| 442 442 493 163 164 164 164 164 164 164 160 164 474 475 442 442 442 442 472 473 4 4 475 475 471 467 472 472 472 468 472 472 471 465 468 468 465 475 475 468 468 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2003 Intel Corp. * * This file is part of the SCTP kernel implementation * * These functions implement the sctp_outq class. The outqueue handles * bundling and queueing of outgoing SCTP chunks. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Perry Melange <pmelange@null.cc.uic.edu> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Jon Grimm <jgrimm@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/list.h> /* For struct list_head */ #include <linux/socket.h> #include <linux/ip.h> #include <linux/slab.h> #include <net/sock.h> /* For skb_set_owner_w */ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> #include <trace/events/sctp.h> /* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); static void sctp_check_transmitted(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sackhdr *sack, __u32 *highest_new_tsn); static void sctp_mark_missing(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, __u32 highest_new_tsn, int count_of_newacks); static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp); /* Add data to the front of the queue. */ static inline void sctp_outq_head_data(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_out_ext *oute; __u16 stream; list_add(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add(&ch->stream_list, &oute->outq); } /* Take data from the front of the queue. */ static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q) { return q->sched->dequeue(q); } /* Add data chunk to the end of the queue. */ static inline void sctp_outq_tail_data(struct sctp_outq *q, struct sctp_chunk *ch) { struct sctp_stream_out_ext *oute; __u16 stream; list_add_tail(&ch->list, &q->out_chunk_list); q->out_qlen += ch->skb->len; stream = sctp_chunk_stream_no(ch); oute = SCTP_SO(&q->asoc->stream, stream)->ext; list_add_tail(&ch->stream_list, &oute->outq); } /* * SFR-CACC algorithm: * D) If count_of_newacks is greater than or equal to 2 * and t was not sent to the current primary then the * sender MUST NOT increment missing report count for t. */ static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { if (count_of_newacks >= 2 && transport != primary) return 1; return 0; } /* * SFR-CACC algorithm: * F) If count_of_newacks is less than 2, let d be the * destination to which t was sent. If cacc_saw_newack * is 0 for destination d, then the sender MUST NOT * increment missing report count for t. */ static inline int sctp_cacc_skip_3_1_f(struct sctp_transport *transport, int count_of_newacks) { if (count_of_newacks < 2 && (transport && !transport->cacc.cacc_saw_newack)) return 1; return 0; } /* * SFR-CACC algorithm: * 3.1) If CYCLING_CHANGEOVER is 0, the sender SHOULD * execute steps C, D, F. * * C has been implemented in sctp_outq_sack */ static inline int sctp_cacc_skip_3_1(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks) { if (!primary->cacc.cycling_changeover) { if (sctp_cacc_skip_3_1_d(primary, transport, count_of_newacks)) return 1; if (sctp_cacc_skip_3_1_f(transport, count_of_newacks)) return 1; return 0; } return 0; } /* * SFR-CACC algorithm: * 3.2) Else if CYCLING_CHANGEOVER is 1, and t is less * than next_tsn_at_change of the current primary, then * the sender MUST NOT increment missing report count * for t. */ static inline int sctp_cacc_skip_3_2(struct sctp_transport *primary, __u32 tsn) { if (primary->cacc.cycling_changeover && TSN_lt(tsn, primary->cacc.next_tsn_at_change)) return 1; return 0; } /* * SFR-CACC algorithm: * 3) If the missing report count for TSN t is to be * incremented according to [RFC2960] and * [SCTP_STEWART-2002], and CHANGEOVER_ACTIVE is set, * then the sender MUST further execute steps 3.1 and * 3.2 to determine if the missing report count for * TSN t SHOULD NOT be incremented. * * 3.3) If 3.1 and 3.2 do not dictate that the missing * report count for t should not be incremented, then * the sender SHOULD increment missing report count for * t (according to [RFC2960] and [SCTP_STEWART_2002]). */ static inline int sctp_cacc_skip(struct sctp_transport *primary, struct sctp_transport *transport, int count_of_newacks, __u32 tsn) { if (primary->cacc.changeover_active && (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) || sctp_cacc_skip_3_2(primary, tsn))) return 1; return 0; } /* Initialize an existing sctp_outq. This does the boring stuff. * You still need to define handlers if you really want to DO * something with this structure... */ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) { memset(q, 0, sizeof(struct sctp_outq)); q->asoc = asoc; INIT_LIST_HEAD(&q->out_chunk_list); INIT_LIST_HEAD(&q->control_chunk_list); INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); sctp_sched_set_sched(asoc, sctp_sk(asoc->base.sk)->default_ss); } /* Free the outqueue structure and any related pending chunks. */ static void __sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *temp; struct sctp_chunk *chunk, *tmp; /* Throw away unacknowledged chunks. */ list_for_each_entry(transport, &q->asoc->peer.transport_addr_list, transports) { while ((lchunk = sctp_list_dequeue(&transport->transmitted)) != NULL) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); /* Mark as part of a failed message. */ sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } } /* Throw away chunks that have been gap ACKed. */ list_for_each_safe(lchunk, temp, &q->sacked) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any chunks in the retransmit queue. */ list_for_each_safe(lchunk, temp, &q->retransmit) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any chunks that are in the abandoned queue. */ list_for_each_safe(lchunk, temp, &q->abandoned) { list_del_init(lchunk); chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any leftover data chunks. */ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) { sctp_sched_dequeue_done(q, chunk); /* Mark as send failure. */ sctp_chunk_fail(chunk, q->error); sctp_chunk_free(chunk); } /* Throw away any leftover control chunks. */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { list_del_init(&chunk->list); sctp_chunk_free(chunk); } } void sctp_outq_teardown(struct sctp_outq *q) { __sctp_outq_teardown(q); sctp_outq_init(q->asoc, q); } /* Free the outqueue structure and any related pending chunks. */ void sctp_outq_free(struct sctp_outq *q) { /* Throw away leftover chunks. */ __sctp_outq_teardown(q); } /* Put a new chunk in an sctp_outq. */ void sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk, gfp_t gfp) { struct net *net = q->asoc->base.net; pr_debug("%s: outq:%p, chunk:%p[%s]\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); /* If it is data, queue it up, otherwise, send it * immediately. */ if (sctp_chunk_is_data(chunk)) { pr_debug("%s: outqueueing: outq:%p, chunk:%p[%s])\n", __func__, q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk"); sctp_outq_tail_data(q, chunk); if (chunk->asoc->peer.prsctp_capable && SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) chunk->asoc->sent_cnt_removable++; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS); else SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS); } else { list_add_tail(&chunk->list, &q->control_chunk_list); SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); } if (!q->cork) sctp_outq_flush(q, 0, gfp); } /* Insert a chunk into the sorted list based on the TSNs. The retransmit list * and the abandoned list are in ascending order. */ static void sctp_insert_list(struct list_head *head, struct list_head *new) { struct list_head *pos; struct sctp_chunk *nchunk, *lchunk; __u32 ntsn, ltsn; int done = 0; nchunk = list_entry(new, struct sctp_chunk, transmitted_list); ntsn = ntohl(nchunk->subh.data_hdr->tsn); list_for_each(pos, head) { lchunk = list_entry(pos, struct sctp_chunk, transmitted_list); ltsn = ntohl(lchunk->subh.data_hdr->tsn); if (TSN_lt(ntsn, ltsn)) { list_add(new, pos->prev); done = 1; break; } } if (!done) list_add_tail(new, head); } static int sctp_prsctp_prune_sent(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct list_head *queue, int msg_len) { struct sctp_chunk *chk, *temp; list_for_each_entry_safe(chk, temp, queue, transmitted_list) { struct sctp_stream_out *streamout; if (!chk->msg->abandoned && (!SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; chk->msg->abandoned = 1; list_del_init(&chk->transmitted_list); sctp_insert_list(&asoc->outqueue.abandoned, &chk->transmitted_list); streamout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); asoc->sent_cnt_removable--; asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++; if (queue != &asoc->outqueue.retransmit && !chk->tsn_gap_acked) { if (chk->transport) chk->transport->flight_size -= sctp_data_size(chk); asoc->outqueue.outstanding_bytes -= sctp_data_size(chk); } msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); if (msg_len <= 0) break; } return msg_len; } static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len) { struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; struct sctp_stream_out *sout; q->sched->unsched_all(&asoc->stream); list_for_each_entry_safe(chk, temp, &q->out_chunk_list, list) { if (!chk->msg->abandoned && (!(chk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG) || !SCTP_PR_PRIO_ENABLED(chk->sinfo.sinfo_flags) || chk->sinfo.sinfo_timetolive <= sinfo->sinfo_timetolive)) continue; chk->msg->abandoned = 1; sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; sout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); sout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; /* clear out_curr if all frag chunks are pruned */ if (asoc->stream.out_curr == sout && list_is_last(&chk->frag_list, &chk->msg->chunks)) asoc->stream.out_curr = NULL; msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); sctp_chunk_free(chk); if (msg_len <= 0) break; } q->sched->sched_all(&asoc->stream); return msg_len; } /* Abandon the chunks according their priorities */ void sctp_prsctp_prune(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len) { struct sctp_transport *transport; if (!asoc->peer.prsctp_capable || !asoc->sent_cnt_removable) return; msg_len = sctp_prsctp_prune_sent(asoc, sinfo, &asoc->outqueue.retransmit, msg_len); if (msg_len <= 0) return; list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { msg_len = sctp_prsctp_prune_sent(asoc, sinfo, &transport->transmitted, msg_len); if (msg_len <= 0) return; } sctp_prsctp_prune_unsent(asoc, sinfo, msg_len); } /* Mark all the eligible packets on a transport for retransmission. */ void sctp_retransmit_mark(struct sctp_outq *q, struct sctp_transport *transport, __u8 reason) { struct list_head *lchunk, *ltemp; struct sctp_chunk *chunk; /* Walk through the specified transmitted queue. */ list_for_each_safe(lchunk, ltemp, &transport->transmitted) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); /* If the chunk is abandoned, move it to abandoned list. */ if (sctp_chunk_abandoned(chunk)) { list_del_init(lchunk); sctp_insert_list(&q->abandoned, lchunk); /* If this chunk has not been previousely acked, * stop considering it 'outstanding'. Our peer * will most likely never see it since it will * not be retransmitted */ if (!chunk->tsn_gap_acked) { if (chunk->transport) chunk->transport->flight_size -= sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); q->asoc->peer.rwnd += sctp_data_size(chunk); } continue; } /* If we are doing retransmission due to a timeout or pmtu * discovery, only the chunks that are not yet acked should * be added to the retransmit queue. */ if ((reason == SCTP_RTXR_FAST_RTX && (chunk->fast_retransmit == SCTP_NEED_FRTX)) || (reason != SCTP_RTXR_FAST_RTX && !chunk->tsn_gap_acked)) { /* RFC 2960 6.2.1 Processing a Received SACK * * C) Any time a DATA chunk is marked for * retransmission (via either T3-rtx timer expiration * (Section 6.3.3) or via fast retransmit * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ q->asoc->peer.rwnd += sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); if (chunk->transport) transport->flight_size -= sctp_data_size(chunk); /* sctpimpguide-05 Section 2.8.2 * M5) If a T3-rtx timer expires, the * 'TSN.Missing.Report' of all affected TSNs is set * to 0. */ chunk->tsn_missing_report = 0; /* If a chunk that is being used for RTT measurement * has to be retransmitted, we cannot use this chunk * anymore for RTT measurements. Reset rto_pending so * that a new RTT measurement is started when a new * data chunk is sent. */ if (chunk->rtt_in_progress) { chunk->rtt_in_progress = 0; transport->rto_pending = 0; } /* Move the chunk to the retransmit queue. The chunks * on the retransmit queue are always kept in order. */ list_del_init(lchunk); sctp_insert_list(&q->retransmit, lchunk); } } pr_debug("%s: transport:%p, reason:%d, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, reason, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); } /* Mark all the eligible packets on a transport for retransmission and force * one packet out. */ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, enum sctp_retransmit_reason reason) { struct net *net = q->asoc->base.net; switch (reason) { case SCTP_RTXR_T3_RTX: SCTP_INC_STATS(net, SCTP_MIB_T3_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX); /* Update the retran path if the T3-rtx timer has expired for * the current retran path. */ if (transport == transport->asoc->peer.retran_path) sctp_assoc_update_retran_path(transport->asoc); transport->asoc->rtx_data_chunks += transport->asoc->unack_data; if (transport->pl.state == SCTP_PL_COMPLETE && transport->asoc->unack_data) sctp_transport_reset_probe_timer(transport); break; case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(net, SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); q->fast_rtx = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(net, SCTP_MIB_PMTUD_RETRANSMITS); break; case SCTP_RTXR_T1_RTX: SCTP_INC_STATS(net, SCTP_MIB_T1_RETRANSMITS); transport->asoc->init_retries++; break; default: BUG(); } sctp_retransmit_mark(q, transport, reason); /* PR-SCTP A5) Any time the T3-rtx timer expires, on any destination, * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by * following the procedures outlined in C1 - C5. */ if (reason == SCTP_RTXR_T3_RTX) q->asoc->stream.si->generate_ftsn(q, q->asoc->ctsn_ack_point); /* Flush the queues only on timeout, since fast_rtx is only * triggered during sack processing and the queue * will be flushed at the end. */ if (reason != SCTP_RTXR_FAST_RTX) sctp_outq_flush(q, /* rtx_timeout */ 1, GFP_ATOMIC); } /* * Transmit DATA chunks on the retransmit queue. Upon return from * __sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which * need to be transmitted by the caller. * We assume that pkt->transport has already been set. * * The return value is a normal kernel error return value. */ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int rtx_timeout, int *start_timer, gfp_t gfp) { struct sctp_transport *transport = pkt->transport; struct sctp_chunk *chunk, *chunk1; struct list_head *lqueue; enum sctp_xmit status; int error = 0; int timer = 0; int done = 0; int fast_rtx; lqueue = &q->retransmit; fast_rtx = q->fast_rtx; /* This loop handles time-out retransmissions, fast retransmissions, * and retransmissions due to opening of whindow. * * RFC 2960 6.3.3 Handle T3-rtx Expiration * * E3) Determine how many of the earliest (i.e., lowest TSN) * outstanding DATA chunks for the address for which the * T3-rtx has expired will fit into a single packet, subject * to the MTU constraint for the path corresponding to the * destination transport address to which the retransmission * is being sent (this may be different from the address for * which the timer expires [see Section 6.4]). Call this value * K. Bundle and retransmit those K DATA chunks in a single * packet to the destination endpoint. * * [Just to be painfully clear, if we are retransmitting * because a timeout just happened, we should send only ONE * packet of retransmitted data.] * * For fast retransmissions we also send only ONE packet. However, * if we are just flushing the queue due to open window, we'll * try to send as much as possible. */ list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) { /* If the chunk is abandoned, move it to abandoned list. */ if (sctp_chunk_abandoned(chunk)) { list_del_init(&chunk->transmitted_list); sctp_insert_list(&q->abandoned, &chunk->transmitted_list); continue; } /* Make sure that Gap Acked TSNs are not retransmitted. A * simple approach is just to move such TSNs out of the * way and into a 'transmitted' queue and skip to the * next chunk. */ if (chunk->tsn_gap_acked) { list_move_tail(&chunk->transmitted_list, &transport->transmitted); continue; } /* If we are doing fast retransmit, ignore non-fast_rtransmit * chunks */ if (fast_rtx && !chunk->fast_retransmit) continue; redo: /* Attempt to append this chunk to the packet. */ status = sctp_packet_append_chunk(pkt, chunk); switch (status) { case SCTP_XMIT_PMTU_FULL: if (!pkt->has_data && !pkt->has_cookie_echo) { /* If this packet did not contain DATA then * retransmission did not happen, so do it * again. We'll ignore the error here since * control chunks are already freed so there * is nothing we can do. */ sctp_packet_transmit(pkt, gfp); goto redo; } /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* If we are retransmitting, we should only * send a single packet. * Otherwise, try appending this chunk again. */ if (rtx_timeout || fast_rtx) done = 1; else goto redo; /* Bundle next chunk in the next round. */ break; case SCTP_XMIT_RWND_FULL: /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA as there is no more room * at the receiver. */ done = 1; break; case SCTP_XMIT_DELAY: /* Send this packet. */ error = sctp_packet_transmit(pkt, gfp); /* Stop sending DATA because of nagle delay. */ done = 1; break; default: /* The append was successful, so add this chunk to * the transmitted list. */ list_move_tail(&chunk->transmitted_list, &transport->transmitted); /* Mark the chunk as ineligible for fast retransmit * after it is retransmitted. */ if (chunk->fast_retransmit == SCTP_NEED_FRTX) chunk->fast_retransmit = SCTP_DONT_FRTX; q->asoc->stats.rtxchunks++; break; } /* Set the timer if there were no errors */ if (!error && !timer) timer = 1; if (done) break; } /* If we are here due to a retransmit timeout or a fast * retransmit and if there are any chunks left in the retransmit * queue that could not fit in the PMTU sized packet, they need * to be marked as ineligible for a subsequent fast retransmit. */ if (rtx_timeout || fast_rtx) { list_for_each_entry(chunk1, lqueue, transmitted_list) { if (chunk1->fast_retransmit == SCTP_NEED_FRTX) chunk1->fast_retransmit = SCTP_DONT_FRTX; } } *start_timer = timer; /* Clear fast retransmit hint */ if (fast_rtx) q->fast_rtx = 0; return error; } /* Cork the outqueue so queued chunks are really queued. */ void sctp_outq_uncork(struct sctp_outq *q, gfp_t gfp) { if (q->cork) q->cork = 0; sctp_outq_flush(q, 0, gfp); } static int sctp_packet_singleton(struct sctp_transport *transport, struct sctp_chunk *chunk, gfp_t gfp) { const struct sctp_association *asoc = transport->asoc; const __u16 sport = asoc->base.bind_addr.port; const __u16 dport = asoc->peer.port; const __u32 vtag = asoc->peer.i.init_tag; struct sctp_packet singleton; sctp_packet_init(&singleton, transport, sport, dport); sctp_packet_config(&singleton, vtag, 0); if (sctp_packet_append_chunk(&singleton, chunk) != SCTP_XMIT_OK) { list_del_init(&chunk->list); sctp_chunk_free(chunk); return -ENOMEM; } return sctp_packet_transmit(&singleton, gfp); } /* Struct to hold the context during sctp outq flush */ struct sctp_flush_ctx { struct sctp_outq *q; /* Current transport being used. It's NOT the same as curr active one */ struct sctp_transport *transport; /* These transports have chunks to send. */ struct list_head transport_list; struct sctp_association *asoc; /* Packet on the current transport above */ struct sctp_packet *packet; gfp_t gfp; }; /* transport: current transport */ static void sctp_outq_select_transport(struct sctp_flush_ctx *ctx, struct sctp_chunk *chunk) { struct sctp_transport *new_transport = chunk->transport; if (!new_transport) { if (!sctp_chunk_is_data(chunk)) { /* If we have a prior transport pointer, see if * the destination address of the chunk * matches the destination address of the * current transport. If not a match, then * try to look up the transport with a given * destination address. We do this because * after processing ASCONFs, we may have new * transports created. */ if (ctx->transport && sctp_cmp_addr_exact(&chunk->dest, &ctx->transport->ipaddr)) new_transport = ctx->transport; else new_transport = sctp_assoc_lookup_paddr(ctx->asoc, &chunk->dest); } /* if we still don't have a new transport, then * use the current active path. */ if (!new_transport) new_transport = ctx->asoc->peer.active_path; } else { __u8 type; switch (new_transport->state) { case SCTP_INACTIVE: case SCTP_UNCONFIRMED: case SCTP_PF: /* If the chunk is Heartbeat or Heartbeat Ack, * send it to chunk->transport, even if it's * inactive. * * 3.3.6 Heartbeat Acknowledgement: * ... * A HEARTBEAT ACK is always sent to the source IP * address of the IP datagram containing the * HEARTBEAT chunk to which this ack is responding. * ... * * ASCONF_ACKs also must be sent to the source. */ type = chunk->chunk_hdr->type; if (type != SCTP_CID_HEARTBEAT && type != SCTP_CID_HEARTBEAT_ACK && type != SCTP_CID_ASCONF_ACK) new_transport = ctx->asoc->peer.active_path; break; default: break; } } /* Are we switching transports? Take care of transport locks. */ if (new_transport != ctx->transport) { ctx->transport = new_transport; ctx->packet = &ctx->transport->packet; if (list_empty(&ctx->transport->send_ready)) list_add_tail(&ctx->transport->send_ready, &ctx->transport_list); sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, ctx->asoc->peer.ecn_capable); /* We've switched transports, so apply the * Burst limit to the new transport. */ sctp_transport_burst_limited(ctx->transport); } } static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) { struct sctp_chunk *chunk, *tmp; enum sctp_xmit status; int one_packet, error; list_for_each_entry_safe(chunk, tmp, &ctx->q->control_chunk_list, list) { one_packet = 0; /* RFC 5061, 5.3 * F1) This means that until such time as the ASCONF * containing the add is acknowledged, the sender MUST * NOT use the new IP address as a source for ANY SCTP * packet except on carrying an ASCONF Chunk. */ if (ctx->asoc->src_out_of_asoc_ok && chunk->chunk_hdr->type != SCTP_CID_ASCONF) continue; list_del_init(&chunk->list); /* Pick the right transport to use. Should always be true for * the first chunk as we don't have a transport by then. */ sctp_outq_select_transport(ctx, chunk); switch (chunk->chunk_hdr->type) { /* 6.10 Bundling * ... * An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN * COMPLETE with any other chunks. [Send them immediately.] */ case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: case SCTP_CID_SHUTDOWN_COMPLETE: error = sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); if (error < 0) { ctx->asoc->base.sk->sk_err = -error; return; } ctx->asoc->stats.octrlchunks++; break; case SCTP_CID_ABORT: if (sctp_test_T_bit(chunk)) ctx->packet->vtag = ctx->asoc->c.my_vtag; fallthrough; /* The following chunks are "response" chunks, i.e. * they are generated in response to something we * received. If we are sending these, then we can * send only 1 packet containing these chunks. */ case SCTP_CID_HEARTBEAT_ACK: case SCTP_CID_SHUTDOWN_ACK: case SCTP_CID_COOKIE_ACK: case SCTP_CID_COOKIE_ECHO: case SCTP_CID_ERROR: case SCTP_CID_ECN_CWR: case SCTP_CID_ASCONF_ACK: one_packet = 1; fallthrough; case SCTP_CID_HEARTBEAT: if (chunk->pmtu_probe) { error = sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); if (!error) ctx->asoc->stats.octrlchunks++; break; } fallthrough; case SCTP_CID_SACK: case SCTP_CID_SHUTDOWN: case SCTP_CID_ECN_ECNE: case SCTP_CID_ASCONF: case SCTP_CID_FWD_TSN: case SCTP_CID_I_FWD_TSN: case SCTP_CID_RECONF: status = sctp_packet_transmit_chunk(ctx->packet, chunk, one_packet, ctx->gfp); if (status != SCTP_XMIT_OK) { /* put the chunk back */ list_add(&chunk->list, &ctx->q->control_chunk_list); break; } ctx->asoc->stats.octrlchunks++; /* PR-SCTP C5) If a FORWARD TSN is sent, the * sender MUST assure that at least one T3-rtx * timer is running. */ if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN || chunk->chunk_hdr->type == SCTP_CID_I_FWD_TSN) { sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; } if (chunk == ctx->asoc->strreset_chunk) sctp_transport_reset_reconf_timer(ctx->transport); break; default: /* We built a chunk with an illegal type! */ BUG(); } } } /* Returns false if new data shouldn't be sent */ static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx, int rtx_timeout) { int error, start_timer = 0; if (ctx->asoc->peer.retran_path->state == SCTP_UNCONFIRMED) return false; if (ctx->transport != ctx->asoc->peer.retran_path) { /* Switch transports & prepare the packet. */ ctx->transport = ctx->asoc->peer.retran_path; ctx->packet = &ctx->transport->packet; if (list_empty(&ctx->transport->send_ready)) list_add_tail(&ctx->transport->send_ready, &ctx->transport_list); sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag, ctx->asoc->peer.ecn_capable); } error = __sctp_outq_flush_rtx(ctx->q, ctx->packet, rtx_timeout, &start_timer, ctx->gfp); if (error < 0) ctx->asoc->base.sk->sk_err = -error; if (start_timer) { sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; } /* This can happen on COOKIE-ECHO resend. Only * one chunk can get bundled with a COOKIE-ECHO. */ if (ctx->packet->has_cookie_echo) return false; /* Don't send new data if there is still data * waiting to retransmit. */ if (!list_empty(&ctx->q->retransmit)) return false; return true; } static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, int rtx_timeout) { struct sctp_chunk *chunk; enum sctp_xmit status; /* Is it OK to send data chunks? */ switch (ctx->asoc->state) { case SCTP_STATE_COOKIE_ECHOED: /* Only allow bundling when this packet has a COOKIE-ECHO * chunk. */ if (!ctx->packet || !ctx->packet->has_cookie_echo) return; fallthrough; case SCTP_STATE_ESTABLISHED: case SCTP_STATE_SHUTDOWN_PENDING: case SCTP_STATE_SHUTDOWN_RECEIVED: break; default: /* Do nothing. */ return; } /* RFC 2960 6.1 Transmission of DATA Chunks * * C) When the time comes for the sender to transmit, * before sending new DATA chunks, the sender MUST * first transmit any outstanding DATA chunks which * are marked for retransmission (limited by the * current cwnd). */ if (!list_empty(&ctx->q->retransmit) && !sctp_outq_flush_rtx(ctx, rtx_timeout)) return; /* Apply Max.Burst limitation to the current transport in * case it will be used for new data. We are going to * rest it before we return, but we want to apply the limit * to the currently queued data. */ if (ctx->transport) sctp_transport_burst_limited(ctx->transport); /* Finally, transmit new packets. */ while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) { __u32 sid = ntohs(chunk->subh.data_hdr->stream); __u8 stream_state = SCTP_SO(&ctx->asoc->stream, sid)->state; /* Has this chunk expired? */ if (sctp_chunk_abandoned(chunk)) { sctp_sched_dequeue_done(ctx->q, chunk); sctp_chunk_fail(chunk, 0); sctp_chunk_free(chunk); continue; } if (stream_state == SCTP_STREAM_CLOSED) { sctp_outq_head_data(ctx->q, chunk); break; } sctp_outq_select_transport(ctx, chunk); pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p skb->users:%d\n", __func__, ctx->q, chunk, chunk && chunk->chunk_hdr ? sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) : "illegal chunk", ntohl(chunk->subh.data_hdr->tsn), chunk->skb ? chunk->skb->head : NULL, chunk->skb ? refcount_read(&chunk->skb->users) : -1); /* Add the chunk to the packet. */ status = sctp_packet_transmit_chunk(ctx->packet, chunk, 0, ctx->gfp); if (status != SCTP_XMIT_OK) { /* We could not append this chunk, so put * the chunk back on the output queue. */ pr_debug("%s: could not transmit tsn:0x%x, status:%d\n", __func__, ntohl(chunk->subh.data_hdr->tsn), status); sctp_outq_head_data(ctx->q, chunk); break; } /* The sender is in the SHUTDOWN-PENDING state, * The sender MAY set the I-bit in the DATA * chunk header. */ if (ctx->asoc->state == SCTP_STATE_SHUTDOWN_PENDING) chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) ctx->asoc->stats.ouodchunks++; else ctx->asoc->stats.oodchunks++; /* Only now it's safe to consider this * chunk as sent, sched-wise. */ sctp_sched_dequeue_done(ctx->q, chunk); list_add_tail(&chunk->transmitted_list, &ctx->transport->transmitted); sctp_transport_reset_t3_rtx(ctx->transport); ctx->transport->last_time_sent = jiffies; /* Only let one DATA chunk get bundled with a * COOKIE-ECHO chunk. */ if (ctx->packet->has_cookie_echo) break; } } static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx) { struct sock *sk = ctx->asoc->base.sk; struct list_head *ltransport; struct sctp_packet *packet; struct sctp_transport *t; int error = 0; while ((ltransport = sctp_list_dequeue(&ctx->transport_list)) != NULL) { t = list_entry(ltransport, struct sctp_transport, send_ready); packet = &t->packet; if (!sctp_packet_empty(packet)) { rcu_read_lock(); if (t->dst && __sk_dst_get(sk) != t->dst) { dst_hold(t->dst); sk_setup_caps(sk, t->dst); } rcu_read_unlock(); error = sctp_packet_transmit(packet, ctx->gfp); if (error < 0) ctx->q->asoc->base.sk->sk_err = -error; } /* Clear the burst limited state, if any */ sctp_transport_burst_reset(t); } } /* Try to flush an outqueue. * * Description: Send everything in q which we legally can, subject to * congestion limitations. * * Note: This function can be called from multiple contexts so appropriate * locking concerns must be made. Today we use the sock lock to protect * this function. */ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) { struct sctp_flush_ctx ctx = { .q = q, .transport = NULL, .transport_list = LIST_HEAD_INIT(ctx.transport_list), .asoc = q->asoc, .packet = NULL, .gfp = gfp, }; /* 6.10 Bundling * ... * When bundling control chunks with DATA chunks, an * endpoint MUST place control chunks first in the outbound * SCTP packet. The transmitter MUST transmit DATA chunks * within a SCTP packet in increasing order of TSN. * ... */ sctp_outq_flush_ctrl(&ctx); if (q->asoc->src_out_of_asoc_ok) goto sctp_flush_out; sctp_outq_flush_data(&ctx, rtx_timeout); sctp_flush_out: sctp_outq_flush_transports(&ctx); } /* Update unack_data based on the incoming SACK chunk */ static void sctp_sack_update_unack_data(struct sctp_association *assoc, struct sctp_sackhdr *sack) { union sctp_sack_variable *frags; __u16 unack_data; int i; unack_data = assoc->next_tsn - assoc->ctsn_ack_point - 1; frags = (union sctp_sack_variable *)(sack + 1); for (i = 0; i < ntohs(sack->num_gap_ack_blocks); i++) { unack_data -= ((ntohs(frags[i].gab.end) - ntohs(frags[i].gab.start) + 1)); } assoc->unack_data = unack_data; } /* This is where we REALLY process a SACK. * * Process the SACK against the outqueue. Mostly, this just frees * things off the transmitted queue. */ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) { struct sctp_association *asoc = q->asoc; struct sctp_sackhdr *sack = chunk->subh.sack_hdr; struct sctp_transport *transport; struct sctp_chunk *tchunk = NULL; struct list_head *lchunk, *transport_list, *temp; __u32 sack_ctsn, ctsn, tsn; __u32 highest_tsn, highest_new_tsn; __u32 sack_a_rwnd; unsigned int outstanding; struct sctp_transport *primary = asoc->peer.primary_path; int count_of_newacks = 0; int gap_ack_blocks; u8 accum_moved = 0; /* Grab the association's destination address list. */ transport_list = &asoc->peer.transport_addr_list; /* SCTP path tracepoint for congestion control debugging. */ if (trace_sctp_probe_path_enabled()) { list_for_each_entry(transport, transport_list, transports) trace_sctp_probe_path(transport, asoc); } sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); asoc->stats.gapcnt += gap_ack_blocks; /* * SFR-CACC algorithm: * On receipt of a SACK the sender SHOULD execute the * following statements. * * 1) If the cumulative ack in the SACK passes next tsn_at_change * on the current primary, the CHANGEOVER_ACTIVE flag SHOULD be * cleared. The CYCLING_CHANGEOVER flag SHOULD also be cleared for * all destinations. * 2) If the SACK contains gap acks and the flag CHANGEOVER_ACTIVE * is set the receiver of the SACK MUST take the following actions: * * A) Initialize the cacc_saw_newack to 0 for all destination * addresses. * * Only bother if changeover_active is set. Otherwise, this is * totally suboptimal to do on every SACK. */ if (primary->cacc.changeover_active) { u8 clear_cycling = 0; if (TSN_lte(primary->cacc.next_tsn_at_change, sack_ctsn)) { primary->cacc.changeover_active = 0; clear_cycling = 1; } if (clear_cycling || gap_ack_blocks) { list_for_each_entry(transport, transport_list, transports) { if (clear_cycling) transport->cacc.cycling_changeover = 0; if (gap_ack_blocks) transport->cacc.cacc_saw_newack = 0; } } } /* Get the highest TSN in the sack. */ highest_tsn = sack_ctsn; if (gap_ack_blocks) { union sctp_sack_variable *frags = (union sctp_sack_variable *)(sack + 1); highest_tsn += ntohs(frags[gap_ack_blocks - 1].gab.end); } if (TSN_lt(asoc->highest_sacked, highest_tsn)) asoc->highest_sacked = highest_tsn; highest_new_tsn = sack_ctsn; /* Run through the retransmit queue. Credit bytes received * and free those chunks that we can. */ sctp_check_transmitted(q, &q->retransmit, NULL, NULL, sack, &highest_new_tsn); /* Run through the transmitted queue. * Credit bytes received and free those chunks which we can. * * This is a MASSIVE candidate for optimization. */ list_for_each_entry(transport, transport_list, transports) { sctp_check_transmitted(q, &transport->transmitted, transport, &chunk->source, sack, &highest_new_tsn); /* * SFR-CACC algorithm: * C) Let count_of_newacks be the number of * destinations for which cacc_saw_newack is set. */ if (transport->cacc.cacc_saw_newack) count_of_newacks++; } /* Move the Cumulative TSN Ack Point if appropriate. */ if (TSN_lt(asoc->ctsn_ack_point, sack_ctsn)) { asoc->ctsn_ack_point = sack_ctsn; accum_moved = 1; } if (gap_ack_blocks) { if (asoc->fast_recovery && accum_moved) highest_new_tsn = highest_tsn; list_for_each_entry(transport, transport_list, transports) sctp_mark_missing(q, &transport->transmitted, transport, highest_new_tsn, count_of_newacks); } /* Update unack_data field in the assoc. */ sctp_sack_update_unack_data(asoc, sack); ctsn = asoc->ctsn_ack_point; /* Throw away stuff rotting on the sack queue. */ list_for_each_safe(lchunk, temp, &q->sacked) { tchunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(tchunk->subh.data_hdr->tsn); if (TSN_lte(tsn, ctsn)) { list_del_init(&tchunk->transmitted_list); if (asoc->peer.prsctp_capable && SCTP_PR_PRIO_ENABLED(chunk->sinfo.sinfo_flags)) asoc->sent_cnt_removable--; sctp_chunk_free(tchunk); } } /* ii) Set rwnd equal to the newly received a_rwnd minus the * number of bytes still outstanding after processing the * Cumulative TSN Ack and the Gap Ack Blocks. */ sack_a_rwnd = ntohl(sack->a_rwnd); asoc->peer.zero_window_announced = !sack_a_rwnd; outstanding = q->outstanding_bytes; if (outstanding < sack_a_rwnd) sack_a_rwnd -= outstanding; else sack_a_rwnd = 0; asoc->peer.rwnd = sack_a_rwnd; asoc->stream.si->generate_ftsn(q, sack_ctsn); pr_debug("%s: sack cumulative tsn ack:0x%x\n", __func__, sack_ctsn); pr_debug("%s: cumulative tsn ack of assoc:%p is 0x%x, " "advertised peer ack point:0x%x\n", __func__, asoc, ctsn, asoc->adv_peer_ack_point); return sctp_outq_is_empty(q); } /* Is the outqueue empty? * The queue is empty when we have not pending data, no in-flight data * and nothing pending retransmissions. */ int sctp_outq_is_empty(const struct sctp_outq *q) { return q->out_qlen == 0 && q->outstanding_bytes == 0 && list_empty(&q->retransmit); } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* Go through a transport's transmitted list or the association's retransmit * list and move chunks that are acked by the Cumulative TSN Ack to q->sacked. * The retransmit list will not have an associated transport. * * I added coherent debug information output. --xguo * * Instead of printing 'sacked' or 'kept' for each TSN on the * transmitted_queue, we print a range: SACKED: TSN1-TSN2, TSN3, TSN4-TSN5. * KEPT TSN6-TSN7, etc. */ static void sctp_check_transmitted(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, union sctp_addr *saddr, struct sctp_sackhdr *sack, __u32 *highest_new_tsn_in_sack) { struct list_head *lchunk; struct sctp_chunk *tchunk; struct list_head tlist; __u32 tsn; __u32 sack_ctsn; __u32 rtt; __u8 restart_timer = 0; int bytes_acked = 0; int migrate_bytes = 0; bool forward_progress = false; sack_ctsn = ntohl(sack->cum_tsn_ack); INIT_LIST_HEAD(&tlist); /* The while loop will skip empty transmitted queues. */ while (NULL != (lchunk = sctp_list_dequeue(transmitted_queue))) { tchunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); if (sctp_chunk_abandoned(tchunk)) { /* Move the chunk to abandoned list. */ sctp_insert_list(&q->abandoned, lchunk); /* If this chunk has not been acked, stop * considering it as 'outstanding'. */ if (transmitted_queue != &q->retransmit && !tchunk->tsn_gap_acked) { if (tchunk->transport) tchunk->transport->flight_size -= sctp_data_size(tchunk); q->outstanding_bytes -= sctp_data_size(tchunk); } continue; } tsn = ntohl(tchunk->subh.data_hdr->tsn); if (sctp_acked(sack, tsn)) { /* If this queue is the retransmit queue, the * retransmit timer has already reclaimed * the outstanding bytes for this chunk, so only * count bytes associated with a transport. */ if (transport && !tchunk->tsn_gap_acked) { /* If this chunk is being used for RTT * measurement, calculate the RTT and update * the RTO using this value. * * 6.3.1 C5) Karn's algorithm: RTT measurements * MUST NOT be made using packets that were * retransmitted (and thus for which it is * ambiguous whether the reply was for the * first instance of the packet or a later * instance). */ if (!sctp_chunk_retransmitted(tchunk) && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; sctp_transport_update_rto(transport, rtt); } if (TSN_lte(tsn, sack_ctsn)) { /* * SFR-CACC algorithm: * 2) If the SACK contains gap acks * and the flag CHANGEOVER_ACTIVE is * set the receiver of the SACK MUST * take the following action: * * B) For each TSN t being acked that * has not been acked in any SACK so * far, set cacc_saw_newack to 1 for * the destination that the TSN was * sent to. */ if (sack->num_gap_ack_blocks && q->asoc->peer.primary_path->cacc. changeover_active) transport->cacc.cacc_saw_newack = 1; } } /* If the chunk hasn't been marked as ACKED, * mark it and account bytes_acked if the * chunk had a valid transport (it will not * have a transport if ASCONF had deleted it * while DATA was outstanding). */ if (!tchunk->tsn_gap_acked) { tchunk->tsn_gap_acked = 1; if (TSN_lt(*highest_new_tsn_in_sack, tsn)) *highest_new_tsn_in_sack = tsn; bytes_acked += sctp_data_size(tchunk); if (!tchunk->transport) migrate_bytes += sctp_data_size(tchunk); forward_progress = true; } if (TSN_lte(tsn, sack_ctsn)) { /* RFC 2960 6.3.2 Retransmission Timer Rules * * R3) Whenever a SACK is received * that acknowledges the DATA chunk * with the earliest outstanding TSN * for that address, restart T3-rtx * timer for that address with its * current RTO. */ restart_timer = 1; forward_progress = true; list_add_tail(&tchunk->transmitted_list, &q->sacked); } else { /* RFC2960 7.2.4, sctpimpguide-05 2.8.2 * M2) Each time a SACK arrives reporting * 'Stray DATA chunk(s)' record the highest TSN * reported as newly acknowledged, call this * value 'HighestTSNinSack'. A newly * acknowledged DATA chunk is one not * previously acknowledged in a SACK. * * When the SCTP sender of data receives a SACK * chunk that acknowledges, for the first time, * the receipt of a DATA chunk, all the still * unacknowledged DATA chunks whose TSN is * older than that newly acknowledged DATA * chunk, are qualified as 'Stray DATA chunks'. */ list_add_tail(lchunk, &tlist); } } else { if (tchunk->tsn_gap_acked) { pr_debug("%s: receiver reneged on data TSN:0x%x\n", __func__, tsn); tchunk->tsn_gap_acked = 0; if (tchunk->transport) bytes_acked -= sctp_data_size(tchunk); /* RFC 2960 6.3.2 Retransmission Timer Rules * * R4) Whenever a SACK is received missing a * TSN that was previously acknowledged via a * Gap Ack Block, start T3-rtx for the * destination address to which the DATA * chunk was originally * transmitted if it is not already running. */ restart_timer = 1; } list_add_tail(lchunk, &tlist); } } if (transport) { if (bytes_acked) { struct sctp_association *asoc = transport->asoc; /* We may have counted DATA that was migrated * to this transport due to DEL-IP operation. * Subtract those bytes, since the were never * send on this transport and shouldn't be * credited to this transport. */ bytes_acked -= migrate_bytes; /* 8.2. When an outstanding TSN is acknowledged, * the endpoint shall clear the error counter of * the destination transport address to which the * DATA chunk was last sent. * The association's overall error counter is * also cleared. */ transport->error_count = 0; transport->asoc->overall_error_count = 0; forward_progress = true; /* * While in SHUTDOWN PENDING, we may have started * the T5 shutdown guard timer after reaching the * retransmission limit. Stop that timer as soon * as the receiver acknowledged any data. */ if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING && del_timer(&asoc->timers [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) sctp_association_put(asoc); /* Mark the destination transport address as * active if it is not so marked. */ if ((transport->state == SCTP_INACTIVE || transport->state == SCTP_UNCONFIRMED) && sctp_cmp_addr_exact(&transport->ipaddr, saddr)) { sctp_assoc_control_transport( transport->asoc, transport, SCTP_TRANSPORT_UP, SCTP_RECEIVED_SACK); } sctp_transport_raise_cwnd(transport, sack_ctsn, bytes_acked); transport->flight_size -= bytes_acked; if (transport->flight_size == 0) transport->partial_bytes_acked = 0; q->outstanding_bytes -= bytes_acked + migrate_bytes; } else { /* RFC 2960 6.1, sctpimpguide-06 2.15.2 * When a sender is doing zero window probing, it * should not timeout the association if it continues * to receive new packets from the receiver. The * reason is that the receiver MAY keep its window * closed for an indefinite time. * A sender is doing zero window probing when the * receiver's advertised window is zero, and there is * only one data chunk in flight to the receiver. * * Allow the association to timeout while in SHUTDOWN * PENDING or SHUTDOWN RECEIVED in case the receiver * stays in zero window mode forever. */ if (!q->asoc->peer.rwnd && !list_empty(&tlist) && (sack_ctsn+2 == q->asoc->next_tsn) && q->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) { pr_debug("%s: sack received for zero window " "probe:%u\n", __func__, sack_ctsn); q->asoc->overall_error_count = 0; transport->error_count = 0; } } /* RFC 2960 6.3.2 Retransmission Timer Rules * * R2) Whenever all outstanding data sent to an address have * been acknowledged, turn off the T3-rtx timer of that * address. */ if (!transport->flight_size) { if (del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); } else if (restart_timer) { if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); } if (forward_progress) { if (transport->dst) sctp_transport_dst_confirm(transport); } } list_splice(&tlist, transmitted_queue); } /* Mark chunks as missing and consequently may get retransmitted. */ static void sctp_mark_missing(struct sctp_outq *q, struct list_head *transmitted_queue, struct sctp_transport *transport, __u32 highest_new_tsn_in_sack, int count_of_newacks) { struct sctp_chunk *chunk; __u32 tsn; char do_fast_retransmit = 0; struct sctp_association *asoc = q->asoc; struct sctp_transport *primary = asoc->peer.primary_path; list_for_each_entry(chunk, transmitted_queue, transmitted_list) { tsn = ntohl(chunk->subh.data_hdr->tsn); /* RFC 2960 7.2.4, sctpimpguide-05 2.8.2 M3) Examine all * 'Unacknowledged TSN's', if the TSN number of an * 'Unacknowledged TSN' is smaller than the 'HighestTSNinSack' * value, increment the 'TSN.Missing.Report' count on that * chunk if it has NOT been fast retransmitted or marked for * fast retransmit already. */ if (chunk->fast_retransmit == SCTP_CAN_FRTX && !chunk->tsn_gap_acked && TSN_lt(tsn, highest_new_tsn_in_sack)) { /* SFR-CACC may require us to skip marking * this chunk as missing. */ if (!transport || !sctp_cacc_skip(primary, chunk->transport, count_of_newacks, tsn)) { chunk->tsn_missing_report++; pr_debug("%s: tsn:0x%x missing counter:%d\n", __func__, tsn, chunk->tsn_missing_report); } } /* * M4) If any DATA chunk is found to have a * 'TSN.Missing.Report' * value larger than or equal to 3, mark that chunk for * retransmission and start the fast retransmit procedure. */ if (chunk->tsn_missing_report >= 3) { chunk->fast_retransmit = SCTP_NEED_FRTX; do_fast_retransmit = 1; } } if (transport) { if (do_fast_retransmit) sctp_retransmit(q, transport, SCTP_RTXR_FAST_RTX); pr_debug("%s: transport:%p, cwnd:%d, ssthresh:%d, " "flight_size:%d, pba:%d\n", __func__, transport, transport->cwnd, transport->ssthresh, transport->flight_size, transport->partial_bytes_acked); } } /* Is the given TSN acked by this packet? */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn) { __u32 ctsn = ntohl(sack->cum_tsn_ack); union sctp_sack_variable *frags; __u16 tsn_offset, blocks; int i; if (TSN_lte(tsn, ctsn)) goto pass; /* 3.3.4 Selective Acknowledgment (SACK) (3): * * Gap Ack Blocks: * These fields contain the Gap Ack Blocks. They are repeated * for each Gap Ack Block up to the number of Gap Ack Blocks * defined in the Number of Gap Ack Blocks field. All DATA * chunks with TSNs greater than or equal to (Cumulative TSN * Ack + Gap Ack Block Start) and less than or equal to * (Cumulative TSN Ack + Gap Ack Block End) of each Gap Ack * Block are assumed to have been received correctly. */ frags = (union sctp_sack_variable *)(sack + 1); blocks = ntohs(sack->num_gap_ack_blocks); tsn_offset = tsn - ctsn; for (i = 0; i < blocks; ++i) { if (tsn_offset >= ntohs(frags[i].gab.start) && tsn_offset <= ntohs(frags[i].gab.end)) goto pass; } return 0; pass: return 1; } static inline int sctp_get_skip_pos(struct sctp_fwdtsn_skip *skiplist, int nskips, __be16 stream) { int i; for (i = 0; i < nskips; i++) { if (skiplist[i].stream == stream) return i; } return i; } /* Create and add a fwdtsn chunk to the outq's control queue if needed. */ void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 ctsn) { struct sctp_association *asoc = q->asoc; struct sctp_chunk *ftsn_chunk = NULL; struct sctp_fwdtsn_skip ftsn_skip_arr[10]; int nskips = 0; int skip_pos = 0; __u32 tsn; struct sctp_chunk *chunk; struct list_head *lchunk, *temp; if (!asoc->peer.prsctp_capable) return; /* PR-SCTP C1) Let SackCumAck be the Cumulative TSN ACK carried in the * received SACK. * * If (Advanced.Peer.Ack.Point < SackCumAck), then update * Advanced.Peer.Ack.Point to be equal to SackCumAck. */ if (TSN_lt(asoc->adv_peer_ack_point, ctsn)) asoc->adv_peer_ack_point = ctsn; /* PR-SCTP C2) Try to further advance the "Advanced.Peer.Ack.Point" * locally, that is, to move "Advanced.Peer.Ack.Point" up as long as * the chunk next in the out-queue space is marked as "abandoned" as * shown in the following example: * * Assuming that a SACK arrived with the Cumulative TSN ACK 102 * and the Advanced.Peer.Ack.Point is updated to this value: * * out-queue at the end of ==> out-queue after Adv.Ack.Point * normal SACK processing local advancement * ... ... * Adv.Ack.Pt-> 102 acked 102 acked * 103 abandoned 103 abandoned * 104 abandoned Adv.Ack.P-> 104 abandoned * 105 105 * 106 acked 106 acked * ... ... * * In this example, the data sender successfully advanced the * "Advanced.Peer.Ack.Point" from 102 to 104 locally. */ list_for_each_safe(lchunk, temp, &q->abandoned) { chunk = list_entry(lchunk, struct sctp_chunk, transmitted_list); tsn = ntohl(chunk->subh.data_hdr->tsn); /* Remove any chunks in the abandoned queue that are acked by * the ctsn. */ if (TSN_lte(tsn, ctsn)) { list_del_init(lchunk); sctp_chunk_free(chunk); } else { if (TSN_lte(tsn, asoc->adv_peer_ack_point+1)) { asoc->adv_peer_ack_point = tsn; if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED) continue; skip_pos = sctp_get_skip_pos(&ftsn_skip_arr[0], nskips, chunk->subh.data_hdr->stream); ftsn_skip_arr[skip_pos].stream = chunk->subh.data_hdr->stream; ftsn_skip_arr[skip_pos].ssn = chunk->subh.data_hdr->ssn; if (skip_pos == nskips) nskips++; if (nskips == 10) break; } else break; } } /* PR-SCTP C3) If, after step C1 and C2, the "Advanced.Peer.Ack.Point" * is greater than the Cumulative TSN ACK carried in the received * SACK, the data sender MUST send the data receiver a FORWARD TSN * chunk containing the latest value of the * "Advanced.Peer.Ack.Point". * * C4) For each "abandoned" TSN the sender of the FORWARD TSN SHOULD * list each stream and sequence number in the forwarded TSN. This * information will enable the receiver to easily find any * stranded TSN's waiting on stream reorder queues. Each stream * SHOULD only be reported once; this means that if multiple * abandoned messages occur in the same stream then only the * highest abandoned stream sequence number is reported. If the * total size of the FORWARD TSN does NOT fit in a single MTU then * the sender of the FORWARD TSN SHOULD lower the * Advanced.Peer.Ack.Point to the last TSN that will fit in a * single MTU. */ if (asoc->adv_peer_ack_point > ctsn) ftsn_chunk = sctp_make_fwdtsn(asoc, asoc->adv_peer_ack_point, nskips, &ftsn_skip_arr[0]); if (ftsn_chunk) { list_add_tail(&ftsn_chunk->list, &q->control_chunk_list); SCTP_INC_STATS(asoc->base.net, SCTP_MIB_OUTCTRLCHUNKS); } } |
| 1638 1638 1638 1638 10270 10272 10272 4864 2912 10273 27 1638 1638 1638 1638 1638 1638 1638 1638 1638 1638 1638 1636 10286 10284 29 10270 30 10272 10273 5043 6213 10273 10264 2606 2603 79 2578 1668 9437 9436 9439 9439 1048 1048 1049 18 2 7 2 5 1042 2297 2297 1609 22674 3 23039 23026 23032 23016 196 85 39 4 37 1587 22669 20428 22840 646 647 858 2780 3639 3641 3622 2282 5 5 3 2 38 6 34 4 47 47 47 47 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> #include "internal.h" unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int count) { unsigned int cpy, set; cpy = count / BITS_PER_BYTE; set = (nfdt->max_fds - count) / BITS_PER_BYTE; memcpy(nfdt->open_fds, ofdt->open_fds, cpy); memset((char *)nfdt->open_fds + cpy, 0, set); memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); memset((char *)nfdt->close_on_exec + cpy, 0, set); cpy = BITBIT_SIZE(count); set = BITBIT_SIZE(nfdt->max_fds) - cpy; memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); memset((char *)nfdt->full_fds_bits + cpy, 0, set); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". * * The ALIGN(nr, BITS_PER_LONG) here is for clarity: since we just multiplied * by that "1024/sizeof(ptr)" before, we already know there are sufficient * clear low bits. Clang seems to realize that, gcc ends up being confused. * * On a 128-bit machine, the ALIGN() would actually matter. In the meantime, * let's consider it documentation (and maybe a test-case for gcc to improve * its code generation ;) */ static struct fdtable * alloc_fdtable(unsigned int nr) { struct fdtable *fdt; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. */ nr /= (1024 / sizeof(struct file *)); nr = roundup_pow_of_two(nr + 1); nr *= (1024 / sizeof(struct file *)); nr = ALIGN(nr, BITS_PER_LONG); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. Deal * with that in caller, it's cheaper that way. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1; fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return NULL; } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 1 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (!new_fdt) return -ENOMEM; /* * extremely unlikely race - sysctl_nr_open decreased between the check in * caller and alloc_fdtable(). Cheaper to catch it here... */ if (unlikely(new_fdt->max_fds <= nr)) { __free_fdtable(new_fdt); return -EMFILE; } cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 1; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 when nothing done; 1 when files were * expanded and execution may have blocked. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int expanded = 0; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return expanded; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt) { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static unsigned int count_open_files(struct fdtable *fdt) { unsigned int size = fdt->max_fds; unsigned int i; /* Find the last open fd */ for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) break; } i = (i + 1) * BITS_PER_LONG; return i; } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * 'max_fds' will normally already be properly aligned, but it * turns out that in the close_range() -> __close_range() -> * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end * up having a 'max_fds' value that isn't already aligned. * * Rather than make close_range() have to worry about this, * just make that BITS_PER_LONG alignment be part of a sane * fdtable size. Becuase that's really what it is. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) { unsigned int count; count = count_open_files(fdt); if (max_fds < NR_OPEN_DEFAULT) max_fds = NR_OPEN_DEFAULT; return ALIGN(min(count, max_fds), BITS_PER_LONG); } /* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files - 1); if (!new_fdt) { *errorp = -ENOMEM; goto out_release; } /* beyond sysctl_nr_open; nothing to do */ if (unlikely(new_fdt->max_fds < open_files)) { __free_fdtable(new_fdt); *errorp = -EMFILE; goto out_release; } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); } copy_fd_bitmaps(new_fdt, old_fdt, open_files); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit > maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (fd < fdt->max_fds) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (fd >= end) goto out; error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); error = fd; #if 1 /* Sanity check */ if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /* for ksys_close() */ /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; unsigned n; spin_lock(&files->file_lock); n = last_fd(files_fdtable(files)); max_fd = min(max_fd, n); for (; fd <= max_fd; fd++) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } /** * __close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. */ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if (flags & CLOSE_RANGE_UNSHARE) { int ret; unsigned int max_unshare_fds = NR_OPEN_MAX; /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (!(flags & CLOSE_RANGE_CLOEXEC)) { /* * If the requested range is greater than the current * maximum, we're closing everything so only copy all * file descriptors beneath the lowest file descriptor. */ rcu_read_lock(); if (max_fd >= last_fd(files_fdtable(cur_fds))) max_unshare_fds = fd; rcu_read_unlock(); } ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); if (ret) return ret; /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ if (fds) swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!atomic_long_inc_not_zero(&file->f_count))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * atomic_long_inc_not_zero() above provided a full memory * barrier when we acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (unlikely(!file)) return NULL; if (unlikely(IS_ERR(file))) continue; return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * atomic_long_inc_not_zero() gives us a full memory * barrier. We only really need an 'acquire' one to * protect the loads below, but we don't have that. */ if (unlikely(!atomic_long_inc_not_zero(&file->f_count))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0); task_unlock(task); return file; } struct file *lookup_fdget_rcu(unsigned int fd) { return __fget_files_rcu(current->files, fd, 0); } EXPORT_SYMBOL_GPL(lookup_fdget_rcu); struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; struct file *file = NULL; task_lock(task); files = task->files; if (files) file = __fget_files_rcu(files, fd, 0); task_unlock(task); return file; } struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(task_lookup_next_fdget_rcu); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { file = __fget_files(files, fd, mask); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; } } unsigned long __fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(__fdget); unsigned long __fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || file->f_op->iterate_shared); } unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return v; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; struct fdtable *fdt; bool res; rcu_read_lock(); fdt = files_fdtable(files); res = close_on_exec(fd, fdt); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; if (ufd) { error = put_user(new_fd, ufd); if (error) { put_unused_fd(new_fd); return error; } } fd_install(new_fd, get_file(file)); __receive_sock(file); return new_fd; } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 7 7 14 14 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 | // SPDX-License-Identifier: GPL-2.0 /* XDP user-space ring structure * Copyright(c) 2018 Intel Corporation. */ #include <linux/log2.h> #include <linux/slab.h> #include <linux/overflow.h> #include <linux/vmalloc.h> #include <net/xdp_sock_drv.h> #include "xsk_queue.h" static size_t xskq_get_ring_size(struct xsk_queue *q, bool umem_queue) { struct xdp_umem_ring *umem_ring; struct xdp_rxtx_ring *rxtx_ring; if (umem_queue) return struct_size(umem_ring, desc, q->nentries); return struct_size(rxtx_ring, desc, q->nentries); } struct xsk_queue *xskq_create(u32 nentries, bool umem_queue) { struct xsk_queue *q; size_t size; q = kzalloc(sizeof(*q), GFP_KERNEL); if (!q) return NULL; q->nentries = nentries; q->ring_mask = nentries - 1; size = xskq_get_ring_size(q, umem_queue); /* size which is overflowing or close to SIZE_MAX will become 0 in * PAGE_ALIGN(), checking SIZE_MAX is enough due to the previous * is_power_of_2(), the rest will be handled by vmalloc_user() */ if (unlikely(size == SIZE_MAX)) { kfree(q); return NULL; } size = PAGE_ALIGN(size); q->ring = vmalloc_user(size); if (!q->ring) { kfree(q); return NULL; } q->ring_vmalloc_size = size; return q; } void xskq_destroy(struct xsk_queue *q) { if (!q) return; vfree(q->ring); kfree(q); } |
| 913 294 1213 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Parameters used to convert the timespec values: */ #define PSEC_PER_NSEC 1000L /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) #define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow / underflow */ if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; if (ts->tv_sec <= KTIME_SEC_MIN) return KTIME_MIN; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */ |
| 1787 170 65 170 176 176 236 65 236 176 6410 229 252 925 5412 22 5410 5411 6543 6546 6726 6545 1124 105 2 43 397 365 141 234 7578 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #ifndef _LINUX_BPF_H #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> #include <uapi/linux/filter.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/percpu.h> #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> #include <linux/mm_types.h> #include <linux/wait.h> #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/capability.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/stddef.h> #include <linux/bpfptr.h> #include <linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/static_call.h> #include <linux/memcontrol.h> #include <linux/cfi.h> struct bpf_verifier_env; struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; struct sock; struct seq_file; struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; struct mem_cgroup; struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); typedef unsigned int (*bpf_func_t)(const void *, const struct bpf_insn *); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; }; /* map is generic key/value storage optionally accessible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); void (*map_release_uref)(struct bpf_map *map); void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_update_batch)(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); long (*map_delete_elem)(struct bpf_map *map, void *key); long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); long (*map_pop_elem)(struct bpf_map *map, void *value); long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); /* If need_defer is true, the implementation should guarantee that * the to-be-put element is still alive before the bpf program, which * may manipulate it, exists. */ void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); /* Prog poke tracking helpers. */ int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new); /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); /* Functions called by bpf_local_storage maps */ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, void *owner, u32 size); void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ long (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure * an inner map can be inserted to an outer map. * * Some properties of the inner map has been used during the * verification time. When inserting an inner map at the runtime, * map_meta_equal has to ensure the inserting map has the same * properties that the verifier has used earlier. */ bool (*map_meta_equal)(const struct bpf_map *meta0, const struct bpf_map *meta1); int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); u64 (*map_mem_usage)(const struct bpf_map *map); /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info; }; enum { /* Support at most 10 fields in a BTF type */ BTF_FIELDS_MAX = 10, }; enum btf_field_type { BPF_SPIN_LOCK = (1 << 0), BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR_PERCPU = (1 << 4), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU, BPF_LIST_HEAD = (1 << 5), BPF_LIST_NODE = (1 << 6), BPF_RB_ROOT = (1 << 7), BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), }; typedef void (*btf_dtor_kfunc_t)(void *); struct btf_field_kptr { struct btf *btf; struct module *module; /* dtor used if btf_is_kernel(btf), otherwise the type is * program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used */ btf_dtor_kfunc_t dtor; u32 btf_id; }; struct btf_field_graph_root { struct btf *btf; u32 value_btf_id; u32 node_offset; struct btf_record *value_rec; }; struct btf_field { u32 offset; u32 size; enum btf_field_type type; union { struct btf_field_kptr kptr; struct btf_field_graph_root graph_root; }; }; struct btf_record { u32 cnt; u32 field_mask; int spin_lock_off; int timer_off; int refcount_off; struct btf_field fields[]; }; /* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */ struct bpf_rb_node_kern { struct rb_node rb_node; void *owner; } __attribute__((aligned(8))); /* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */ struct bpf_list_node_kern { struct list_head list_head; void *owner; } __attribute__((aligned(8))); struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). */ const struct bpf_map_ops *ops ____cacheline_aligned; struct bpf_map *inner_map_meta; #ifdef CONFIG_SECURITY void *security; #endif enum bpf_map_type map_type; u32 key_size; u32 value_size; u32 max_entries; u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; u32 id; struct btf_record *record; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG_KMEM struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; struct rcu_head rcu; }; struct mutex freeze_mutex; atomic64_t writecnt; /* 'Ownership' of program-containing map is claimed by the first program * that is going to use this map or by the first program which FD is * stored in the map to make sure that all callers and callees have the * same prog type, JITed flag and xdp_has_frags flag. */ struct { spinlock_t lock; enum bpf_prog_type type; bool jited; bool xdp_has_frags; } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ bool free_after_mult_rcu_gp; bool free_after_rcu_gp; atomic64_t sleepable_refcnt; s64 __percpu *elem_count; }; static inline const char *btf_field_type_name(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return "bpf_spin_lock"; case BPF_TIMER: return "bpf_timer"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; case BPF_KPTR_PERCPU: return "percpu_kptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: return "bpf_list_node"; case BPF_RB_ROOT: return "bpf_rb_root"; case BPF_RB_NODE: return "bpf_rb_node"; case BPF_REFCOUNT: return "bpf_refcount"; default: WARN_ON_ONCE(1); return "unknown"; } } static inline u32 btf_field_type_size(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return sizeof(struct bpf_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); case BPF_LIST_NODE: return sizeof(struct bpf_list_node); case BPF_RB_ROOT: return sizeof(struct bpf_rb_root); case BPF_RB_NODE: return sizeof(struct bpf_rb_node); case BPF_REFCOUNT: return sizeof(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } static inline u32 btf_field_type_align(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return __alignof__(struct bpf_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); case BPF_LIST_NODE: return __alignof__(struct bpf_list_node); case BPF_RB_ROOT: return __alignof__(struct bpf_rb_root); case BPF_RB_NODE: return __alignof__(struct bpf_rb_node); case BPF_REFCOUNT: return __alignof__(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) { memset(addr, 0, field->size); switch (field->type) { case BPF_REFCOUNT: refcount_set((refcount_t *)addr, 1); break; case BPF_RB_NODE: RB_CLEAR_NODE((struct rb_node *)addr); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: INIT_LIST_HEAD((struct list_head *)addr); break; case BPF_RB_ROOT: /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: break; default: WARN_ON_ONCE(1); return; } } static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) { if (IS_ERR_OR_NULL(rec)) return false; return rec->field_mask & type; } static inline void bpf_obj_init(const struct btf_record *rec, void *obj) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset); } /* 'dst' must be a temporary buffer and should not point to memory that is being * used in parallel by a bpf program or bpf syscall, otherwise the access from * the bpf program or bpf syscall may be corrupted by the reinitialization, * leading to weird problems. Even 'dst' is newly-allocated from bpf memory * allocator, it is still possible for 'dst' to be used in parallel by a bpf * program or bpf syscall. */ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { bpf_obj_init(map->record, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent * updates from BPF programs. Called from bpf syscall and mostly used with * size 8 or 16 bytes, so ask compiler to inline it. */ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) { const long *lsrc = src; long *ldst = dst; size /= sizeof(long); while (size--) data_race(*ldst++ = *lsrc++); } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ static inline void bpf_obj_memcpy(struct btf_record *rec, void *dst, void *src, u32 size, bool long_memcpy) { u32 curr_off = 0; int i; if (IS_ERR_OR_NULL(rec)) { if (long_memcpy) bpf_long_memcpy(dst, src, round_up(size, 8)); else memcpy(dst, src, size); return; } for (i = 0; i < rec->cnt; i++) { u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); curr_off += rec->fields[i].size + sz; } memcpy(dst + curr_off, src + curr_off, size - curr_off); } static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { bpf_obj_memcpy(map->record, dst, src, map->value_size, false); } static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) { bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; int i; if (IS_ERR_OR_NULL(rec)) { memset(dst, 0, size); return; } for (i = 0; i < rec->cnt; i++) { u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); curr_off += rec->fields[i].size + sz; } memset(dst + curr_off, 0, size - curr_off); } static inline void zero_map_value(struct bpf_map *map, void *dst) { bpf_obj_memzero(map->record, dst, map->value_size); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, struct bpf_spin_lock *spin_lock); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; struct bpf_offloaded_map; struct bpf_map_dev_ops { int (*map_get_next_key)(struct bpf_offloaded_map *map, void *key, void *next_key); int (*map_lookup_elem)(struct bpf_offloaded_map *map, void *key, void *value); int (*map_update_elem)(struct bpf_offloaded_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key); }; struct bpf_offloaded_map { struct bpf_map map; struct net_device *netdev; const struct bpf_map_dev_ops *dev_ops; void *dev_priv; struct list_head offloads; }; static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) { return container_of(map, struct bpf_offloaded_map, map); } static inline bool bpf_map_offload_neutral(const struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) && map->ops->map_seq_show_elem; } int map_check_no_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); bool bpf_map_meta_equal(const struct bpf_map *meta0, const struct bpf_map *meta1); extern const struct bpf_map_ops bpf_map_offload_ops; /* bpf_type_flag contains a set of flags that are applicable to the values of * arg_type, ret_type and reg_type. For example, a pointer value may be null, * or a memory is read-only. We classify types into two categories: base types * and extended types. Extended types are base types combined with a type flag. * * Currently there are no more than 32 base types in arg_type, ret_type and * reg_types. */ #define BPF_BASE_TYPE_BITS 8 enum bpf_type_flag { /* PTR may be NULL. */ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), /* MEM is read-only. When applied on bpf_arg, it indicates the arg is * compatible with both mutable and immutable memory. */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), /* MEM points to BPF ring buffer reservation. */ MEM_RINGBUF = BIT(2 + BPF_BASE_TYPE_BITS), /* MEM is in user address space. */ MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), /* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged * with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In * order to drop this tag, it must be passed into bpf_per_cpu_ptr() * or bpf_this_cpu_ptr(), which will return the pointer corresponding * to the specified cpu. */ MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), /* Indicates that the argument will be released. */ OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), /* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark * unreferenced and referenced kptr loaded from map value using a load * instruction, so that they can only be dereferenced but not escape the * BPF program into the kernel (i.e. cannot be passed as arguments to * kfunc or bpf helpers). */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), /* DYNPTR points to a kernel-produced ringbuf record. */ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), /* Size is known at compile time. */ MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), /* MEM is of an allocated object of type in program BTF. This is used to * tag PTR_TO_BTF_ID allocated using bpf_obj_new. */ MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), /* PTR was passed from the kernel in a trusted context, and may be * passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions. * Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above. * PTR_UNTRUSTED refers to a kptr that was read directly from a map * without invoking bpf_kptr_xchg(). What we really need to know is * whether a pointer is safe to pass to a kfunc or BPF helper function. * While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF * helpers, they do not cover all possible instances of unsafe * pointers. For example, a pointer that was obtained from walking a * struct will _not_ get the PTR_UNTRUSTED type modifier, despite the * fact that it may be NULL, invalid, etc. This is due to backwards * compatibility requirements, as this was the behavior that was first * introduced when kptrs were added. The behavior is now considered * deprecated, and PTR_UNTRUSTED will eventually be removed. * * PTR_TRUSTED, on the other hand, is a pointer that the kernel * guarantees to be valid and safe to pass to kfuncs and BPF helpers. * For example, pointers passed to tracepoint arguments are considered * PTR_TRUSTED, as are pointers that are passed to struct_ops * callbacks. As alluded to above, pointers that are obtained from * walking PTR_TRUSTED pointers are _not_ trusted. For example, if a * struct task_struct *task is PTR_TRUSTED, then accessing * task->last_wakee will lose the PTR_TRUSTED modifier when it's stored * in a BPF register. Similarly, pointers passed to certain programs * types such as kretprobes are not guaranteed to be valid, as they may * for example contain an object that was recently freed. */ PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS), /* MEM is tagged with rcu and memory access needs rcu_read_lock protection. */ MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS), /* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning. * Currently only valid for linked-list and rbtree nodes. If the nodes * have a bpf_refcount_field, they must be tagged MEM_RCU as well. */ NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS), /* DYNPTR points to sk_buff */ DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS), /* DYNPTR points to xdp_buff */ DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; #define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \ | DYNPTR_TYPE_XDP) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) /* Max number of all types. */ #define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1)) /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ /* the following constraints used to prototype * bpf_map_lookup/update/delete_elem() functions */ ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ /* Used to prototype bpf_memcmp() and other functions that access data * on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, /* pointer to memory does not need to be initialized, helper function must fill * all bytes or clear them in error case. */ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* type of values returned from helper functions */ enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ RET_PTR_TO_MEM, /* returns a pointer to memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ __BPF_RET_TYPE_MAX, /* Extended ret_types. */ RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE, RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, RET_PTR_TO_RINGBUF_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM, RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, RET_PTR_TO_BTF_ID_TRUSTED = PTR_TRUSTED | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL * instructions after verifying */ struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; bool pkt_access; bool might_sleep; enum bpf_return_type ret_type; union { struct { enum bpf_arg_type arg1_type; enum bpf_arg_type arg2_type; enum bpf_arg_type arg3_type; enum bpf_arg_type arg4_type; enum bpf_arg_type arg5_type; }; enum bpf_arg_type arg_type[5]; }; union { struct { u32 *arg1_btf_id; u32 *arg2_btf_id; u32 *arg3_btf_id; u32 *arg4_btf_id; u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; struct { size_t arg1_size; size_t arg2_size; size_t arg3_size; size_t arg4_size; size_t arg5_size; }; size_t arg_size[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is * the first argument to eBPF programs. * For socket filters: 'struct bpf_context *' == 'struct sk_buff *' */ struct bpf_context; enum bpf_access_type { BPF_READ = 1, BPF_WRITE = 2 }; /* types of values stored in eBPF registers */ /* Pointer types represent: * pointer * pointer + imm * pointer + (u16) var * pointer + (u16) var + imm * if (range > 0) then [ptr, ptr + range - off) is safe to access * if (id > 0) means that some 'var' was added * if (off > 0) means that 'imm' was added */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need * to be null checked by the BPF program. This does not imply the * pointer is _not_ null and in practice this can easily be a null * pointer when reading pointer chains. The assumption is program * context will handle null pointer dereference typically via fault * handling. The verifier must keep this in mind and can make no * assumptions about null or non-null when doing branch analysis. * Further, when passed into helpers the helpers can not, without * additional context, assume the value is non-null. */ PTR_TO_BTF_ID, /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* The information passed from prog-specific *_is_valid_access * back to the verifier. */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; union { int ctx_field_size; struct { struct btf *btf; u32 btf_id; }; }; struct bpf_verifier_log *log; /* for verbose logs */ }; static inline void bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) { aux->ctx_field_size = size; } static bool bpf_is_ldimm64(const struct bpf_insn *insn) { return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); }; struct bpf_reg_state; struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto * (*get_func_proto)(enum bpf_func_id func_id, const struct bpf_prog *prog); /* return true if 'size' wide access at offset 'off' within bpf_context * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); int (*gen_ld_abs)(const struct bpf_insn *orig, struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); }; struct bpf_prog_offload_ops { /* verifier basic callbacks */ int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); /* verifier optimization callbacks (called after .finalize) */ int (*replace_insn)(struct bpf_verifier_env *env, u32 off, struct bpf_insn *insn); int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt); /* program management callbacks */ int (*prepare)(struct bpf_prog *prog); int (*translate)(struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); }; struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; struct bpf_offload_dev *offdev; void *dev_priv; struct list_head offloads; bool dev_state; bool opt_failed; void *jited_image; u32 jited_len; }; enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX }; #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX /* The longest tracepoint has 12 args. * See include/trace/bpf_probe.h */ #define MAX_BPF_FUNC_ARGS 12 /* The maximum number of arguments passed through registers * a single function may have. */ #define MAX_BPF_FUNC_REG_ARGS 5 /* The argument is a structure. */ #define BTF_FMODEL_STRUCT_ARG BIT(0) /* The argument is signed. */ #define BTF_FMODEL_SIGNED_ARG BIT(1) struct btf_func_model { u8 ret_size; u8 ret_flags; u8 nr_args; u8 arg_size[MAX_BPF_FUNC_ARGS]; u8 arg_flags[MAX_BPF_FUNC_ARGS]; }; /* Restore arguments before returning from trampoline to let original function * continue executing. This flag is used for fentry progs when there are no * fexit progs. */ #define BPF_TRAMP_F_RESTORE_REGS BIT(0) /* Call original function after fentry progs, but before fexit progs. * Makes sense for fentry/fexit, normal calls and indirect calls. */ #define BPF_TRAMP_F_CALL_ORIG BIT(1) /* Skip current frame and return to parent. Makes sense for fentry/fexit * programs only. Should not be used with normal calls and indirect calls. */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) /* Store IP address of the caller on the trampoline stack, * so it's available for trampoline's programs. */ #define BPF_TRAMP_F_IP_ARG BIT(3) /* Return the return value of fentry prog. Only used by bpf_struct_ops. */ #define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Get original function from stack instead of from provided direct address. * Makes sense for trampolines with fexit or fmod_ret programs. */ #define BPF_TRAMP_F_ORIG_STACK BIT(5) /* This trampoline is on a function with another ftrace_ops with IPMODIFY, * e.g., a live patch. This flag is set and cleared by ftrace call backs, */ #define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) /* Indicate that current trampoline is in a tail call context. Then, it has to * cache and restore tail_call_cnt to avoid infinite tail call loop. */ #define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) /* * Indicate the trampoline should be suitable to receive indirect calls; * without this indirectly calling the generated code can result in #UD/#CP, * depending on the CFI options. * * Used by bpf_struct_ops. * * Incompatible with FENTRY usage, overloads @func_addr argument. */ #define BPF_TRAMP_F_INDIRECT BIT(8) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ enum { #if defined(__s390x__) BPF_MAX_TRAMP_LINKS = 27, #else BPF_MAX_TRAMP_LINKS = 38, #endif }; struct bpf_tramp_links { struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; int nr_links; }; struct bpf_tramp_run_ctx; /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS * fentry = a set of programs to run before returning from trampoline * * 2. replace nop at the function entry (kprobe + kretprobe equivalent) * flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME * orig_call = fentry_ip + MCOUNT_INSN_SIZE * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function * * 3. replace direct call instruction anywhere in the function body * or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid) * With flags = 0 * fentry = a set of programs to run before returning from trampoline * With flags = BPF_TRAMP_F_CALL_ORIG * orig_call = original callback addr or direct function addr * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ struct bpf_tramp_image; int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); void arch_protect_bpf_trampoline(void *image, unsigned int size); void arch_unprotect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); typedef u64 (*bpf_trampoline_enter_t)(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog); bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog); struct bpf_ksym { unsigned long start; unsigned long end; char name[KSYM_NAME_LEN]; struct list_head lnode; struct latch_tree_node tnode; bool prog; }; enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ }; struct bpf_tramp_image { void *image; int size; struct bpf_ksym ksym; struct percpu_ref pcref; void *ip_after_call; void *ip_epilogue; union { struct rcu_head rcu; struct work_struct work; }; }; struct bpf_trampoline { /* hlist for trampoline_table */ struct hlist_node hlist; struct ftrace_ops *fops; /* serializes access to fields of this trampoline */ struct mutex mutex; refcount_t refcnt; u32 flags; u64 key; struct { struct btf_func_model model; void *addr; bool ftrace_managed; } func; /* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF * program by replacing one of its functions. func.addr is the address * of the function it replaced. */ struct bpf_prog *extension_prog; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; /* Number of attached programs. A counter per kind. */ int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ struct bpf_tramp_image *cur_image; struct module *mod; }; struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; struct module *tgt_mod; const char *tgt_name; const struct btf_type *tgt_type; }; #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ struct bpf_dispatcher_prog { struct bpf_prog *prog; refcount_t users; }; struct bpf_dispatcher { /* dispatcher mutex */ struct mutex mutex; void *func; struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX]; int num_progs; void *image; void *rw_image; u32 image_off; struct bpf_ksym ksym; #ifdef CONFIG_HAVE_STATIC_CALL struct static_call_key *sc_key; void *sc_tramp; #endif }; #ifndef __bpfcall #define __bpfcall __nocfi #endif static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, bpf_func_t bpf_func) { return bpf_func(ctx, insnsi); } /* the implementation of the opaque uapi struct bpf_dynptr */ struct bpf_dynptr_kern { void *data; /* Size represents the number of usable bytes of dynptr data. * If for example the offset is at 4 for a local dynptr whose data is * of type u64, the number of usable bytes is 4. * * The upper 8 bits are reserved. It is as follows: * Bits 0 - 23 = size * Bits 24 - 30 = dynptr type * Bit 31 = whether dynptr is read-only */ u32 size; u32 offset; } __aligned(8); enum bpf_dynptr_type { BPF_DYNPTR_TYPE_INVALID, /* Points to memory that is local to the bpf program */ BPF_DYNPTR_TYPE_LOCAL, /* Underlying data is a ringbuf record */ BPF_DYNPTR_TYPE_RINGBUF, /* Underlying data is a sk_buff */ BPF_DYNPTR_TYPE_SKB, /* Underlying data is a xdp_buff */ BPF_DYNPTR_TYPE_XDP, }; int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); /* * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn * indirection with a direct call to the bpf program. If the architecture does * not have STATIC_CALL, avoid a double-indirection. */ #ifdef CONFIG_HAVE_STATIC_CALL #define __BPF_DISPATCHER_SC_INIT(_name) \ .sc_key = &STATIC_CALL_KEY(_name), \ .sc_tramp = STATIC_CALL_TRAMP_ADDR(_name), #define __BPF_DISPATCHER_SC(name) \ DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func) #define __BPF_DISPATCHER_CALL(name) \ static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func) #define __BPF_DISPATCHER_UPDATE(_d, _new) \ __static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new)) #else #define __BPF_DISPATCHER_SC_INIT(name) #define __BPF_DISPATCHER_SC(name) #define __BPF_DISPATCHER_CALL(name) bpf_func(ctx, insnsi) #define __BPF_DISPATCHER_UPDATE(_d, _new) #endif #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ .progs = {}, \ .num_progs = 0, \ .image = NULL, \ .image_off = 0, \ .ksym = { \ .name = #_name, \ .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ }, \ __BPF_DISPATCHER_SC_INIT(_name##_call) \ } #define DEFINE_BPF_DISPATCHER(name) \ __BPF_DISPATCHER_SC(name); \ noinline __bpfcall unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ { \ return __BPF_DISPATCHER_CALL(name); \ } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ BPF_DISPATCHER_INIT(bpf_dispatcher_##name); #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func); \ extern struct bpf_dispatcher bpf_dispatcher_##name; #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); int bpf_jit_charge_modmem(u32 size); void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; } static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) #define DECLARE_BPF_DISPATCHER(name) #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func #define BPF_DISPATCHER_PTR(name) NULL static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to) {} static inline bool is_bpf_image_address(unsigned long address) { return false; } static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) { return false; } #endif struct bpf_func_info_aux { u16 linkage; bool unreliable; bool called : 1; bool verified : 1; }; enum bpf_jit_poke_reason { BPF_POKE_REASON_TAIL_CALL, }; /* Descriptor of pokes pointing /into/ the JITed image. */ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; void *aux; union { struct { struct bpf_map *map; u32 key; } tail_call; }; bool tailcall_target_stable; u8 adj_off; u16 reason; u32 insn_idx; }; /* reg_type info for ctx arguments */ struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; u32 btf_id; }; struct btf_mod_pair { struct btf *btf; struct module *module; }; struct bpf_kfunc_desc_tab; struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; u32 used_btf_cnt; u32 max_ctx_offset; u32 max_pkt_offset; u32 max_tp_access; u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; struct btf *attach_btf; const struct bpf_ctx_arg_aux *ctx_arg_info; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; struct bpf_trampoline *dst_trampoline; enum bpf_prog_type saved_dst_prog_type; enum bpf_attach_type saved_dst_attach_type; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool dev_bound; /* Program is bound to the netdev. */ bool offload_requested; /* Program is bound and offloaded to the netdev. */ bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool attach_tracing_prog; /* true if tracing another tracing program */ bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; bool xdp_has_frags; bool exception_cb; bool exception_boundary; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; struct bpf_kfunc_desc_tab *kfunc_tab; struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; #ifdef CONFIG_FINEIBT struct bpf_ksym ksym_prefix; #endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct btf_mod_pair *used_btfs; struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ u32 verified_insns; int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64); #ifdef CONFIG_SECURITY void *security; #endif struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; struct bpf_func_info_aux *func_info_aux; /* bpf_line_info loaded from userspace. linfo->insn_off * has the xlated insn offset. * Both the main and sub prog share the same linfo. * The subprog can access its first linfo by * using the linfo_idx. */ struct bpf_line_info *linfo; /* jited_linfo is the jited addr of the linfo. It has a * one to one mapping to linfo: * jited_linfo[i] is the jited addr for the linfo[i]->insn_off. * Both the main and sub prog share the same jited_linfo. * The subprog can access its first jited_linfo by * using the linfo_idx. */ void **jited_linfo; u32 func_info_cnt; u32 nr_linfo; /* subprog can use linfo_idx to access its first linfo and * jited_linfo. * main prog always has linfo_idx == 0 */ u32 linfo_idx; struct module *mod; u32 num_exentries; struct exception_table_entry *extable; union { struct work_struct work; struct rcu_head rcu; }; }; struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ blinding_requested:1, /* needs constant blinding */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_stats __percpu *stats; int __percpu *active; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ union { DECLARE_FLEX_ARRAY(struct sock_filter, insns); DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); }; }; struct bpf_array_aux { /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; struct mutex poke_mutex; struct work_struct work; }; struct bpf_link { atomic64_t refcnt; u32 id; enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; struct work_struct work; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); void (*dealloc)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); int (*fill_link_info)(const struct bpf_link *link, struct bpf_link_info *info); int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, struct bpf_map *old_map); }; struct bpf_tramp_link { struct bpf_link link; struct hlist_node tramp_hlist; u64 cookie; }; struct bpf_shim_tramp_link { struct bpf_tramp_link link; struct bpf_trampoline *trampoline; }; struct bpf_tracing_link { struct bpf_tramp_link link; enum bpf_attach_type attach_type; struct bpf_trampoline *trampoline; struct bpf_prog *tgt_prog; }; struct bpf_link_primer { struct bpf_link *link; struct file *file; int fd; u32 id; }; struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 /** * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to * define a BPF_MAP_TYPE_STRUCT_OPS map type composed * of BPF_PROG_TYPE_STRUCT_OPS progs. * @verifier_ops: A structure of callbacks that are invoked by the verifier * when determining whether the struct_ops progs in the * struct_ops map are valid. * @init: A callback that is invoked a single time, and before any other * callback, to initialize the structure. A nonzero return value means * the subsystem could not be initialized. * @check_member: When defined, a callback invoked by the verifier to allow * the subsystem to determine if an entry in the struct_ops map * is valid. A nonzero return value means that the map is * invalid and should be rejected by the verifier. * @init_member: A callback that is invoked for each member of the struct_ops * map to allow the subsystem to initialize the member. A nonzero * value means the member could not be initialized. This callback * is exclusive with the @type, @type_id, @value_type, and * @value_id fields. * @reg: A callback that is invoked when the struct_ops map has been * initialized and is being attached to. Zero means the struct_ops map * has been successfully registered and is live. A nonzero return value * means the struct_ops map could not be registered. * @unreg: A callback that is invoked when the struct_ops map should be * unregistered. * @update: A callback that is invoked when the live struct_ops map is being * updated to contain new values. This callback is only invoked when * the struct_ops map is loaded with BPF_F_LINK. If not defined, the * it is assumed that the struct_ops map cannot be updated. * @validate: A callback that is invoked after all of the members have been * initialized. This callback should perform static checks on the * map, meaning that it should either fail or succeed * deterministically. A struct_ops map that has been validated may * not necessarily succeed in being registered if the call to @reg * fails. For example, a valid struct_ops map may be loaded, but * then fail to be registered due to there being another active * struct_ops map on the system in the subsystem already. For this * reason, if this callback is not defined, the check is skipped as * the struct_ops map will have final verification performed in * @reg. * @type: BTF type. * @value_type: Value type. * @name: The name of the struct bpf_struct_ops object. * @func_models: Func models * @type_id: BTF type id. * @value_id: BTF value id. */ struct bpf_struct_ops { const struct bpf_verifier_ops *verifier_ops; int (*init)(struct btf *btf); int (*check_member)(const struct btf_type *t, const struct btf_member *member, const struct bpf_prog *prog); int (*init_member)(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata); int (*reg)(void *kdata); void (*unreg)(void *kdata); int (*update)(void *kdata, void *old_kdata); int (*validate)(void *kdata); const struct btf_type *type; const struct btf_type *value_type; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; u32 type_id; u32 value_id; void *cfi_stubs; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id); void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log); bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, void *stub_func, void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) return bpf_struct_ops_get(data); else return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) bpf_struct_ops_put(data); else module_put(owner); } int bpf_struct_ops_link_create(union bpf_attr *attr); #ifdef CONFIG_NET /* Define it here to avoid the use of forward declaration */ struct bpf_dummy_ops_state { int val; }; struct bpf_dummy_ops { int (*test_1)(struct bpf_dummy_ops_state *cb); int (*test_2)(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, char a3, unsigned long a4); int (*test_sleepable)(struct bpf_dummy_ops_state *cb); }; int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif #else static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { return NULL; } static inline void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) { } static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { module_put(owner); } static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EINVAL; } static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } #endif #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype); void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog); #else static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype) { return -EOPNOTSUPP; } static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) { } #endif struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; struct bpf_array_aux *aux; union { DECLARE_FLEX_ARRAY(char, value) __aligned(8); DECLARE_FLEX_ARRAY(void *, ptrs) __aligned(8); DECLARE_FLEX_ARRAY(void __percpu *, pptrs) __aligned(8); }; }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 /* Maximum number of loops for bpf_loop and bpf_iter_num. * It's enum to expose it (and thus make it discoverable) through BTF. */ enum { BPF_MAX_LOOPS = 8 * 1024 * 1024, }; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ BPF_F_WRONLY | \ BPF_F_WRONLY_PROG) #define BPF_MAP_CAN_READ BIT(0) #define BPF_MAP_CAN_WRITE BIT(1) /* Maximum number of user-producer ring buffer samples that can be drained in * a call to bpf_user_ringbuf_drain(). */ #define BPF_MAX_USER_RINGBUF_SAMPLES (128 * 1024) static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) { u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); /* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is * not possible. */ if (access_flags & BPF_F_RDONLY_PROG) return BPF_MAP_CAN_READ; else if (access_flags & BPF_F_WRONLY_PROG) return BPF_MAP_CAN_WRITE; else return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE; } static inline bool bpf_map_flags_access_ok(u32 access_flags) { return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) != (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); } struct bpf_event_entry { struct perf_event *event; struct file *perf_file; struct file *map_file; struct rcu_head rcu; }; static inline bool map_type_contains_progs(struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || map->map_type == BPF_MAP_TYPE_DEVMAP || map->map_type == BPF_MAP_TYPE_CPUMAP; } bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); /* an array of programs to be executed under rcu_lock. * * Typical usage: * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. * The user has to keep refcnt on the program and make sure the program * is removed from the array before bpf_prog_put(). * The 'struct bpf_prog_array *' should only be replaced with xchg() * since other cpus are walking the array of pointers in parallel. */ struct bpf_prog_array_item { struct bpf_prog *prog; union { struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; u64 bpf_cookie; }; }; struct bpf_prog_array { struct rcu_head rcu; struct bpf_prog_array_item items[]; }; struct bpf_empty_prog_array { struct bpf_prog_array hdr; struct bpf_prog *null_prog; }; /* to avoid allocating empty bpf_prog_array for cgroups that * don't have bpf program attached use one global 'bpf_empty_prog_array' * It will not be modified the caller of bpf_prog_array_alloc() * (since caller requested prog_cnt == 0) * that pointer should be 'freed' by bpf_prog_array_free() */ extern struct bpf_empty_prog_array bpf_empty_prog_array; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); /* Use when traversal over the bpf_prog_array uses tasks_trace rcu */ void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index); int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog); int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array); struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; int retval; }; struct bpf_trace_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; bool is_uprobe; }; struct bpf_tramp_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; struct bpf_run_ctx *saved_run_ctx; }; static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; #ifdef CONFIG_BPF_SYSCALL old_ctx = current->bpf_ctx; current->bpf_ctx = new_ctx; #endif return old_ctx; } static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) { #ifdef CONFIG_BPF_SYSCALL current->bpf_ctx = old_ctx; #endif } /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); static __always_inline u32 bpf_prog_run_array(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held"); if (unlikely(!array)) return ret; run_ctx.is_uprobe = false; migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); migrate_enable(); return ret; } /* Notes on RCU design for bpf_prog_arrays containing sleepable programs: * * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array * overall. As a result, we must use the bpf_prog_array_free_sleepable * in order to use the tasks_trace rcu grace period. * * When a non-sleepable program is inside the array, we take the rcu read * section and disable preemption for that program alone, so it can access * rcu-protected dynamically sized maps. */ static __always_inline u32 bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); rcu_read_lock_trace(); migrate_disable(); run_ctx.is_uprobe = true; array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); if (unlikely(!array)) goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { if (!prog->aux->sleepable) rcu_read_lock(); run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; if (!prog->aux->sleepable) rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); out: migrate_enable(); rcu_read_unlock_trace(); return ret; } #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; /* * Block execution of BPF programs attached to instrumentation (perf, * kprobes, tracepoints) to prevent deadlocks on map operations as any of * these events can happen inside a region which holds a map bucket lock * and can deadlock on it. */ static inline void bpf_disable_instrumentation(void) { migrate_disable(); this_cpu_inc(bpf_prog_active); } static inline void bpf_enable_instrumentation(void) { this_cpu_dec(bpf_prog_active); migrate_enable(); } extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog); void bpf_map_free_id(struct bpf_map *map); struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, u32 field_mask); void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); #ifdef CONFIG_MEMCG_KMEM void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags); void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else static inline void * bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags, node); } static inline void * bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { return kzalloc(size, flags); } static inline void * bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) { return kvcalloc(n, size, flags); } static inline void __percpu * bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { return __alloc_percpu_gfp(size, align, flags); } #endif static inline int bpf_map_init_elem_count(struct bpf_map *map) { size_t size = sizeof(*map->elem_count), align = size; gfp_t flags = GFP_USER | __GFP_NOWARN; map->elem_count = bpf_map_alloc_percpu(map, size, align, flags); if (!map->elem_count) return -ENOMEM; return 0; } static inline void bpf_map_free_elem_count(struct bpf_map *map) { free_percpu(map->elem_count); } static inline void bpf_map_inc_elem_count(struct bpf_map *map) { this_cpu_inc(*map->elem_count); } static inline void bpf_map_dec_elem_count(struct bpf_map *map) { this_cpu_dec(*map->elem_count); } extern int sysctl_unprivileged_bpf_disabled; static inline bool bpf_allow_ptr_leaks(void) { return perfmon_capable(); } static inline bool bpf_allow_uninit_stack(void) { return perfmon_capable(); } static inline bool bpf_bypass_spec_v1(void) { return cpu_mitigations_off() || perfmon_capable(); } static inline bool bpf_bypass_spec_v4(void) { return cpu_mitigations_off() || perfmon_capable(); } int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } /* * The task type of iterators. * * For BPF task iterators, they can be parameterized with various * parameters to visit only some of tasks. * * BPF_TASK_ITER_ALL (default) * Iterate over resources of every task. * * BPF_TASK_ITER_TID * Iterate over resources of a task/tid. * * BPF_TASK_ITER_TGID * Iterate over resources of every task of a process / task group. */ enum bpf_iter_task_type { BPF_TASK_ITER_ALL = 0, BPF_TASK_ITER_TID, BPF_TASK_ITER_TGID, }; struct bpf_iter_aux_info { /* for map_elem iter */ struct bpf_map *map; /* for cgroup iter */ struct { struct cgroup *start; /* starting cgroup */ enum bpf_cgroup_iter_order order; } cgroup; struct { enum bpf_iter_task_type type; u32 pid; } task; }; typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, struct seq_file *seq); typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); typedef const struct bpf_func_proto * (*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id, const struct bpf_prog *prog); enum bpf_iter_feature { BPF_ITER_RESCHED = BIT(0), }; #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; bpf_iter_attach_target_t attach_target; bpf_iter_detach_target_t detach_target; bpf_iter_show_fdinfo_t show_fdinfo; bpf_iter_fill_link_info_t fill_link_info; bpf_iter_get_func_proto_t get_func_proto; u32 ctx_arg_info_size; u32 feature; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; struct bpf_iter_meta { __bpf_md_ptr(struct seq_file *, seq); u64 session_id; u64 seq_num; }; struct bpf_iter__bpf_map_elem { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(void *, key); __bpf_md_ptr(void *, value); }; int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq); int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); int map_set_for_each_callback_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); #endif struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(void); int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); void __cpu_map_flush(void); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { return (attr->map_flags & BPF_F_NUMA_NODE) ? attr->numa_node : NUMA_NO_NODE; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); int array_map_alloc_check(union bpf_attr *attr); int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_nf(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); static inline bool bpf_tracing_ctx_access(int off, int size, enum bpf_access_type type) { if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; return true; } static inline bool bpf_tracing_btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_tracing_ctx_access(off, size, type)) return false; return btf_ctx_access(off, size, type, prog, info); } int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, bool strict); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func_proto, const char *func_name, struct btf_func_model *m); struct bpf_reg_state; int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr); struct bpf_core_ctx { struct bpf_verifier_log *log; const struct btf *btf; }; bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, const char *field_name, u32 btf_id, const char *suffix); bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, const struct btf *arg_btf, u32 arg_id); int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, int relo_idx, void *insn); static inline bool unprivileged_ebpf_enabled(void) { return !sysctl_unprivileged_bpf_disabled; } /* Not all bpf prog type has the bpf_ctx. * For the bpf prog type that has initialized the bpf_ctx, * this function can be used to decide if a kernel function * is called by a bpf program. */ static inline bool has_current_bpf_ctx(void) { return !!current->bpf_ctx; } void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog); void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); bool dev_check_flush(void); bool cpu_map_check_flush(void); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_add(struct bpf_prog *prog, int i) { } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) { } static inline void bpf_prog_put(struct bpf_prog *prog) { } static inline void bpf_prog_inc(struct bpf_prog *prog) { } static inline struct bpf_prog *__must_check bpf_prog_inc_not_zero(struct bpf_prog *prog) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { } static inline int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline int bpf_link_settle(struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline void bpf_link_cleanup(struct bpf_link_primer *primer) { } static inline void bpf_link_inc(struct bpf_link *link) { } static inline void bpf_link_put(struct bpf_link *link) { } static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } static inline void __dev_flush(void) { } struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; } struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { return 0; } static inline int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { return 0; } static inline void __cpu_map_flush(void) { } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { return ERR_PTR(-EOPNOTSUPP); } static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline void bpf_map_put(struct bpf_map *map) { } static inline struct bpf_prog *bpf_prog_by_id(u32 id) { return ERR_PTR(-ENOTSUPP); } static inline int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name) { return -EACCES; } static inline const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { return NULL; } static inline void bpf_task_storage_free(struct task_struct *task) { } static inline bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) { return false; } static inline const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn) { return NULL; } static inline int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr) { return -ENOTSUPP; } static inline bool unprivileged_ebpf_enabled(void) { return false; } static inline bool has_current_bpf_ctx(void) { return false; } static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) { } static inline void bpf_cgrp_storage_free(struct cgroup *cgroup) { } static inline void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size) { } static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) { } static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) { } #endif /* CONFIG_BPF_SYSCALL */ static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { int ret = -EFAULT; if (IS_ENABLED(CONFIG_BPF_EVENTS)) ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } void __bpf_free_used_btfs(struct bpf_prog_aux *aux, struct btf_mod_pair *used_btfs, u32 len); static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { return bpf_prog_get_type_dev(ufd, type, false); } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len); bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_dev_bound_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map); int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_map_offload_update_elem(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key); bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); struct bpf_offload_dev * bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); void unpriv_ebpf_notify(int new_state); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, struct bpf_prog_aux *prog_aux); void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id); int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr); int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog); void bpf_dev_bound_netdev_unregister(struct net_device *dev); static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return aux->dev_bound; } static inline bool bpf_prog_is_offloaded(const struct bpf_prog_aux *aux) { return aux->offload_requested; } bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs); static inline bool bpf_map_is_offloaded(struct bpf_map *map) { return unlikely(map->ops == &bpf_map_offload_ops); } struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, struct bpf_prog_aux *prog_aux) { return -EOPNOTSUPP; } static inline void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id) { return NULL; } static inline int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) { return -EOPNOTSUPP; } static inline int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog) { return -EOPNOTSUPP; } static inline void bpf_dev_bound_netdev_unregister(struct net_device *dev) { } static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return false; } static inline bool bpf_prog_is_offloaded(struct bpf_prog_aux *aux) { return false; } static inline bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs) { return false; } static inline bool bpf_map_is_offloaded(struct bpf_map *map) { return false; } static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_map_offload_map_free(struct bpf_map *map) { } static inline u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map) { return 0; } static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } #ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { return -EOPNOTSUPP; } static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags) { return -EOPNOTSUPP; } static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ static __always_inline void bpf_prog_inc_misses_counters(const struct bpf_prog_array *array) { const struct bpf_prog_array_item *item; struct bpf_prog *prog; if (unlikely(!array)) return; item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { bpf_prog_inc_misses_counter(prog); item++; } } #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags); #else static inline void bpf_sk_reuseport_detach(struct sock *sk) { } #ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EOPNOTSUPP; } static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */ /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_map_push_elem_proto; extern const struct bpf_func_proto bpf_map_pop_elem_proto; extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; extern const struct bpf_func_proto bpf_get_stackid_proto_pe; extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_spin_lock_proto; extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_event_output_data_proto; extern const struct bpf_func_proto bpf_ringbuf_output_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_recur_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_recur_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; extern const struct bpf_func_proto bpf_set_retval_proto; extern const struct bpf_func_proto bpf_get_retval_proto; extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto; extern const struct bpf_func_proto bpf_cgrp_storage_get_proto; extern const struct bpf_func_proto bpf_cgrp_storage_delete_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, struct bpf_dynptr_kern *ptr); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, struct bpf_dynptr_kern *ptr) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_INET struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; bool bind_inany; }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); #else static inline bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } #endif /* CONFIG_INET */ enum bpf_text_poke_type { BPF_MOD_CALL, BPF_MOD_JUMP, }; int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, struct bpf_prog *new, struct bpf_prog *old); void *bpf_arch_text_copy(void *dst, void *src, size_t len); int bpf_arch_text_invalidate(void *dst, size_t len); struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 #define MAX_BPRINTF_BUF 1024 struct bpf_bprintf_data { u32 *bin_args; char *buf; bool get_bin_args; bool get_buf; }; int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data); void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); void bpf_cgroup_atype_put(int cgroup_atype); #else static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {} static inline void bpf_cgroup_atype_put(int cgroup_atype) {} #endif /* CONFIG_BPF_LSM */ struct key; #ifdef CONFIG_KEYS struct bpf_key { struct key *key; bool has_ref; }; #endif /* CONFIG_KEYS */ static inline bool type_is_alloc(u32 type) { return type & MEM_ALLOC; } static inline gfp_t bpf_memcg_flags(gfp_t flags) { if (memcg_bpf_enabled()) return flags | __GFP_ACCOUNT; return flags; } static inline bool bpf_is_subprog(const struct bpf_prog *prog) { return prog->aux->func_idx != 0; } #endif /* _LINUX_BPF_H */ |
