget(&hctx->queue->q_usage_counter)) { while (blk_mq_hctx_has_requests(hctx)) msleep(5); percpu_ref_put(&hctx->queue->q_usage_counter); } return 0; } static int blk_mq_hctx_notify_online(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_online); if (cpumask_test_cpu(cpu, hctx->cpumask)) clear_bit(BLK_MQ_S_INACTIVE, &hctx->state); return 0; } /* * 'cpu' is going away. splice any existing rq_list entries from this * software queue to the hw queue dispatch list, and ensure that it * gets run. */ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); enum hctx_type type; hctx = hlist_entry_safe(node, struct blk_mq_hw_ctx, cpuhp_dead); if (!cpumask_test_cpu(cpu, hctx->cpumask)) return 0; ctx = __blk_mq_get_ctx(hctx->queue, cpu); type = hctx->type; spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_lists[type])) { list_splice_init(&ctx->rq_lists[type], &tmp); blk_mq_hctx_clear_pending(hctx, ctx); } spin_unlock(&ctx->lock); if (list_empty(&tmp)) return 0; spin_lock(&hctx->lock); list_splice_tail_init(&tmp, &hctx->dispatch); spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); return 0; } static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { if (!(hctx->flags & BLK_MQ_F_STACKING)) cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); } /* * Before freeing hw queue, clearing the flush request reference in * tags->rqs[] for avoiding potential UAF. */ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags, unsigned int queue_depth, struct request *flush_rq) { int i; unsigned long flags; /* The hw queue may not be mapped yet */ if (!tags) return; WARN_ON_ONCE(req_ref_read(flush_rq) != 0); for (i = 0; i < queue_depth; i++) cmpxchg(&tags->rqs[i], flush_rq, NULL); /* * Wait until all pending iteration is done. * * Request reference is cleared and it is guaranteed to be observed * after the ->lock is released. */ spin_lock_irqsave(&tags->lock, flags); spin_unlock_irqrestore(&tags->lock, flags); } /* hctx->ctxs will be freed in queue's release handler */ static void blk_mq_exit_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { struct request *flush_rq = hctx->fq->flush_rq; if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); if (blk_queue_init_done(q)) blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], set->queue_depth, flush_rq); if (set->ops->exit_request) set->ops->exit_request(set, flush_rq, hctx_idx); if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); blk_mq_remove_cpuhp(hctx); xa_erase(&q->hctx_table, hctx_idx); spin_lock(&q->unused_hctx_lock); list_add(&hctx->hctx_list, &q->unused_hctx_list); spin_unlock(&q->unused_hctx_lock); } static void blk_mq_exit_hw_queues(struct request_queue *q, struct blk_mq_tag_set *set, int nr_queue) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) { if (i == nr_queue) break; blk_mq_exit_hctx(q, set, hctx, i); } } static int blk_mq_init_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned hctx_idx) { hctx->queue_num = hctx_idx; if (!(hctx->flags & BLK_MQ_F_STACKING)) cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); hctx->tags = set->tags[hctx_idx]; if (set->ops->init_hctx && set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) goto unregister_cpu_notifier; if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, hctx->numa_node)) goto exit_hctx; if (xa_insert(&q->hctx_table, hctx_idx, hctx, GFP_KERNEL)) goto exit_flush_rq; return 0; exit_flush_rq: if (set->ops->exit_request) set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx); exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); unregister_cpu_notifier: blk_mq_remove_cpuhp(hctx); return -1; } static struct blk_mq_hw_ctx * blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, int node) { struct blk_mq_hw_ctx *hctx; gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY; hctx = kzalloc_node(sizeof(struct blk_mq_hw_ctx), gfp, node); if (!hctx) goto fail_alloc_hctx; if (!zalloc_cpumask_var_node(&hctx->cpumask, gfp, node)) goto free_hctx; atomic_set(&hctx->nr_active, 0); if (node == NUMA_NO_NODE) node = set->numa_node; hctx->numa_node = node; INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED; INIT_LIST_HEAD(&hctx->hctx_list); /* * Allocate space for all possible cpus to avoid allocation at * runtime */ hctx->ctxs = kmalloc_array_node(nr_cpu_ids, sizeof(void *), gfp, node); if (!hctx->ctxs) goto free_cpumask; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), gfp, node, false, false)) goto free_ctxs; hctx->nr_ctx = 0; spin_lock_init(&hctx->dispatch_wait_lock); init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake); INIT_LIST_HEAD(&hctx->dispatch_wait.entry); hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp); if (!hctx->fq) goto free_bitmap; blk_mq_hctx_kobj_init(hctx); return hctx; free_bitmap: sbitmap_free(&hctx->ctx_map); free_ctxs: kfree(hctx->ctxs); free_cpumask: free_cpumask_var(hctx->cpumask); free_hctx: kfree(hctx); fail_alloc_hctx: return NULL; } static void blk_mq_init_cpu_queues(struct request_queue *q, unsigned int nr_hw_queues) { struct blk_mq_tag_set *set = q->tag_set; unsigned int i, j; for_each_possible_cpu(i) { struct blk_mq_ctx *__ctx = per_cpu_ptr(q->queue_ctx, i); struct blk_mq_hw_ctx *hctx; int k; __ctx->cpu = i; spin_lock_init(&__ctx->lock); for (k = HCTX_TYPE_DEFAULT; k < HCTX_MAX_TYPES; k++) INIT_LIST_HEAD(&__ctx->rq_lists[k]); __ctx->queue = q; /* * Set local node, IFF we have more than one hw queue. If * not, we remain on the home node of the device */ for (j = 0; j < set->nr_maps; j++) { hctx = blk_mq_map_queue_type(q, j, i); if (nr_hw_queues > 1 && hctx->numa_node == NUMA_NO_NODE) hctx->numa_node = cpu_to_node(i); } } } struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int depth) { struct blk_mq_tags *tags; int ret; tags = blk_mq_alloc_rq_map(set, hctx_idx, depth, set->reserved_tags); if (!tags) return NULL; ret = blk_mq_alloc_rqs(set, tags, hctx_idx, depth); if (ret) { blk_mq_free_rq_map(tags); return NULL; } return tags; } static bool __blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, int hctx_idx) { if (blk_mq_is_shared_tags(set->flags)) { set->tags[hctx_idx] = set->shared_tags; return true; } set->tags[hctx_idx] = blk_mq_alloc_map_and_rqs(set, hctx_idx, set->queue_depth); return set->tags[hctx_idx]; } void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { if (tags) { blk_mq_free_rqs(set, tags, hctx_idx); blk_mq_free_rq_map(tags); } } static void __blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx) { if (!blk_mq_is_shared_tags(set->flags)) blk_mq_free_map_and_rqs(set, set->tags[hctx_idx], hctx_idx); set->tags[hctx_idx] = NULL; } static void blk_mq_map_swqueue(struct request_queue *q) { unsigned int j, hctx_idx; unsigned long i; struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx; struct blk_mq_tag_set *set = q->tag_set; queue_for_each_hw_ctx(q, hctx, i) { cpumask_clear(hctx->cpumask); hctx->nr_ctx = 0; hctx->dispatch_from = NULL; } /* * Map software to hardware queues. * * If the cpu isn't present, the cpu is mapped to first hctx. */ for_each_possible_cpu(i) { ctx = per_cpu_ptr(q->queue_ctx, i); for (j = 0; j < set->nr_maps; j++) { if (!set->map[j].nr_queues) { ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); continue; } hctx_idx = set->map[j].mq_map[i]; /* unmapped hw queue can be remapped after CPU topo changed */ if (!set->tags[hctx_idx] && !__blk_mq_alloc_map_and_rqs(set, hctx_idx)) { /* * If tags initialization fail for some hctx, * that hctx won't be brought online. In this * case, remap the current ctx to hctx[0] which * is guaranteed to always have tags allocated */ set->map[j].mq_map[i] = 0; } hctx = blk_mq_map_queue_type(q, j, i); ctx->hctxs[j] = hctx; /* * If the CPU is already set in the mask, then we've * mapped this one already. This can happen if * devices share queues across queue maps. */ if (cpumask_test_cpu(i, hctx->cpumask)) continue; cpumask_set_cpu(i, hctx->cpumask); hctx->type = j; ctx->index_hw[hctx->type] = hctx->nr_ctx; hctx->ctxs[hctx->nr_ctx++] = ctx; /* * If the nr_ctx type overflows, we have exceeded the * amount of sw queues we can support. */ BUG_ON(!hctx->nr_ctx); } for (; j < HCTX_MAX_TYPES; j++) ctx->hctxs[j] = blk_mq_map_queue_type(q, HCTX_TYPE_DEFAULT, i); } queue_for_each_hw_ctx(q, hctx, i) { int cpu; /* * If no software queues are mapped to this hardware queue, * disable it and free the request entries. */ if (!hctx->nr_ctx) { /* Never unmap queue 0. We need it as a * fallback in case of a new remap fails * allocation */ if (i) __blk_mq_free_map_and_rqs(set, i); hctx->tags = NULL; continue; } hctx->tags = set->tags[i]; WARN_ON(!hctx->tags); /* * Set the map size to the number of mapped software queues. * This is more accurate and more efficient than looping * over all possibly mapped software queues. */ sbitmap_resize(&hctx->ctx_map, hctx->nr_ctx); /* * Rule out isolated CPUs from hctx->cpumask to avoid * running block kworker on isolated CPUs */ for_each_cpu(cpu, hctx->cpumask) { if (cpu_is_isolated(cpu)) cpumask_clear_cpu(cpu, hctx->cpumask); } /* * Initialize batch roundrobin counts */ hctx->next_cpu = blk_mq_first_mapped_cpu(hctx); hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH; } } /* * Caller needs to ensure that we're either frozen/quiesced, or that * the queue isn't live yet. */ static void queue_set_hctx_shared(struct request_queue *q, bool shared) { struct blk_mq_hw_ctx *hctx; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) { if (shared) { hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; } else { blk_mq_tag_idle(hctx); hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; } } } static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set, bool shared) { struct request_queue *q; lockdep_assert_held(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_freeze_queue(q); queue_set_hctx_shared(q, shared); blk_mq_unfreeze_queue(q); } } static void blk_mq_del_queue_tag_set(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; mutex_lock(&set->tag_list_lock); list_del(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_shared(set, false); } mutex_unlock(&set->tag_list_lock); INIT_LIST_HEAD(&q->tag_set_list); } static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, struct request_queue *q) { mutex_lock(&set->tag_list_lock); /* * Check to see if we're transitioning to shared (from 1 to 2 queues). */ if (!list_empty(&set->tag_list) && !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_shared(set, true); } if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); list_add_tail(&q->tag_set_list, &set->tag_list); mutex_unlock(&set->tag_list_lock); } /* All allocations will be freed in release handler of q->mq_kobj */ static int blk_mq_alloc_ctxs(struct request_queue *q) { struct blk_mq_ctxs *ctxs; int cpu; ctxs = kzalloc(sizeof(*ctxs), GFP_KERNEL); if (!ctxs) return -ENOMEM; ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx); if (!ctxs->queue_ctx) goto fail; for_each_possible_cpu(cpu) { struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu); ctx->ctxs = ctxs; } q->mq_kobj = &ctxs->kobj; q->queue_ctx = ctxs->queue_ctx; return 0; fail: kfree(ctxs); return -ENOMEM; } /* * It is the actual release handler for mq, but we do it from * request queue's release handler for avoiding use-after-free * and headache because q->mq_kobj shouldn't have been introduced, * but we can't group ctx/kctx kobj without it. */ void blk_mq_release(struct request_queue *q) { struct blk_mq_hw_ctx *hctx, *next; unsigned long i; queue_for_each_hw_ctx(q, hctx, i) WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list)); /* all hctx are in .unused_hctx_list now */ list_for_each_entry_safe(hctx, next, &q->unused_hctx_list, hctx_list) { list_del_init(&hctx->hctx_list); kobject_put(&hctx->kobj); } xa_destroy(&q->hctx_table); /* * release .mq_kobj and sw queue's kobject now because * both share lifetime with request queue. */ blk_mq_sysfs_deinit(q); } struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata) { struct queue_limits default_lim = { }; struct request_queue *q; int ret; q = blk_alloc_queue(lim ? lim : &default_lim, set->numa_node); if (IS_ERR(q)) return q; q->queuedata = queuedata; ret = blk_mq_init_allocated_queue(set, q); if (ret) { blk_put_queue(q); return ERR_PTR(ret); } return q; } EXPORT_SYMBOL(blk_mq_alloc_queue); /** * blk_mq_destroy_queue - shutdown a request queue * @q: request queue to shutdown * * This shuts down a request queue allocated by blk_mq_alloc_queue(). All future * requests will be failed with -ENODEV. The caller is responsible for dropping * the reference from blk_mq_alloc_queue() by calling blk_put_queue(). * * Context: can sleep */ void blk_mq_destroy_queue(struct request_queue *q) { WARN_ON_ONCE(!queue_is_mq(q)); WARN_ON_ONCE(blk_queue_registered(q)); might_sleep(); blk_queue_flag_set(QUEUE_FLAG_DYING, q); blk_queue_start_drain(q); blk_mq_freeze_queue_wait(q); blk_sync_queue(q); blk_mq_cancel_work_sync(q); blk_mq_exit_queue(q); } EXPORT_SYMBOL(blk_mq_destroy_queue); struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass) { struct request_queue *q; struct gendisk *disk; q = blk_mq_alloc_queue(set, lim, queuedata); if (IS_ERR(q)) return ERR_CAST(q); disk = __alloc_disk_node(q, set->numa_node, lkclass); if (!disk) { blk_mq_destroy_queue(q); blk_put_queue(q); return ERR_PTR(-ENOMEM); } set_bit(GD_OWNS_QUEUE, &disk->state); return disk; } EXPORT_SYMBOL(__blk_mq_alloc_disk); struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, struct lock_class_key *lkclass) { struct gendisk *disk; if (!blk_get_queue(q)) return NULL; disk = __alloc_disk_node(q, NUMA_NO_NODE, lkclass); if (!disk) blk_put_queue(q); return disk; } EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) { struct blk_mq_hw_ctx *hctx = NULL, *tmp; /* reuse dead hctx first */ spin_lock(&q->unused_hctx_lock); list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) { if (tmp->numa_node == node) { hctx = tmp; break; } } if (hctx) list_del_init(&hctx->hctx_list); spin_unlock(&q->unused_hctx_lock); if (!hctx) hctx = blk_mq_alloc_hctx(q, set, node); if (!hctx) goto fail; if (blk_mq_init_hctx(q, set, hctx, hctx_idx)) goto free_hctx; return hctx; free_hctx: kobject_put(&hctx->kobj); fail: return NULL; } static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i, j; /* protect against switching io scheduler */ mutex_lock(&q->sysfs_lock); for (i = 0; i < set->nr_hw_queues; i++) { int old_node; int node = blk_mq_get_hctx_node(set, i); struct blk_mq_hw_ctx *old_hctx = xa_load(&q->hctx_table, i); if (old_hctx) { old_node = old_hctx->numa_node; blk_mq_exit_hctx(q, set, old_hctx, i); } if (!blk_mq_alloc_and_init_hctx(set, q, i, node)) { if (!old_hctx) break; pr_warn("Allocate new hctx on node %d fails, fallback to previous one on node %d\n", node, old_node); hctx = blk_mq_alloc_and_init_hctx(set, q, i, old_node); WARN_ON_ONCE(!hctx); } } /* * Increasing nr_hw_queues fails. Free the newly allocated * hctxs and keep the previous q->nr_hw_queues. */ if (i != set->nr_hw_queues) { j = q->nr_hw_queues; } else { j = i; q->nr_hw_queues = set->nr_hw_queues; } xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); mutex_unlock(&q->sysfs_lock); } static void blk_mq_update_poll_flag(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; if (set->nr_maps > HCTX_TYPE_POLL && set->map[HCTX_TYPE_POLL].nr_queues) blk_queue_flag_set(QUEUE_FLAG_POLL, q); else blk_queue_flag_clear(QUEUE_FLAG_POLL, q); } int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q) { /* mark the queue as mq asap */ q->mq_ops = set->ops; if (blk_mq_alloc_ctxs(q)) goto err_exit; /* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); INIT_LIST_HEAD(&q->unused_hctx_list); spin_lock_init(&q->unused_hctx_lock); xa_init(&q->hctx_table); blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; INIT_WORK(&q->timeout_work, blk_mq_timeout_work); blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); q->tag_set = set; q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; blk_mq_update_poll_flag(q); INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); INIT_LIST_HEAD(&q->flush_list); INIT_LIST_HEAD(&q->requeue_list); spin_lock_init(&q->requeue_lock); q->nr_requests = set->queue_depth; blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q); return 0; err_hctxs: blk_mq_release(q); err_exit: q->mq_ops = NULL; return -ENOMEM; } EXPORT_SYMBOL(blk_mq_init_allocated_queue); /* tags can _not_ be used after returning from blk_mq_exit_queue */ void blk_mq_exit_queue(struct request_queue *q) { struct blk_mq_tag_set *set = q->tag_set; /* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */ blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); /* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */ blk_mq_del_queue_tag_set(q); } static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; if (blk_mq_is_shared_tags(set->flags)) { set->shared_tags = blk_mq_alloc_map_and_rqs(set, BLK_MQ_NO_HCTX_IDX, set->queue_depth); if (!set->shared_tags) return -ENOMEM; } for (i = 0; i < set->nr_hw_queues; i++) { if (!__blk_mq_alloc_map_and_rqs(set, i)) goto out_unwind; cond_resched(); } return 0; out_unwind: while (--i >= 0) __blk_mq_free_map_and_rqs(set, i); if (blk_mq_is_shared_tags(set->flags)) { blk_mq_free_map_and_rqs(set, set->shared_tags, BLK_MQ_NO_HCTX_IDX); } return -ENOMEM; } /* * Allocate the request maps associated with this tag_set. Note that this * may reduce the depth asked for, if memory is tight. set->queue_depth * will be updated to reflect the allocated depth. */ static int blk_mq_alloc_set_map_and_rqs(struct blk_mq_tag_set *set) { unsigned int depth; int err; depth = set->queue_depth; do { err = __blk_mq_alloc_rq_maps(set); if (!err) break; set->queue_depth >>= 1; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) { err = -ENOMEM; break; } } while (set->queue_depth); if (!set->queue_depth || err) { pr_err("blk-mq: failed to allocate request map\n"); return -ENOMEM; } if (depth != set->queue_depth) pr_info("blk-mq: reduced tag depth (%u -> %u)\n", depth, set->queue_depth); return 0; } static void blk_mq_update_queue_map(struct blk_mq_tag_set *set) { /* * blk_mq_map_queues() and multiple .map_queues() implementations * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the * number of hardware queues. */ if (set->nr_maps == 1) set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues; if (set->ops->map_queues) { int i; /* * transport .map_queues is usually done in the following * way: * * for (queue = 0; queue < set->nr_hw_queues; queue++) { * mask = get_cpu_mask(queue) * for_each_cpu(cpu, mask) * set->map[x].mq_map[cpu] = queue; * } * * When we need to remap, the table has to be cleared for * killing stale mapping since one CPU may not be mapped * to any hw queue. */ for (i = 0; i < set->nr_maps; i++) blk_mq_clear_mq_map(&set->map[i]); set->ops->map_queues(set); } else { BUG_ON(set->nr_maps > 1); blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); } } static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set, int new_nr_hw_queues) { struct blk_mq_tags **new_tags; int i; if (set->nr_hw_queues >= new_nr_hw_queues) goto done; new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!new_tags) return -ENOMEM; if (set->tags) memcpy(new_tags, set->tags, set->nr_hw_queues * sizeof(*set->tags)); kfree(set->tags); set->tags = new_tags; for (i = set->nr_hw_queues; i < new_nr_hw_queues; i++) { if (!__blk_mq_alloc_map_and_rqs(set, i)) { while (--i >= set->nr_hw_queues) __blk_mq_free_map_and_rqs(set, i); return -ENOMEM; } cond_resched(); } done: set->nr_hw_queues = new_nr_hw_queues; return 0; } /* * Alloc a tag set to be associated with one or more request queues. * May fail with EINVAL for various error conditions. May adjust the * requested depth down, if it's too large. In that case, the set * value will be stored in set->queue_depth. */ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) { int i, ret; BUILD_BUG_ON(BLK_MQ_MAX_DEPTH > 1 << BLK_MQ_UNIQUE_TAG_BITS); if (!set->nr_hw_queues) return -EINVAL; if (!set->queue_depth) return -EINVAL; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) return -EINVAL; if (!set->ops->queue_rq) return -EINVAL; if (!set->ops->get_budget ^ !set->ops->put_budget) return -EINVAL; if (set->queue_depth > BLK_MQ_MAX_DEPTH) { pr_info("blk-mq: reduced tag depth to %u\n", BLK_MQ_MAX_DEPTH); set->queue_depth = BLK_MQ_MAX_DEPTH; } if (!set->nr_maps) set->nr_maps = 1; else if (set->nr_maps > HCTX_MAX_TYPES) return -EINVAL; /* * If a crashdump is active, then we are potentially in a very * memory constrained environment. Limit us to 64 tags to prevent * using too much memory. */ if (is_kdump_kernel()) set->queue_depth = min(64U, set->queue_depth); /* * There is no use for more h/w queues than cpus if we just have * a single map */ if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids) set->nr_hw_queues = nr_cpu_ids; if (set->flags & BLK_MQ_F_BLOCKING) { set->srcu = kmalloc(sizeof(*set->srcu), GFP_KERNEL); if (!set->srcu) return -ENOMEM; ret = init_srcu_struct(set->srcu); if (ret) goto out_free_srcu; } ret = -ENOMEM; set->tags = kcalloc_node(set->nr_hw_queues, sizeof(struct blk_mq_tags *), GFP_KERNEL, set->numa_node); if (!set->tags) goto out_cleanup_srcu; for (i = 0; i < set->nr_maps; i++) { set->map[i].mq_map = kcalloc_node(nr_cpu_ids, sizeof(set->map[i].mq_map[0]), GFP_KERNEL, set->numa_node); if (!set->map[i].mq_map) goto out_free_mq_map; set->map[i].nr_queues = set->nr_hw_queues; } blk_mq_update_queue_map(set); ret = blk_mq_alloc_set_map_and_rqs(set); if (ret) goto out_free_mq_map; mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; out_free_mq_map: for (i = 0; i < set->nr_maps; i++) { kfree(set->map[i].mq_map); set->map[i].mq_map = NULL; } kfree(set->tags); set->tags = NULL; out_cleanup_srcu: if (set->flags & BLK_MQ_F_BLOCKING) cleanup_srcu_struct(set->srcu); out_free_srcu: if (set->flags & BLK_MQ_F_BLOCKING) kfree(set->srcu); return ret; } EXPORT_SYMBOL(blk_mq_alloc_tag_set); /* allocate and initialize a tagset for a simple single-queue device */ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, const struct blk_mq_ops *ops, unsigned int queue_depth, unsigned int set_flags) { memset(set, 0, sizeof(*set)); set->ops = ops; set->nr_hw_queues = 1; set->nr_maps = 1; set->queue_depth = queue_depth; set->numa_node = NUMA_NO_NODE; set->flags = set_flags; return blk_mq_alloc_tag_set(set); } EXPORT_SYMBOL_GPL(blk_mq_alloc_sq_tag_set); void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; for (i = 0; i < set->nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); if (blk_mq_is_shared_tags(set->flags)) { blk_mq_free_map_and_rqs(set, set->shared_tags, BLK_MQ_NO_HCTX_IDX); } for (j = 0; j < set->nr_maps; j++) { kfree(set->map[j].mq_map); set->map[j].mq_map = NULL; } kfree(set->tags); set->tags = NULL; if (set->flags & BLK_MQ_F_BLOCKING) { cleanup_srcu_struct(set->srcu); kfree(set->srcu); } } EXPORT_SYMBOL(blk_mq_free_tag_set); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) { struct blk_mq_tag_set *set = q->tag_set; struct blk_mq_hw_ctx *hctx; int ret; unsigned long i; if (!set) return -EINVAL; if (q->nr_requests == nr) return 0; blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); ret = 0; queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->tags) continue; /* * If we're using an MQ scheduler, just update the scheduler * queue depth. This is similar to what the old code would do. */ if (hctx->sched_tags) { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); } else { ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr, false); } if (ret) break; if (q->elevator && q->elevator->type->ops.depth_updated) q->elevator->type->ops.depth_updated(hctx); } if (!ret) { q->nr_requests = nr; if (blk_mq_is_shared_tags(set->flags)) { if (q->elevator) blk_mq_tag_update_sched_shared_tags(q); else blk_mq_tag_resize_shared_tags(set, nr); } } blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); return ret; } /* * request_queue and elevator_type pair. * It is just used by __blk_mq_update_nr_hw_queues to cache * the elevator_type associated with a request_queue. */ struct blk_mq_qe_pair { struct list_head node; struct request_queue *q; struct elevator_type *type; }; /* * Cache the elevator_type in qe pair list and switch the * io scheduler to 'none' */ static bool blk_mq_elv_switch_none(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; qe = kmalloc(sizeof(*qe), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (!qe) return false; /* q->elevator needs protection from ->sysfs_lock */ mutex_lock(&q->sysfs_lock); /* the check has to be done with holding sysfs_lock */ if (!q->elevator) { kfree(qe); goto unlock; } INIT_LIST_HEAD(&qe->node); qe->q = q; qe->type = q->elevator->type; /* keep a reference to the elevator module as we'll switch back */ __elevator_get(qe->type); list_add(&qe->node, head); elevator_disable(q); unlock: mutex_unlock(&q->sysfs_lock); return true; } static struct blk_mq_qe_pair *blk_lookup_qe_pair(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; list_for_each_entry(qe, head, node) if (qe->q == q) return qe; return NULL; } static void blk_mq_elv_switch_back(struct