| 3 12 12 12 3 2 2 2 2 2 1 1 1 1 1 6 8 7 14 14 14 14 14 14 14 14 14 14 26 1 19 2 7 6 1 1 5 4 9 8 2134 2132 536 6 17 2 1 14 14 927 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* XDP sockets * * AF_XDP sockets allows a channel between XDP programs and userspace * applications. * Copyright(c) 2018 Intel Corporation. * * Author(s): Björn Töpel <bjorn.topel@intel.com> * Magnus Karlsson <magnus.karlsson@intel.com> */ #define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__ #include <linux/if_xdp.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/uaccess.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/rculist.h> #include <linux/vmalloc.h> #include <net/xdp_sock_drv.h> #include <net/busy_poll.h> #include <net/netdev_rx_queue.h> #include <net/xdp.h> #include "xsk_queue.h" #include "xdp_umem.h" #include "xsk.h" #define TX_BATCH_SIZE 32 #define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE) static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { if (pool->cached_need_wakeup & XDP_WAKEUP_RX) return; pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP; pool->cached_need_wakeup |= XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_set_rx_need_wakeup); void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool) { struct xdp_sock *xs; if (pool->cached_need_wakeup & XDP_WAKEUP_TX) return; rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); pool->cached_need_wakeup |= XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_set_tx_need_wakeup); void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool) { if (!(pool->cached_need_wakeup & XDP_WAKEUP_RX)) return; pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP; pool->cached_need_wakeup &= ~XDP_WAKEUP_RX; } EXPORT_SYMBOL(xsk_clear_rx_need_wakeup); void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool) { struct xdp_sock *xs; if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX)) return; rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP; } rcu_read_unlock(); pool->cached_need_wakeup &= ~XDP_WAKEUP_TX; } EXPORT_SYMBOL(xsk_clear_tx_need_wakeup); bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool) { return pool->uses_need_wakeup; } EXPORT_SYMBOL(xsk_uses_need_wakeup); struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id) { if (queue_id < dev->real_num_rx_queues) return dev->_rx[queue_id].pool; if (queue_id < dev->real_num_tx_queues) return dev->_tx[queue_id].pool; return NULL; } EXPORT_SYMBOL(xsk_get_pool_from_qid); void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id) { if (queue_id < dev->num_rx_queues) dev->_rx[queue_id].pool = NULL; if (queue_id < dev->num_tx_queues) dev->_tx[queue_id].pool = NULL; } /* The buffer pool is stored both in the _rx struct and the _tx struct as we do * not know if the device has more tx queues than rx, or the opposite. * This might also change during run time. */ int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, u16 queue_id) { if (queue_id >= max_t(unsigned int, dev->real_num_rx_queues, dev->real_num_tx_queues)) return -EINVAL; if (queue_id < dev->real_num_rx_queues) dev->_rx[queue_id].pool = pool; if (queue_id < dev->real_num_tx_queues) dev->_tx[queue_id].pool = pool; return 0; } static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len, u32 flags) { u64 addr; int err; addr = xp_get_handle(xskb); err = xskq_prod_reserve_desc(xs->rx, addr, len, flags); if (err) { xs->rx_queue_full++; return err; } xp_release(xskb); return 0; } static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); u32 frags = xdp_buff_has_frags(xdp); struct xdp_buff_xsk *pos, *tmp; struct list_head *xskb_list; u32 contd = 0; int err; if (frags) contd = XDP_PKT_CONTD; err = __xsk_rcv_zc(xs, xskb, len, contd); if (err) goto err; if (likely(!frags)) return 0; xskb_list = &xskb->pool->xskb_list; list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) { if (list_is_singular(xskb_list)) contd = 0; len = pos->xdp.data_end - pos->xdp.data; err = __xsk_rcv_zc(xs, pos, len, contd); if (err) goto err; list_del(&pos->xskb_list_node); } return 0; err: xsk_buff_free(xdp); return err; } static void *xsk_copy_xdp_start(struct xdp_buff *from) { if (unlikely(xdp_data_meta_unsupported(from))) return from->data; else return from->data_meta; } static u32 xsk_copy_xdp(void *to, void **from, u32 to_len, u32 *from_len, skb_frag_t **frag, u32 rem) { u32 copied = 0; while (1) { u32 copy_len = min_t(u32, *from_len, to_len); memcpy(to, *from, copy_len); copied += copy_len; if (rem == copied) return copied; if (*from_len == copy_len) { *from = skb_frag_address(*frag); *from_len = skb_frag_size((*frag)++); } else { *from += copy_len; *from_len -= copy_len; } if (to_len == copy_len) return copied; to_len -= copy_len; to += copy_len; } } static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { u32 frame_size = xsk_pool_get_rx_frame_size(xs->pool); void *copy_from = xsk_copy_xdp_start(xdp), *copy_to; u32 from_len, meta_len, rem, num_desc; struct xdp_buff_xsk *xskb; struct xdp_buff *xsk_xdp; skb_frag_t *frag; from_len = xdp->data_end - copy_from; meta_len = xdp->data - copy_from; rem = len + meta_len; if (len <= frame_size && !xdp_buff_has_frags(xdp)) { int err; xsk_xdp = xsk_buff_alloc(xs->pool); if (!xsk_xdp) { xs->rx_dropped++; return -ENOMEM; } memcpy(xsk_xdp->data - meta_len, copy_from, rem); xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp); err = __xsk_rcv_zc(xs, xskb, len, 0); if (err) { xsk_buff_free(xsk_xdp); return err; } return 0; } num_desc = (len - 1) / frame_size + 1; if (!xsk_buff_can_alloc(xs->pool, num_desc)) { xs->rx_dropped++; return -ENOMEM; } if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) { xs->rx_queue_full++; return -ENOBUFS; } if (xdp_buff_has_frags(xdp)) { struct skb_shared_info *sinfo; sinfo = xdp_get_shared_info_from_buff(xdp); frag = &sinfo->frags[0]; } do { u32 to_len = frame_size + meta_len; u32 copied; xsk_xdp = xsk_buff_alloc(xs->pool); copy_to = xsk_xdp->data - meta_len; copied = xsk_copy_xdp(copy_to, ©_from, to_len, &from_len, &frag, rem); rem -= copied; xskb = container_of(xsk_xdp, struct xdp_buff_xsk, xdp); __xsk_rcv_zc(xs, xskb, copied - meta_len, rem ? XDP_PKT_CONTD : 0); meta_len = 0; } while (rem); return 0; } static bool xsk_tx_writeable(struct xdp_sock *xs) { if (xskq_cons_present_entries(xs->tx) > xs->tx->nentries / 2) return false; return true; } static bool xsk_is_bound(struct xdp_sock *xs) { if (READ_ONCE(xs->state) == XSK_BOUND) { /* Matches smp_wmb() in bind(). */ smp_rmb(); return true; } return false; } static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { if (!xsk_is_bound(xs)) return -ENXIO; if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) return -EINVAL; if (len > xsk_pool_get_rx_frame_size(xs->pool) && !xs->sg) { xs->rx_dropped++; return -ENOSPC; } sk_mark_napi_id_once_xdp(&xs->sk, xdp); return 0; } static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); __xskq_cons_release(xs->pool->fq); sock_def_readable(&xs->sk); } int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { u32 len = xdp_get_buff_len(xdp); int err; spin_lock_bh(&xs->rx_lock); err = xsk_rcv_check(xs, xdp, len); if (!err) { err = __xsk_rcv(xs, xdp, len); xsk_flush(xs); } spin_unlock_bh(&xs->rx_lock); return err; } static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { u32 len = xdp_get_buff_len(xdp); int err; err = xsk_rcv_check(xs, xdp, len); if (err) return err; if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) { len = xdp->data_end - xdp->data; return xsk_rcv_zc(xs, xdp, len); } err = __xsk_rcv(xs, xdp, len); if (!err) xdp_return_buff(xdp); return err; } int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) { struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); int err; err = xsk_rcv(xs, xdp); if (err) return err; if (!xs->flush_node.prev) list_add(&xs->flush_node, flush_list); return 0; } void __xsk_map_flush(void) { struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); struct xdp_sock *xs, *tmp; list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { xsk_flush(xs); __list_del_clearprev(&xs->flush_node); } } #ifdef CONFIG_DEBUG_NET bool xsk_map_check_flush(void) { if (list_empty(this_cpu_ptr(&xskmap_flush_list))) return false; __xsk_map_flush(); return true; } #endif void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { xskq_prod_submit_n(pool->cq, nb_entries); } EXPORT_SYMBOL(xsk_tx_completed); void xsk_tx_release(struct xsk_buff_pool *pool) { struct xdp_sock *xs; rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { __xskq_cons_release(xs->tx); if (xsk_tx_writeable(xs)) xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); } EXPORT_SYMBOL(xsk_tx_release); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { bool budget_exhausted = false; struct xdp_sock *xs; rcu_read_lock(); again: list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { if (xs->tx_budget_spent >= MAX_PER_SOCKET_BUDGET) { budget_exhausted = true; continue; } if (!xskq_cons_peek_desc(xs->tx, desc, pool)) { if (xskq_has_descs(xs->tx)) xskq_cons_release(xs->tx); continue; } xs->tx_budget_spent++; /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ if (xskq_prod_reserve_addr(pool->cq, desc->addr)) goto out; xskq_cons_release(xs->tx); rcu_read_unlock(); return true; } if (budget_exhausted) { list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) xs->tx_budget_spent = 0; budget_exhausted = false; goto again; } out: rcu_read_unlock(); return false; } EXPORT_SYMBOL(xsk_tx_peek_desc); static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, u32 max_entries) { struct xdp_desc *descs = pool->tx_descs; u32 nb_pkts = 0; while (nb_pkts < max_entries && xsk_tx_peek_desc(pool, &descs[nb_pkts])) nb_pkts++; xsk_tx_release(pool); return nb_pkts; } u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 nb_pkts) { struct xdp_sock *xs; rcu_read_lock(); if (!list_is_singular(&pool->xsk_tx_list)) { /* Fallback to the non-batched version */ rcu_read_unlock(); return xsk_tx_peek_release_fallback(pool, nb_pkts); } xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list); if (!xs) { nb_pkts = 0; goto out; } nb_pkts = xskq_cons_nb_entries(xs->tx, nb_pkts); /* This is the backpressure mechanism for the Tx path. Try to * reserve space in the completion queue for all packets, but * if there are fewer slots available, just process that many * packets. This avoids having to implement any buffering in * the Tx path. */ nb_pkts = xskq_prod_nb_free(pool->cq, nb_pkts); if (!nb_pkts) goto out; nb_pkts = xskq_cons_read_desc_batch(xs->tx, pool, nb_pkts); if (!nb_pkts) { xs->tx->queue_empty_descs++; goto out; } __xskq_cons_release(xs->tx); xskq_prod_write_addr_batch(pool->cq, pool->tx_descs, nb_pkts); xs->sk.sk_write_space(&xs->sk); out: rcu_read_unlock(); return nb_pkts; } EXPORT_SYMBOL(xsk_tx_peek_release_desc_batch); static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { struct net_device *dev = xs->dev; return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); } static int xsk_cq_reserve_addr_locked(struct xdp_sock *xs, u64 addr) { unsigned long flags; int ret; spin_lock_irqsave(&xs->pool->cq_lock, flags); ret = xskq_prod_reserve_addr(xs->pool->cq, addr); spin_unlock_irqrestore(&xs->pool->cq_lock, flags); return ret; } static void xsk_cq_submit_locked(struct xdp_sock *xs, u32 n) { unsigned long flags; spin_lock_irqsave(&xs->pool->cq_lock, flags); xskq_prod_submit_n(xs->pool->cq, n); spin_unlock_irqrestore(&xs->pool->cq_lock, flags); } static void xsk_cq_cancel_locked(struct xdp_sock *xs, u32 n) { unsigned long flags; spin_lock_irqsave(&xs->pool->cq_lock, flags); xskq_prod_cancel_n(xs->pool->cq, n); spin_unlock_irqrestore(&xs->pool->cq_lock, flags); } static u32 xsk_get_num_desc(struct sk_buff *skb) { return skb ? (long)skb_shinfo(skb)->destructor_arg : 0; } static void xsk_destruct_skb(struct sk_buff *skb) { struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta; if (compl->tx_timestamp) { /* sw completion timestamp, not a real one */ *compl->tx_timestamp = ktime_get_tai_fast_ns(); } xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb)); sock_wfree(skb); } static void xsk_set_destructor_arg(struct sk_buff *skb) { long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1; skb_shinfo(skb)->destructor_arg = (void *)num; } static void xsk_consume_skb(struct sk_buff *skb) { struct xdp_sock *xs = xdp_sk(skb->sk); skb->destructor = sock_wfree; xsk_cq_cancel_locked(xs, xsk_get_num_desc(skb)); /* Free skb without triggering the perf drop trace */ consume_skb(skb); xs->skb = NULL; } static void xsk_drop_skb(struct sk_buff *skb) { xdp_sk(skb->sk)->tx->invalid_descs += xsk_get_num_desc(skb); xsk_consume_skb(skb); } static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, struct xdp_desc *desc) { struct xsk_buff_pool *pool = xs->pool; u32 hr, len, ts, offset, copy, copied; struct sk_buff *skb = xs->skb; struct page *page; void *buffer; int err, i; u64 addr; if (!skb) { hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom)); skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err); if (unlikely(!skb)) return ERR_PTR(err); skb_reserve(skb, hr); } addr = desc->addr; len = desc->len; ts = pool->unaligned ? len : pool->chunk_size; buffer = xsk_buff_raw_get_data(pool, addr); offset = offset_in_page(buffer); addr = buffer - pool->addrs; for (copied = 0, i = skb_shinfo(skb)->nr_frags; copied < len; i++) { if (unlikely(i >= MAX_SKB_FRAGS)) return ERR_PTR(-EOVERFLOW); page = pool->umem->pgs[addr >> PAGE_SHIFT]; get_page(page); copy = min_t(u32, PAGE_SIZE - offset, len - copied); skb_fill_page_desc(skb, i, page, offset, copy); copied += copy; addr += copy; offset = 0; } skb->len += len; skb->data_len += len; skb->truesize += ts; refcount_add(ts, &xs->sk.sk_wmem_alloc); return skb; } static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, struct xdp_desc *desc) { struct xsk_tx_metadata *meta = NULL; struct net_device *dev = xs->dev; struct sk_buff *skb = xs->skb; bool first_frag = false; int err; if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) { skb = xsk_build_skb_zerocopy(xs, desc); if (IS_ERR(skb)) { err = PTR_ERR(skb); goto free_err; } } else { u32 hr, tr, len; void *buffer; buffer = xsk_buff_raw_get_data(xs->pool, desc->addr); len = desc->len; if (!skb) { hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom)); tr = dev->needed_tailroom; skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err); if (unlikely(!skb)) goto free_err; skb_reserve(skb, hr); skb_put(skb, len); err = skb_store_bits(skb, 0, buffer, len); if (unlikely(err)) { kfree_skb(skb); goto free_err; } first_frag = true; } else { int nr_frags = skb_shinfo(skb)->nr_frags; struct page *page; u8 *vaddr; if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) { err = -EOVERFLOW; goto free_err; } page = alloc_page(xs->sk.sk_allocation); if (unlikely(!page)) { err = -EAGAIN; goto free_err; } vaddr = kmap_local_page(page); memcpy(vaddr, buffer, len); kunmap_local(vaddr); skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); } if (first_frag && desc->options & XDP_TX_METADATA) { if (unlikely(xs->pool->tx_metadata_len == 0)) { err = -EINVAL; goto free_err; } meta = buffer - xs->pool->tx_metadata_len; if (unlikely(!xsk_buff_valid_tx_metadata(meta))) { err = -EINVAL; goto free_err; } if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM) { if (unlikely(meta->request.csum_start + meta->request.csum_offset + sizeof(__sum16) > len)) { err = -EINVAL; goto free_err; } skb->csum_start = hr + meta->request.csum_start; skb->csum_offset = meta->request.csum_offset; skb->ip_summed = CHECKSUM_PARTIAL; if (unlikely(xs->pool->tx_sw_csum)) { err = skb_checksum_help(skb); if (err) goto free_err; } } } } skb->dev = dev; skb->priority = READ_ONCE(xs->sk.sk_priority); skb->mark = READ_ONCE(xs->sk.sk_mark); skb->destructor = xsk_destruct_skb; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); xsk_set_destructor_arg(skb); return skb; free_err: if (err == -EOVERFLOW) { /* Drop the packet */ xsk_set_destructor_arg(xs->skb); xsk_drop_skb(xs->skb); xskq_cons_release(xs->tx); } else { /* Let application retry */ xsk_cq_cancel_locked(xs, 1); } return ERR_PTR(err); } static int __xsk_generic_xmit(struct sock *sk) { struct xdp_sock *xs = xdp_sk(sk); u32 max_batch = TX_BATCH_SIZE; bool sent_frame = false; struct xdp_desc desc; struct sk_buff *skb; int err = 0; mutex_lock(&xs->mutex); /* Since we dropped the RCU read lock, the socket state might have changed. */ if (unlikely(!xsk_is_bound(xs))) { err = -ENXIO; goto out; } if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) { if (max_batch-- == 0) { err = -EAGAIN; goto out; } /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ if (xsk_cq_reserve_addr_locked(xs, desc.addr)) goto out; skb = xsk_build_skb(xs, &desc); if (IS_ERR(skb)) { err = PTR_ERR(skb); if (err != -EOVERFLOW) goto out; err = 0; continue; } xskq_cons_release(xs->tx); if (xp_mb_desc(&desc)) { xs->skb = skb; continue; } err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ xskq_cons_cancel_n(xs->tx, xsk_get_num_desc(skb)); xsk_consume_skb(skb); err = -EAGAIN; goto out; } /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP) { /* SKB completed but not sent */ err = -EBUSY; xs->skb = NULL; goto out; } sent_frame = true; xs->skb = NULL; } if (xskq_has_descs(xs->tx)) { if (xs->skb) xsk_drop_skb(xs->skb); xskq_cons_release(xs->tx); } out: if (sent_frame) if (xsk_tx_writeable(xs)) sk->sk_write_space(sk); mutex_unlock(&xs->mutex); return err; } static int xsk_generic_xmit(struct sock *sk) { int ret; /* Drop the RCU lock since the SKB path might sleep. */ rcu_read_unlock(); ret = __xsk_generic_xmit(sk); /* Reaquire RCU lock before going into common code. */ rcu_read_lock(); return ret; } static bool xsk_no_wakeup(struct sock *sk) { #ifdef CONFIG_NET_RX_BUSY_POLL /* Prefer busy-polling, skip the wakeup. */ return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) && READ_ONCE(sk->sk_napi_id) >= MIN_NAPI_ID; #else return false; #endif } static int xsk_check_common(struct xdp_sock *xs) { if (unlikely(!xsk_is_bound(xs))) return -ENXIO; if (unlikely(!(xs->dev->flags & IFF_UP))) return -ENETDOWN; return 0; } static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { bool need_wait = !(m->msg_flags & MSG_DONTWAIT); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; int err; err = xsk_check_common(xs); if (err) return err; if (unlikely(need_wait)) return -EOPNOTSUPP; if (unlikely(!xs->tx)) return -ENOBUFS; if (sk_can_busy_loop(sk)) { if (xs->zc) __sk_mark_napi_id_once(sk, xsk_pool_get_napi_id(xs->pool)); sk_busy_loop(sk, 1); /* only support non-blocking sockets */ } if (xs->zc && xsk_no_wakeup(sk)) return 0; pool = xs->pool; if (pool->cached_need_wakeup & XDP_WAKEUP_TX) { if (xs->zc) return xsk_wakeup(xs, XDP_WAKEUP_TX); return xsk_generic_xmit(sk); } return 0; } static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { int ret; rcu_read_lock(); ret = __xsk_sendmsg(sock, m, total_len); rcu_read_unlock(); return ret; } static int __xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { bool need_wait = !(flags & MSG_DONTWAIT); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); int err; err = xsk_check_common(xs); if (err) return err; if (unlikely(!xs->rx)) return -ENOBUFS; if (unlikely(need_wait)) return -EOPNOTSUPP; if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ if (xsk_no_wakeup(sk)) return 0; if (xs->pool->cached_need_wakeup & XDP_WAKEUP_RX && xs->zc) return xsk_wakeup(xs, XDP_WAKEUP_RX); return 0; } static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) { int ret; rcu_read_lock(); ret = __xsk_recvmsg(sock, m, len, flags); rcu_read_unlock(); return ret; } static __poll_t xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { __poll_t mask = 0; struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; sock_poll_wait(file, sock, wait); rcu_read_lock(); if (xsk_check_common(xs)) goto out; pool = xs->pool; if (pool->cached_need_wakeup) { if (xs->zc) xsk_wakeup(xs, pool->cached_need_wakeup); else if (xs->tx) /* Poll needs to drive Tx also in copy mode */ xsk_generic_xmit(sk); } if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; if (xs->tx && xsk_tx_writeable(xs)) mask |= EPOLLOUT | EPOLLWRNORM; out: rcu_read_unlock(); return mask; } static int xsk_init_queue(u32 entries, struct xsk_queue **queue, bool umem_queue) { struct xsk_queue *q; if (entries == 0 || *queue || !is_power_of_2(entries)) return -EINVAL; q = xskq_create(entries, umem_queue); if (!q) return -ENOMEM; /* Make sure queue is ready before it can be seen by others */ smp_wmb(); WRITE_ONCE(*queue, q); return 0; } static void xsk_unbind_dev(struct xdp_sock *xs) { struct net_device *dev = xs->dev; if (xs->state != XSK_BOUND) return; WRITE_ONCE(xs->state, XSK_UNBOUND); /* Wait for driver to stop using the xdp socket. */ xp_del_xsk(xs->pool, xs); synchronize_net(); dev_put(dev); } static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs, struct xdp_sock __rcu ***map_entry) { struct xsk_map *map = NULL; struct xsk_map_node *node; *map_entry = NULL; spin_lock_bh(&xs->map_list_lock); node = list_first_entry_or_null(&xs->map_list, struct xsk_map_node, node); if (node) { bpf_map_inc(&node->map->map); map = node->map; *map_entry = node->map_entry; } spin_unlock_bh(&xs->map_list_lock); return map; } static void xsk_delete_from_maps(struct xdp_sock *xs) { /* This function removes the current XDP socket from all the * maps it resides in. We need to take extra care here, due to * the two locks involved. Each map has a lock synchronizing * updates to the entries, and each socket has a lock that * synchronizes access to the list of maps (map_list). For * deadlock avoidance the locks need to be taken in the order * "map lock"->"socket map list lock". We start off by * accessing the socket map list, and take a reference to the * map to guarantee existence between the * xsk_get_map_list_entry() and xsk_map_try_sock_delete() * calls. Then we ask the map to remove the socket, which * tries to remove the socket from the map. Note that there * might be updates to the map between * xsk_get_map_list_entry() and xsk_map_try_sock_delete(). */ struct xdp_sock __rcu **map_entry = NULL; struct xsk_map *map; while ((map = xsk_get_map_list_entry(xs, &map_entry))) { xsk_map_try_sock_delete(map, xs, map_entry); bpf_map_put(&map->map); } } static int xsk_release(struct socket *sock) { struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct net *net; if (!sk) return 0; net = sock_net(sk); if (xs->skb) xsk_drop_skb(xs->skb); mutex_lock(&net->xdp.lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->xdp.lock); sock_prot_inuse_add(net, sk->sk_prot, -1); xsk_delete_from_maps(xs); mutex_lock(&xs->mutex); xsk_unbind_dev(xs); mutex_unlock(&xs->mutex); xskq_destroy(xs->rx); xskq_destroy(xs->tx); xskq_destroy(xs->fq_tmp); xskq_destroy(xs->cq_tmp); sock_orphan(sk); sock->sk = NULL; sock_put(sk); return 0; } static struct socket *xsk_lookup_xsk_from_fd(int fd) { struct socket *sock; int err; sock = sockfd_lookup(fd, &err); if (!sock) return ERR_PTR(-ENOTSOCK); if (sock->sk->sk_family != PF_XDP) { sockfd_put(sock); return ERR_PTR(-ENOPROTOOPT); } return sock; } static bool xsk_validate_queues(struct xdp_sock *xs) { return xs->fq_tmp && xs->cq_tmp; } static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev; int bound_dev_if; u32 flags, qid; int err = 0; if (addr_len < sizeof(struct sockaddr_xdp)) return -EINVAL; if (sxdp->sxdp_family != AF_XDP) return -EINVAL; flags = sxdp->sxdp_flags; if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY | XDP_USE_NEED_WAKEUP | XDP_USE_SG)) return -EINVAL; bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); if (bound_dev_if && bound_dev_if != sxdp->sxdp_ifindex) return -EINVAL; rtnl_lock(); mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { err = -EBUSY; goto out_release; } dev = dev_get_by_index(sock_net(sk), sxdp->sxdp_ifindex); if (!dev) { err = -ENODEV; goto out_release; } if (!xs->rx && !xs->tx) { err = -EINVAL; goto out_unlock; } qid = sxdp->sxdp_queue_id; if (flags & XDP_SHARED_UMEM) { struct xdp_sock *umem_xs; struct socket *sock; if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY) || (flags & XDP_USE_NEED_WAKEUP) || (flags & XDP_USE_SG)) { /* Cannot specify flags for shared sockets. */ err = -EINVAL; goto out_unlock; } if (xs->umem) { /* We have already our own. */ err = -EINVAL; goto out_unlock; } sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd); if (IS_ERR(sock)) { err = PTR_ERR(sock); goto out_unlock; } umem_xs = xdp_sk(sock->sk); if (!xsk_is_bound(umem_xs)) { err = -EBADF; sockfd_put(sock); goto out_unlock; } if (umem_xs->queue_id != qid || umem_xs->dev != dev) { /* Share the umem with another socket on another qid * and/or device. */ xs->pool = xp_create_and_assign_umem(xs, umem_xs->umem); if (!xs->pool) { err = -ENOMEM; sockfd_put(sock); goto out_unlock; } err = xp_assign_dev_shared(xs->pool, umem_xs, dev, qid); if (err) { xp_destroy(xs->pool); xs->pool = NULL; sockfd_put(sock); goto out_unlock; } } else { /* Share the buffer pool with the other socket. */ if (xs->fq_tmp || xs->cq_tmp) { /* Do not allow setting your own fq or cq. */ err = -EINVAL; sockfd_put(sock); goto out_unlock; } xp_get_pool(umem_xs->pool); xs->pool = umem_xs->pool; /* If underlying shared umem was created without Tx * ring, allocate Tx descs array that Tx batching API * utilizes */ if (xs->tx && !xs->pool->tx_descs) { err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); xs->pool = NULL; sockfd_put(sock); goto out_unlock; } } } xdp_get_umem(umem_xs->umem); WRITE_ONCE(xs->umem, umem_xs->umem); sockfd_put(sock); } else if (!xs->umem || !xsk_validate_queues(xs)) { err = -EINVAL; goto out_unlock; } else { /* This xsk has its own umem. */ xs->pool = xp_create_and_assign_umem(xs, xs->umem); if (!xs->pool) { err = -ENOMEM; goto out_unlock; } err = xp_assign_dev(xs->pool, dev, qid, flags); if (err) { xp_destroy(xs->pool); xs->pool = NULL; goto out_unlock; } } /* FQ and CQ are now owned by the buffer pool and cleaned up with it. */ xs->fq_tmp = NULL; xs->cq_tmp = NULL; xs->dev = dev; xs->zc = xs->umem->zc; xs->sg = !!(xs->umem->flags & XDP_UMEM_SG_FLAG); xs->queue_id = qid; xp_add_xsk(xs->pool, xs); out_unlock: if (err) { dev_put(dev); } else { /* Matches smp_rmb() in bind() for shared umem * sockets, and xsk_is_bound(). */ smp_wmb(); WRITE_ONCE(xs->state, XSK_BOUND); } out_release: mutex_unlock(&xs->mutex); rtnl_unlock(); return err; } struct xdp_umem_reg_v1 { __u64 addr; /* Start of packet data area */ __u64 len; /* Length of packet data area */ __u32 chunk_size; __u32 headroom; }; struct xdp_umem_reg_v2 { __u64 addr; /* Start of packet data area */ __u64 len; /* Length of packet data area */ __u32 chunk_size; __u32 headroom; __u32 flags; }; static int xsk_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); int err; if (level != SOL_XDP) return -ENOPROTOOPT; switch (optname) { case XDP_RX_RING: case XDP_TX_RING: { struct xsk_queue **q; int entries; if (optlen < sizeof(entries)) return -EINVAL; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { mutex_unlock(&xs->mutex); return -EBUSY; } q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx; err = xsk_init_queue(entries, q, false); if (!err && optname == XDP_TX_RING) /* Tx needs to be explicitly woken up the first time */ xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP; mutex_unlock(&xs->mutex); return err; } case XDP_UMEM_REG: { size_t mr_size = sizeof(struct xdp_umem_reg); struct xdp_umem_reg mr = {}; struct xdp_umem *umem; if (optlen < sizeof(struct xdp_umem_reg_v1)) return -EINVAL; else if (optlen < sizeof(struct xdp_umem_reg_v2)) mr_size = sizeof(struct xdp_umem_reg_v1); else if (optlen < sizeof(mr)) mr_size = sizeof(struct xdp_umem_reg_v2); if (copy_from_sockptr(&mr, optval, mr_size)) return -EFAULT; mutex_lock(&xs->mutex); if (xs->state != XSK_READY || xs->umem) { mutex_unlock(&xs->mutex); return -EBUSY; } umem = xdp_umem_create(&mr); if (IS_ERR(umem)) { mutex_unlock(&xs->mutex); return PTR_ERR(umem); } /* Make sure umem is ready before it can be seen by others */ smp_wmb(); WRITE_ONCE(xs->umem, umem); mutex_unlock(&xs->mutex); return 0; } case XDP_UMEM_FILL_RING: case XDP_UMEM_COMPLETION_RING: { struct xsk_queue **q; int entries; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { mutex_unlock(&xs->mutex); return -EBUSY; } q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp : &xs->cq_tmp; err = xsk_init_queue(entries, q, true); mutex_unlock(&xs->mutex); return err; } default: break; } return -ENOPROTOOPT; } static void xsk_enter_rxtx_offsets(struct xdp_ring_offset_v1 *ring) { ring->producer = offsetof(struct xdp_rxtx_ring, ptrs.producer); ring->consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer); ring->desc = offsetof(struct xdp_rxtx_ring, desc); } static void xsk_enter_umem_offsets(struct xdp_ring_offset_v1 *ring) { ring->producer = offsetof(struct xdp_umem_ring, ptrs.producer); ring->consumer = offsetof(struct xdp_umem_ring, ptrs.consumer); ring->desc = offsetof(struct xdp_umem_ring, desc); } struct xdp_statistics_v1 { __u64 rx_dropped; __u64 rx_invalid_descs; __u64 tx_invalid_descs; }; static int xsk_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); int len; if (level != SOL_XDP) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case XDP_STATISTICS: { struct xdp_statistics stats = {}; bool extra_stats = true; size_t stats_size; if (len < sizeof(struct xdp_statistics_v1)) { return -EINVAL; } else if (len < sizeof(stats)) { extra_stats = false; stats_size = sizeof(struct xdp_statistics_v1); } else { stats_size = sizeof(stats); } mutex_lock(&xs->mutex); stats.rx_dropped = xs->rx_dropped; if (extra_stats) { stats.rx_ring_full = xs->rx_queue_full; stats.rx_fill_ring_empty_descs = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx); } else { stats.rx_dropped += xs->rx_queue_full; } stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx); stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx); mutex_unlock(&xs->mutex); if (copy_to_user(optval, &stats, stats_size)) return -EFAULT; if (put_user(stats_size, optlen)) return -EFAULT; return 0; } case XDP_MMAP_OFFSETS: { struct xdp_mmap_offsets off; struct xdp_mmap_offsets_v1 off_v1; bool flags_supported = true; void *to_copy; if (len < sizeof(off_v1)) return -EINVAL; else if (len < sizeof(off)) flags_supported = false; if (flags_supported) { /* xdp_ring_offset is identical to xdp_ring_offset_v1 * except for the flags field added to the end. */ xsk_enter_rxtx_offsets((struct xdp_ring_offset_v1 *) &off.rx); xsk_enter_rxtx_offsets((struct xdp_ring_offset_v1 *) &off.tx); xsk_enter_umem_offsets((struct xdp_ring_offset_v1 *) &off.fr); xsk_enter_umem_offsets((struct xdp_ring_offset_v1 *) &off.cr); off.rx.flags = offsetof(struct xdp_rxtx_ring, ptrs.flags); off.tx.flags = offsetof(struct xdp_rxtx_ring, ptrs.flags); off.fr.flags = offsetof(struct xdp_umem_ring, ptrs.flags); off.cr.flags = offsetof(struct xdp_umem_ring, ptrs.flags); len = sizeof(off); to_copy = &off; } else { xsk_enter_rxtx_offsets(&off_v1.rx); xsk_enter_rxtx_offsets(&off_v1.tx); xsk_enter_umem_offsets(&off_v1.fr); xsk_enter_umem_offsets(&off_v1.cr); len = sizeof(off_v1); to_copy = &off_v1; } if (copy_to_user(optval, to_copy, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } case XDP_OPTIONS: { struct xdp_options opts = {}; if (len < sizeof(opts)) return -EINVAL; mutex_lock(&xs->mutex); if (xs->zc) opts.flags |= XDP_OPTIONS_ZEROCOPY; mutex_unlock(&xs->mutex); len = sizeof(opts); if (copy_to_user(optval, &opts, len)) return -EFAULT; if (put_user(len, optlen)) return -EFAULT; return 0; } default: break; } return -EOPNOTSUPP; } static int xsk_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { loff_t offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; unsigned long size = vma->vm_end - vma->vm_start; struct xdp_sock *xs = xdp_sk(sock->sk); int state = READ_ONCE(xs->state); struct xsk_queue *q = NULL; if (state != XSK_READY && state != XSK_BOUND) return -EBUSY; if (offset == XDP_PGOFF_RX_RING) { q = READ_ONCE(xs->rx); } else if (offset == XDP_PGOFF_TX_RING) { q = READ_ONCE(xs->tx); } else { /* Matches the smp_wmb() in XDP_UMEM_REG */ smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) q = state == XSK_READY ? READ_ONCE(xs->fq_tmp) : READ_ONCE(xs->pool->fq); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) q = state == XSK_READY ? READ_ONCE(xs->cq_tmp) : READ_ONCE(xs->pool->cq); } if (!q) return -EINVAL; /* Matches the smp_wmb() in xsk_init_queue */ smp_rmb(); if (size > q->ring_vmalloc_size) return -EINVAL; return remap_vmalloc_range(vma, q->ring, 0); } static int xsk_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct sock *sk; switch (msg) { case NETDEV_UNREGISTER: mutex_lock(&net->xdp.lock); sk_for_each(sk, &net->xdp.list) { struct xdp_sock *xs = xdp_sk(sk); mutex_lock(&xs->mutex); if (xs->dev == dev) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); xsk_unbind_dev(xs); /* Clear device references. */ xp_clear_dev(xs->pool); } mutex_unlock(&xs->mutex); } mutex_unlock(&net->xdp.lock); break; } return NOTIFY_DONE; } static struct proto xsk_proto = { .name = "XDP", .owner = THIS_MODULE, .obj_size = sizeof(struct xdp_sock), }; static const struct proto_ops xsk_proto_ops = { .family = PF_XDP, .owner = THIS_MODULE, .release = xsk_release, .bind = xsk_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = xsk_poll, .ioctl = sock_no_ioctl, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = xsk_setsockopt, .getsockopt = xsk_getsockopt, .sendmsg = xsk_sendmsg, .recvmsg = xsk_recvmsg, .mmap = xsk_mmap, }; static void xsk_destruct(struct sock *sk) { struct xdp_sock *xs = xdp_sk(sk); if (!sock_flag(sk, SOCK_DEAD)) return; if (!xp_put_pool(xs->pool)) xdp_put_umem(xs->umem, !xs->pool); } static int xsk_create(struct net *net, struct socket *sock, int protocol, int kern) { struct xdp_sock *xs; struct sock *sk; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; if (protocol) return -EPROTONOSUPPORT; sock->state = SS_UNCONNECTED; sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern); if (!sk) return -ENOBUFS; sock->ops = &xsk_proto_ops; sock_init_data(sock, sk); sk->sk_family = PF_XDP; sk->sk_destruct = xsk_destruct; sock_set_flag(sk, SOCK_RCU_FREE); xs = xdp_sk(sk); xs->state = XSK_READY; mutex_init(&xs->mutex); spin_lock_init(&xs->rx_lock); INIT_LIST_HEAD(&xs->map_list); spin_lock_init(&xs->map_list_lock); mutex_lock(&net->xdp.lock); sk_add_node_rcu(sk, &net->xdp.list); mutex_unlock(&net->xdp.lock); sock_prot_inuse_add(net, &xsk_proto, 1); return 0; } static const struct net_proto_family xsk_family_ops = { .family = PF_XDP, .create = xsk_create, .owner = THIS_MODULE, }; static struct notifier_block xsk_netdev_notifier = { .notifier_call = xsk_notifier, }; static int __net_init xsk_net_init(struct net *net) { mutex_init(&net->xdp.lock); INIT_HLIST_HEAD(&net->xdp.list); return 0; } static void __net_exit xsk_net_exit(struct net *net) { WARN_ON_ONCE(!hlist_empty(&net->xdp.list)); } static struct pernet_operations xsk_net_ops = { .init = xsk_net_init, .exit = xsk_net_exit, }; static int __init xsk_init(void) { int err, cpu; err = proto_register(&xsk_proto, 0 /* no slab */); if (err) goto out; err = sock_register(&xsk_family_ops); if (err) goto out_proto; err = register_pernet_subsys(&xsk_net_ops); if (err) goto out_sk; err = register_netdevice_notifier(&xsk_netdev_notifier); if (err) goto out_pernet; for_each_possible_cpu(cpu) INIT_LIST_HEAD(&per_cpu(xskmap_flush_list, cpu)); return 0; out_pernet: unregister_pernet_subsys(&xsk_net_ops); out_sk: sock_unregister(PF_XDP); out_proto: proto_unregister(&xsk_proto); out: return err; } fs_initcall(xsk_init); |
| 86 964 964 51 51 51 51 51 51 51 51 51 51 51 115 115 129 6 128 128 26 115 26 128 94 86 1 10 22 22 22 22 22 22 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 | // SPDX-License-Identifier: GPL-2.0-or-later /* * inet fragments management * * Authors: Pavel Emelyanov <xemul@openvz.org> * Started as consolidation of ipv4/ip_fragment.c, * ipv6/reassembly. and ipv6 nf conntrack reassembly */ #include <linux/list.h> #include <linux/spinlock.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/rhashtable.h> #include <net/sock.h> #include <net/inet_frag.h> #include <net/inet_ecn.h> #include <net/ip.h> #include <net/ipv6.h> /* Use skb->cb to track consecutive/adjacent fragments coming at * the end of the queue. Nodes in the rb-tree queue will * contain "runs" of one or more adjacent fragments. * * Invariants: * - next_frag is NULL at the tail of a "run"; * - the head of a "run" has the sum of all fragment lengths in frag_run_len. */ struct ipfrag_skb_cb { union { struct inet_skb_parm h4; struct inet6_skb_parm h6; }; struct sk_buff *next_frag; int frag_run_len; }; #define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) static void fragcb_clear(struct sk_buff *skb) { RB_CLEAR_NODE(&skb->rbnode); FRAG_CB(skb)->next_frag = NULL; FRAG_CB(skb)->frag_run_len = skb->len; } /* Append skb to the last "run". */ static void fragrun_append_to_last(struct inet_frag_queue *q, struct sk_buff *skb) { fragcb_clear(skb); FRAG_CB(q->last_run_head)->frag_run_len += skb->len; FRAG_CB(q->fragments_tail)->next_frag = skb; q->fragments_tail = skb; } /* Create a new "run" with the skb. */ static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) { BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); fragcb_clear(skb); if (q->last_run_head) rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, &q->last_run_head->rbnode.rb_right); else rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); rb_insert_color(&skb->rbnode, &q->rb_fragments); q->fragments_tail = skb; q->last_run_head = skb; } /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field */ const u8 ip_frag_ecn_table[16] = { /* at least one fragment had CE, and others ECT_0 or ECT_1 */ [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = INET_ECN_CE, [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = INET_ECN_CE, [IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = INET_ECN_CE, /* invalid combinations : drop frame */ [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_1] = 0xff, [IPFRAG_ECN_NOT_ECT | IPFRAG_ECN_CE | IPFRAG_ECN_ECT_0 | IPFRAG_ECN_ECT_1] = 0xff, }; EXPORT_SYMBOL(ip_frag_ecn_table); int inet_frags_init(struct inet_frags *f) { f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0, NULL); if (!f->frags_cachep) return -ENOMEM; refcount_set(&f->refcnt, 1); init_completion(&f->completion); return 0; } EXPORT_SYMBOL(inet_frags_init); void inet_frags_fini(struct inet_frags *f) { if (refcount_dec_and_test(&f->refcnt)) complete(&f->completion); wait_for_completion(&f->completion); kmem_cache_destroy(f->frags_cachep); f->frags_cachep = NULL; } EXPORT_SYMBOL(inet_frags_fini); /* called from rhashtable_free_and_destroy() at netns_frags dismantle */ static void inet_frags_free_cb(void *ptr, void *arg) { struct inet_frag_queue *fq = ptr; int count; count = del_timer_sync(&fq->timer) ? 1 : 0; spin_lock_bh(&fq->lock); fq->flags |= INET_FRAG_DROP; if (!(fq->flags & INET_FRAG_COMPLETE)) { fq->flags |= INET_FRAG_COMPLETE; count++; } else if (fq->flags & INET_FRAG_HASH_DEAD) { count++; } spin_unlock_bh(&fq->lock); if (refcount_sub_and_test(count, &fq->refcnt)) inet_frag_destroy(fq); } static LLIST_HEAD(fqdir_free_list); static void fqdir_free_fn(struct work_struct *work) { struct llist_node *kill_list; struct fqdir *fqdir, *tmp; struct inet_frags *f; /* Atomically snapshot the list of fqdirs to free */ kill_list = llist_del_all(&fqdir_free_list); /* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu) * have completed, since they need to dereference fqdir. * Would it not be nice to have kfree_rcu_barrier() ? :) */ rcu_barrier(); llist_for_each_entry_safe(fqdir, tmp, kill_list, free_list) { f = fqdir->f; if (refcount_dec_and_test(&f->refcnt)) complete(&f->completion); kfree(fqdir); } } static DECLARE_WORK(fqdir_free_work, fqdir_free_fn); static void fqdir_work_fn(struct work_struct *work) { struct fqdir *fqdir = container_of(work, struct fqdir, destroy_work); rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL); if (llist_add(&fqdir->free_list, &fqdir_free_list)) queue_work(system_wq, &fqdir_free_work); } int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net) { struct fqdir *fqdir = kzalloc(sizeof(*fqdir), GFP_KERNEL); int res; if (!fqdir) return -ENOMEM; fqdir->f = f; fqdir->net = net; res = rhashtable_init(&fqdir->rhashtable, &fqdir->f->rhash_params); if (res < 0) { kfree(fqdir); return res; } refcount_inc(&f->refcnt); *fqdirp = fqdir; return 0; } EXPORT_SYMBOL(fqdir_init); static struct workqueue_struct *inet_frag_wq; static int __init inet_frag_wq_init(void) { inet_frag_wq = create_workqueue("inet_frag_wq"); if (!inet_frag_wq) panic("Could not create inet frag workq"); return 0; } pure_initcall(inet_frag_wq_init); void fqdir_exit(struct fqdir *fqdir) { INIT_WORK(&fqdir->destroy_work, fqdir_work_fn); queue_work(inet_frag_wq, &fqdir->destroy_work); } EXPORT_SYMBOL(fqdir_exit); void inet_frag_kill(struct inet_frag_queue *fq) { if (del_timer(&fq->timer)) refcount_dec(&fq->refcnt); if (!(fq->flags & INET_FRAG_COMPLETE)) { struct fqdir *fqdir = fq->fqdir; fq->flags |= INET_FRAG_COMPLETE; rcu_read_lock(); /* The RCU read lock provides a memory barrier * guaranteeing that if fqdir->dead is false then * the hash table destruction will not start until * after we unlock. Paired with fqdir_pre_exit(). */ if (!READ_ONCE(fqdir->dead)) { rhashtable_remove_fast(&fqdir->rhashtable, &fq->node, fqdir->f->rhash_params); refcount_dec(&fq->refcnt); } else { fq->flags |= INET_FRAG_HASH_DEAD; } rcu_read_unlock(); } } EXPORT_SYMBOL(inet_frag_kill); static void inet_frag_destroy_rcu(struct rcu_head *head) { struct inet_frag_queue *q = container_of(head, struct inet_frag_queue, rcu); struct inet_frags *f = q->fqdir->f; if (f->destructor) f->destructor(q); kmem_cache_free(f->frags_cachep, q); } unsigned int inet_frag_rbtree_purge(struct rb_root *root, enum skb_drop_reason reason) { struct rb_node *p = rb_first(root); unsigned int sum = 0; while (p) { struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); p = rb_next(p); rb_erase(&skb->rbnode, root); while (skb) { struct sk_buff *next = FRAG_CB(skb)->next_frag; sum += skb->truesize; kfree_skb_reason(skb, reason); skb = next; } } return sum; } EXPORT_SYMBOL(inet_frag_rbtree_purge); void inet_frag_destroy(struct inet_frag_queue *q) { unsigned int sum, sum_truesize = 0; enum skb_drop_reason reason; struct inet_frags *f; struct fqdir *fqdir; WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); reason = (q->flags & INET_FRAG_DROP) ? SKB_DROP_REASON_FRAG_REASM_TIMEOUT : SKB_CONSUMED; WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ fqdir = q->fqdir; f = fqdir->f; sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments, reason); sum = sum_truesize + f->qsize; call_rcu(&q->rcu, inet_frag_destroy_rcu); sub_frag_mem_limit(fqdir, sum); } EXPORT_SYMBOL(inet_frag_destroy); static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir, struct inet_frags *f, void *arg) { struct inet_frag_queue *q; q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) return NULL; q->fqdir = fqdir; f->constructor(q, arg); add_frag_mem_limit(fqdir, f->qsize); timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); refcount_set(&q->refcnt, 3); return q; } static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir, void *arg, struct inet_frag_queue **prev) { struct inet_frags *f = fqdir->f; struct inet_frag_queue *q; q = inet_frag_alloc(fqdir, f, arg); if (!q) { *prev = ERR_PTR(-ENOMEM); return NULL; } mod_timer(&q->timer, jiffies + fqdir->timeout); *prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key, &q->node, f->rhash_params); if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); return NULL; } return q; } /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key) { /* This pairs with WRITE_ONCE() in fqdir_pre_exit(). */ long high_thresh = READ_ONCE(fqdir->high_thresh); struct inet_frag_queue *fq = NULL, *prev; if (!high_thresh || frag_mem_limit(fqdir) > high_thresh) return NULL; rcu_read_lock(); prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params); if (!prev) fq = inet_frag_create(fqdir, key, &prev); if (!IS_ERR_OR_NULL(prev)) { fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; } rcu_read_unlock(); return fq; } EXPORT_SYMBOL(inet_frag_find); int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, int offset, int end) { struct sk_buff *last = q->fragments_tail; /* RFC5722, Section 4, amended by Errata ID : 3089 * When reassembling an IPv6 datagram, if * one or more its constituent fragments is determined to be an * overlapping fragment, the entire datagram (and any constituent * fragments) MUST be silently discarded. * * Duplicates, however, should be ignored (i.e. skb dropped, but the * queue/fragments kept for later reassembly). */ if (!last) fragrun_create(q, skb); /* First fragment. */ else if (last->ip_defrag_offset + last->len < end) { /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ if (offset < last->ip_defrag_offset + last->len) return IPFRAG_OVERLAP; if (offset == last->ip_defrag_offset + last->len) fragrun_append_to_last(q, skb); else fragrun_create(q, skb); } else { /* Binary search. Note that skb can become the first fragment, * but not the last (covered above). */ struct rb_node **rbn, *parent; rbn = &q->rb_fragments.rb_node; do { struct sk_buff *curr; int curr_run_end; parent = *rbn; curr = rb_to_skb(parent); curr_run_end = curr->ip_defrag_offset + FRAG_CB(curr)->frag_run_len; if (end <= curr->ip_defrag_offset) rbn = &parent->rb_left; else if (offset >= curr_run_end) rbn = &parent->rb_right; else if (offset >= curr->ip_defrag_offset && end <= curr_run_end) return IPFRAG_DUP; else return IPFRAG_OVERLAP; } while (*rbn); /* Here we have parent properly set, and rbn pointing to * one of its NULL left/right children. Insert skb. */ fragcb_clear(skb); rb_link_node(&skb->rbnode, parent, rbn); rb_insert_color(&skb->rbnode, &q->rb_fragments); } skb->ip_defrag_offset = offset; return IPFRAG_OK; } EXPORT_SYMBOL(inet_frag_queue_insert); void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent) { struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); struct sk_buff **nextp; int delta; if (head != skb) { fp = skb_clone(skb, GFP_ATOMIC); if (!fp) return NULL; FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; if (RB_EMPTY_NODE(&skb->rbnode)) FRAG_CB(parent)->next_frag = fp; else rb_replace_node(&skb->rbnode, &fp->rbnode, &q->rb_fragments); if (q->fragments_tail == skb) q->fragments_tail = fp; skb_morph(skb, head); FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; rb_replace_node(&head->rbnode, &skb->rbnode, &q->rb_fragments); consume_skb(head); head = skb; } WARN_ON(head->ip_defrag_offset != 0); delta = -head->truesize; /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) return NULL; delta += head->truesize; if (delta) add_frag_mem_limit(q->fqdir, delta); /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ if (skb_has_frag_list(head)) { struct sk_buff *clone; int i, plen = 0; clone = alloc_skb(0, GFP_ATOMIC); if (!clone) return NULL; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) plen += skb_frag_size(&skb_shinfo(head)->frags[i]); clone->data_len = head->data_len - plen; clone->len = clone->data_len; head->truesize += clone->truesize; clone->csum = 0; clone->ip_summed = head->ip_summed; add_frag_mem_limit(q->fqdir, clone->truesize); skb_shinfo(head)->frag_list = clone; nextp = &clone->next; } else { nextp = &skb_shinfo(head)->frag_list; } return nextp; } EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce) { struct sk_buff **nextp = reasm_data; struct rb_node *rbn; struct sk_buff *fp; int sum_truesize; skb_push(head, head->data - skb_network_header(head)); /* Traverse the tree in order, to build frag_list. */ fp = FRAG_CB(head)->next_frag; rbn = rb_next(&head->rbnode); rb_erase(&head->rbnode, &q->rb_fragments); sum_truesize = head->truesize; while (rbn || fp) { /* fp points to the next sk_buff in the current run; * rbn points to the next run. */ /* Go through the current run. */ while (fp) { struct sk_buff *next_frag = FRAG_CB(fp)->next_frag; bool stolen; int delta; sum_truesize += fp->truesize; if (head->ip_summed != fp->ip_summed) head->ip_summed = CHECKSUM_NONE; else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); if (try_coalesce && skb_try_coalesce(head, fp, &stolen, &delta)) { kfree_skb_partial(fp, stolen); } else { fp->prev = NULL; memset(&fp->rbnode, 0, sizeof(fp->rbnode)); fp->sk = NULL; head->data_len += fp->len; head->len += fp->len; head->truesize += fp->truesize; *nextp = fp; nextp = &fp->next; } fp = next_frag; } /* Move to the next run. */ if (rbn) { struct rb_node *rbnext = rb_next(rbn); fp = rb_to_skb(rbn); rb_erase(rbn, &q->rb_fragments); rbn = rbnext; } } sub_frag_mem_limit(q->fqdir, sum_truesize); *nextp = NULL; skb_mark_not_on_list(head); head->prev = NULL; head->tstamp = q->stamp; head->mono_delivery_time = q->mono_delivery_time; } EXPORT_SYMBOL(inet_frag_reasm_finish); struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) { struct sk_buff *head, *skb; head = skb_rb_first(&q->rb_fragments); if (!head) return NULL; skb = FRAG_CB(head)->next_frag; if (skb) rb_replace_node(&head->rbnode, &skb->rbnode, &q->rb_fragments); else rb_erase(&head->rbnode, &q->rb_fragments); memset(&head->rbnode, 0, sizeof(head->rbnode)); barrier(); if (head == q->fragments_tail) q->fragments_tail = NULL; sub_frag_mem_limit(q->fqdir, head->truesize); return head; } EXPORT_SYMBOL(inet_frag_pull_head); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_DAX_H #define _LINUX_DAX_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/radix-tree.h> typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; struct iomap_iter; struct iomap; enum dax_access_mode { DAX_ACCESS, DAX_RECOVERY_WRITE, }; struct dax_operations { /* * direct_access: translate a device-relative * logical-page-offset into an absolute physical pfn. Return the * number of pages available for DAX at that pfn. */ long (*direct_access)(struct dax_device *, pgoff_t, long, enum dax_access_mode, void **, pfn_t *); /* * Validate whether this device is usable as an fsdax backing * device. */ bool (*dax_supported)(struct dax_device *, struct block_device *, int, sector_t, sector_t); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); /* * recovery_write: recover a poisoned range by DAX device driver * capable of clearing poison. */ size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *iter); }; struct dax_holder_operations { /* * notify_failure - notify memory failure into inner holder device * @dax_dev: the dax device which contains the holder * @offset: offset on this dax device where memory failure occurs * @len: length of this memory failure event * @flags: action flags for memory failure handler */ int (*notify_failure)(struct dax_device *dax_dev, u64 offset, u64 len, int mf_flags); }; #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); void *dax_holder(struct dax_device *dax_dev); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); bool dax_synchronous(struct dax_device *dax_dev); void set_dax_synchronous(struct dax_device *dax_dev); size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); /* * Check if given mapping is supported by the file / underlying device. */ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { if (!(vma->vm_flags & VM_SYNC)) return true; if (!IS_DAX(file_inode(vma->vm_file))) return false; return dax_synchronous(dax_dev); } #else static inline void *dax_holder(struct dax_device *dax_dev) { return NULL; } static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this * NULL is an error or expected. */ return NULL; } static inline void put_dax(struct dax_device *dax_dev) { } static inline void kill_dax(struct dax_device *dax_dev) { } static inline void dax_write_cache(struct dax_device *dax_dev, bool wc) { } static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) { return false; } static inline bool dax_synchronous(struct dax_device *dax_dev) { return true; } static inline void set_dax_synchronous(struct dax_device *dax_dev) { } static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct dax_device *dax_dev) { return !(vma->vm_flags & VM_SYNC); } static inline size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { return 0; } #endif void set_dax_nocache(struct dax_device *dax_dev); void set_dax_nomc(struct dax_device *dax_dev); struct writeback_control; #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, void *holder, const struct dax_holder_operations *ops); void fs_put_dax(struct dax_device *dax_dev, void *holder); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { return 0; } static inline void dax_remove_host(struct gendisk *disk) { } static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off, void *holder, const struct dax_holder_operations *ops) { return NULL; } static inline void fs_put_dax(struct dax_device *dax_dev, void *holder) { } #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ #if IS_ENABLED(CONFIG_FS_DAX) int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_folio(struct folio *folio); void dax_unlock_folio(struct folio *folio, dax_entry_t cookie); dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page); void dax_unlock_mapping_entry(struct address_space *mapping, unsigned long index, dax_entry_t cookie); #else static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; } static inline struct page *dax_layout_busy_page_range(struct address_space *mapping, pgoff_t start, pgoff_t nr_pages) { return NULL; } static inline int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc) { return -EOPNOTSUPP; } static inline dax_entry_t dax_lock_folio(struct folio *folio) { if (IS_DAX(folio->mapping->host)) return ~0UL; return 0; } static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie) { } static inline dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, unsigned long index, struct page **page) { return 0; } static inline void dax_unlock_mapping_entry(struct address_space *mapping, unsigned long index, dax_entry_t cookie) { } #endif int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, const struct iomap_ops *ops); #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); #else static inline int dax_read_lock(void) { return 0; } static inline void dax_read_unlock(int id) { } #endif /* CONFIG_DAX */ bool dax_alive(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages); int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len, int mf_flags); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order, pfn_t *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order, pfn_t pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same, const struct iomap_ops *ops); int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *ops); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } /* * Due to dax's memory and block duo personalities, hwpoison reporting * takes into consideration which personality is presently visible. * When dax acts like a block device, such as in block IO, an encounter of * dax hwpoison is reported as -EIO. * When dax acts like memory, such as in page fault, a detection of hwpoison * is reported as -EHWPOISON which leads to VM_FAULT_HWPOISON. */ static inline int dax_mem2blk_err(int err) { return (err == -EHWPOISON) ? -EIO : err; } #ifdef CONFIG_DEV_DAX_HMEM_DEVICES void hmem_register_resource(int target_nid, struct resource *r); #else static inline void hmem_register_resource(int target_nid, struct resource *r) { } #endif typedef int (*walk_hmem_fn)(struct device *dev, int target_nid, const struct resource *res); int walk_hmem_resources(struct device *dev, walk_hmem_fn fn); #endif |
| 1191 1191 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TTY_H #define _LINUX_TTY_H #include <linux/fs.h> #include <linux/major.h> #include <linux/termios.h> #include <linux/workqueue.h> #include <linux/tty_buffer.h> #include <linux/tty_driver.h> #include <linux/tty_ldisc.h> #include <linux/tty_port.h> #include <linux/mutex.h> #include <linux/tty_flags.h> #include <uapi/linux/tty.h> #include <linux/rwsem.h> #include <linux/llist.h> /* * (Note: the *_driver.minor_start values 1, 64, 128, 192 are * hardcoded at present.) */ #define NR_UNIX98_PTY_DEFAULT 4096 /* Default maximum for Unix98 ptys */ #define NR_UNIX98_PTY_RESERVE 1024 /* Default reserve for main devpts */ #define NR_UNIX98_PTY_MAX (1 << MINORBITS) /* Absolute limit */ /* * This character is the same as _POSIX_VDISABLE: it cannot be used as * a c_cc[] character, but indicates that a particular special character * isn't in use (eg VINTR has no character etc) */ #define __DISABLED_CHAR '\0' #define INTR_CHAR(tty) ((tty)->termios.c_cc[VINTR]) #define QUIT_CHAR(tty) ((tty)->termios.c_cc[VQUIT]) #define ERASE_CHAR(tty) ((tty)->termios.c_cc[VERASE]) #define KILL_CHAR(tty) ((tty)->termios.c_cc[VKILL]) #define EOF_CHAR(tty) ((tty)->termios.c_cc[VEOF]) #define TIME_CHAR(tty) ((tty)->termios.c_cc[VTIME]) #define MIN_CHAR(tty) ((tty)->termios.c_cc[VMIN]) #define SWTC_CHAR(tty) ((tty)->termios.c_cc[VSWTC]) #define START_CHAR(tty) ((tty)->termios.c_cc[VSTART]) #define STOP_CHAR(tty) ((tty)->termios.c_cc[VSTOP]) #define SUSP_CHAR(tty) ((tty)->termios.c_cc[VSUSP]) #define EOL_CHAR(tty) ((tty)->termios.c_cc[VEOL]) #define REPRINT_CHAR(tty) ((tty)->termios.c_cc[VREPRINT]) #define DISCARD_CHAR(tty) ((tty)->termios.c_cc[VDISCARD]) #define WERASE_CHAR(tty) ((tty)->termios.c_cc[VWERASE]) #define LNEXT_CHAR(tty) ((tty)->termios.c_cc[VLNEXT]) #define EOL2_CHAR(tty) ((tty)->termios.c_cc[VEOL2]) #define _I_FLAG(tty, f) ((tty)->termios.c_iflag & (f)) #define _O_FLAG(tty, f) ((tty)->termios.c_oflag & (f)) #define _C_FLAG(tty, f) ((tty)->termios.c_cflag & (f)) #define _L_FLAG(tty, f) ((tty)->termios.c_lflag & (f)) #define I_IGNBRK(tty) _I_FLAG((tty), IGNBRK) #define I_BRKINT(tty) _I_FLAG((tty), BRKINT) #define I_IGNPAR(tty) _I_FLAG((tty), IGNPAR) #define I_PARMRK(tty) _I_FLAG((tty), PARMRK) #define I_INPCK(tty) _I_FLAG((tty), INPCK) #define I_ISTRIP(tty) _I_FLAG((tty), ISTRIP) #define I_INLCR(tty) _I_FLAG((tty), INLCR) #define I_IGNCR(tty) _I_FLAG((tty), IGNCR) #define I_ICRNL(tty) _I_FLAG((tty), ICRNL) #define I_IUCLC(tty) _I_FLAG((tty), IUCLC) #define I_IXON(tty) _I_FLAG((tty), IXON) #define I_IXANY(tty) _I_FLAG((tty), IXANY) #define I_IXOFF(tty) _I_FLAG((tty), IXOFF) #define I_IMAXBEL(tty) _I_FLAG((tty), IMAXBEL) #define I_IUTF8(tty) _I_FLAG((tty), IUTF8) #define O_OPOST(tty) _O_FLAG((tty), OPOST) #define O_OLCUC(tty) _O_FLAG((tty), OLCUC) #define O_ONLCR(tty) _O_FLAG((tty), ONLCR) #define O_OCRNL(tty) _O_FLAG((tty), OCRNL) #define O_ONOCR(tty) _O_FLAG((tty), ONOCR) #define O_ONLRET(tty) _O_FLAG((tty), ONLRET) #define O_OFILL(tty) _O_FLAG((tty), OFILL) #define O_OFDEL(tty) _O_FLAG((tty), OFDEL) #define O_NLDLY(tty) _O_FLAG((tty), NLDLY) #define O_CRDLY(tty) _O_FLAG((tty), CRDLY) #define O_TABDLY(tty) _O_FLAG((tty), TABDLY) #define O_BSDLY(tty) _O_FLAG((tty), BSDLY) #define O_VTDLY(tty) _O_FLAG((tty), VTDLY) #define O_FFDLY(tty) _O_FLAG((tty), FFDLY) #define C_BAUD(tty) _C_FLAG((tty), CBAUD) #define C_CSIZE(tty) _C_FLAG((tty), CSIZE) #define C_CSTOPB(tty) _C_FLAG((tty), CSTOPB) #define C_CREAD(tty) _C_FLAG((tty), CREAD) #define C_PARENB(tty) _C_FLAG((tty), PARENB) #define C_PARODD(tty) _C_FLAG((tty), PARODD) #define C_HUPCL(tty) _C_FLAG((tty), HUPCL) #define C_CLOCAL(tty) _C_FLAG((tty), CLOCAL) #define C_CIBAUD(tty) _C_FLAG((tty), CIBAUD) #define C_CRTSCTS(tty) _C_FLAG((tty), CRTSCTS) #define C_CMSPAR(tty) _C_FLAG((tty), CMSPAR) #define L_ISIG(tty) _L_FLAG((tty), ISIG) #define L_ICANON(tty) _L_FLAG((tty), ICANON) #define L_XCASE(tty) _L_FLAG((tty), XCASE) #define L_ECHO(tty) _L_FLAG((tty), ECHO) #define L_ECHOE(tty) _L_FLAG((tty), ECHOE) #define L_ECHOK(tty) _L_FLAG((tty), ECHOK) #define L_ECHONL(tty) _L_FLAG((tty), ECHONL) #define L_NOFLSH(tty) _L_FLAG((tty), NOFLSH) #define L_TOSTOP(tty) _L_FLAG((tty), TOSTOP) #define L_ECHOCTL(tty) _L_FLAG((tty), ECHOCTL) #define L_ECHOPRT(tty) _L_FLAG((tty), ECHOPRT) #define L_ECHOKE(tty) _L_FLAG((tty), ECHOKE) #define L_FLUSHO(tty) _L_FLAG((tty), FLUSHO) #define L_PENDIN(tty) _L_FLAG((tty), PENDIN) #define L_IEXTEN(tty) _L_FLAG((tty), IEXTEN) #define L_EXTPROC(tty) _L_FLAG((tty), EXTPROC) struct device; struct signal_struct; struct tty_operations; /** * struct tty_struct - state associated with a tty while open * * @kref: reference counting by tty_kref_get() and tty_kref_put(), reaching zero * frees the structure * @dev: class device or %NULL (e.g. ptys, serdev) * @driver: &struct tty_driver operating this tty * @ops: &struct tty_operations of @driver for this tty (open, close, etc.) * @index: index of this tty (e.g. to construct @name like tty12) * @ldisc_sem: protects line discipline changes (@ldisc) -- lock tty not pty * @ldisc: the current line discipline for this tty (n_tty by default) * @atomic_write_lock: protects against concurrent writers, i.e. locks * @write_cnt, @write_buf and similar * @legacy_mutex: leftover from history (BKL -> BTM -> @legacy_mutex), * protecting several operations on this tty * @throttle_mutex: protects against concurrent tty_throttle_safe() and * tty_unthrottle_safe() (but not tty_unthrottle()) * @termios_rwsem: protects @termios and @termios_locked * @winsize_mutex: protects @winsize * @termios: termios for the current tty, copied from/to @driver.termios * @termios_locked: locked termios (by %TIOCGLCKTRMIOS and %TIOCSLCKTRMIOS * ioctls) * @name: name of the tty constructed by tty_line_name() (e.g. ttyS3) * @flags: bitwise OR of %TTY_THROTTLED, %TTY_IO_ERROR, ... * @count: count of open processes, reaching zero cancels all the work for * this tty and drops a @kref too (but does not free this tty) * @winsize: size of the terminal "window" (cf. @winsize_mutex) * @flow: flow settings grouped together, see also @flow.unused * @flow.lock: lock for @flow members * @flow.stopped: tty stopped/started by stop_tty()/start_tty() * @flow.tco_stopped: tty stopped/started by %TCOOFF/%TCOON ioctls (it has * precedence over @flow.stopped) * @flow.unused: alignment for Alpha, so that no members other than @flow.* are * modified by the same 64b word store. The @flow's __aligned is * there for the very same reason. * @ctrl: control settings grouped together, see also @ctrl.unused * @ctrl.lock: lock for @ctrl members * @ctrl.pgrp: process group of this tty (setpgrp(2)) * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both * @ctrl.lock and @legacy_mutex, readers must use at least one of * them. * @ctrl.pktstatus: packet mode status (bitwise OR of %TIOCPKT_ constants) * @ctrl.packet: packet mode enabled * @ctrl.unused: alignment for Alpha, see @flow.unused for explanation * @hw_stopped: not controlled by the tty layer, under @driver's control for CTS * handling * @receive_room: bytes permitted to feed to @ldisc without any being lost * @flow_change: controls behavior of throttling, see tty_throttle_safe() and * tty_unthrottle_safe() * @link: link to another pty (master -> slave and vice versa) * @fasync: state for %O_ASYNC (for %SIGIO); managed by fasync_helper() * @write_wait: concurrent writers are waiting in this queue until they are * allowed to write * @read_wait: readers wait for data in this queue * @hangup_work: normally a work to perform a hangup (do_tty_hangup()); while * freeing the tty, (re)used to release_one_tty() * @disc_data: pointer to @ldisc's private data (e.g. to &struct n_tty_data) * @driver_data: pointer to @driver's private data (e.g. &struct uart_state) * @files_lock: protects @tty_files list * @tty_files: list of (re)openers of this tty (i.e. linked &struct * tty_file_private) * @closing: when set during close, n_tty processes only START & STOP chars * @write_buf: temporary buffer used during tty_write() to copy user data to * @write_cnt: count of bytes written in tty_write() to @write_buf * @SAK_work: if the tty has a pending do_SAK, it is queued here * @port: persistent storage for this device (i.e. &struct tty_port) * * All of the state associated with a tty while the tty is open. Persistent * storage for tty devices is referenced here as @port and is documented in * &struct tty_port. */ struct tty_struct { struct kref kref; int index; struct device *dev; struct tty_driver *driver; struct tty_port *port; const struct tty_operations *ops; struct tty_ldisc *ldisc; struct ld_semaphore ldisc_sem; struct mutex atomic_write_lock; struct mutex legacy_mutex; struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; struct mutex winsize_mutex; struct ktermios termios, termios_locked; char name[64]; unsigned long flags; int count; unsigned int receive_room; struct winsize winsize; struct { spinlock_t lock; bool stopped; bool tco_stopped; unsigned long unused[0]; } __aligned(sizeof(unsigned long)) flow; struct { struct pid *pgrp; struct pid *session; spinlock_t lock; unsigned char pktstatus; bool packet; unsigned long unused[0]; } __aligned(sizeof(unsigned long)) ctrl; bool hw_stopped; bool closing; int flow_change; struct tty_struct *link; struct fasync_struct *fasync; wait_queue_head_t write_wait; wait_queue_head_t read_wait; struct work_struct hangup_work; void *disc_data; void *driver_data; spinlock_t files_lock; int write_cnt; u8 *write_buf; struct list_head tty_files; #define N_TTY_BUF_SIZE 4096 struct work_struct SAK_work; } __randomize_layout; /* Each of a tty's open files has private_data pointing to tty_file_private */ struct tty_file_private { struct tty_struct *tty; struct file *file; struct list_head list; }; /** * DOC: TTY Struct Flags * * These bits are used in the :c:member:`tty_struct.flags` field. * * So that interrupts won't be able to mess up the queues, * copy_to_cooked must be atomic with respect to itself, as must * tty->write. Thus, you must use the inline functions set_bit() and * clear_bit() to make things atomic. * * TTY_THROTTLED * Driver input is throttled. The ldisc should call * :c:member:`tty_driver.unthrottle()` in order to resume reception when * it is ready to process more data (at threshold min). * * TTY_IO_ERROR * If set, causes all subsequent userspace read/write calls on the tty to * fail, returning -%EIO. (May be no ldisc too.) * * TTY_OTHER_CLOSED * Device is a pty and the other side has closed. * * TTY_EXCLUSIVE * Exclusive open mode (a single opener). * * TTY_DO_WRITE_WAKEUP * If set, causes the driver to call the * :c:member:`tty_ldisc_ops.write_wakeup()` method in order to resume * transmission when it can accept more data to transmit. * * TTY_LDISC_OPEN * Indicates that a line discipline is open. For debugging purposes only. * * TTY_PTY_LOCK * A flag private to pty code to implement %TIOCSPTLCK/%TIOCGPTLCK logic. * * TTY_NO_WRITE_SPLIT * Prevent driver from splitting up writes into smaller chunks (preserve * write boundaries to driver). * * TTY_HUPPED * The TTY was hung up. This is set post :c:member:`tty_driver.hangup()`. * * TTY_HUPPING * The TTY is in the process of hanging up to abort potential readers. * * TTY_LDISC_CHANGING * Line discipline for this TTY is being changed. I/O should not block * when this is set. Use tty_io_nonblock() to check. * * TTY_LDISC_HALTED * Line discipline for this TTY was stopped. No work should be queued to * this ldisc. */ #define TTY_THROTTLED 0 #define TTY_IO_ERROR 1 #define TTY_OTHER_CLOSED 2 #define TTY_EXCLUSIVE 3 #define TTY_DO_WRITE_WAKEUP 5 #define TTY_LDISC_OPEN 11 #define TTY_PTY_LOCK 16 #define TTY_NO_WRITE_SPLIT 17 #define TTY_HUPPED 18 #define TTY_HUPPING 19 #define TTY_LDISC_CHANGING 20 #define TTY_LDISC_HALTED 22 static inline bool tty_io_nonblock(struct tty_struct *tty, struct file *file) { return file->f_flags & O_NONBLOCK || test_bit(TTY_LDISC_CHANGING, &tty->flags); } static inline bool tty_io_error(struct tty_struct *tty) { return test_bit(TTY_IO_ERROR, &tty->flags); } static inline bool tty_throttled(struct tty_struct *tty) { return test_bit(TTY_THROTTLED, &tty->flags); } #ifdef CONFIG_TTY void tty_kref_put(struct tty_struct *tty); struct pid *tty_get_pgrp(struct tty_struct *tty); void tty_vhangup_self(void); void disassociate_ctty(int priv); dev_t tty_devnum(struct tty_struct *tty); void proc_clear_tty(struct task_struct *p); struct tty_struct *get_current_tty(void); /* tty_io.c */ int __init tty_init(void); const char *tty_name(const struct tty_struct *tty); struct tty_struct *tty_kopen_exclusive(dev_t device); struct tty_struct *tty_kopen_shared(dev_t device); void tty_kclose(struct tty_struct *tty); int tty_dev_name_to_number(const char *name, dev_t *number); #else static inline void tty_kref_put(struct tty_struct *tty) { } static inline struct pid *tty_get_pgrp(struct tty_struct *tty) { return NULL; } static inline void tty_vhangup_self(void) { } static inline void disassociate_ctty(int priv) { } static inline dev_t tty_devnum(struct tty_struct *tty) { return 0; } static inline void proc_clear_tty(struct task_struct *p) { } static inline struct tty_struct *get_current_tty(void) { return NULL; } /* tty_io.c */ static inline int __init tty_init(void) { return 0; } static inline const char *tty_name(const struct tty_struct *tty) { return "(none)"; } static inline struct tty_struct *tty_kopen_exclusive(dev_t device) { return ERR_PTR(-ENODEV); } static inline void tty_kclose(struct tty_struct *tty) { } static inline int tty_dev_name_to_number(const char *name, dev_t *number) { return -ENOTSUPP; } #endif extern struct ktermios tty_std_termios; int vcs_init(void); extern const struct class tty_class; /** * tty_kref_get - get a tty reference * @tty: tty device * * Returns: a new reference to a tty object * * Locking: The caller must hold sufficient locks/counts to ensure that their * existing reference cannot go away. */ static inline struct tty_struct *tty_kref_get(struct tty_struct *tty) { if (tty) kref_get(&tty->kref); return tty; } const char *tty_driver_name(const struct tty_struct *tty); void tty_wait_until_sent(struct tty_struct *tty, long timeout); void stop_tty(struct tty_struct *tty); void start_tty(struct tty_struct *tty); void tty_write_message(struct tty_struct *tty, char *msg); int tty_send_xchar(struct tty_struct *tty, u8 ch); int tty_put_char(struct tty_struct *tty, u8 c); unsigned int tty_chars_in_buffer(struct tty_struct *tty); unsigned int tty_write_room(struct tty_struct *tty); void tty_driver_flush_buffer(struct tty_struct *tty); void tty_unthrottle(struct tty_struct *tty); bool tty_throttle_safe(struct tty_struct *tty); bool tty_unthrottle_safe(struct tty_struct *tty); int tty_do_resize(struct tty_struct *tty, struct winsize *ws); int tty_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount); int tty_get_tiocm(struct tty_struct *tty); int is_current_pgrp_orphaned(void); void tty_hangup(struct tty_struct *tty); void tty_vhangup(struct tty_struct *tty); int tty_hung_up_p(struct file *filp); void do_SAK(struct tty_struct *tty); void __do_SAK(struct tty_struct *tty); void no_tty(void); speed_t tty_termios_baud_rate(const struct ktermios *termios); void tty_termios_encode_baud_rate(struct ktermios *termios, speed_t ibaud, speed_t obaud); void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud, speed_t obaud); /** * tty_get_baud_rate - get tty bit rates * @tty: tty to query * * Returns: the baud rate as an integer for this terminal * * Locking: The termios lock must be held by the caller. */ static inline speed_t tty_get_baud_rate(const struct tty_struct *tty) { return tty_termios_baud_rate(&tty->termios); } unsigned char tty_get_char_size(unsigned int cflag); unsigned char tty_get_frame_size(unsigned int cflag); void tty_termios_copy_hw(struct ktermios *new, const struct ktermios *old); bool tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); void tty_wakeup(struct tty_struct *tty); int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg); int tty_perform_flush(struct tty_struct *tty, unsigned long arg); struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); void tty_release_struct(struct tty_struct *tty, int idx); void tty_init_termios(struct tty_struct *tty); void tty_save_termios(struct tty_struct *tty); int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty); extern struct mutex tty_mutex; /* n_tty.c */ void n_tty_inherit_ops(struct tty_ldisc_ops *ops); #ifdef CONFIG_TTY void __init n_tty_init(void); #else static inline void n_tty_init(void) { } #endif /* tty_audit.c */ #ifdef CONFIG_AUDIT void tty_audit_exit(void); void tty_audit_fork(struct signal_struct *sig); int tty_audit_push(void); #else static inline void tty_audit_exit(void) { } static inline void tty_audit_fork(struct signal_struct *sig) { } static inline int tty_audit_push(void) { return 0; } #endif /* tty_ioctl.c */ int n_tty_ioctl_helper(struct tty_struct *tty, unsigned int cmd, unsigned long arg); /* vt.c */ int vt_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg); long vt_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg); /* tty_mutex.c */ /* functions for preparation of BKL removal */ void tty_lock(struct tty_struct *tty); int tty_lock_interruptible(struct tty_struct *tty); void tty_unlock(struct tty_struct *tty); void tty_lock_slave(struct tty_struct *tty); void tty_unlock_slave(struct tty_struct *tty); void tty_set_lock_subclass(struct tty_struct *tty); #endif |
| 677 1005 1005 677 1673 7489 6578 1675 1002 677 1673 1674 1675 1675 14 1676 1587 1589 7491 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 | // SPDX-License-Identifier: GPL-2.0 /* * A fast, small, non-recursive O(n log n) sort for the Linux kernel * * This performs n*log2(n) + 0.37*n + o(n) comparisons on average, * and 1.5*n*log2(n) + O(n) in the (very contrived) worst case. * * Glibc qsort() manages n*log2(n) - 1.26*n for random inputs (1.63*n * better) at the expense of stack usage and much larger code to avoid * quicksort's O(n^2) worst case. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/export.h> #include <linux/sort.h> /** * is_aligned - is this pointer & size okay for word-wide copying? * @base: pointer to data * @size: size of each element * @align: required alignment (typically 4 or 8) * * Returns true if elements can be copied using word loads and stores. * The size must be a multiple of the alignment, and the base address must * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS. * * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)" * to "if ((a | b) & mask)", so we do that by hand. */ __attribute_const__ __always_inline static bool is_aligned(const void *base, size_t size, unsigned char align) { unsigned char lsbits = (unsigned char)size; (void)base; #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS lsbits |= (unsigned char)(uintptr_t)base; #endif return (lsbits & (align - 1)) == 0; } /** * swap_words_32 - swap two elements in 32-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 4) * * Exchange the two objects in memory. This exploits base+index addressing, * which basically all CPUs have, to minimize loop overhead computations. * * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the * bottom of the loop, even though the zero flag is still valid from the * subtract (since the intervening mov instructions don't alter the flags). * Gcc 8.1.0 doesn't have that problem. */ static void swap_words_32(void *a, void *b, size_t n) { do { u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; } while (n); } /** * swap_words_64 - swap two elements in 64-bit chunks * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size (must be a multiple of 8) * * Exchange the two objects in memory. This exploits base+index * addressing, which basically all CPUs have, to minimize loop overhead * computations. * * We'd like to use 64-bit loads if possible. If they're not, emulating * one requires base+index+4 addressing which x86 has but most other * processors do not. If CONFIG_64BIT, we definitely have 64-bit loads, * but it's possible to have 64-bit loads without 64-bit pointers (e.g. * x32 ABI). Are there any cases the kernel needs to worry about? */ static void swap_words_64(void *a, void *b, size_t n) { do { #ifdef CONFIG_64BIT u64 t = *(u64 *)(a + (n -= 8)); *(u64 *)(a + n) = *(u64 *)(b + n); *(u64 *)(b + n) = t; #else /* Use two 32-bit transfers to avoid base+index+4 addressing */ u32 t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; t = *(u32 *)(a + (n -= 4)); *(u32 *)(a + n) = *(u32 *)(b + n); *(u32 *)(b + n) = t; #endif } while (n); } /** * swap_bytes - swap two elements a byte at a time * @a: pointer to the first element to swap * @b: pointer to the second element to swap * @n: element size * * This is the fallback if alignment doesn't allow using larger chunks. */ static void swap_bytes(void *a, void *b, size_t n) { do { char t = ((char *)a)[--n]; ((char *)a)[n] = ((char *)b)[n]; ((char *)b)[n] = t; } while (n); } /* * The values are arbitrary as long as they can't be confused with * a pointer, but small integers make for the smallest compare * instructions. */ #define SWAP_WORDS_64 (swap_r_func_t)0 #define SWAP_WORDS_32 (swap_r_func_t)1 #define SWAP_BYTES (swap_r_func_t)2 #define SWAP_WRAPPER (swap_r_func_t)3 struct wrapper { cmp_func_t cmp; swap_func_t swap; }; /* * The function pointer is last to make tail calls most efficient if the * compiler decides not to inline this function. */ static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv) { if (swap_func == SWAP_WRAPPER) { ((const struct wrapper *)priv)->swap(a, b, (int)size); return; } if (swap_func == SWAP_WORDS_64) swap_words_64(a, b, size); else if (swap_func == SWAP_WORDS_32) swap_words_32(a, b, size); else if (swap_func == SWAP_BYTES) swap_bytes(a, b, size); else swap_func(a, b, (int)size, priv); } #define _CMP_WRAPPER ((cmp_r_func_t)0L) static int do_cmp(const void *a, const void *b, cmp_r_func_t cmp, const void *priv) { if (cmp == _CMP_WRAPPER) return ((const struct wrapper *)priv)->cmp(a, b); return cmp(a, b, priv); } /** * parent - given the offset of the child, find the offset of the parent. * @i: the offset of the heap element whose parent is sought. Non-zero. * @lsbit: a precomputed 1-bit mask, equal to "size & -size" * @size: size of each element * * In terms of array indexes, the parent of element j = @i/@size is simply * (j-1)/2. But when working in byte offsets, we can't use implicit * truncation of integer divides. * * Fortunately, we only need one bit of the quotient, not the full divide. * @size has a least significant bit. That bit will be clear if @i is * an even multiple of @size, and set if it's an odd multiple. * * Logically, we're doing "if (i & lsbit) i -= size;", but since the * branch is unpredictable, it's done with a bit of clever branch-free * code instead. */ __attribute_const__ __always_inline static size_t parent(size_t i, unsigned int lsbit, size_t size) { i -= size; i -= size & -(i & lsbit); return i / 2; } /** * sort_r - sort an array of elements * @base: pointer to data to sort * @num: number of elements * @size: size of each element * @cmp_func: pointer to comparison function * @swap_func: pointer to swap function or NULL * @priv: third argument passed to comparison function * * This function does a heapsort on the given array. You may provide * a swap_func function if you need to do something more than a memory * copy (e.g. fix up pointers or auxiliary data), but the built-in swap * avoids a slow retpoline and so is significantly faster. * * Sorting time is O(n log n) both on average and worst-case. While * quicksort is slightly faster on average, it suffers from exploitable * O(n*n) worst-case behavior and extra memory requirements that make * it less suitable for kernel use. */ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, swap_r_func_t swap_func, const void *priv) { /* pre-scale counters for performance */ size_t n = num * size, a = (num/2) * size; const unsigned int lsbit = size & -size; /* Used to find parent */ if (!a) /* num < 2 || size == 0 */ return; /* called from 'sort' without swap function, let's pick the default */ if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap) swap_func = NULL; if (!swap_func) { if (is_aligned(base, size, 8)) swap_func = SWAP_WORDS_64; else if (is_aligned(base, size, 4)) swap_func = SWAP_WORDS_32; else swap_func = SWAP_BYTES; } /* * Loop invariants: * 1. elements [a,n) satisfy the heap property (compare greater than * all of their children), * 2. elements [n,num*size) are sorted, and * 3. a <= b <= c <= d <= n (whenever they are valid). */ for (;;) { size_t b, c, d; if (a) /* Building heap: sift down --a */ a -= size; else if (n -= size) /* Sorting: Extract root to --n */ do_swap(base, base + n, size, swap_func, priv); else /* Sort complete */ break; /* * Sift element at "a" down into heap. This is the * "bottom-up" variant, which significantly reduces * calls to cmp_func(): we find the sift-down path all * the way to the leaves (one compare per level), then * backtrack to find where to insert the target element. * * Because elements tend to sift down close to the leaves, * this uses fewer compares than doing two per level * on the way down. (A bit more than half as many on * average, 3/4 worst-case.) */ for (b = a; c = 2*b + size, (d = c + size) < n;) b = do_cmp(base + c, base + d, cmp_func, priv) >= 0 ? c : d; if (d == n) /* Special case last leaf with no sibling */ b = c; /* Now backtrack from "b" to the correct location for "a" */ while (b != a && do_cmp(base + a, base + b, cmp_func, priv) >= 0) b = parent(b, lsbit, size); c = b; /* Where "a" belongs */ while (b != a) { /* Shift it into place */ b = parent(b, lsbit, size); do_swap(base + b, base + c, size, swap_func, priv); } } } EXPORT_SYMBOL(sort_r); void sort(void *base, size_t num, size_t size, cmp_func_t cmp_func, swap_func_t swap_func) { struct wrapper w = { .cmp = cmp_func, .swap = swap_func, }; return sort_r(base, num, size, _CMP_WRAPPER, SWAP_WRAPPER, &w); } EXPORT_SYMBOL(sort); |
| 4306 8037 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * include/linux/idr.h * * 2002-10-18 written by Jim Houston jim.houston@ccur.com * Copyright (C) 2002 by Concurrent Computer Corporation * * Small id to pointer translation service avoiding fixed sized * tables. */ #ifndef __IDR_H__ #define __IDR_H__ #include <linux/radix-tree.h> #include <linux/gfp.h> #include <linux/percpu.h> struct idr { struct radix_tree_root idr_rt; unsigned int idr_base; unsigned int idr_next; }; /* * The IDR API does not expose the tagging functionality of the radix tree * to users. Use tag 0 to track whether a node has free space below it. */ #define IDR_FREE 0 /* Set the IDR flag and the IDR_FREE tag */ #define IDR_RT_MARKER (ROOT_IS_IDR | (__force gfp_t) \ (1 << (ROOT_TAG_SHIFT + IDR_FREE))) #define IDR_INIT_BASE(name, base) { \ .idr_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER), \ .idr_base = (base), \ .idr_next = 0, \ } /** * IDR_INIT() - Initialise an IDR. * @name: Name of IDR. * * A freshly-initialised IDR contains no IDs. */ #define IDR_INIT(name) IDR_INIT_BASE(name, 0) /** * DEFINE_IDR() - Define a statically-allocated IDR. * @name: Name of IDR. * * An IDR defined using this macro is ready for use with no additional * initialisation required. It contains no IDs. */ #define DEFINE_IDR(name) struct idr name = IDR_INIT(name) /** * idr_get_cursor - Return the current position of the cyclic allocator * @idr: idr handle * * The value returned is the value that will be next returned from * idr_alloc_cyclic() if it is free (otherwise the search will start from * this position). */ static inline unsigned int idr_get_cursor(const struct idr *idr) { return READ_ONCE(idr->idr_next); } /** * idr_set_cursor - Set the current position of the cyclic allocator * @idr: idr handle * @val: new position * * The next call to idr_alloc_cyclic() will return @val if it is free * (otherwise the search will start from this position). */ static inline void idr_set_cursor(struct idr *idr, unsigned int val) { WRITE_ONCE(idr->idr_next, val); } /** * DOC: idr sync * idr synchronization (stolen from radix-tree.h) * * idr_find() is able to be called locklessly, using RCU. The caller must * ensure calls to this function are made within rcu_read_lock() regions. * Other readers (lock-free or otherwise) and modifications may be running * concurrently. * * It is still required that the caller manage the synchronization and * lifetimes of the items. So if RCU lock-free lookups are used, typically * this would mean that the items have their own locks, or are amenable to * lock-free access; and that the items are freed by RCU (or only freed after * having been deleted from the idr tree *and* a synchronize_rcu() grace * period). */ #define idr_lock(idr) xa_lock(&(idr)->idr_rt) #define idr_unlock(idr) xa_unlock(&(idr)->idr_rt) #define idr_lock_bh(idr) xa_lock_bh(&(idr)->idr_rt) #define idr_unlock_bh(idr) xa_unlock_bh(&(idr)->idr_rt) #define idr_lock_irq(idr) xa_lock_irq(&(idr)->idr_rt) #define idr_unlock_irq(idr) xa_unlock_irq(&(idr)->idr_rt) #define idr_lock_irqsave(idr, flags) \ xa_lock_irqsave(&(idr)->idr_rt, flags) #define idr_unlock_irqrestore(idr, flags) \ xa_unlock_irqrestore(&(idr)->idr_rt, flags) void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *, void *ptr, int start, int end, gfp_t); int __must_check idr_alloc_u32(struct idr *, void *ptr, u32 *id, unsigned long max, gfp_t); int idr_alloc_cyclic(struct idr *, void *ptr, int start, int end, gfp_t); void *idr_remove(struct idr *, unsigned long id); void *idr_find(const struct idr *, unsigned long id); int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *, int *nextid); void *idr_get_next_ul(struct idr *, unsigned long *nextid); void *idr_replace(struct idr *, void *, unsigned long id); void idr_destroy(struct idr *); /** * idr_init_base() - Initialise an IDR. * @idr: IDR handle. * @base: The base value for the IDR. * * This variation of idr_init() creates an IDR which will allocate IDs * starting at %base. */ static inline void idr_init_base(struct idr *idr, int base) { INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); idr->idr_base = base; idr->idr_next = 0; } /** * idr_init() - Initialise an IDR. * @idr: IDR handle. * * Initialise a dynamically allocated IDR. To initialise a * statically allocated IDR, use DEFINE_IDR(). */ static inline void idr_init(struct idr *idr) { idr_init_base(idr, 0); } /** * idr_is_empty() - Are there any IDs allocated? * @idr: IDR handle. * * Return: %true if any IDs have been allocated from this IDR. */ static inline bool idr_is_empty(const struct idr *idr) { return radix_tree_empty(&idr->idr_rt) && radix_tree_tagged(&idr->idr_rt, IDR_FREE); } /** * idr_preload_end - end preload section started with idr_preload() * * Each idr_preload() should be matched with an invocation of this * function. See idr_preload() for details. */ static inline void idr_preload_end(void) { local_unlock(&radix_tree_preloads.lock); } /** * idr_for_each_entry() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry(idr, entry, id) \ for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; id += 1U) /** * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor. * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry_ul(idr, entry, tmp, id) \ for (tmp = 0, id = 0; \ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /** * idr_for_each_entry_continue() - Continue iteration over an IDR's elements of a given type * @idr: IDR handle. * @entry: The type * to use as a cursor. * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. */ #define idr_for_each_entry_continue(idr, entry, id) \ for ((entry) = idr_get_next((idr), &(id)); \ entry; \ ++id, (entry) = idr_get_next((idr), &(id))) /** * idr_for_each_entry_continue_ul() - Continue iteration over an IDR's elements of a given type * @idr: IDR handle. * @entry: The type * to use as a cursor. * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. * After normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry_continue_ul(idr, entry, tmp, id) \ for (tmp = id; \ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /* * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ #define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) #define IDA_BITMAP_BITS (IDA_BITMAP_LONGS * sizeof(long) * 8) struct ida_bitmap { unsigned long bitmap[IDA_BITMAP_LONGS]; }; struct ida { struct xarray xa; }; #define IDA_INIT_FLAGS (XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC) #define IDA_INIT(name) { \ .xa = XARRAY_INIT(name, IDA_INIT_FLAGS) \ } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t); void ida_free(struct ida *, unsigned int id); void ida_destroy(struct ida *ida); /** * ida_alloc() - Allocate an unused ID. * @ida: IDA handle. * @gfp: Memory allocation flags. * * Allocate an ID between 0 and %INT_MAX, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc(struct ida *ida, gfp_t gfp) { return ida_alloc_range(ida, 0, ~0, gfp); } /** * ida_alloc_min() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and %INT_MAX, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp) { return ida_alloc_range(ida, min, ~0, gfp); } /** * ida_alloc_max() - Allocate an unused ID. * @ida: IDA handle. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between 0 and @max, inclusive. * * Context: Any context. It is safe to call this function without * locking in your code. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp) { return ida_alloc_range(ida, 0, max, gfp); } static inline void ida_init(struct ida *ida) { xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } /* * ida_simple_get() and ida_simple_remove() are deprecated. Use * ida_alloc() and ida_free() instead respectively. */ #define ida_simple_get(ida, start, end, gfp) \ ida_alloc_range(ida, start, (end) - 1, gfp) #define ida_simple_remove(ida, id) ida_free(ida, id) static inline bool ida_is_empty(const struct ida *ida) { return xa_empty(&ida->xa); } #endif /* __IDR_H__ */ |
| 8603 15058 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2021, Google LLC. * Pasha Tatashin <pasha.tatashin@soleen.com> */ #ifndef __LINUX_PAGE_TABLE_CHECK_H #define __LINUX_PAGE_TABLE_CHECK_H #ifdef CONFIG_PAGE_TABLE_CHECK #include <linux/jump_label.h> extern struct static_key_true page_table_check_disabled; extern struct page_ext_operations page_table_check_ops; void __page_table_check_zero(struct page *page, unsigned int order); void __page_table_check_pte_clear(struct mm_struct *mm, pte_t pte); void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd); void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud); void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr); void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd); void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud); void __page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd); static inline void page_table_check_alloc(struct page *page, unsigned int order) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_zero(page, order); } static inline void page_table_check_free(struct page *page, unsigned int order) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_zero(page, order); } static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pte_clear(mm, pte); } static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pmd_clear(mm, pmd); } static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pud_clear(mm, pud); } static inline void page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_ptes_set(mm, ptep, pte, nr); } static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pmd_set(mm, pmdp, pmd); } static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pud_set(mm, pudp, pud); } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pte_clear_range(mm, addr, pmd); } #else static inline void page_table_check_alloc(struct page *page, unsigned int order) { } static inline void page_table_check_free(struct page *page, unsigned int order) { } static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { } static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { } static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { } static inline void page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { } static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { } static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { } #endif /* CONFIG_PAGE_TABLE_CHECK */ #endif /* __LINUX_PAGE_TABLE_CHECK_H */ |
| 6 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Framework and drivers for configuring and reading different PHYs * Based on code in sungem_phy.c and (long-removed) gianfar_phy.c * * Author: Andy Fleming * * Copyright (c) 2004 Freescale Semiconductor, Inc. */ #ifndef __PHY_H #define __PHY_H #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/ethtool.h> #include <linux/leds.h> #include <linux/linkmode.h> #include <linux/netlink.h> #include <linux/mdio.h> #include <linux/mii.h> #include <linux/mii_timestamper.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/mod_devicetable.h> #include <linux/u64_stats_sync.h> #include <linux/irqreturn.h> #include <linux/iopoll.h> #include <linux/refcount.h> #include <linux/atomic.h> #define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ SUPPORTED_TP | \ SUPPORTED_MII) #define PHY_10BT_FEATURES (SUPPORTED_10baseT_Half | \ SUPPORTED_10baseT_Full) #define PHY_100BT_FEATURES (SUPPORTED_100baseT_Half | \ SUPPORTED_100baseT_Full) #define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ SUPPORTED_1000baseT_Full) extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) #define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) #define PHY_BASIC_T1S_P2MP_FEATURES ((unsigned long *)&phy_basic_t1s_p2mp_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) #define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) #define PHY_EEE_CAP1_FEATURES ((unsigned long *)&phy_eee_cap1_features) extern const int phy_basic_ports_array[3]; extern const int phy_fibre_port_array[1]; extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[3]; extern const int phy_basic_t1s_p2mp_features_array[2]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, * or not desired for this PHY. Set to PHY_MAC_INTERRUPT if * the attached MAC driver handles the interrupt */ #define PHY_POLL -1 #define PHY_MAC_INTERRUPT -2 #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 #define PHY_POLL_CABLE_TEST 0x00000004 #define PHY_ALWAYS_CALL_SUSPEND 0x00000008 #define MDIO_DEVICE_IS_PHY 0x80000000 /** * enum phy_interface_t - Interface Mode definitions * * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined * @PHY_INTERFACE_MODE_MII: Media-independent interface * @PHY_INTERFACE_MODE_GMII: Gigabit media-independent interface * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RTBI: Reduced TBI * @PHY_INTERFACE_MODE_SMII: Serial MII * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax * @PHY_INTERFACE_MODE_PSGMII: Penta SGMII * @PHY_INTERFACE_MODE_QSGMII: Quad SGMII * @PHY_INTERFACE_MODE_TRGMII: Turbo RGMII * @PHY_INTERFACE_MODE_100BASEX: 100 BaseX * @PHY_INTERFACE_MODE_1000BASEX: 1000 BaseX * @PHY_INTERFACE_MODE_2500BASEX: 2500 BaseX * @PHY_INTERFACE_MODE_5GBASER: 5G BaseR * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. */ typedef enum { PHY_INTERFACE_MODE_NA, PHY_INTERFACE_MODE_INTERNAL, PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_SGMII, PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, PHY_INTERFACE_MODE_REVRMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, PHY_INTERFACE_MODE_RGMII_TXID, PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_XLGMII, PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_PSGMII, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_100BASEX, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_5GBASER, PHY_INTERFACE_MODE_RXAUI, PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GBASER, PHY_INTERFACE_MODE_25GBASER, PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_QUSGMII, PHY_INTERFACE_MODE_1000BASEKX, PHY_INTERFACE_MODE_MAX, } phy_interface_t; /* PHY interface mode bitmap handling */ #define DECLARE_PHY_INTERFACE_MASK(name) \ DECLARE_BITMAP(name, PHY_INTERFACE_MODE_MAX) static inline void phy_interface_zero(unsigned long *intf) { bitmap_zero(intf, PHY_INTERFACE_MODE_MAX); } static inline bool phy_interface_empty(const unsigned long *intf) { return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_and(unsigned long *dst, const unsigned long *a, const unsigned long *b) { bitmap_and(dst, a, b, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_or(unsigned long *dst, const unsigned long *a, const unsigned long *b) { bitmap_or(dst, a, b, PHY_INTERFACE_MODE_MAX); } static inline void phy_interface_set_rgmii(unsigned long *intf) { __set_bit(PHY_INTERFACE_MODE_RGMII, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_ID, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, intf); __set_bit(PHY_INTERFACE_MODE_RGMII_TXID, intf); } /* * phy_supported_speeds - return all speeds currently supported by a PHY device */ unsigned int phy_supported_speeds(struct phy_device *phy, unsigned int *speeds, unsigned int size); /** * phy_modes - map phy_interface_t enum to device tree binding of phy-mode * @interface: enum phy_interface_t value * * Description: maps enum &phy_interface_t defined in this file * into the device tree binding of 'phy-mode', so that Ethernet * device driver can get PHY interface from device tree. */ static inline const char *phy_modes(phy_interface_t interface) { switch (interface) { case PHY_INTERFACE_MODE_NA: return ""; case PHY_INTERFACE_MODE_INTERNAL: return "internal"; case PHY_INTERFACE_MODE_MII: return "mii"; case PHY_INTERFACE_MODE_GMII: return "gmii"; case PHY_INTERFACE_MODE_SGMII: return "sgmii"; case PHY_INTERFACE_MODE_TBI: return "tbi"; case PHY_INTERFACE_MODE_REVMII: return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; case PHY_INTERFACE_MODE_REVRMII: return "rev-rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: return "rgmii-id"; case PHY_INTERFACE_MODE_RGMII_RXID: return "rgmii-rxid"; case PHY_INTERFACE_MODE_RGMII_TXID: return "rgmii-txid"; case PHY_INTERFACE_MODE_RTBI: return "rtbi"; case PHY_INTERFACE_MODE_SMII: return "smii"; case PHY_INTERFACE_MODE_XGMII: return "xgmii"; case PHY_INTERFACE_MODE_XLGMII: return "xlgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; case PHY_INTERFACE_MODE_PSGMII: return "psgmii"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: return "trgmii"; case PHY_INTERFACE_MODE_1000BASEX: return "1000base-x"; case PHY_INTERFACE_MODE_1000BASEKX: return "1000base-kx"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; case PHY_INTERFACE_MODE_5GBASER: return "5gbase-r"; case PHY_INTERFACE_MODE_RXAUI: return "rxaui"; case PHY_INTERFACE_MODE_XAUI: return "xaui"; case PHY_INTERFACE_MODE_10GBASER: return "10gbase-r"; case PHY_INTERFACE_MODE_25GBASER: return "25gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; case PHY_INTERFACE_MODE_100BASEX: return "100base-x"; case PHY_INTERFACE_MODE_QUSGMII: return "qusgmii"; default: return "unknown"; } } #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 #define PHY_MAX_ADDR 32 /* Used when trying to connect to a specific phy (mii bus id:phy device id) */ #define PHY_ID_FMT "%s:%02x" #define MII_BUS_ID_SIZE 61 struct device; struct kernel_hwtstamp_config; struct phylink; struct sfp_bus; struct sfp_upstream_ops; struct sk_buff; /** * struct mdio_bus_stats - Statistics counters for MDIO busses * @transfers: Total number of transfers, i.e. @writes + @reads * @errors: Number of MDIO transfers that returned an error * @writes: Number of write transfers * @reads: Number of read transfers * @syncp: Synchronisation for incrementing statistics */ struct mdio_bus_stats { u64_stats_t transfers; u64_stats_t errors; u64_stats_t writes; u64_stats_t reads; /* Must be last, add new statistics above */ struct u64_stats_sync syncp; }; /** * struct phy_package_shared - Shared information in PHY packages * @base_addr: Base PHY address of PHY package used to combine PHYs * in one package and for offset calculation of phy_package_read/write * @refcnt: Number of PHYs connected to this shared data * @flags: Initialization of PHY package * @priv_size: Size of the shared private data @priv * @priv: Driver private data shared across a PHY package * * Represents a shared structure between different phydev's in the same * package, for example a quad PHY. See phy_package_join() and * phy_package_leave(). */ struct phy_package_shared { u8 base_addr; refcount_t refcnt; unsigned long flags; size_t priv_size; /* private data pointer */ /* note that this pointer is shared between different phydevs and * the user has to take care of appropriate locking. It is allocated * and freed automatically by phy_package_join() and * phy_package_leave(). */ void *priv; }; /* used as bit number in atomic bitops */ #define PHY_SHARED_F_INIT_DONE 0 #define PHY_SHARED_F_PROBE_DONE 1 /** * struct mii_bus - Represents an MDIO bus * * @owner: Who owns this device * @name: User friendly name for this MDIO device, or driver name * @id: Unique identifier for this bus, typical from bus hierarchy * @priv: Driver private data * * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure */ struct mii_bus { struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; /** @read: Perform a read transfer on the bus */ int (*read)(struct mii_bus *bus, int addr, int regnum); /** @write: Perform a write transfer on the bus */ int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); /** @read_c45: Perform a C45 read transfer on the bus */ int (*read_c45)(struct mii_bus *bus, int addr, int devnum, int regnum); /** @write_c45: Perform a C45 write transfer on the bus */ int (*write_c45)(struct mii_bus *bus, int addr, int devnum, int regnum, u16 val); /** @reset: Perform a reset of the bus */ int (*reset)(struct mii_bus *bus); /** @stats: Statistic counters per device on the bus */ struct mdio_bus_stats stats[PHY_MAX_ADDR]; /** * @mdio_lock: A lock to ensure that only one thing can read/write * the MDIO bus at a time */ struct mutex mdio_lock; /** @parent: Parent device of this bus */ struct device *parent; /** @state: State of bus structure */ enum { MDIOBUS_ALLOCATED = 1, MDIOBUS_REGISTERED, MDIOBUS_UNREGISTERED, MDIOBUS_RELEASED, } state; /** @dev: Kernel device representation */ struct device dev; /** @mdio_map: list of all MDIO devices on bus */ struct mdio_device *mdio_map[PHY_MAX_ADDR]; /** @phy_mask: PHY addresses to be ignored when probing */ u32 phy_mask; /** @phy_ignore_ta_mask: PHY addresses to ignore the TA/read failure */ u32 phy_ignore_ta_mask; /** * @irq: An array of interrupts, each PHY's interrupt at the index * matching its address */ int irq[PHY_MAX_ADDR]; /** @reset_delay_us: GPIO reset pulse width in microseconds */ int reset_delay_us; /** @reset_post_delay_us: GPIO reset deassert delay in microseconds */ int reset_post_delay_us; /** @reset_gpiod: Reset GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; /** @shared_lock: protect access to the shared element */ struct mutex shared_lock; /** @shared: shared state across different PHYs */ struct phy_package_shared *shared[PHY_MAX_ADDR]; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) struct mii_bus *mdiobus_alloc_size(size_t size); /** * mdiobus_alloc - Allocate an MDIO bus structure * * The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready * for the driver to register the bus. */ static inline struct mii_bus *mdiobus_alloc(void) { return mdiobus_alloc_size(0); } int __mdiobus_register(struct mii_bus *bus, struct module *owner); int __devm_mdiobus_register(struct device *dev, struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) #define devm_mdiobus_register(dev, bus) \ __devm_mdiobus_register(dev, bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) { return devm_mdiobus_alloc_size(dev, 0); } struct mii_bus *mdio_find_bus(const char *mdio_name); struct phy_device *mdiobus_scan_c22(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false #define PHY_INTERRUPT_ENABLED true /** * enum phy_state - PHY state machine states: * * @PHY_DOWN: PHY device and driver are not ready for anything. probe * should be called if and only if the PHY is in this state, * given that the PHY device exists. * - PHY driver probe function will set the state to @PHY_READY * * @PHY_READY: PHY is ready to send and receive packets, but the * controller is not. By default, PHYs which do not implement * probe will be set to this state by phy_probe(). * - start will set the state to UP * * @PHY_UP: The PHY and attached device are ready to do work. * Interrupts should be started here. * - timer moves to @PHY_NOLINK or @PHY_RUNNING * * @PHY_NOLINK: PHY is up, but not currently plugged in. * - irq or timer will set @PHY_RUNNING if link comes back * - phy_stop moves to @PHY_HALTED * * @PHY_RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets * - irq or timer will set @PHY_NOLINK if link goes down * - phy_stop moves to @PHY_HALTED * * @PHY_CABLETEST: PHY is performing a cable test. Packet reception/sending * is not expected to work, carrier will be indicated as down. PHY will be * poll once per second, or on interrupt for it current state. * Once complete, move to UP to restart the PHY. * - phy_stop aborts the running test and moves to @PHY_HALTED * * @PHY_HALTED: PHY is up, but no polling or interrupts are done. * - phy_start moves to @PHY_UP * * @PHY_ERROR: PHY is up, but is in an error state. * - phy_stop moves to @PHY_HALTED */ enum phy_state { PHY_DOWN = 0, PHY_READY, PHY_HALTED, PHY_ERROR, PHY_UP, PHY_RUNNING, PHY_NOLINK, PHY_CABLETEST, }; #define MDIO_MMD_NUM 32 /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers * @devices_in_package: IEEE 802.3 devices in package register value. * @mmds_present: bit vector of MMDs present. * @device_ids: The device identifer for each present device. */ struct phy_c45_device_ids { u32 devices_in_package; u32 mmds_present; u32 device_ids[MDIO_MMD_NUM]; }; struct macsec_context; struct macsec_ops; /** * struct phy_device - An instance of a PHY * * @mdio: MDIO bus this PHY is on * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. * @is_internal: Set to true if this PHY is internal to a MAC. * @is_pseudo_fixed_link: Set to true if this PHY is an Ethernet switch, etc. * @is_gigabit_capable: Set to true if PHY supports 1000Mbps * @has_fixups: Set to true if this PHY has fixups/quirks. * @suspended: Set to true if this PHY has been suspended successfully. * @suspended_by_mdio_bus: Set to true if this PHY was suspended by MDIO bus. * @sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * @loopback_enabled: Set true if this PHY has been loopbacked successfully. * @downshifted_rate: Set true if link speed has been downshifted. * @is_on_sfp_module: Set true if PHY is located on an SFP module. * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @wol_enabled: Set to true if the PHY or the attached MAC have Wake-on-LAN * enabled. * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. * * - Bits [15:0] are free to use by the PHY driver to communicate * driver specific behavior. * - Bits [23:16] are currently reserved for future use. * - Bits [31:24] are reserved for defining generic * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phylink: Pointer to phylink instance for this PHY * @sfp_bus_attached: Flag indicating whether the SFP bus has been attached * @sfp_bus: SFP bus attached to this PHY's fiber port * @attached_dev: The attached enet driver's device instance ptr * @adjust_link: Callback for the enet controller to respond to changes: in the * link state. * @phy_link_change: Callback for phylink for notification of link change * @macsec_ops: MACsec offloading ops. * * @speed: Current link speed * @duplex: Current duplex * @port: Current port * @pause: Current pause * @asym_pause: Current asymmetric pause * @supported: Combined MAC/PHY supported linkmodes * @advertising: Currently advertised linkmodes * @adv_old: Saved advertised while power saving for WoL * @supported_eee: supported PHY EEE linkmodes * @advertising_eee: Currently advertised EEE linkmodes * @eee_enabled: Flag indicating whether the EEE feature is enabled * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited * @autoneg: Flag autoneg being used * @rate_matching: Current rate matching mode * @link: Current link state * @autoneg_complete: Flag auto negotiation of the link has completed * @mdix: Current crossover * @mdix_ctrl: User setting of crossover * @pma_extable: Cached value of PMA/PMD Extended Abilities Register * @interrupts: Flag interrupts have been enabled * @irq_suspended: Flag indicating PHY is suspended and therefore interrupt * handling shall be postponed until PHY has resumed * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume * @interface: enum phy_interface_t value * @possible_interfaces: bitmap if interface modes that the attached PHY * will switch between depending on media speed. * @skb: Netlink message for cable diagnostics * @nest: Netlink nest used for cable diagnostics * @ehdr: nNtlink header for cable diagnostics * @phy_led_triggers: Array of LED triggers * @phy_num_led_triggers: Number of triggers in @phy_led_triggers * @led_link_trigger: LED trigger for link up/down * @last_triggered: last LED trigger for link speed * @leds: list of PHY LED structures * @master_slave_set: User requested master/slave configuration * @master_slave_get: Current master/slave advertisement * @master_slave_state: Current master/slave configuration * @mii_ts: Pointer to time stamper callbacks * @psec: Pointer to Power Sourcing Equipment control struct * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine * @link_down_events: Number of times link was lost * @shared: Pointer to private data shared by phys in one package * @priv: Pointer to driver private data * * interrupts currently only supports enabled or disabled, * but could be changed in the future to support enabling * and disabling specific interrupts * * Contains some infrastructure for polling and interrupt * handling, as well as handling shifts in PHY hardware state */ struct phy_device { struct mdio_device mdio; /* Information about the PHY type */ /* And management functions */ struct phy_driver *drv; struct device_link *devlink; u32 phy_id; struct phy_c45_device_ids c45_ids; unsigned is_c45:1; unsigned is_internal:1; unsigned is_pseudo_fixed_link:1; unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; unsigned downshifted_rate:1; unsigned is_on_sfp_module:1; unsigned mac_managed_pm:1; unsigned wol_enabled:1; unsigned autoneg:1; /* The most recently read link state */ unsigned link:1; unsigned autoneg_complete:1; /* Interrupts are enabled */ unsigned interrupts:1; unsigned irq_suspended:1; unsigned irq_rerun:1; int rate_matching; enum phy_state state; u32 dev_flags; phy_interface_t interface; DECLARE_PHY_INTERFACE_MASK(possible_interfaces); /* * forced speed & duplex (no autoneg) * partner speed & duplex & pause (autoneg) */ int speed; int duplex; int port; int pause; int asym_pause; u8 master_slave_get; u8 master_slave_set; u8 master_slave_state; /* Union of PHY and Attached devices' supported link modes */ /* See ethtool.h for more info */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* used for eee validation */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee); bool eee_enabled; /* Host supported PHY interface types. Should be ignored if empty. */ DECLARE_PHY_INTERFACE_MASK(host_interfaces); /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; struct phy_led_trigger *last_triggered; struct phy_led_trigger *led_link_trigger; #endif struct list_head leds; /* * Interrupt number for this PHY * -1 means no interrupt */ int irq; /* private data pointer */ /* For use by PHYs to maintain extra state */ void *priv; /* shared data pointer */ /* For use by PHYs inside the same package that need a shared state. */ struct phy_package_shared *shared; /* Reporting cable test results */ struct sk_buff *skb; void *ehdr; struct nlattr *nest; /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; struct mutex lock; /* This may be modified under the rtnl lock */ bool sfp_bus_attached; struct sfp_bus *sfp_bus; struct phylink *phylink; struct net_device *attached_dev; struct mii_timestamper *mii_ts; struct pse_control *psec; u8 mdix; u8 mdix_ctrl; int pma_extable; unsigned int link_down_events; void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); #if IS_ENABLED(CONFIG_MACSEC) /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif }; /* Generic phy_device::dev_flags */ #define PHY_F_NO_IRQ 0x80000000 static inline struct phy_device *to_phy_device(const struct device *dev) { return container_of(to_mdio_device(dev), struct phy_device, mdio); } /** * struct phy_tdr_config - Configuration of a TDR raw test * * @first: Distance for first data collection point * @last: Distance for last data collection point * @step: Step between data collection points * @pair: Bitmap of cable pairs to collect data for * * A structure containing possible configuration parameters * for a TDR cable test. The driver does not need to implement * all the parameters, but should report what is actually used. * All distances are in centimeters. */ struct phy_tdr_config { u32 first; u32 last; u32 step; s8 pair; }; #define PHY_PAIR_ALL -1 /** * struct phy_plca_cfg - Configuration of the PLCA (Physical Layer Collision * Avoidance) Reconciliation Sublayer. * * @version: read-only PLCA register map version. -1 = not available. Ignored * when setting the configuration. Format is the same as reported by the PLCA * IDVER register (31.CA00). -1 = not available. * @enabled: PLCA configured mode (enabled/disabled). -1 = not available / don't * set. 0 = disabled, anything else = enabled. * @node_id: the PLCA local node identifier. -1 = not available / don't set. * Allowed values [0 .. 254]. 255 = node disabled. * @node_cnt: the PLCA node count (maximum number of nodes having a TO). Only * meaningful for the coordinator (node_id = 0). -1 = not available / don't * set. Allowed values [1 .. 255]. * @to_tmr: The value of the PLCA to_timer in bit-times, which determines the * PLCA transmit opportunity window opening. See IEEE802.3 Clause 148 for * more details. The to_timer shall be set equal over all nodes. * -1 = not available / don't set. Allowed values [0 .. 255]. * @burst_cnt: controls how many additional frames a node is allowed to send in * single transmit opportunity (TO). The default value of 0 means that the * node is allowed exactly one frame per TO. A value of 1 allows two frames * per TO, and so on. -1 = not available / don't set. * Allowed values [0 .. 255]. * @burst_tmr: controls how many bit times to wait for the MAC to send a new * frame before interrupting the burst. This value should be set to a value * greater than the MAC inter-packet gap (which is typically 96 bits). * -1 = not available / don't set. Allowed values [0 .. 255]. * * A structure containing configuration parameters for setting/getting the PLCA * RS configuration. The driver does not need to implement all the parameters, * but should report what is actually used. */ struct phy_plca_cfg { int version; int enabled; int node_id; int node_cnt; int to_tmr; int burst_cnt; int burst_tmr; }; /** * struct phy_plca_status - Status of the PLCA (Physical Layer Collision * Avoidance) Reconciliation Sublayer. * * @pst: The PLCA status as reported by the PST bit in the PLCA STATUS * register(31.CA03), indicating BEACON activity. * * A structure containing status information of the PLCA RS configuration. * The driver does not need to implement all the parameters, but should report * what is actually used. */ struct phy_plca_status { bool pst; }; /** * struct phy_led: An LED driven by the PHY * * @list: List of LEDs * @phydev: PHY this LED is attached to * @led_cdev: Standard LED class structure * @index: Number of the LED */ struct phy_led { struct list_head list; struct phy_device *phydev; struct led_classdev led_cdev; u8 index; }; #define to_phy_led(d) container_of(d, struct phy_led, led_cdev) /** * struct phy_driver - Driver structure for a particular PHY type * * @mdiodrv: Data common to all MDIO devices * @phy_id: The result of reading the UID registers of this PHY * type, and ANDing them with the phy_id_mask. This driver * only works for PHYs with IDs which match this field * @name: The friendly name of this PHY type * @phy_id_mask: Defines the important bits of the phy_id * @features: A mandatory list of features (speed, duplex, etc) * supported by this PHY * @flags: A bitfield defining certain other features this PHY * supports (like interrupts) * @driver_data: Static driver data * * All functions are optional. If config_aneg or read_status * are not implemented, the phy core uses the genphy versions. * Note that none of these functions should be called from * interrupt time. The goal is for the bus read/write functions * to be able to block when the bus transaction is happening, * and be freed up by an interrupt (The MPC85xx has this ability, * though it is not currently supported in the driver). */ struct phy_driver { struct mdio_driver_common mdiodrv; u32 phy_id; char *name; u32 phy_id_mask; const unsigned long * const features; u32 flags; const void *driver_data; /** * @soft_reset: Called to issue a PHY software reset */ int (*soft_reset)(struct phy_device *phydev); /** * @config_init: Called to initialize the PHY, * including after a reset */ int (*config_init)(struct phy_device *phydev); /** * @probe: Called during discovery. Used to set * up device-specific structures, if any */ int (*probe)(struct phy_device *phydev); /** * @get_features: Probe the hardware to determine what * abilities it has. Should only set phydev->supported. */ int (*get_features)(struct phy_device *phydev); /** * @get_rate_matching: Get the supported type of rate matching for a * particular phy interface. This is used by phy consumers to determine * whether to advertise lower-speed modes for that interface. It is * assumed that if a rate matching mode is supported on an interface, * then that interface's rate can be adapted to all slower link speeds * supported by the phy. If the interface is not supported, this should * return %RATE_MATCH_NONE. */ int (*get_rate_matching)(struct phy_device *phydev, phy_interface_t iface); /* PHY Power Management */ /** @suspend: Suspend the hardware, saving state if needed */ int (*suspend)(struct phy_device *phydev); /** @resume: Resume the hardware, restoring state if needed */ int (*resume)(struct phy_device *phydev); /** * @config_aneg: Configures the advertisement and resets * autonegotiation if phydev->autoneg is on, * forces the speed to the current settings in phydev * if phydev->autoneg is off */ int (*config_aneg)(struct phy_device *phydev); /** @aneg_done: Determines the auto negotiation result */ int (*aneg_done)(struct phy_device *phydev); /** @read_status: Determines the negotiated speed and duplex */ int (*read_status)(struct phy_device *phydev); /** * @config_intr: Enables or disables interrupts. * It should also clear any pending interrupts prior to enabling the * IRQs and after disabling them. */ int (*config_intr)(struct phy_device *phydev); /** @handle_interrupt: Override default interrupt handling */ irqreturn_t (*handle_interrupt)(struct phy_device *phydev); /** @remove: Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); /** * @match_phy_device: Returns true if this is a suitable * driver for the given phydev. If NULL, matching is based on * phy_id and phy_id_mask. */ int (*match_phy_device)(struct phy_device *phydev); /** * @set_wol: Some devices (e.g. qnap TS-119P II) require PHY * register changes to enable Wake on LAN, so set_wol is * provided to be called in the ethernet driver's set_wol * function. */ int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /** * @get_wol: See set_wol, but for checking whether Wake on LAN * is enabled. */ void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /** * @link_change_notify: Called to inform a PHY device driver * when the core is about to change the link state. This * callback is supposed to be used as fixup hook for drivers * that need to take action when the link state * changes. Drivers are by no means allowed to mess with the * PHY device structure in their implementations. */ void (*link_change_notify)(struct phy_device *dev); /** * @read_mmd: PHY specific driver override for reading a MMD * register. This function is optional for PHY specific * drivers. When not provided, the default MMD read function * will be used by phy_read_mmd(), which will use either a * direct read for Clause 45 PHYs or an indirect read for * Clause 22 PHYs. devnum is the MMD device number within the * PHY device, regnum is the register within the selected MMD * device. */ int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum); /** * @write_mmd: PHY specific driver override for writing a MMD * register. This function is optional for PHY specific * drivers. When not provided, the default MMD write function * will be used by phy_write_mmd(), which will use either a * direct write for Clause 45 PHYs, or an indirect write for * Clause 22 PHYs. devnum is the MMD device number within the * PHY device, regnum is the register within the selected MMD * device. val is the value to be written. */ int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum, u16 val); /** @read_page: Return the current PHY register page number */ int (*read_page)(struct phy_device *dev); /** @write_page: Set the current PHY register page number */ int (*write_page)(struct phy_device *dev, int page); /** * @module_info: Get the size and type of the eeprom contained * within a plug-in module */ int (*module_info)(struct phy_device *dev, struct ethtool_modinfo *modinfo); /** * @module_eeprom: Get the eeprom information from the plug-in * module */ int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); /** @cable_test_start: Start a cable test */ int (*cable_test_start)(struct phy_device *dev); /** @cable_test_tdr_start: Start a raw TDR cable test */ int (*cable_test_tdr_start)(struct phy_device *dev, const struct phy_tdr_config *config); /** * @cable_test_get_status: Once per second, or on interrupt, * request the status of the test. */ int (*cable_test_get_status)(struct phy_device *dev, bool *finished); /* Get statistics from the PHY using ethtool */ /** @get_sset_count: Number of statistic counters */ int (*get_sset_count)(struct phy_device *dev); /** @get_strings: Names of the statistic counters */ void (*get_strings)(struct phy_device *dev, u8 *data); /** @get_stats: Return the statistic counter values */ void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); /* Get and Set PHY tunables */ /** @get_tunable: Return the value of a tunable */ int (*get_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, void *data); /** @set_tunable: Set the value of a tunable */ int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); /** @set_loopback: Set the loopback mood of the PHY */ int (*set_loopback)(struct phy_device *dev, bool enable); /** @get_sqi: Get the signal quality indication */ int (*get_sqi)(struct phy_device *dev); /** @get_sqi_max: Get the maximum signal quality indication */ int (*get_sqi_max)(struct phy_device *dev); /* PLCA RS interface */ /** @get_plca_cfg: Return the current PLCA configuration */ int (*get_plca_cfg)(struct phy_device *dev, struct phy_plca_cfg *plca_cfg); /** @set_plca_cfg: Set the PLCA configuration */ int (*set_plca_cfg)(struct phy_device *dev, const struct phy_plca_cfg *plca_cfg); /** @get_plca_status: Return the current PLCA status info */ int (*get_plca_status)(struct phy_device *dev, struct phy_plca_status *plca_st); /** * @led_brightness_set: Set a PHY LED brightness. Index * indicates which of the PHYs led should be set. Value * follows the standard LED class meaning, e.g. LED_OFF, * LED_HALF, LED_FULL. */ int (*led_brightness_set)(struct phy_device *dev, u8 index, enum led_brightness value); /** * @led_blink_set: Set a PHY LED brightness. Index indicates * which of the PHYs led should be configured to blink. Delays * are in milliseconds and if both are zero then a sensible * default should be chosen. The call should adjust the * timings in that case and if it can't match the values * specified exactly. */ int (*led_blink_set)(struct phy_device *dev, u8 index, unsigned long *delay_on, unsigned long *delay_off); /** * @led_hw_is_supported: Can the HW support the given rules. * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules The core is interested in these rules * * Return 0 if yes, -EOPNOTSUPP if not, or an error code. */ int (*led_hw_is_supported)(struct phy_device *dev, u8 index, unsigned long rules); /** * @led_hw_control_set: Set the HW to control the LED * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules The rules used to control the LED * * Returns 0, or a an error code. */ int (*led_hw_control_set)(struct phy_device *dev, u8 index, unsigned long rules); /** * @led_hw_control_get: Get how the HW is controlling the LED * @dev: PHY device which has the LED * @index: Which LED of the PHY device * @rules Pointer to the rules used to control the LED * * Set *@rules to how the HW is currently blinking. Returns 0 * on success, or a error code if the current blinking cannot * be represented in rules, or some other error happens. */ int (*led_hw_control_get)(struct phy_device *dev, u8 index, unsigned long *rules); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) #define PHY_ANY_ID "MATCH ANY PHY" #define PHY_ANY_UID 0xffffffff #define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0) #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) /** * phy_id_compare - compare @id1 with @id2 taking account of @mask * @id1: first PHY ID * @id2: second PHY ID * @mask: the PHY ID mask, set bits are significant in matching * * Return true if the bits from @id1 and @id2 specified by @mask match. * This uses an equivalent test to (@id & @mask) == (@phy_id & @mask). */ static inline bool phy_id_compare(u32 id1, u32 id2, u32 mask) { return !