list_head *head, struct request_queue *q) { struct blk_mq_qe_pair *qe; struct elevator_type *t; qe = blk_lookup_qe_pair(head, q); if (!qe) return; t = qe->type; list_del(&qe->node); kfree(qe); mutex_lock(&q->sysfs_lock); elevator_switch(q, t); /* drop the reference acquired in blk_mq_elv_switch_none */ elevator_put(t); mutex_unlock(&q->sysfs_lock); } static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { struct request_queue *q; LIST_HEAD(head); int prev_nr_hw_queues = set->nr_hw_queues; int i; lockdep_assert_held(&set->tag_list_lock); if (set->nr_maps == 1 && nr_hw_queues > nr_cpu_ids) nr_hw_queues = nr_cpu_ids; if (nr_hw_queues < 1) return; if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_freeze_queue(q); /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done * updating the new sw to hw queue mappings. */ list_for_each_entry(q, &set->tag_list, tag_set_list) if (!blk_mq_elv_switch_none(&head, q)) goto switch_back; list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_debugfs_unregister_hctxs(q); blk_mq_sysfs_unregister_hctxs(q); } if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0) goto reregister; fallback: blk_mq_update_queue_map(set); list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_realloc_hw_ctxs(set, q); blk_mq_update_poll_flag(q); if (q->nr_hw_queues != set->nr_hw_queues) { int i = prev_nr_hw_queues; pr_warn("Increasing nr_hw_queues to %d fails, fallback to %d\n", nr_hw_queues, prev_nr_hw_queues); for (; i < set->nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); set->nr_hw_queues = prev_nr_hw_queues; goto fallback; } blk_mq_map_swqueue(q); } reregister: list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_sysfs_register_hctxs(q); blk_mq_debugfs_register_hctxs(q); } switch_back: list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_elv_switch_back(&head, q); list_for_each_entry(q, &set->tag_list, tag_set_list) blk_mq_unfreeze_queue(q); /* Free the excess tags when nr_hw_queues shrink. */ for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); } void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues) { mutex_lock(&set->tag_list_lock); __blk_mq_update_nr_hw_queues(set, nr_hw_queues); mutex_unlock(&set->tag_list_lock); } EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues); static int blk_hctx_poll(struct request_queue *q, struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob, unsigned int flags) { long state = get_current_state(); int ret; do { ret = q->mq_ops->poll(hctx, iob); if (ret > 0) { __set_current_state(TASK_RUNNING); return ret; } if (signal_pending_state(state, current)) __set_current_state(TASK_RUNNING); if (task_is_running(current)) return 1; if (ret < 0 || (flags & BLK_POLL_ONESHOT)) break; cpu_relax(); } while (!need_resched()); __set_current_state(TASK_RUNNING); return 0; } int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob, unsigned int flags) { struct blk_mq_hw_ctx *hctx = xa_load(&q->hctx_table, cookie); return blk_hctx_poll(q, hctx, iob, flags); } int blk_rq_poll(struct request *rq, struct io_comp_batch *iob, unsigned int poll_flags) { struct request_queue *q = rq->q; int ret; if (!blk_rq_is_poll(rq)) return 0; if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; ret = blk_hctx_poll(q, rq->mq_hctx, iob, poll_flags); blk_queue_exit(q); return ret; } EXPORT_SYMBOL_GPL(blk_rq_poll); unsigned int blk_mq_rq_cpu(struct request *rq) { return rq->mq_ctx->cpu; } EXPORT_SYMBOL(blk_mq_rq_cpu); void blk_mq_cancel_work_sync(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; cancel_delayed_work_sync(&q->requeue_work); queue_for_each_hw_ctx(q, hctx, i) cancel_delayed_work_sync(&hctx->run_work); } static int __init blk_mq_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(blk_cpu_done, i)); for_each_possible_cpu(i) INIT_CSD(&per_cpu(blk_cpu_csd, i), __blk_mq_complete_request_remote, NULL); open_softirq(BLOCK_SOFTIRQ, blk_done_softirq); cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD, "block/softirq:dead", NULL, blk_softirq_cpu_dead); cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); cpuhp_setup_state_multi(CPUHP_AP_BLK_MQ_ONLINE, "block/mq:online", blk_mq_hctx_notify_online, blk_mq_hctx_notify_offline); return 0; } subsys_initcall(blk_mq_init); |
| 17 4 15 90 89 5 25 16 3 3 9 17 2 2 15 17 1 9 9 9 7 2 49 28 22 22 18 22 18 17 17 22 5 18 15 12 9 1 6 9 3 22 18 5 1 1 46 29 87 29 57 45 34 33 4 82 92 44 84 45 43 43 6 1 2 50 3 3 2 54 54 54 1 51 7 2 2 2 10 14 4 12 1 6 3 13 14 14 9 12 9 5 13 46 46 38 4 1 36 32 32 1 1 2 2 2 4 4 11 2 1 15 14 2 15 21 19 4 4 37 11 11 11 11 11 11 364 364 56 37 11 39 9 32 16 8 16 16 16 16 4 11 11 2 4 11 9 9 5 9 277 276 7 21 21 20 20 1 9 3 4 7 14 14 10 4 10 4 13 20 20 20 20 8 8 8 8 8 3 4 4 4 3 3 15 15 15 19 2 1 4 4 11 7 5 1 4 5 3 3 5 5 11 91 60 59 2 22 21 2 22 21 6 1 5 21 14 7 7 7 1 6 7 7 7 7 7 7 85 85 42 39 38 20 14 6 353 354 78 78 89 88 39 39 15 15 15 15 15 15 15 1 14 348 349 79 79 3 24 24 1 23 41 41 41 19 23 23 3 3 2 1 8 8 2 2 3 3 3 1 1 2 1 1 1 363 364 4 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Local APIC virtualization * * Copyright (C) 2006 Qumranet, Inc. * Copyright (C) 2007 Novell * Copyright (C) 2007 Intel * Copyright 2009 Red Hat, Inc. and/or its affiliates. * * Authors: * Dor Laor <dor.laor@qumranet.com> * Gregory Haskins <ghaskins@novell.com> * Yaozu (Eddie) Dong <eddie.dong@intel.com> * * Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/smp.h> #include <linux/hrtimer.h> #include <linux/io.h> #include <linux/export.h> #include <linux/math64.h> #include <linux/slab.h> #include <asm/processor.h> #include <asm/mce.h> #include <asm/msr.h> #include <asm/page.h> #include <asm/current.h> #include <asm/apicdef.h> #include <asm/delay.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include "kvm_cache_regs.h" #include "irq.h" #include "ioapic.h" #include "trace.h" #include "x86.h" #include "xen.h" #include "cpuid.h" #include "hyperv.h" #include "smm.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) #else #define mod_64(x, y) ((x) % (y)) #endif /* 14 is the version for Xeon and Pentium 8.4.8*/ #define APIC_VERSION 0x14UL #define LAPIC_MMIO_LENGTH (1 << 12) /* followed define is not in apicdef.h */ #define MAX_APIC_VECTOR 256 #define APIC_VECTORS_PER_REG 32 static bool lapic_timer_advance_dynamic __read_mostly; #define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100 /* clock cycles */ #define LAPIC_TIMER_ADVANCE_ADJUST_MAX 10000 /* clock cycles */ #define LAPIC_TIMER_ADVANCE_NS_INIT 1000 #define LAPIC_TIMER_ADVANCE_NS_MAX 5000 /* step-by-step approximation to mitigate fluctuation */ #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8 static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data); static int kvm_lapic_msr_write(struct kvm_lapic *apic, u32 reg, u64 data); static inline void __kvm_lapic_set_reg(char *regs, int reg_off, u32 val) { *((u32 *) (regs + reg_off)) = val; } static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val) { __kvm_lapic_set_reg(apic->regs, reg_off, val); } static __always_inline u64 __kvm_lapic_get_reg64(char *regs, int reg) { BUILD_BUG_ON(reg != APIC_ICR); return *((u64 *) (regs + reg)); } static __always_inline u64 kvm_lapic_get_reg64(struct kvm_lapic *apic, int reg) { return __kvm_lapic_get_reg64(apic->regs, reg); } static __always_inline void __kvm_lapic_set_reg64(char *regs, int reg, u64 val) { BUILD_BUG_ON(reg != APIC_ICR); *((u64 *) (regs + reg)) = val; } static __always_inline void kvm_lapic_set_reg64(struct kvm_lapic *apic, int reg, u64 val) { __kvm_lapic_set_reg64(apic->regs, reg, val); } static inline int apic_test_vector(int vec, void *bitmap) { return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector) { struct kvm_lapic *apic = vcpu->arch.apic; return apic_test_vector(vector, apic->regs + APIC_ISR) || apic_test_vector(vector, apic->regs + APIC_IRR); } static inline int __apic_test_and_set_vector(int vec, void *bitmap) { return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } static inline int __apic_test_and_clear_vector(int vec, void *bitmap) { return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } __read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu); __read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_hw_disabled, HZ); __read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_sw_disabled, HZ); static inline int apic_enabled(struct kvm_lapic *apic) { return kvm_apic_sw_enabled(apic) && kvm_apic_hw_enabled(apic); } #define LVT_MASK \ (APIC_LVT_MASKED | APIC_SEND_PENDING | APIC_VECTOR_MASK) #define LINT_MASK \ (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) static inline u32 kvm_x2apic_id(struct kvm_lapic *apic) { return apic->vcpu->vcpu_id; } static bool kvm_can_post_timer_interrupt(struct kvm_vcpu *vcpu) { return pi_inject_timer && kvm_vcpu_apicv_active(vcpu) && (kvm_mwait_in_guest(vcpu->kvm) || kvm_hlt_in_guest(vcpu->kvm)); } bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu) { return kvm_x86_ops.set_hv_timer && !(kvm_mwait_in_guest(vcpu->kvm) || kvm_can_post_timer_interrupt(vcpu)); } static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu) { return kvm_can_post_timer_interrupt(vcpu) && vcpu->mode == IN_GUEST_MODE; } static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) { return ((id >> 4) << 16) | (1 << (id & 0xf)); } static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) { switch (map->logical_mode) { case KVM_APIC_MODE_SW_DISABLED: /* Arbitrarily use the flat map so that @cluster isn't NULL. */ *cluster = map->xapic_flat_map; *mask = 0; return true; case KVM_APIC_MODE_X2APIC: { u32 offset = (dest_id >> 16) * 16; u32 max_apic_id = map->max_apic_id; if (offset <= max_apic_id) { u8 cluster_size = min(max_apic_id - offset + 1, 16U); offset = array_index_nospec(offset, map->max_apic_id + 1); *cluster = &map->phys_map[offset]; *mask = dest_id & (0xffff >> (16 - cluster_size)); } else { *mask = 0; } return true; } case KVM_APIC_MODE_XAPIC_FLAT: *cluster = map->xapic_flat_map; *mask = dest_id & 0xff; return true; case KVM_APIC_MODE_XAPIC_CLUSTER: *cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf]; *mask = dest_id & 0xf; return true; case KVM_APIC_MODE_MAP_DISABLED: return false; default: WARN_ON_ONCE(1); return false; } } static void kvm_apic_map_free(struct rcu_head *rcu) { struct kvm_apic_map *map = container_of(rcu, struct kvm_apic_map, rcu); kvfree(map); } static int kvm_recalculate_phys_map(struct kvm_apic_map *new, struct kvm_vcpu *vcpu, bool *xapic_id_mismatch) { struct kvm_lapic *apic = vcpu->arch.apic; u32 x2apic_id = kvm_x2apic_id(apic); u32 xapic_id = kvm_xapic_id(apic); u32 physical_id; /* * For simplicity, KVM always allocates enough space for all possible * xAPIC IDs. Yell, but don't kill the VM, as KVM can continue on * without the optimized map. */ if (WARN_ON_ONCE(xapic_id > new->max_apic_id)) return -EINVAL; /* * Bail if a vCPU was added and/or enabled its APIC between allocating * the map and doing the actual calculations for the map. Note, KVM * hardcodes the x2APIC ID to vcpu_id, i.e. there's no TOCTOU bug if * the compiler decides to reload x2apic_id after this check. */ if (x2apic_id > new->max_apic_id) return -E2BIG; /* * Deliberately truncate the vCPU ID when detecting a mismatched APIC * ID to avoid false positives if the vCPU ID, i.e. x2APIC ID, is a * 32-bit value. Any unwanted aliasing due to truncation results will * be detected below. */ if (!apic_x2apic_mode(apic) && xapic_id != (u8)vcpu->vcpu_id) *xapic_id_mismatch = true; /* * Apply KVM's hotplug hack if userspace has enable 32-bit APIC IDs. * Allow sending events to vCPUs by their x2APIC ID even if the target * vCPU is in legacy xAPIC mode, and silently ignore aliased xAPIC IDs * (the x2APIC ID is truncated to 8 bits, causing IDs > 0xff to wrap * and collide). * * Honor the architectural (and KVM's non-optimized) behavior if * userspace has not enabled 32-bit x2APIC IDs. Each APIC is supposed * to process messages independently. If multiple vCPUs have the same * effective APIC ID, e.g. due to the x2APIC wrap or because the guest * manually modified its xAPIC IDs, events targeting that ID are * supposed to be recognized by all vCPUs with said ID. */ if (vcpu->kvm->arch.x2apic_format) { /* See also kvm_apic_match_physical_addr(). */ if (apic_x2apic_mode(apic) || x2apic_id > 0xff) new->phys_map[x2apic_id] = apic; if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) new->phys_map[xapic_id] = apic; } else { /* * Disable the optimized map if the physical APIC ID is already * mapped, i.e. is aliased to multiple vCPUs. The optimized * map requires a strict 1:1 mapping between IDs and vCPUs. */ if (apic_x2apic_mode(apic)) physical_id = x2apic_id; else physical_id = xapic_id; if (new->phys_map[physical_id]) return -EINVAL; new->phys_map[physical_id] = apic; } return 0; } static void kvm_recalculate_logical_map(struct kvm_apic_map *new, struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; enum kvm_apic_logical_mode logical_mode; struct kvm_lapic **cluster; u16 mask; u32 ldr; if (new->logical_mode == KVM_APIC_MODE_MAP_DISABLED) return; if (!kvm_apic_sw_enabled(apic)) return; ldr = kvm_lapic_get_reg(apic, APIC_LDR); if (!ldr) return; if (apic_x2apic_mode(apic)) { logical_mode = KVM_APIC_MODE_X2APIC; } else { ldr = GET_APIC_LOGICAL_ID(ldr); if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) logical_mode = KVM_APIC_MODE_XAPIC_FLAT; else logical_mode = KVM_APIC_MODE_XAPIC_CLUSTER; } /* * To optimize logical mode delivery, all software-enabled APICs must * be configured for the same mode. */ if (new->logical_mode == KVM_APIC_MODE_SW_DISABLED) { new->logical_mode = logical_mode; } else if (new->logical_mode != logical_mode) { new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; return; } /* * In x2APIC mode, the LDR is read-only and derived directly from the * x2APIC ID, thus is guaranteed to be addressable. KVM reuses * kvm_apic_map.phys_map to optimize logical mode x2APIC interrupts by * reversing the LDR calculation to get cluster of APICs, i.e. no * additional work is required. */ if (apic_x2apic_mode(apic)) { WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic))); return; } if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask))) { new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; return; } if (!mask) return; ldr = ffs(mask) - 1; if (!is_power_of_2(mask) || cluster[ldr]) new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; else cluster[ldr] = apic; } /* * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock. * * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with * apic_map_lock_held. */ enum { CLEAN, UPDATE_IN_PROGRESS, DIRTY }; void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ bool xapic_id_mismatch; int r; /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) return; WARN_ONCE(!irqchip_in_kernel(kvm), "Dirty APIC map without an in-kernel local APIC"); mutex_lock(&kvm->arch.apic_map_lock); retry: /* * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map (if clean) * or the APIC registers (if dirty). Note, on retry the map may have * not yet been marked dirty by whatever task changed a vCPU's x2APIC * ID, i.e. the map may still show up as in-progress. In that case * this task still needs to retry and complete its calculation. */ if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty, DIRTY, UPDATE_IN_PROGRESS) == CLEAN) { /* Someone else has updated the map. */ mutex_unlock(&kvm->arch.apic_map_lock); return; } /* * Reset the mismatch flag between attempts so that KVM does the right * thing if a vCPU changes its xAPIC ID, but do NOT reset max_id, i.e. * keep max_id strictly increasing. Disallowing max_id from shrinking * ensures KVM won't get stuck in an infinite loop, e.g. if the vCPU * with the highest x2APIC ID is toggling its APIC on and off. */ xapic_id_mismatch = false; kvm_for_each_vcpu(i, vcpu, kvm) if (kvm_apic_present(vcpu)) max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic)); new = kvzalloc(sizeof(struct kvm_apic_map) + sizeof(struct kvm_lapic *) * ((u64)max_id + 1), GFP_KERNEL_ACCOUNT); if (!new) goto out; new->max_apic_id = max_id; new->logical_mode = KVM_APIC_MODE_SW_DISABLED; kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_apic_present(vcpu)) continue; r = kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch); if (r) { kvfree(new); new = NULL; if (r == -E2BIG) { cond_resched(); goto retry; } goto out; } kvm_recalculate_logical_map(new, vcpu); } out: /* * The optimized map is effectively KVM's internal version of APICv, * and all unwanted aliasing that results in disabling the optimized * map also applies to APICv. */ if (!new) kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED); else kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED); if (!new || new->logical_mode == KVM_APIC_MODE_MAP_DISABLED) kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED); else kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED); if (xapic_id_mismatch) kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); else kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); old = rcu_dereference_protected(kvm->arch.apic_map, lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); /* * Write kvm->arch.apic_map before clearing apic->apic_map_dirty. * If another update has come in, leave it DIRTY. */ atomic_cmpxchg_release(&kvm->arch.apic_map_dirty, UPDATE_IN_PROGRESS, CLEAN); mutex_unlock(&kvm->arch.apic_map_lock); if (old) call_rcu(&old->rcu, kvm_apic_map_free); kvm_make_scan_ioapic_request(kvm); } static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) { bool enabled = val & APIC_SPIV_APIC_ENABLED; kvm_lapic_set_reg(apic, APIC_SPIV, val); if (enabled != apic->sw_enabled) { apic->sw_enabled = enabled; if (enabled) static_branch_slow_dec_deferred(&apic_sw_disabled); else static_branch_inc(&apic_sw_disabled.key); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } /* Check if there are APF page ready requests pending */ if (enabled) { kvm_make_request(KVM_REQ_APF_READY, apic->vcpu); kvm_xen_sw_enable_lapic(apic->vcpu); } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) { kvm_lapic_set_reg(apic, APIC_ID, id << 24); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) { kvm_lapic_set_reg(apic, APIC_LDR, id); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline void kvm_apic_set_dfr(struct kvm_lapic *apic, u32 val) { kvm_lapic_set_reg(apic, APIC_DFR, val); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) { u32 ldr = kvm_apic_calc_x2apic_ldr(id); WARN_ON_ONCE(id != apic->vcpu->vcpu_id); kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) { return !(kvm_lapic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); } static inline int apic_lvtt_oneshot(struct kvm_lapic *apic) { return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_ONESHOT; } static inline int apic_lvtt_period(struct kvm_lapic *apic) { return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_PERIODIC; } static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic) { return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_TSCDEADLINE; } static inline int apic_lvt_nmi_mode(u32 lvt_val) { return (lvt_val & (APIC_MODE_MASK | APIC_LVT_MASKED)) == APIC_DM_NMI; } static inline bool kvm_lapic_lvt_supported(struct kvm_lapic *apic, int lvt_index) { return apic->nr_lvt_entries > lvt_index; } static inline int kvm_apic_calc_nr_lvt_entries(struct kvm_vcpu *vcpu) { return KVM_APIC_MAX_NR_LVT_ENTRIES - !(vcpu->arch.mcg_cap & MCG_CMCI_P); } void kvm_apic_set_version(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; u32 v = 0; if (!lapic_in_kernel(vcpu)) return; v = APIC_VERSION | ((apic->nr_lvt_entries - 1) << 16); /* * KVM emulates 82093AA datasheet (with in-kernel IOAPIC implementation) * which doesn't have EOI register; Some buggy OSes (e.g. Windows with * Hyper-V role) disable EOI broadcast in lapic not checking for IOAPIC * version first and level-triggered interrupts never get EOIed in * IOAPIC. */ if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) && !ioapic_in_kernel(vcpu->kvm)) v |= APIC_LVR_DIRECTED_EOI; kvm_lapic_set_reg(apic, APIC_LVR, v); } void kvm_apic_after_set_mcg_cap(struct kvm_vcpu *vcpu) { int nr_lvt_entries = kvm_apic_calc_nr_lvt_entries(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; int i; if (!lapic_in_kernel(vcpu) || nr_lvt_entries == apic->nr_lvt_entries) return; /* Initialize/mask any "new" LVT entries. */ for (i = apic->nr_lvt_entries; i < nr_lvt_entries; i++) kvm_lapic_set_reg(apic, APIC_LVTx(i), APIC_LVT_MASKED); apic->nr_lvt_entries = nr_lvt_entries; /* The number of LVT entries is reflected in the version register. */ kvm_apic_set_version(vcpu); } static const unsigned int apic_lvt_mask[KVM_APIC_MAX_NR_LVT_ENTRIES] = { [LVT_TIMER] = LVT_MASK, /* timer mode mask added at runtime */ [LVT_THERMAL_MONITOR] = LVT_MASK | APIC_MODE_MASK, [LVT_PERFORMANCE_COUNTER] = LVT_MASK | APIC_MODE_MASK, [LVT_LINT0] = LINT_MASK, [LVT_LINT1] = LINT_MASK, [LVT_ERROR] = LVT_MASK, [LVT_CMCI] = LVT_MASK | APIC_MODE_MASK }; static int find_highest_vector(void *bitmap) { int vec; u32 *reg; for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG; vec >= 0; vec -= APIC_VECTORS_PER_REG) { reg = bitmap + REG_POS(vec); if (*reg) return __fls(*reg) + vec; } return -1; } static u8 count_vectors(void *bitmap) { int vec; u32 *reg; u8 count = 0; for (vec = 0; vec < MAX_APIC_VECTOR; vec += APIC_VECTORS_PER_REG) { reg = bitmap + REG_POS(vec); count += hweight32(*reg); } return count; } bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr) { u32 i, vec; u32 pir_val, irr_val, prev_irr_val; int max_updated_irr; max_updated_irr = -1; *max_irr = -1; for (i = vec = 0; i <= 7; i++, vec += 32) { u32 *p_irr = (u32 *)(regs + APIC_IRR + i * 0x10); irr_val = *p_irr; pir_val = READ_ONCE(pir[i]); if (pir_val) { pir_val = xchg(&pir[i], 0); prev_irr_val = irr_val; do { irr_val = prev_irr_val | pir_val; } while (prev_irr_val != irr_val && !try_cmpxchg(p_irr, &prev_irr_val, irr_val)); if (prev_irr_val != irr_val) max_updated_irr = __fls(irr_val ^ prev_irr_val) + vec; } if (irr_val) *max_irr = __fls(irr_val) + vec; } return ((max_updated_irr != -1) && (max_updated_irr == *max_irr)); } EXPORT_SYMBOL_GPL(__kvm_apic_update_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr) { struct kvm_lapic *apic = vcpu->arch.apic; bool irr_updated = __kvm_apic_update_irr(pir, apic->regs, max_irr); if (unlikely(!apic->apicv_active && irr_updated)) apic->irr_pending = true; return irr_updated; } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); static inline int apic_search_irr(struct kvm_lapic *apic) { return find_highest_vector(apic->regs + APIC_IRR); } static inline int apic_find_highest_irr(struct kvm_lapic *apic) { int result; /* * Note that irr_pending is just a hint. It will be always * true with virtual interrupt delivery enabled. */ if (!apic->irr_pending) return -1; result = apic_search_irr(apic); ASSERT(result == -1 || result >= 16); return result; } static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) { if (unlikely(apic->apicv_active)) { /* need to update RVI */ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); static_call_cond(kvm_x86_hwapic_irr_update)(apic->vcpu, apic_find_highest_irr(apic)); } else { apic->irr_pending = false; kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); if (apic_search_irr(apic) != -1) apic->irr_pending = true; } } void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec) { apic_clear_irr(vec, vcpu->arch.apic); } EXPORT_SYMBOL_GPL(kvm_apic_clear_irr); static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) return; /* * With APIC virtualization enabled, all caching is disabled * because the processor can modify ISR under the hood. Instead * just set SVI. */ if (unlikely(apic->apicv_active)) static_call_cond(kvm_x86_hwapic_isr_update)(vec); else { ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); /* * ISR (in service register) bit is set when injecting an interrupt. * The highest vector is injected. Thus the latest bit set matches * the highest bit in ISR. */ apic->highest_isr_cache = vec; } } static inline int apic_find_highest_isr(struct kvm_lapic *apic) { int result; /* * Note that isr_count is always 1, and highest_isr_cache * is always -1, with APIC virtualization enabled. */ if (!apic->isr_count) return -1; if (likely(apic->highest_isr_cache != -1)) return apic->highest_isr_cache; result = find_highest_vector(apic->regs + APIC_ISR); ASSERT(result == -1 || result >= 16); return result; } static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) { if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) return; /* * We do get here for APIC virtualization enabled if the guest * uses the Hyper-V APIC enlightenment. In this case we may need * to trigger a new interrupt delivery by writing the SVI field; * on the other hand isr_count and highest_isr_cache are unused * and must be left alone. */ if (unlikely(apic->apicv_active)) static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic)); else { --apic->isr_count; BUG_ON(apic->isr_count < 0); apic->highest_isr_cache = -1; } } int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) { /* This may race with setting of irr in __apic_accept_irq() and * value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq * will cause vmexit immediately and the value will be recalculated * on the next vmentry. */ return apic_find_highest_irr(vcpu->arch.apic); } EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr); static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, int vector, int level, int trig_mode, struct dest_map *dest_map); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map) { struct kvm_lapic *apic = vcpu->arch.apic; return __apic_accept_irq(apic, irq->delivery_mode, irq->vector, irq->level, irq->trig_mode, dest_map); } static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map, struct kvm_lapic_irq *irq, u32 min) { int i, count = 0; struct kvm_vcpu *vcpu; if (min > map->max_apic_id) return 0; for_each_set_bit(i, ipi_bitmap, min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { if (map->phys_map[min + i]) { vcpu = map->phys_map[min + i]->vcpu; count += kvm_apic_set_irq(vcpu, irq, NULL); } } return count; } int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit) { struct kvm_apic_map *map; struct kvm_lapic_irq irq = {0}; int cluster_size = op_64_bit ? 