((id1 ^ id2) & mask); } /** * phydev_id_compare - compare @id with the PHY's Clause 22 ID * @phydev: the PHY device * @id: the PHY ID to be matched * * Compare the @phydev clause 22 ID with the provided @id and return true or * false depending whether it matches, using the bound driver mask. The * @phydev must be bound to a driver. */ static inline bool phydev_id_compare(struct phy_device *phydev, u32 id) { return phy_id_compare(id, phydev->phy_id, phydev->drv->phy_id_mask); } /* A Structure for boards to register fixups with the PHY Lib */ struct phy_fixup { struct list_head list; char bus_id[MII_BUS_ID_SIZE + 3]; u32 phy_uid; u32 phy_uid_mask; int (*run)(struct phy_device *phydev); }; const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); const char *phy_rate_matching_to_str(int rate_matching); int phy_interface_num_ports(phy_interface_t interface); /* A structure for mapping a particular speed and duplex * combination to a particular SUPPORTED and ADVERTISED value */ struct phy_setting { u32 speed; u8 duplex; u8 bit; }; const struct phy_setting * phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact); size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); void of_set_phy_supported(struct phy_device *phydev); void of_set_phy_eee_broken(struct phy_device *phydev); int phy_speed_down_core(struct phy_device *phydev); /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ static inline bool phy_is_started(struct phy_device *phydev) { return phydev->state >= PHY_UP; } void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); void phy_check_downshift(struct phy_device *phydev); /** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_read(struct phy_device *phydev, u32 regnum) { return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } #define phy_read_poll_timeout(phydev, regnum, val, cond, sleep_us, \ timeout_us, sleep_before_read) \ ({ \ int __ret, __val; \ __ret = read_poll_timeout(__val = phy_read, val, \ __val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, phydev, regnum); \ if (__val < 0) \ __ret = __val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) /** * __phy_read - convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * The caller must have taken the MDIO bus lock. */ static inline int __phy_read(struct phy_device *phydev, u32 regnum) { return __mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } /** * phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * The caller must have taken the MDIO bus lock. */ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return __mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_modify_changed() - Convenience function for modifying a PHY register * @phydev: a pointer to a &struct phy_device * @regnum: register number * @mask: bit mask of bits to clear * @set: bit mask of bits to set * * Unlocked helper function which allows a PHY register to be modified as * new register value = (old register value & ~mask) | set * * Returns negative errno, 0 if there was no change, and 1 in case of change */ static inline int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) { return __mdiobus_modify_changed(phydev->mdio.bus, phydev->mdio.addr, regnum, mask, set); } /* * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /** * phy_read_mmd_poll_timeout - Periodically poll a PHY register until a * condition is met or a timeout occurs * * @phydev: The phy_device struct * @devaddr: The MMD to read from * @regnum: The register on the MMD to read * @val: Variable to read the register into * @cond: Break condition (usually involving @val) * @sleep_us: Maximum time to sleep between reads in us (0 * tight-loops). Should be less than ~20ms since usleep_range * is used (see Documentation/timers/timers-howto.rst). * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. * Returns 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. */ #define phy_read_mmd_poll_timeout(phydev, devaddr, regnum, val, cond, \ sleep_us, timeout_us, sleep_before_read) \ ({ \ int __ret, __val; \ __ret = read_poll_timeout(__val = phy_read_mmd, val, \ __val < 0 || (cond), \ sleep_us, timeout_us, sleep_before_read, \ phydev, devaddr, regnum); \ if (__val < 0) \ __ret = __val; \ if (__ret) \ phydev_err(phydev, "%s failed: %d\n", __func__, __ret); \ __ret; \ }) /* * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. */ int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /* * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. */ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); /* * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. */ int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); /** * __phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, 0, val); } /** * __phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, val, 0); } /** * phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set */ static inline int phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, 0, val); } /** * phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear */ static inline int phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, val, 0); } /** * __phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * __phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set */ static inline int phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear */ static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_interrupt_is_valid - Convenience function for testing a given PHY irq * @phydev: the phy_device struct * * NOTE: must be kept in sync with addition/removal of PHY_POLL and * PHY_MAC_INTERRUPT */ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) { return phydev->irq != PHY_POLL && phydev->irq != PHY_MAC_INTERRUPT; } /** * phy_polling_mode - Convenience function for testing whether polling is * used to detect PHY status changes * @phydev: the phy_device struct */ static inline bool phy_polling_mode(struct phy_device *phydev) { if (phydev->state == PHY_CABLETEST) if (phydev->drv->flags & PHY_POLL_CABLE_TEST) return true; return phydev->irq == PHY_POLL; } /** * phy_has_hwtstamp - Tests whether a PHY time stamp configuration. * @phydev: the phy_device struct */ static inline bool phy_has_hwtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->hwtstamp; } /** * phy_has_rxtstamp - Tests whether a PHY supports receive time stamping. * @phydev: the phy_device struct */ static inline bool phy_has_rxtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->rxtstamp; } /** * phy_has_tsinfo - Tests whether a PHY reports time stamping and/or * PTP hardware clock capabilities. * @phydev: the phy_device struct */ static inline bool phy_has_tsinfo(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->ts_info; } /** * phy_has_txtstamp - Tests whether a PHY supports transmit time stamping. * @phydev: the phy_device struct */ static inline bool phy_has_txtstamp(struct phy_device *phydev) { return phydev && phydev->mii_ts && phydev->mii_ts->txtstamp; } static inline int phy_hwtstamp(struct phy_device *phydev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { return phydev->mii_ts->hwtstamp(phydev->mii_ts, cfg, extack); } static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { return phydev->mii_ts->rxtstamp(phydev->mii_ts, skb, type); } static inline int phy_ts_info(struct phy_device *phydev, struct ethtool_ts_info *tsinfo) { return phydev->mii_ts->ts_info(phydev->mii_ts, tsinfo); } static inline void phy_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { phydev->mii_ts->txtstamp(phydev->mii_ts, skb, type); } /** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct */ static inline bool phy_is_internal(struct phy_device *phydev) { return phydev->is_internal; } /** * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module * @phydev: the phy_device struct */ static inline bool phy_on_sfp(struct phy_device *phydev) { return phydev->is_on_sfp_module; } /** * phy_interface_mode_is_rgmii - Convenience function for testing if a * PHY interface mode is RGMII (all variants) * @mode: the &phy_interface_t enum */ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) { return mode >= PHY_INTERFACE_MODE_RGMII && mode <= PHY_INTERFACE_MODE_RGMII_TXID; }; /** * phy_interface_mode_is_8023z() - does the PHY interface mode use 802.3z * negotiation * @mode: one of &enum phy_interface_t * * Returns true if the PHY interface mode uses the 16-bit negotiation * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding) */ static inline bool phy_interface_mode_is_8023z(phy_interface_t mode) { return mode == PHY_INTERFACE_MODE_1000BASEX || mode == PHY_INTERFACE_MODE_2500BASEX; } /** * phy_interface_is_rgmii - Convenience function for testing if a PHY interface * is RGMII (all variants) * @phydev: the phy_device struct */ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) { return phy_interface_mode_is_rgmii(phydev->interface); }; /** * phy_is_pseudo_fixed_link - Convenience function for testing if this * PHY is the CPU port facing side of an Ethernet switch, or similar. * @phydev: the phy_device struct */ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) { return phydev->is_pseudo_fixed_link; } int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); int phy_read_paged(struct phy_device *phydev, int page, u32 regnum); int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val); int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) { return 0; } static inline struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) { return 0; } static inline struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) { return NULL; } static inline struct phy_device *device_phy_find_device(struct device *dev) { return NULL; } static inline struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) { return NULL; } static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { return NULL; } static inline int phy_device_register(struct phy_device *phy) { return 0; } static inline void phy_device_free(struct phy_device *phydev) { } #endif /* CONFIG_PHYLIB */ void phy_device_remove(struct phy_device *phydev); int phy_get_c45_ids(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); void phy_sfp_attach(void *upstream, struct sfp_bus *bus); void phy_sfp_detach(void *upstream, struct sfp_bus *bus); int phy_sfp_probe(struct phy_device *phydev, const struct sfp_upstream_ops *ops); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), phy_interface_t interface); struct phy_device *phy_connect(struct net_device *dev, const char *bus_id, void (*handler)(struct net_device *), phy_interface_t interface); void phy_disconnect(struct phy_device *phydev); void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_config_aneg(struct phy_device *phydev); int _phy_start_aneg(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); int phy_speed_down(struct phy_device *phydev, bool sync); int phy_speed_up(struct phy_device *phydev); bool phy_check_valid(int speed, int duplex, unsigned long *features); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); #if IS_ENABLED(CONFIG_PHYLIB) int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); int phy_start_cable_test_tdr(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config); #else static inline int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } static inline int phy_start_cable_test_tdr(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config) { NL_SET_ERR_MSG(extack, "Kernel not compiled with PHYLIB support"); return -EOPNOTSUPP; } #endif static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); } #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) #define phydev_err_probe(_phydev, err, format, args...) \ dev_err_probe(&_phydev->mdio.dev, err, format, ##args) #define phydev_info(_phydev, format, args...) \ dev_info(&_phydev->mdio.dev, format, ##args) #define phydev_warn(_phydev, format, args...) \ dev_warn(&_phydev->mdio.dev, format, ##args) #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->mdio.dev, format, ##args) static inline const char *phydev_name(const struct phy_device *phydev) { return dev_name(&phydev->mdio.dev); } static inline void phy_lock_mdio_bus(struct phy_device *phydev) { mutex_lock(&phydev->mdio.bus->mdio_lock); } static inline void phy_unlock_mdio_bus(struct phy_device *phydev) { mutex_unlock(&phydev->mdio.bus->mdio_lock); } void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); char *phy_attached_info_irq(struct phy_device *phydev) __malloc; void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_check_and_restart_aneg(struct phy_device *phydev, bool restart); int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status_fixed(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_read_master_slave(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev); static inline int genphy_config_aneg(struct phy_device *phydev) { return __genphy_config_aneg(phydev, false); } static inline int genphy_no_config_intr(struct phy_device *phydev) { return 0; } int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum); int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, u16 regnum, u16 val); /* Clause 37 */ int genphy_c37_config_aneg(struct phy_device *phydev); int genphy_c37_read_status(struct phy_device *phydev); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart); int genphy_c45_aneg_done(struct phy_device *phydev); int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); int genphy_c45_pma_baset1_setup_master_slave(struct phy_device *phydev); int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev); int genphy_c45_read_eee_abilities(struct phy_device *phydev); int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_baset1_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); int genphy_c45_pma_resume(struct phy_device *phydev); int genphy_c45_pma_suspend(struct phy_device *phydev); int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable); int genphy_c45_plca_get_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_set_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_get_status(struct phy_device *phydev, struct phy_plca_status *plca_st); int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, unsigned long *lp, bool *is_enabled); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv); int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { if (!phydev->drv) return -EIO; if (phydev->drv->read_status) return phydev->drv->read_status(phydev); else return genphy_read_status(phydev); } void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_error(struct phy_device *phydev); void phy_state_machine(struct work_struct *work); void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_trigger_machine(struct phy_device *phydev); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_get_rate_matching(struct phy_device *phydev, phy_interface_t iface); void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, const int *delay_values, int size, bool is_rx); void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, bool *tx_pause, bool *rx_pause); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_register_fixup_for_id(const char *bus_id, int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask); int phy_unregister_fixup_for_id(const char *bus_id); int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); int phy_ethtool_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *cmd); int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size); void phy_package_leave(struct phy_device *phydev); int devm_phy_package_join(struct device *dev, struct phy_device *phydev, int base_addr, size_t priv_size); int __init mdio_bus_init(void); void mdio_bus_exit(void); int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data); int phy_ethtool_get_plca_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int phy_ethtool_set_plca_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg, struct netlink_ext_ack *extack); int phy_ethtool_get_plca_status(struct phy_device *phydev, struct phy_plca_status *plca_st); int __phy_hwtstamp_get(struct phy_device *phydev, struct kernel_hwtstamp_config *config); int __phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); static inline int phy_package_address(struct phy_device *phydev, unsigned int addr_offset) { struct phy_package_shared *shared = phydev->shared; u8 base_addr = shared->base_addr; if (addr_offset >= PHY_MAX_ADDR - base_addr) return -EIO; /* we know that addr will be in the range 0..31 and thus the * implicit cast to a signed int is not a problem. */ return base_addr + addr_offset; } static inline int phy_package_read(struct phy_device *phydev, unsigned int addr_offset, u32 regnum) { int addr = phy_package_address(phydev, addr_offset); if (addr < 0) return addr; return mdiobus_read(phydev->mdio.bus, addr, regnum); } static inline int __phy_package_read(struct phy_device *phydev, unsigned int addr_offset, u32 regnum) { int addr = phy_package_address(phydev, addr_offset); if (addr < 0) return addr; return __mdiobus_read(phydev->mdio.bus, addr, regnum); } static inline int phy_package_write(struct phy_device *phydev, unsigned int addr_offset, u32 regnum, u16 val) { int addr = phy_package_address(phydev, addr_offset); if (addr < 0) return addr; return mdiobus_write(phydev->mdio.bus, addr, regnum, val); } static inline int __phy_package_write(struct phy_device *phydev, unsigned int addr_offset, u32 regnum, u16 val) { int addr = phy_package_address(phydev, addr_offset); if (addr < 0) return addr; return __mdiobus_write(phydev->mdio.bus, addr, regnum, val); } int __phy_package_read_mmd(struct phy_device *phydev, unsigned int addr_offset, int devad, u32 regnum); int phy_package_read_mmd(struct phy_device *phydev, unsigned int addr_offset, int devad, u32 regnum); int __phy_package_write_mmd(struct phy_device *phydev, unsigned int addr_offset, int devad, u32 regnum, u16 val); int phy_package_write_mmd(struct phy_device *phydev, unsigned int addr_offset, int devad, u32 regnum, u16 val); static inline bool __phy_package_set_once(struct phy_device *phydev, unsigned int b) { struct phy_package_shared *shared = phydev->shared; if (!shared) return false; return !test_and_set_bit(b, &shared->flags); } static inline bool phy_package_init_once(struct phy_device *phydev) { return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE); } static inline bool phy_package_probe_once(struct phy_device *phydev) { return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE); } extern struct bus_type mdio_bus_type; struct mdio_board_info { const char *bus_id; char modalias[MDIO_NAME_SIZE]; int mdio_addr; const void *platform_data; }; #if IS_ENABLED(CONFIG_MDIO_DEVICE) int mdiobus_register_board_info(const struct mdio_board_info *info, unsigned int n); #else static inline int mdiobus_register_board_info(const struct mdio_board_info *i, unsigned int n) { return 0; } #endif /** * phy_module_driver() - Helper macro for registering PHY drivers * @__phy_drivers: array of PHY drivers to register * @__count: Numbers of members in array * * Helper macro for PHY drivers which do not do anything special in module * init/exit. Each module may only use this macro once, and calling it * replaces module_init() and module_exit(). */ #define phy_module_driver(__phy_drivers, __count) \ static int __init phy_module_init(void) \ { \ return phy_drivers_register(__phy_drivers, __count, THIS_MODULE); \ } \ module_init(phy_module_init); \ static void __exit phy_module_exit(void) \ { \ phy_drivers_unregister(__phy_drivers, __count); \ } \ module_exit(phy_module_exit) #define module_phy_driver(__phy_drivers) \ phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers)) bool phy_driver_is_genphy(struct phy_device *phydev); bool phy_driver_is_genphy_10g(struct phy_device *phydev); #endif /* __PHY_H */ |
| 15 605 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 | // SPDX-License-Identifier: GPL-2.0 /* * trace_export.c - export basic ftrace utilities to user space * * Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com> */ #include <linux/stringify.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> #include <linux/uaccess.h> #include <linux/ftrace.h> #include <linux/module.h> #include <linux/init.h> #include "trace_output.h" /* Stub function for events with triggers */ static int ftrace_event_register(struct trace_event_call *call, enum trace_reg type, void *data) { return 0; } #undef TRACE_SYSTEM #define TRACE_SYSTEM ftrace /* * The FTRACE_ENTRY_REG macro allows ftrace entry to define register * function and thus become accessible via perf. */ #undef FTRACE_ENTRY_REG #define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) /* not needed for this file */ #undef __field_struct #define __field_struct(type, item) #undef __field #define __field(type, item) type item; #undef __field_fn #define __field_fn(type, item) type item; #undef __field_desc #define __field_desc(type, container, item) type item; #undef __field_packed #define __field_packed(type, container, item) type item; #undef __array #define __array(type, item, size) type item[size]; #undef __stack_array #define __stack_array(type, item, size, field) __array(type, item, size) #undef __array_desc #define __array_desc(type, container, item, size) type item[size]; #undef __dynamic_array #define __dynamic_array(type, item) type item[]; #undef F_STRUCT #define F_STRUCT(args...) args #undef F_printk #define F_printk(fmt, args...) fmt, args #undef FTRACE_ENTRY #define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct ____ftrace_##name { \ tstruct \ }; \ static void __always_unused ____ftrace_check_##name(void) \ { \ struct ____ftrace_##name *__entry = NULL; \ \ /* force compile-time check on F_printk() */ \ printk(print); \ } #undef FTRACE_ENTRY_DUP #define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \ FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" #undef __field_ext #define __field_ext(_type, _item, _filter_type) { \ .type = #_type, .name = #_item, \ .size = sizeof(_type), .align = __alignof__(_type), \ is_signed_type(_type), .filter_type = _filter_type }, #undef __field_ext_packed #define __field_ext_packed(_type, _item, _filter_type) { \ .type = #_type, .name = #_item, \ .size = sizeof(_type), .align = 1, \ is_signed_type(_type), .filter_type = _filter_type }, #undef __field #define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER) #undef __field_fn #define __field_fn(_type, _item) __field_ext(_type, _item, FILTER_TRACE_FN) #undef __field_desc #define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER) #undef __field_packed #define __field_packed(_type, _container, _item) __field_ext_packed(_type, _item, FILTER_OTHER) #undef __array #define __array(_type, _item, _len) { \ .type = #_type"["__stringify(_len)"]", .name = #_item, \ .size = sizeof(_type[_len]), .align = __alignof__(_type), \ is_signed_type(_type), .filter_type = FILTER_OTHER, \ .len = _len }, #undef __stack_array #define __stack_array(_type, _item, _len, _field) __array(_type, _item, _len) #undef __array_desc #define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len) #undef __dynamic_array #define __dynamic_array(_type, _item) { \ .type = #_type "[]", .name = #_item, \ .size = 0, .align = __alignof__(_type), \ is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef FTRACE_ENTRY #define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ static struct trace_event_fields ftrace_event_fields_##name[] = { \ tstruct \ {} }; #include "trace_entries.h" #undef __entry #define __entry REC #undef __field #define __field(type, item) #undef __field_fn #define __field_fn(type, item) #undef __field_desc #define __field_desc(type, container, item) #undef __field_packed #define __field_packed(type, container, item) #undef __array #define __array(type, item, len) #undef __stack_array #define __stack_array(type, item, len, field) #undef __array_desc #define __array_desc(type, container, item, len) #undef __dynamic_array #define __dynamic_array(type, item) #undef F_printk #define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) #undef FTRACE_ENTRY_REG #define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn) \ static struct trace_event_class __refdata event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ .fields_array = ftrace_event_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ .reg = regfn, \ }; \ \ struct trace_event_call __used event_##call = { \ .class = &event_class_ftrace_##call, \ { \ .name = #call, \ }, \ .event.type = etype, \ .print_fmt = print, \ .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ }; \ static struct trace_event_call __used \ __section("_ftrace_events") *__event_##call = &event_##call; #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ FTRACE_ENTRY_REG(call, struct_name, etype, \ PARAMS(tstruct), PARAMS(print), NULL) bool ftrace_event_is_function(struct trace_event_call *call) { return call == &event_function; } #include "trace_entries.h" |
| 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Interface for controlling IO bandwidth on a request queue * * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/blktrace_api.h> #include "blk.h" #include "blk-cgroup-rwstat.h" #include "blk-stat.h" #include "blk-throttle.h" /* Max dispatch from a group in 1 round */ #define THROTL_GRP_QUANTUM 8 /* Total max dispatch from all groups in one round */ #define THROTL_QUANTUM 32 /* Throttling is performed over a slice and after that slice is renewed */ #define DFL_THROTL_SLICE_HD (HZ / 10) #define DFL_THROTL_SLICE_SSD (HZ / 50) #define MAX_THROTL_SLICE (HZ) #define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */ #define MIN_THROTL_BPS (320 * 1024) #define MIN_THROTL_IOPS (10) #define DFL_LATENCY_TARGET (-1L) #define DFL_IDLE_THRESHOLD (0) #define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */ #define LATENCY_FILTERED_SSD (0) /* * For HD, very small latency comes from sequential IO. Such IO is helpless to * help determine if its IO is impacted by others, hence we ignore the IO */ #define LATENCY_FILTERED_HD (1000L) /* 1ms */ /* A workqueue to queue throttle related work */ static struct workqueue_struct *kthrotld_workqueue; #define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node) /* We measure latency for request size from <= 4k to >= 1M */ #define LATENCY_BUCKET_SIZE 9 struct latency_bucket { unsigned long total_latency; /* ns / 1024 */ int samples; }; struct avg_latency_bucket { unsigned long latency; /* ns / 1024 */ bool valid; }; struct throtl_data { /* service tree for active throtl groups */ struct throtl_service_queue service_queue; struct request_queue *queue; /* Total Number of queued bios on READ and WRITE lists */ unsigned int nr_queued[2]; unsigned int throtl_slice; /* Work for dispatching throttled bios */ struct work_struct dispatch_work; unsigned int limit_index; bool limit_valid[LIMIT_CNT]; unsigned long low_upgrade_time; unsigned long low_downgrade_time; unsigned int scale; struct latency_bucket tmp_buckets[2][LATENCY_BUCKET_SIZE]; struct avg_latency_bucket avg_buckets[2][LATENCY_BUCKET_SIZE]; struct latency_bucket __percpu *latency_buckets[2]; unsigned long last_calculate_time; unsigned long filtered_latency; bool track_bio_latency; }; static void throtl_pending_timer_fn(struct timer_list *t); static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg) { return pd_to_blkg(&tg->pd); } /** * sq_to_tg - return the throl_grp the specified service queue belongs to * @sq: the throtl_service_queue of interest * * Return the throtl_grp @sq belongs to. If @sq is the top-level one * embedded in throtl_data, %NULL is returned. */ static struct throtl_grp *sq_to_tg(struct throtl_service_queue *sq) { if (sq && sq->parent_sq) return container_of(sq, struct throtl_grp, service_queue); else return NULL; } /** * sq_to_td - return throtl_data the specified service queue belongs to * @sq: the throtl_service_queue of interest * * A service_queue can be embedded in either a throtl_grp or throtl_data. * Determine the associated throtl_data accordingly and return it. */ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq) { struct throtl_grp *tg = sq_to_tg(sq); if (tg) return tg->td; else return container_of(sq, struct throtl_data, service_queue); } /* * cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to * make the IO dispatch more smooth. * Scale up: linearly scale up according to elapsed time since upgrade. For * every throtl_slice, the limit scales up 1/2 .low limit till the * limit hits .max limit * Scale down: exponentially scale down if a cgroup doesn't hit its .low limit */ static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td) { /* arbitrary value to avoid too big scale */ if (td->scale < 4096 && time_after_eq(jiffies, td->low_upgrade_time + td->scale * td->throtl_slice)) td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice; return low + (low >> 1) * td->scale; } static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw) { struct blkcg_gq *blkg = tg_to_blkg(tg); struct throtl_data *td; uint64_t ret; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return U64_MAX; td = tg->td; ret = tg->bps[rw][td->limit_index]; if (ret == 0 && td->limit_index == LIMIT_LOW) { /* intermediate node or iops isn't 0 */ if (!list_empty(&blkg->blkcg->css.children) || tg->iops[rw][td->limit_index]) return U64_MAX; else return MIN_THROTL_BPS; } if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] && tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) { uint64_t adjusted; adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td); ret = min(tg->bps[rw][LIMIT_MAX], adjusted); } return ret; } static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw) { struct blkcg_gq *blkg = tg_to_blkg(tg); struct throtl_data *td; unsigned int ret; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return UINT_MAX; td = tg->td; ret = tg->iops[rw][td->limit_index]; if (ret == 0 && tg->td->limit_index == LIMIT_LOW) { /* intermediate node or bps isn't 0 */ if (!list_empty(&blkg->blkcg->css.children) || tg->bps[rw][td->limit_index]) return UINT_MAX; else return MIN_THROTL_IOPS; } if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] && tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) { uint64_t adjusted; adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td); if (adjusted > UINT_MAX) adjusted = UINT_MAX; ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted); } return ret; } #define request_bucket_index(sectors) \ clamp_t(int, order_base_2(sectors) - 3, 0, LATENCY_BUCKET_SIZE - 1) /** * throtl_log - log debug message via blktrace * @sq: the service_queue being reported * @fmt: printf format string * @args: printf args * * The messages are prefixed with "throtl BLKG_NAME" if @sq belongs to a * throtl_grp; otherwise, just "throtl". */ #define throtl_log(sq, fmt, args...) do { \ struct throtl_grp *__tg = sq_to_tg((sq)); \ struct throtl_data *__td = sq_to_td((sq)); \ \ (void)__td; \ if (likely(!blk_trace_note_message_enabled(__td->queue))) \ break; \ if ((__tg)) { \ blk_add_cgroup_trace_msg(__td->queue, \ &tg_to_blkg(__tg)->blkcg->css, "throtl " fmt, ##args);\ } else { \ blk_add_trace_msg(__td->queue, "throtl " fmt, ##args); \ } \ } while (0) static inline unsigned int throtl_bio_data_size(struct bio *bio) { /* assume it's one sector */ if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) return 512; return bio->bi_iter.bi_size; } static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg) { INIT_LIST_HEAD(&qn->node); bio_list_init(&qn->bios); qn->tg = tg; } /** * throtl_qnode_add_bio - add a bio to a throtl_qnode and activate it * @bio: bio being added * @qn: qnode to add bio to * @queued: the service_queue->queued[] list @qn belongs to * * Add @bio to @qn and put @qn on @queued if it's not already on. * @qn->tg's reference count is bumped when @qn is activated. See the * comment on top of throtl_qnode definition for details. */ static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn, struct list_head *queued) { bio_list_add(&qn->bios, bio); if (list_empty(&qn->node)) { list_add_tail(&qn->node, queued); blkg_get(tg_to_blkg(qn->tg)); } } /** * throtl_peek_queued - peek the first bio on a qnode list * @queued: the qnode list to peek */ static struct bio *throtl_peek_queued(struct list_head *queued) { struct throtl_qnode *qn; struct bio *bio; if (list_empty(queued)) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); bio = bio_list_peek(&qn->bios); WARN_ON_ONCE(!bio); return bio; } /** * throtl_pop_queued - pop the first bio form a qnode list * @queued: the qnode list to pop a bio from * @tg_to_put: optional out argument for throtl_grp to put * * Pop the first bio from the qnode list @queued. After popping, the first * qnode is removed from @queued if empty or moved to the end of @queued so * that the popping order is round-robin. * * When the first qnode is removed, its associated throtl_grp should be put * too. If @tg_to_put is NULL, this function automatically puts it; * otherwise, *@tg_to_put is set to the throtl_grp to put and the caller is * responsible for putting it. */ static struct bio *throtl_pop_queued(struct list_head *queued, struct throtl_grp **tg_to_put) { struct throtl_qnode *qn; struct bio *bio; if (list_empty(queued)) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); bio = bio_list_pop(&qn->bios); WARN_ON_ONCE(!bio); if (bio_list_empty(&qn->bios)) { list_del_init(&qn->node); if (tg_to_put) *tg_to_put = qn->tg; else blkg_put(tg_to_blkg(qn->tg)); } else { list_move_tail(&qn->node, queued); } return bio; } /* init a service_queue, assumes the caller zeroed it */ static void throtl_service_queue_init(struct throtl_service_queue *sq) { INIT_LIST_HEAD(&sq->queued[READ]); INIT_LIST_HEAD(&sq->queued[WRITE]); sq->pending_tree = RB_ROOT_CACHED; timer_setup(&sq->pending_timer, throtl_pending_timer_fn, 0); } static struct blkg_policy_data *throtl_pd_alloc(struct gendisk *disk, struct blkcg *blkcg, gfp_t gfp) { struct throtl_grp *tg; int rw; tg = kzalloc_node(sizeof(*tg), gfp, disk->node_id); if (!tg) return NULL; if (blkg_rwstat_init(&tg->stat_bytes, gfp)) goto err_free_tg; if (blkg_rwstat_init(&tg->stat_ios, gfp)) goto err_exit_stat_bytes; throtl_service_queue_init(&tg->service_queue); for (rw = READ; rw <= WRITE; rw++) { throtl_qnode_init(&tg->qnode_on_self[rw], tg); throtl_qnode_init(&tg->qnode_on_parent[rw], tg); } RB_CLEAR_NODE(&tg->rb_node); tg->bps[READ][LIMIT_MAX] = U64_MAX; tg->bps[WRITE][LIMIT_MAX] = U64_MAX; tg->iops[READ][LIMIT_MAX] = UINT_MAX; tg->iops[WRITE][LIMIT_MAX] = UINT_MAX; tg->bps_conf[READ][LIMIT_MAX] = U64_MAX; tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX; tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX; tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX; /* LIMIT_LOW will have default value 0 */ tg->latency_target = DFL_LATENCY_TARGET; tg->latency_target_conf = DFL_LATENCY_TARGET; tg->idletime_threshold = DFL_IDLE_THRESHOLD; tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD; return &tg->pd; err_exit_stat_bytes: blkg_rwstat_exit(&tg->stat_bytes); err_free_tg: kfree(tg); return NULL; } static void throtl_pd_init(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); struct blkcg_gq *blkg = tg_to_blkg(tg); struct throtl_data *td = blkg->q->td; struct throtl_service_queue *sq = &tg->service_queue; /* * If on the default hierarchy, we switch to properly hierarchical * behavior where limits on a given throtl_grp are applied to the * whole subtree rather than just the group itself. e.g. If 16M * read_bps limit is set on a parent group, summary bps of * parent group and its subtree groups can't exceed 16M for the * device. * * If not on the default hierarchy, the broken flat hierarchy * behavior is retained where all throtl_grps are treated as if * they're all separate root groups right below throtl_data. * Limits of a group don't interact with limits of other groups * regardless of the position of the group in the hierarchy. */ sq->parent_sq = &td->service_queue; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent) sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue; tg->td = td; } /* * Set has_rules[] if @tg or any of its parents have limits configured. * This doesn't require walking up to the top of the hierarchy as the * parent's has_rules[] is guaranteed to be correct. */ static void tg_update_has_rules(struct throtl_grp *tg) { struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq); struct throtl_data *td = tg->td; int rw; for (rw = READ; rw <= WRITE; rw++) { tg->has_rules_iops[rw] = (parent_tg && parent_tg->has_rules_iops[rw]) || (td->limit_valid[td->limit_index] && tg_iops_limit(tg, rw) != UINT_MAX); tg->has_rules_bps[rw] = (parent_tg && parent_tg->has_rules_bps[rw]) || (td->limit_valid[td->limit_index] && (tg_bps_limit(tg, rw) != U64_MAX)); } } static void throtl_pd_online(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); /* * We don't want new groups to escape the limits of its ancestors. * Update has_rules[] after a new group is brought online. */ tg_update_has_rules(tg); } #ifdef CONFIG_BLK_DEV_THROTTLING_LOW static void blk_throtl_update_limit_valid(struct throtl_data *td) { struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; bool low_valid = false; rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { struct throtl_grp *tg = blkg_to_tg(blkg); if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) { low_valid = true; break; } } rcu_read_unlock(); td->limit_valid[LIMIT_LOW] = low_valid; } #else static inline void blk_throtl_update_limit_valid(struct throtl_data *td) { } #endif static void throtl_upgrade_state(struct throtl_data *td); static void throtl_pd_offline(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); tg->bps[READ][LIMIT_LOW] = 0; tg->bps[WRITE][LIMIT_LOW] = 0; tg->iops[READ][LIMIT_LOW] = 0; tg->iops[WRITE][LIMIT_LOW] = 0; blk_throtl_update_limit_valid(tg->td); if (!tg->td->limit_valid[tg->td->limit_index]) throtl_upgrade_state(tg->td); } static void throtl_pd_free(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); del_timer_sync(&tg->service_queue.pending_timer); blkg_rwstat_exit(&tg->stat_bytes); blkg_rwstat_exit(&tg->stat_ios); kfree(tg); } static struct throtl_grp * throtl_rb_first(struct throtl_service_queue *parent_sq) { struct rb_node *n; n = rb_first_cached(&parent_sq->pending_tree); WARN_ON_ONCE(!n); if (!n) return NULL; return rb_entry_tg(n); } static void throtl_rb_erase(struct rb_node *n, struct throtl_service_queue *parent_sq) { rb_erase_cached(n, &parent_sq->pending_tree); RB_CLEAR_NODE(n); } static void update_min_dispatch_time(struct throtl_service_queue *parent_sq) { struct throtl_grp *tg; tg = throtl_rb_first(parent_sq); if (!tg) return; parent_sq->first_pending_disptime = tg->disptime; } static void tg_service_queue_add(struct throtl_grp *tg) { struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq; struct rb_node **node = &parent_sq->pending_tree.rb_root.rb_node; struct rb_node *parent = NULL; struct throtl_grp *__tg; unsigned long key = tg->disptime; bool leftmost = true; while (*node != NULL) { parent = *node; __tg = rb_entry_tg(parent); if (time_before(key, __tg->disptime)) node = &parent->rb_left; else { node = &parent->rb_right; leftmost = false; } } rb_link_node(&tg->rb_node, parent, node); rb_insert_color_cached(&tg->rb_node, &parent_sq->pending_tree, leftmost); } static void throtl_enqueue_tg(struct throtl_grp *tg) { if (!(tg->flags & THROTL_TG_PENDING)) { tg_service_queue_add(tg); tg->flags |= THROTL_TG_PENDING; tg->service_queue.parent_sq->nr_pending++; } } static void throtl_dequeue_tg(struct throtl_grp *tg) { if (tg->flags & THROTL_TG_PENDING) { struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq; throtl_rb_erase(&tg->rb_node, parent_sq); --parent_sq->nr_pending; tg->flags &= ~THROTL_TG_PENDING; } } /* Call with queue lock held */ static void throtl_schedule_pending_timer(struct throtl_service_queue *sq, unsigned long expires) { unsigned long max_expire = jiffies + 8 * sq_to_td(sq)->throtl_slice; /* * Since we are adjusting the throttle limit dynamically, the sleep * time calculated according to previous limit might be invalid. It's * possible the cgroup sleep time is very long and no other cgroups * have IO running so notify the limit changes. Make sure the cgroup * doesn't sleep too long to avoid the missed notification. */ if (time_after(expires, max_expire)) expires = max_expire; mod_timer(&sq->pending_timer, expires); throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu", expires - jiffies, jiffies); } /** * throtl_schedule_next_dispatch - schedule the next dispatch cycle * @sq: the service_queue to schedule dispatch for * @force: force scheduling * * Arm @sq->pending_timer so that the next dispatch cycle starts on the * dispatch time of the first pending child. Returns %true if either timer * is armed or there's no pending child left. %false if the current * dispatch window is still open and the caller should continue * dispatching. * * If @force is %true, the dispatch timer is always scheduled and this * function is guaranteed to return %true. This is to be used when the * caller can't dispatch itself and needs to invoke pending_timer * unconditionally. Note that forced scheduling is likely to induce short * delay before dispatch starts even if @sq->first_pending_disptime is not * in the future and thus shouldn't be used in hot paths. */ static bool throtl_schedule_next_dispatch(struct throtl_service_queue *sq, bool force) { /* any pending children left? */ if (!sq->nr_pending) return true; update_min_dispatch_time(sq); /* is the next dispatch time in the future? */ if (force || time_after(sq->first_pending_disptime, jiffies)) { throtl_schedule_pending_timer(sq, sq->first_pending_disptime); return true; } /* tell the caller to continue dispatching */ return false; } static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, bool rw, unsigned long start) { tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; tg->carryover_bytes[rw] = 0; tg->carryover_ios[rw] = 0; /* * Previous slice has expired. We must have trimmed it after last * bio dispatch. That means since start of last slice, we never used * that bandwidth. Do try to make use of that bandwidth while giving * credit. */ if (time_after(start, tg->slice_start[rw])) tg->slice_start[rw] = start; tg->slice_end[rw] = jiffies + tg->td->throtl_slice; throtl_log(&tg->service_queue, "[%c] new slice with credit start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', tg->slice_start[rw], tg->slice_end[rw], jiffies); } static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw, bool clear_carryover) { tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; tg->slice_start[rw] = jiffies; tg->slice_end[rw] = jiffies + tg->td->throtl_slice; if (clear_carryover) { tg->carryover_bytes[rw] = 0; tg->carryover_ios[rw] = 0; } throtl_log(&tg->service_queue, "[%c] new slice start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', tg->slice_start[rw], tg->slice_end[rw], jiffies); } static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw, unsigned long jiffy_end) { tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice); } static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw, unsigned long jiffy_end) { throtl_set_slice_end(tg, rw, jiffy_end); throtl_log(&tg->service_queue, "[%c] extend slice start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', tg->slice_start[rw], tg->slice_end[rw], jiffies); } /* Determine if previously allocated or extended slice is complete or not */ static bool throtl_slice_used(struct throtl_grp *tg, bool rw) { if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw])) return false; return true; } static unsigned int calculate_io_allowed(u32 iops_limit, unsigned long jiffy_elapsed) { unsigned int io_allowed; u64 tmp; /* * jiffy_elapsed should not be a big value as minimum iops can be * 1 then at max jiffy elapsed should be equivalent of 1 second as we * will allow dispatch after 1 second and after that slice should * have been trimmed. */ tmp = (u64)iops_limit * jiffy_elapsed; do_div(tmp, HZ); if (tmp > UINT_MAX) io_allowed = UINT_MAX; else io_allowed = tmp; return io_allowed; } static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed) { /* * Can result be wider than 64 bits? * We check against 62, not 64, due to ilog2 truncation. */ if (ilog2(bps_limit) + ilog2(jiffy_elapsed) - ilog2(HZ) > 62) return U64_MAX; return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ); } /* Trim the used slices and adjust slice start accordingly */ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) { unsigned long time_elapsed; long long bytes_trim; int io_trim; BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw])); /* * If bps are unlimited (-1), then time slice don't get * renewed. Don't try to trim the slice if slice is used. A new * slice will start when appropriate. */ if (throtl_slice_used(tg, rw)) return; /* * A bio has been dispatched. Also adjust slice_end. It might happen * that initially cgroup limit was very low resulting in high * slice_end, but later limit was bumped up and bio was dispatched * sooner, then we need to reduce slice_end. A high bogus slice_end * is bad because it does not allow new slice to start. */ throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice); time_elapsed = rounddown(jiffies - tg->slice_start[rw], tg->td->throtl_slice); if (!time_elapsed) return; bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw), time_elapsed) + tg->carryover_bytes[rw]; io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) + tg->carryover_ios[rw]; if (bytes_trim <= 0 && io_trim <= 0) return; tg->carryover_bytes[rw] = 0; if ((long long)tg->bytes_disp[rw] >= bytes_trim) tg->bytes_disp[rw] -= bytes_trim; else tg->bytes_disp[rw] = 0; tg->carryover_ios[rw] = 0; if ((int)tg->io_disp[rw] >= io_trim) tg->io_disp[rw] -= io_trim; else tg->io_disp[rw] = 0; tg->slice_start[rw] += time_elapsed; throtl_log(&tg->service_queue, "[%c] trim slice nr=%lu bytes=%lld io=%d start=%lu end=%lu jiffies=%lu", rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice, bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw], jiffies); } static void __tg_update_carryover(struct throtl_grp *tg, bool rw) { unsigned long jiffy_elapsed = jiffies - tg->slice_start[rw]; u64 bps_limit = tg_bps_limit(tg, rw); u32 iops_limit = tg_iops_limit(tg, rw); /* * If config is updated while bios are still throttled, calculate and * accumulate how many bytes/ios are waited across changes. And * carryover_bytes/ios will be used to calculate new wait time under new * configuration. */ if (bps_limit != U64_MAX) tg->carryover_bytes[rw] += calculate_bytes_allowed(bps_limit, jiffy_elapsed) - tg->bytes_disp[rw]; if (iops_limit != UINT_MAX) tg->carryover_ios[rw] += calculate_io_allowed(iops_limit, jiffy_elapsed) - tg->io_disp[rw]; } static void tg_update_carryover(struct throtl_grp *tg) { if (tg->service_queue.nr_queued[READ]) __tg_update_carryover(tg, READ); if (tg->service_queue.nr_queued[WRITE]) __tg_update_carryover(tg, WRITE); /* see comments in struct throtl_grp for meaning of these fields. */ throtl_log(&tg->service_queue, "%s: %lld %lld %d %d\n", __func__, tg->carryover_bytes[READ], tg->carryover_bytes[WRITE], tg->carryover_ios[READ], tg->carryover_ios[WRITE]); } static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio, u32 iops_limit) { bool rw = bio_data_dir(bio); int io_allowed; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; if (iops_limit == UINT_MAX) { return 0; } jiffy_elapsed = jiffies - tg->slice_start[rw]; /* Round up to the next throttle slice, wait time must be nonzero */ jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice); io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd) + tg->carryover_ios[rw]; if (io_allowed > 0 && tg->io_disp[rw] + 1 <= io_allowed) return 0; /* Calc approx time to dispatch */ jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed; return jiffy_wait; } static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, u64 bps_limit) { bool rw = bio_data_dir(bio); long long bytes_allowed; u64 extra_bytes; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; unsigned int bio_size = throtl_bio_data_size(bio); /* no need to throttle if this bio's bytes have been accounted */ if (bps_limit == U64_MAX || bio_flagged(bio, BIO_BPS_THROTTLED)) { return 0; } jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw]; /* Slice has just started. Consider one slice interval */ if (!jiffy_elapsed) jiffy_elapsed_rnd = tg->td->throtl_slice; jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice); bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd) + tg->carryover_bytes[rw]; if (bytes_allowed > 0 && tg->bytes_disp[rw] + bio_size <= bytes_allowed) return 0; /* Calc approx time to dispatch */ extra_bytes = tg->bytes_disp[rw] + bio_size - bytes_allowed; jiffy_wait = div64_u64(extra_bytes * HZ, bps_limit); if (!jiffy_wait) jiffy_wait = 1; /* * This wait time is without taking into consideration the rounding * up we did. Add that time also. */ jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed); return jiffy_wait; } /* * Returns whether one can dispatch a bio or not. Also returns approx number * of jiffies to wait before this bio is with-in IO rate and can be dispatched */ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, unsigned long *wait) { bool rw = bio_data_dir(bio); unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0; u64 bps_limit = tg_bps_limit(tg, rw); u32 iops_limit = tg_iops_limit(tg, rw); /* * Currently whole state machine of group depends on first bio * queued in the group bio list. So one should not be calling * this function with a different bio if there are other bios * queued. */ BUG_ON(tg->service_queue.nr_queued[rw] && bio != throtl_peek_queued(&tg->service_queue.queued[rw])); /* If tg->bps = -1, then BW is unlimited */ if ((bps_limit == U64_MAX && iops_limit == UINT_MAX) || tg->flags & THROTL_TG_CANCELING) { if (wait) *wait = 0; return true; } /* * If previous slice expired, start a new one otherwise renew/extend * existing slice to make sure it is at least throtl_slice interval * long since now. New slice is started only for empty throttle group. * If there is queued bio, that means there should be an active * slice and it should be extended instead. */ if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw])) throtl_start_new_slice(tg, rw, true); else { if (time_before(tg->slice_end[rw], jiffies + tg->td->throtl_slice)) throtl_extend_slice(tg, rw, jiffies + tg->td->throtl_slice); } bps_wait = tg_within_bps_limit(tg, bio, bps_limit); iops_wait = tg_within_iops_limit(tg, bio, iops_limit); if (bps_wait + iops_wait == 0) { if (wait) *wait = 0; return true; } max_wait = max(bps_wait, iops_wait); if (wait) *wait = max_wait; if (time_before(tg->slice_end[rw], jiffies + max_wait)) throtl_extend_slice(tg, rw, jiffies + max_wait); return false; } static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) { bool rw = bio_data_dir(bio); unsigned int bio_size = throtl_bio_data_size(bio); /* Charge the bio to the group */ if (!bio_flagged(bio, BIO_BPS_THROTTLED)) { tg->bytes_disp[rw] += bio_size; tg->last_bytes_disp[rw] += bio_size; } tg->io_disp[rw]++; tg->last_io_disp[rw]++; } /** * throtl_add_bio_tg - add a bio to the specified throtl_grp * @bio: bio to add * @qn: qnode to use * @tg: the target throtl_grp * * Add @bio to @tg's service_queue using @qn. If @qn is not specified, * tg->qnode_on_self[] is used. */ static void throtl_add_bio_tg(struct bio *bio, struct throtl_qnode *qn, struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; bool rw = bio_data_dir(bio); if (!qn) qn = &tg->qnode_on_self[rw]; /* * If @tg doesn't currently have any bios queued in the same * direction, queueing @bio can change when @tg should be * dispatched. Mark that @tg was empty. This is automatically * cleared on the next tg_update_disptime(). */ if (!sq->nr_queued[rw]) tg->flags |= THROTL_TG_WAS_EMPTY; throtl_qnode_add_bio(bio, qn, &sq->queued[rw]); sq->nr_queued[rw]++; throtl_enqueue_tg(tg); } static void tg_update_disptime(struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime; struct bio *bio; bio = throtl_peek_queued(&sq->queued[READ]); if (bio) tg_may_dispatch(tg, bio, &read_wait); bio = throtl_peek_queued(&sq->queued[WRITE]); if (bio) tg_may_dispatch(tg, bio, &write_wait); min_wait = min(read_wait, write_wait); disptime = jiffies + min_wait; /* Update dispatch time */ throtl_rb_erase(&tg->rb_node, tg->service_queue.parent_sq); tg->disptime = disptime; tg_service_queue_add(tg); /* see throtl_add_bio_tg() */ tg->flags &= ~THROTL_TG_WAS_EMPTY; } static void start_parent_slice_with_credit(struct throtl_grp *child_tg, struct throtl_grp *parent_tg, bool rw) { if (throtl_slice_used(parent_tg, rw)) { throtl_start_new_slice_with_credit(parent_tg, rw, child_tg->slice_start[rw]); } } static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw) { struct throtl_service_queue *sq = &tg->service_queue; struct throtl_service_queue *parent_sq = sq->parent_sq; struct throtl_grp *parent_tg = sq_to_tg(parent_sq); struct throtl_grp *tg_to_put = NULL; struct bio *bio; /* * @bio is being transferred from @tg to @parent_sq. Popping a bio * from @tg may put its reference and @parent_sq might end up * getting released prematurely. Remember the tg to put and put it * after @bio is transferred to @parent_sq. */ bio = throtl_pop_queued(&sq->queued[rw], &tg_to_put); sq->nr_queued[rw]--; throtl_charge_bio(tg, bio); /* * If our parent is another tg, we just need to transfer @bio to * the parent using throtl_add_bio_tg(). If our parent is * @td->service_queue, @bio is ready to be issued. Put it on its * bio_lists[] and decrease total number queued. The caller is * responsible for issuing these bios. */ if (parent_tg) { throtl_add_bio_tg(bio, &tg->qnode_on_parent[rw], parent_tg); start_parent_slice_with_credit(tg, parent_tg, rw); } else { bio_set_flag(bio, BIO_BPS_THROTTLED); throtl_qnode_add_bio(bio, &tg->qnode_on_parent[rw], &parent_sq->queued[rw]); BUG_ON(tg->td->nr_queued[rw] <= 0); tg->td->nr_queued[rw]--; } throtl_trim_slice(tg, rw); if (tg_to_put) blkg_put(tg_to_blkg(tg_to_put)); } static int throtl_dispatch_tg(struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; unsigned int nr_reads = 0, nr_writes = 0; unsigned int max_nr_reads = THROTL_GRP_QUANTUM * 3 / 4; unsigned int max_nr_writes = THROTL_GRP_QUANTUM - max_nr_reads; struct bio *bio; /* Try to dispatch 75% READS and 25% WRITES */ while ((bio = throtl_peek_queued(&sq->queued[READ])) && tg_may_dispatch(tg, bio, NULL)) { tg_dispatch_one_bio(tg, bio_data_dir(bio)); nr_reads++; if (nr_reads >= max_nr_reads) break; } while ((bio = throtl_peek_queued(&sq->queued[WRITE])) && tg_may_dispatch(tg, bio, NULL)) { tg_dispatch_one_bio(tg, bio_data_dir(bio)); nr_writes++; if (nr_writes >= max_nr_writes) break; } return nr_reads + nr_writes; } static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) { unsigned int nr_disp = 0; while (1) { struct throtl_grp *tg; struct throtl_service_queue *sq; if (!parent_sq->nr_pending) break; tg = throtl_rb_first(parent_sq); if (!tg) break; if (time_before(jiffies, tg->disptime)) break; nr_disp += throtl_dispatch_tg(tg); sq = &tg->service_queue; if (sq->nr_queued[READ] || sq->nr_queued[WRITE]) tg_update_disptime(tg); else throtl_dequeue_tg(tg); if (nr_disp >= THROTL_QUANTUM) break; } return nr_disp; } static bool throtl_can_upgrade(struct throtl_data *td, struct throtl_grp *this_tg); /** * throtl_pending_timer_fn - timer function for service_queue->pending_timer * @t: the pending_timer member of the throtl_service_queue being serviced * * This timer is armed when a child throtl_grp with active bio's become * pending and queued on the service_queue's pending_tree and expires when * the first child throtl_grp should be dispatched. This function * dispatches bio's from the children throtl_grps to the parent * service_queue. * * If the parent's parent is another throtl_grp, dispatching is propagated * by either arming its pending_timer or repeating dispatch directly. If * the top-level service_tree is reached, throtl_data->dispatch_work is * kicked so that the ready bio's are issued. */ static void throtl_pending_timer_fn(struct timer_list *t) { struct throtl_service_queue *sq = from_timer(sq, t, pending_timer); struct throtl_grp *tg = sq_to_tg(sq); struct throtl_data *td = sq_to_td(sq); struct throtl_service_queue *parent_sq; struct request_queue *q; bool dispatched; int ret; /* throtl_data may be gone, so figure out request queue by blkg */ if (tg) q = tg->pd.blkg->q; else q = td->queue; spin_lock_irq(&q->queue_lock); if (!q->root_blkg) goto out_unlock; if (throtl_can_upgrade(td, NULL)) throtl_upgrade_state(td); again: parent_sq = sq->parent_sq; dispatched = false; while (true) { throtl_log(sq, "dispatch nr_queued=%u read=%u write=%u", sq->nr_queued[READ] + sq->nr_queued[WRITE], sq->nr_queued[READ], sq->nr_queued[WRITE]); ret = throtl_select_dispatch(sq); if (ret) { throtl_log(sq, "bios disp=%u", ret); dispatched = true; } if (throtl_schedule_next_dispatch(sq, false)) break; /* this dispatch windows is still open, relax and repeat */ spin_unlock_irq(&q->queue_lock); cpu_relax(); spin_lock_irq(&q->queue_lock); } if (!dispatched) goto out_unlock; if (parent_sq) { /* @parent_sq is another throl_grp, propagate dispatch */ if (tg->flags & THROTL_TG_WAS_EMPTY) { tg_update_disptime(tg); if (!throtl_schedule_next_dispatch(parent_sq, false)) { /* window is already open, repeat dispatching */ sq = parent_sq; tg = sq_to_tg(sq); goto again; } } } else { /* reached the top-level, queue issuing */ queue_work(kthrotld_workqueue, &td->dispatch_work); } out_unlock: spin_unlock_irq(&q->queue_lock); } /** * blk_throtl_dispatch_work_fn - work function for throtl_data->dispatch_work * @work: work item being executed * * This function is queued for execution when bios reach the bio_lists[] * of throtl_data->service_queue. Those bios are ready and issued by this * function. */ static void blk_throtl_dispatch_work_fn(struct work_struct *work) { struct throtl_data *td = container_of(work, struct throtl_data, dispatch_work); struct throtl_service_queue *td_sq = &td->service_queue; struct request_queue *q = td->queue; struct bio_list bio_list_on_stack; struct bio *bio; struct blk_plug plug; int rw; bio_list_init(&bio_list_on_stack); spin_lock_irq(&q->queue_lock); for (rw = READ; rw <= WRITE; rw++) while ((bio = throtl_pop_queued(&td_sq->queued[rw], NULL))) bio_list_add(&bio_list_on_stack, bio); spin_unlock_irq(&q->queue_lock); if (!bio_list_empty(&bio_list_on_stack)) { blk_start_plug(&plug); while ((bio = bio_list_pop(&bio_list_on_stack))) submit_bio_noacct_nocheck(bio); blk_finish_plug(&plug); } } static u64 tg_prfill_conf_u64(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct throtl_grp *tg = pd_to_tg(pd); u64 v = *(u64 *)((void *)tg + off); if (v == U64_MAX) return 0; return __blkg_prfill_u64(sf, pd, v); } static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct throtl_grp *tg = pd_to_tg(pd); unsigned int v = *(unsigned int *)((void *)tg + off); if (v == UINT_MAX) return 0; return __blkg_prfill_u64(sf, pd, v); } static int tg_print_conf_u64(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_u64, &blkcg_policy_throtl, seq_cft(sf)->private, false); return 0; } static int tg_print_conf_uint(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_conf_uint, &blkcg_policy_throtl, seq_cft(sf)->private, false); return 0; } static void tg_conf_updated(struct throtl_grp *tg, bool global) { struct throtl_service_queue *sq = &tg->service_queue; struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; throtl_log(&tg->service_queue, "limit change rbps=%llu wbps=%llu riops=%u wiops=%u", tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE), tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE)); rcu_read_lock(); /* * Update has_rules[] flags for the updated tg's subtree. A tg is * considered to have rules if either the tg itself or any of its * ancestors has rules. This identifies groups without any * restrictions in the whole hierarchy and allows them to bypass * blk-throttle. */ blkg_for_each_descendant_pre(blkg, pos_css, global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) { struct throtl_grp *this_tg = blkg_to_tg(blkg); struct throtl_grp *parent_tg; tg_update_has_rules(this_tg); /* ignore root/second level */ if (!cgroup_subsys_on_dfl(io_cgrp_subsys) || !blkg->parent || !blkg->parent->parent) continue; parent_tg = blkg_to_tg(blkg->parent); /* * make sure all children has lower idle time threshold and * higher latency target */ this_tg->idletime_threshold = min(this_tg->idletime_threshold, parent_tg->idletime_threshold); this_tg->latency_target = max(this_tg->latency_target, parent_tg->latency_target); } rcu_read_unlock(); /* * We're already holding queue_lock and know @tg is valid. Let's * apply the new config directly. * * Restart the slices for both READ and WRITES. It might happen * that a group's limit are dropped suddenly and we don't want to * account recently dispatched IO with new low rate. */ throtl_start_new_slice(tg, READ, false); throtl_start_new_slice(tg, WRITE, false); if (tg->flags & THROTL_TG_PENDING) { tg_update_disptime(tg); throtl_schedule_next_dispatch(sq->parent_sq, true); } } static ssize_t tg_set_conf(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool is_u64) { struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct blkg_conf_ctx ctx; struct throtl_grp *tg; int ret; u64 v; blkg_conf_init(&ctx, buf); ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, &ctx); if (ret) goto out_finish; ret = -EINVAL; if (sscanf(ctx.body, "%llu", &v) != 1) goto out_finish; if (!v) v = U64_MAX; tg = blkg_to_tg(ctx.blkg); tg_update_carryover(tg); if (is_u64) *(u64 *)((void *)tg + of_cft(of)->private) = v; else *(unsigned int *)((void *)tg + of_cft(of)->private) = v; tg_conf_updated(tg, false); ret = 0; out_finish: blkg_conf_exit(&ctx); return ret ?: nbytes; } static ssize_t tg_set_conf_u64(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return tg_set_conf(of, buf, nbytes, off, true); } static ssize_t tg_set_conf_uint(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return tg_set_conf(of, buf, nbytes, off, false); } static int tg_print_rwstat(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, &blkcg_policy_throtl, seq_cft(sf)->private, true); return 0; } static u64 tg_prfill_rwstat_recursive(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct blkg_rwstat_sample sum; blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_throtl, off, &sum); return __blkg_prfill_rwstat(sf, pd, &sum); } static int tg_print_rwstat_recursive(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_rwstat_recursive, &blkcg_policy_throtl, seq_cft(sf)->private, true); return 0; } static struct cftype throtl_legacy_files[] = { { .name = "throttle.read_bps_device", .private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]), .seq_show = tg_print_conf_u64, .write = tg_set_conf_u64, }, { .name = "throttle.write_bps_device", .private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]), .seq_show = tg_print_conf_u64, .write = tg_set_conf_u64, }, { .name = "throttle.read_iops_device", .private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]), .seq_show = tg_print_conf_uint, .write = tg_set_conf_uint, }, { .name = "throttle.write_iops_device", .private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]), .seq_show = tg_print_conf_uint, .write = tg_set_conf_uint, }, { .name = "throttle.io_service_bytes", .private = offsetof(struct throtl_grp, stat_bytes), .seq_show = tg_print_rwstat, }, { .name = "throttle.io_service_bytes_recursive", .private = offsetof(struct throtl_grp, stat_bytes), .seq_show = tg_print_rwstat_recursive, }, { .name = "throttle.io_serviced", .private = offsetof(struct throtl_grp, stat_ios), .seq_show = tg_print_rwstat, }, { .name = "throttle.io_serviced_recursive", .private = offsetof(struct throtl_grp, stat_ios), .seq_show = tg_print_rwstat_recursive, }, { } /* terminate */ }; static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd, int off) { struct throtl_grp *tg = pd_to_tg(pd); const char *dname = blkg_dev_name(pd->blkg); char bufs[4][21] = { "max", "max", "max", "max" }; u64 bps_dft; unsigned int iops_dft; char idle_time[26] = ""; char latency_time[26] = ""; if (!dname) return 0; if (off == LIMIT_LOW) { bps_dft = 0; iops_dft = 0; } else { bps_dft = U64_MAX; iops_dft = UINT_MAX; } if (tg->bps_conf[READ][off] == bps_dft && tg->bps_conf[WRITE][off] == bps_dft && tg->iops_conf[READ][off] == iops_dft && tg->iops_conf[WRITE][off] == iops_dft && (off != LIMIT_LOW || (tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD && tg->latency_target_conf == DFL_LATENCY_TARGET))) return 0; if (tg->bps_conf[READ][off] != U64_MAX) snprintf(bufs[0], sizeof(bufs[0]), "%llu", tg->bps_conf[READ][off]); if (tg->bps_conf[WRITE][off] != U64_MAX) snprintf(bufs[1], sizeof(bufs[1]), "%llu", tg->bps_conf[WRITE][off]); if (tg->iops_conf[READ][off] != UINT_MAX) snprintf(bufs[2], sizeof(bufs[2]), "%u", tg->iops_conf[READ][off]); if (tg->iops_conf[WRITE][off] != UINT_MAX) snprintf(bufs[3], sizeof(bufs[3]), "%u", tg->iops_conf[WRITE][off]); if (off == LIMIT_LOW) { if (tg->idletime_threshold_conf == ULONG_MAX) strcpy(idle_time, " idle=max"); else snprintf(idle_time, sizeof(idle_time), " idle=%lu", tg->idletime_threshold_conf); if (tg->latency_target_conf == ULONG_MAX) strcpy(latency_time, " latency=max"); else snprintf(latency_time, sizeof(latency_time), " latency=%lu", tg->latency_target_conf); } seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n", dname, bufs[0], bufs[1], bufs[2], bufs[3], idle_time, latency_time); return 0; } static int tg_print_limit(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_limit, &blkcg_policy_throtl, seq_cft(sf)->private, false); return 0; } static ssize_t tg_set_limit(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct blkcg *blkcg = css_to_blkcg(of_css(of)); struct blkg_conf_ctx ctx; struct throtl_grp *tg; u64 v[4]; unsigned long idle_time; unsigned long latency_time; int ret; int index = of_cft(of)->private; blkg_conf_init(&ctx, buf); ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, &ctx); if (ret) goto out_finish; tg = blkg_to_tg(ctx.blkg); tg_update_carryover(tg); v[0] = tg->bps_conf[READ][index]; v[1] = tg->bps_conf[WRITE][index]; v[2] = tg->iops_conf[READ][index]; v[3] = tg->iops_conf[WRITE][index]; idle_time = tg->idletime_threshold_conf; latency_time = tg->latency_target_conf; while (true) { char tok[27]; /* wiops=18446744073709551616 */ char *p; u64 val = U64_MAX; int len; if (sscanf(ctx.body, "%26s%n", tok, &len) != 1) break; if (tok[0] == '\0') break; ctx.body += len; ret = -EINVAL; p = tok; strsep(&p, "="); if (!p || (sscanf(p, "%llu", &val) != 1 && strcmp(p, "max"))) goto out_finish; ret = -ERANGE; if (!val) goto out_finish; ret = -EINVAL; if (!strcmp(tok, "rbps") && val > 1) v[0] = val; else if (!strcmp(tok, "wbps") && val > 1) v[1] = val; else if (!strcmp(tok, "riops") && val > 1) v[2] = min_t(u64, val, UINT_MAX); else if (!strcmp(tok, "wiops") && val > 1) v[3] = min_t(u64, val, UINT_MAX); else if (off == LIMIT_LOW && !strcmp(tok, "idle")) idle_time = val; else if (off == LIMIT_LOW && !strcmp(tok, "latency")) latency_time = val; else goto out_finish; } tg->bps_conf[READ][index] = v[0]; tg->bps_conf[WRITE][index] = v[1]; tg->iops_conf[READ][index] = v[2]; tg->iops_conf[WRITE][index] = v[3]; if (index == LIMIT_MAX) { tg->bps[READ][index] = v[0]; tg->bps[WRITE][index] = v[1]; tg->iops[READ][index] = v[2]; tg->iops[WRITE][index] = v[3]; } tg->bps[READ][LIMIT_LOW] = min(tg->bps_conf[READ][LIMIT_LOW], tg->bps_conf[READ][LIMIT_MAX]); tg->bps[WRITE][LIMIT_LOW] = min(tg->bps_conf[WRITE][LIMIT_LOW], tg->bps_conf[WRITE][LIMIT_MAX]); tg->iops[READ][LIMIT_LOW] = min(tg->iops_conf[READ][LIMIT_LOW], tg->iops_conf[READ][LIMIT_MAX]); tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW], tg->iops_conf[WRITE][LIMIT_MAX]); tg->idletime_threshold_conf = idle_time; tg->latency_target_conf = latency_time; /* force user to configure all settings for low limit */ if (!(tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) || tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD || tg->latency_target_conf == DFL_LATENCY_TARGET) { tg->bps[READ][LIMIT_LOW] = 0; tg->bps[WRITE][LIMIT_LOW] = 0; tg->iops[READ][LIMIT_LOW] = 0; tg->iops[WRITE][LIMIT_LOW] = 0; tg->idletime_threshold = DFL_IDLE_THRESHOLD; tg->latency_target = DFL_LATENCY_TARGET; } else if (index == LIMIT_LOW) { tg->idletime_threshold = tg->idletime_threshold_conf; tg->latency_target = tg->latency_target_conf; } blk_throtl_update_limit_valid(tg->td); if (tg->td->limit_valid[LIMIT_LOW]) { if (index == LIMIT_LOW) tg->td->limit_index = LIMIT_LOW; } else tg->td->limit_index = LIMIT_MAX; tg_conf_updated(tg, index == LIMIT_LOW && tg->td->limit_valid[LIMIT_LOW]); ret = 0; out_finish: blkg_conf_exit(&ctx); return ret ?: nbytes; } static struct cftype throtl_files[] = { #ifdef CONFIG_BLK_DEV_THROTTLING_LOW { .name = "low", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = tg_print_limit, .write = tg_set_limit, .private = LIMIT_LOW, }, #endif { .name = "max", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = tg_print_limit, .write = tg_set_limit, .private = LIMIT_MAX, }, { } /* terminate */ }; static void throtl_shutdown_wq(struct request_queue *q) { struct throtl_data *td = q->td; cancel_work_sync(&td->dispatch_work); } struct blkcg_policy blkcg_policy_throtl = { .dfl_cftypes = throtl_files, .legacy_cftypes = throtl_legacy_files, .pd_alloc_fn = throtl_pd_alloc, .pd_init_fn = throtl_pd_init, .pd_online_fn = throtl_pd_online, .pd_offline_fn = throtl_pd_offline, .pd_free_fn = throtl_pd_free, }; void blk_throtl_cancel_bios(struct gendisk *disk) { struct request_queue *q = disk->queue; struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; spin_lock_irq(&q->queue_lock); /* * queue_lock is held, rcu lock is not needed here technically. * However, rcu lock is still held to emphasize that following * path need RCU protection and to prevent warning from lockdep. */ rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) { struct throtl_grp *tg = blkg_to_tg(blkg); struct throtl_service_queue *sq = &tg->service_queue; /* * Set the flag to make sure throtl_pending_timer_fn() won't * stop until all throttled bios are dispatched. */ tg->flags |= THROTL_TG_CANCELING; /* * Do not dispatch cgroup without THROTL_TG_PENDING or cgroup * will be inserted to service queue without THROTL_TG_PENDING * set in tg_update_disptime below. Then IO dispatched from * child in tg_dispatch_one_bio will trigger double insertion * and corrupt the tree. */ if (!(tg->flags & THROTL_TG_PENDING)) continue; /* * Update disptime after setting the above flag to make sure * throtl_select_dispatch() won't exit without dispatching. */ tg_update_disptime(tg); throtl_schedule_pending_timer(sq, jiffies + 1); } rcu_read_unlock(); spin_unlock_irq(&q->queue_lock); } #ifdef CONFIG_BLK_DEV_THROTTLING_LOW static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg) { unsigned long rtime = jiffies, wtime = jiffies; if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW]) rtime = tg->last_low_overflow_time[READ]; if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) wtime = tg->last_low_overflow_time[WRITE]; return min(rtime, wtime); } static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg) { struct throtl_service_queue *parent_sq; struct throtl_grp *parent = tg; unsigned long ret = __tg_last_low_overflow_time(tg); while (true) { parent_sq = parent->service_queue.parent_sq; parent = sq_to_tg(parent_sq); if (!parent) break; /* * The parent doesn't have low limit, it always reaches low * limit. Its overflow time is useless for children */ if (!parent->bps[READ][LIMIT_LOW] && !parent->iops[READ][LIMIT_LOW] && !parent->bps[WRITE][LIMIT_LOW] && !parent->iops[WRITE][LIMIT_LOW]) continue; if (time_after(__tg_last_low_overflow_time(parent), ret)) ret = __tg_last_low_overflow_time(parent); } return ret; } static bool throtl_tg_is_idle(struct throtl_grp *tg) { /* * cgroup is idle if: * - single idle is too long, longer than a fixed value (in case user * configure a too big threshold) or 4 times of idletime threshold * - average think time is more than threshold * - IO latency is largely below threshold */ unsigned long time; bool ret; time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold); ret = tg->latency_target == DFL_LATENCY_TARGET || tg->idletime_threshold == DFL_IDLE_THRESHOLD || (ktime_get_ns() >> 10) - tg->last_finish_time > time || tg->avg_idletime > tg->idletime_threshold || (tg->latency_target && tg->bio_cnt && tg->bad_bio_cnt * 5 < tg->bio_cnt); throtl_log(&tg->service_queue, "avg_idle=%ld, idle_threshold=%ld, bad_bio=%d, total_bio=%d, is_idle=%d, scale=%d", tg->avg_idletime, tg->idletime_threshold, tg->bad_bio_cnt, tg->bio_cnt, ret, tg->td->scale); return ret; } static bool throtl_low_limit_reached(struct throtl_grp *tg, int rw) { struct throtl_service_queue *sq = &tg->service_queue; bool limit = tg->bps[rw][LIMIT_LOW] || tg->iops[rw][LIMIT_LOW]; /* * if low limit is zero, low limit is always reached. * if low limit is non-zero, we can check if there is any request * is queued to determine if low limit is reached as we throttle * request according to limit. */ return !limit || sq->nr_queued[rw]; } static bool throtl_tg_can_upgrade(struct throtl_grp *tg) { /* * cgroup reaches low limit when low limit of READ and WRITE are * both reached, it's ok to upgrade to next limit if cgroup reaches * low limit */ if (throtl_low_limit_reached(tg, READ) && throtl_low_limit_reached(tg, WRITE)) return true; if (time_after_eq(jiffies, tg_last_low_overflow_time(tg) + tg->td->throtl_slice) && throtl_tg_is_idle(tg)) return true; return false; } static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg) { while (true) { if (throtl_tg_can_upgrade(tg)) return true; tg = sq_to_tg(tg->service_queue.parent_sq); if (!tg || !tg_to_blkg(tg)->parent) return false; } return false; } static bool throtl_can_upgrade(struct throtl_data *td, struct throtl_grp *this_tg) { struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; if (td->limit_index != LIMIT_LOW) return false; if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice)) return false; rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { struct throtl_grp *tg = blkg_to_tg(blkg); if (tg == this_tg) continue; if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children)) continue; if (!throtl_hierarchy_can_upgrade(tg)) { rcu_read_unlock(); return false; } } rcu_read_unlock(); return true; } static void throtl_upgrade_check(struct throtl_grp *tg) { unsigned long now = jiffies; if (tg->td->limit_index != LIMIT_LOW) return; if (time_after(tg->last_check_time + tg->td->throtl_slice, now)) return; tg->last_check_time = now; if (!time_after_eq(now, __tg_last_low_overflow_time(tg) + tg->td->throtl_slice)) return; if (throtl_can_upgrade(tg->td, NULL)) throtl_upgrade_state(tg->td); } static void throtl_upgrade_state(struct throtl_data *td) { struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; throtl_log(&td->service_queue, "upgrade to max"); td->limit_index = LIMIT_MAX; td->low_upgrade_time = jiffies; td->scale = 0; rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { struct throtl_grp *tg = blkg_to_tg(blkg); struct throtl_service_queue *sq = &tg->service_queue; tg->disptime = jiffies - 1; throtl_select_dispatch(sq); throtl_schedule_next_dispatch(sq, true); } rcu_read_unlock(); throtl_select_dispatch(&td->service_queue); throtl_schedule_next_dispatch(&td->service_queue, true); queue_work(kthrotld_workqueue, &td->dispatch_work); } static void throtl_downgrade_state(struct throtl_data *td) { td->scale /= 2; throtl_log(&td->service_queue, "downgrade, scale %d", td->scale); if (td->scale) { td->low_upgrade_time = jiffies - td->scale * td->throtl_slice; return; } td->limit_index = LIMIT_LOW; td->low_downgrade_time = jiffies; } static bool throtl_tg_can_downgrade(struct throtl_grp *tg) { struct throtl_data *td = tg->td; unsigned long now = jiffies; /* * If cgroup is below low limit, consider downgrade and throttle other * cgroups */ if (time_after_eq(now, tg_last_low_overflow_time(tg) + td->throtl_slice) && (!throtl_tg_is_idle(tg) || !list_empty(&tg_to_blkg(tg)->blkcg->css.children))) return true; return false; } static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg) { struct throtl_data *td = tg->td; if (time_before(jiffies, td->low_upgrade_time + td->throtl_slice)) return false; while (true) { if (!throtl_tg_can_downgrade(tg)) return false; tg = sq_to_tg(tg->service_queue.parent_sq); if (!tg || !tg_to_blkg(tg)->parent) break; } return true; } static void throtl_downgrade_check(struct throtl_grp *tg) { uint64_t bps; unsigned int iops; unsigned long elapsed_time; unsigned long now = jiffies; if (tg->td->limit_index != LIMIT_MAX || !tg->td->limit_valid[LIMIT_LOW]) return; if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children)) return; if (time_after(tg->last_check_time + tg->td->throtl_slice, now)) return; elapsed_time = now - tg->last_check_time; tg->last_check_time = now; if (time_before(now, tg_last_low_overflow_time(tg) + tg->td->throtl_slice)) return; if (tg->bps[READ][LIMIT_LOW]) { bps = tg->last_bytes_disp[READ] * HZ; do_div(bps, elapsed_time); if (bps >= tg->bps[READ][LIMIT_LOW]) tg->last_low_overflow_time[READ] = now; } if (tg->bps[WRITE][LIMIT_LOW]) { bps = tg->last_bytes_disp[WRITE] * HZ; do_div(bps, elapsed_time); if (bps >= tg->bps[WRITE][LIMIT_LOW]) tg->last_low_overflow_time[WRITE] = now; } if (tg->iops[READ][LIMIT_LOW]) { iops = tg->last_io_disp[READ] * HZ / elapsed_time; if (iops >= tg->iops[READ][LIMIT_LOW]) tg->last_low_overflow_time[READ] = now; } if (tg->iops[WRITE][LIMIT_LOW]) { iops = tg->last_io_disp[WRITE] * HZ / elapsed_time; if (iops >= tg->iops[WRITE][LIMIT_LOW]) tg->last_low_overflow_time[WRITE] = now; } /* * If cgroup is below low limit, consider downgrade and throttle other * cgroups */ if (throtl_hierarchy_can_downgrade(tg)) throtl_downgrade_state(tg->td); tg->last_bytes_disp[READ] = 0; tg->last_bytes_disp[WRITE] = 0; tg->last_io_disp[READ] = 0; tg->last_io_disp[WRITE] = 0; } static void blk_throtl_update_idletime(struct throtl_grp *tg) { unsigned long now; unsigned long last_finish_time = tg->last_finish_time; if (last_finish_time == 0) return; now = ktime_get_ns() >> 10; if (now <= last_finish_time || last_finish_time == tg->checked_last_finish_time) return; tg->avg_idletime = (tg->avg_idletime * 7 + now - last_finish_time) >> 3; tg->checked_last_finish_time = last_finish_time; } static void throtl_update_latency_buckets(struct throtl_data *td) { struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE]; int i, cpu, rw; unsigned long last_latency[2] = { 0 }; unsigned long latency[2]; if (!blk_queue_nonrot(td->queue) || !td->limit_valid[LIMIT_LOW]) return; if (time_before(jiffies, td->last_calculate_time + HZ)) return; td->last_calculate_time = jiffies; memset(avg_latency, 0, sizeof(avg_latency)); for (rw = READ; rw <= WRITE; rw++) { for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { struct latency_bucket *tmp = &td->tmp_buckets[rw][i]; for_each_possible_cpu(cpu) { struct latency_bucket *bucket; /* this isn't race free, but ok in practice */ bucket = per_cpu_ptr(td->latency_buckets[rw], cpu); tmp->total_latency += bucket[i].total_latency; tmp->samples += bucket[i].samples; bucket[i].total_latency = 0; bucket[i].samples = 0; } if (tmp->samples >= 32) { int samples = tmp->samples; latency[rw] = tmp->total_latency; tmp->total_latency = 0; tmp->samples = 0; latency[rw] /= samples; if (latency[rw] == 0) continue; avg_latency[rw][i].latency = latency[rw]; } } } for (rw = READ; rw <= WRITE; rw++) { for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { if (!avg_latency[rw][i].latency) { if (td->avg_buckets[rw][i].latency < last_latency[rw]) td->avg_buckets[rw][i].latency = last_latency[rw]; continue; } if (!td->avg_buckets[rw][i].valid) latency[rw] = avg_latency[rw][i].latency; else latency[rw] = (td->avg_buckets[rw][i].latency * 7 + avg_latency[rw][i].latency) >> 3; td->avg_buckets[rw][i].latency = max(latency[rw], last_latency[rw]); td->avg_buckets[rw][i].valid = true; last_latency[rw] = td->avg_buckets[rw][i].latency; } } for (i = 0; i < LATENCY_BUCKET_SIZE; i++) throtl_log(&td->service_queue, "Latency bucket %d: read latency=%ld, read valid=%d, " "write latency=%ld, write valid=%d", i, td->avg_buckets[READ][i].latency, td->avg_buckets[READ][i].valid, td->avg_buckets[WRITE][i].latency, td->avg_buckets[WRITE][i].valid); } #else static inline void throtl_update_latency_buckets(struct throtl_data *td) { } static void blk_throtl_update_idletime(struct throtl_grp *tg) { } static void throtl_downgrade_check(struct throtl_grp *tg) { } static void throtl_upgrade_check(struct throtl_grp *tg) { } static bool throtl_can_upgrade(struct throtl_data *td, struct throtl_grp *this_tg) { return false; } static void throtl_upgrade_state(struct throtl_data *td) { } #endif bool __blk_throtl_bio(struct bio *bio) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct blkcg_gq *blkg = bio->bi_blkg; struct throtl_qnode *qn = NULL; struct throtl_grp *tg = blkg_to_tg(blkg); struct throtl_service_queue *sq; bool rw = bio_data_dir(bio); bool throttled = false; struct throtl_data *td = tg->td; rcu_read_lock(); spin_lock_irq(&q->queue_lock); throtl_update_latency_buckets(td); blk_throtl_update_idletime(tg); sq = &tg->service_queue; again: while (true) { if (tg->last_low_overflow_time[rw] == 0) tg->last_low_overflow_time[rw] = jiffies; throtl_downgrade_check(tg); throtl_upgrade_check(tg); /* throtl is FIFO - if bios are already queued, should queue */ if (sq->nr_queued[rw]) break; /* if above limits, break to queue */ if (!tg_may_dispatch(tg, bio, NULL)) { tg->last_low_overflow_time[rw] = jiffies; if (throtl_can_upgrade(td, tg)) { throtl_upgrade_state(td); goto again; } break; } /* within limits, let's charge and dispatch directly */ throtl_charge_bio(tg, bio); /* * We need to trim slice even when bios are not being queued * otherwise it might happen that a bio is not queued for * a long time and slice keeps on extending and trim is not * called for a long time. Now if limits are reduced suddenly * we take into account all the IO dispatched so far at new * low rate and * newly queued IO gets a really long dispatch * time. * * So keep on trimming slice even if bio is not queued. */ throtl_trim_slice(tg, rw); /* * @bio passed through this layer without being throttled. * Climb up the ladder. If we're already at the top, it * can be executed directly. */ qn = &tg->qnode_on_parent[rw]; sq = sq->parent_sq; tg = sq_to_tg(sq); if (!tg) { bio_set_flag(bio, BIO_BPS_THROTTLED); goto out_unlock; } } /* out-of-limit, queue to @tg */ throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d", rw == READ ? 'R' : 'W', tg->bytes_disp[rw], bio->bi_iter.bi_size, tg_bps_limit(tg, rw), tg->io_disp[rw], tg_iops_limit(tg, rw), sq->nr_queued[READ], sq->nr_queued[WRITE]); tg->last_low_overflow_time[rw] = jiffies; td->nr_queued[rw]++; throtl_add_bio_tg(bio, qn, tg); throttled = true; /* * Update @tg's dispatch time and force schedule dispatch if @tg * was empty before @bio. The forced scheduling isn't likely to * cause undue delay as @bio is likely to be dispatched directly if * its @tg's disptime is not in the future. */ if (tg->flags & THROTL_TG_WAS_EMPTY) { tg_update_disptime(tg); throtl_schedule_next_dispatch(tg->service_queue.parent_sq, true); } out_unlock: #ifdef CONFIG_BLK_DEV_THROTTLING_LOW if (throttled || !td->track_bio_latency) bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; #endif spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); return throttled; } #ifdef CONFIG_BLK_DEV_THROTTLING_LOW static void throtl_track_latency(struct throtl_data *td, sector_t size, enum req_op op, unsigned long time) { const bool rw = op_is_write(op); struct latency_bucket *latency; int index; if (!td || td->limit_index != LIMIT_LOW || !(op == REQ_OP_READ || op == REQ_OP_WRITE) || !blk_queue_nonrot(td->queue)) return; index = request_bucket_index(size); latency = get_cpu_ptr(td->latency_buckets[rw]); latency[index].total_latency += time; latency[index].samples++; put_cpu_ptr(td->latency_buckets[rw]); } void blk_throtl_stat_add(struct request *rq, u64 time_ns) { struct request_queue *q = rq->q; struct throtl_data *td = q->td; throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq), time_ns >> 10); } void blk_throtl_bio_endio(struct bio *bio) { struct blkcg_gq *blkg; struct throtl_grp *tg; u64 finish_time_ns; unsigned long finish_time; unsigned long start_time; unsigned long lat; int rw = bio_data_dir(bio); blkg = bio->bi_blkg; if (!blkg) return; tg = blkg_to_tg(blkg); if (!tg->td->limit_valid[LIMIT_LOW]) return; finish_time_ns = ktime_get_ns(); tg->last_finish_time = finish_time_ns >> 10; start_time = bio_issue_time(&bio->bi_issue) >> 10; finish_time = __bio_issue_time(finish_time_ns) >> 10; if (!start_time || finish_time <= start_time) return; lat = finish_time - start_time; /* this is only for bio based driver */ if (!(bio->bi_issue.value & BIO_ISSUE_THROTL_SKIP_LATENCY)) throtl_track_latency(tg->td, bio_issue_size(&bio->bi_issue), bio_op(bio), lat); if (tg->latency_target && lat >= tg->td->filtered_latency) { int bucket; unsigned int threshold; bucket = request_bucket_index(bio_issue_size(&bio->bi_issue)); threshold = tg->td->avg_buckets[rw][bucket].latency + tg->latency_target; if (lat > threshold) tg->bad_bio_cnt++; /* * Not race free, could get wrong count, which means cgroups * will be throttled */ tg->bio_cnt++; } if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) { tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies; tg->bio_cnt /= 2; tg->bad_bio_cnt /= 2; } } #endif int blk_throtl_init(struct gendisk *disk) { struct request_queue *q = disk->queue; struct throtl_data *td; int ret; td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node); if (!td) return -ENOMEM; td->latency_buckets[READ] = __alloc_percpu(sizeof(struct latency_bucket) * LATENCY_BUCKET_SIZE, __alignof__(u64)); if (!td->latency_buckets[READ]) { kfree(td); return -ENOMEM; } td->latency_buckets[WRITE] = __alloc_percpu(sizeof(struct latency_bucket) * LATENCY_BUCKET_SIZE, __alignof__(u64)); if (!td->latency_buckets[WRITE]) { free_percpu(td->latency_buckets[READ]); kfree(td); return -ENOMEM; } INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn); throtl_service_queue_init(&td->service_queue); q->td = td; td->queue = q; td->limit_valid[LIMIT_MAX] = true; td->limit_index = LIMIT_MAX; td->low_upgrade_time = jiffies; td->low_downgrade_time = jiffies; /* activate policy */ ret = blkcg_activate_policy(disk, &blkcg_policy_throtl); if (ret) { free_percpu(td->latency_buckets[READ]); free_percpu(td->latency_buckets[WRITE]); kfree(td); } return ret; } void blk_throtl_exit(struct gendisk *disk) { struct request_queue *q = disk->queue; BUG_ON(!q->td); del_timer_sync(&q->td->service_queue.pending_timer); throtl_shutdown_wq(q); blkcg_deactivate_policy(disk, &blkcg_policy_throtl); free_percpu(q->td->latency_buckets[READ]); free_percpu(q->td->latency_buckets[WRITE]); kfree(q->td); } void blk_throtl_register(struct gendisk *disk) { struct request_queue *q = disk->queue; struct throtl_data *td; int i; td = q->td; BUG_ON(!td); if (blk_queue_nonrot(q)) { td->throtl_slice = DFL_THROTL_SLICE_SSD; td->filtered_latency = LATENCY_FILTERED_SSD; } else { td->throtl_slice = DFL_THROTL_SLICE_HD; td->filtered_latency = LATENCY_FILTERED_HD; for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { td->avg_buckets[READ][i].latency = DFL_HD_BASELINE_LATENCY; td->avg_buckets[WRITE][i].latency = DFL_HD_BASELINE_LATENCY; } } #ifndef CONFIG_BLK_DEV_THROTTLING_LOW /* if no low limit, use previous default */ td->throtl_slice = DFL_THROTL_SLICE_HD; #else td->track_bio_latency = !queue_is_mq(q); if (!td->track_bio_latency) blk_stat_enable_accounting(q); #endif } #ifdef CONFIG_BLK_DEV_THROTTLING_LOW ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page) { if (!q->td) return -EINVAL; return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice)); } ssize_t blk_throtl_sample_time_store(struct request_queue *q, const char *page, size_t count) { unsigned long v; unsigned long t; if (!q->td) return -EINVAL; if (kstrtoul(page, 10, &v)) return -EINVAL; t = msecs_to_jiffies(v); if (t == 0 || t > MAX_THROTL_SLICE) return -EINVAL; q->td->throtl_slice = t; return count; } #endif static int __init throtl_init(void) { kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0); if (!kthrotld_workqueue) panic("Failed to create kthrotld\n"); return blkcg_policy_register(&blkcg_policy_throtl); } module_init(throtl_init); |
| 6 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Point-to-Point Tunneling Protocol for Linux * * Authors: Dmitry Kozlov <xeb@mail.ru> */ #include <linux/string.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/ppp_channel.h> #include <linux/ppp_defs.h> #include <linux/if_pppox.h> #include <linux/ppp-ioctl.h> #include <linux/notifier.h> #include <linux/file.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/rcupdate.h> #include <linux/security.h> #include <linux/spinlock.h> #include <net/sock.h> #include <net/protocol.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/gre.h> #include <net/pptp.h> #include <linux/uaccess.h> #define PPTP_DRIVER_VERSION "0.8.5" #define MAX_CALLID 65535 static DECLARE_BITMAP(callid_bitmap, MAX_CALLID + 1); static struct pppox_sock __rcu **callid_sock; static DEFINE_SPINLOCK(chan_lock); static struct proto pptp_sk_proto __read_mostly; static const struct ppp_channel_ops pptp_chan_ops; static const struct proto_ops pptp_ops; static struct pppox_sock *lookup_chan(u16 call_id, __be32 s_addr) { struct pppox_sock *sock; struct pptp_opt *opt; rcu_read_lock(); sock = rcu_dereference(callid_sock[call_id]); if (sock) { opt = &sock->proto.pptp; if (opt->dst_addr.sin_addr.s_addr != s_addr) sock = NULL; else sock_hold(sk_pppox(sock)); } rcu_read_unlock(); return sock; } static int lookup_chan_dst(u16 call_id, __be32 d_addr) { struct pppox_sock *sock; struct pptp_opt *opt; int i; rcu_read_lock(); i = 1; for_each_set_bit_from(i, callid_bitmap, MAX_CALLID) { sock = rcu_dereference(callid_sock[i]); if (!sock) continue; opt = &sock->proto.pptp; if (opt->dst_addr.call_id == call_id && opt->dst_addr.sin_addr.s_addr == d_addr) break; } rcu_read_unlock(); return i < MAX_CALLID; } static int add_chan(struct pppox_sock *sock, struct pptp_addr *sa) { static int call_id; spin_lock(&chan_lock); if (!sa->call_id) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1); if (call_id == MAX_CALLID) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1); if (call_id == MAX_CALLID) goto out_err; } sa->call_id = call_id; } else if (test_bit(sa->call_id, callid_bitmap)) { goto out_err; } sock->proto.pptp.src_addr = *sa; set_bit(sa->call_id, callid_bitmap); rcu_assign_pointer(callid_sock[sa->call_id], sock); spin_unlock(&chan_lock); return 0; out_err: spin_unlock(&chan_lock); return -1; } static void del_chan(struct pppox_sock *sock) { spin_lock(&chan_lock); clear_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap); RCU_INIT_POINTER(callid_sock[sock->proto.pptp.src_addr.call_id], NULL); spin_unlock(&chan_lock); } static struct rtable *pptp_route_output(const struct pppox_sock *po, struct flowi4 *fl4) { const struct sock *sk = &po->sk; struct net *net; net = sock_net(sk); flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, 0, RT_SCOPE_UNIVERSE, IPPROTO_GRE, 0, po->proto.pptp.dst_addr.sin_addr.s_addr, po->proto.pptp.src_addr.sin_addr.s_addr, 0, 0, sock_net_uid(net, sk)); security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); } static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) { struct sock *sk = chan->private; struct pppox_sock *po = pppox_sk(sk); struct net *net = sock_net(sk); struct pptp_opt *opt = &po->proto.pptp; struct pptp_gre_header *hdr; unsigned int header_len = sizeof(*hdr); struct flowi4 fl4; int islcp; int len; unsigned char *data; __u32 seq_recv; struct rtable *rt; struct net_device *tdev; struct iphdr *iph; int max_headroom; if (sk_pppox(po)->sk_state & PPPOX_DEAD) goto tx_error; rt = pptp_route_output(po, &fl4); if (IS_ERR(rt)) goto tx_error; tdev = rt->dst.dev; max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(*iph) + sizeof(*hdr) + 2; if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); goto tx_error; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); consume_skb(skb); skb = new_skb; } data = skb->data; islcp = ((data[0] << 8) + data[1]) == PPP_LCP && 1 <= data[2] && data[2] <= 7; /* compress protocol field */ if ((opt->ppp_flags & SC_COMP_PROT) && data[0] == 0 && !islcp) skb_pull(skb, 1); /* Put in the address/control bytes if necessary */ if ((opt->ppp_flags & SC_COMP_AC) == 0 || islcp) { data = skb_push(skb, 2); data[0] = PPP_ALLSTATIONS; data[1] = PPP_UI; } len = skb->len; seq_recv = opt->seq_recv; if (opt->ack_sent == seq_recv) header_len -= sizeof(hdr->ack); /* Push down and install GRE header */ skb_push(skb, header_len); hdr = (struct pptp_gre_header *)(skb->data); hdr->gre_hd.flags = GRE_KEY | GRE_VERSION_1 | GRE_SEQ; hdr->gre_hd.protocol = GRE_PROTO_PPP; hdr->call_id = htons(opt->dst_addr.call_id); hdr->seq = htonl(++opt->seq_sent); if (opt->ack_sent != seq_recv) { /* send ack with this message */ hdr->gre_hd.flags |= GRE_ACK; hdr->ack = htonl(seq_recv); opt->ack_sent = seq_recv; } hdr->payload_len = htons(len); /* Push down and install the IP header. */ skb_reset_transport_header(skb); skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr) >> 2; if (ip_dont_fragment(sk, &rt->dst)) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->protocol = IPPROTO_GRE; iph->tos = 0; iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; iph->ttl = ip4_dst_hoplimit(&rt->dst); iph->tot_len = htons(skb->len); skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); nf_reset_ct(skb); skb->ip_summed = CHECKSUM_NONE; ip_select_ident(net, skb, NULL); ip_send_check(iph); ip_local_out(net, skb->sk, skb); return 1; tx_error: kfree_skb(skb); return 1; } static int pptp_rcv_core(struct sock *sk, struct sk_buff *skb) { struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; int headersize, payload_len, seq; __u8 *payload; struct pptp_gre_header *header; if (!(sk->sk_state & PPPOX_CONNECTED)) { if (sock_queue_rcv_skb(sk, skb)) goto drop; return NET_RX_SUCCESS; } header = (struct pptp_gre_header *)(skb->data); headersize = sizeof(*header); /* test if acknowledgement present */ if (GRE_IS_ACK(header->gre_hd.flags)) { __u32 ack; if (!pskb_may_pull(skb, headersize)) goto drop; header = (struct pptp_gre_header *)(skb->data); /* ack in different place if S = 0 */ ack = GRE_IS_SEQ(header->gre_hd.flags) ? ntohl(header->ack) : ntohl(header->seq); if (ack > opt->ack_recv) opt->ack_recv = ack; /* also handle sequence number wrap-around */ if (WRAPPED(ack, opt->ack_recv)) opt->ack_recv = ack; } else { headersize -= sizeof(header->ack); } /* test if payload present */ if (!GRE_IS_SEQ(header->gre_hd.flags)) goto drop; payload_len = ntohs(header->payload_len); seq = ntohl(header->seq); /* check for incomplete packet (length smaller than expected) */ if (!pskb_may_pull(skb, headersize + payload_len)) goto drop; payload = skb->data + headersize; /* check for expected sequence number */ if (seq < opt->seq_recv + 1 || WRAPPED(opt->seq_recv, seq)) { if ((payload[0] == PPP_ALLSTATIONS) && (payload[1] == PPP_UI) && (PPP_PROTOCOL(payload) == PPP_LCP) && ((payload[4] == PPP_LCP_ECHOREQ) || (payload[4] == PPP_LCP_ECHOREP))) goto allow_packet; } else { opt->seq_recv = seq; allow_packet: skb_pull(skb, headersize); if (payload[0] == PPP_ALLSTATIONS && payload[1] == PPP_UI) { /* chop off address/control */ if (skb->len < 3) goto drop; skb_pull(skb, 2); } skb->ip_summed = CHECKSUM_NONE; skb_set_network_header(skb, skb->head-skb->data); ppp_input(&po->chan, skb); return NET_RX_SUCCESS; } drop: kfree_skb(skb); return NET_RX_DROP; } static int pptp_rcv(struct sk_buff *skb) { struct pppox_sock *po; struct pptp_gre_header *header; struct iphdr *iph; if (skb->pkt_type != PACKET_HOST) goto drop; if (!pskb_may_pull(skb, 12)) goto drop; iph = ip_hdr(skb); header = (struct pptp_gre_header *)skb->data; if (header->gre_hd.protocol != GRE_PROTO_PPP || /* PPTP-GRE protocol for PPTP */ GRE_IS_CSUM(header->gre_hd.flags) || /* flag CSUM should be clear */ GRE_IS_ROUTING(header->gre_hd.flags) || /* flag ROUTING should be clear */ !GRE_IS_KEY(header->gre_hd.flags) || /* flag KEY should be set */ (header->gre_hd.flags & GRE_FLAGS)) /* flag Recursion Ctrl should be clear */ /* if invalid, discard this packet */ goto drop; po = lookup_chan(ntohs(header->call_id), iph->saddr); if (po) { skb_dst_drop(skb); nf_reset_ct(skb); return sk_receive_skb(sk_pppox(po), skb, 0); } drop: kfree_skb(skb); return NET_RX_DROP; } static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, int sockaddr_len) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) return -EINVAL; lock_sock(sk); if (sk->sk_state & PPPOX_DEAD) { error = -EALREADY; goto out; } if (sk->sk_state & PPPOX_BOUND) { error = -EBUSY; goto out; } if (add_chan(po, &sp->sa_addr.pptp)) error = -EBUSY; else sk->sk_state |= PPPOX_BOUND; out: release_sock(sk); return error; } static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, int sockaddr_len, int flags) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; struct rtable *rt; struct flowi4 fl4; int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) return -EINVAL; if (sp->sa_protocol != PX_PROTO_PPTP) return -EINVAL; if (lookup_chan_dst(sp->sa_addr.pptp.call_id, sp->sa_addr.pptp.sin_addr.s_addr)) return -EALREADY; lock_sock(sk); /* Check for already bound sockets */ if (sk->sk_state & PPPOX_CONNECTED) { error = -EBUSY; goto end; } /* Check for already disconnected sockets, on attempts to disconnect */ if (sk->sk_state & PPPOX_DEAD) { error = -EALREADY; goto end; } if (!opt->src_addr.sin_addr.s_addr || !sp->sa_addr.pptp.sin_addr.s_addr) { error = -EINVAL; goto end; } po->chan.private = sk; po->chan.ops = &pptp_chan_ops; rt = pptp_route_output(po, &fl4); if (IS_ERR(rt)) { error = -EHOSTUNREACH; goto end; } sk_setup_caps(sk, &rt->dst); po->chan.mtu = dst_mtu(&rt->dst); if (!po->chan.mtu) po->chan.mtu = PPP_MRU; po->chan.mtu -= PPTP_HEADER_OVERHEAD; po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header); error = ppp_register_channel(&po->chan); if (error) { pr_err("PPTP: failed to register PPP channel (%d)\n", error); goto end; } opt->dst_addr = sp->sa_addr.pptp; sk->sk_state |= PPPOX_CONNECTED; end: release_sock(sk); return error; } static int pptp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { int len = sizeof(struct sockaddr_pppox); struct sockaddr_pppox sp; memset(&sp.sa_addr, 0, sizeof(sp.sa_addr)); sp.sa_family = AF_PPPOX; sp.sa_protocol = PX_PROTO_PPTP; sp.sa_addr.pptp = pppox_sk(sock->sk)->proto.pptp.src_addr; memcpy(uaddr, &sp, len); return len; } static int pptp_release(struct socket *sock) { struct sock *sk = sock->sk; struct pppox_sock *po; int error = 0; if (!sk) return 0; lock_sock(sk); if (sock_flag(sk, SOCK_DEAD)) { release_sock(sk); return -EBADF; } po = pppox_sk(sk); del_chan(po); synchronize_rcu(); pppox_unbind_sock(sk); sk->sk_state = PPPOX_DEAD; sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return error; } static void pptp_sock_destruct(struct sock *sk) { if (!(sk->sk_state & PPPOX_DEAD)) { del_chan(pppox_sk(sk)); pppox_unbind_sock(sk); } skb_queue_purge(&sk->sk_receive_queue); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); } static int pptp_create(struct net *net, struct socket *sock, int kern) { int error = -ENOMEM; struct sock *sk; struct pppox_sock *po; struct pptp_opt *opt; sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pptp_sk_proto, kern); if (!sk) goto out; sock_init_data(sock, sk); sock->state = SS_UNCONNECTED; sock->ops = &pptp_ops; sk->sk_backlog_rcv = pptp_rcv_core; sk->sk_state = PPPOX_NONE; sk->sk_type = SOCK_STREAM; sk->sk_family = PF_PPPOX; sk->sk_protocol = PX_PROTO_PPTP; sk->sk_destruct = pptp_sock_destruct; po = pppox_sk(sk); opt = &po->proto.pptp; opt->seq_sent = 0; opt->seq_recv = 0xffffffff; opt->ack_recv = 0; opt->ack_sent = 0xffffffff; error = 0; out: return error; } static int pptp_ppp_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) { struct sock *sk = chan->private; struct pppox_sock *po = pppox_sk(sk); struct pptp_opt *opt = &po->proto.pptp; void __user *argp = (void __user *)arg; int __user *p = argp; int err, val; err = -EFAULT; switch (cmd) { case PPPIOCGFLAGS: val = opt->ppp_flags; if (put_user(val, p)) break; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; opt->ppp_flags = val & ~SC_RCV_BITS; err = 0; break; default: err = -ENOTTY; } return err; } static const struct ppp_channel_ops pptp_chan_ops = { .start_xmit = pptp_xmit, .ioctl = pptp_ppp_ioctl, }; static struct proto pptp_sk_proto __read_mostly = { .name = "PPTP", .owner = THIS_MODULE, .obj_size = sizeof(struct pppox_sock), }; static const struct proto_ops pptp_ops = { .family = AF_PPPOX, .owner = THIS_MODULE, .release = pptp_release, .bind = pptp_bind, .connect = pptp_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = pptp_getname, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = sock_no_sendmsg, .recvmsg = sock_no_recvmsg, .mmap = sock_no_mmap, .ioctl = pppox_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = pppox_compat_ioctl, #endif }; static const struct pppox_proto pppox_pptp_proto = { .create = pptp_create, .owner = THIS_MODULE, }; static const struct gre_protocol gre_pptp_protocol = { .handler = pptp_rcv, }; static int __init pptp_init_module(void) { int err = 0; pr_info("PPTP driver version " PPTP_DRIVER_VERSION "\n"); callid_sock = vzalloc(array_size(sizeof(void *), (MAX_CALLID + 1))); if (!callid_sock) return -ENOMEM; err = gre_add_protocol(&gre_pptp_protocol, GREPROTO_PPTP); if (err) { pr_err("PPTP: can't add gre protocol\n"); goto out_mem_free; } err = proto_register(&pptp_sk_proto, 0); if (err) { pr_err("PPTP: can't register sk_proto\n"); goto out_gre_del_protocol; } err = register_pppox_proto(PX_PROTO_PPTP, &pppox_pptp_proto); if (err) { pr_err("PPTP: can't register pppox_proto\n"); goto out_unregister_sk_proto; } return 0; out_unregister_sk_proto: proto_unregister(&pptp_sk_proto); out_gre_del_protocol: gre_del_protocol(&gre_pptp_protocol, GREPROTO_PPTP); out_mem_free: vfree(callid_sock); return err; } static void __exit pptp_exit_module(void) { unregister_pppox_proto(PX_PROTO_PPTP); proto_unregister(&pptp_sk_proto); gre_del_protocol(&gre_pptp_protocol, GREPROTO_PPTP); vfree(callid_sock); } module_init(pptp_init_module); module_exit(pptp_exit_module); MODULE_DESCRIPTION("Point-to-Point Tunneling Protocol"); MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_PPTP); |
| 2 64 236 665 160 160 247 248 214 86 82 43 214 35 178 178 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_IP_TUNNELS_H #define __NET_IP_TUNNELS_H 1 #include <linux/if_tunnel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/types.h> #include <linux/u64_stats_sync.h> #include <linux/bitops.h> #include <net/dsfield.h> #include <net/gro_cells.h> #include <net/inet_ecn.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/lwtunnel.h> #include <net/dst_cache.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #endif /* Keep error state on tunnel for 30 sec */ #define IPTUNNEL_ERR_TIMEO (30*HZ) /* Used to memset ip_tunnel padding. */ #define IP_TUNNEL_KEY_SIZE offsetofend(struct ip_tunnel_key, tp_dst) /* Used to memset ipv4 address padding. */ #define IP_TUNNEL_KEY_IPV4_PAD offsetofend(struct ip_tunnel_key, u.ipv4.dst) #define IP_TUNNEL_KEY_IPV4_PAD_LEN \ (sizeof_field(struct ip_tunnel_key, u) - \ sizeof_field(struct ip_tunnel_key, u.ipv4)) struct ip_tunnel_key { __be64 tun_id; union { struct { __be32 src; __be32 dst; } ipv4; struct { struct in6_addr src; struct in6_addr dst; } ipv6; } u; __be16 tun_flags; u8 tos; /* TOS for IPv4, TC for IPv6 */ u8 ttl; /* TTL for IPv4, HL for IPv6 */ __be32 label; /* Flow Label for IPv6 */ u32 nhid; __be16 tp_src; __be16 tp_dst; __u8 flow_flags; }; struct ip_tunnel_encap { u16 type; u16 flags; __be16 sport; __be16 dport; }; /* Flags for ip_tunnel_info mode. */ #define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */ #define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */ #define IP_TUNNEL_INFO_BRIDGE 0x04 /* represents a bridged tunnel id */ /* Maximum tunnel options length. */ #define IP_TUNNEL_OPTS_MAX \ GENMASK((sizeof_field(struct ip_tunnel_info, \ options_len) * BITS_PER_BYTE) - 1, 0) #define ip_tunnel_info_opts(info) \ _Generic(info, \ const struct ip_tunnel_info * : ((const void *)((info) + 1)),\ struct ip_tunnel_info * : ((void *)((info) + 1))\ ) struct ip_tunnel_info { struct ip_tunnel_key key; struct ip_tunnel_encap encap; #ifdef CONFIG_DST_CACHE struct dst_cache dst_cache; #endif u8 options_len; u8 mode; }; /* 6rd prefix/relay information */ #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd_parm { struct in6_addr prefix; __be32 relay_prefix; u16 prefixlen; u16 relay_prefixlen; }; #endif struct ip_tunnel_prl_entry { struct ip_tunnel_prl_entry __rcu *next; __be32 addr; u16 flags; struct rcu_head rcu_head; }; struct metadata_dst; struct ip_tunnel { struct ip_tunnel __rcu *next; struct hlist_node hash_node; struct net_device *dev; netdevice_tracker dev_tracker; struct net *net; /* netns for packet i/o */ unsigned long err_time; /* Time when the last ICMP error * arrived */ int err_count; /* Number of arrived ICMP errors */ /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ u32 index; /* ERSPAN type II index */ u8 erspan_ver; /* ERSPAN version */ u8 dir; /* ERSPAN direction */ u16 hwid; /* ERSPAN hardware ID */ struct dst_cache dst_cache; struct ip_tunnel_parm parms; int mlink; int encap_hlen; /* Encap header length (FOU,GUE) */ int hlen; /* tun_hlen + encap_hlen */ struct ip_tunnel_encap encap; /* for SIT */ #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd_parm ip6rd; #endif struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ unsigned int prl_count; /* # of entries in PRL */ unsigned int ip_tnl_net_id; struct gro_cells gro_cells; __u32 fwmark; bool collect_md; bool ignore_df; }; struct tnl_ptk_info { __be16 flags; __be16 proto; __be32 key; __be32 seq; int hdr_len; }; #define PACKET_RCVD 0 #define PACKET_REJECT 1 #define PACKET_NEXT 2 #define IP_TNL_HASH_BITS 7 #define IP_TNL_HASH_SIZE (1 << IP_TNL_HASH_BITS) struct ip_tunnel_net { struct net_device *fb_tunnel_dev; struct rtnl_link_ops *rtnl_link_ops; struct hlist_head tunnels[IP_TNL_HASH_SIZE]; struct ip_tunnel __rcu *collect_md_tun; int type; }; static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, __be64 tun_id, __be16 tun_flags) { key->tun_id = tun_id; key->u.ipv4.src = saddr; key->u.ipv4.dst = daddr; memset((unsigned char *)key + IP_TUNNEL_KEY_IPV4_PAD, 0, IP_TUNNEL_KEY_IPV4_PAD_LEN); key->tos = tos; key->ttl = ttl; key->label = label; key->tun_flags = tun_flags; /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of * the upper tunnel are used. * E.g: GRE over IPSEC, the tp_src and tp_port are zero. */ key->tp_src = tp_src; key->tp_dst = tp_dst; /* Clear struct padding. */ if (sizeof(*key) != IP_TUNNEL_KEY_SIZE) memset((unsigned char *)key + IP_TUNNEL_KEY_SIZE, 0, sizeof(*key) - IP_TUNNEL_KEY_SIZE); } static inline bool ip_tunnel_dst_cache_usable(const struct sk_buff *skb, const struct ip_tunnel_info *info) { if (skb->mark) return false; if (!info) return true; if (info->key.tun_flags & TUNNEL_NOCACHE) return false; return true; } static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info *tun_info) { return tun_info->mode & IP_TUNNEL_INFO_IPV6 ? AF_INET6 : AF_INET; } static inline __be64 key32_to_tunnel_id(__be32 key) { #ifdef __BIG_ENDIAN return (__force __be64)key; #else return (__force __be64)((__force u64)key << 32); #endif } /* Returns the least-significant 32 bits of a __be64. */ static inline __be32 tunnel_id_to_key32(__be64 tun_id) { #ifdef __BIG_ENDIAN return (__force __be32)tun_id; #else return (__force __be32)((__force u64)tun_id >> 32); #endif } #ifdef CONFIG_INET static inline void ip_tunnel_init_flow(struct flowi4 *fl4, int proto, __be32 daddr, __be32 saddr, __be32 key, __u8 tos, struct net *net, int oif, __u32 mark, __u32 tun_inner_hash, __u8 flow_flags) { memset(fl4, 0, sizeof(*fl4)); if (oif) { fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif); /* Legacy VRF/l3mdev use case */ fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif; } fl4->daddr = daddr; fl4->saddr = saddr; fl4->flowi4_tos = tos; fl4->flowi4_proto = proto; fl4->fl4_gre_key = key; fl4->flowi4_mark = mark; fl4->flowi4_multipath_hash = tun_inner_hash; fl4->flowi4_flags = flow_flags; } int ip_tunnel_init(struct net_device *dev); void ip_tunnel_uninit(struct net_device *dev); void ip_tunnel_dellink(struct net_device *dev, struct list_head *head); struct net *ip_tunnel_get_link_net(const struct net_device *dev); int ip_tunnel_get_iflink(const struct net_device *dev); int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct rtnl_link_ops *ops, char *devname); void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id, struct rtnl_link_ops *ops); void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const u8 proto, int tunnel_hlen); int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, int link, __be16 flags, __be32 remote, __be32 local, __be32 key); void ip_tunnel_md_udp_encap(struct sk_buff *skb, struct ip_tunnel_info *info); int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_error); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *encap); void ip_tunnel_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm *parms); extern const struct header_ops ip_tunnel_header_ops; __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb); struct ip_tunnel_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4); int (*err_handler)(struct sk_buff *skb, u32 info); }; #define MAX_IPTUN_ENCAP_OPS 8 extern const struct ip_tunnel_encap_ops __rcu * iptun_encaps[MAX_IPTUN_ENCAP_OPS]; int ip_tunnel_encap_add_ops(const struct ip_tunnel_encap_ops *op, unsigned int num); int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, unsigned int num); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap); static inline bool pskb_inet_may_pull(struct sk_buff *skb) { int nhlen; switch (skb->protocol) { #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): nhlen = sizeof(struct ipv6hdr); break; #endif case htons(ETH_P_IP): nhlen = sizeof(struct iphdr); break; default: nhlen = 0; } return pskb_network_may_pull(skb, nhlen); } static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; int hlen = -EINVAL; if (e->type == TUNNEL_ENCAP_NONE) return 0; if (e->type >= MAX_IPTUN_ENCAP_OPS) return -EINVAL; rcu_read_lock(); ops = rcu_dereference(iptun_encaps[e->type]); if (likely(ops && ops->encap_hlen)) hlen = ops->encap_hlen(e); rcu_read_unlock(); return hlen; } static inline int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4) { const struct ip_tunnel_encap_ops *ops; int ret = -EINVAL; if (e->type == TUNNEL_ENCAP_NONE) return 0; if (e->type >= MAX_IPTUN_ENCAP_OPS) return -EINVAL; rcu_read_lock(); ops = rcu_dereference(iptun_encaps[e->type]); if (likely(ops && ops->build_header)) ret = ops->build_header(skb, e, protocol, fl4); rcu_read_unlock(); return ret; } /* Extract dsfield from inner protocol */ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, const struct sk_buff *skb) { __be16 payload_protocol = skb_protocol(skb, true); if (payload_protocol == htons(ETH_P_IP)) return iph->tos; else if (payload_protocol == htons(ETH_P_IPV6)) return ipv6_get_dsfield((const struct ipv6hdr *)iph); else return 0; } static inline __be32 ip_tunnel_get_flowlabel(const struct iphdr *iph, const struct sk_buff *skb) { __be16 payload_protocol = skb_protocol(skb, true); if (payload_protocol == htons(ETH_P_IPV6)) return ip6_flowlabel((const struct ipv6hdr *)iph); else return 0; } static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, const struct sk_buff *skb) { __be16 payload_protocol = skb_protocol(skb, true); if (payload_protocol == htons(ETH_P_IP)) return iph->ttl; else if (payload_protocol == htons(ETH_P_IPV6)) return ((const struct ipv6hdr *)iph)->hop_limit; else return 0; } /* Propogate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) { u8 inner = ip_tunnel_get_dsfield(iph, skb); return INET_ECN_encapsulate(tos, inner); } int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, bool raw_proto, bool xnet); static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, bool xnet) { return __iptunnel_pull_header(skb, hdr_len, inner_proto, false, xnet); } void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, u8 proto, u8 tos, u8 ttl, __be16 df, bool xnet); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, int headroom, bool reply); int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); static inline int iptunnel_pull_offloads(struct sk_buff *skb) { if (skb_is_gso(skb)) { int err; err = skb_unclone(skb, GFP_ATOMIC); if (unlikely(err)) return err; skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >> NETIF_F_GSO_SHIFT); } skb->encapsulation = 0; return 0; } static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { if (pkt_len > 0) { struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); u64_stats_add(&tstats->tx_bytes, pkt_len); u64_stats_inc(&tstats->tx_packets); u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); return; } if (pkt_len < 0) { DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_aborted_errors); } else { DEV_STATS_INC(dev, tx_dropped); } } static inline void ip_tunnel_info_opts_get(void *to, const struct ip_tunnel_info *info) { memcpy(to, info + 1, info->options_len); } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { info->options_len = len; if (len > 0) { memcpy(ip_tunnel_info_opts(info), from, len); info->key.tun_flags |= flags; } } static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) { return (struct ip_tunnel_info *)lwtstate->data; } DECLARE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt); /* Returns > 0 if metadata should be collected */ static inline int ip_tunnel_collect_metadata(void) { return static_branch_unlikely(&ip_tunnel_metadata_cnt); } void __init ip_tunnel_core_init(void); void ip_tunnel_need_metadata(void); void ip_tunnel_unneed_metadata(void); #else /* CONFIG_INET */ static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate) { return NULL; } static inline void ip_tunnel_need_metadata(void) { } static inline void ip_tunnel_unneed_metadata(void) { } static inline void ip_tunnel_info_opts_get(void *to, const struct ip_tunnel_info *info) { } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, const void *from, int len, __be16 flags) { info->options_len = 0; } #endif /* CONFIG_INET */ #endif /* __NET_IP_TUNNELS_H */ |
| 6 7 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ #include "netlink.h" #include "main.h" #include <linux/array_size.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/genetlink.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/minmax.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/printk.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/stddef.h> #include <linux/types.h> #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/sock.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" #include "gateway_client.h" #include "gateway_common.h" #include "hard-interface.h" #include "log.h" #include "multicast.h" #include "network-coding.h" #include "originator.h" #include "soft-interface.h" #include "tp_meter.h" #include "translation-table.h" struct genl_family batadv_netlink_family; /* multicast groups */ enum batadv_netlink_multicast_groups { BATADV_NL_MCGRP_CONFIG, BATADV_NL_MCGRP_TPMETER, }; /** * enum batadv_genl_ops_flags - flags for genl_ops's internal_flags */ enum batadv_genl_ops_flags { /** * @BATADV_FLAG_NEED_MESH: request requires valid soft interface in * attribute BATADV_ATTR_MESH_IFINDEX and expects a pointer to it to be * saved in info->user_ptr[0] */ BATADV_FLAG_NEED_MESH = BIT(0), /** * @BATADV_FLAG_NEED_HARDIF: request requires valid hard interface in * attribute BATADV_ATTR_HARD_IFINDEX and expects a pointer to it to be * saved in info->user_ptr[1] */ BATADV_FLAG_NEED_HARDIF = BIT(1), /** * @BATADV_FLAG_NEED_VLAN: request requires valid vlan in * attribute BATADV_ATTR_VLANID and expects a pointer to it to be * saved in info->user_ptr[1] */ BATADV_FLAG_NEED_VLAN = BIT(2), }; static const struct genl_multicast_group batadv_netlink_mcgrps[] = { [BATADV_NL_MCGRP_CONFIG] = { .name = BATADV_NL_MCAST_GROUP_CONFIG }, [BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER }, }; static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_VERSION] = { .type = NLA_STRING }, [BATADV_ATTR_ALGO_NAME] = { .type = NLA_STRING }, [BATADV_ATTR_MESH_IFINDEX] = { .type = NLA_U32 }, [BATADV_ATTR_MESH_IFNAME] = { .type = NLA_STRING }, [BATADV_ATTR_MESH_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_HARD_IFINDEX] = { .type = NLA_U32 }, [BATADV_ATTR_HARD_IFNAME] = { .type = NLA_STRING }, [BATADV_ATTR_HARD_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_ORIG_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TPMETER_RESULT] = { .type = NLA_U8 }, [BATADV_ATTR_TPMETER_TEST_TIME] = { .type = NLA_U32 }, [BATADV_ATTR_TPMETER_BYTES] = { .type = NLA_U64 }, [BATADV_ATTR_TPMETER_COOKIE] = { .type = NLA_U32 }, [BATADV_ATTR_ACTIVE] = { .type = NLA_FLAG }, [BATADV_ATTR_TT_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TT_TTVN] = { .type = NLA_U8 }, [BATADV_ATTR_TT_LAST_TTVN] = { .type = NLA_U8 }, [BATADV_ATTR_TT_CRC32] = { .type = NLA_U32 }, [BATADV_ATTR_TT_VID] = { .type = NLA_U16 }, [BATADV_ATTR_TT_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_FLAG_BEST] = { .type = NLA_FLAG }, [BATADV_ATTR_LAST_SEEN_MSECS] = { .type = NLA_U32 }, [BATADV_ATTR_NEIGH_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TQ] = { .type = NLA_U8 }, [BATADV_ATTR_THROUGHPUT] = { .type = NLA_U32 }, [BATADV_ATTR_BANDWIDTH_UP] = { .type = NLA_U32 }, [BATADV_ATTR_BANDWIDTH_DOWN] = { .type = NLA_U32 }, [BATADV_ATTR_ROUTER] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_OWN] = { .type = NLA_FLAG }, [BATADV_ATTR_BLA_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_VID] = { .type = NLA_U16 }, [BATADV_ATTR_BLA_BACKBONE] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_CRC] = { .type = NLA_U16 }, [BATADV_ATTR_DAT_CACHE_IP4ADDRESS] = { .type = NLA_U32 }, [BATADV_ATTR_DAT_CACHE_HWADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_DAT_CACHE_VID] = { .type = NLA_U16 }, [BATADV_ATTR_MCAST_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_MCAST_FLAGS_PRIV] = { .type = NLA_U32 }, [BATADV_ATTR_VLANID] = { .type = NLA_U16 }, [BATADV_ATTR_AGGREGATED_OGMS_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_AP_ISOLATION_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_ISOLATION_MARK] = { .type = NLA_U32 }, [BATADV_ATTR_ISOLATION_MASK] = { .type = NLA_U32 }, [BATADV_ATTR_BONDING_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_FRAGMENTATION_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_GW_BANDWIDTH_DOWN] = { .type = NLA_U32 }, [BATADV_ATTR_GW_BANDWIDTH_UP] = { .type = NLA_U32 }, [BATADV_ATTR_GW_MODE] = { .type = NLA_U8 }, [BATADV_ATTR_GW_SEL_CLASS] = { .type = NLA_U32 }, [BATADV_ATTR_HOP_PENALTY] = { .type = NLA_U8 }, [BATADV_ATTR_LOG_LEVEL] = { .type = NLA_U32 }, [BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_MULTICAST_FANOUT] = { .type = NLA_U32 }, [BATADV_ATTR_NETWORK_CODING_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_ORIG_INTERVAL] = { .type = NLA_U32 }, [BATADV_ATTR_ELP_INTERVAL] = { .type = NLA_U32 }, [BATADV_ATTR_THROUGHPUT_OVERRIDE] = { .type = NLA_U32 }, }; /** * batadv_netlink_get_ifindex() - Extract an interface index from a message * @nlh: Message header * @attrtype: Attribute which holds an interface index * * Return: interface index, or 0. */ int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) { struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype); return (attr && nla_len(attr) == sizeof(u32)) ? nla_get_u32(attr) : 0; } /** * batadv_netlink_mesh_fill_ap_isolation() - Add ap_isolation softif attribute * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_mesh_fill_ap_isolation(struct sk_buff *msg, struct batadv_priv *bat_priv) { struct batadv_softif_vlan *vlan; u8 ap_isolation; vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); if (!vlan) return 0; ap_isolation = atomic_read(&vlan->ap_isolation); batadv_softif_vlan_put(vlan); return nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, !!ap_isolation); } /** * batadv_netlink_set_mesh_ap_isolation() - Set ap_isolation from genl msg * @attr: parsed BATADV_ATTR_AP_ISOLATION_ENABLED attribute * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_mesh_ap_isolation(struct nlattr *attr, struct batadv_priv *bat_priv) { struct batadv_softif_vlan *vlan; vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); if (!vlan) return -ENOENT; atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); batadv_softif_vlan_put(vlan); return 0; } /** * batadv_netlink_mesh_fill() - Fill message with mesh attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the soft interface information * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_mesh_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags) { struct net_device *soft_iface = bat_priv->soft_iface; struct batadv_hard_iface *primary_if = NULL; struct net_device *hard_iface; void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) || nla_put_string(msg, BATADV_ATTR_ALGO_NAME, bat_priv->algo_ops->name) || nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, soft_iface->ifindex) || nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, soft_iface->name) || nla_put(msg, BATADV_ATTR_MESH_ADDRESS, ETH_ALEN, soft_iface->dev_addr) || nla_put_u8(msg, BATADV_ATTR_TT_TTVN, (u8)atomic_read(&bat_priv->tt.vn))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BLA if (nla_put_u16(msg, BATADV_ATTR_BLA_CRC, ntohs(bat_priv->bla.claim_dest.group))) goto nla_put_failure; #endif if (batadv_mcast_mesh_info_put(msg, bat_priv)) goto nla_put_failure; primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) { hard_iface = primary_if->net_dev; if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, hard_iface->ifindex) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, hard_iface->name) || nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, hard_iface->dev_addr)) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_AGGREGATED_OGMS_ENABLED, !!atomic_read(&bat_priv->aggregated_ogms))) goto nla_put_failure; if (batadv_netlink_mesh_fill_ap_isolation(msg, bat_priv)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MARK, bat_priv->isolation_mark)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MASK, bat_priv->isolation_mark_mask)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_BONDING_ENABLED, !!atomic_read(&bat_priv->bonding))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BLA if (nla_put_u8(msg, BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED, !!atomic_read(&bat_priv->bridge_loop_avoidance))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_BLA */ #ifdef CONFIG_BATMAN_ADV_DAT if (nla_put_u8(msg, BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED, !!atomic_read(&bat_priv->distributed_arp_table))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_DAT */ if (nla_put_u8(msg, BATADV_ATTR_FRAGMENTATION_ENABLED, !!atomic_read(&bat_priv->fragmentation))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_DOWN, atomic_read(&bat_priv->gw.bandwidth_down))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_UP, atomic_read(&bat_priv->gw.bandwidth_up))) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_GW_MODE, atomic_read(&bat_priv->gw.mode))) goto nla_put_failure; if (bat_priv->algo_ops->gw.get_best_gw_node && bat_priv->algo_ops->gw.is_eligible) { /* GW selection class is not available if the routing algorithm * in use does not implement the GW API */ if (nla_put_u32(msg, BATADV_ATTR_GW_SEL_CLASS, atomic_read(&bat_priv->gw.sel_class))) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY, atomic_read(&bat_priv->hop_penalty))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_DEBUG if (nla_put_u32(msg, BATADV_ATTR_LOG_LEVEL, atomic_read(&bat_priv->log_level))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_DEBUG */ #ifdef CONFIG_BATMAN_ADV_MCAST if (nla_put_u8(msg, BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED, !atomic_read(&bat_priv->multicast_mode))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_MULTICAST_FANOUT, atomic_read(&bat_priv->multicast_fanout))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_MCAST */ #ifdef CONFIG_BATMAN_ADV_NC if (nla_put_u8(msg, BATADV_ATTR_NETWORK_CODING_ENABLED, !!atomic_read(&bat_priv->network_coding))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_NC */ if (nla_put_u32(msg, BATADV_ATTR_ORIG_INTERVAL, atomic_read(&bat_priv->orig_interval))) goto nla_put_failure; batadv_hardif_put(primary_if); genlmsg_end(msg, hdr); return 0; nla_put_failure: batadv_hardif_put(primary_if); genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_mesh() - send softif attributes to listener * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success, < 0 on error */ static int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_SET_MESH, 0, 0, 0); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->soft_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_get_mesh() - Get softif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_get_mesh(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_GET_MESH, info->snd_portid, info->snd_seq, 0); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_mesh() - Set softif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]) { attr = info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]; atomic_set(&bat_priv->aggregated_ogms, !!nla_get_u8(attr)); } if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; batadv_netlink_set_mesh_ap_isolation(attr, bat_priv); } if (info->attrs[BATADV_ATTR_ISOLATION_MARK]) { attr = info->attrs[BATADV_ATTR_ISOLATION_MARK]; bat_priv->isolation_mark = nla_get_u32(attr); } if (info->attrs[BATADV_ATTR_ISOLATION_MASK]) { attr = info->attrs[BATADV_ATTR_ISOLATION_MASK]; bat_priv->isolation_mark_mask = nla_get_u32(attr); } if (info->attrs[BATADV_ATTR_BONDING_ENABLED]) { attr = info->attrs[BATADV_ATTR_BONDING_ENABLED]; atomic_set(&bat_priv->bonding, !!nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_BLA if (info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]) { attr = info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]; atomic_set(&bat_priv->bridge_loop_avoidance, !!nla_get_u8(attr)); batadv_bla_status_update(bat_priv->soft_iface); } #endif /* CONFIG_BATMAN_ADV_BLA */ #ifdef CONFIG_BATMAN_ADV_DAT if (info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]) { attr = info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]; atomic_set(&bat_priv->distributed_arp_table, !!nla_get_u8(attr)); batadv_dat_status_update(bat_priv->soft_iface); } #endif /* CONFIG_BATMAN_ADV_DAT */ if (info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); rtnl_lock(); batadv_update_min_mtu(bat_priv->soft_iface); rtnl_unlock(); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]; atomic_set(&bat_priv->gw.bandwidth_down, nla_get_u32(attr)); batadv_gw_tvlv_container_update(bat_priv); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]) { attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]; atomic_set(&bat_priv->gw.bandwidth_up, nla_get_u32(attr)); batadv_gw_tvlv_container_update(bat_priv); } if (info->attrs[BATADV_ATTR_GW_MODE]) { u8 gw_mode; attr = info->attrs[BATADV_ATTR_GW_MODE]; gw_mode = nla_get_u8(attr); if (gw_mode <= BATADV_GW_MODE_SERVER) { /* Invoking batadv_gw_reselect() is not enough to really * de-select the current GW. It will only instruct the * gateway client code to perform a re-election the next * time that this is needed. * * When gw client mode is being switched off the current * GW must be de-selected explicitly otherwise no GW_ADD * uevent is thrown on client mode re-activation. This * is operation is performed in * batadv_gw_check_client_stop(). */ batadv_gw_reselect(bat_priv); /* always call batadv_gw_check_client_stop() before * changing the gateway state */ batadv_gw_check_client_stop(bat_priv); atomic_set(&bat_priv->gw.mode, gw_mode); batadv_gw_tvlv_container_update(bat_priv); } } if (info->attrs[BATADV_ATTR_GW_SEL_CLASS] && bat_priv->algo_ops->gw.get_best_gw_node && bat_priv->algo_ops->gw.is_eligible) { /* setting the GW selection class is allowed only if the routing * algorithm in use implements the GW API */ u32 sel_class_max = bat_priv->algo_ops->gw.sel_class_max; u32 sel_class; attr = info->attrs[BATADV_ATTR_GW_SEL_CLASS]; sel_class = nla_get_u32(attr); if (sel_class >= 1 && sel_class <= sel_class_max) { atomic_set(&bat_priv->gw.sel_class, sel_class); batadv_gw_reselect(bat_priv); } } if (info->attrs[BATADV_ATTR_HOP_PENALTY]) { attr = info->attrs[BATADV_ATTR_HOP_PENALTY]; atomic_set(&bat_priv->hop_penalty, nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_DEBUG if (info->attrs[BATADV_ATTR_LOG_LEVEL]) { attr = info->attrs[BATADV_ATTR_LOG_LEVEL]; atomic_set(&bat_priv->log_level, nla_get_u32(attr) & BATADV_DBG_ALL); } #endif /* CONFIG_BATMAN_ADV_DEBUG */ #ifdef CONFIG_BATMAN_ADV_MCAST if (info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]) { attr = info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]; atomic_set(&bat_priv->multicast_mode, !nla_get_u8(attr)); } if (info->attrs[BATADV_ATTR_MULTICAST_FANOUT]) { attr = info->attrs[BATADV_ATTR_MULTICAST_FANOUT]; atomic_set(&bat_priv->multicast_fanout, nla_get_u32(attr)); } #endif /* CONFIG_BATMAN_ADV_MCAST */ #ifdef CONFIG_BATMAN_ADV_NC if (info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]) { attr = info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]; atomic_set(&bat_priv->network_coding, !!nla_get_u8(attr)); batadv_nc_status_update(bat_priv->soft_iface); } #endif /* CONFIG_BATMAN_ADV_NC */ if (info->attrs[BATADV_ATTR_ORIG_INTERVAL]) { u32 orig_interval; attr = info->attrs[BATADV_ATTR_ORIG_INTERVAL]; orig_interval = nla_get_u32(attr); orig_interval = min_t(u32, orig_interval, INT_MAX); orig_interval = max_t(u32, orig_interval, 2 * BATADV_JITTER); atomic_set(&bat_priv->orig_interval, orig_interval); } batadv_netlink_notify_mesh(bat_priv); return 0; } /** * batadv_netlink_tp_meter_put() - Fill information of started tp_meter session * @msg: netlink message to be sent back * @cookie: tp meter session cookie * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_put(struct sk_buff *msg, u32 cookie) { if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie)) return -ENOBUFS; return 0; } /** * batadv_netlink_tpmeter_notify() - send tp_meter result via netlink to client * @bat_priv: the bat priv with all the soft interface information * @dst: destination of tp_meter session * @result: reason for tp meter session stop * @test_time: total time of the tp_meter session * @total_bytes: bytes acked to the receiver * @cookie: cookie of tp_meter session * * Return: 0 on success, < 0 on error */ int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst, u8 result, u32 test_time, u64 total_bytes, u32 cookie) { struct sk_buff *msg; void *hdr; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &batadv_netlink_family, 0, BATADV_CMD_TP_METER); if (!hdr) { ret = -ENOBUFS; goto err_genlmsg; } if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_TPMETER_TEST_TIME, test_time)) goto nla_put_failure; if (nla_put_u64_64bit(msg, BATADV_ATTR_TPMETER_BYTES, total_bytes, BATADV_ATTR_PAD)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_TPMETER_RESULT, result)) goto nla_put_failure; if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, dst)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->soft_iface), msg, 0, BATADV_NL_MCGRP_TPMETER, GFP_KERNEL); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); ret = -EMSGSIZE; err_genlmsg: nlmsg_free(msg); return ret; } /** * batadv_netlink_tp_meter_start() - Start a new tp_meter session * @skb: received netlink message * @info: receiver information * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg = NULL; u32 test_length; void *msg_head; u32 cookie; u8 *dst; int ret; if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; if (!info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]) return -EINVAL; dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); test_length = nla_get_u32(info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto out; } msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq, &batadv_netlink_family, 0, BATADV_CMD_TP_METER); if (!msg_head) { ret = -ENOBUFS; goto out; } batadv_tp_start(bat_priv, dst, test_length, &cookie); ret = batadv_netlink_tp_meter_put(msg, cookie); out: if (ret) { if (msg) nlmsg_free(msg); return ret; } genlmsg_end(msg, msg_head); return genlmsg_reply(msg, info); } /** * batadv_netlink_tp_meter_cancel() - Cancel a running tp_meter session * @skb: received netlink message * @info: receiver information * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; u8 *dst; int ret = 0; if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); batadv_tp_stop(bat_priv, dst, BATADV_TP_REASON_CANCEL); return ret; } /** * batadv_netlink_hardif_fill() - Fill message with hardif attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the soft interface information * @hard_iface: hard interface which was modified * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * @cb: Control block containing additional options * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_hardif_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, struct batadv_hard_iface *hard_iface, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags, struct netlink_callback *cb) { struct net_device *net_dev = hard_iface->net_dev; void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (cb) genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, bat_priv->soft_iface->ifindex)) goto nla_put_failure; if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, bat_priv->soft_iface->name)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, net_dev->ifindex) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, net_dev->name) || nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, net_dev->dev_addr)) goto nla_put_failure; if (hard_iface->if_status == BATADV_IF_ACTIVE) { if (nla_put_flag(msg, BATADV_ATTR_ACTIVE)) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY, atomic_read(&hard_iface->hop_penalty))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BATMAN_V if (nla_put_u32(msg, BATADV_ATTR_ELP_INTERVAL, atomic_read(&hard_iface->bat_v.elp_interval))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_THROUGHPUT_OVERRIDE, atomic_read(&hard_iface->bat_v.throughput_override))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_BATMAN_V */ genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_hardif() - send hardif attributes to listener * @bat_priv: the bat priv with all the soft interface information * @hard_iface: hard interface which was modified * * Return: 0 on success, < 0 on error */ static int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv, struct batadv_hard_iface *hard_iface) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_SET_HARDIF, 0, 0, 0, NULL); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->soft_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_get_hardif() - Get hardif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_get_hardif(struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_GET_HARDIF, info->snd_portid, info->snd_seq, 0, NULL); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_hardif() - Set hardif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_hardif(struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_HOP_PENALTY]) { attr = info->attrs[BATADV_ATTR_HOP_PENALTY]; atomic_set(&hard_iface->hop_penalty, nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_BATMAN_V if (info->attrs[BATADV_ATTR_ELP_INTERVAL]) { attr = info->attrs[BATADV_ATTR_ELP_INTERVAL]; atomic_set(&hard_iface->bat_v.elp_interval, nla_get_u32(attr)); } if (info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]) { attr = info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]; atomic_set(&hard_iface->bat_v.throughput_override, nla_get_u32(attr)); } #endif /* CONFIG_BATMAN_ADV_BATMAN_V */ batadv_netlink_notify_hardif(bat_priv, hard_iface); return 0; } /** * batadv_netlink_dump_hardif() - Dump all hard interface into a messages * @msg: Netlink message to dump into * @cb: Parameters from query * * Return: error code, or length of reply message on success */ static int batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hard_iface *hard_iface; struct batadv_priv *bat_priv; int ifindex; int portid = NETLINK_CB(cb->skb).portid; int skip = cb->args[0]; int i = 0; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface) return -ENODEV; if (!batadv_softif_is_valid(soft_iface)) { dev_put(soft_iface); return -ENODEV; } bat_priv = netdev_priv(soft_iface); rtnl_lock(); cb->seq = batadv_hardif_generation << 1 | 1; list_for_each_entry(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != soft_iface) continue; if (i++ < skip) continue; if (batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_GET_HARDIF, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb)) { i--; break; } } rtnl_unlock(); dev_put(soft_iface); cb->args[0] = i; return msg->len; } /** * batadv_netlink_vlan_fill() - Fill message with vlan attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the soft interface information * @vlan: vlan which was modified * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_vlan_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, struct batadv_softif_vlan *vlan, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, bat_priv->soft_iface->ifindex)) goto nla_put_failure; if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, bat_priv->soft_iface->name)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, !!atomic_read(&vlan->ap_isolation))) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_vlan() - send vlan attributes to listener * @bat_priv: the bat priv with all the soft interface information * @vlan: vlan which was modified * * Return: 0 on success, < 0 on error */ static int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv, struct batadv_softif_vlan *vlan) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_SET_VLAN, 0, 0, 0); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->soft_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_get_vlan() - Get vlan attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_get_vlan(struct sk_buff *skb, struct genl_info *info) { struct batadv_softif_vlan *vlan = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_GET_VLAN, info->snd_portid, info->snd_seq, 0); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_vlan() - Get vlan attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info) { struct batadv_softif_vlan *vlan = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); } batadv_netlink_notify_vlan(bat_priv, vlan); return 0; } /** * batadv_get_softif_from_info() - Retrieve soft interface from genl attributes * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to soft interface (with increased refcnt) on success, error * pointer on error */ static struct net_device * batadv_get_softif_from_info(struct net *net, struct genl_info *info) { struct net_device *soft_iface; int ifindex; if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) return ERR_PTR(-EINVAL); ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface) return ERR_PTR(-ENODEV); if (!batadv_softif_is_valid(soft_iface)) goto err_put_softif; return soft_iface; err_put_softif: dev_put(soft_iface); return ERR_PTR(-EINVAL); } /** * batadv_get_hardif_from_info() - Retrieve hardif from genl attributes * @bat_priv: the bat priv with all the soft interface information * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to hard interface (with increased refcnt) on success, error * pointer on error */ static struct batadv_hard_iface * batadv_get_hardif_from_info(struct batadv_priv *bat_priv, struct net *net, struct genl_info *info) { struct batadv_hard_iface *hard_iface; struct net_device *hard_dev; unsigned int hardif_index; if (!info->attrs[BATADV_ATTR_HARD_IFINDEX]) return ERR_PTR(-EINVAL); hardif_index = nla_get_u32(info->attrs[BATADV_ATTR_HARD_IFINDEX]); hard_dev = dev_get_by_index(net, hardif_index); if (!hard_dev) return ERR_PTR(-ENODEV); hard_iface = batadv_hardif_get_by_netdev(hard_dev); if (!hard_iface) goto err_put_harddev; if (hard_iface->soft_iface != bat_priv->soft_iface) goto err_put_hardif; /* hard_dev is referenced by hard_iface and not needed here */ dev_put(hard_dev); return hard_iface; err_put_hardif: batadv_hardif_put(hard_iface); err_put_harddev: dev_put(hard_dev); return ERR_PTR(-EINVAL); } /** * batadv_get_vlan_from_info() - Retrieve vlan from genl attributes * @bat_priv: the bat priv with all the soft interface information * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to vlan on success (with increased refcnt), error pointer * on error */ static struct batadv_softif_vlan * batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net, struct genl_info *info) { struct batadv_softif_vlan *vlan; u16 vid; if (!info->attrs[BATADV_ATTR_VLANID]) return ERR_PTR(-EINVAL); vid = nla_get_u16(info->attrs[BATADV_ATTR_VLANID]); vlan = batadv_softif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG); if (!vlan) return ERR_PTR(-ENOENT); return vlan; } /** * batadv_pre_doit() - Prepare batman-adv genl doit request * @ops: requested netlink operation * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct batadv_hard_iface *hard_iface; struct batadv_priv *bat_priv = NULL; struct batadv_softif_vlan *vlan; struct net_device *soft_iface; u8 user_ptr1_flags; u8 mesh_dep_flags; int ret; user_ptr1_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; if (WARN_ON(hweight8(ops->internal_flags & user_ptr1_flags) > 1)) return -EINVAL; mesh_dep_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; if (WARN_ON((ops->internal_flags & mesh_dep_flags) && (~ops->internal_flags & BATADV_FLAG_NEED_MESH))) return -EINVAL; if (ops->internal_flags & BATADV_FLAG_NEED_MESH) { soft_iface = batadv_get_softif_from_info(net, info); if (IS_ERR(soft_iface)) return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); info->user_ptr[0] = bat_priv; } if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF) { hard_iface = batadv_get_hardif_from_info(bat_priv, net, info); if (IS_ERR(hard_iface)) { ret = PTR_ERR(hard_iface); goto err_put_softif; } info->user_ptr[1] = hard_iface; } if (ops->internal_flags & BATADV_FLAG_NEED_VLAN) { vlan = batadv_get_vlan_from_info(bat_priv, net, info); if (IS_ERR(vlan)) { ret = PTR_ERR(vlan); goto err_put_softif; } info->user_ptr[1] = vlan; } return 0; err_put_softif: if (bat_priv) dev_put(bat_priv->soft_iface); return ret; } /** * batadv_post_doit() - End batman-adv genl doit request * @ops: requested netlink operation * @skb: Netlink message with request data * @info: receiver information */ static void batadv_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface; struct batadv_softif_vlan *vlan; struct batadv_priv *bat_priv; if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF && info->user_ptr[1]) { hard_iface = info->user_ptr[1]; batadv_hardif_put(hard_iface); } if (ops->internal_flags & BATADV_FLAG_NEED_VLAN && info->user_ptr[1]) { vlan = info->user_ptr[1]; batadv_softif_vlan_put(vlan); } if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) { bat_priv = info->user_ptr[0]; dev_put(bat_priv->soft_iface); } } static const struct genl_small_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = batadv_netlink_get_mesh, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_tp_meter_start, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER_CANCEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_tp_meter_cancel, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_GET_ROUTING_ALGOS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_algo_dump, }, { .cmd = BATADV_CMD_GET_HARDIF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .dumpit = batadv_netlink_dump_hardif, .doit = batadv_netlink_get_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_HARDIF, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_tt_local_dump, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_GLOBAL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_tt_global_dump, }, { .cmd = BATADV_CMD_GET_ORIGINATORS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_orig_dump, }, { .cmd = BATADV_CMD_GET_NEIGHBORS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_hardif_neigh_dump, }, { .cmd = BATADV_CMD_GET_GATEWAYS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_gw_dump, }, { .cmd = BATADV_CMD_GET_BLA_CLAIM, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_bla_claim_dump, }, { .cmd = BATADV_CMD_GET_BLA_BACKBONE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_bla_backbone_dump, }, { .cmd = BATADV_CMD_GET_DAT_CACHE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_dat_cache_dump, }, { .cmd = BATADV_CMD_GET_MCAST_FLAGS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_mcast_flags_dump, }, { .cmd = BATADV_CMD_SET_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_mesh, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_SET_HARDIF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_HARDIF, }, { .cmd = BATADV_CMD_GET_VLAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = batadv_netlink_get_vlan, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_VLAN, }, { .cmd = BATADV_CMD_SET_VLAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_vlan, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_VLAN, }, }; struct genl_family batadv_netlink_family __ro_after_init = { .hdrsize = 0, .name = BATADV_NL_NAME, .version = 1, .maxattr = BATADV_ATTR_MAX, .policy = batadv_netlink_policy, .netnsok = true, .pre_doit = batadv_pre_doit, .post_doit = batadv_post_doit, .module = THIS_MODULE, .small_ops = batadv_netlink_ops, .n_small_ops = ARRAY_SIZE(batadv_netlink_ops), .resv_start_op = BATADV_CMD_SET_VLAN + 1, .mcgrps = batadv_netlink_mcgrps, .n_mcgrps = ARRAY_SIZE(batadv_netlink_mcgrps), }; /** * batadv_netlink_register() - register batadv genl netlink family */ void __init batadv_netlink_register(void) { int ret; ret = genl_register_family(&batadv_netlink_family); if (ret) pr_warn("unable to register netlink family"); } /** * batadv_netlink_unregister() - unregister batadv genl netlink family */ void batadv_netlink_unregister(void) { genl_unregister_family(&batadv_netlink_family); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Declarations of X.25 Packet Layer type objects. * * History * nov/17/96 Jonathan Naylor Initial version. * mar/20/00 Daniela Squassoni Disabling/enabling of facilities * negotiation. */ #ifndef _X25_H #define _X25_H #include <linux/x25.h> #include <linux/slab.h> #include <linux/refcount.h> #include <net/sock.h> #define X25_ADDR_LEN 16 #define X25_MAX_L2_LEN 18 /* 802.2 LLC */ #define X25_STD_MIN_LEN 3 #define X25_EXT_MIN_LEN 4 #define X25_GFI_SEQ_MASK 0x30 #define X25_GFI_STDSEQ 0x10 #define X25_GFI_EXTSEQ 0x20 #define X25_Q_BIT 0x80 #define X25_D_BIT 0x40 #define X25_STD_M_BIT 0x10 #define X25_EXT_M_BIT 0x01 #define X25_CALL_REQUEST 0x0B #define X25_CALL_ACCEPTED 0x0F #define X25_CLEAR_REQUEST 0x13 #define X25_CLEAR_CONFIRMATION 0x17 #define X25_DATA 0x00 #define X25_INTERRUPT 0x23 #define X25_INTERRUPT_CONFIRMATION 0x27 #define X25_RR 0x01 #define X25_RNR 0x05 #define X25_REJ 0x09 #define X25_RESET_REQUEST 0x1B #define X25_RESET_CONFIRMATION 0x1F #define X25_REGISTRATION_REQUEST 0xF3 #define X25_REGISTRATION_CONFIRMATION 0xF7 #define X25_RESTART_REQUEST 0xFB #define X25_RESTART_CONFIRMATION 0xFF #define X25_DIAGNOSTIC 0xF1 #define X25_ILLEGAL 0xFD /* Define the various conditions that may exist */ #define X25_COND_ACK_PENDING 0x01 #define X25_COND_OWN_RX_BUSY 0x02 #define X25_COND_PEER_RX_BUSY 0x04 /* Define Link State constants. */ enum { X25_STATE_0, /* Ready */ X25_STATE_1, /* Awaiting Call Accepted */ X25_STATE_2, /* Awaiting Clear Confirmation */ X25_STATE_3, /* Data Transfer */ X25_STATE_4, /* Awaiting Reset Confirmation */ X25_STATE_5 /* Call Accepted / Call Connected pending */ }; enum { X25_LINK_STATE_0, X25_LINK_STATE_1, X25_LINK_STATE_2, X25_LINK_STATE_3 }; #define X25_DEFAULT_T20 (180 * HZ) /* Default T20 value */ #define X25_DEFAULT_T21 (200 * HZ) /* Default T21 value */ #define X25_DEFAULT_T22 (180 * HZ) /* Default T22 value */ #define X25_DEFAULT_T23 (180 * HZ) /* Default T23 value */ #define X25_DEFAULT_T2 (3 * HZ) /* Default ack holdback value */ #define X25_DEFAULT_WINDOW_SIZE 2 /* Default Window Size */ #define X25_DEFAULT_PACKET_SIZE X25_PS128 /* Default Packet Size */ #define X25_DEFAULT_THROUGHPUT 0x0A /* Deafult Throughput */ #define X25_DEFAULT_REVERSE 0x00 /* Default Reverse Charging */ #define X25_SMODULUS 8 #define X25_EMODULUS 128 /* * X.25 Facilities constants. */ #define X25_FAC_CLASS_MASK 0xC0 #define X25_FAC_CLASS_A 0x00 #define X25_FAC_CLASS_B 0x40 #define X25_FAC_CLASS_C 0x80 #define X25_FAC_CLASS_D 0xC0 #define X25_FAC_REVERSE 0x01 /* also fast select */ #define X25_FAC_THROUGHPUT 0x02 #define X25_FAC_PACKET_SIZE 0x42 #define X25_FAC_WINDOW_SIZE 0x43 #define X25_MAX_FAC_LEN 60 #define X25_MAX_CUD_LEN 128 #define X25_FAC_CALLING_AE 0xCB #define X25_FAC_CALLED_AE 0xC9 #define X25_MARKER 0x00 #define X25_DTE_SERVICES 0x0F #define X25_MAX_AE_LEN 40 /* Max num of semi-octets in AE - OSI Nw */ #define X25_MAX_DTE_FACIL_LEN 21 /* Max length of DTE facility params */ /* Bitset in x25_sock->flags for misc flags */ #define X25_Q_BIT_FLAG 0 #define X25_INTERRUPT_FLAG 1 #define X25_ACCPT_APPRV_FLAG 2 /** * struct x25_route - x25 routing entry * @node - entry in x25_list_lock * @address - Start of address range * @sigdigits - Number of sig digits * @dev - More than one for MLP * @refcnt - reference counter */ struct x25_route { struct list_head node; struct x25_address address; unsigned int sigdigits; struct net_device *dev; refcount_t refcnt; }; struct x25_neigh { struct list_head node; struct net_device *dev; unsigned int state; unsigned int extended; struct sk_buff_head queue; unsigned long t20; struct timer_list t20timer; unsigned long global_facil_mask; refcount_t refcnt; }; struct x25_sock { struct sock sk; struct x25_address source_addr, dest_addr; struct x25_neigh *neighbour; unsigned int lci, cudmatchlength; unsigned char state, condition; unsigned short vs, vr, va, vl; unsigned long t2, t21, t22, t23; unsigned short fraglen; unsigned long flags; struct sk_buff_head ack_queue; struct sk_buff_head fragment_queue; struct sk_buff_head interrupt_in_queue; struct sk_buff_head interrupt_out_queue; struct timer_list timer; struct x25_causediag causediag; struct x25_facilities facilities; struct x25_dte_facilities dte_facilities; struct x25_calluserdata calluserdata; unsigned long vc_facil_mask; /* inc_call facilities mask */ }; struct x25_forward { struct list_head node; unsigned int lci; struct net_device *dev1; struct net_device *dev2; atomic_t refcnt; }; #define x25_sk(ptr) container_of_const(ptr, struct x25_sock, sk) /* af_x25.c */ extern int sysctl_x25_restart_request_timeout; extern int sysctl_x25_call_request_timeout; extern int sysctl_x25_reset_request_timeout; extern int sysctl_x25_clear_request_timeout; extern int sysctl_x25_ack_holdback_timeout; extern int sysctl_x25_forward; int x25_parse_address_block(struct sk_buff *skb, struct x25_address *called_addr, struct x25_address *calling_addr); int x25_addr_ntoa(unsigned char *, struct x25_address *, struct x25_address *); int x25_addr_aton(unsigned char *, struct x25_address *, struct x25_address *); struct sock *x25_find_socket(unsigned int, struct x25_neigh *); void x25_destroy_socket_from_timer(struct sock *); int x25_rx_call_request(struct sk_buff *, struct x25_neigh *, unsigned int); void x25_kill_by_neigh(struct x25_neigh *); /* x25_dev.c */ void x25_send_frame(struct sk_buff *, struct x25_neigh *); int x25_lapb_receive_frame(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); void x25_establish_link(struct x25_neigh *); void x25_terminate_link(struct x25_neigh *); /* x25_facilities.c */ int x25_parse_facilities(struct sk_buff *, struct x25_facilities *, struct x25_dte_facilities *, unsigned long *); int x25_create_facilities(unsigned char *, struct x25_facilities *, struct x25_dte_facilities *, unsigned long); int x25_negotiate_facilities(struct sk_buff *, struct sock *, struct x25_facilities *, struct x25_dte_facilities *); void x25_limit_facilities(struct x25_facilities *, struct x25_neigh *); /* x25_forward.c */ void x25_clear_forward_by_lci(unsigned int lci); void x25_clear_forward_by_dev(struct net_device *); int x25_forward_data(int, struct x25_neigh *, struct sk_buff *); int x25_forward_call(struct x25_address *, struct x25_neigh *, struct sk_buff *, int); /* x25_in.c */ int x25_process_rx_frame(struct sock *, struct sk_buff *); int x25_backlog_rcv(struct sock *, struct sk_buff *); /* x25_link.c */ void x25_link_control(struct sk_buff *, struct x25_neigh *, unsigned short); void x25_link_device_up(struct net_device *); void x25_link_device_down(struct net_device *); void x25_link_established(struct x25_neigh *); void x25_link_terminated(struct x25_neigh *); void x25_transmit_clear_request(struct x25_neigh *, unsigned int, unsigned char); void x25_transmit_link(struct sk_buff *, struct x25_neigh *); int x25_subscr_ioctl(unsigned int, void __user *); struct x25_neigh *x25_get_neigh(struct net_device *); void x25_link_free(void); /* x25_neigh.c */ static __inline__ void x25_neigh_hold(struct x25_neigh *nb) { refcount_inc(&nb->refcnt); } static __inline__ void x25_neigh_put(struct x25_neigh *nb) { if (refcount_dec_and_test(&nb->refcnt)) kfree(nb); } /* x25_out.c */ int x25_output(struct sock *, struct sk_buff *); void x25_kick(struct sock *); void x25_enquiry_response(struct sock *); /* x25_route.c */ struct x25_route *x25_get_route(struct x25_address *addr); struct net_device *x25_dev_get(char *); void x25_route_device_down(struct net_device *dev); int x25_route_ioctl(unsigned int, void __user *); void x25_route_free(void); static __inline__ void x25_route_hold(struct x25_route *rt) { refcount_inc(&rt->refcnt); } static __inline__ void x25_route_put(struct x25_route *rt) { if (refcount_dec_and_test(&rt->refcnt)) kfree(rt); } /* x25_subr.c */ void x25_clear_queues(struct sock *); void x25_frames_acked(struct sock *, unsigned short); void x25_requeue_frames(struct sock *); int x25_validate_nr(struct sock *, unsigned short); void x25_write_internal(struct sock *, int); int x25_decode(struct sock *, struct sk_buff *, int *, int *, int *, int *, int *); void x25_disconnect(struct sock *, int, unsigned char, unsigned char); /* x25_timer.c */ void x25_init_timers(struct sock *sk); void x25_start_heartbeat(struct sock *); void x25_start_t2timer(struct sock *); void x25_start_t21timer(struct sock *); void x25_start_t22timer(struct sock *); void x25_start_t23timer(struct sock *); void x25_stop_heartbeat(struct sock *); void x25_stop_timer(struct sock *); unsigned long x25_display_timer(struct sock *); void x25_check_rbuf(struct sock *); /* sysctl_net_x25.c */ #ifdef CONFIG_SYSCTL int x25_register_sysctl(void); void x25_unregister_sysctl(void); #else static inline int x25_register_sysctl(void) { return 0; }; static inline void x25_unregister_sysctl(void) {}; #endif /* CONFIG_SYSCTL */ struct x25_skb_cb { unsigned int flags; }; #define X25_SKB_CB(s) ((struct x25_skb_cb *) ((s)->cb)) extern struct hlist_head x25_list; extern rwlock_t x25_list_lock; extern struct list_head x25_route_list; extern rwlock_t x25_route_list_lock; extern struct list_head x25_forward_list; extern rwlock_t x25_forward_list_lock; extern struct list_head x25_neigh_list; extern rwlock_t x25_neigh_list_lock; int x25_proc_init(void); void x25_proc_exit(void); #endif |
| 6 6 6 4 4 7 2 6 5 1 4 4 4 4 2 1 1 2 2 1 2 2 2 6 6 6 4 2 2 51 51 49 1 45 1 1 2 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 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 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Copyright (C) 2011 ProFUSION Embedded Systems Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth HCI core. */ #include <linux/export.h> #include <linux/rfkill.h> #include <linux/debugfs.h> #include <linux/crypto.h> #include <linux/kcov.h> #include <linux/property.h> #include <linux/suspend.h> #include <linux/wait.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/mgmt.h> #include "hci_request.h" #include "hci_debugfs.h" #include "smp.h" #include "leds.h" #include "msft.h" #include "aosp.h" #include "hci_codec.h" static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); static void hci_tx_work(struct work_struct *work); /* HCI device list */ LIST_HEAD(hci_dev_list); DEFINE_RWLOCK(hci_dev_list_lock); /* HCI callback list */ LIST_HEAD(hci_cb_list); DEFINE_MUTEX(hci_cb_list_lock); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); static int hci_scan_req(struct hci_request *req, unsigned long opt) { __u8 scan = opt; BT_DBG("%s %x", req->hdev->name, scan); /* Inquiry and Page scans */ hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); return 0; } static int hci_auth_req(struct hci_request *req, unsigned long opt) { __u8 auth = opt; BT_DBG("%s %x", req->hdev->name, auth); /* Authentication */ hci_req_add(req, HCI_OP_WRITE_AUTH_ENABLE, 1, &auth); return 0; } static int hci_encrypt_req(struct hci_request *req, unsigned long opt) { __u8 encrypt = opt; BT_DBG("%s %x", req->hdev->name, encrypt); /* Encryption */ hci_req_add(req, HCI_OP_WRITE_ENCRYPT_MODE, 1, &encrypt); return 0; } static int hci_linkpol_req(struct hci_request *req, unsigned long opt) { __le16 policy = cpu_to_le16(opt); BT_DBG("%s %x", req->hdev->name, policy); /* Default link policy */ hci_req_add(req, HCI_OP_WRITE_DEF_LINK_POLICY, 2, &policy); return 0; } /* Get HCI device by index. * Device is held on return. */ struct hci_dev *hci_dev_get(int index) { struct hci_dev *hdev = NULL, *d; BT_DBG("%d", index); if (index < 0) return NULL; read_lock(&hci_dev_list_lock); list_for_each_entry(d, &hci_dev_list, list) { if (d->id == index) { hdev = hci_dev_hold(d); break; } } read_unlock(&hci_dev_list_lock); return hdev; } /* ---- Inquiry support ---- */ bool hci_discovery_active(struct hci_dev *hdev) { struct discovery_state *discov = &hdev->discovery; switch (discov->state) { case DISCOVERY_FINDING: case DISCOVERY_RESOLVING: return true; default: return false; } } void hci_discovery_set_state(struct hci_dev *hdev, int state) { int old_state = hdev->discovery.state; BT_DBG("%s state %u -> %u", hdev->name, hdev->discovery.state, state); if (old_state == state) return; hdev->discovery.state = state; switch (state) { case DISCOVERY_STOPPED: hci_update_passive_scan(hdev); if (old_state != DISCOVERY_STARTING) mgmt_discovering(hdev, 0); break; case DISCOVERY_STARTING: break; case DISCOVERY_FINDING: mgmt_discovering(hdev, 1); break; case DISCOVERY_RESOLVING: break; case DISCOVERY_STOPPING: break; } } void hci_inquiry_cache_flush(struct hci_dev *hdev) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *p, *n; list_for_each_entry_safe(p, n, &cache->all, all) { list_del(&p->all); kfree(p); } INIT_LIST_HEAD(&cache->unknown); INIT_LIST_HEAD(&cache->resolve); } struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p, %pMR", cache, bdaddr); list_for_each_entry(e, &cache->all, all) { if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } struct inquiry_entry *hci_inquiry_cache_lookup_unknown(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p, %pMR", cache, bdaddr); list_for_each_entry(e, &cache->unknown, list) { if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } struct inquiry_entry *hci_inquiry_cache_lookup_resolve(struct hci_dev *hdev, bdaddr_t *bdaddr, int state) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p bdaddr %pMR state %d", cache, bdaddr, state); list_for_each_entry(e, &cache->resolve, list) { if (!bacmp(bdaddr, BDADDR_ANY) && e->name_state == state) return e; if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } void hci_inquiry_cache_update_resolve(struct hci_dev *hdev, struct inquiry_entry *ie) { struct discovery_state *cache = &hdev->discovery; struct list_head *pos = &cache->resolve; struct inquiry_entry *p; list_del(&ie->list); list_for_each_entry(p, &cache->resolve, list) { if (p->name_state != NAME_PENDING && abs(p->data.rssi) >= abs(ie->data.rssi)) break; pos = &p->list; } list_add(&ie->list, pos); } u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, bool name_known) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *ie; u32 flags = 0; BT_DBG("cache %p, %pMR", cache, &data->bdaddr); hci_remove_remote_oob_data(hdev, &data->bdaddr, BDADDR_BREDR); if (!data->ssp_mode) flags |= MGMT_DEV_FOUND_LEGACY_PAIRING; ie = hci_inquiry_cache_lookup(hdev, &data->bdaddr); if (ie) { if (!ie->data.ssp_mode) flags |= MGMT_DEV_FOUND_LEGACY_PAIRING; if (ie->name_state == NAME_NEEDED && data->rssi != ie->data.rssi) { ie->data.rssi = data->rssi; hci_inquiry_cache_update_resolve(hdev, ie); } goto update; } /* Entry not in the cache. Add new one. */ ie = kzalloc(sizeof(*ie), GFP_KERNEL); if (!ie) { flags |= MGMT_DEV_FOUND_CONFIRM_NAME; goto done; } list_add(&ie->all, &cache->all); if (name_known) { ie->name_state = NAME_KNOWN; } else { ie->name_state = NAME_NOT_KNOWN; list_add(&ie->list, &cache->unknown); } update: if (name_known && ie->name_state != NAME_KNOWN && ie->name_state != NAME_PENDING) { ie->name_state = NAME_KNOWN; list_del(&ie->list); } memcpy(&ie->data, data, sizeof(*data)); ie->timestamp = jiffies; cache->timestamp = jiffies; if (ie->name_state == NAME_NOT_KNOWN) flags |= MGMT_DEV_FOUND_CONFIRM_NAME; done: return flags; } static int inquiry_cache_dump(struct hci_dev *hdev, int num, __u8 *buf) { struct discovery_state *cache = &hdev->discovery; struct inquiry_info *info = (struct inquiry_info *) buf; struct inquiry_entry *e; int copied = 0; list_for_each_entry(e, &cache->all, all) { struct inquiry_data *data = &e->data; if (copied >= num) break; bacpy(&info->bdaddr, &data->bdaddr); info->pscan_rep_mode = data->pscan_rep_mode; info->pscan_period_mode = data->pscan_period_mode; info->pscan_mode = data->pscan_mode; memcpy(info->dev_class, data->dev_class, 3); info->clock_offset = data->clock_offset; info++; copied++; } BT_DBG("cache %p, copied %d", cache, copied); return copied; } static int hci_inq_req(struct hci_request *req, unsigned long opt) { struct hci_inquiry_req *ir = (struct hci_inquiry_req *) opt; struct hci_dev *hdev = req->hdev; struct hci_cp_inquiry cp; BT_DBG("%s", hdev->name); if (test_bit(HCI_INQUIRY, &hdev->flags)) return 0; /* Start Inquiry */ memcpy(&cp.lap, &ir->lap, 3); cp.length = ir->length; cp.num_rsp = ir->num_rsp; hci_req_add(req, HCI_OP_INQUIRY, sizeof(cp), &cp); return 0; } int hci_inquiry(void __user *arg) { __u8 __user *ptr = arg; struct hci_inquiry_req ir; struct hci_dev *hdev; int err = 0, do_inquiry = 0, max_rsp; long timeo; __u8 *buf; if (copy_from_user(&ir, ptr, sizeof(ir))) return -EFAULT; hdev = hci_dev_get(ir.dev_id); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } if (hdev->dev_type != HCI_PRIMARY) { err = -EOPNOTSUPP; goto done; } if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; } /* Restrict maximum inquiry length to 60 seconds */ if (ir.length > 60) { err = -EINVAL; goto done; } hci_dev_lock(hdev); if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX || inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) { hci_inquiry_cache_flush(hdev); do_inquiry = 1; } hci_dev_unlock(hdev); timeo = ir.length * msecs_to_jiffies(2000); if (do_inquiry) { err = hci_req_sync(hdev, hci_inq_req, (unsigned long) &ir, timeo, NULL); if (err < 0) goto done; /* Wait until Inquiry procedure finishes (HCI_INQUIRY flag is * cleared). If it is interrupted by a signal, return -EINTR. */ if (wait_on_bit(&hdev->flags, HCI_INQUIRY, TASK_INTERRUPTIBLE)) { err = -EINTR; goto done; } } /* for unlimited number of responses we will use buffer with * 255 entries */ max_rsp = (ir.num_rsp == 0) ? 255 : ir.num_rsp; /* cache_dump can't sleep. Therefore we allocate temp buffer and then * copy it to the user space. */ buf = kmalloc_array(max_rsp, sizeof(struct inquiry_info), GFP_KERNEL); if (!buf) { err = -ENOMEM; goto done; } hci_dev_lock(hdev); ir.num_rsp = inquiry_cache_dump(hdev, max_rsp, buf); hci_dev_unlock(hdev); BT_DBG("num_rsp %d", ir.num_rsp); if (!copy_to_user(ptr, &ir, sizeof(ir))) { ptr += sizeof(ir); if (copy_to_user(ptr, buf, sizeof(struct inquiry_info) * ir.num_rsp)) err = -EFAULT; } else err = -EFAULT; kfree(buf); done: hci_dev_put(hdev); return err; } static int hci_dev_do_open(struct hci_dev *hdev) { int ret = 0; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); ret = hci_dev_open_sync(hdev); hci_req_sync_unlock(hdev); return ret; } /* ---- HCI ioctl helpers ---- */ int hci_dev_open(__u16 dev) { struct hci_dev *hdev; int err; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; /* Devices that are marked as unconfigured can only be powered * up as user channel. Trying to bring them up as normal devices * will result into a failure. Only user channel operation is * possible. * * When this function is called for a user channel, the flag * HCI_USER_CHANNEL will be set first before attempting to * open the device. */ if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EOPNOTSUPP; goto done; } /* We need to ensure that no other power on/off work is pending * before proceeding to call hci_dev_do_open. This is * particularly important if the setup procedure has not yet * completed. */ if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); /* After this call it is guaranteed that the setup procedure * has finished. This means that error conditions like RFKILL * or no valid public or static random address apply. */ flush_workqueue(hdev->req_workqueue); /* For controllers not using the management interface and that * are brought up using legacy ioctl, set the HCI_BONDABLE bit * so that pairing works for them. Once the management interface * is in use this bit will be cleared again and userspace has * to explicitly enable it. */ if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && !hci_dev_test_flag(hdev, HCI_MGMT)) hci_dev_set_flag(hdev, HCI_BONDABLE); err = hci_dev_do_open(hdev); done: hci_dev_put(hdev); return err; } int hci_dev_do_close(struct hci_dev *hdev) { int err; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); err = hci_dev_close_sync(hdev); hci_req_sync_unlock(hdev); return err; } int hci_dev_close(__u16 dev) { struct hci_dev *hdev; int err; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } cancel_work_sync(&hdev->power_on); if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); err = hci_dev_do_close(hdev); done: hci_dev_put(hdev); return err; } static int hci_dev_do_reset(struct hci_dev *hdev) { int ret; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); /* Drop queues */ skb_queue_purge(&hdev->rx_q); skb_queue_purge(&hdev->cmd_q); /* Cancel these to avoid queueing non-chained pending work */ hci_dev_set_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); /* Wait for * * if (!hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) * queue_delayed_work(&hdev->{cmd,ncmd}_timer) * * inside RCU section to see the flag or complete scheduling. */ synchronize_rcu(); /* Explicitly cancel works in case scheduled after setting the flag. */ cancel_delayed_work(&hdev->cmd_timer); cancel_delayed_work(&hdev->ncmd_timer); /* Avoid potential lockdep warnings from the *_flush() calls by * ensuring the workqueue is empty up front. */ drain_workqueue(hdev->workqueue); hci_dev_lock(hdev); hci_inquiry_cache_flush(hdev); hci_conn_hash_flush(hdev); hci_dev_unlock(hdev); if (hdev->flush) hdev->flush(hdev); hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); atomic_set(&hdev->cmd_cnt, 1); hdev->acl_cnt = 0; hdev->sco_cnt = 0; hdev->le_cnt = 0; hdev->iso_cnt = 0; ret = hci_reset_sync(hdev); hci_req_sync_unlock(hdev); return ret; } int hci_dev_reset(__u16 dev) { struct hci_dev *hdev; int err; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; if (!test_bit(HCI_UP, &hdev->flags)) { err = -ENETDOWN; goto done; } if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } err = hci_dev_do_reset(hdev); done: hci_dev_put(hdev); return err; } int hci_dev_reset_stat(__u16 dev) { struct hci_dev *hdev; int ret = 0; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { ret = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { ret = -EOPNOTSUPP; goto done; } memset(&hdev->stat, 0, sizeof(struct hci_dev_stats)); done: hci_dev_put(hdev); return ret; } static void hci_update_passive_scan_state(struct hci_dev *hdev, u8 scan) { bool conn_changed, discov_changed; BT_DBG("%s scan 0x%02x", hdev->name, scan); if ((scan & SCAN_PAGE)) conn_changed = !hci_dev_test_and_set_flag(hdev, HCI_CONNECTABLE); else conn_changed = hci_dev_test_and_clear_flag(hdev, HCI_CONNECTABLE); if ((scan & SCAN_INQUIRY)) { discov_changed = !hci_dev_test_and_set_flag(hdev, HCI_DISCOVERABLE); } else { hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); discov_changed = hci_dev_test_and_clear_flag(hdev, HCI_DISCOVERABLE); } if (!hci_dev_test_flag(hdev, HCI_MGMT)) return; if (conn_changed || discov_changed) { /* In case this was disabled through mgmt */ hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) hci_update_adv_data(hdev, hdev->cur_adv_instance); mgmt_new_settings(hdev); } } int hci_dev_cmd(unsigned int cmd, void __user *arg) { struct hci_dev *hdev; struct hci_dev_req dr; int err = 0; if (copy_from_user(&dr, arg, sizeof(dr))) return -EFAULT; hdev = hci_dev_get(dr.dev_id); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } if (hdev->dev_type != HCI_PRIMARY) { err = -EOPNOTSUPP; goto done; } if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; } switch (cmd) { case HCISETAUTH: err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt, HCI_INIT_TIMEOUT, NULL); break; case HCISETENCRYPT: if (!lmp_encrypt_capable(hdev)) { err = -EOPNOTSUPP; break; } if (!test_bit(HCI_AUTH, &hdev->flags)) { /* Auth must be enabled first */ err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt, HCI_INIT_TIMEOUT, NULL); if (err) break; } err = hci_req_sync(hdev, hci_encrypt_req, dr.dev_opt, HCI_INIT_TIMEOUT, NULL); break; case HCISETSCAN: err = hci_req_sync(hdev, hci_scan_req, dr.dev_opt, HCI_INIT_TIMEOUT, NULL); /* Ensure that the connectable and discoverable states * get correctly modified as this was a non-mgmt change. */ if (!err) hci_update_passive_scan_state(hdev, dr.dev_opt); break; case HCISETLINKPOL: err = hci_req_sync(hdev, hci_linkpol_req, dr.dev_opt, HCI_INIT_TIMEOUT, NULL); break; case HCISETLINKMODE: hdev->link_mode = ((__u16) dr.dev_opt) & (HCI_LM_MASTER | HCI_LM_ACCEPT); break; case HCISETPTYPE: if (hdev->pkt_type == (__u16) dr.dev_opt) break; hdev->pkt_type = (__u16) dr.dev_opt; mgmt_phy_configuration_changed(hdev, NULL); break; case HCISETACLMTU: hdev->acl_mtu = *((__u16 *) &dr.dev_opt + 1); hdev->acl_pkts = *((__u16 *) &dr.dev_opt + 0); break; case HCISETSCOMTU: hdev->sco_mtu = *((__u16 *) &dr.dev_opt + 1); hdev->sco_pkts = *((__u16 *) &dr.dev_opt + 0); break; default: err = -EINVAL; break; } done: hci_dev_put(hdev); return err; } int hci_get_dev_list(void __user *arg) { struct hci_dev *hdev; struct hci_dev_list_req *dl; struct hci_dev_req *dr; int n = 0, size, err; __u16 dev_num; if (get_user(dev_num, (__u16 __user *) arg)) return -EFAULT; if (!dev_num || dev_num > (PAGE_SIZE * 2) / sizeof(*dr)) return -EINVAL; size = sizeof(*dl) + dev_num * sizeof(*dr); dl = kzalloc(size, GFP_KERNEL); if (!dl) return -ENOMEM; dr = dl->dev_req; read_lock(&hci_dev_list_lock); list_for_each_entry(hdev, &hci_dev_list, list) { unsigned long flags = hdev->flags; /* When the auto-off is configured it means the transport * is running, but in that case still indicate that the * device is actually down. */ if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags &= ~BIT(HCI_UP); (dr + n)->dev_id = hdev->id; (dr + n)->dev_opt = flags; if (++n >= dev_num) break; } read_unlock(&hci_dev_list_lock); dl->dev_num = n; size = sizeof(*dl) + n * sizeof(*dr); err = copy_to_user(arg, dl, size); kfree(dl); return err ? -EFAULT : 0; } int hci_get_dev_info(void __user *arg) { struct hci_dev *hdev; struct hci_dev_info di; unsigned long flags; int err = 0; if (copy_from_user(&di, arg, sizeof(di))) return -EFAULT; hdev = hci_dev_get(di.dev_id); if (!hdev) return -ENODEV; /* When the auto-off is configured it means the transport * is running, but in that case still indicate that the * device is actually down. */ if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags = hdev->flags & ~BIT(HCI_UP); else flags = hdev->flags; strcpy(di.name, hdev->name); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); di.flags = flags; di.pkt_type = hdev->pkt_type; if (lmp_bredr_capable(hdev)) { di.acl_mtu = hdev->acl_mtu; di.acl_pkts = hdev->acl_pkts; di.sco_mtu = hdev->sco_mtu; di.sco_pkts = hdev->sco_pkts; } else { di.acl_mtu = hdev->le_mtu; di.acl_pkts = hdev->le_pkts; di.sco_mtu = 0; di.sco_pkts = 0; } di.link_policy = hdev->link_policy; di.link_mode = hdev->link_mode; memcpy(&di.stat, &hdev->stat, sizeof(di.stat)); memcpy(&di.features, &hdev->features, sizeof(di.features)); if (copy_to_user(arg, &di, sizeof(di))) err = -EFAULT; hci_dev_put(hdev); return err; } /* ---- Interface to HCI drivers ---- */ static int hci_rfkill_set_block(void *data, bool blocked) { struct hci_dev *hdev = data; BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; if (blocked) { hci_dev_set_flag(hdev, HCI_RFKILLED); if (!hci_dev_test_flag(hdev, HCI_SETUP) && !hci_dev_test_flag(hdev, HCI_CONFIG)) hci_dev_do_close(hdev); } else { hci_dev_clear_flag(hdev, HCI_RFKILLED); } return 0; } static const struct rfkill_ops hci_rfkill_ops = { .set_block = hci_rfkill_set_block, }; static void hci_power_on(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, power_on); int err; BT_DBG("%s", hdev->name); if (test_bit(HCI_UP, &hdev->flags) && hci_dev_test_flag(hdev, HCI_MGMT) && hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) { cancel_delayed_work(&hdev->power_off); err = hci_powered_update_sync(hdev); mgmt_power_on(hdev, err); return; } err = hci_dev_do_open(hdev); if (err < 0) { hci_dev_lock(hdev); mgmt_set_powered_failed(hdev, err); hci_dev_unlock(hdev); return; } /* During the HCI setup phase, a few error conditions are * ignored and they need to be checked now. If they are still * valid, it is important to turn the device back off. */ if (hci_dev_test_flag(hdev, HCI_RFKILLED) || hci_dev_test_flag(hdev, HCI_UNCONFIGURED) || (hdev->dev_type == HCI_PRIMARY && !bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { hci_dev_clear_flag(hdev, HCI_AUTO_OFF); hci_dev_do_close(hdev); } else if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) { queue_delayed_work(hdev->req_workqueue, &hdev->power_off, HCI_AUTO_OFF_TIMEOUT); } if (hci_dev_test_and_clear_flag(hdev, HCI_SETUP)) { /* For unconfigured devices, set the HCI_RAW flag * so that userspace can easily identify them. */ if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) set_bit(HCI_RAW, &hdev->flags); /* For fully configured devices, this will send * the Index Added event. For unconfigured devices, * it will send Unconfigued Index Added event. * * Devices with HCI_QUIRK_RAW_DEVICE are ignored * and no event will be send. */ mgmt_index_added(hdev); } else if (hci_dev_test_and_clear_flag(hdev, HCI_CONFIG)) { /* When the controller is now configured, then it * is important to clear the HCI_RAW flag. */ if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) clear_bit(HCI_RAW, &hdev->flags); /* Powering on the controller with HCI_CONFIG set only * happens with the transition from unconfigured to * configured. This will send the Index Added event. */ mgmt_index_added(hdev); } } static void hci_power_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, power_off.work); BT_DBG("%s", hdev->name); hci_dev_do_close(hdev); } static void hci_error_reset(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset); BT_DBG("%s", hdev->name); if (hdev->hw_error) hdev->hw_error(hdev, hdev->hw_error_code); else bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code); if (hci_dev_do_close(hdev)) return; hci_dev_do_open(hdev); } void hci_uuids_clear(struct hci_dev *hdev) { struct bt_uuid *uuid, *tmp; list_for_each_entry_safe(uuid, tmp, &hdev->uuids, list) { list_del(&uuid->list); kfree(uuid); } } void hci_link_keys_clear(struct hci_dev *hdev) { struct link_key *key, *tmp; list_for_each_entry_safe(key, tmp, &hdev->link_keys, list) { list_del_rcu(&key->list); kfree_rcu(key, rcu); } } void hci_smp_ltks_clear(struct hci_dev *hdev) { struct smp_ltk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } } void hci_smp_irks_clear(struct hci_dev *hdev) { struct smp_irk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } } void hci_blocked_keys_clear(struct hci_dev *hdev) { struct blocked_key *b, *tmp; list_for_each_entry_safe(b, tmp, &hdev->blocked_keys, list) { list_del_rcu(&b->list); kfree_rcu(b, rcu); } } bool hci_is_blocked_key(struct hci_dev *hdev, u8 type, u8 val[16]) { bool blocked = false; struct blocked_key *b; rcu_read_lock(); list_for_each_entry_rcu(b, &hdev->blocked_keys, list) { if (b->type == type && !memcmp(b->val, val, sizeof(b->val))) { blocked = true; break; } } rcu_read_unlock(); return blocked; } struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct link_key *k; rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->link_keys, list) { if (bacmp(bdaddr, &k->bdaddr) == 0) { rcu_read_unlock(); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LINKKEY, k->val)) { bt_dev_warn_ratelimited(hdev, "Link key blocked for %pMR", &k->bdaddr); return NULL; } return k; } } rcu_read_unlock(); return NULL; } static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, u8 key_type, u8 old_key_type) { /* Legacy key */ if (key_type < 0x03) return true; /* Debug keys are insecure so don't store them persistently */ if (key_type == HCI_LK_DEBUG_COMBINATION) return false; /* Changed combination key and there's no previous one */ if (key_type == HCI_LK_CHANGED_COMBINATION && old_key_type == 0xff) return false; /* Security mode 3 case */ if (!conn) return true; /* BR/EDR key derived using SC from an LE link */ if (conn->type == LE_LINK) return true; /* Neither local nor remote side had no-bonding as requirement */ if (conn->auth_type > 0x01 && conn->remote_auth > 0x01) return true; /* Local side had dedicated bonding as requirement */ if (conn->auth_type == 0x02 || conn->auth_type == 0x03) return true; /* Remote side had dedicated bonding as requirement */ if (conn->remote_auth == 0x02 || conn->remote_auth == 0x03) return true; /* If none of the above criteria match, then don't store the key * persistently */ return false; } static u8 ltk_role(u8 type) { if (type == SMP_LTK) return HCI_ROLE_MASTER; return HCI_ROLE_SLAVE; } struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 role) { struct smp_ltk *k; rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { if (addr_type != k->bdaddr_type || bacmp(bdaddr, &k->bdaddr)) continue; if (smp_ltk_is_sc(k) || ltk_role(k->type) == role) { rcu_read_unlock(); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, k->val)) { bt_dev_warn_ratelimited(hdev, "LTK blocked for %pMR", &k->bdaddr); return NULL; } return k; } } rcu_read_unlock(); return NULL; } struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa) { struct smp_irk *irk_to_return = NULL; struct smp_irk *irk; rcu_read_lock(); list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (!bacmp(&irk->rpa, rpa)) { irk_to_return = irk; goto done; } } list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (smp_irk_matches(hdev, irk->val, rpa)) { bacpy(&irk->rpa, rpa); irk_to_return = irk; goto done; } } done: if (irk_to_return && hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, irk_to_return->val)) { bt_dev_warn_ratelimited(hdev, "Identity key blocked for %pMR", &irk_to_return->bdaddr); irk_to_return = NULL; } rcu_read_unlock(); return irk_to_return; } struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { struct smp_irk *irk_to_return = NULL; struct smp_irk *irk; /* Identity Address must be public or static random */ if (addr_type == ADDR_LE_DEV_RANDOM && (bdaddr->b[5] & 0xc0) != 0xc0) return NULL; rcu_read_lock(); list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (addr_type == irk->addr_type && bacmp(bdaddr, &irk->bdaddr) == 0) { irk_to_return = irk; goto done; } } done: if (irk_to_return && hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, irk_to_return->val)) { bt_dev_warn_ratelimited(hdev, "Identity key blocked for %pMR", &irk_to_return->bdaddr); irk_to_return = NULL; } rcu_read_unlock(); return irk_to_return; } struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len, bool *persistent) { struct link_key *key, *old_key; u8 old_key_type; old_key = hci_find_link_key(hdev, bdaddr); if (old_key) { old_key_type = old_key->type; key = old_key; } else { old_key_type = conn ? conn->key_type : 0xff; key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) return NULL; list_add_rcu(&key->list, &hdev->link_keys); } BT_DBG("%s key for %pMR type %u", hdev->name, bdaddr, type); /* Some buggy controller combinations generate a changed * combination key for legacy pairing even when there's no * previous key */ if (type == HCI_LK_CHANGED_COMBINATION && (!conn || conn->remote_auth == 0xff) && old_key_type == 0xff) { type = HCI_LK_COMBINATION; if (conn) conn->key_type = type; } bacpy(&key->bdaddr, bdaddr); memcpy(key->val, val, HCI_LINK_KEY_SIZE); key->pin_len = pin_len; if (type == HCI_LK_CHANGED_COMBINATION) key->type = old_key_type; else key->type = type; if (persistent) *persistent = hci_persistent_key(hdev, conn, type, old_key_type); return key; } struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, u8 authenticated, u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand) { struct smp_ltk *key, *old_key; u8 role = ltk_role(type); old_key = hci_find_ltk(hdev, bdaddr, addr_type, role); if (old_key) key = old_key; else { key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) return NULL; list_add_rcu(&key->list, &hdev->long_term_keys); } bacpy(&key->bdaddr, bdaddr); key->bdaddr_type = addr_type; memcpy(key->val, tk, sizeof(key->val)); key->authenticated = authenticated; key->ediv = ediv; key->rand = rand; key->enc_size = enc_size; key->type = type; return key; } struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 val[16], bdaddr_t *rpa) { struct smp_irk *irk; irk = hci_find_irk_by_addr(hdev, bdaddr, addr_type); if (!irk) { irk = kzalloc(sizeof(*irk), GFP_KERNEL); if (!irk) return NULL; bacpy(&irk->bdaddr, bdaddr); irk->addr_type = addr_type; list_add_rcu(&irk->list, &hdev->identity_resolving_keys); } memcpy(irk->val, val, 16); bacpy(&irk->rpa, rpa); return irk; } int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct link_key *key; key = hci_find_link_key(hdev, bdaddr); if (!key) return -ENOENT; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&key->list); kfree_rcu(key, rcu); return 0; } int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct smp_ltk *k, *tmp; int removed = 0; list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type) continue; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&k->list); kfree_rcu(k, rcu); removed++; } return removed ? 