64 : 32; int count; if (icr & (APIC_DEST_MASK | APIC_SHORT_MASK)) return -KVM_EINVAL; irq.vector = icr & APIC_VECTOR_MASK; irq.delivery_mode = icr & APIC_MODE_MASK; irq.level = (icr & APIC_INT_ASSERT) != 0; irq.trig_mode = icr & APIC_INT_LEVELTRIG; rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); count = -EOPNOTSUPP; if (likely(map)) { count = __pv_send_ipi(&ipi_bitmap_low, map, &irq, min); min += cluster_size; count += __pv_send_ipi(&ipi_bitmap_high, map, &irq, min); } rcu_read_unlock(); return count; } static int pv_eoi_put_user(struct kvm_vcpu *vcpu, u8 val) { return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, &val, sizeof(val)); } static int pv_eoi_get_user(struct kvm_vcpu *vcpu, u8 *val) { return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, val, sizeof(*val)); } static inline bool pv_eoi_enabled(struct kvm_vcpu *vcpu) { return vcpu->arch.pv_eoi.msr_val & KVM_MSR_ENABLED; } static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) { if (pv_eoi_put_user(vcpu, KVM_PV_EOI_ENABLED) < 0) return; __set_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } static bool pv_eoi_test_and_clr_pending(struct kvm_vcpu *vcpu) { u8 val; if (pv_eoi_get_user(vcpu, &val) < 0) return false; val &= KVM_PV_EOI_ENABLED; if (val && pv_eoi_put_user(vcpu, KVM_PV_EOI_DISABLED) < 0) return false; /* * Clear pending bit in any case: it will be set again on vmentry. * While this might not be ideal from performance point of view, * this makes sure pv eoi is only enabled when we know it's safe. */ __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); return val; } static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr) { int highest_irr; if (kvm_x86_ops.sync_pir_to_irr) highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu); else highest_irr = apic_find_highest_irr(apic); if (highest_irr == -1 || (highest_irr & 0xF0) <= ppr) return -1; return highest_irr; } static bool __apic_update_ppr(struct kvm_lapic *apic, u32 *new_ppr) { u32 tpr, isrv, ppr, old_ppr; int isr; old_ppr = kvm_lapic_get_reg(apic, APIC_PROCPRI); tpr = kvm_lapic_get_reg(apic, APIC_TASKPRI); isr = apic_find_highest_isr(apic); isrv = (isr != -1) ? isr : 0; if ((tpr & 0xf0) >= (isrv & 0xf0)) ppr = tpr & 0xff; else ppr = isrv & 0xf0; *new_ppr = ppr; if (old_ppr != ppr) kvm_lapic_set_reg(apic, APIC_PROCPRI, ppr); return ppr < old_ppr; } static void apic_update_ppr(struct kvm_lapic *apic) { u32 ppr; if (__apic_update_ppr(apic, &ppr) && apic_has_interrupt_for_ppr(apic, ppr) != -1) kvm_make_request(KVM_REQ_EVENT, apic->vcpu); } void kvm_apic_update_ppr(struct kvm_vcpu *vcpu) { apic_update_ppr(vcpu->arch.apic); } EXPORT_SYMBOL_GPL(kvm_apic_update_ppr); static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) { kvm_lapic_set_reg(apic, APIC_TASKPRI, tpr); apic_update_ppr(apic); } static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda) { return mda == (apic_x2apic_mode(apic) ? X2APIC_BROADCAST : APIC_BROADCAST); } static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda) { if (kvm_apic_broadcast(apic, mda)) return true; /* * Hotplug hack: Accept interrupts for vCPUs in xAPIC mode as if they * were in x2APIC mode if the target APIC ID can't be encoded as an * xAPIC ID. This allows unique addressing of hotplugged vCPUs (which * start in xAPIC mode) with an APIC ID that is unaddressable in xAPIC * mode. Match the x2APIC ID if and only if the target APIC ID can't * be encoded in xAPIC to avoid spurious matches against a vCPU that * changed its (addressable) xAPIC ID (which is writable). */ if (apic_x2apic_mode(apic) || mda > 0xff) return mda == kvm_x2apic_id(apic); return mda == kvm_xapic_id(apic); } static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) { u32 logical_id; if (kvm_apic_broadcast(apic, mda)) return true; logical_id = kvm_lapic_get_reg(apic, APIC_LDR); if (apic_x2apic_mode(apic)) return ((logical_id >> 16) == (mda >> 16)) && (logical_id & mda & 0xffff) != 0; logical_id = GET_APIC_LOGICAL_ID(logical_id); switch (kvm_lapic_get_reg(apic, APIC_DFR)) { case APIC_DFR_FLAT: return (logical_id & mda) != 0; case APIC_DFR_CLUSTER: return ((logical_id >> 4) == (mda >> 4)) && (logical_id & mda & 0xf) != 0; default: return false; } } /* The KVM local APIC implementation has two quirks: * * - Real hardware delivers interrupts destined to x2APIC ID > 0xff to LAPICs * in xAPIC mode if the "destination & 0xff" matches its xAPIC ID. * KVM doesn't do that aliasing. * * - in-kernel IOAPIC messages have to be delivered directly to * x2APIC, because the kernel does not support interrupt remapping. * In order to support broadcast without interrupt remapping, x2APIC * rewrites the destination of non-IPI messages from APIC_BROADCAST * to X2APIC_BROADCAST. * * The broadcast quirk can be disabled with KVM_CAP_X2APIC_API. This is * important when userspace wants to use x2APIC-format MSIs, because * APIC_BROADCAST (0xff) is a legal route for "cluster 0, CPUs 0-7". */ static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id, struct kvm_lapic *source, struct kvm_lapic *target) { bool ipi = source != NULL; if (!vcpu->kvm->arch.x2apic_broadcast_quirk_disabled && !ipi && dest_id == APIC_BROADCAST && apic_x2apic_mode(target)) return X2APIC_BROADCAST; return dest_id; } bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int shorthand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; u32 mda = kvm_apic_mda(vcpu, dest, source, target); ASSERT(target); switch (shorthand) { case APIC_DEST_NOSHORT: if (dest_mode == APIC_DEST_PHYSICAL) return kvm_apic_match_physical_addr(target, mda); else return kvm_apic_match_logical_addr(target, mda); case APIC_DEST_SELF: return target == source; case APIC_DEST_ALLINC: return true; case APIC_DEST_ALLBUT: return target != source; default: return false; } } EXPORT_SYMBOL_GPL(kvm_apic_match_dest); int kvm_vector_to_index(u32 vector, u32 dest_vcpus, const unsigned long *bitmap, u32 bitmap_size) { u32 mod; int i, idx = -1; mod = vector % dest_vcpus; for (i = 0; i <= mod; i++) { idx = find_next_bit(bitmap, bitmap_size, idx + 1); BUG_ON(idx == bitmap_size); } return idx; } static void kvm_apic_disabled_lapic_found(struct kvm *kvm) { if (!kvm->arch.disabled_lapic_found) { kvm->arch.disabled_lapic_found = true; pr_info("Disabled LAPIC found during irq injection\n"); } } static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src, struct kvm_lapic_irq *irq, struct kvm_apic_map *map) { if (kvm->arch.x2apic_broadcast_quirk_disabled) { if ((irq->dest_id == APIC_BROADCAST && map->logical_mode != KVM_APIC_MODE_X2APIC)) return true; if (irq->dest_id == X2APIC_BROADCAST) return true; } else { bool x2apic_ipi = src && *src && apic_x2apic_mode(*src); if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST)) return true; } return false; } /* Return true if the interrupt can be handled by using *bitmap as index mask * for valid destinations in *dst array. * Return false if kvm_apic_map_get_dest_lapic did nothing useful. * Note: we may have zero kvm_lapic destinations when we return true, which * means that the interrupt should be dropped. In this case, *bitmap would be * zero and *dst undefined. */ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, struct kvm_lapic **src, struct kvm_lapic_irq *irq, struct kvm_apic_map *map, struct kvm_lapic ***dst, unsigned long *bitmap) { int i, lowest; if (irq->shorthand == APIC_DEST_SELF && src) { *dst = src; *bitmap = 1; return true; } else if (irq->shorthand) return false; if (!map || kvm_apic_is_broadcast_dest(kvm, src, irq, map)) return false; if (irq->dest_mode == APIC_DEST_PHYSICAL) { if (irq->dest_id > map->max_apic_id) { *bitmap = 0; } else { u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1); *dst = &map->phys_map[dest_id]; *bitmap = 1; } return true; } *bitmap = 0; if (!kvm_apic_map_get_logical_dest(map, irq->dest_id, dst, (u16 *)bitmap)) return false; if (!kvm_lowest_prio_delivery(irq)) return true; if (!kvm_vector_hashing_enabled()) { lowest = -1; for_each_set_bit(i, bitmap, 16) { if (!(*dst)[i]) continue; if (lowest < 0) lowest = i; else if (kvm_apic_compare_prio((*dst)[i]->vcpu, (*dst)[lowest]->vcpu) < 0) lowest = i; } } else { if (!*bitmap) return true; lowest = kvm_vector_to_index(irq->vector, hweight16(*bitmap), bitmap, 16); if (!(*dst)[lowest]) { kvm_apic_disabled_lapic_found(kvm); *bitmap = 0; return true; } } *bitmap = (lowest >= 0) ? 1 << lowest : 0; return true; } bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map) { struct kvm_apic_map *map; unsigned long bitmap; struct kvm_lapic **dst = NULL; int i; bool ret; *r = -1; if (irq->shorthand == APIC_DEST_SELF) { if (KVM_BUG_ON(!src, kvm)) { *r = 0; return true; } *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); return true; } rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dst, &bitmap); if (ret) { *r = 0; for_each_set_bit(i, &bitmap, 16) { if (!dst[i]) continue; *r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map); } } rcu_read_unlock(); return ret; } /* * This routine tries to handle interrupts in posted mode, here is how * it deals with different cases: * - For single-destination interrupts, handle it in posted mode * - Else if vector hashing is enabled and it is a lowest-priority * interrupt, handle it in posted mode and use the following mechanism * to find the destination vCPU. * 1. For lowest-priority interrupts, store all the possible * destination vCPUs in an array. * 2. Use "guest vector % max number of destination vCPUs" to find * the right destination vCPU in the array for the lowest-priority * interrupt. * - Otherwise, use remapped mode to inject the interrupt. */ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu) { struct kvm_apic_map *map; unsigned long bitmap; struct kvm_lapic **dst = NULL; bool ret = false; if (irq->shorthand) return false; rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); if (kvm_apic_map_get_dest_lapic(kvm, NULL, irq, map, &dst, &bitmap) && hweight16(bitmap) == 1) { unsigned long i = find_first_bit(&bitmap, 16); if (dst[i]) { *dest_vcpu = dst[i]->vcpu; ret = true; } } rcu_read_unlock(); return ret; } /* * Add a pending IRQ into lapic. * Return 1 if successfully added and 0 if discarded. */ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, int vector, int level, int trig_mode, struct dest_map *dest_map) { int result = 0; struct kvm_vcpu *vcpu = apic->vcpu; trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); switch (delivery_mode) { case APIC_DM_LOWEST: vcpu->arch.apic_arb_prio++; fallthrough; case APIC_DM_FIXED: if (unlikely(trig_mode && !level)) break; /* FIXME add logic for vcpu on reset */ if (unlikely(!apic_enabled(apic))) break; result = 1; if (dest_map) { __set_bit(vcpu->vcpu_id, dest_map->map); dest_map->vectors[vcpu->vcpu_id] = vector; } if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) { if (trig_mode) kvm_lapic_set_vector(vector, apic->regs + APIC_TMR); else kvm_lapic_clear_vector(vector, apic->regs + APIC_TMR); } static_call(kvm_x86_deliver_interrupt)(apic, delivery_mode, trig_mode, vector); break; case APIC_DM_REMRD: result = 1; vcpu->arch.pv.pv_unhalted = 1; kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); break; case APIC_DM_SMI: if (!kvm_inject_smi(vcpu)) { kvm_vcpu_kick(vcpu); result = 1; } break; case APIC_DM_NMI: result = 1; kvm_inject_nmi(vcpu); kvm_vcpu_kick(vcpu); break; case APIC_DM_INIT: if (!trig_mode || level) { result = 1; /* assumes that there are only KVM_APIC_INIT/SIPI */ apic->pending_events = (1UL << KVM_APIC_INIT); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } break; case APIC_DM_STARTUP: result = 1; apic->sipi_vector = vector; /* make sure sipi_vector is visible for the receiver */ smp_wmb(); set_bit(KVM_APIC_SIPI, &apic->pending_events); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); break; case APIC_DM_EXTINT: /* * Should only be called by kvm_apic_local_deliver() with LVT0, * before NMI watchdog was enabled. Already handled by * kvm_apic_accept_pic_intr(). */ break; default: printk(KERN_ERR "TODO: unsupported delivery mode %x\n", delivery_mode); break; } return result; } /* * This routine identifies the destination vcpus mask meant to receive the * IOAPIC interrupts. It either uses kvm_apic_map_get_dest_lapic() to find * out the destination vcpus array and set the bitmap or it traverses to * each available vcpu to identify the same. */ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, unsigned long *vcpu_bitmap) { struct kvm_lapic **dest_vcpu = NULL; struct kvm_lapic *src = NULL; struct kvm_apic_map *map; struct kvm_vcpu *vcpu; unsigned long bitmap, i; int vcpu_idx; bool ret; rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); ret = kvm_apic_map_get_dest_lapic(kvm, &src, irq, map, &dest_vcpu, &bitmap); if (ret) { for_each_set_bit(i, &bitmap, 16) { if (!dest_vcpu[i]) continue; vcpu_idx = dest_vcpu[i]->vcpu->vcpu_idx; __set_bit(vcpu_idx, vcpu_bitmap); } } else { kvm_for_each_vcpu(i, vcpu, kvm) { if (!kvm_apic_present(vcpu)) continue; if (!kvm_apic_match_dest(vcpu, NULL, irq->shorthand, irq->dest_id, irq->dest_mode)) continue; __set_bit(i, vcpu_bitmap); } } rcu_read_unlock(); } int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) { return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; } static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector) { return test_bit(vector, apic->vcpu->arch.ioapic_handled_vectors); } static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) { int trigger_mode; /* Eoi the ioapic only if the ioapic doesn't own the vector. */ if (!kvm_ioapic_handles_vector(apic, vector)) return; /* Request a KVM exit to inform the userspace IOAPIC. */ if (irqchip_split(apic->vcpu->kvm)) { apic->vcpu->arch.pending_ioapic_eoi = vector; kvm_make_request(KVM_REQ_IOAPIC_EOI_EXIT, apic->vcpu); return; } if (apic_test_vector(vector, apic->regs + APIC_TMR)) trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); } static int apic_set_eoi(struct kvm_lapic *apic) { int vector = apic_find_highest_isr(apic); trace_kvm_eoi(apic, vector); /* * Not every write EOI will has corresponding ISR, * one example is when Kernel check timer on setup_IO_APIC */ if (vector == -1) return vector; apic_clear_isr(vector, apic); apic_update_ppr(apic); if (kvm_hv_synic_has_vector(apic->vcpu, vector)) kvm_hv_synic_send_eoi(apic->vcpu, vector); kvm_ioapic_send_eoi(apic, vector); kvm_make_request(KVM_REQ_EVENT, apic->vcpu); return vector; } /* * this interface assumes a trap-like exit, which has already finished * desired side effect including vISR and vPPR update. */ void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector) { struct kvm_lapic *apic = vcpu->arch.apic; trace_kvm_eoi(apic, vector); kvm_ioapic_send_eoi(apic, vector); kvm_make_request(KVM_REQ_EVENT, apic->vcpu); } EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated); void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high) { struct kvm_lapic_irq irq; /* KVM has no delay and should always clear the BUSY/PENDING flag. */ WARN_ON_ONCE(icr_low & APIC_ICR_BUSY); irq.vector = icr_low & APIC_VECTOR_MASK; irq.delivery_mode = icr_low & APIC_MODE_MASK; irq.dest_mode = icr_low & APIC_DEST_MASK; irq.level = (icr_low & APIC_INT_ASSERT) != 0; irq.trig_mode = icr_low & APIC_INT_LEVELTRIG; irq.shorthand = icr_low & APIC_SHORT_MASK; irq.msi_redir_hint = false; if (apic_x2apic_mode(apic)) irq.dest_id = icr_high; else irq.dest_id = GET_XAPIC_DEST_FIELD(icr_high); trace_kvm_apic_ipi(icr_low, irq.dest_id); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL); } EXPORT_SYMBOL_GPL(kvm_apic_send_ipi); static u32 apic_get_tmcct(struct kvm_lapic *apic) { ktime_t remaining, now; s64 ns; ASSERT(apic != NULL); /* if initial count is 0, current count should also be 0 */ if (kvm_lapic_get_reg(apic, APIC_TMICT) == 0 || apic->lapic_timer.period == 0) return 0; now = ktime_get(); remaining = ktime_sub(apic->lapic_timer.target_expiration, now); if (ktime_to_ns(remaining) < 0) remaining = 0; ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period); return div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->divide_count)); } static void __report_tpr_access(struct kvm_lapic *apic, bool write) { struct kvm_vcpu *vcpu = apic->vcpu; struct kvm_run *run = vcpu->run; kvm_make_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu); run->tpr_access.rip = kvm_rip_read(vcpu); run->tpr_access.is_write = write; } static inline void report_tpr_access(struct kvm_lapic *apic, bool write) { if (apic->vcpu->arch.tpr_access_reporting) __report_tpr_access(apic, write); } static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) { u32 val = 0; if (offset >= LAPIC_MMIO_LENGTH) return 0; switch (offset) { case APIC_ARBPRI: break; case APIC_TMCCT: /* Timer CCR */ if (apic_lvtt_tscdeadline(apic)) return 0; val = apic_get_tmcct(apic); break; case APIC_PROCPRI: apic_update_ppr(apic); val = kvm_lapic_get_reg(apic, offset); break; case APIC_TASKPRI: report_tpr_access(apic, false); fallthrough; default: val = kvm_lapic_get_reg(apic, offset); break; } return val; } static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev) { return container_of(dev, struct kvm_lapic, dev); } #define APIC_REG_MASK(reg) (1ull << ((reg) >> 4)) #define APIC_REGS_MASK(first, count) \ (APIC_REG_MASK(first) * ((1ull << (count)) - 1)) u64 kvm_lapic_readable_reg_mask(struct kvm_lapic *apic) { /* Leave bits '0' for reserved and write-only registers. */ u64 valid_reg_mask = APIC_REG_MASK(APIC_ID) | APIC_REG_MASK(APIC_LVR) | APIC_REG_MASK(APIC_TASKPRI) | APIC_REG_MASK(APIC_PROCPRI) | APIC_REG_MASK(APIC_LDR) | APIC_REG_MASK(APIC_SPIV) | APIC_REGS_MASK(APIC_ISR, APIC_ISR_NR) | APIC_REGS_MASK(APIC_TMR, APIC_ISR_NR) | APIC_REGS_MASK(APIC_IRR, APIC_ISR_NR) | APIC_REG_MASK(APIC_ESR) | APIC_REG_MASK(APIC_ICR) | APIC_REG_MASK(APIC_LVTT) | APIC_REG_MASK(APIC_LVTTHMR) | APIC_REG_MASK(APIC_LVTPC) | APIC_REG_MASK(APIC_LVT0) | APIC_REG_MASK(APIC_LVT1) | APIC_REG_MASK(APIC_LVTERR) | APIC_REG_MASK(APIC_TMICT) | APIC_REG_MASK(APIC_TMCCT) | APIC_REG_MASK(APIC_TDCR); if (kvm_lapic_lvt_supported(apic, LVT_CMCI)) valid_reg_mask |= APIC_REG_MASK(APIC_LVTCMCI); /* ARBPRI, DFR, and ICR2 are not valid in x2APIC mode. */ if (!apic_x2apic_mode(apic)) valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI) | APIC_REG_MASK(APIC_DFR) | APIC_REG_MASK(APIC_ICR2); return valid_reg_mask; } EXPORT_SYMBOL_GPL(kvm_lapic_readable_reg_mask); static int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len, void *data) { unsigned char alignment = offset & 0xf; u32 result; /* * WARN if KVM reads ICR in x2APIC mode, as it's an 8-byte register in * x2APIC and needs to be manually handled by the caller. */ WARN_ON_ONCE(apic_x2apic_mode(apic) && offset == APIC_ICR); if (alignment + len > 4) return 1; if (offset > 0x3f0 || !(kvm_lapic_readable_reg_mask(apic) & APIC_REG_MASK(offset))) return 1; result = __apic_read(apic, offset & ~0xf); trace_kvm_apic_read(offset, result); switch (len) { case 1: case 2: case 4: memcpy(data, (char *)&result + alignment, len); break; default: printk(KERN_ERR "Local APIC read with len = %x, " "should be 1,2, or 4 instead\n", len); break; } return 0; } static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) { return addr >= apic->base_address && addr < apic->base_address + LAPIC_MMIO_LENGTH; } static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, void *data) { struct kvm_lapic *apic = to_lapic(this); u32 offset = address - apic->base_address; if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) return -EOPNOTSUPP; memset(data, 0xff, len); return 0; } kvm_lapic_reg_read(apic, offset, len, data); return 0; } static void update_divide_count(struct kvm_lapic *apic) { u32 tmp1, tmp2, tdcr; tdcr = kvm_lapic_get_reg(apic, APIC_TDCR); tmp1 = tdcr & 0xf; tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1; apic->divide_count = 0x1 << (tmp2 & 0x7); } static void limit_periodic_timer_frequency(struct kvm_lapic *apic) { /* * Do not allow the guest to program periodic timers with small * interval, since the hrtimers are not throttled by the host * scheduler. */ if (apic_lvtt_period(apic) && apic->lapic_timer.period) { s64 min_period = min_timer_period_us * 1000LL; if (apic->lapic_timer.period < min_period) { pr_info_ratelimited( "vcpu %i: requested %lld ns " "lapic timer period limited to %lld ns\n", apic->vcpu->vcpu_id, apic->lapic_timer.period, min_period); apic->lapic_timer.period = min_period; } } } static void cancel_hv_timer(struct kvm_lapic *apic); static void cancel_apic_timer(struct kvm_lapic *apic) { hrtimer_cancel(&apic->lapic_timer.timer); preempt_disable(); if (apic->lapic_timer.hv_timer_in_use) cancel_hv_timer(apic); preempt_enable(); atomic_set(&apic->lapic_timer.pending, 0); } static void apic_update_lvtt(struct kvm_lapic *apic) { u32 timer_mode = kvm_lapic_get_reg(apic, APIC_LVTT) & apic->lapic_timer.timer_mode_mask; if (apic->lapic_timer.timer_mode != timer_mode) { if (apic_lvtt_tscdeadline(apic) != (timer_mode == APIC_LVT_TIMER_TSCDEADLINE)) { cancel_apic_timer(apic); kvm_lapic_set_reg(apic, APIC_TMICT, 0); apic->lapic_timer.period = 0; apic->lapic_timer.tscdeadline = 0; } apic->lapic_timer.timer_mode = timer_mode; limit_periodic_timer_frequency(apic); } } /* * On APICv, this test will cause a busy wait * during a higher-priority task. */ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = kvm_lapic_get_reg(apic, APIC_LVTT); if (kvm_apic_hw_enabled(apic)) { int vec = reg & APIC_VECTOR_MASK; void *bitmap = apic->regs + APIC_ISR; if (apic->apicv_active) bitmap = apic->regs + APIC_IRR; if (apic_test_vector(vec, bitmap)) return true; } return false; } static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles) { u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns; /* * If the guest TSC is running at a different ratio than the host, then * convert the delay to nanoseconds to achieve an accurate delay. Note * that __delay() uses delay_tsc whenever the hardware has TSC, thus * always for VMX enabled hardware. */ if (vcpu->arch.tsc_scaling_ratio == kvm_caps.default_tsc_scaling_ratio) { __delay(min(guest_cycles, nsec_to_cycles(vcpu, timer_advance_ns))); } else { u64 delay_ns = guest_cycles * 1000000ULL; do_div(delay_ns, vcpu->arch.virtual_tsc_khz); ndelay(min_t(u32, delay_ns, timer_advance_ns)); } } static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu, s64 advance_expire_delta) { struct kvm_lapic *apic = vcpu->arch.apic; u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns; u64 ns; /* Do not adjust for tiny fluctuations or large random spikes. */ if (abs(advance_expire_delta) > LAPIC_TIMER_ADVANCE_ADJUST_MAX || abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_MIN) return; /* too early */ if (advance_expire_delta < 0) { ns = -advance_expire_delta * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); timer_advance_ns -= ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } else { /* too late */ ns = advance_expire_delta * 1000000ULL; do_div(ns, vcpu->arch.virtual_tsc_khz); timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP; } if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX)) timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; apic->lapic_timer.timer_advance_ns = timer_advance_ns; } static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; u64 guest_tsc, tsc_deadline; tsc_deadline = apic->lapic_timer.expired_tscdeadline; apic->lapic_timer.expired_tscdeadline = 0; guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); if (lapic_timer_advance_dynamic) { adjust_lapic_timer_advance(vcpu, guest_tsc - tsc_deadline); /* * If the timer fired early, reread the TSC to account for the * overhead of the above adjustment to avoid waiting longer * than is necessary. */ if (guest_tsc < tsc_deadline) guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); } if (guest_tsc < tsc_deadline) __wait_lapic_expire(vcpu, tsc_deadline - guest_tsc); } void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu) { if (lapic_in_kernel(vcpu) && vcpu->arch.apic->lapic_timer.expired_tscdeadline && vcpu->arch.apic->lapic_timer.timer_advance_ns && lapic_timer_int_injected(vcpu)) __kvm_wait_lapic_expire(vcpu); } EXPORT_SYMBOL_GPL(kvm_wait_lapic_expire); static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic) { struct kvm_timer *ktimer = &apic->lapic_timer; kvm_apic_local_deliver(apic, APIC_LVTT); if (apic_lvtt_tscdeadline(apic)) { ktimer->tscdeadline = 0; } else if (apic_lvtt_oneshot(apic)) { ktimer->tscdeadline = 0; ktimer->target_expiration = 0; } } static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) { struct kvm_vcpu *vcpu = apic->vcpu; struct kvm_timer *ktimer = &apic->lapic_timer; if (atomic_read(&apic->lapic_timer.pending)) return; if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use) ktimer->expired_tscdeadline = ktimer->tscdeadline; if (!from_timer_fn && apic->apicv_active) { WARN_ON(kvm_get_running_vcpu() != vcpu); kvm_apic_inject_pending_timer_irqs(apic); return; } if (kvm_use_posted_timer_interrupt(apic->vcpu)) { /* * Ensure the guest's timer has truly expired before posting an * interrupt. Open code the relevant checks to avoid querying * lapic_timer_int_injected(), which will be false since the * interrupt isn't yet injected. Waiting until after injecting * is not an option since that won't help a posted interrupt. */ if (vcpu->arch.apic->lapic_timer.expired_tscdeadline && vcpu->arch.apic->lapic_timer.timer_advance_ns) __kvm_wait_lapic_expire(vcpu); kvm_apic_inject_pending_timer_irqs(apic); return; } atomic_inc(&apic->lapic_timer.pending); kvm_make_request(KVM_REQ_UNBLOCK, vcpu); if (from_timer_fn) kvm_vcpu_kick(vcpu); } static void start_sw_tscdeadline(struct kvm_lapic *apic) { struct kvm_timer *ktimer = &apic->lapic_timer; u64 guest_tsc, tscdeadline = ktimer->tscdeadline; u64 ns = 0; ktime_t expire; struct kvm_vcpu *vcpu = apic->vcpu; unsigned long this_tsc_khz = vcpu->arch.virtual_tsc_khz; unsigned long flags; ktime_t now; if (unlikely(!tscdeadline || !this_tsc_khz)) return; local_irq_save(flags); now = ktime_get(); guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); ns = (tscdeadline - guest_tsc) * 1000000ULL; do_div(ns, this_tsc_khz); if (likely(tscdeadline > guest_tsc) && likely(ns > apic->lapic_timer.timer_advance_ns)) { expire = ktime_add_ns(now, ns); expire = ktime_sub_ns(expire, ktimer->timer_advance_ns); hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_HARD); } else apic_timer_expired(apic, false); local_irq_restore(flags); } static inline u64 tmict_to_ns(struct kvm_lapic *apic, u32 tmict) { return (u64)tmict * APIC_BUS_CYCLE_NS * (u64)apic->divide_count; } static void update_target_expiration(struct kvm_lapic *apic, uint32_t old_divisor) { ktime_t now, remaining; u64 ns_remaining_old, ns_remaining_new; apic->lapic_timer.period = tmict_to_ns(apic, kvm_lapic_get_reg(apic, APIC_TMICT)); limit_periodic_timer_frequency(apic); now = ktime_get(); remaining = ktime_sub(apic->lapic_timer.target_expiration, now); if (ktime_to_ns(remaining) < 0) remaining = 0; ns_remaining_old = ktime_to_ns(remaining); ns_remaining_new = mul_u64_u32_div(ns_remaining_old, apic->divide_count, old_divisor); apic->lapic_timer.tscdeadline += nsec_to_cycles(apic->vcpu, ns_remaining_new) - nsec_to_cycles(apic->vcpu, ns_remaining_old); apic->lapic_timer.target_expiration = ktime_add_ns(now, ns_remaining_new); } static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg) { ktime_t now; u64 tscl = rdtsc(); s64 deadline; now = ktime_get(); apic->lapic_timer.period = tmict_to_ns(apic, kvm_lapic_get_reg(apic, APIC_TMICT)); if (!apic->lapic_timer.period) { apic->lapic_timer.tscdeadline = 0; return false; } limit_periodic_timer_frequency(apic); deadline = apic->lapic_timer.period; if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { if (unlikely(count_reg != APIC_TMICT)) { deadline = tmict_to_ns(apic, kvm_lapic_get_reg(apic, count_reg)); if (unlikely(deadline <= 0)) { if (apic_lvtt_period(apic)) deadline = apic->lapic_timer.period; else deadline = 0; } else if (unlikely(deadline > apic->lapic_timer.period)) { pr_info_ratelimited( "vcpu %i: requested lapic timer restore with " "starting count register %#x=%u (%lld ns) > initial count (%lld ns). " "Using initial count to start timer.\n", apic->vcpu->vcpu_id, count_reg, kvm_lapic_get_reg(apic, count_reg), deadline, apic->lapic_timer.period); kvm_lapic_set_reg(apic, count_reg, 0); deadline = apic->lapic_timer.period; } } } apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + nsec_to_cycles(apic->vcpu, deadline); apic->lapic_timer.target_expiration = ktime_add_ns(now, deadline); return true; } static void advance_periodic_target_expiration(struct kvm_lapic *apic) { ktime_t now = ktime_get(); u64 tscl = rdtsc(); ktime_t delta; /* * Synchronize both deadlines to the same time source or * differences in the periods (caused by differences in the * underlying clocks or numerical approximation errors) will * cause the two to drift apart over time as the errors * accumulate. */ apic->lapic_timer.target_expiration = ktime_add_ns(apic->lapic_timer.target_expiration, apic->lapic_timer.period); delta = ktime_sub(apic->lapic_timer.target_expiration, now); apic->lapic_timer.tscdeadline = kvm_read_l1_tsc(apic->vcpu, tscl) + nsec_to_cycles(apic->vcpu, delta); } static void start_sw_period(struct kvm_lapic *apic) { if (!apic->lapic_timer.period) return; if (ktime_after(ktime_get(), apic->lapic_timer.target_expiration)) { apic_timer_expired(apic, false); if (apic_lvtt_oneshot(apic)) return; advance_periodic_target_expiration(apic); } hrtimer_start(&apic->lapic_timer.timer, apic->lapic_timer.target_expiration, HRTIMER_MODE_ABS_HARD); } bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) return false; return vcpu->arch.apic->lapic_timer.hv_timer_in_use; } static void cancel_hv_timer(struct kvm_lapic *apic) { WARN_ON(preemptible()); WARN_ON(!apic->lapic_timer.hv_timer_in_use); static_call(kvm_x86_cancel_hv_timer)(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; } static bool start_hv_timer(struct kvm_lapic *apic) { struct kvm_timer *ktimer = &apic->lapic_timer; struct kvm_vcpu *vcpu = apic->vcpu; bool expired; WARN_ON(preemptible()); if (!kvm_can_use_hv_timer(vcpu)) return false; if (!ktimer->tscdeadline) return false; if (static_call(kvm_x86_set_hv_timer)(vcpu, ktimer->tscdeadline, &expired)) return false; ktimer->hv_timer_in_use = true; hrtimer_cancel(&ktimer->timer); /* * To simplify handling the periodic timer, leave the hv timer running * even if the deadline timer has expired, i.e. rely on the resulting * VM-Exit to recompute the periodic timer's target expiration. */ if (!apic_lvtt_period(apic)) { /* * Cancel the hv timer if the sw timer fired while the hv timer * was being programmed, or if the hv timer itself expired. */ if (atomic_read(&ktimer->pending)) { cancel_hv_timer(apic); } else if (expired) { apic_timer_expired(apic, false); cancel_hv_timer(apic); } } trace_kvm_hv_timer_state(vcpu->vcpu_id, ktimer->hv_timer_in_use); return true; } static void start_sw_timer(struct kvm_lapic *apic) { struct kvm_timer *ktimer = &apic->lapic_timer; WARN_ON(preemptible()); if (apic->lapic_timer.hv_timer_in_use) cancel_hv_timer(apic); if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) return; if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) start_sw_period(apic); else if (apic_lvtt_tscdeadline(apic)) start_sw_tscdeadline(apic); trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, false); } static void restart_apic_timer(struct kvm_lapic *apic) { preempt_disable(); if (!apic_lvtt_period(apic) && atomic_read(&apic->lapic_timer.pending)) goto out; if (!start_hv_timer(apic)) start_sw_timer(apic); out: preempt_enable(); } void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; preempt_disable(); /* If the preempt notifier has already run, it also called apic_timer_expired */ if (!apic->lapic_timer.hv_timer_in_use) goto out; WARN_ON(kvm_vcpu_is_blocking(vcpu)); apic_timer_expired(apic, false); cancel_hv_timer(apic); if (apic_lvtt_period(apic) && apic->lapic_timer.period) { advance_periodic_target_expiration(apic); restart_apic_timer(apic); } out: preempt_enable(); } EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu) { restart_apic_timer(vcpu->arch.apic); } void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; preempt_disable(); /* Possibly the TSC deadline timer is not enabled yet */ if (apic->lapic_timer.hv_timer_in_use) start_sw_timer(apic); preempt_enable(); } void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; WARN_ON(!apic->lapic_timer.hv_timer_in_use); restart_apic_timer(apic); } static void __start_apic_timer(struct kvm_lapic *apic, u32 count_reg) { atomic_set(&apic->lapic_timer.pending, 0); if ((apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) && !set_target_expiration(apic, count_reg)) return; restart_apic_timer(apic); } static void start_apic_timer(struct kvm_lapic *apic) { __start_apic_timer(apic, APIC_TMICT); } static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) { bool lvt0_in_nmi_mode = apic_lvt_nmi_mode(lvt0_val); if (apic->lvt0_in_nmi_mode != lvt0_in_nmi_mode) { apic->lvt0_in_nmi_mode = lvt0_in_nmi_mode; if (lvt0_in_nmi_mode) { atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); } else atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); } } static int get_lvt_index(u32 reg) { if (reg == APIC_LVTCMCI) return LVT_CMCI; if (reg < APIC_LVTT || reg > APIC_LVTERR) return -1; return array_index_nospec( (reg - APIC_LVTT) >> 4, KVM_APIC_MAX_NR_LVT_ENTRIES); } static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) { int ret = 0; trace_kvm_apic_write(reg, val); switch (reg) { case APIC_ID: /* Local APIC ID */ if (!apic_x2apic_mode(apic)) { kvm_apic_set_xapic_id(apic, val >> 24); } else { ret = 1; } break; case APIC_TASKPRI: report_tpr_access(apic, true); apic_set_tpr(apic, val & 0xff); break; case APIC_EOI: apic_set_eoi(apic); break; case APIC_LDR: if (!apic_x2apic_mode(apic)) kvm_apic_set_ldr(apic, val & APIC_LDR_MASK); else ret = 1; break; case APIC_DFR: if (!apic_x2apic_mode(apic)) kvm_apic_set_dfr(apic, val | 0x0FFFFFFF); else ret = 1; break; case APIC_SPIV: { u32 mask = 0x3ff; if (kvm_lapic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI) mask |= APIC_SPIV_DIRECTED_EOI; apic_set_spiv(apic, val & mask); if (!(val & APIC_SPIV_APIC_ENABLED)) { int i; for (i = 0; i < apic->nr_lvt_entries; i++) { kvm_lapic_set_reg(apic, APIC_LVTx(i), kvm_lapic_get_reg(apic, APIC_LVTx(i)) | APIC_LVT_MASKED); } apic_update_lvtt(apic); atomic_set(&apic->lapic_timer.pending, 0); } break; } case APIC_ICR: WARN_ON_ONCE(apic_x2apic_mode(apic)); /* No delay here, so we always clear the pending bit */ val &= ~APIC_ICR_BUSY; kvm_apic_send_ipi(apic, val, kvm_lapic_get_reg(apic, APIC_ICR2)); kvm_lapic_set_reg(apic, APIC_ICR, val); break; case APIC_ICR2: if (apic_x2apic_mode(apic)) ret = 1; else kvm_lapic_set_reg(apic, APIC_ICR2, val & 0xff000000); break; case APIC_LVT0: apic_manage_nmi_watchdog(apic, val); fallthrough; case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: case APIC_LVTERR: case APIC_LVTCMCI: { u32 index = get_lvt_index(reg); if (!kvm_lapic_lvt_supported(apic, index)) { ret = 1; break; } if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; val &= apic_lvt_mask[index]; kvm_lapic_set_reg(apic, reg, val); break; } case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); kvm_lapic_set_reg(apic, APIC_LVTT, val); apic_update_lvtt(apic); break; case APIC_TMICT: if (apic_lvtt_tscdeadline(apic)) break; cancel_apic_timer(apic); kvm_lapic_set_reg(apic, APIC_TMICT, val); start_apic_timer(apic); break; case APIC_TDCR: { uint32_t old_divisor = apic->divide_count; kvm_lapic_set_reg(apic, APIC_TDCR, val & 0xb); update_divide_count(apic); if (apic->divide_count != old_divisor && apic->lapic_timer.period) { hrtimer_cancel(&apic->lapic_timer.timer); update_target_expiration(apic, old_divisor); restart_apic_timer(apic); } break; } case APIC_ESR: if (apic_x2apic_mode(apic) && val != 0) ret = 1; break; case APIC_SELF_IPI: /* * Self-IPI exists only when x2APIC is enabled. Bits 7:0 hold * the vector, everything else is reserved. */ if (!apic_x2apic_mode(apic) || (val & ~APIC_VECTOR_MASK)) ret = 1; else kvm_apic_send_ipi(apic, APIC_DEST_SELF | val, 0); break; default: ret = 1; break; } /* * Recalculate APIC maps if necessary, e.g. if the software enable bit * was toggled, the APIC ID changed, etc... The maps are marked dirty * on relevant changes, i.e. this is a nop for most writes. */ kvm_recalculate_apic_map(apic->vcpu->kvm); return ret; } static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, const void *data) { struct kvm_lapic *apic = to_lapic(this); unsigned int offset = address - apic->base_address; u32 val; if (!apic_mmio_in_range(apic, address)) return -EOPNOTSUPP; if (!kvm_apic_hw_enabled(apic) || apic_x2apic_mode(apic)) { if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LAPIC_MMIO_HOLE)) return -EOPNOTSUPP; return 0; } /* * APIC register must be aligned on 128-bits boundary. * 32/64/128 bits registers must be accessed thru 32 bits. * Refer SDM 8.4.1 */ if (len != 4 || (offset & 0xf)) return 0; val = *(u32*)data; kvm_lapic_reg_write(apic, offset & 0xff0, val); return 0; } void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) { kvm_lapic_reg_write(vcpu->arch.apic, APIC_EOI, 0); } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); /* emulate APIC access in a trap manner */ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { struct kvm_lapic *apic = vcpu->arch.apic; /* * ICR is a single 64-bit register when x2APIC is enabled, all others * registers hold 32-bit values. For legacy xAPIC, ICR writes need to * go down the common path to get the upper half from ICR2. * * Note, using the write helpers may incur an unnecessary write to the * virtual APIC state, but KVM needs to conditionally modify the value * in certain cases, e.g. to clear the ICR busy bit. The cost of extra * conditional branches is likely a wash relative to the cost of the * maybe-unecessary write, and both are in the noise anyways. */ if (apic_x2apic_mode(apic) && offset == APIC_ICR) kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); else kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode); void kvm_free_lapic(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; if (!vcpu->arch.apic) { static_branch_dec(&kvm_has_noapic_vcpu); return; } hrtimer_cancel(&apic->lapic_timer.timer); if (!(vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE)) static_branch_slow_dec_deferred(&apic_hw_disabled); if (!apic->sw_enabled) static_branch_slow_dec_deferred(&apic_sw_disabled); if (apic->regs) free_page((unsigned long)apic->regs); kfree(apic); } /* *---------------------------------------------------------------------- * LAPIC interface *---------------------------------------------------------------------- */ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; if (!kvm_apic_present(vcpu) || !apic_lvtt_tscdeadline(apic)) return 0; return apic->lapic_timer.tscdeadline; } void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; if (!kvm_apic_present(vcpu) || !apic_lvtt_tscdeadline(apic)) return; hrtimer_cancel(&apic->lapic_timer.timer); apic->lapic_timer.tscdeadline = data; start_apic_timer(apic); } void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) { apic_set_tpr(vcpu->arch.apic, (cr8 & 0x0f) << 4); } u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) { u64 tpr; tpr = (u64) kvm_lapic_get_reg(vcpu->arch.apic, APIC_TASKPRI); return (tpr & 0xf0) >> 4; } void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) { u64 old_value = vcpu->arch.apic_base; struct kvm_lapic *apic = vcpu->arch.apic; vcpu->arch.apic_base = value; if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) kvm_update_cpuid_runtime(vcpu); if (!apic) return; /* update jump label if enable bit changes */ if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) { if (value & MSR_IA32_APICBASE_ENABLE) { kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); static_branch_slow_dec_deferred(&apic_hw_disabled); /* Check if there are APF page ready requests pending */ kvm_make_request(KVM_REQ_APF_READY, vcpu); } else { static_branch_inc(&apic_hw_disabled.key); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } if ((old_value ^ value) & X2APIC_ENABLE) { if (value & X2APIC_ENABLE) kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); else if (value & MSR_IA32_APICBASE_ENABLE) kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); } if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) { kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); static_call_cond(kvm_x86_set_virtual_apic_mode)(vcpu); } apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; if ((value & MSR_IA32_APICBASE_ENABLE) && apic->base_address != APIC_DEFAULT_PHYS_BASE) { kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); } } void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; if (apic->apicv_active) { /* irr_pending is always true when apicv is activated. */ apic->irr_pending = true; apic->isr_count = 1; } else { /* * Don't clear irr_pending, searching the IRR can race with * updates from the CPU as APICv is still active from hardware's * perspective. The flag will be cleared as appropriate when * KVM injects the interrupt. */ apic->isr_count = count_vectors(apic->regs + APIC_ISR); } apic->highest_isr_cache = -1; } int kvm_alloc_apic_access_page(struct kvm *kvm) { struct page *page; void __user *hva; int ret = 0; mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_memslot_enabled || kvm->arch.apic_access_memslot_inhibited) goto out; hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); if (IS_ERR(hva)) { ret = PTR_ERR(hva); goto out; } page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (is_error_page(page)) { ret = -EFAULT; goto out; } /* * Do not pin the page in memory, so that memory hot-unplug * is able to migrate it. */ put_page(page); kvm->arch.apic_access_memslot_enabled = true; out: mutex_unlock(&kvm->slots_lock); return ret; } EXPORT_SYMBOL_GPL(kvm_alloc_apic_access_page); void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; if (!kvm->arch.apic_access_memslot_enabled) return; kvm_vcpu_srcu_read_unlock(vcpu); mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_memslot_enabled) { __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); /* * Clear "enabled" after the memslot is deleted so that a * different vCPU doesn't get a false negative when checking * the flag out of slots_lock. No additional memory barrier is * needed as modifying memslots requires waiting other vCPUs to * drop SRCU (see above), and false positives are ok as the * flag is rechecked after acquiring slots_lock. */ kvm->arch.apic_access_memslot_enabled = false; /* * Mark the memslot as inhibited to prevent reallocating the * memslot during vCPU creation, e.g. if a vCPU is hotplugged. */ kvm->arch.apic_access_memslot_inhibited = true; } mutex_unlock(&kvm->slots_lock); kvm_vcpu_srcu_read_lock(vcpu); } void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic = vcpu->arch.apic; u64 msr_val; int i; static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); if (!init_event) { msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_reset_bsp(vcpu)) msr_val |= MSR_IA32_APICBASE_BSP; kvm_lapic_set_base(vcpu, msr_val); } if (!apic) return; /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); /* The xAPIC ID is set at RESET even if the APIC was already enabled. */ if (!init_event) kvm_apic_set_xapic_id(apic, vcpu->vcpu_id); kvm_apic_set_version(apic->vcpu); for (i = 0; i < apic->nr_lvt_entries; i++) kvm_lapic_set_reg(apic, APIC_LVTx(i), APIC_LVT_MASKED); apic_update_lvtt(apic); if (kvm_vcpu_is_reset_bsp(vcpu) && kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) kvm_lapic_set_reg(apic, APIC_LVT0, SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); kvm_apic_set_dfr(apic, 0xffffffffU); apic_set_spiv(apic, 0xff); kvm_lapic_set_reg(apic, APIC_TASKPRI, 0); if (!apic_x2apic_mode(apic)) kvm_apic_set_ldr(apic, 0); kvm_lapic_set_reg(apic, APIC_ESR, 0); if (!apic_x2apic_mode(apic)) { kvm_lapic_set_reg(apic, APIC_ICR, 0); kvm_lapic_set_reg(apic, APIC_ICR2, 0); } else { kvm_lapic_set_reg64(apic, APIC_ICR, 0); } kvm_lapic_set_reg(apic, APIC_TDCR, 0); kvm_lapic_set_reg(apic, APIC_TMICT, 0); for (i = 0; i < 8; i++) { kvm_lapic_set_reg(apic, APIC_IRR + 0x10 * i, 0); kvm_lapic_set_reg(apic, APIC_ISR + 0x10 * i, 0); kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } kvm_apic_update_apicv(vcpu); update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, -1); static_call_cond(kvm_x86_hwapic_isr_update)(-1); } vcpu->arch.apic_arb_prio = 0; vcpu->arch.apic_attention = 0; kvm_recalculate_apic_map(vcpu->kvm); } /* *---------------------------------------------------------------------- * timer interface *---------------------------------------------------------------------- */ static bool lapic_is_periodic(struct kvm_lapic *apic) { return apic_lvtt_period(apic); } int apic_has_pending_timer(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; if (apic_enabled(apic) && apic_lvt_enabled(apic, APIC_LVTT)) return atomic_read(&apic->lapic_timer.pending); return 0; } int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; int r; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); if (r && lvt_type == APIC_LVTPC && guest_cpuid_is_intel_compatible(apic->vcpu)) kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); return r; } return 0; } void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; if (apic) kvm_apic_local_deliver(apic, APIC_LVT0); } static const struct kvm_io_device_ops apic_mmio_ops = { .read = apic_mmio_read, .write = apic_mmio_write, }; static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) { struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer); apic_timer_expired(apic, true); if (lapic_is_periodic(apic)) { advance_periodic_target_expiration(apic); hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); return HRTIMER_RESTART; } else return HRTIMER_NORESTART; } int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) { struct kvm_lapic *apic; ASSERT(vcpu != NULL); if (!irqchip_in_kernel(vcpu->kvm)) { static_branch_inc(&kvm_has_noapic_vcpu); return 0; } apic = kzalloc(sizeof(*apic), GFP_KERNEL_ACCOUNT); if (!apic) goto nomem; vcpu->arch.apic = apic; if (kvm_x86_ops.alloc_apic_backing_page) apic->regs = static_call(kvm_x86_alloc_apic_backing_page)(vcpu); else apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!apic->regs) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); goto nomem_free_apic; } apic->vcpu = vcpu; apic->nr_lvt_entries = kvm_apic_calc_nr_lvt_entries(vcpu); hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); apic->lapic_timer.timer.function = apic_timer_fn; if (timer_advance_ns == -1) { apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT; lapic_timer_advance_dynamic = true; } else { apic->lapic_timer.timer_advance_ns = timer_advance_ns; lapic_timer_advance_dynamic = false; } /* * Stuff the APIC ENABLE bit in lieu of temporarily incrementing * apic_hw_disabled; the full RESET value is set by kvm_lapic_reset(). */ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE; static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_iodevice_init(&apic->dev, &apic_mmio_ops); /* * Defer evaluating inhibits until the vCPU is first run, as this vCPU * will not get notified of any changes until this vCPU is visible to * other vCPUs (marked online and added to the set of vCPUs). * * Opportunistically mark APICv active as VMX in particularly is highly * unlikely to have inhibits. Ignore the current per-VM APICv state so * that vCPU creation is guaranteed to run with a deterministic value, * the request will ensure the vCPU gets the correct state before VM-Entry. */ if (enable_apicv) { apic->apicv_active = true; kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } return 0; nomem_free_apic: kfree(apic); vcpu->arch.apic = NULL; nomem: return -ENOMEM; } int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; if (!kvm_apic_present(vcpu)) return -1; __apic_update_ppr(apic, &ppr); return apic_has_interrupt_for_ppr(apic, ppr); } EXPORT_SYMBOL_GPL(kvm_apic_has_interrupt); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) { u32 lvt0 = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVT0); if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return 1; if ((lvt0 & APIC_LVT_MASKED) == 0 && GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) return 1; return 0; } void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; if (atomic_read(&apic->lapic_timer.pending) > 0) { kvm_apic_inject_pending_timer_irqs(apic); atomic_set(&apic->lapic_timer.pending, 0); } } int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) { int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; if (vector == -1) return -1; /* * We get here even with APIC virtualization enabled, if doing * nested virtualization and L1 runs with the "acknowledge interrupt * on exit" mode. Then we cannot inject the interrupt via RVI, * because the process would deliver it through the IDT. */ apic_clear_irr(vector, apic); if (kvm_hv_synic_auto_eoi_set(vcpu, vector)) { /* * For auto-EOI interrupts, there might be another pending * interrupt above PPR, so check whether to raise another * KVM_REQ_EVENT. */ apic_update_ppr(apic); } else { /* * For normal interrupts, PPR has been raised and there cannot * be a higher-priority pending interrupt---except if there was * a concurrent interrupt injection, but that would have * triggered KVM_REQ_EVENT already. */ apic_set_isr(vector, apic); __apic_update_ppr(apic, &ppr); } return vector; } static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s, bool set) { if (apic_x2apic_mode(vcpu->arch.apic)) { u32 *id = (u32 *)(s->regs + APIC_ID); u32 *ldr = (u32 *)(s->regs + APIC_LDR); u64 icr; if (vcpu->kvm->arch.x2apic_format) { if (*id != vcpu->vcpu_id) return -EINVAL; } else { if (set) *id >>= 24; else *id <<= 24; } /* * In x2APIC mode, the LDR is fixed and based on the id. And * ICR is internally a single 64-bit register, but needs to be * split to ICR+ICR2 in userspace for backwards compatibility. */ if (set) { *ldr = kvm_apic_calc_x2apic_ldr(*id); icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) | (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32; __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr); } else { icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); } } return 0; } int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { memcpy(s->regs, vcpu->arch.apic->regs, sizeof(*s)); /* * Get calculated timer current count for remaining timer period (if * any) and store it in the returned register set. */ __kvm_lapic_set_reg(s->regs, APIC_TMCCT, __apic_read(vcpu->arch.apic, APIC_TMCCT)); return kvm_apic_state_fixup(vcpu, s, false); } int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { struct kvm_lapic *apic = vcpu->arch.apic; int r; static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); r = kvm_apic_state_fixup(vcpu, s, true); if (r) { kvm_recalculate_apic_map(vcpu->kvm); return r; } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); apic_update_ppr(apic); cancel_apic_timer(apic); apic->lapic_timer.expired_tscdeadline = 0; apic_update_lvtt(apic); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); update_divide_count(apic); __start_apic_timer(apic, APIC_TMCCT); kvm_lapic_set_reg(apic, APIC_TMCCT, 0); kvm_apic_update_apicv(vcpu); if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_rtc_eoi_tracking_restore_one(vcpu); vcpu->arch.apic_arb_prio = 0; return 0; } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) { struct hrtimer *timer; if (!lapic_in_kernel(vcpu) || kvm_can_post_timer_interrupt(vcpu)) return; timer = &vcpu->arch.apic->lapic_timer.timer; if (hrtimer_cancel(timer)) hrtimer_start_expires(timer, HRTIMER_MODE_ABS_HARD); } /* * apic_sync_pv_eoi_from_guest - called on vmexit or cancel interrupt * * Detect whether guest triggered PV EOI since the * last entry. If yes, set EOI on guests's behalf. * Clear PV EOI in guest memory in any case. */ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, struct kvm_lapic *apic) { int vector; /* * PV EOI state is derived from KVM_APIC_PV_EOI_PENDING in host * and KVM_PV_EOI_ENABLED in guest memory as follows: * * KVM_APIC_PV_EOI_PENDING is unset: * -> host disabled PV EOI. * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is set: * -> host enabled PV EOI, guest did not execute EOI yet. * KVM_APIC_PV_EOI_PENDING is set, KVM_PV_EOI_ENABLED is unset: * -> host enabled PV EOI, guest executed EOI. */ BUG_ON(!pv_eoi_enabled(vcpu)); if (pv_eoi_test_and_clr_pending(vcpu)) return; vector = apic_set_eoi(apic); trace_kvm_pv_eoi(apic, vector); } void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) { u32 data; if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention)) apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic); if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, sizeof(u32))) return; apic_set_tpr(vcpu->arch.apic, data & 0xff); } /* * apic_sync_pv_eoi_to_guest - called before vmentry * * Detect whether it's safe to enable PV EOI and * if yes do so. */ static void apic_sync_pv_eoi_to_guest(struct kvm_vcpu *vcpu, struct kvm_lapic *apic) { if (!pv_eoi_enabled(vcpu) || /* IRR set or many bits in ISR: could be nested. */ apic->irr_pending || /* Cache not set: could be safe but we don't bother. */ apic->highest_isr_cache == -1 || /* Need EOI to update ioapic. */ kvm_ioapic_handles_vector(apic, apic->highest_isr_cache)) { /* * PV EOI was disabled by apic_sync_pv_eoi_from_guest * so we need not do anything here. */ return; } pv_eoi_set_pending(apic->vcpu); } void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) { u32 data, tpr; int max_irr, max_isr; struct kvm_lapic *apic = vcpu->arch.apic; apic_sync_pv_eoi_to_guest(vcpu, apic); if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; tpr = kvm_lapic_get_reg(apic, APIC_TASKPRI) & 0xff; max_irr = apic_find_highest_irr(apic); if (max_irr < 0) max_irr = 0; max_isr = apic_find_highest_isr(apic); if (max_isr < 0) max_isr = 0; data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24); kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, sizeof(u32)); } int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) { if (vapic_addr) { if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apic->vapic_cache, vapic_addr, sizeof(u32))) return -EINVAL; __set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention); } else { __clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention); } vcpu->arch.apic->vapic_addr = vapic_addr; return 0; } int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) { data &= ~APIC_ICR_BUSY; kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); kvm_lapic_set_reg64(apic, APIC_ICR, data); trace_kvm_apic_write(APIC_ICR, data); return 0; } static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data) { u32 low; if (reg == APIC_ICR) { *data = kvm_lapic_get_reg64(apic, APIC_ICR); return 0; } if (kvm_lapic_reg_read(apic, reg, 4, &low)) return 1; *data = low; return 0; } static int kvm_lapic_msr_write(struct kvm_lapic *apic, u32 reg, u64 data) { /* * ICR is a 64-bit register in x2APIC mode (and Hyper-V PV vAPIC) and * can be written as such, all other registers remain accessible only * through 32-bit reads/writes. */ if (reg == APIC_ICR) return kvm_x2apic_icr_write(apic, data); /* Bits 63:32 are reserved in all other registers. */ if (data >> 32) return 1; return kvm_lapic_reg_write(apic, reg, (u32)data); } int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data) { struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = (msr - APIC_BASE_MSR) << 4; if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) return 1; return kvm_lapic_msr_write(apic, reg, data); } int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) { struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = (msr - APIC_BASE_MSR) << 4; if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) return 1; return kvm_lapic_msr_read(apic, reg, data); } int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data) { if (!lapic_in_kernel(vcpu)) return 1; return kvm_lapic_msr_write(vcpu->arch.apic, reg, data); } int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data) { if (!lapic_in_kernel(vcpu)) return 1; return kvm_lapic_msr_read(vcpu->arch.apic, reg, data); } int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len) { u64 addr = data & ~KVM_MSR_ENABLED; struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data; unsigned long new_len; int ret; if (!IS_ALIGNED(addr, 4)) return 1; if (data & KVM_MSR_ENABLED) { if (addr == ghc->gpa && len <= ghc->len) new_len = ghc->len; else new_len = len; ret = kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len); if (ret) return ret; } vcpu->arch.pv_eoi.msr_val = data; return 0; } int kvm_apic_accept_events(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; u8 sipi_vector; int r; if (!kvm_apic_has_pending_init_or_sipi(vcpu)) return 0; if (is_guest_mode(vcpu)) { r = kvm_check_nested_events(vcpu); if (r < 0) return r == -EBUSY ? 0 : r; /* * Continue processing INIT/SIPI even if a nested VM-Exit * occurred, e.g. pending SIPIs should be dropped if INIT+SIPI * are blocked as a result of transitioning to VMX root mode. */ } /* * INITs are blocked while CPU is in specific states (SMM, VMX root * mode, SVM with GIF=0), while SIPIs are dropped if the CPU isn't in * wait-for-SIPI (WFS). */ if (!kvm_apic_init_sipi_allowed(vcpu)) { WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); clear_bit(KVM_APIC_SIPI, &apic->pending_events); return 0; } if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) { kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; } if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events)) { if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { /* evaluate pending_events before reading the vector */ smp_rmb(); sipi_vector = apic->sipi_vector; static_call(kvm_x86_vcpu_deliver_sipi_vector)(vcpu, sipi_vector); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } } return 0; } void kvm_lapic_exit(void) { static_key_deferred_flush(&apic_hw_disabled); WARN_ON(static_branch_unlikely(&apic_hw_disabled.key)); static_key_deferred_flush(&apic_sw_disabled); WARN_ON(static_branch_unlikely(&apic_sw_disabled.key)); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * SM4 Cipher Algorithm, AES-NI/AVX2 optimized. * as specified in * https://tools.ietf.org/id/draft-ribose-cfrg-sm4-10.html * * Copyright (c) 2021, Alibaba Group. * Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com> */ #include <linux/module.h> #include <linux/crypto.h> #include <linux/kernel.h> #include <asm/simd.h> #include <crypto/internal/simd.h> #include <crypto/internal/skcipher.h> #include <crypto/sm4.h> #include "sm4-avx.h" #define SM4_CRYPT16_BLOCK_SIZE (SM4_BLOCK_SIZE * 16) asmlinkage void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); asmlinkage void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int key_len) { struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); return sm4_expandkey(ctx, key, key_len); } static int cbc_decrypt(struct skcipher_request *req) { return sm4_avx_cbc_decrypt(req, SM4_CRYPT16_BLOCK_SIZE, sm4_aesni_avx2_cbc_dec_blk16); } static int ctr_crypt(struct skcipher_request *req) { return sm4_avx_ctr_crypt(req, SM4_CRYPT16_BLOCK_SIZE, sm4_aesni_avx2_ctr_enc_blk16); } static struct skcipher_alg sm4_aesni_avx2_skciphers[] = { { .base = { .cra_name = "__ecb(sm4)", .cra_driver_name = "__ecb-sm4-aesni-avx2", .cra_priority = 500, .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = SM4_BLOCK_SIZE, .cra_ctxsize = sizeof(struct sm4_ctx), .cra_module = THIS_MODULE, }, .min_keysize = SM4_KEY_SIZE, .max_keysize = SM4_KEY_SIZE, .walksize = 16 * SM4_BLOCK_SIZE, .setkey = sm4_skcipher_setkey, .encrypt = sm4_avx_ecb_encrypt, .decrypt = sm4_avx_ecb_decrypt, }, { .base = { .cra_name = "__cbc(sm4)", .cra_driver_name = "__cbc-sm4-aesni-avx2", .cra_priority = 500, .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = SM4_BLOCK_SIZE, .cra_ctxsize = sizeof(struct sm4_ctx), .cra_module = THIS_MODULE, }, .min_keysize = SM4_KEY_SIZE, .max_keysize = SM4_KEY_SIZE, .ivsize = SM4_BLOCK_SIZE, .walksize = 16 * SM4_BLOCK_SIZE, .setkey = sm4_skcipher_setkey, .encrypt = sm4_cbc_encrypt, .decrypt = cbc_decrypt, }, { .base = { .cra_name = "__ctr(sm4)", .cra_driver_name = "__ctr-sm4-aesni-avx2", .cra_priority = 500, .cra_flags = CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct sm4_ctx), .cra_module = THIS_MODULE, }, .min_keysize = SM4_KEY_SIZE, .max_keysize = SM4_KEY_SIZE, .ivsize = SM4_BLOCK_SIZE, .chunksize = SM4_BLOCK_SIZE, .walksize = 16 * SM4_BLOCK_SIZE, .setkey = sm4_skcipher_setkey, .encrypt = ctr_crypt, .decrypt = ctr_crypt, } }; static struct simd_skcipher_alg * simd_sm4_aesni_avx2_skciphers[ARRAY_SIZE(sm4_aesni_avx2_skciphers)]; static int __init sm4_init(void) { const char *feature_name; if (!boot_cpu_has(X86_FEATURE_AVX) || !boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_AES) || !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX2 or AES-NI instructions are not detected.\n"); return -ENODEV; } if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, &feature_name)) { pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } return simd_register_skciphers_compat(sm4_aesni_avx2_skciphers, ARRAY_SIZE(sm4_aesni_avx2_skciphers), simd_sm4_aesni_avx2_skciphers); } static void __exit sm4_exit(void) { simd_unregister_skciphers(sm4_aesni_avx2_skciphers, ARRAY_SIZE(sm4_aesni_avx2_skciphers), simd_sm4_aesni_avx2_skciphers); } module_init(sm4_init); module_exit(sm4_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Tianjia Zhang <tianjia.zhang@linux.alibaba.com>"); MODULE_DESCRIPTION("SM4 Cipher Algorithm, AES-NI/AVX2 optimized"); MODULE_ALIAS_CRYPTO("sm4"); MODULE_ALIAS_CRYPTO("sm4-aesni-avx2"); |
| 24 693 144 3484 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_H #define _IPV6_H #include <uapi/linux/ipv6.h> #include <linux/cache.h> #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) #define ipv6_authlen(p) (((p)->hdrlen+2) << 2) /* * This structure contains configuration options per IPv6 link. */ struct ipv6_devconf { /* RX & TX fastpath fields. */ __cacheline_group_begin(ipv6_devconf_read_txrx); __s32 disable_ipv6; __s32 hop_limit; __s32 mtu6; __s32 forwarding; __s32 disable_policy; __s32 proxy_ndp; __cacheline_group_end(ipv6_devconf_read_txrx); __s32 accept_ra; __s32 accept_redirects; __s32 autoconf; __s32 dad_transmits; __s32 rtr_solicits; __s32 rtr_solicit_interval; __s32 rtr_solicit_max_interval; __s32 rtr_solicit_delay; __s32 force_mld_version; __s32 mldv1_unsolicited_report_interval; __s32 mldv2_unsolicited_report_interval; __s32 use_tempaddr; __s32 temp_valid_lft; __s32 temp_prefered_lft; __s32 regen_min_advance; __s32 regen_max_retry; __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; __u32 ra_defrtr_metric; __s32 accept_ra_min_hop_limit; __s32 accept_ra_min_lft; __s32 accept_ra_pinfo; __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; #ifdef CONFIG_IPV6_ROUTE_INFO __s32 accept_ra_rt_info_min_plen; __s32 accept_ra_rt_info_max_plen; #endif #endif __s32 accept_source_route; __s32 accept_ra_from_local; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD __s32 optimistic_dad; __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE atomic_t mc_forwarding; #endif __s32 drop_unicast_in_l2_multicast; __s32 accept_dad; __s32 force_tllao; __s32 ndisc_notify; __s32 suppress_frag_ndisc; __s32 accept_ra_mtu; __s32 drop_unsolicited_na; __s32 accept_untracked_na; struct ipv6_stable_secret { bool initialized; struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; __s32 keep_addr_on_down; __s32 seg6_enabled; #ifdef CONFIG_IPV6_SEG6_HMAC __s32 seg6_require_hmac; #endif __u32 enhanced_dad; __u32 addr_gen_mode; __s32 ndisc_tclass; __s32 rpl_seg_enabled; __u32 ioam6_id; __u32 ioam6_id_wide; __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; __u8 ra_honor_pio_life; struct ctl_table_header *sysctl_header; }; struct ipv6_params { __s32 disable_ipv6; __s32 autoconf; }; extern struct ipv6_params ipv6_defaults; #include <linux/tcp.h> #include <linux/udp.h> #include <net/inet_sock.h> static inline struct ipv6hdr *ipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_network_header(skb); } static inline struct ipv6hdr *inner_ipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_inner_network_header(skb); } static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) { return (struct ipv6hdr *)skb_transport_header(skb); } static inline unsigned int ipv6_transport_len(const struct sk_buff *skb) { return ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr) - skb_network_header_len(skb); } /* This structure contains results of exthdrs parsing as offsets from skb->nh. */ struct inet6_skb_parm { int iif; __be16 ra; __u16 dst0; __u16 srcrt; __u16 dst1; __u16 lastopt; __u16 nhoff; __u16 flags; #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) __u16 dsthao; #endif __u16 frag_max_size; __u16 srhoff; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 #define IP6SKB_REROUTED 4 #define IP6SKB_ROUTERALERT 8 #define IP6SKB_FRAGMENTED 16 #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 #define IP6SKB_SEG6 256 #define IP6SKB_FAKEJUMBO 512 #define IP6SKB_MULTIPATH 1024 }; #if defined(CONFIG_NET_L3_MASTER_DEV) static inline bool ipv6_l3mdev_skb(__u16 flags) { return flags & IP6SKB_L3SLAVE; } #else static inline bool ipv6_l3mdev_skb(__u16 flags) { return false; } #endif #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) #define IP6CBMTU(skb) ((struct ip6_mtuinfo *)((skb)->cb)) static inline int inet6_iif(const struct sk_buff *skb) { bool l3_slave = ipv6_l3mdev_skb(IP6CB(skb)->flags); return l3_slave ? skb->skb_iif : IP6CB(skb)->iif; } static inline bool inet6_is_jumbogram(const struct sk_buff *skb) { return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM); } /* can not be used in TCP layer after tcp_v6_fill_cb */ static inline int inet6_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) return IP6CB(skb)->iif; #endif return 0; } struct tcp6_request_sock { struct tcp_request_sock tcp6rsk_tcp; }; struct ipv6_mc_socklist; struct ipv6_ac_socklist; struct ipv6_fl_socklist; struct inet6_cork { struct ipv6_txoptions *opt; u8 hop_limit; u8 tclass; }; /* struct ipv6_pinfo - ipv6 private area */ struct ipv6_pinfo { struct in6_addr saddr; struct in6_pktinfo sticky_pktinfo; const struct in6_addr *daddr_cache; #ifdef CONFIG_IPV6_SUBTREES const struct in6_addr *saddr_cache; #endif __be32 flow_label; __u32 frag_size; s16 hop_limit; u8 mcast_hops; int ucast_oif; int mcast_oif; /* pktoption flags */ union { struct { __u16 srcrt:1, osrcrt:1, rxinfo:1, rxoinfo:1, rxhlim:1, rxohlim:1, hopopts:1, ohopopts:1, dstopts:1, odstopts:1, rxflow:1, rxtclass:1, rxpmtu:1, rxorigdstaddr:1, recvfragsize:1; /* 1 bits hole */ } bits; __u16 all; } rxopt; /* sockopt flags */ __u8 srcprefs; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ __u8 pmtudisc; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; __u32 dst_cookie; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; struct ipv6_fl_socklist __rcu *ipv6_fl_list; struct ipv6_txoptions __rcu *opt; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; struct inet6_cork cork; }; /* We currently use available bits from inet_sk(sk)->inet_flags, * this could change in the future. */ #define inet6_test_bit(nr, sk) \ test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_set_bit(nr, sk) \ set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_clear_bit(nr, sk) \ clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) #define inet6_assign_bit(nr, sk, val) \ assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */ struct raw6_sock { /* inet_sock has to be the first member of raw6_sock */ struct inet_sock inet; __u32 checksum; /* perform checksum */ __u32 offset; /* checksum offset */ struct icmp6_filter filter; __u32 ip6mr_table; struct ipv6_pinfo inet6; }; struct udp6_sock { struct udp_sock udp; struct ipv6_pinfo inet6; }; struct tcp6_sock { struct tcp_sock tcp; struct ipv6_pinfo inet6; }; extern int inet6_sk_rebuild_header(struct sock *sk); struct tcp6_timewait_sock { struct tcp_timewait_sock tcp6tw_tcp; }; #if IS_ENABLED(CONFIG_IPV6) bool ipv6_mod_enabled(void); static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { return sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL; } #define raw6_sk(ptr) container_of_const(ptr, struct raw6_sock, inet.sk) #define ipv6_only_sock(sk) (sk->sk_ipv6only) #define ipv6_sk_rxinfo(sk) ((sk)->sk_family == PF_INET6 && \ inet6_sk(sk)->rxopt.bits.rxinfo) static inline const struct in6_addr *inet6_rcv_saddr(const struct sock *sk) { if (sk->sk_family == AF_INET6) return &sk->sk_v6_rcv_saddr; return NULL; } static inline int inet_v6_ipv6only(const struct sock *sk) { /* ipv6only field is at same position for timewait and other sockets */ return ipv6_only_sock(sk); } #else #define ipv6_only_sock(sk) 0 #define ipv6_sk_rxinfo(sk) 0 static inline bool ipv6_mod_enabled(void) { return false; } static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) { return NULL; } static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ |
| 9 2 1 2 2 1 1 3 14 1 1 1 11 4 9 1 7 3 4 2 1 3 1 3 1 1 50 2 3 36 10 22 14 11 5 1 7 2 1 3 6 6 23 23 23 104 30 2 1 1 1 3 6 16 2 2 2 1 2 1 1 1 24 1 4 1 1 1 1 7 2 1 5 5 3 2 3 1 3 7 2 10 2 3 4 1 4 2 3 9 12 12 1 13 13 13 8 1 1 6 5 1 1 3 1 22 22 22 22 12 12 12 12 11 11 15 36 36 36 36 36 36 35 36 36 5 18 15 7 6 18 6 12 2 5 3 23 3 20 36 36 20 10 10 10 2 2 10 10 10 2 1 3 3 3 3 3 3 3 3 3 3 2 2 11 22 22 22 14 2 12 3 3 27 7 22 22 1 1 24 1 1 3 20 7 9 3 3 3 1 1 10 9 1 9 1 1 17 17 9 7 2 9 9 1 2 1 3 2 1 1 1 1 1 1 23 23 23 23 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic PPP layer for Linux. * * Copyright 1999-2002 Paul Mackerras. * * The generic PPP layer handles the PPP network interfaces, the * /dev/ppp device, packet and VJ compression, and multilink. * It talks to PPP `channels' via the interface defined in * include/linux/ppp_channel.h. Channels provide the basic means for * sending and receiving PPP frames on some kind of communications * channel. * * Part of the code in this driver was inspired by the old async-only * PPP driver, written by Michael Callahan and Al Longyear, and * subsequently hacked by Paul Mackerras. * * ==FILEVERSION 20041108== */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/list.h> #include <linux/idr.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/ppp_defs.h> #include <linux/filter.h> #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/ppp-comp.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/spinlock.h> #include <linux/rwsem.h> #include <linux/stddef.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/file.h> #include <asm/unaligned.h> #include <net/slhc_vj.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #define PPP_VERSION "2.4.2" /* * Network protocols we support. */ #define NP_IP 0 /* Internet Protocol V4 */ #define NP_IPV6 1 /* Internet Protocol V6 */ #define NP_IPX 2 /* IPX protocol */ #define NP_AT 3 /* Appletalk protocol */ #define NP_MPLS_UC 4 /* MPLS unicast */ #define NP_MPLS_MC 5 /* MPLS multicast */ #define NUM_NP 6 /* Number of NPs. */ #define MPHDRLEN 6 /* multilink protocol header length */ #define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */ #define PPP_PROTO_LEN 2 /* * An instance of /dev/ppp can be associated with either a ppp * interface unit or a ppp channel. In both cases, file->private_data * points to one of these. */ struct ppp_file { enum { INTERFACE=1, CHANNEL } kind; struct sk_buff_head xq; /* pppd transmit queue */ struct sk_buff_head rq; /* receive queue for pppd */ wait_queue_head_t rwait; /* for poll on reading /dev/ppp */ refcount_t refcnt; /* # refs (incl /dev/ppp attached) */ int hdrlen; /* space to leave for headers */ int index; /* interface unit / channel number */ int dead; /* unit/channel has been shut down */ }; #define PF_TO_X(pf, X) container_of(pf, X, file) #define PF_TO_PPP(pf) PF_TO_X(pf, struct ppp) #define PF_TO_CHANNEL(pf) PF_TO_X(pf, struct channel) /* * Data structure to hold primary network stats for which * we want to use 64 bit storage. Other network stats * are stored in dev->stats of the ppp strucute. */ struct ppp_link_stats { u64 rx_packets; u64 tx_packets; u64 rx_bytes; u64 tx_bytes; }; /* * Data structure describing one ppp unit. * A ppp unit corresponds to a ppp network interface device * and represents a multilink bundle. * It can have 0 or more ppp channels connected to it. */ struct ppp { struct ppp_file file; /* stuff for read/write/poll 0 */ struct file *owner; /* file that owns this unit 48 */ struct list_head channels; /* list of attached channels 4c */ int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ int __percpu *xmit_recursion; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ unsigned int rstate; /* receive state bits 6c */ int debug; /* debug flags 70 */ struct slcompress *vj; /* state for VJ header compression */ enum NPmode npmode[NUM_NP]; /* what to do with each net proto 78 */ struct sk_buff *xmit_pending; /* a packet ready to go out 88 */ struct compressor *xcomp; /* transmit packet compressor 8c */ void *xc_state; /* its internal state 90 */ struct compressor *rcomp; /* receive decompressor 94 */ void *rc_state; /* its internal state 98 */ unsigned long last_xmit; /* jiffies when last pkt sent 9c */ unsigned long last_recv; /* jiffies when last pkt rcvd a0 */ struct net_device *dev; /* network interface device a4 */ int closing; /* is device closing down? a8 */ #ifdef CONFIG_PPP_MULTILINK int nxchan; /* next channel to send something on */ u32 nxseq; /* next sequence number to send */ int mrru; /* MP: max reconst. receive unit */ u32 nextseq; /* MP: seq no of next packet */ u32 minseq; /* MP: min of most recent seqnos */ struct sk_buff_head mrq; /* MP: receive reconstruction queue */ #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER struct bpf_prog *pass_filter; /* filter for packets to pass */ struct bpf_prog *active_filter; /* filter for pkts to reset idle */ #endif /* CONFIG_PPP_FILTER */ struct net *ppp_net; /* the net we belong to */ struct ppp_link_stats stats64; /* 64 bit network stats */ }; /* * Bits in flags: SC_NO_TCP_CCID, SC_CCP_OPEN, SC_CCP_UP, SC_LOOP_TRAFFIC, * SC_MULTILINK, SC_MP_SHORTSEQ, SC_MP_XSHORTSEQ, SC_COMP_TCP, SC_REJ_COMP_TCP, * SC_MUST_COMP * Bits in rstate: SC_DECOMP_RUN, SC_DC_ERROR, SC_DC_FERROR. * Bits in xstate: SC_COMP_RUN */ #define SC_FLAG_BITS (SC_NO_TCP_CCID|SC_CCP_OPEN|SC_CCP_UP|SC_LOOP_TRAFFIC \ |SC_MULTILINK|SC_MP_SHORTSEQ|SC_MP_XSHORTSEQ \ |SC_COMP_TCP|SC_REJ_COMP_TCP|SC_MUST_COMP) /* * Private data structure for each channel. * This includes the data structure used for multilink. */ struct channel { struct ppp_file file; /* stuff for read/write/poll */ struct list_head list; /* link in all/new_channels list */ struct ppp_channel *chan; /* public channel data structure */ struct rw_semaphore chan_sem; /* protects `chan' during chan ioctl */ spinlock_t downl; /* protects `chan', file.xq dequeue */ struct ppp *ppp; /* ppp unit we're connected to */ struct net *chan_net; /* the net channel belongs to */ netns_tracker ns_tracker; struct list_head clist; /* link in list of channels per unit */ rwlock_t upl; /* protects `ppp' and 'bridge' */ struct channel __rcu *bridge; /* "bridged" ppp channel */ #ifdef CONFIG_PPP_MULTILINK u8 avail; /* flag used in multilink stuff */ u8 had_frag; /* >= 1 fragments have been sent */ u32 lastseq; /* MP: last sequence # received */ int speed; /* speed of the corresponding ppp channel*/ #endif /* CONFIG_PPP_MULTILINK */ }; struct ppp_config { struct file *file; s32 unit; bool ifname_is_set; }; /* * SMP locking issues: * Both the ppp.rlock and ppp.wlock locks protect the ppp.channels * list and the ppp.n_channels field, you need to take both locks * before you modify them. * The lock ordering is: channel.upl -> ppp.wlock -> ppp.rlock -> * channel.downl. */ static DEFINE_MUTEX(ppp_mutex); static atomic_t ppp_unit_count = ATOMIC_INIT(0); static atomic_t channel_count = ATOMIC_INIT(0); /* per-net private data for this module */ static unsigned int ppp_net_id __read_mostly; struct ppp_net { /* units to ppp mapping */ struct idr units_idr; /* * all_ppp_mutex protects the units_idr mapping. * It also ensures that finding a ppp unit in the units_idr * map and updating its file.refcnt field is atomic. */ struct mutex all_ppp_mutex; /* channels */ struct list_head all_channels; struct list_head new_channels; int last_channel_index; /* * all_channels_lock protects all_channels and * last_channel_index, and the atomicity of find * a channel and updating its file.refcnt field. */ spinlock_t all_channels_lock; }; /* Get the PPP protocol number from a skb */ #define PPP_PROTO(skb) get_unaligned_be16((skb)->data) /* We limit the length of ppp->file.rq to this (arbitrary) value */ #define PPP_MAX_RQLEN 32 /* * Maximum number of multilink fragments queued up. * This has to be large enough to cope with the maximum latency of * the slowest channel relative to the others. Strictly it should * depend on the number of channels and their characteristics. */ #define PPP_MP_MAX_QLEN 128 /* Multilink header bits. */ #define B 0x80 /* this fragment begins a packet */ #define E 0x40 /* this fragment ends a packet */ /* Compare multilink sequence numbers (assumed to be 32 bits wide) */ #define seq_before(a, b) ((s32)((a) - (b)) < 0) #define seq_after(a, b) ((s32)((a) - (b)) > 0) /* Prototypes. */ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg); static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb); static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb); static void ppp_push(struct ppp *ppp); static void ppp_channel_push(struct channel *pch); static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_receive_error(struct ppp *ppp); static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb); #ifdef CONFIG_PPP_MULTILINK static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_mp_reconstruct(struct ppp *ppp); static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb); #endif /* CONFIG_PPP_MULTILINK */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data); static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound); static void ppp_ccp_closed(struct ppp *ppp); static struct compressor *find_compressor(int type); static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st); static int ppp_create_interface(struct net *net, struct file *file, int *unit); static void init_ppp_file(struct ppp_file *pf, int kind); static void ppp_destroy_interface(struct ppp *ppp); static struct ppp *ppp_find_unit(struct ppp_net *pn, int unit); static struct channel *ppp_find_channel(struct ppp_net *pn, int unit); static int ppp_connect_channel(struct channel *pch, int unit); static int ppp_disconnect_channel(struct channel *pch); static void ppp_destroy_channel(struct channel *pch); static int unit_get(struct idr *p, void *ptr, int min); static int unit_set(struct idr *p, void *ptr, int n); static void unit_put(struct idr *p, int n); static void *unit_find(struct idr *p, int n); static void ppp_setup(struct net_device *dev); static const struct net_device_ops ppp_netdev_ops; static const struct class ppp_class = { .name = "ppp", }; /* per net-namespace data */ static inline struct ppp_net *ppp_pernet(struct net *net) { return net_generic(net, ppp_net_id); } /* Translates a PPP protocol number to a NP index (NP == network protocol) */ static inline int proto_to_npindex(int proto) { switch (proto) { case PPP_IP: return NP_IP; case PPP_IPV6: return NP_IPV6; case PPP_IPX: return NP_IPX; case PPP_AT: return NP_AT; case PPP_MPLS_UC: return NP_MPLS_UC; case PPP_MPLS_MC: return NP_MPLS_MC; } return -EINVAL; } /* Translates an NP index into a PPP protocol number */ static const int npindex_to_proto[NUM_NP] = { PPP_IP, PPP_IPV6, PPP_IPX, PPP_AT, PPP_MPLS_UC, PPP_MPLS_MC, }; /* Translates an ethertype into an NP index */ static inline int ethertype_to_npindex(int ethertype) { switch (ethertype) { case ETH_P_IP: return NP_IP; case ETH_P_IPV6: return NP_IPV6; case ETH_P_IPX: return NP_IPX; case ETH_P_PPPTALK: case ETH_P_ATALK: return NP_AT; case ETH_P_MPLS_UC: return NP_MPLS_UC; case ETH_P_MPLS_MC: return NP_MPLS_MC; } return -1; } /* Translates an NP index into an ethertype */ static const int npindex_to_ethertype[NUM_NP] = { ETH_P_IP, ETH_P_IPV6, ETH_P_IPX, ETH_P_PPPTALK, ETH_P_MPLS_UC, ETH_P_MPLS_MC, }; /* * Locking shorthand. */ #define ppp_xmit_lock(ppp) spin_lock_bh(&(ppp)->wlock) #define ppp_xmit_unlock(ppp) spin_unlock_bh(&(ppp)->wlock) #define ppp_recv_lock(ppp) spin_lock_bh(&(ppp)->rlock) #define ppp_recv_unlock(ppp) spin_unlock_bh(&(ppp)->rlock) #define ppp_lock(ppp) do { ppp_xmit_lock(ppp); \ ppp_recv_lock(ppp); } while (0) #define ppp_unlock(ppp) do { ppp_recv_unlock(ppp); \ ppp_xmit_unlock(ppp); } while (0) /* * /dev/ppp device routines. * The /dev/ppp device is used by pppd to control the ppp unit. * It supports the read, write, ioctl and poll functions. * Open instances of /dev/ppp can be in one of three states: * unattached, attached to a ppp unit, or attached to a ppp channel. */ static int ppp_open(struct inode *inode, struct file *file) { /* * This could (should?) be enforced by the permissions on /dev/ppp. */ if (!ns_capable(file->f_cred->user_ns, CAP_NET_ADMIN)) return -EPERM; return 0; } static int ppp_release(struct inode *unused, struct file *file) { struct ppp_file *pf = file->private_data; struct ppp *ppp; if (pf) { file->private_data = NULL; if (pf->kind == INTERFACE) { ppp = PF_TO_PPP(pf); rtnl_lock(); if (file == ppp->owner) unregister_netdevice(ppp->dev); rtnl_unlock(); } if (refcount_dec_and_test(&pf->refcnt)) { switch (pf->kind) { case INTERFACE: ppp_destroy_interface(PF_TO_PPP(pf)); break; case CHANNEL: ppp_destroy_channel(PF_TO_CHANNEL(pf)); break; } } } return 0; } static ssize_t ppp_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; DECLARE_WAITQUEUE(wait, current); ssize_t ret; struct sk_buff *skb = NULL; struct iovec iov; struct iov_iter to; ret = count; if (!pf) return -ENXIO; add_wait_queue(&pf->rwait, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); skb = skb_dequeue(&pf->rq); if (skb) break; ret = 0; if (pf->dead) break; if (pf->kind == INTERFACE) { /* * Return 0 (EOF) on an interface that has no * channels connected, unless it is looping * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) { ppp_recv_unlock(ppp); break; } ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) break; ret = -ERESTARTSYS; if (signal_pending(current)) break; schedule(); } set_current_state(TASK_RUNNING); remove_wait_queue(&pf->rwait, &wait); if (!skb) goto out; ret = -EOVERFLOW; if (skb->len > count) goto outf; ret = -EFAULT; iov.iov_base = buf; iov.iov_len = count; iov_iter_init(&to, ITER_DEST, &iov, 1, count); if (skb_copy_datagram_iter(skb, 0, &to, skb->len)) goto outf; ret = skb->len; outf: kfree_skb(skb); out: return ret; } static ssize_t ppp_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; struct sk_buff *skb; ssize_t ret; if (!pf) return -ENXIO; /* All PPP packets should start with the 2-byte protocol */ if (count < PPP_PROTO_LEN) return -EINVAL; ret = -ENOMEM; skb = alloc_skb(count + pf->hdrlen, GFP_KERNEL); if (!skb) goto out; skb_reserve(skb, pf->hdrlen); ret = -EFAULT; if (copy_from_user(skb_put(skb, count), buf, count)) { kfree_skb(skb); goto out; } switch (pf->kind) { case INTERFACE: ppp_xmit_process(PF_TO_PPP(pf), skb); break; case CHANNEL: skb_queue_tail(&pf->xq, skb); ppp_channel_push(PF_TO_CHANNEL(pf)); break; } ret = count; out: return ret; } /* No kernel lock - fine */ static __poll_t ppp_poll(struct file *file, poll_table *wait) { struct ppp_file *pf = file->private_data; __poll_t mask; if (!pf) return 0; poll_wait(file, &pf->rwait, wait); mask = EPOLLOUT | EPOLLWRNORM; if (skb_peek(&pf->rq)) mask |= EPOLLIN | EPOLLRDNORM; if (pf->dead) mask |= EPOLLHUP; else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= EPOLLIN | EPOLLRDNORM; ppp_recv_unlock(ppp); } return mask; } #ifdef CONFIG_PPP_FILTER static struct bpf_prog *get_filter(struct sock_fprog *uprog) { struct sock_fprog_kern fprog; struct bpf_prog *res = NULL; int err; if (!uprog->len) return NULL; /* uprog->len is unsigned short, so no overflow here */ fprog.len = uprog->len; fprog.filter = memdup_array_user(uprog->filter, uprog->len, sizeof(struct sock_filter)); if (IS_ERR(fprog.filter)) return ERR_CAST(fprog.filter); err = bpf_prog_create(&res, &fprog); kfree(fprog.filter); return err ? ERR_PTR(err) : res; } static struct bpf_prog *ppp_get_filter(struct sock_fprog __user *p) { struct sock_fprog uprog; if (copy_from_user(&uprog, p, sizeof(struct sock_fprog))) return ERR_PTR(-EFAULT); return get_filter(&uprog); } #ifdef CONFIG_COMPAT struct sock_fprog32 { unsigned short len; compat_caddr_t filter; }; #define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32) #define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32) static struct bpf_prog *compat_ppp_get_filter(struct sock_fprog32 __user *p) { struct sock_fprog32 uprog32; struct sock_fprog uprog; if (copy_from_user(&uprog32, p, sizeof(struct sock_fprog32))) return ERR_PTR(-EFAULT); uprog.len = uprog32.len; uprog.filter = compat_ptr(uprog32.filter); return get_filter(&uprog); } #endif #endif /* Bridge one PPP channel to another. * When two channels are bridged, ppp_input on one channel is redirected to * the other's ops->start_xmit handler. * In order to safely bridge channels we must reject channels which are already * part of a bridge instance, or which form part of an existing unit. * Once successfully bridged, each channel holds a reference on the other * to prevent it being freed while the bridge is extant. */ static int ppp_bridge_channels(struct channel *pch, struct channel *pchb) { write_lock_bh(&pch->upl); if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) { write_unlock_bh(&pch->upl); return -EALREADY; } refcount_inc(&pchb->file.refcnt); rcu_assign_pointer(pch->bridge, pchb); write_unlock_bh(&pch->upl); write_lock_bh(&pchb->upl); if (pchb->ppp || rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl))) { write_unlock_bh(&pchb->upl); goto err_unset; } refcount_inc(&pch->file.refcnt); rcu_assign_pointer(pchb->bridge, pch); write_unlock_bh(&pchb->upl); return 0; err_unset: write_lock_bh(&pch->upl); /* Re-read pch->bridge with upl held in case it was modified concurrently */ pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); synchronize_rcu(); if (pchb) if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return -EALREADY; } static int ppp_unbridge_channels(struct channel *pch) { struct channel *pchb, *pchbb; write_lock_bh(&pch->upl); pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); if (!pchb) { write_unlock_bh(&pch->upl); return -EINVAL; } RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); /* Only modify pchb if phcb->bridge points back to pch. * If not, it implies that there has been a race unbridging (and possibly * even rebridging) pchb. We should leave pchb alone to avoid either a * refcount underflow, or breaking another established bridge instance. */ write_lock_bh(&pchb->upl); pchbb = rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl)); if (pchbb == pch) RCU_INIT_POINTER(pchb->bridge, NULL); write_unlock_bh(&pchb->upl); synchronize_rcu(); if (pchbb == pch) if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return 0; } static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; struct ppp *ppp; int err = -EFAULT, val, val2, i; struct ppp_idle32 idle32; struct ppp_idle64 idle64; struct npioctl npi; int unit, cflags; struct slcompress *vj; void __user *argp = (void __user *)arg; int __user *p = argp; mutex_lock(&ppp_mutex); pf = file->private_data; if (!pf) { err = ppp_unattached_ioctl(current->nsproxy->net_ns, pf, file, cmd, arg); goto out; } if (cmd == PPPIOCDETACH) { /* * PPPIOCDETACH is no longer supported as it was heavily broken, * and is only known to have been used by pppd older than * ppp-2.4.2 (released November 2003). */ pr_warn_once("%s (%d) used obsolete PPPIOCDETACH ioctl\n", current->comm, current->pid); err = -EINVAL; goto out; } if (pf->kind == CHANNEL) { struct channel *pch, *pchb; struct ppp_channel *chan; struct ppp_net *pn; pch = PF_TO_CHANNEL(pf); switch (cmd) { case PPPIOCCONNECT: if (get_user(unit, p)) break; err = ppp_connect_channel(pch, unit); break; case PPPIOCDISCONN: err = ppp_disconnect_channel(pch); break; case PPPIOCBRIDGECHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(current->nsproxy->net_ns); spin_lock_bh(&pn->all_channels_lock); pchb = ppp_find_channel(pn, unit); /* Hold a reference to prevent pchb being freed while * we establish the bridge. */ if (pchb) refcount_inc(&pchb->file.refcnt); spin_unlock_bh(&pn->all_channels_lock); if (!pchb) break; err = ppp_bridge_channels(pch, pchb); /* Drop earlier refcount now bridge establishment is complete */ if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); break; case PPPIOCUNBRIDGECHAN: err = ppp_unbridge_channels(pch); break; default: down_read(&pch->chan_sem); chan = pch->chan; err = -ENOTTY; if (chan && chan->ops->ioctl) err = chan->ops->ioctl(chan, cmd, arg); up_read(&pch->chan_sem); } goto out; } if (pf->kind != INTERFACE) { /* can't happen */ pr_err("PPP: not interface or channel??\n"); err = -EINVAL; goto out; } ppp = PF_TO_PPP(pf); switch (cmd) { case PPPIOCSMRU: if (get_user(val, p)) break; ppp->mru = val; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; ppp_lock(ppp); cflags = ppp->flags & ~val; #ifdef CONFIG_PPP_MULTILINK if (!(ppp->flags & SC_MULTILINK) && (val & SC_MULTILINK)) ppp->nextseq = 0; #endif ppp->flags = val & SC_FLAG_BITS; ppp_unlock(ppp); if (cflags & SC_CCP_OPEN) ppp_ccp_closed(ppp); err = 0; break; case PPPIOCGFLAGS: val = ppp->flags | ppp->xstate | ppp->rstate; if (put_user(val, p)) break; err = 0; break; case PPPIOCSCOMPRESS: { struct ppp_option_data data; if (copy_from_user(&data, argp, sizeof(data))) err = -EFAULT; else err = ppp_set_compress(ppp, &data); break; } case PPPIOCGUNIT: if (put_user(ppp->file.index, p)) break; err = 0; break; case PPPIOCSDEBUG: if (get_user(val, p)) break; ppp->debug = val; err = 0; break; case PPPIOCGDEBUG: if (put_user(ppp->debug, p)) break; err = 0; break; case PPPIOCGIDLE32: idle32.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle32.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle32, sizeof(idle32))) break; err = 0; break; case PPPIOCGIDLE64: idle64.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle64.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle64, sizeof(idle64))) break; err = 0; break; case PPPIOCSMAXCID: if (get_user(val, p)) break; val2 = 15; if ((val >> 16) != 0) { val2 = val >> 16; val &= 0xffff; } vj = slhc_init(val2+1, val+1); if (IS_ERR(vj)) { err = PTR_ERR(vj); break; } ppp_lock(ppp); if (ppp->vj) slhc_free(ppp->vj); ppp->vj = vj; ppp_unlock(ppp); err = 0; break; case PPPIOCGNPMODE: case PPPIOCSNPMODE: if (copy_from_user(&npi, argp, sizeof(npi))) break; err = proto_to_npindex(npi.protocol); if (err < 0) break; i = err; if (cmd == PPPIOCGNPMODE) { err = -EFAULT; npi.mode = ppp->npmode[i]; if (copy_to_user(argp, &npi, sizeof(npi))) break; } else { ppp->npmode[i] = npi.mode; /* we may be able to transmit more packets now (??) */ netif_wake_queue(ppp->dev); } err = 0; break; #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS: case PPPIOCSACTIVE: { struct bpf_prog *filter = ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ #ifdef CONFIG_PPP_MULTILINK case PPPIOCSMRRU: if (get_user(val, p)) break; ppp_recv_lock(ppp); ppp->mrru = val; ppp_recv_unlock(ppp); err = 0; break; #endif /* CONFIG_PPP_MULTILINK */ default: err = -ENOTTY; } out: mutex_unlock(&ppp_mutex); return err; } #ifdef CONFIG_COMPAT struct ppp_option_data32 { compat_uptr_t ptr; u32 length; compat_int_t transmit; }; #define PPPIOCSCOMPRESS32 _IOW('t', 77, struct ppp_option_data32) static long ppp_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; int err = -ENOIOCTLCMD; void __user *argp = (void __user *)arg; mutex_lock(&ppp_mutex); pf = file->private_data; if (pf && pf->kind == INTERFACE) { struct ppp *ppp = PF_TO_PPP(pf); switch (cmd) { #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS32: case PPPIOCSACTIVE32: { struct bpf_prog *filter = compat_ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS32) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ case PPPIOCSCOMPRESS32: { struct ppp_option_data32 data32; if (copy_from_user(&data32, argp, sizeof(data32))) { err = -EFAULT; } else { struct ppp_option_data data = { .ptr = compat_ptr(data32.ptr), .length = data32.length, .transmit = data32.transmit }; err = ppp_set_compress(ppp, &data); } break; } } } mutex_unlock(&ppp_mutex); /* all other commands have compatible arguments */ if (err == -ENOIOCTLCMD) err = ppp_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); return err; } #endif static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg) { int unit, err = -EFAULT; struct ppp *ppp; struct channel *chan; struct ppp_net *pn; int __user *p = (int __user *)arg; switch (cmd) { case PPPIOCNEWUNIT: /* Create a new ppp unit */ if (get_user(unit, p)) break; err = ppp_create_interface(net, file, &unit); if (err < 0) break; err = -EFAULT; if (put_user(unit, p)) break; err = 0; break; case PPPIOCATTACH: /* Attach to an existing ppp unit */ if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (ppp) { refcount_inc(&ppp->file.refcnt); file->private_data = &ppp->file; err = 0; } mutex_unlock(&pn->all_ppp_mutex); break; case PPPIOCATTCHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); spin_lock_bh(&pn->all_channels_lock); chan = ppp_find_channel(pn, unit); if (chan) { refcount_inc(&chan->file.refcnt); file->private_data = &chan->file; err = 0; } spin_unlock_bh(&pn->all_channels_lock); break; default: err = -ENOTTY; } return err; } static const struct file_operations ppp_device_fops = { .owner = THIS_MODULE, .read = ppp_read, .write = ppp_write, .poll = ppp_poll, .unlocked_ioctl = ppp_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ppp_compat_ioctl, #endif .open = ppp_open, .release = ppp_release, .llseek = noop_llseek, }; static __net_init int ppp_init_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); idr_init(&pn->units_idr); mutex_init(&pn->all_ppp_mutex); INIT_LIST_HEAD(&pn->all_channels); INIT_LIST_HEAD(&pn->new_channels); spin_lock_init(&pn->all_channels_lock); return 0; } static __net_exit void ppp_exit_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); struct net_device *dev; struct net_device *aux; struct ppp *ppp; LIST_HEAD(list); int id; rtnl_lock(); for_each_netdev_safe(net, dev, aux) { if (dev->netdev_ops == &ppp_netdev_ops) unregister_netdevice_queue(dev, &list); } idr_for_each_entry(&pn->units_idr, ppp, id) /* Skip devices already unregistered by previous loop */ if (!net_eq(dev_net(ppp->dev), net)) unregister_netdevice_queue(ppp->dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); mutex_destroy(&pn->all_ppp_mutex); idr_destroy(&pn->units_idr); WARN_ON_ONCE(!list_empty(&pn->all_channels)); WARN_ON_ONCE(!list_empty(&pn->new_channels)); } static struct pernet_operations ppp_net_ops = { .init = ppp_init_net, .exit = ppp_exit_net, .id = &ppp_net_id, .size = sizeof(struct ppp_net), }; static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) { struct ppp_net *pn = ppp_pernet(ppp->ppp_net); int ret; mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { ret = unit_get(&pn->units_idr, ppp, 0); if (ret < 0) goto err; if (!ifname_is_set) { while (1) { snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); if (!netdev_name_in_use(ppp->ppp_net, ppp->dev->name)) break; unit_put(&pn->units_idr, ret); ret = unit_get(&pn->units_idr, ppp, ret + 1); if (ret < 0) goto err; } } } else { /* Caller asked for a specific unit number. Fail with -EEXIST * if unavailable. For backward compatibility, return -EEXIST * too if idr allocation fails; this makes pppd retry without * requesting a specific unit number. */ if (unit_find(&pn->units_idr, unit)) { ret = -EEXIST; goto err; } ret = unit_set(&pn->units_idr, ppp, unit); if (ret < 0) { /* Rewrite error for backward compatibility */ ret = -EEXIST; goto err; } } ppp->file.index = ret; if (!ifname_is_set) snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ret = register_netdevice(ppp->dev); if (ret < 0) goto err_unit; atomic_inc(&ppp_unit_count); return 0; err_unit: mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); err: mutex_unlock(&pn->all_ppp_mutex); return ret; } static int ppp_dev_configure(struct net *src_net, struct net_device *dev, const struct ppp_config *conf) { struct ppp *ppp = netdev_priv(dev); int indx; int err; int cpu; ppp->dev = dev; ppp->ppp_net = src_net; ppp->mru = PPP_MRU; ppp->owner = conf->file; init_ppp_file(&ppp->file, INTERFACE); ppp->file.hdrlen = PPP_HDRLEN - 2; /* don't count proto bytes */ for (indx = 0; indx < NUM_NP; ++indx) ppp->npmode[indx] = NPMODE_PASS; INIT_LIST_HEAD(&ppp->channels); spin_lock_init(&ppp->rlock); spin_lock_init(&ppp->wlock); ppp->xmit_recursion = alloc_percpu(int); if (!ppp->xmit_recursion) { err = -ENOMEM; goto err1; } for_each_possible_cpu(cpu) (*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0; #ifdef CONFIG_PPP_MULTILINK ppp->minseq = -1; skb_queue_head_init(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER ppp->pass_filter = NULL; ppp->active_filter = NULL; #endif /* CONFIG_PPP_FILTER */ err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set); if (err < 0) goto err2; conf->file->private_data = &ppp->file; return 0; err2: free_percpu(ppp->xmit_recursion); err1: return err; } static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { [IFLA_PPP_DEV_FD] = { .type = NLA_S32 }, }; static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return -EINVAL; if (!data[IFLA_PPP_DEV_FD]) return -EINVAL; if (nla_get_s32(data[IFLA_PPP_DEV_FD]) < 0) return -EBADF; return 0; } static int ppp_nl_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ppp_config conf = { .unit = -1, .ifname_is_set = true, }; struct file *file; int err; file = fget(nla_get_s32(data[IFLA_PPP_DEV_FD])); if (!file) return -EBADF; /* rtnl_lock is already held here, but ppp_create_interface() locks * ppp_mutex before holding rtnl_lock. Using mutex_trylock() avoids * possible deadlock due to lock order inversion, at the cost of * pushing the problem back to userspace. */ if (!mutex_trylock(&ppp_mutex)) { err = -EBUSY; goto out; } if (file->f_op != &ppp_device_fops || file->private_data) { err = -EBADF; goto out_unlock; } conf.file = file; /* Don't use device name generated by the rtnetlink layer when ifname * isn't specified. Let ppp_dev_configure() set the device name using * the PPP unit identifer as suffix (i.e. ppp<unit_id>). This allows * userspace to infer the device name using to the PPPIOCGUNIT ioctl. */ if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME])) conf.ifname_is_set = false; err = ppp_dev_configure(src_net, dev, &conf); out_unlock: mutex_unlock(&ppp_mutex); out: fput(file); return err; } static void ppp_nl_dellink(struct net_device *dev, struct list_head *head) { unregister_netdevice_queue(dev, head); } static size_t ppp_nl_get_size(const struct net_device *dev) { return 0; } static int ppp_nl_fill_info(struct sk_buff *skb, const struct net_device *dev) { return 0; } static struct net *ppp_nl_get_link_net(const struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); return READ_ONCE(ppp->ppp_net); } static struct rtnl_link_ops ppp_link_ops __read_mostly = { .kind = "ppp", .maxtype = IFLA_PPP_MAX, .policy = ppp_nl_policy, .priv_size = sizeof(struct ppp), .setup = ppp_setup, .validate = ppp_nl_validate, .newlink = ppp_nl_newlink, .dellink = ppp_nl_dellink, .get_size = ppp_nl_get_size, .fill_info = ppp_nl_fill_info, .get_link_net = ppp_nl_get_link_net, }; #define PPP_MAJOR 108 /* Called at boot time if ppp is compiled into the kernel, or at module load time (from init_module) if compiled as a module. */ static int __init ppp_init(void) { int err; pr_info("PPP generic driver version " PPP_VERSION "\n"); err = register_pernet_device(&ppp_net_ops); if (err) { pr_err("failed to register PPP pernet device (%d)\n", err); goto out; } err = register_chrdev(PPP_MAJOR, "ppp", &ppp_device_fops); if (err) { pr_err("failed to register PPP device (%d)\n", err); goto out_net; } err = class_register(&ppp_class); if (err) goto out_chrdev; err = rtnl_link_register(&ppp_link_ops); if (err) { pr_err("failed to register rtnetlink PPP handler\n"); goto out_class; } /* not a big deal if we fail here :-) */ device_create(&ppp_class, NULL, MKDEV(PPP_MAJOR, 0), NULL, "ppp"); return 0; out_class: class_unregister(&ppp_class); out_chrdev: unregister_chrdev(PPP_MAJOR, "ppp"); out_net: unregister_pernet_device(&ppp_net_ops); out: return err; } /* * Network interface unit routines. */ static netdev_tx_t ppp_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); int npi, proto; unsigned char *pp; npi = ethertype_to_npindex(ntohs(skb->protocol)); if (npi < 0) goto outf; /* Drop, accept or reject the packet */ switch (ppp->npmode[npi]) { case NPMODE_PASS: break; case NPMODE_QUEUE: /* it would be nice to have a way to tell the network system to queue this one up for later. */ goto outf; case NPMODE_DROP: case NPMODE_ERROR: goto outf; } /* Put the 2-byte PPP protocol number on the front, making sure there is room for the address and control fields. */ if (skb_cow_head(skb, PPP_HDRLEN)) goto outf; pp = skb_push(skb, 2); proto = npindex_to_proto[npi]; put_unaligned_be16(proto, pp); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev))); ppp_xmit_process(ppp, skb); return NETDEV_TX_OK; outf: kfree_skb(skb); ++dev->stats.tx_dropped; return NETDEV_TX_OK; } static int ppp_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *addr, int cmd) { struct ppp *ppp = netdev_priv(dev); int err = -EFAULT; struct ppp_stats stats; struct ppp_comp_stats cstats; char *vers; switch (cmd) { case SIOCGPPPSTATS: ppp_get_stats(ppp, &stats); if (copy_to_user(addr, &stats, sizeof(stats))) break; err = 0; break; case SIOCGPPPCSTATS: memset(&cstats, 0, sizeof(cstats)); if (ppp->xc_state) ppp->xcomp->comp_stat(ppp->xc_state, &cstats.c); if (ppp->rc_state) ppp->rcomp->decomp_stat(ppp->rc_state, &cstats.d); if (copy_to_user(addr, &cstats, sizeof(cstats))) break; err = 0; break; case SIOCGPPPVER: vers = PPP_VERSION; if (copy_to_user(addr, vers, strlen(vers) + 1)) break; err = 0; break; default: err = -EINVAL; } return err; } static void ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) { struct ppp *ppp = netdev_priv(dev); ppp_recv_lock(ppp); stats64->rx_packets = ppp->stats64.rx_packets; stats64->rx_bytes = ppp->stats64.rx_bytes; ppp_recv_unlock(ppp); ppp_xmit_lock(ppp); stats64->tx_packets = ppp->stats64.tx_packets; stats64->tx_bytes = ppp->stats64.tx_bytes; ppp_xmit_unlock(ppp); stats64->rx_errors = dev->stats.rx_errors; stats64->tx_errors = dev->stats.tx_errors; stats64->rx_dropped = dev->stats.rx_dropped; stats64->tx_dropped = dev->stats.tx_dropped; stats64->rx_length_errors = dev->stats.rx_length_errors; } static int ppp_dev_init(struct net_device *dev) { struct ppp *ppp; netdev_lockdep_set_classes(dev); ppp = netdev_priv(dev); /* Let the netdevice take a reference on the ppp file. This ensures * that ppp_destroy_interface() won't run before the device gets * unregistered. */ refcount_inc(&ppp->file.refcnt); return 0; } static void ppp_dev_uninit(struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); struct ppp_net *pn = ppp_pernet(ppp->ppp_net); ppp_lock(ppp); ppp->closing = 1; ppp_unlock(ppp); mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ppp->owner = NULL; ppp->file.dead = 1; wake_up_interruptible(&ppp->file.rwait); } static void ppp_dev_priv_destructor(struct net_device *dev) { struct ppp *ppp; ppp = netdev_priv(dev); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); } static int ppp_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ppp *ppp = netdev_priv(ctx->dev); struct ppp_channel *chan; struct channel *pch; if (ppp->flags & SC_MULTILINK) return -EOPNOTSUPP; if (list_empty(&ppp->channels)) return -ENODEV; pch = list_first_entry(&ppp->channels, struct channel, clist); chan = pch->chan; if (!chan->ops->fill_forward_path) return -EOPNOTSUPP; return chan->ops->fill_forward_path(ctx, path, chan); } static const struct net_device_ops ppp_netdev_ops = { .ndo_init = ppp_dev_init, .ndo_uninit = ppp_dev_uninit, .ndo_start_xmit = ppp_start_xmit, .ndo_siocdevprivate = ppp_net_siocdevprivate, .ndo_get_stats64 = ppp_get_stats64, .ndo_fill_forward_path = ppp_fill_forward_path, }; static const struct device_type ppp_type = { .name = "ppp", }; static void ppp_setup(struct net_device *dev) { dev->netdev_ops = &ppp_netdev_ops; SET_NETDEV_DEVTYPE(dev, &ppp_type); dev->features |= NETIF_F_LLTX; dev->hard_header_len = PPP_HDRLEN; dev->mtu = PPP_MRU; dev->addr_len = 0; dev->tx_queue_len = 3; dev->type = ARPHRD_PPP; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->priv_destructor = ppp_dev_priv_destructor; netif_keep_dst(dev); } /* * Transmit-side routines. */ /* Called to do any work queued up on the transmit side that can now be done */ static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { ppp_xmit_lock(ppp); if (!ppp->closing) { ppp_push(ppp); if (skb) skb_queue_tail(&ppp->file.xq, skb); while (!ppp->xmit_pending && (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); /* If there's no work left to do, tell the core net code that we can accept some more. */ if (!ppp->xmit_pending && !skb_peek(&ppp->file.xq)) netif_wake_queue(ppp->dev); else netif_stop_queue(ppp->dev); } else { kfree_skb(skb); } ppp_xmit_unlock(ppp); } static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { local_bh_disable(); if (unlikely(*this_cpu_ptr(ppp->xmit_recursion))) goto err; (*this_cpu_ptr(ppp->xmit_recursion))++; __ppp_xmit_process(ppp, skb); (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); return; err: local_bh_enable(); kfree_skb(skb); if (net_ratelimit()) netdev_err(ppp->dev, "recursion detected\n"); } static inline struct sk_buff * pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *new_skb; int len; int new_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + ppp->dev->hard_header_len; int compressor_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + PPP_HDRLEN; new_skb = alloc_skb(new_skb_size, GFP_ATOMIC); if (!new_skb) { if (net_ratelimit()) netdev_err(ppp->dev, "PPP: no memory (comp pkt)\n"); return NULL; } if (ppp->dev->hard_header_len > PPP_HDRLEN) skb_reserve(new_skb, ppp->dev->hard_header_len - PPP_HDRLEN); /* compressor still expects A/C bytes in hdr */ len = ppp->xcomp->compress(ppp->xc_state, skb->data - 2, new_skb->data, skb->len + 2, compressor_skb_size); if (len > 0 && (ppp->flags & SC_CCP_UP)) { consume_skb(skb); skb = new_skb; skb_put(skb, len); skb_pull(skb, 2); /* pull off A/C bytes */ } else if (len == 0) { /* didn't compress, or CCP not up yet */ consume_skb(new_skb); new_skb = skb; } else { /* * (len < 0) * MPPE requires that we do not send unencrypted * frames. The compressor will return -1 if we * should drop the frame. We cannot simply test * the compress_proto because MPPE and MPPC share * the same number. */ if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compressor dropped pkt\n"); kfree_skb(skb); consume_skb(new_skb); new_skb = NULL; } return new_skb; } /* * Compress and send a frame. * The caller should have locked the xmit path, * and xmit_pending should be 0. */ static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *new_skb; int len; unsigned char *cp; skb->dev = ppp->dev; if (proto < 0x8000) { #ifdef CONFIG_PPP_FILTER /* check if we should pass this packet */ /* the filter instructions are constructed assuming a four-byte PPP header on each packet */ *(u8 *)skb_push(skb, 2) = 1; if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: outbound frame " "not passed\n"); kfree_skb(skb); return; } /* if this packet passes the active filter, record the time */ if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_xmit = jiffies; skb_pull(skb, 2); #else /* for data packets, record the time */ ppp->last_xmit = jiffies; #endif /* CONFIG_PPP_FILTER */ } ++ppp->stats64.tx_packets; ppp->stats64.tx_bytes += skb->len - PPP_PROTO_LEN; switch (proto) { case PPP_IP: if (!ppp->vj || (ppp->flags & SC_COMP_TCP) == 0) break; /* try to do VJ TCP header compression */ new_skb = alloc_skb(skb->len + ppp->dev->hard_header_len - 2, GFP_ATOMIC); if (!new_skb) { netdev_err(ppp->dev, "PPP: no memory (VJ comp pkt)\n"); goto drop; } skb_reserve(new_skb, ppp->dev->hard_header_len - 2); cp = skb->data + 2; len = slhc_compress(ppp->vj, cp, skb->len - 2, new_skb->data + 2, &cp, !(ppp->flags & SC_NO_TCP_CCID)); if (cp == skb->data + 2) { /* didn't compress */ consume_skb(new_skb); } else { if (cp[0] & SL_TYPE_COMPRESSED_TCP) { proto = PPP_VJC_COMP; cp[0] &= ~SL_TYPE_COMPRESSED_TCP; } else { proto = PPP_VJC_UNCOMP; cp[0] = skb->data[2]; } consume_skb(skb); skb = new_skb; cp = skb_put(skb, len + 2); cp[0] = 0; cp[1] = proto; } break; case PPP_CCP: /* peek at outbound CCP frames */ ppp_ccp_peek(ppp, skb, 0); break; } /* try to do packet compression */ if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state && proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compression required but " "down - pkt dropped.\n"); goto drop; } skb = pad_compress_skb(ppp, skb); if (!skb) goto drop; } /* * If we are waiting for traffic (demand dialling), * queue it up for pppd to receive. */ if (ppp->flags & SC_LOOP_TRAFFIC) { if (ppp->file.rq.qlen > PPP_MAX_RQLEN) goto drop; skb_queue_tail(&ppp->file.rq, skb); wake_up_interruptible(&ppp->file.rwait); return; } ppp->xmit_pending = skb; ppp_push(ppp); return; drop: kfree_skb(skb); ++ppp->dev->stats.tx_errors; } /* * Try to send the frame in xmit_pending. * The caller should have the xmit path locked. */ static void ppp_push(struct ppp *ppp) { struct list_head *list; struct channel *pch; struct sk_buff *skb = ppp->xmit_pending; if (!skb) return; list = &ppp->channels; if (list_empty(list)) { /* nowhere to send the packet, just drop it */ ppp->xmit_pending = NULL; kfree_skb(skb); return; } if ((ppp->flags & SC_MULTILINK) == 0) { /* not doing multilink: send it down the first channel */ list = list->next; pch = list_entry(list, struct channel, clist); spin_lock(&pch->downl); if (pch->chan) { if (pch->chan->ops->start_xmit(pch->chan, skb)) ppp->xmit_pending = NULL; } else { /* channel got unregistered */ kfree_skb(skb); ppp->xmit_pending = NULL; } spin_unlock(&pch->downl); return; } #ifdef CONFIG_PPP_MULTILINK /* Multilink: fragment the packet over as many links as can take the packet at the moment. */ if (!ppp_mp_explode(ppp, skb)) return; #endif /* CONFIG_PPP_MULTILINK */ ppp->xmit_pending = NULL; kfree_skb(skb); } #ifdef CONFIG_PPP_MULTILINK static bool mp_protocol_compress __read_mostly = true; module_param(mp_protocol_compress, bool, 0644); MODULE_PARM_DESC(mp_protocol_compress, "compress protocol id in multilink fragments"); /* * Divide a packet to be transmitted into fragments and * send them out the individual links. */ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) { int len, totlen; int i, bits, hdrlen, mtu; int flen; int navail, nfree, nzero; int nbigger; int totspeed; int totfree; unsigned char *p, *q; struct list_head *list; struct channel *pch; struct sk_buff *frag; struct ppp_channel *chan; totspeed = 0; /*total bitrate of the bundle*/ nfree = 0; /* # channels which have no packet already queued */ navail = 0; /* total # of usable channels (not deregistered) */ nzero = 0; /* number of channels with zero speed associated*/ totfree = 0; /*total # of channels available and *having no queued packets before *starting the fragmentation*/ hdrlen = (ppp->flags & SC_MP_XSHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; i = 0; list_for_each_entry(pch, &ppp->channels, clist) { if (pch->chan) { pch->avail = 1; navail++; pch->speed = pch->chan->speed; } else { pch->avail = 0; } if (pch->avail) { if (skb_queue_empty(&pch->file.xq) || !pch->had_frag) { if (pch->speed == 0) nzero++; else totspeed += pch->speed; pch->avail = 2; ++nfree; ++totfree; } if (!pch->had_frag && i < ppp->nxchan) ppp->nxchan = i; } ++i; } /* * Don't start sending this packet unless at least half of * the channels are free. This gives much better TCP * performance if we have a lot of channels. */ if (nfree == 0 || nfree < navail / 2) return 0; /* can't take now, leave it in xmit_pending */ /* Do protocol field compression */ p = skb->data; len = skb->len; if (*p == 0 && mp_protocol_compress) { ++p; --len; } totlen = len; nbigger = len % nfree; /* skip to the channel after the one we last used and start at that one */ list = &ppp->channels; for (i = 0; i < ppp->nxchan; ++i) { list = list->next; if (list == &ppp->channels) { i = 0; break; } } /* create a fragment for each channel */ bits = B; while (len > 0) { list = list->next; if (list == &ppp->channels) { i = 0; continue; } pch = list_entry(list, struct channel, clist); ++i; if (!pch->avail) continue; /* * Skip this channel if it has a fragment pending already and * we haven't given a fragment to all of the free channels. */ if (pch->avail == 1) { if (nfree > 0) continue; } else { pch->avail = 1; } /* check the channel's mtu and whether it is still attached. */ spin_lock(&pch->downl); if (pch->chan == NULL) { /* can't use this channel, it's being deregistered */ if (pch->speed == 0) nzero--; else totspeed -= pch->speed; spin_unlock(&pch->downl); pch->avail = 0; totlen = len; totfree--; nfree--; if (--navail == 0) break; continue; } /* *if the channel speed is not set divide *the packet evenly among the free channels; *otherwise divide it according to the speed *of the channel we are going to transmit on */ flen = len; if (nfree > 0) { if (pch->speed == 0) { flen = len/nfree; if (nbigger > 0) { flen++; nbigger--; } } else { flen = (((totfree - nzero)*(totlen + hdrlen*totfree)) / ((totspeed*totfree)/pch->speed)) - hdrlen; if (nbigger > 0) { flen += ((totfree - nzero)*pch->speed)/totspeed; nbigger -= ((totfree - nzero)*pch->speed)/ totspeed; } } nfree--; } /* *check if we are on the last channel or *we exceded the length of the data to *fragment */ if ((nfree <= 0) || (flen > len)) flen = len; /* *it is not worth to tx on slow channels: *in that case from the resulting flen according to the *above formula will be equal or less than zero. *Skip the channel in this case */ if (flen <= 0) { pch->avail = 2; spin_unlock(&pch->downl); continue; } /* * hdrlen includes the 2-byte PPP protocol field, but the * MTU counts only the payload excluding the protocol field. * (RFC1661 Section 2) */ mtu = pch->chan->mtu - (hdrlen - 2); if (mtu < 4) mtu = 4; if (flen > mtu) flen = mtu; if (flen == len) bits |= E; frag = alloc_skb(flen + hdrlen + (flen == 0), GFP_ATOMIC); if (!frag) goto noskb; q = skb_put(frag, flen + hdrlen); /* make the MP header */ put_unaligned_be16(PPP_MP, q); if (ppp->flags & SC_MP_XSHORTSEQ) { q[2] = bits + ((ppp->nxseq >> 8) & 0xf); q[3] = ppp->nxseq; } else { q[2] = bits; q[3] = ppp->nxseq >> 16; q[4] = ppp->nxseq >> 8; q[5] = ppp->nxseq; } memcpy(q + hdrlen, p, flen); /* try to send it down the channel */ chan = pch->chan; if (!skb_queue_empty(&pch->file.xq) || !chan->ops->start_xmit(chan, frag)) skb_queue_tail(&pch->file.xq, frag); pch->had_frag = 1; p += flen; len -= flen; ++ppp->nxseq; bits = 0; spin_unlock(&pch->downl); } ppp->nxchan = i; return 1; noskb: spin_unlock(&pch->downl); if (ppp->debug & 1) netdev_err(ppp->dev, "PPP: no memory (fragment)\n"); ++ppp->dev->stats.tx_errors; ++ppp->nxseq; return 1; /* abandon the frame */ } #endif /* CONFIG_PPP_MULTILINK */ /* Try to send data out on a channel */ static void __ppp_channel_push(struct channel *pch) { struct sk_buff *skb; struct ppp *ppp; spin_lock(&pch->downl); if (pch->chan) { while (!skb_queue_empty(&pch->file.xq)) { skb = skb_dequeue(&pch->file.xq); if (!pch->chan->ops->start_xmit(pch->chan, skb)) { /* put the packet back and try again later */ skb_queue_head(&pch->file.xq, skb); break; } } } else { /* channel got deregistered */ skb_queue_purge(&pch->file.xq); } spin_unlock(&pch->downl); /* see if there is anything from the attached unit to be sent */ if (skb_queue_empty(&pch->file.xq)) { ppp = pch->ppp; if (ppp) __ppp_xmit_process(ppp, NULL); } } static void ppp_channel_push(struct channel *pch) { read_lock_bh(&pch->upl); if (pch->ppp) { (*this_cpu_ptr(pch->ppp->xmit_recursion))++; __ppp_channel_push(pch); (*this_cpu_ptr(pch->ppp->xmit_recursion))--; } else { __ppp_channel_push(pch); } read_unlock_bh(&pch->upl); } /* * Receive-side routines. */ struct ppp_mp_skb_parm { u32 sequence; u8 BEbits; }; #define PPP_MP_CB(skb) ((struct ppp_mp_skb_parm *)((skb)->cb)) static inline void ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { ppp_recv_lock(ppp); if (!ppp->closing) ppp_receive_frame(ppp, skb, pch); else kfree_skb(skb); ppp_recv_unlock(ppp); } /** * __ppp_decompress_proto - Decompress protocol field, slim version. * @skb: Socket buffer where protocol field should be decompressed. It must have * at least 1 byte of head room and 1 byte of linear data. First byte of * data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. No checks w.r.t. skb data * length are done in this function. */ static void __ppp_decompress_proto(struct sk_buff *skb) { if (skb->data[0] & 0x01) *(u8 *)skb_push(skb, 1) = 0x00; } /** * ppp_decompress_proto - Check skb data room and decompress protocol field. * @skb: Socket buffer where protocol field should be decompressed. First byte * of data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. This function also makes * sure that skb data room is sufficient for Protocol field, before and after * decompression. * * Return: true - decompressed successfully, false - not enough room in skb. */ static bool ppp_decompress_proto(struct sk_buff *skb) { /* At least one byte should be present (if protocol is compressed) */ if (!pskb_may_pull(skb, 1)) return false; __ppp_decompress_proto(skb); /* Protocol field should occupy 2 bytes when not compressed */ return pskb_may_pull(skb, 2); } /* Attempt to handle a frame via. a bridged channel, if one exists. * If the channel is bridged, the frame is consumed by the bridge. * If not, the caller must handle the frame by normal recv mechanisms. * Returns true if the frame is consumed, false otherwise. */ static bool ppp_channel_bridge_input(struct channel *pch, struct sk_buff *skb) { struct channel *pchb; rcu_read_lock(); pchb = rcu_dereference(pch->bridge); if (!pchb) goto out_rcu; spin_lock(&pchb->downl); if (!pchb->chan) { /* channel got unregistered */ kfree_skb(skb); goto outl; } skb_scrub_packet(skb, !net_eq(pch->chan_net, pchb->chan_net)); if (!pchb->chan->ops->start_xmit(pchb->chan, skb)) kfree_skb(skb); outl: spin_unlock(&pchb->downl); out_rcu: rcu_read_unlock(); /* If pchb is set then we've consumed the packet */ return !!pchb; } void ppp_input(struct ppp_channel *chan, struct sk_buff *skb) { struct channel *pch = chan->ppp; int proto; if (!pch) { kfree_skb(skb); return; } /* If the channel is bridged, transmit via. bridge */ if (ppp_channel_bridge_input(pch, skb)) return; read_lock_bh(&pch->upl); if (!ppp_decompress_proto(skb)) { kfree_skb(skb); if (pch->ppp) { ++pch->ppp->dev->stats.rx_length_errors; ppp_receive_error(pch->ppp); } goto done; } proto = PPP_PROTO(skb); if (!pch->ppp || proto >= 0xc000 || proto == PPP_CCPFRAG) { /* put it on the channel queue */ skb_queue_tail(&pch->file.rq, skb); /* drop old frames if queue too long */ while (pch->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&pch->file.rq))) kfree_skb(skb); wake_up_interruptible(&pch->file.rwait); } else { ppp_do_recv(pch->ppp, skb, pch); } done: read_unlock_bh(&pch->upl); } /* Put a 0-length skb in the receive queue as an error indication */ void ppp_input_error(struct ppp_channel *chan, int code) { struct channel *pch = chan->ppp; struct sk_buff *skb; if (!pch) return; read_lock_bh(&pch->upl); if (pch->ppp) { skb = alloc_skb(0, GFP_ATOMIC); if (skb) { skb->len = 0; /* probably unnecessary */ skb->cb[0] = code; ppp_do_recv(pch->ppp, skb, pch); } } read_unlock_bh(&pch->upl); } /* * We come in here to process a received frame. * The receive side of the ppp unit is locked. */ static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { /* note: a 0-length skb is used as an error indication */ if (skb->len > 0) { skb_checksum_complete_unset(skb); #ifdef CONFIG_PPP_MULTILINK /* XXX do channel-level decompression here */ if (PPP_PROTO(skb) == PPP_MP) ppp_receive_mp_frame(ppp, skb, pch); else #endif /* CONFIG_PPP_MULTILINK */ ppp_receive_nonmp_frame(ppp, skb); } else { kfree_skb(skb); ppp_receive_error(ppp); } } static void ppp_receive_error(struct ppp *ppp) { ++ppp->dev->stats.rx_errors; if (ppp->vj) slhc_toss(ppp->vj); } static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *ns; int proto, len, npi; /* * Decompress the frame, if compressed. * Note that some decompressors need to see uncompressed frames * that come in as well as compressed frames. */ if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN) && (ppp->rstate & (SC_DC_FERROR | SC_DC_ERROR)) == 0) skb = ppp_decompress_frame(ppp, skb); if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR) goto err; /* At this point the "Protocol" field MUST be decompressed, either in * ppp_input(), ppp_decompress_frame() or in ppp_receive_mp_frame(). */ proto = PPP_PROTO(skb); switch (proto) { case PPP_VJC_COMP: /* decompress VJ compressed packets */ if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; if (skb_tailroom(skb) < 124 || skb_cloned(skb)) { /* copy to a new sk_buff with more tailroom */ ns = dev_alloc_skb(skb->len + 128); if (!ns) { netdev_err(ppp->dev, "PPP: no memory " "(VJ decomp)\n"); goto err; } skb_reserve(ns, 2); skb_copy_bits(skb, 0, skb_put(ns, skb->len), skb->len); consume_skb(skb); skb = ns; } else skb->ip_summed = CHECKSUM_NONE; len = slhc_uncompress(ppp->vj, skb->data + 2, skb->len - 2); if (len <= 0) { netdev_printk(KERN_DEBUG, ppp->dev, "PPP: VJ decompression error\n"); goto err; } len += 2; if (len > skb->len) skb_put(skb, len - skb->len); else if (len < skb->len) skb_trim(skb, len); proto = PPP_IP; break; case PPP_VJC_UNCOMP: if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; /* Until we fix the decompressor need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (slhc_remember(ppp->vj, skb->data + 2, skb->len - 2) <= 0) { netdev_err(ppp->dev, "PPP: VJ uncompressed error\n"); goto err; } proto = PPP_IP; break; case PPP_CCP: ppp_ccp_peek(ppp, skb, 1); break; } ++ppp->stats64.rx_packets; ppp->stats64.rx_bytes += skb->len - 2; npi = proto_to_npindex(proto); if (npi < 0) { /* control or unknown frame - pass it to pppd */ skb_queue_tail(&ppp->file.rq, skb); /* limit queue length by dropping old frames */ while (ppp->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&ppp->file.rq))) kfree_skb(skb); /* wake up any process polling or blocking on read */ wake_up_interruptible(&ppp->file.rwait); } else { /* network protocol frame - give it to the kernel */ #ifdef CONFIG_PPP_FILTER /* check if the packet passes the pass and active filters */ /* the filter instructions are constructed assuming a four-byte PPP header on each packet */ if (ppp->pass_filter || ppp->active_filter) { if (skb_unclone(skb, GFP_ATOMIC)) goto err; *(u8 *)skb_push(skb, 2) = 0; if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: inbound frame " "not passed\n"); kfree_skb(skb); return; } if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_recv = jiffies; __skb_pull(skb, 2); } else #endif /* CONFIG_PPP_FILTER */ ppp->last_recv = jiffies; if ((ppp->dev->flags & IFF_UP) == 0 || ppp->npmode[npi] != NPMODE_PASS) { kfree_skb(skb); } else { /* chop off protocol */ skb_pull_rcsum(skb, 2); skb->dev = ppp->dev; skb->protocol = htons(npindex_to_ethertype[npi]); skb_reset_mac_header(skb); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(ppp->dev))); netif_rx(skb); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } static struct sk_buff * ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *ns; int len; /* Until we fix all the decompressor's need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (proto == PPP_COMP) { int obuff_size; switch(ppp->rcomp->compress_proto) { case CI_MPPE: obuff_size = ppp->mru + PPP_HDRLEN + 1; break; default: obuff_size = ppp->mru + PPP_HDRLEN; break; } ns = dev_alloc_skb(obuff_size); if (!ns) { netdev_err(ppp->dev, "ppp_decompress_frame: " "no memory\n"); goto err; } /* the decompressor still expects the A/C bytes in the hdr */ len = ppp->rcomp->decompress(ppp->rc_state, skb->data - 2, skb->len + 2, ns->data, obuff_size); if (len < 0) { /* Pass the compressed frame to pppd as an error indication. */ if (len == DECOMP_FATALERROR) ppp->rstate |= SC_DC_FERROR; kfree_skb(ns); goto err; } consume_skb(skb); skb = ns; skb_put(skb, len); skb_pull(skb, 2); /* pull off the A/C bytes */ /* Don't call __ppp_decompress_proto() here, but instead rely on * corresponding algo (mppe/bsd/deflate) to decompress it. */ } else { /* Uncompressed frame - pass to decompressor so it can update its dictionary if necessary. */ if (ppp->rcomp->incomp) ppp->rcomp->incomp(ppp->rc_state, skb->data - 2, skb->len + 2); } return skb; err: ppp->rstate |= SC_DC_ERROR; ppp_receive_error(ppp); return skb; } #ifdef CONFIG_PPP_MULTILINK /* * Receive a multilink frame. * We put it on the reconstruction queue and then pull off * as many completed frames as we can. */ static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { u32 mask, seq; struct channel *ch; int mphdrlen = (ppp->flags & SC_MP_SHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; if (!pskb_may_pull(skb, mphdrlen + 1) || ppp->mrru == 0) goto err; /* no good, throw it away */ /* Decode sequence number and begin/end bits */ if (ppp->flags & SC_MP_SHORTSEQ) { seq = ((skb->data[2] & 0x0f) << 8) | skb->data[3]; mask = 0xfff; } else { seq = (skb->data[3] << 16) | (skb->data[4] << 8)| skb->data[5]; mask = 0xffffff; } PPP_MP_CB(skb)->BEbits = skb->data[2]; skb_pull(skb, mphdrlen); /* pull off PPP and MP headers */ /* * Do protocol ID decompression on the first fragment of each packet. * We have to do that here, because ppp_receive_nonmp_frame() expects * decompressed protocol field. */ if (PPP_MP_CB(skb)->BEbits & B) __ppp_decompress_proto(skb); /* * Expand sequence number to 32 bits, making it as close * as possible to ppp->minseq. */ seq |= ppp->minseq & ~mask; if ((int)(ppp->minseq - seq) > (int)(mask >> 1)) seq += mask + 1; else if ((int)(seq - ppp->minseq) > (int)(mask >> 1)) seq -= mask + 1; /* should never happen */ PPP_MP_CB(skb)->sequence = seq; pch->lastseq = seq; /* * If this packet comes before the next one we were expecting, * drop it. */ if (seq_before(seq, ppp->nextseq)) { kfree_skb(skb); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); return; } /* * Reevaluate minseq, the minimum over all channels of the * last sequence number received on each channel. Because of * the increasing sequence number rule, we know that any fragment * before `minseq' which hasn't arrived is never going to arrive. * The list of channels can't change because we have the receive * side of the ppp unit locked. */ list_for_each_entry(ch, &ppp->channels, clist) { if (seq_before(ch->lastseq, seq)) seq = ch->lastseq; } if (seq_before(ppp->minseq, seq)) ppp->minseq = seq; /* Put the fragment on the reconstruction queue */ ppp_mp_insert(ppp, skb); /* If the queue is getting long, don't wait any longer for packets before the start of the queue. */ if (skb_queue_len(&ppp->mrq) >= PPP_MP_MAX_QLEN) { struct sk_buff *mskb = skb_peek(&ppp->mrq); if (seq_before(ppp->minseq, PPP_MP_CB(mskb)->sequence)) ppp->minseq = PPP_MP_CB(mskb)->sequence; } /* Pull completed packets off the queue and receive them. */ while ((skb = ppp_mp_reconstruct(ppp))) { if (pskb_may_pull(skb, 2)) ppp_receive_nonmp_frame(ppp, skb); else { ++ppp->dev->stats.rx_length_errors; kfree_skb(skb); ppp_receive_error(ppp); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } /* * Insert a fragment on the MP reconstruction queue. * The queue is ordered by increasing sequence number. */ static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *p; struct sk_buff_head *list = &ppp->mrq; u32 seq = PPP_MP_CB(skb)->sequence; /* N.B. we don't need to lock the list lock because we have the ppp unit receive-side lock. */ skb_queue_walk(list, p) { if (seq_before(seq, PPP_MP_CB(p)->sequence)) break; } __skb_queue_before(list, p, skb); } /* * Reconstruct a packet from the MP fragment queue. * We go through increasing sequence numbers until we find a * complete packet, or we get to the sequence number for a fragment * which hasn't arrived but might still do so. */ static struct sk_buff * ppp_mp_reconstruct(struct ppp *ppp) { u32 seq = ppp->nextseq; u32 minseq = ppp->minseq; struct sk_buff_head *list = &ppp->mrq; struct sk_buff *p, *tmp; struct sk_buff *head, *tail; struct sk_buff *skb = NULL; int lost = 0, len = 0; if (ppp->mrru == 0) /* do nothing until mrru is set */ return NULL; head = __skb_peek(list); tail = NULL; skb_queue_walk_safe(list, p, tmp) { again: if (seq_before(PPP_MP_CB(p)->sequence, seq)) { /* this can't happen, anyway ignore the skb */ netdev_err(ppp->dev, "ppp_mp_reconstruct bad " "seq %u < %u\n", PPP_MP_CB(p)->sequence, seq); __skb_unlink(p, list); kfree_skb(p); continue; } if (PPP_MP_CB(p)->sequence != seq) { u32 oldseq; /* Fragment `seq' is missing. If it is after minseq, it might arrive later, so stop here. */ if (seq_after(seq, minseq)) break; /* Fragment `seq' is lost, keep going. */ lost = 1; oldseq = seq; seq = seq_before(minseq, PPP_MP_CB(p)->sequence)? minseq + 1: PPP_MP_CB(p)->sequence; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "lost frag %u..%u\n", oldseq, seq-1); goto again; } /* * At this point we know that all the fragments from * ppp->nextseq to seq are either present or lost. * Also, there are no complete packets in the queue * that have no missing fragments and end before this * fragment. */ /* B bit set indicates this fragment starts a packet */ if (PPP_MP_CB(p)->BEbits & B) { head = p; lost = 0; len = 0; } len += p->len; /* Got a complete packet yet? */ if (lost == 0 && (PPP_MP_CB(p)->BEbits & E) && (PPP_MP_CB(head)->BEbits & B)) { if (len > ppp->mrru + 2) { ++ppp->dev->stats.rx_length_errors; netdev_printk(KERN_DEBUG, ppp->dev, "PPP: reconstructed packet" " is too long (%d)\n", len); } else { tail = p; break; } ppp->nextseq = seq + 1; } /* * If this is the ending fragment of a packet, * and we haven't found a complete valid packet yet, * we can discard up to and including this fragment. */ if (PPP_MP_CB(p)->BEbits & E) { struct sk_buff *tmp2; skb_queue_reverse_walk_from_safe(list, p, tmp2) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } head = skb_peek(list); if (!head) break; } ++seq; } /* If we have a complete packet, copy it all into one skb. */ if (tail != NULL) { /* If we have discarded any fragments, signal a receive error. */ if (PPP_MP_CB(head)->sequence != ppp->nextseq) { skb_queue_walk_safe(list, p, tmp) { if (p == head) break; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, " missed pkts %u..%u\n", ppp->nextseq, PPP_MP_CB(head)->sequence-1); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); } skb = head; if (head != tail) { struct sk_buff **fragpp = &skb_shinfo(skb)->frag_list; p = skb_queue_next(list, head); __skb_unlink(skb, list); skb_queue_walk_from_safe(list, p, tmp) { __skb_unlink(p, list); *fragpp = p; p->next = NULL; fragpp = &p->next; skb->len += p->len; skb->data_len += p->len; skb->truesize += p->truesize; if (p == tail) break; } } else { __skb_unlink(skb, list); } ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; } return skb; } #endif /* CONFIG_PPP_MULTILINK */ /* * Channel interface. */ /* Create a new, unattached ppp channel. */ int ppp_register_channel(struct ppp_channel *chan) { return ppp_register_net_channel(current->nsproxy->net_ns, chan); } /* Create a new, unattached ppp channel for specified net. */ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan) { struct channel *pch; struct ppp_net *pn; pch = kzalloc(sizeof(struct channel), GFP_KERNEL); if (!pch) return -ENOMEM; pn = ppp_pernet(net); pch->ppp = NULL; pch->chan = chan; pch->chan_net = get_net_track(net, &pch->ns_tracker, GFP_KERNEL); chan->ppp = pch; init_ppp_file(&pch->file, CHANNEL); pch->file.hdrlen = chan->hdrlen; #ifdef CONFIG_PPP_MULTILINK pch->lastseq = -1; #endif /* CONFIG_PPP_MULTILINK */ init_rwsem(&pch->chan_sem); spin_lock_init(&pch->downl); rwlock_init(&pch->upl); spin_lock_bh(&pn->all_channels_lock); pch->file.index = ++pn->last_channel_index; list_add(&pch->list, &pn->new_channels); atomic_inc(&channel_count); spin_unlock_bh(&pn->all_channels_lock); return 0; } /* * Return the index of a channel. */ int ppp_channel_index(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (pch) return pch->file.index; return -1; } /* * Return the PPP unit number to which a channel is connected. */ int ppp_unit_number(struct ppp_channel *chan) { struct channel *pch = chan->ppp; int unit = -1; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp) unit = pch->ppp->file.index; read_unlock_bh(&pch->upl); } return unit; } /* * Return the PPP device interface name of a channel. */ char *ppp_dev_name(struct ppp_channel *chan) { struct channel *pch = chan->ppp; char *name = NULL; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp && pch->ppp->dev) name = pch->ppp->dev->name; read_unlock_bh(&pch->upl); } return name; } /* * Disconnect a channel from the generic layer. * This must be called in process context. */ void ppp_unregister_channel(struct ppp_channel *chan) { struct channel *pch = chan->ppp; struct ppp_net *pn; if (!pch) return; /* should never happen */ chan->ppp = NULL; /* * This ensures that we have returned from any calls into * the channel's start_xmit or ioctl routine before we proceed. */ down_write(&pch->chan_sem); spin_lock_bh(&pch->downl); pch->chan = NULL; spin_unlock_bh(&pch->downl); up_write(&pch->chan_sem); ppp_disconnect_channel(pch); pn = ppp_pernet(pch->chan_net); spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); ppp_unbridge_channels(pch); pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); } /* * Callback from a channel when it can accept more to transmit. * This should be called at BH/softirq level, not interrupt level. */ void ppp_output_wakeup(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (!pch) return; ppp_channel_push(pch); } /* * Compression control. */ /* Process the PPPIOCSCOMPRESS ioctl. */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data) { int err = -EFAULT; struct compressor *cp, *ocomp; void *state, *ostate; unsigned char ccp_option[CCP_MAX_OPTION_LENGTH]; if (data->length > CCP_MAX_OPTION_LENGTH) goto out; if (copy_from_user(ccp_option, data->ptr, data->length)) goto out; err = -EINVAL; if (data->length < 2 || ccp_option[1] < 2 || ccp_option[1] > data->length) goto out; cp = try_then_request_module( find_compressor(ccp_option[0]), "ppp-compress-%d", ccp_option[0]); if (!cp) goto out; err = -ENOBUFS; if (data->transmit) { state = cp->comp_alloc(ccp_option, data->length); if (state) { ppp_xmit_lock(ppp); ppp->xstate &= ~SC_COMP_RUN; ocomp = ppp->xcomp; ostate = ppp->xc_state; ppp->xcomp = cp; ppp->xc_state = state; ppp_xmit_unlock(ppp); if (ostate) { ocomp->comp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } else { state = cp->decomp_alloc(ccp_option, data->length); if (state) { ppp_recv_lock(ppp); ppp->rstate &= ~SC_DECOMP_RUN; ocomp = ppp->rcomp; ostate = ppp->rc_state; ppp->rcomp = cp; ppp->rc_state = state; ppp_recv_unlock(ppp); if (ostate) { ocomp->decomp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } out: return err; } /* * Look at a CCP packet and update our state accordingly. * We assume the caller has the xmit or recv path locked. */ static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) { unsigned char *dp; int len; if (!pskb_may_pull(skb, CCP_HDRLEN + 2)) return; /* no header */ dp = skb->data + 2; switch (CCP_CODE(dp)) { case CCP_CONFREQ: /* A ConfReq starts negotiation of compression * in one direction of transmission, * and hence brings it down...but which way? * * Remember: * A ConfReq indicates what the sender would like to receive */ if(inbound) /* He is proposing what I should send */ ppp->xstate &= ~SC_COMP_RUN; else /* I am proposing to what he should send */ ppp->rstate &= ~SC_DECOMP_RUN; break; case CCP_TERMREQ: case CCP_TERMACK: /* * CCP is going down, both directions of transmission */ ppp->rstate &= ~SC_DECOMP_RUN; ppp->xstate &= ~SC_COMP_RUN; break; case CCP_CONFACK: if ((ppp->flags & (SC_CCP_OPEN | SC_CCP_UP)) != SC_CCP_OPEN) break; len = CCP_LENGTH(dp); if (!pskb_may_pull(skb, len + 2)) return; /* too short */ dp += CCP_HDRLEN; len -= CCP_HDRLEN; if (len < CCP_OPT_MINLEN || len < CCP_OPT_LENGTH(dp)) break; if (inbound) { /* we will start receiving compressed packets */ if (!ppp->rc_state) break; if (ppp->rcomp->decomp_init(ppp->rc_state, dp, len, ppp->file.index, 0, ppp->mru, ppp->debug)) { ppp->rstate |= SC_DECOMP_RUN; ppp->rstate &= ~(SC_DC_ERROR | SC_DC_FERROR); } } else { /* we will soon start sending compressed packets */ if (!ppp->xc_state) break; if (ppp->xcomp->comp_init(ppp->xc_state, dp, len, ppp->file.index, 0, ppp->debug)) ppp->xstate |= SC_COMP_RUN; } break; case CCP_RESETACK: /* reset the [de]compressor */ if ((ppp->flags & SC_CCP_UP) == 0) break; if (inbound) { if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN)) { ppp->rcomp->decomp_reset(ppp->rc_state); ppp->rstate &= ~SC_DC_ERROR; } } else { if (ppp->xc_state && (ppp->xstate & SC_COMP_RUN)) ppp->xcomp->comp_reset(ppp->xc_state); } break; } } /* Free up compression resources. */ static void ppp_ccp_closed(struct ppp *ppp) { void *xstate, *rstate; struct compressor *xcomp, *rcomp; ppp_lock(ppp); ppp->flags &= ~(SC_CCP_OPEN | SC_CCP_UP); ppp->xstate = 0; xcomp = ppp->xcomp; xstate = ppp->xc_state; ppp->xc_state = NULL; ppp->rstate = 0; rcomp = ppp->rcomp; rstate = ppp->rc_state; ppp->rc_state = NULL; ppp_unlock(ppp); if (xstate) { xcomp->comp_free(xstate); module_put(xcomp->owner); } if (rstate) { rcomp->decomp_free(rstate); module_put(rcomp->owner); } } /* List of compressors. */ static LIST_HEAD(compressor_list); static DEFINE_SPINLOCK(compressor_list_lock); struct compressor_entry { struct list_head list; struct compressor *comp; }; static struct compressor_entry * find_comp_entry(int proto) { struct compressor_entry *ce; list_for_each_entry(ce, &compressor_list, list) { if (ce->comp->compress_proto == proto) return ce; } return NULL; } /* Register a compressor */ int ppp_register_compressor(struct compressor *cp) { struct compressor_entry *ce; int ret; spin_lock(&compressor_list_lock); ret = -EEXIST; if (find_comp_entry(cp->compress_proto)) goto out; ret = -ENOMEM; ce = kmalloc(sizeof(struct compressor_entry), GFP_ATOMIC); if (!ce) goto out; ret = 0; ce->comp = cp; list_add(&ce->list, &compressor_list); out: spin_unlock(&compressor_list_lock); return ret; } /* Unregister a compressor */ void ppp_unregister_compressor(struct compressor *cp) { struct compressor_entry *ce; spin_lock(&compressor_list_lock); ce = find_comp_entry(cp->compress_proto); if (ce && ce->comp == cp) { list_del(&ce->list); kfree(ce); } spin_unlock(&compressor_list_lock); } /* Find a compressor. */ static struct compressor * find_compressor(int type) { struct compressor_entry *ce; struct compressor *cp = NULL; spin_lock(&compressor_list_lock); ce = find_comp_entry(type); if (ce) { cp = ce->comp; if (!try_module_get(cp->owner)) cp = NULL; } spin_unlock(&compressor_list_lock); return cp; } /* * Miscelleneous stuff. */ static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st) { struct slcompress *vj = ppp->vj; memset(st, 0, sizeof(*st)); st->p.ppp_ipackets = ppp->stats64.rx_packets; st->p.ppp_ierrors = ppp->dev->stats.rx_errors; st->p.ppp_ibytes = ppp->stats64.rx_bytes; st->p.ppp_opackets = ppp->stats64.tx_packets; st->p.ppp_oerrors = ppp->dev->stats.tx_errors; st->p.ppp_obytes = ppp->stats64.tx_bytes; if (!vj) return; st->vj.vjs_packets = vj->sls_o_compressed + vj->sls_o_uncompressed; st->vj.vjs_compressed = vj->sls_o_compressed; st->vj.vjs_searches = vj->sls_o_searches; st->vj.vjs_misses = vj->sls_o_misses; st->vj.vjs_errorin = vj->sls_i_error; st->vj.vjs_tossed = vj->sls_i_tossed; st->vj.vjs_uncompressedin = vj->sls_i_uncompressed; st->vj.vjs_compressedin = vj->sls_i_compressed; } /* * Stuff for handling the lists of ppp units and channels * and for initialization. */ /* * Create a new ppp interface unit. Fails if it can't allocate memory * or if there is already a unit with the requested number. * unit == -1 means allocate a new number. */ static int ppp_create_interface(struct net *net, struct file *file, int *unit) { struct ppp_config conf = { .file = file, .unit = *unit, .ifname_is_set = false, }; struct net_device *dev; struct ppp *ppp; int err; dev = alloc_netdev(sizeof(struct ppp), "", NET_NAME_ENUM, ppp_setup); if (!dev) { err = -ENOMEM; goto err; } dev_net_set(dev, net); dev->rtnl_link_ops = &ppp_link_ops; rtnl_lock(); err = ppp_dev_configure(net, dev, &conf); if (err < 0) goto err_dev; ppp = netdev_priv(dev); *unit = ppp->file.index; rtnl_unlock(); return 0; err_dev: rtnl_unlock(); free_netdev(dev); err: return err; } /* * Initialize a ppp_file structure. */ static void init_ppp_file(struct ppp_file *pf, int kind) { pf->kind = kind; skb_queue_head_init(&pf->xq); skb_queue_head_init(&pf->rq); refcount_set(&pf->refcnt, 1); init_waitqueue_head(&pf->rwait); } /* * Free the memory used by a ppp unit. This is only called once * there are no channels connected to the unit and no file structs * that reference the unit. */ static void ppp_destroy_interface(struct ppp *ppp) { atomic_dec(&ppp_unit_count); if (!ppp->file.dead || ppp->n_channels) { /* "can't happen" */ netdev_err(ppp->dev, "ppp: destroying ppp struct %p " "but dead=%d n_channels=%d !\n", ppp, ppp->file.dead, ppp->n_channels); return; } ppp_ccp_closed(ppp); if (ppp->vj) { slhc_free(ppp->vj); ppp->vj = NULL; } skb_queue_purge(&ppp->file.xq); skb_queue_purge(&ppp->file.rq); #ifdef CONFIG_PPP_MULTILINK skb_queue_purge(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER if (ppp->pass_filter) { bpf_prog_destroy(ppp->pass_filter); ppp->pass_filter = NULL; } if (ppp->active_filter) { bpf_prog_destroy(ppp->active_filter); ppp->active_filter = NULL; } #endif /* CONFIG_PPP_FILTER */ kfree_skb(ppp->xmit_pending); free_percpu(ppp->xmit_recursion); free_netdev(ppp->dev); } /* * Locate an existing ppp unit. * The caller should have locked the all_ppp_mutex. */ static struct ppp * ppp_find_unit(struct ppp_net *pn, int unit) { return unit_find(&pn->units_idr, unit); } /* * Locate an existing ppp channel. * The caller should have locked the all_channels_lock. * First we look in the new_channels list, then in the * all_channels list. If found in the new_channels list, * we move it to the all_channels list. This is for speed * when we have a lot of channels in use. */ static struct channel * ppp_find_channel(struct ppp_net *pn, int unit) { struct channel *pch; list_for_each_entry(pch, &pn->new_channels, list) { if (pch->file.index == unit) { list_move(&pch->list, &pn->all_channels); return pch; } } list_for_each_entry(pch, &pn->all_channels, list) { if (pch->file.index == unit) return pch; } return NULL; } /* * Connect a PPP channel to a PPP interface unit. */ static int ppp_connect_channel(struct channel *pch, int unit) { struct ppp *ppp; struct ppp_net *pn; int ret = -ENXIO; int hdrlen; pn = ppp_pernet(pch->chan_net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (!ppp) goto out; write_lock_bh(&pch->upl); ret = -EINVAL; if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) goto outl; ppp_lock(ppp); spin_lock_bh(&pch->downl); if (!pch->chan) { /* Don't connect unregistered channels */ spin_unlock_bh(&pch->downl); ppp_unlock(ppp); ret = -ENOTCONN; goto outl; } spin_unlock_bh(&pch->downl); if (pch->file.hdrlen > ppp->file.hdrlen) ppp->file.hdrlen = pch->file.hdrlen; hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ if (hdrlen > ppp->dev->hard_header_len) ppp->dev->hard_header_len = hdrlen; list_add_tail(&pch->clist, &ppp->channels); ++ppp->n_channels; pch->ppp = ppp; refcount_inc(&ppp->file.refcnt); ppp_unlock(ppp); ret = 0; outl: write_unlock_bh(&pch->upl); out: mutex_unlock(&pn->all_ppp_mutex); return ret; } /* * Disconnect a channel from its ppp unit. */ static int ppp_disconnect_channel(struct channel *pch) { struct ppp *ppp; int err = -EINVAL; write_lock_bh(&pch->upl); ppp = pch->ppp; pch->ppp = NULL; write_unlock_bh(&pch->upl); if (ppp) { /* remove it from the ppp unit's list */ ppp_lock(ppp); list_del(&pch->clist); if (--ppp->n_channels == 0) wake_up_interruptible(&ppp->file.rwait); ppp_unlock(ppp); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); err = 0; } return err; } /* * Free up the resources used by a ppp channel. */ static void ppp_destroy_channel(struct channel *pch) { put_net_track(pch->chan_net, &pch->ns_tracker); pch->chan_net = NULL; atomic_dec(&channel_count); if (!pch->file.dead) { /* "can't happen" */ pr_err("ppp: destroying undead channel %p !\n", pch); return; } skb_queue_purge(&pch->file.xq); skb_queue_purge(&pch->file.rq); kfree(pch); } static void __exit ppp_cleanup(void) { /* should never happen */ if (atomic_read(&ppp_unit_count) || atomic_read(&channel_count)) pr_err("PPP: removing module but units remain!\n"); rtnl_link_unregister(&ppp_link_ops); unregister_chrdev(PPP_MAJOR, "ppp"); device_destroy(&ppp_class, MKDEV(PPP_MAJOR, 0)); class_unregister(&ppp_class); unregister_pernet_device(&ppp_net_ops); } /* * Units handling. Caller must protect concurrent access * by holding all_ppp_mutex */ /* associate pointer with specified number */ static int unit_set(struct idr *p, void *ptr, int n) { int unit; unit = idr_alloc(p, ptr, n, n + 1, GFP_KERNEL); if (unit == -ENOSPC) unit = -EINVAL; return unit; } /* get new free unit number and associate pointer with it */ static int unit_get(struct idr *p, void *ptr, int min) { return idr_alloc(p, ptr, min, 0, GFP_KERNEL); } /* put unit number back to a pool */ static void unit_put(struct idr *p, int n) { idr_remove(p, n); } /* get pointer associated with the number */ static void *unit_find(struct idr *p, int n) { return idr_find(p, n); } /* Module/initialization stuff */ module_init(ppp_init); module_exit(ppp_cleanup); EXPORT_SYMBOL(ppp_register_net_channel); EXPORT_SYMBOL(ppp_register_channel); EXPORT_SYMBOL(ppp_unregister_channel); EXPORT_SYMBOL(ppp_channel_index); EXPORT_SYMBOL(ppp_unit_number); EXPORT_SYMBOL(ppp_dev_name); EXPORT_SYMBOL(ppp_input); EXPORT_SYMBOL(ppp_input_error); EXPORT_SYMBOL(ppp_output_wakeup); EXPORT_SYMBOL(ppp_register_compressor); EXPORT_SYMBOL(ppp_unregister_compressor); MODULE_DESCRIPTION("Generic PPP layer driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0); MODULE_ALIAS_RTNL_LINK("ppp"); MODULE_ALIAS("devname:ppp"); |
| 5 5 5 5 5 20 2 1 1 108 3 3 5 5 2 2 3 3 1 1 2 2 3 3 3 3 2 2 1 1 107 107 106 107 107 3 3 3 3 3 11 11 11 11 11 11 1 1 1 1 1 2 2 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 | /* * 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/debugfs.h> #include <linux/etherdevice.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <net/netdev_queues.h> #include <net/page_pool/helpers.h> #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/rtnetlink.h> #include <net/udp_tunnel.h> #include "netdevsim.h" #define NSIM_RING_SIZE 256 static int nsim_napi_rx(struct nsim_rq *rq, struct sk_buff *skb) { if (skb_queue_len(&rq->skb_queue) > NSIM_RING_SIZE) { dev_kfree_skb_any(skb); return NET_RX_DROP; } skb_queue_tail(&rq->skb_queue, skb); return NET_RX_SUCCESS; } static int nsim_forward_skb(struct net_device *dev, struct sk_buff *skb, struct nsim_rq *rq) { return __dev_forward_skb(dev, skb) ?: nsim_napi_rx(rq, skb); } static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); struct net_device *peer_dev; unsigned int len = skb->len; struct netdevsim *peer_ns; struct nsim_rq *rq; int rxq; rcu_read_lock(); if (!nsim_ipsec_tx(ns, skb)) goto out_drop_free; peer_ns = rcu_dereference(ns->peer); if (!peer_ns) goto out_drop_free; peer_dev = peer_ns->netdev; rxq = skb_get_queue_mapping(skb); if (rxq >= peer_dev->num_rx_queues) rxq = rxq % peer_dev->num_rx_queues; rq = &peer_ns->rq[rxq]; skb_tx_timestamp(skb); if (unlikely(nsim_forward_skb(peer_dev, skb, rq) == NET_RX_DROP)) goto out_drop_cnt; napi_schedule(&rq->napi); rcu_read_unlock(); u64_stats_update_begin(&ns->syncp); ns->tx_packets++; ns->tx_bytes += len; u64_stats_update_end(&ns->syncp); return NETDEV_TX_OK; out_drop_free: dev_kfree_skb(skb); out_drop_cnt: rcu_read_unlock(); u64_stats_update_begin(&ns->syncp); ns->tx_dropped++; u64_stats_update_end(&ns->syncp); return NETDEV_TX_OK; } static void nsim_set_rx_mode(struct net_device *dev) { } static int nsim_change_mtu(struct net_device *dev, int new_mtu) { st |