0 : -ENOENT; } void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { struct smp_irk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type) continue; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&k->list); kfree_rcu(k, rcu); } } bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) { struct smp_ltk *k; struct smp_irk *irk; u8 addr_type; if (type == BDADDR_BREDR) { if (hci_find_link_key(hdev, bdaddr)) return true; return false; } /* Convert to HCI addr type which struct smp_ltk uses */ if (type == BDADDR_LE_PUBLIC) addr_type = ADDR_LE_DEV_PUBLIC; else addr_type = ADDR_LE_DEV_RANDOM; irk = hci_get_irk(hdev, bdaddr, addr_type); if (irk) { bdaddr = &irk->bdaddr; addr_type = irk->addr_type; } rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { if (k->bdaddr_type == addr_type && !bacmp(bdaddr, &k->bdaddr)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } /* HCI command timer function */ static void hci_cmd_timeout(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_timer.work); if (hdev->sent_cmd) { struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data; u16 opcode = __le16_to_cpu(sent->opcode); bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode); } else { bt_dev_err(hdev, "command tx timeout"); } if (hdev->cmd_timeout) hdev->cmd_timeout(hdev); atomic_set(&hdev->cmd_cnt, 1); queue_work(hdev->workqueue, &hdev->cmd_work); } /* HCI ncmd timer function */ static void hci_ncmd_timeout(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, ncmd_timer.work); bt_dev_err(hdev, "Controller not accepting commands anymore: ncmd = 0"); /* During HCI_INIT phase no events can be injected if the ncmd timer * triggers since the procedure has its own timeout handling. */ if (test_bit(HCI_INIT, &hdev->flags)) return; /* This is an irrecoverable state, inject hardware error event */ hci_reset_dev(hdev); } struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct oob_data *data; list_for_each_entry(data, &hdev->remote_oob_data, list) { if (bacmp(bdaddr, &data->bdaddr) != 0) continue; if (data->bdaddr_type != bdaddr_type) continue; return data; } return NULL; } int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct oob_data *data; data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type); if (!data) return -ENOENT; BT_DBG("%s removing %pMR (%u)", hdev->name, bdaddr, bdaddr_type); list_del(&data->list); kfree(data); return 0; } void hci_remote_oob_data_clear(struct hci_dev *hdev) { struct oob_data *data, *n; list_for_each_entry_safe(data, n, &hdev->remote_oob_data, list) { list_del(&data->list); kfree(data); } } int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 *hash192, u8 *rand192, u8 *hash256, u8 *rand256) { struct oob_data *data; data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type); if (!data) { data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; bacpy(&data->bdaddr, bdaddr); data->bdaddr_type = bdaddr_type; list_add(&data->list, &hdev->remote_oob_data); } if (hash192 && rand192) { memcpy(data->hash192, hash192, sizeof(data->hash192)); memcpy(data->rand192, rand192, sizeof(data->rand192)); if (hash256 && rand256) data->present = 0x03; } else { memset(data->hash192, 0, sizeof(data->hash192)); memset(data->rand192, 0, sizeof(data->rand192)); if (hash256 && rand256) data->present = 0x02; else data->present = 0x00; } if (hash256 && rand256) { memcpy(data->hash256, hash256, sizeof(data->hash256)); memcpy(data->rand256, rand256, sizeof(data->rand256)); } else { memset(data->hash256, 0, sizeof(data->hash256)); memset(data->rand256, 0, sizeof(data->rand256)); if (hash192 && rand192) data->present = 0x01; } BT_DBG("%s for %pMR", hdev->name, bdaddr); return 0; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *adv_instance; list_for_each_entry(adv_instance, &hdev->adv_instances, list) { if (adv_instance->instance == instance) return adv_instance; } return NULL; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *cur_instance; cur_instance = hci_find_adv_instance(hdev, instance); if (!cur_instance) return NULL; if (cur_instance == list_last_entry(&hdev->adv_instances, struct adv_info, list)) return list_first_entry(&hdev->adv_instances, struct adv_info, list); else return list_next_entry(cur_instance, list); } /* This function requires the caller holds hdev->lock */ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *adv_instance; adv_instance = hci_find_adv_instance(hdev, instance); if (!adv_instance) return -ENOENT; BT_DBG("%s removing %dMR", hdev->name, instance); if (hdev->cur_adv_instance == instance) { if (hdev->adv_instance_timeout) { cancel_delayed_work(&hdev->adv_instance_expire); hdev->adv_instance_timeout = 0; } hdev->cur_adv_instance = 0x00; } cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); list_del(&adv_instance->list); kfree(adv_instance); hdev->adv_instance_cnt--; return 0; } void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired) { struct adv_info *adv_instance, *n; list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) adv_instance->rpa_expired = rpa_expired; } /* This function requires the caller holds hdev->lock */ void hci_adv_instances_clear(struct hci_dev *hdev) { struct adv_info *adv_instance, *n; if (hdev->adv_instance_timeout) { cancel_delayed_work(&hdev->adv_instance_expire); hdev->adv_instance_timeout = 0; } list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) { cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); list_del(&adv_instance->list); kfree(adv_instance); } hdev->adv_instance_cnt = 0; hdev->cur_adv_instance = 0x00; } static void adv_instance_rpa_expired(struct work_struct *work) { struct adv_info *adv_instance = container_of(work, struct adv_info, rpa_expired_cb.work); BT_DBG(""); adv_instance->rpa_expired = true; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration, s8 tx_power, u32 min_interval, u32 max_interval, u8 mesh_handle) { struct adv_info *adv; adv = hci_find_adv_instance(hdev, instance); if (adv) { memset(adv->adv_data, 0, sizeof(adv->adv_data)); memset(adv->scan_rsp_data, 0, sizeof(adv->scan_rsp_data)); memset(adv->per_adv_data, 0, sizeof(adv->per_adv_data)); } else { if (hdev->adv_instance_cnt >= hdev->le_num_of_adv_sets || instance < 1 || instance > hdev->le_num_of_adv_sets + 1) return ERR_PTR(-EOVERFLOW); adv = kzalloc(sizeof(*adv), GFP_KERNEL); if (!adv) return ERR_PTR(-ENOMEM); adv->pending = true; adv->instance = instance; list_add(&adv->list, &hdev->adv_instances); hdev->adv_instance_cnt++; } adv->flags = flags; adv->min_interval = min_interval; adv->max_interval = max_interval; adv->tx_power = tx_power; /* Defining a mesh_handle changes the timing units to ms, * rather than seconds, and ties the instance to the requested * mesh_tx queue. */ adv->mesh = mesh_handle; hci_set_adv_instance_data(hdev, instance, adv_data_len, adv_data, scan_rsp_len, scan_rsp_data); adv->timeout = timeout; adv->remaining_time = timeout; if (duration == 0) adv->duration = hdev->def_multi_adv_rotation_duration; else adv->duration = duration; INIT_DELAYED_WORK(&adv->rpa_expired_cb, adv_instance_rpa_expired); BT_DBG("%s for %dMR", hdev->name, instance); return adv; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u32 flags, u8 data_len, u8 *data, u32 min_interval, u32 max_interval) { struct adv_info *adv; adv = hci_add_adv_instance(hdev, instance, flags, 0, NULL, 0, NULL, 0, 0, HCI_ADV_TX_POWER_NO_PREFERENCE, min_interval, max_interval, 0); if (IS_ERR(adv)) return adv; adv->periodic = true; adv->per_adv_data_len = data_len; if (data) memcpy(adv->per_adv_data, data, data_len); return adv; } /* This function requires the caller holds hdev->lock */ int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data) { struct adv_info *adv; adv = hci_find_adv_instance(hdev, instance); /* If advertisement doesn't exist, we can't modify its data */ if (!adv) return -ENOENT; if (adv_data_len && ADV_DATA_CMP(adv, adv_data, adv_data_len)) { memset(adv->adv_data, 0, sizeof(adv->adv_data)); memcpy(adv->adv_data, adv_data, adv_data_len); adv->adv_data_len = adv_data_len; adv->adv_data_changed = true; } if (scan_rsp_len && SCAN_RSP_CMP(adv, scan_rsp_data, scan_rsp_len)) { memset(adv->scan_rsp_data, 0, sizeof(adv->scan_rsp_data)); memcpy(adv->scan_rsp_data, scan_rsp_data, scan_rsp_len); adv->scan_rsp_len = scan_rsp_len; adv->scan_rsp_changed = true; } /* Mark as changed if there are flags which would affect it */ if (((adv->flags & MGMT_ADV_FLAG_APPEARANCE) && hdev->appearance) || adv->flags & MGMT_ADV_FLAG_LOCAL_NAME) adv->scan_rsp_changed = true; return 0; } /* This function requires the caller holds hdev->lock */ u32 hci_adv_instance_flags(struct hci_dev *hdev, u8 instance) { u32 flags; struct adv_info *adv; if (instance == 0x00) { /* Instance 0 always manages the "Tx Power" and "Flags" * fields */ flags = MGMT_ADV_FLAG_TX_POWER | MGMT_ADV_FLAG_MANAGED_FLAGS; /* For instance 0, the HCI_ADVERTISING_CONNECTABLE setting * corresponds to the "connectable" instance flag. */ if (hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE)) flags |= MGMT_ADV_FLAG_CONNECTABLE; if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) flags |= MGMT_ADV_FLAG_LIMITED_DISCOV; else if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) flags |= MGMT_ADV_FLAG_DISCOV; return flags; } adv = hci_find_adv_instance(hdev, instance); /* Return 0 when we got an invalid instance identifier. */ if (!adv) return 0; return adv->flags; } bool hci_adv_instance_is_scannable(struct hci_dev *hdev, u8 instance) { struct adv_info *adv; /* Instance 0x00 always set local name */ if (instance == 0x00) return true; adv = hci_find_adv_instance(hdev, instance); if (!adv) return false; if (adv->flags & MGMT_ADV_FLAG_APPEARANCE || adv->flags & MGMT_ADV_FLAG_LOCAL_NAME) return true; return adv->scan_rsp_len ? true : false; } /* This function requires the caller holds hdev->lock */ void hci_adv_monitors_clear(struct hci_dev *hdev) { struct adv_monitor *monitor; int handle; idr_for_each_entry(&hdev->adv_monitors_idr, monitor, handle) hci_free_adv_monitor(hdev, monitor); idr_destroy(&hdev->adv_monitors_idr); } /* Frees the monitor structure and do some bookkeepings. * This function requires the caller holds hdev->lock. */ void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { struct adv_pattern *pattern; struct adv_pattern *tmp; if (!monitor) return; list_for_each_entry_safe(pattern, tmp, &monitor->patterns, list) { list_del(&pattern->list); kfree(pattern); } if (monitor->handle) idr_remove(&hdev->adv_monitors_idr, monitor->handle); if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) { hdev->adv_monitors_cnt--; mgmt_adv_monitor_removed(hdev, monitor->handle); } kfree(monitor); } /* Assigns handle to a monitor, and if offloading is supported and power is on, * also attempts to forward the request to the controller. * This function requires the caller holds hci_req_sync_lock. */ int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int min, max, handle; int status = 0; if (!monitor) return -EINVAL; hci_dev_lock(hdev); min = HCI_MIN_ADV_MONITOR_HANDLE; max = HCI_MIN_ADV_MONITOR_HANDLE + HCI_MAX_ADV_MONITOR_NUM_HANDLES; handle = idr_alloc(&hdev->adv_monitors_idr, monitor, min, max, GFP_KERNEL); hci_dev_unlock(hdev); if (handle < 0) return handle; monitor->handle = handle; if (!hdev_is_powered(hdev)) return status; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: bt_dev_dbg(hdev, "add monitor %d status %d", monitor->handle, status); /* Message was not forwarded to controller - not an error */ break; case HCI_ADV_MONITOR_EXT_MSFT: status = msft_add_monitor_pattern(hdev, monitor); bt_dev_dbg(hdev, "add monitor %d msft status %d", handle, status); break; } return status; } /* Attempts to tell the controller and free the monitor. If somehow the * controller doesn't have a corresponding handle, remove anyway. * This function requires the caller holds hci_req_sync_lock. */ static int hci_remove_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int status = 0; int handle; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ bt_dev_dbg(hdev, "remove monitor %d status %d", monitor->handle, status); goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); bt_dev_dbg(hdev, "remove monitor %d msft status %d", handle, status); break; } /* In case no matching handle registered, just free the monitor */ if (status == -ENOENT) goto free_monitor; return status; free_monitor: if (status == -ENOENT) bt_dev_warn(hdev, "Removing monitor with no matching handle %d", monitor->handle); hci_free_adv_monitor(hdev, monitor); return status; } /* This function requires the caller holds hci_req_sync_lock */ int hci_remove_single_adv_monitor(struct hci_dev *hdev, u16 handle) { struct adv_monitor *monitor = idr_find(&hdev->adv_monitors_idr, handle); if (!monitor) return -EINVAL; return hci_remove_adv_monitor(hdev, monitor); } /* This function requires the caller holds hci_req_sync_lock */ int hci_remove_all_adv_monitor(struct hci_dev *hdev) { struct adv_monitor *monitor; int idr_next_id = 0; int status = 0; while (1) { monitor = idr_get_next(&hdev->adv_monitors_idr, &idr_next_id); if (!monitor) break; status = hci_remove_adv_monitor(hdev, monitor); if (status) return status; idr_next_id++; } return status; } /* This function requires the caller holds hdev->lock */ bool hci_is_adv_monitoring(struct hci_dev *hdev) { return !idr_is_empty(&hdev->adv_monitors_idr); } int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev) { if (msft_monitor_supported(hdev)) return HCI_ADV_MONITOR_EXT_MSFT; return HCI_ADV_MONITOR_EXT_NONE; } struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_irk *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } struct bdaddr_list_with_flags * hci_bdaddr_list_lookup_with_flags(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_flags *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } void hci_bdaddr_list_clear(struct list_head *bdaddr_list) { struct bdaddr_list *b, *n; list_for_each_entry_safe(b, n, bdaddr_list, list) { list_del(&b->list); kfree(b); } } int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; list_add(&entry->list, list); return 0; } int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type, u8 *peer_irk, u8 *local_irk) { struct bdaddr_list_with_irk *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; if (peer_irk) memcpy(entry->peer_irk, peer_irk, 16); if (local_irk) memcpy(entry->local_irk, local_irk, 16); list_add(&entry->list, list); return 0; } int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type, u32 flags) { struct bdaddr_list_with_flags *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; entry->flags = flags; list_add(&entry->list, list); return 0; } int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; if (!bacmp(bdaddr, BDADDR_ANY)) { hci_bdaddr_list_clear(list); return 0; } entry = hci_bdaddr_list_lookup(list, bdaddr, type); if (!entry) return -ENOENT; list_del(&entry->list); kfree(entry); return 0; } int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_irk *entry; if (!bacmp(bdaddr, BDADDR_ANY)) { hci_bdaddr_list_clear(list); return 0; } entry = hci_bdaddr_list_lookup_with_irk(list, bdaddr, type); if (!entry) return -ENOENT; list_del(&entry->list); kfree(entry); return 0; } int hci_bdaddr_list_del_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_flags *entry; if (!bacmp(bdaddr, BDADDR_ANY)) { hci_bdaddr_list_clear(list); return 0; } entry = hci_bdaddr_list_lookup_with_flags(list, bdaddr, type); if (!entry) return -ENOENT; list_del(&entry->list); kfree(entry); return 0; } /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; list_for_each_entry(params, &hdev->le_conn_params, list) { if (bacmp(¶ms->addr, addr) == 0 && params->addr_type == addr_type) { return params; } } return NULL; } /* This function requires the caller holds hdev->lock or rcu_read_lock */ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *param; rcu_read_lock(); list_for_each_entry_rcu(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && param->addr_type == addr_type) { rcu_read_unlock(); return param; } } rcu_read_unlock(); return NULL; } /* This function requires the caller holds hdev->lock */ void hci_pend_le_list_del_init(struct hci_conn_params *param) { if (list_empty(¶m->action)) return; list_del_rcu(¶m->action); synchronize_rcu(); INIT_LIST_HEAD(¶m->action); } /* This function requires the caller holds hdev->lock */ void hci_pend_le_list_add(struct hci_conn_params *param, struct list_head *list) { list_add_rcu(¶m->action, list); } /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; params = hci_conn_params_lookup(hdev, addr, addr_type); if (params) return params; params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) { bt_dev_err(hdev, "out of memory"); return NULL; } bacpy(¶ms->addr, addr); params->addr_type = addr_type; list_add(¶ms->list, &hdev->le_conn_params); INIT_LIST_HEAD(¶ms->action); params->conn_min_interval = hdev->le_conn_min_interval; params->conn_max_interval = hdev->le_conn_max_interval; params->conn_latency = hdev->le_conn_latency; params->supervision_timeout = hdev->le_supv_timeout; params->auto_connect = HCI_AUTO_CONN_DISABLED; BT_DBG("addr %pMR (type %u)", addr, addr_type); return params; } void hci_conn_params_free(struct hci_conn_params *params) { hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); } list_del(¶ms->list); kfree(params); } /* This function requires the caller holds hdev->lock */ void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; params = hci_conn_params_lookup(hdev, addr, addr_type); if (!params) return; hci_conn_params_free(params); hci_update_passive_scan(hdev); BT_DBG("addr %pMR (type %u)", addr, addr_type); } /* This function requires the caller holds hdev->lock */ void hci_conn_params_clear_disabled(struct hci_dev *hdev) { struct hci_conn_params *params, *tmp; list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { if (params->auto_connect != HCI_AUTO_CONN_DISABLED) continue; /* If trying to establish one time connection to disabled * device, leave the params, but mark them as just once. */ if (params->explicit_connect) { params->auto_connect = HCI_AUTO_CONN_EXPLICIT; continue; } hci_conn_params_free(params); } BT_DBG("All LE disabled connection parameters were removed"); } /* This function requires the caller holds hdev->lock */ static void hci_conn_params_clear_all(struct hci_dev *hdev) { struct hci_conn_params *params, *tmp; list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) hci_conn_params_free(params); BT_DBG("All LE connection parameters were removed"); } /* Copy the Identity Address of the controller. * * If the controller has a public BD_ADDR, then by default use that one. * If this is a LE only controller without a public address, default to * the static random address. * * For debugging purposes it is possible to force controllers with a * public address to use the static random address instead. * * In case BR/EDR has been disabled on a dual-mode controller and * userspace has configured a static address, then that address * becomes the identity address instead of the public BR/EDR address. */ void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type) { if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) || !bacmp(&hdev->bdaddr, BDADDR_ANY) || (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && bacmp(&hdev->static_addr, BDADDR_ANY))) { bacpy(bdaddr, &hdev->static_addr); *bdaddr_type = ADDR_LE_DEV_RANDOM; } else { bacpy(bdaddr, &hdev->bdaddr); *bdaddr_type = ADDR_LE_DEV_PUBLIC; } } static void hci_clear_wake_reason(struct hci_dev *hdev) { hci_dev_lock(hdev); hdev->wake_reason = 0; bacpy(&hdev->wake_addr, BDADDR_ANY); hdev->wake_addr_type = 0; hci_dev_unlock(hdev); } static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct hci_dev *hdev = container_of(nb, struct hci_dev, suspend_notifier); int ret = 0; /* Userspace has full control of this device. Do nothing. */ if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return NOTIFY_DONE; /* To avoid a potential race with hci_unregister_dev. */ hci_dev_hold(hdev); if (action == PM_SUSPEND_PREPARE) ret = hci_suspend_dev(hdev); else if (action == PM_POST_SUSPEND) ret = hci_resume_dev(hdev); if (ret) bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", action, ret); hci_dev_put(hdev); return NOTIFY_DONE; } /* Alloc HCI device */ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) { struct hci_dev *hdev; unsigned int alloc_size; alloc_size = sizeof(*hdev); if (sizeof_priv) { /* Fixme: May need ALIGN-ment? */ alloc_size += sizeof_priv; } hdev = kzalloc(alloc_size, GFP_KERNEL); if (!hdev) return NULL; hdev->pkt_type = (HCI_DM1 | HCI_DH1 | HCI_HV1); hdev->esco_type = (ESCO_HV1); hdev->link_mode = (HCI_LM_ACCEPT); hdev->num_iac = 0x01; /* One IAC support is mandatory */ hdev->io_capability = 0x03; /* No Input No Output */ hdev->manufacturer = 0xffff; /* Default to internal use */ hdev->inq_tx_power = HCI_TX_POWER_INVALID; hdev->adv_tx_power = HCI_TX_POWER_INVALID; hdev->adv_instance_cnt = 0; hdev->cur_adv_instance = 0x00; hdev->adv_instance_timeout = 0; hdev->advmon_allowlist_duration = 300; hdev->advmon_no_filter_duration = 500; hdev->enable_advmon_interleave_scan = 0x00; /* Default to disable */ hdev->sniff_max_interval = 800; hdev->sniff_min_interval = 80; hdev->le_adv_channel_map = 0x07; hdev->le_adv_min_interval = 0x0800; hdev->le_adv_max_interval = 0x0800; hdev->le_scan_interval = 0x0060; hdev->le_scan_window = 0x0030; hdev->le_scan_int_suspend = 0x0400; hdev->le_scan_window_suspend = 0x0012; hdev->le_scan_int_discovery = DISCOV_LE_SCAN_INT; hdev->le_scan_window_discovery = DISCOV_LE_SCAN_WIN; hdev->le_scan_int_adv_monitor = 0x0060; hdev->le_scan_window_adv_monitor = 0x0030; hdev->le_scan_int_connect = 0x0060; hdev->le_scan_window_connect = 0x0060; hdev->le_conn_min_interval = 0x0018; hdev->le_conn_max_interval = 0x0028; hdev->le_conn_latency = 0x0000; hdev->le_supv_timeout = 0x002a; hdev->le_def_tx_len = 0x001b; hdev->le_def_tx_time = 0x0148; hdev->le_max_tx_len = 0x001b; hdev->le_max_tx_time = 0x0148; hdev->le_max_rx_len = 0x001b; hdev->le_max_rx_time = 0x0148; hdev->le_max_key_size = SMP_MAX_ENC_KEY_SIZE; hdev->le_min_key_size = SMP_MIN_ENC_KEY_SIZE; hdev->le_tx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_num_of_adv_sets = HCI_MAX_ADV_INSTANCES; hdev->def_multi_adv_rotation_duration = HCI_DEFAULT_ADV_DURATION; hdev->def_le_autoconnect_timeout = HCI_LE_AUTOCONN_TIMEOUT; hdev->min_le_tx_power = HCI_TX_POWER_INVALID; hdev->max_le_tx_power = HCI_TX_POWER_INVALID; hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT; hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE; hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE; hdev->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT; hdev->min_enc_key_size = HCI_MIN_ENC_KEY_SIZE; /* default 1.28 sec page scan */ hdev->def_page_scan_type = PAGE_SCAN_TYPE_STANDARD; hdev->def_page_scan_int = 0x0800; hdev->def_page_scan_window = 0x0012; mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); ida_init(&hdev->unset_handle_ida); INIT_LIST_HEAD(&hdev->mesh_pending); INIT_LIST_HEAD(&hdev->mgmt_pending); INIT_LIST_HEAD(&hdev->reject_list); INIT_LIST_HEAD(&hdev->accept_list); INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); INIT_LIST_HEAD(&hdev->le_accept_list); INIT_LIST_HEAD(&hdev->le_resolv_list); INIT_LIST_HEAD(&hdev->le_conn_params); INIT_LIST_HEAD(&hdev->pend_le_conns); INIT_LIST_HEAD(&hdev->pend_le_reports); INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_LIST_HEAD(&hdev->adv_instances); INIT_LIST_HEAD(&hdev->blocked_keys); INIT_LIST_HEAD(&hdev->monitored_devices); INIT_LIST_HEAD(&hdev->local_codecs); INIT_WORK(&hdev->rx_work, hci_rx_work); INIT_WORK(&hdev->cmd_work, hci_cmd_work); INIT_WORK(&hdev->tx_work, hci_tx_work); INIT_WORK(&hdev->power_on, hci_power_on); INIT_WORK(&hdev->error_reset, hci_error_reset); hci_cmd_sync_init(hdev); INIT_DELAYED_WORK(&hdev->power_off, hci_power_off); skb_queue_head_init(&hdev->rx_q); skb_queue_head_init(&hdev->cmd_q); skb_queue_head_init(&hdev->raw_q); init_waitqueue_head(&hdev->req_wait_q); INIT_DELAYED_WORK(&hdev->cmd_timer, hci_cmd_timeout); INIT_DELAYED_WORK(&hdev->ncmd_timer, hci_ncmd_timeout); hci_devcd_setup(hdev); hci_request_setup(hdev); hci_init_sysfs(hdev); discovery_init(hdev); return hdev; } EXPORT_SYMBOL(hci_alloc_dev_priv); /* Free HCI device */ void hci_free_dev(struct hci_dev *hdev) { /* will free via device release */ put_device(&hdev->dev); } EXPORT_SYMBOL(hci_free_dev); /* Register HCI device */ int hci_register_dev(struct hci_dev *hdev) { int id, error; if (!hdev->open || !hdev->close || !hdev->send) return -EINVAL; /* Do not allow HCI_AMP devices to register at index 0, * so the index can be used as the AMP controller ID. */ switch (hdev->dev_type) { case HCI_PRIMARY: id = ida_simple_get(&hci_index_ida, 0, HCI_MAX_ID, GFP_KERNEL); break; case HCI_AMP: id = ida_simple_get(&hci_index_ida, 1, HCI_MAX_ID, GFP_KERNEL); break; default: return -EINVAL; } if (id < 0) return id; error = dev_set_name(&hdev->dev, "hci%u", id); if (error) return error; hdev->name = dev_name(&hdev->dev); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); hdev->workqueue = alloc_ordered_workqueue("%s", WQ_HIGHPRI, hdev->name); if (!hdev->workqueue) { error = -ENOMEM; goto err; } hdev->req_workqueue = alloc_ordered_workqueue("%s", WQ_HIGHPRI, hdev->name); if (!hdev->req_workqueue) { destroy_workqueue(hdev->workqueue); error = -ENOMEM; goto err; } if (!IS_ERR_OR_NULL(bt_debugfs)) hdev->debugfs = debugfs_create_dir(hdev->name, bt_debugfs); error = device_add(&hdev->dev); if (error < 0) goto err_wqueue; hci_leds_init(hdev); hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, hdev); if (hdev->rfkill) { if (rfkill_register(hdev->rfkill) < 0) { rfkill_destroy(hdev->rfkill); hdev->rfkill = NULL; } } if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) hci_dev_set_flag(hdev, HCI_RFKILLED); hci_dev_set_flag(hdev, HCI_SETUP); hci_dev_set_flag(hdev, HCI_AUTO_OFF); if (hdev->dev_type == HCI_PRIMARY) { /* Assume BR/EDR support until proven otherwise (such as * through reading supported features during init. */ hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); } write_lock(&hci_dev_list_lock); list_add(&hdev->list, &hci_dev_list); write_unlock(&hci_dev_list_lock); /* Devices that are marked for raw-only usage are unconfigured * and should not be included in normal operation. */ if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) hci_dev_set_flag(hdev, HCI_UNCONFIGURED); /* Mark Remote Wakeup connection flag as supported if driver has wakeup * callback. */ if (hdev->wakeup) hdev->conn_flags |= HCI_CONN_FLAG_REMOTE_WAKEUP; hci_sock_dev_event(hdev, HCI_DEV_REG); hci_dev_hold(hdev); error = hci_register_suspend_notifier(hdev); if (error) BT_WARN("register suspend notifier failed error:%d\n", error); queue_work(hdev->req_workqueue, &hdev->power_on); idr_init(&hdev->adv_monitors_idr); msft_register(hdev); return id; err_wqueue: debugfs_remove_recursive(hdev->debugfs); destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); err: ida_simple_remove(&hci_index_ida, hdev->id); return error; } EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); mutex_lock(&hdev->unregister_lock); hci_dev_set_flag(hdev, HCI_UNREGISTER); mutex_unlock(&hdev->unregister_lock); write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); cancel_work_sync(&hdev->power_on); hci_cmd_sync_clear(hdev); hci_unregister_suspend_notifier(hdev); msft_unregister(hdev); hci_dev_do_close(hdev); if (!test_bit(HCI_INIT, &hdev->flags) && !hci_dev_test_flag(hdev, HCI_SETUP) && !hci_dev_test_flag(hdev, HCI_CONFIG)) { hci_dev_lock(hdev); mgmt_index_removed(hdev); hci_dev_unlock(hdev); } /* mgmt_index_removed should take care of emptying the * pending list */ BUG_ON(!list_empty(&hdev->mgmt_pending)); hci_sock_dev_event(hdev, HCI_DEV_UNREG); if (hdev->rfkill) { rfkill_unregister(hdev->rfkill); rfkill_destroy(hdev->rfkill); } device_del(&hdev->dev); /* Actual cleanup is deferred until hci_release_dev(). */ hci_dev_put(hdev); } EXPORT_SYMBOL(hci_unregister_dev); /* Release HCI device */ void hci_release_dev(struct hci_dev *hdev) { debugfs_remove_recursive(hdev->debugfs); kfree_const(hdev->hw_info); kfree_const(hdev->fw_info); destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); hci_dev_lock(hdev); hci_bdaddr_list_clear(&hdev->reject_list); hci_bdaddr_list_clear(&hdev->accept_list); hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_smp_ltks_clear(hdev); hci_smp_irks_clear(hdev); hci_remote_oob_data_clear(hdev); hci_adv_instances_clear(hdev); hci_adv_monitors_clear(hdev); hci_bdaddr_list_clear(&hdev->le_accept_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); hci_blocked_keys_clear(hdev); hci_codec_list_clear(&hdev->local_codecs); hci_dev_unlock(hdev); ida_destroy(&hdev->unset_handle_ida); ida_simple_remove(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); kfree_skb(hdev->recv_event); kfree(hdev); } EXPORT_SYMBOL(hci_release_dev); int hci_register_suspend_notifier(struct hci_dev *hdev) { int ret = 0; if (!hdev->suspend_notifier.notifier_call && !test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { hdev->suspend_notifier.notifier_call = hci_suspend_notifier; ret = register_pm_notifier(&hdev->suspend_notifier); } return ret; } int hci_unregister_suspend_notifier(struct hci_dev *hdev) { int ret = 0; if (hdev->suspend_notifier.notifier_call) { ret = unregister_pm_notifier(&hdev->suspend_notifier); if (!ret) hdev->suspend_notifier.notifier_call = NULL; } return ret; } /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) { int ret; bt_dev_dbg(hdev, ""); /* Suspend should only act on when powered. */ if (!hdev_is_powered(hdev) || hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; /* If powering down don't attempt to suspend */ if (mgmt_powering_down(hdev)) return 0; /* Cancel potentially blocking sync operation before suspend */ __hci_cmd_sync_cancel(hdev, -EHOSTDOWN); hci_req_sync_lock(hdev); ret = hci_suspend_sync(hdev); hci_req_sync_unlock(hdev); hci_clear_wake_reason(hdev); mgmt_suspending(hdev, hdev->suspend_state); hci_sock_dev_event(hdev, HCI_DEV_SUSPEND); return ret; } EXPORT_SYMBOL(hci_suspend_dev); /* Resume HCI device */ int hci_resume_dev(struct hci_dev *hdev) { int ret; bt_dev_dbg(hdev, ""); /* Resume should only act on when powered. */ if (!hdev_is_powered(hdev) || hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; /* If powering down don't attempt to resume */ if (mgmt_powering_down(hdev)) return 0; hci_req_sync_lock(hdev); ret = hci_resume_sync(hdev); hci_req_sync_unlock(hdev); mgmt_resuming(hdev, hdev->wake_reason, &hdev->wake_addr, hdev->wake_addr_type); hci_sock_dev_event(hdev, HCI_DEV_RESUME); return ret; } EXPORT_SYMBOL(hci_resume_dev); /* Reset HCI device */ int hci_reset_dev(struct hci_dev *hdev) { static const u8 hw_err[] = { HCI_EV_HARDWARE_ERROR, 0x01, 0x00 }; struct sk_buff *skb; skb = bt_skb_alloc(3, GFP_ATOMIC); if (!skb) return -ENOMEM; hci_skb_pkt_type(skb) = HCI_EVENT_PKT; skb_put_data(skb, hw_err, 3); bt_dev_err(hdev, "Injecting HCI hardware error event"); /* Send Hardware Error to upper stack */ return hci_recv_frame(hdev, skb); } EXPORT_SYMBOL(hci_reset_dev); /* Receive frame from HCI drivers */ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb) { if (!hdev || (!test_bit(HCI_UP, &hdev->flags) && !test_bit(HCI_INIT, &hdev->flags))) { kfree_skb(skb); return -ENXIO; } switch (hci_skb_pkt_type(skb)) { case HCI_EVENT_PKT: break; case HCI_ACLDATA_PKT: /* Detect if ISO packet has been sent as ACL */ if (hci_conn_num(hdev, ISO_LINK)) { __u16 handle = __le16_to_cpu(hci_acl_hdr(skb)->handle); __u8 type; type = hci_conn_lookup_type(hdev, hci_handle(handle)); if (type == ISO_LINK) hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; } break; case HCI_SCODATA_PKT: break; case HCI_ISODATA_PKT: break; default: kfree_skb(skb); return -EINVAL; } /* Incoming skb */ bt_cb(skb)->incoming = 1; /* Time stamp */ __net_timestamp(skb); skb_queue_tail(&hdev->rx_q, skb); queue_work(hdev->workqueue, &hdev->rx_work); return 0; } EXPORT_SYMBOL(hci_recv_frame); /* Receive diagnostic message from HCI drivers */ int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb) { /* Mark as diagnostic packet */ hci_skb_pkt_type(skb) = HCI_DIAG_PKT; /* Time stamp */ __net_timestamp(skb); skb_queue_tail(&hdev->rx_q, skb); queue_work(hdev->workqueue, &hdev->rx_work); return 0; } EXPORT_SYMBOL(hci_recv_diag); void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...) { va_list vargs; va_start(vargs, fmt); kfree_const(hdev->hw_info); hdev->hw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs); va_end(vargs); } EXPORT_SYMBOL(hci_set_hw_info); void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...) { va_list vargs; va_start(vargs, fmt); kfree_const(hdev->fw_info); hdev->fw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs); va_end(vargs); } EXPORT_SYMBOL(hci_set_fw_info); /* ---- Interface to upper protocols ---- */ int hci_register_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); mutex_lock(&hci_cb_list_lock); list_add_tail(&cb->list, &hci_cb_list); mutex_unlock(&hci_cb_list_lock); return 0; } EXPORT_SYMBOL(hci_register_cb); int hci_unregister_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); mutex_lock(&hci_cb_list_lock); list_del(&cb->list); mutex_unlock(&hci_cb_list_lock); return 0; } EXPORT_SYMBOL(hci_unregister_cb); static int hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) { int err; BT_DBG("%s type %d len %d", hdev->name, hci_skb_pkt_type(skb), skb->len); /* Time stamp */ __net_timestamp(skb); /* Send copy to monitor */ hci_send_to_monitor(hdev, skb); if (atomic_read(&hdev->promisc)) { /* Send copy to the sockets */ hci_send_to_sock(hdev, skb); } /* Get rid of skb owner, prior to sending to the driver. */ skb_orphan(skb); if (!test_bit(HCI_RUNNING, &hdev->flags)) { kfree_skb(skb); return -EINVAL; } err = hdev->send(hdev, skb); if (err < 0) { bt_dev_err(hdev, "sending frame failed (%d)", err); kfree_skb(skb); return err; } return 0; } /* Send HCI command */ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, const void *param) { struct sk_buff *skb; BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen); skb = hci_prepare_cmd(hdev, opcode, plen, param); if (!skb) { bt_dev_err(hdev, "no memory for command"); return -ENOMEM; } /* Stand-alone HCI commands must be flagged as * single-command requests. */ bt_cb(skb)->hci.req_flags |= HCI_REQ_START; skb_queue_tail(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); return 0; } int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param) { struct sk_buff *skb; if (hci_opcode_ogf(opcode) != 0x3f) { /* A controller receiving a command shall respond with either * a Command Status Event or a Command Complete Event. * Therefore, all standard HCI commands must be sent via the * standard API, using hci_send_cmd or hci_cmd_sync helpers. * Some vendors do not comply with this rule for vendor-specific * commands and do not return any event. We want to support * unresponded commands for such cases only. */ bt_dev_err(hdev, "unresponded command not supported"); return -EINVAL; } skb = hci_prepare_cmd(hdev, opcode, plen, param); if (!skb) { bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)", opcode); return -ENOMEM; } hci_send_frame(hdev, skb); return 0; } EXPORT_SYMBOL(__hci_cmd_send); /* Get data from the previously sent command */ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) { struct hci_command_hdr *hdr; if (!hdev->sent_cmd) return NULL; hdr = (void *) hdev->sent_cmd->data; if (hdr->opcode != cpu_to_le16(opcode)) return NULL; BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; } /* Get data from last received event */ void *hci_recv_event_data(struct hci_dev *hdev, __u8 event) { struct hci_event_hdr *hdr; int offset; if (!hdev->recv_event) return NULL; hdr = (void *)hdev->recv_event->data; offset = sizeof(*hdr); if (hdr->evt != event) { /* In case of LE metaevent check the subevent match */ if (hdr->evt == HCI_EV_LE_META) { struct hci_ev_le_meta *ev; ev = (void *)hdev->recv_event->data + offset; offset += sizeof(*ev); if (ev->subevent == event) goto found; } return NULL; } found: bt_dev_dbg(hdev, "event 0x%2.2x", event); return hdev->recv_event->data + offset; } /* Send ACL data */ static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags) { struct hci_acl_hdr *hdr; int len = skb->len; skb_push(skb, HCI_ACL_HDR_SIZE); skb_reset_transport_header(skb); hdr = (struct hci_acl_hdr *)skb_transport_header(skb); hdr->handle = cpu_to_le16(hci_handle_pack(handle, flags)); hdr->dlen = cpu_to_le16(len); } static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue, struct sk_buff *skb, __u16 flags) { struct hci_conn *conn = chan->conn; struct hci_dev *hdev = conn->hdev; struct sk_buff *list; skb->len = skb_headlen(skb); skb->data_len = 0; hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT; switch (hdev->dev_type) { case HCI_PRIMARY: hci_add_acl_hdr(skb, conn->handle, flags); break; case HCI_AMP: hci_add_acl_hdr(skb, chan->handle, flags); break; default: bt_dev_err(hdev, "unknown dev_type %d", hdev->dev_type); return; } list = skb_shinfo(skb)->frag_list; if (!list) { /* Non fragmented */ BT_DBG("%s nonfrag skb %p len %d", hdev->name, skb, skb->len); skb_queue_tail(queue, skb); } else { /* Fragmented */ BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); skb_shinfo(skb)->frag_list = NULL; /* Queue all fragments atomically. We need to use spin_lock_bh * here because of 6LoWPAN links, as there this function is * called from softirq and using normal spin lock could cause * deadlocks. */ spin_lock_bh(&queue->lock); __skb_queue_tail(queue, skb); flags &= ~ACL_START; flags |= ACL_CONT; do { skb = list; list = list->next; hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT; hci_add_acl_hdr(skb, conn->handle, flags); BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); __skb_queue_tail(queue, skb); } while (list); spin_unlock_bh(&queue->lock); } } void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags) { struct hci_dev *hdev = chan->conn->hdev; BT_DBG("%s chan %p flags 0x%4.4x", hdev->name, chan, flags); hci_queue_acl(chan, &chan->data_q, skb, flags); queue_work(hdev->workqueue, &hdev->tx_work); } /* Send SCO data */ void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; struct hci_sco_hdr hdr; BT_DBG("%s len %d", hdev->name, skb->len); hdr.handle = cpu_to_le16(conn->handle); hdr.dlen = skb->len; skb_push(skb, HCI_SCO_HDR_SIZE); skb_reset_transport_header(skb); memcpy(skb_transport_header(skb), &hdr, HCI_SCO_HDR_SIZE); hci_skb_pkt_type(skb) = HCI_SCODATA_PKT; skb_queue_tail(&conn->data_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } /* Send ISO data */ static void hci_add_iso_hdr(struct sk_buff *skb, __u16 handle, __u8 flags) { struct hci_iso_hdr *hdr; int len = skb->len; skb_push(skb, HCI_ISO_HDR_SIZE); skb_reset_transport_header(skb); hdr = (struct hci_iso_hdr *)skb_transport_header(skb); hdr->handle = cpu_to_le16(hci_handle_pack(handle, flags)); hdr->dlen = cpu_to_le16(len); } static void hci_queue_iso(struct hci_conn *conn, struct sk_buff_head *queue, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; struct sk_buff *list; __u16 flags; skb->len = skb_headlen(skb); skb->data_len = 0; hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; list = skb_shinfo(skb)->frag_list; flags = hci_iso_flags_pack(list ? ISO_START : ISO_SINGLE, 0x00); hci_add_iso_hdr(skb, conn->handle, flags); if (!list) { /* Non fragmented */ BT_DBG("%s nonfrag skb %p len %d", hdev->name, skb, skb->len); skb_queue_tail(queue, skb); } else { /* Fragmented */ BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); skb_shinfo(skb)->frag_list = NULL; __skb_queue_tail(queue, skb); do { skb = list; list = list->next; hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; flags = hci_iso_flags_pack(list ? ISO_CONT : ISO_END, 0x00); hci_add_iso_hdr(skb, conn->handle, flags); BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); __skb_queue_tail(queue, skb); } while (list); } } void hci_send_iso(struct hci_conn *conn, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; BT_DBG("%s len %d", hdev->name, skb->len); hci_queue_iso(conn, &conn->data_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } /* ---- HCI TX task (outgoing data) ---- */ /* HCI Connection scheduler */ static inline void hci_quote_sent(struct hci_conn *conn, int num, int *quote) { struct hci_dev *hdev; int cnt, q; if (!conn) { *quote = 0; return; } hdev = conn->hdev; switch (conn->type) { case ACL_LINK: cnt = hdev->acl_cnt; break; case AMP_LINK: cnt = hdev->block_cnt; break; case SCO_LINK: case ESCO_LINK: cnt = hdev->sco_cnt; break; case LE_LINK: cnt = hdev->le_mtu ? hdev->le_cnt : hdev->acl_cnt; break; case ISO_LINK: cnt = hdev->iso_mtu ? hdev->iso_cnt : hdev->le_mtu ? hdev->le_cnt : hdev->acl_cnt; break; default: cnt = 0; bt_dev_err(hdev, "unknown link type %d", conn->type); } q = cnt / num; *quote = q ? q : 1; } static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int *quote) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *conn = NULL, *c; unsigned int num = 0, min = ~0; /* We don't have to lock device here. Connections are always * added and removed with TX task disabled. */ rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != type || skb_queue_empty(&c->data_q)) continue; if (c->state != BT_CONNECTED && c->state != BT_CONFIG) continue; num++; if (c->sent < min) { min = c->sent; conn = c; } if (hci_conn_num(hdev, type) == num) break; } rcu_read_unlock(); hci_quote_sent(conn, num, quote); BT_DBG("conn %p quote %d", conn, *quote); return conn; } static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; bt_dev_err(hdev, "link tx timeout"); rcu_read_lock(); /* Kill stalled connections */ list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->sent) { bt_dev_err(hdev, "killing stalled connection %pMR", &c->dst); /* hci_disconnect might sleep, so, we have to release * the RCU read lock before calling it. */ rcu_read_unlock(); hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM); rcu_read_lock(); } } rcu_read_unlock(); } static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, int *quote) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_chan *chan = NULL; unsigned int num = 0, min = ~0, cur_prio = 0; struct hci_conn *conn; int conn_num = 0; BT_DBG("%s", hdev->name); rcu_read_lock(); list_for_each_entry_rcu(conn, &h->list, list) { struct hci_chan *tmp; if (conn->type != type) continue; if (conn->state != BT_CONNECTED && conn->state != BT_CONFIG) continue; conn_num++; list_for_each_entry_rcu(tmp, &conn->chan_list, list) { struct sk_buff *skb; if (skb_queue_empty(&tmp->data_q)) continue; skb = skb_peek(&tmp->data_q); if (skb->priority < cur_prio) continue; if (skb->priority > cur_prio) { num = 0; min = ~0; cur_prio = skb->priority; } num++; if (conn->sent < min) { min = conn->sent; chan = tmp; } } if (hci_conn_num(hdev, type) == conn_num) break; } rcu_read_unlock(); if (!chan) return NULL; hci_quote_sent(chan->conn, num, quote); BT_DBG("chan %p quote %d", chan, *quote); return chan; } static void hci_prio_recalculate(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *conn; int num = 0; BT_DBG("%s", hdev->name); rcu_read_lock(); list_for_each_entry_rcu(conn, &h->list, list) { struct hci_chan *chan; if (conn->type != type) continue; if (conn->state != BT_CONNECTED && conn->state != BT_CONFIG) continue; num++; list_for_each_entry_rcu(chan, &conn->chan_list, list) { struct sk_buff *skb; if (chan->sent) { chan->sent = 0; continue; } if (skb_queue_empty(&chan->data_q)) continue; skb = skb_peek(&chan->data_q); if (skb->priority >= HCI_PRIO_MAX - 1) continue; skb->priority = HCI_PRIO_MAX - 1; BT_DBG("chan %p skb %p promoted to %d", chan, skb, skb->priority); } if (hci_conn_num(hdev, type) == num) break; } rcu_read_unlock(); } static inline int __get_blocks(struct hci_dev *hdev, struct sk_buff *skb) { /* Calculate count of blocks used by this packet */ return DIV_ROUND_UP(skb->len - HCI_ACL_HDR_SIZE, hdev->block_len); } static void __check_timeout(struct hci_dev *hdev, unsigned int cnt, u8 type) { unsigned long last_tx; if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) return; switch (type) { case LE_LINK: last_tx = hdev->le_last_tx; break; default: last_tx = hdev->acl_last_tx; break; } /* tx timeout must be longer than maximum link supervision timeout * (40.9 seconds) */ if (!cnt && time_after(jiffies, last_tx + HCI_ACL_TX_TIMEOUT)) hci_link_tx_to(hdev, type); } /* Schedule SCO */ static void hci_sched_sco(struct hci_dev *hdev) { struct hci_conn *conn; struct sk_buff *skb; int quote; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, SCO_LINK)) return; while (hdev->sco_cnt && (conn = hci_low_sent(hdev, SCO_LINK, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_frame(hdev, skb); conn->sent++; if (conn->sent == ~0) conn->sent = 0; } } } static void hci_sched_esco(struct hci_dev *hdev) { struct hci_conn *conn; struct sk_buff *skb; int quote; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, ESCO_LINK)) return; while (hdev->sco_cnt && (conn = hci_low_sent(hdev, ESCO_LINK, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_frame(hdev, skb); conn->sent++; if (conn->sent == ~0) conn->sent = 0; } } } static void hci_sched_acl_pkt(struct hci_dev *hdev) { unsigned int cnt = hdev->acl_cnt; struct hci_chan *chan; struct sk_buff *skb; int quote; __check_timeout(hdev, cnt, ACL_LINK); while (hdev->acl_cnt && (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) break; skb = skb_dequeue(&chan->data_q); hci_conn_enter_active_mode(chan->conn, bt_cb(skb)->force_active); hci_send_frame(hdev, skb); hdev->acl_last_tx = jiffies; hdev->acl_cnt--; chan->sent++; chan->conn->sent++; /* Send pending SCO packets right away */ hci_sched_sco(hdev); hci_sched_esco(hdev); } } if (cnt != hdev->acl_cnt) hci_prio_recalculate(hdev, ACL_LINK); } static void hci_sched_acl_blk(struct hci_dev *hdev) { unsigned int cnt = hdev->block_cnt; struct hci_chan *chan; struct sk_buff *skb; int quote; u8 type; BT_DBG("%s", hdev->name); if (hdev->dev_type == HCI_AMP) type = AMP_LINK; else type = ACL_LINK; __check_timeout(hdev, cnt, type); while (hdev->block_cnt > 0 && (chan = hci_chan_sent(hdev, type, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote > 0 && (skb = skb_peek(&chan->data_q))) { int blocks; BT_DBG("chan %p skb %p len %d priority %u", chan, skb, skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) break; skb = skb_dequeue(&chan->data_q); blocks = __get_blocks(hdev, skb); if (blocks > hdev->block_cnt) return; hci_conn_enter_active_mode(chan->conn, bt_cb(skb)->force_active); hci_send_frame(hdev, skb); hdev->acl_last_tx = jiffies; hdev->block_cnt -= blocks; quote -= blocks; chan->sent += blocks; chan->conn->sent += blocks; } } if (cnt != hdev->block_cnt) hci_prio_recalculate(hdev, type); } static void hci_sched_acl(struct hci_dev *hdev) { BT_DBG("%s", hdev->name); /* No ACL link over BR/EDR controller */ if (!hci_conn_num(hdev, ACL_LINK) && hdev->dev_type == HCI_PRIMARY) return; /* No AMP link over AMP controller */ if (!hci_conn_num(hdev, AMP_LINK) && hdev->dev_type == HCI_AMP) return; switch (hdev->flow_ctl_mode) { case HCI_FLOW_CTL_MODE_PACKET_BASED: hci_sched_acl_pkt(hdev); break; case HCI_FLOW_CTL_MODE_BLOCK_BASED: hci_sched_acl_blk(hdev); break; } } static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; int quote, cnt, tmp; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, LE_LINK)) return; cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; __check_timeout(hdev, cnt, LE_LINK); tmp = cnt; while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) break; skb = skb_dequeue(&chan->data_q); hci_send_frame(hdev, skb); hdev->le_last_tx = jiffies; cnt--; chan->sent++; chan->conn->sent++; /* Send pending SCO packets right away */ hci_sched_sco(hdev); hci_sched_esco(hdev); } } if (hdev->le_pkts) hdev->le_cnt = cnt; else hdev->acl_cnt = cnt; if (cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); } /* Schedule CIS */ static void hci_sched_iso(struct hci_dev *hdev) { struct hci_conn *conn; struct sk_buff *skb; int quote, *cnt; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, ISO_LINK)) return; cnt = hdev->iso_pkts ? &hdev->iso_cnt : hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; while (*cnt && (conn = hci_low_sent(hdev, ISO_LINK, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_frame(hdev, skb); conn->sent++; if (conn->sent == ~0) conn->sent = 0; (*cnt)--; } } } static void hci_tx_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, tx_work); struct sk_buff *skb; BT_DBG("%s acl %d sco %d le %d iso %d", hdev->name, hdev->acl_cnt, hdev->sco_cnt, hdev->le_cnt, hdev->iso_cnt); if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { /* Schedule queues and send stuff to HCI driver */ hci_sched_sco(hdev); hci_sched_esco(hdev); hci_sched_iso(hdev); hci_sched_acl(hdev); hci_sched_le(hdev); } /* Send next queued raw (unknown type) packet */ while ((skb = skb_dequeue(&hdev->raw_q))) hci_send_frame(hdev, skb); } /* ----- HCI RX task (incoming data processing) ----- */ /* ACL data packet */ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_acl_hdr *hdr = (void *) skb->data; struct hci_conn *conn; __u16 handle, flags; skb_pull(skb, HCI_ACL_HDR_SIZE); handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); BT_DBG("%s len %d handle 0x%4.4x flags 0x%4.4x", hdev->name, skb->len, handle, flags); hdev->stat.acl_rx++; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); hci_dev_unlock(hdev); if (conn) { hci_conn_enter_active_mode(conn, BT_POWER_FORCE_ACTIVE_OFF); /* Send to upper protocol */ l2cap_recv_acldata(conn, skb, flags); return; } else { bt_dev_err(hdev, "ACL packet for unknown connection handle %d", handle); } kfree_skb(skb); } /* SCO data packet */ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_sco_hdr *hdr = (void *) skb->data; struct hci_conn *conn; __u16 handle, flags; skb_pull(skb, HCI_SCO_HDR_SIZE); handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); BT_DBG("%s len %d handle 0x%4.4x flags 0x%4.4x", hdev->name, skb->len, handle, flags); hdev->stat.sco_rx++; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); hci_dev_unlock(hdev); if (conn) { /* Send to upper protocol */ hci_skb_pkt_status(skb) = flags & 0x03; sco_recv_scodata(conn, skb); return; } else { bt_dev_err_ratelimited(hdev, "SCO packet for unknown connection handle %d", handle); } kfree_skb(skb); } static void hci_isodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_iso_hdr *hdr; struct hci_conn *conn; __u16 handle, flags; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "ISO packet too small"); goto drop; } handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); bt_dev_dbg(hdev, "len %d handle 0x%4.4x flags 0x%4.4x", skb->len, handle, flags); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); hci_dev_unlock(hdev); if (!conn) { bt_dev_err(hdev, "ISO packet for unknown connection handle %d", handle); goto drop; } /* Send to upper protocol */ iso_recv(conn, skb, flags); return; drop: kfree_skb(skb); } static bool hci_req_is_complete(struct hci_dev *hdev) { struct sk_buff *skb; skb = skb_peek(&hdev->cmd_q); if (!skb) return true; return (bt_cb(skb)->hci.req_flags & HCI_REQ_START); } static void hci_resend_last(struct hci_dev *hdev) { struct hci_command_hdr *sent; struct sk_buff *skb; u16 opcode; if (!hdev->sent_cmd) return; sent = (void *) hdev->sent_cmd->data; opcode = __le16_to_cpu(sent->opcode); if (opcode == HCI_OP_RESET) return; skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); if (!skb) return; skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); } void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb) { struct sk_buff *skb; unsigned long flags; BT_DBG("opcode 0x%04x status 0x%02x", opcode, status); /* If the completed command doesn't match the last one that was * sent we need to do special handling of it. */ if (!hci_sent_cmd_data(hdev, opcode)) { /* Some CSR based controllers generate a spontaneous * reset complete event during init and any pending * command will never be completed. In such a case we * need to resend whatever was the last sent * command. */ if (test_bit(HCI_INIT, &hdev->flags) && opcode == HCI_OP_RESET) hci_resend_last(hdev); return; } /* If we reach this point this event matches the last command sent */ hci_dev_clear_flag(hdev, HCI_CMD_PENDING); /* If the command succeeded and there's still more commands in * this request the request is not yet complete. */ if (!status && !hci_req_is_complete(hdev)) return; /* If this was the last command in a request the complete * callback would be found in hdev->sent_cmd instead of the * command queue (hdev->cmd_q). */ if (bt_cb(hdev->sent_cmd)->hci.req_flags & HCI_REQ_SKB) { *req_complete_skb = bt_cb(hdev->sent_cmd)->hci.req_complete_skb; return; } if (bt_cb(hdev->sent_cmd)->hci.req_complete) { *req_complete = bt_cb(hdev->sent_cmd)->hci.req_complete; return; } /* Remove all pending commands belonging to this request */ spin_lock_irqsave(&hdev->cmd_q.lock, flags); while ((skb = __skb_dequeue(&hdev->cmd_q))) { if (bt_cb(skb)->hci.req_flags & HCI_REQ_START) { __skb_queue_head(&hdev->cmd_q, skb); break; } if (bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; else *req_complete = bt_cb(skb)->hci.req_complete; dev_kfree_skb_irq(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); } static void hci_rx_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, rx_work); struct sk_buff *skb; BT_DBG("%s", hdev->name); /* The kcov_remote functions used for collecting packet parsing * coverage information from this background thread and associate * the coverage with the syscall's thread which originally injected * the packet. This helps fuzzing the kernel. */ for (; (skb = skb_dequeue(&hdev->rx_q)); kcov_remote_stop()) { kcov_remote_start_common(skb_get_kcov_handle(skb)); /* Send copy to monitor */ hci_send_to_monitor(hdev, skb); if (atomic_read(&hdev->promisc)) { /* Send copy to the sockets */ hci_send_to_sock(hdev, skb); } /* If the device has been opened in HCI_USER_CHANNEL, * the userspace has exclusive access to device. * When device is HCI_INIT, we still need to process * the data packets to the driver in order * to complete its setup(). */ if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && !test_bit(HCI_INIT, &hdev->flags)) { kfree_skb(skb); continue; } if (test_bit(HCI_INIT, &hdev->flags)) { /* Don't process data packets in this states. */ switch (hci_skb_pkt_type(skb)) { case HCI_ACLDATA_PKT: case HCI_SCODATA_PKT: case HCI_ISODATA_PKT: kfree_skb(skb); continue; } } /* Process frame */ switch (hci_skb_pkt_type(skb)) { case HCI_EVENT_PKT: BT_DBG("%s Event packet", hdev->name); hci_event_packet(hdev, skb); break; case HCI_ACLDATA_PKT: BT_DBG("%s ACL data packet", hdev->name); hci_acldata_packet(hdev, skb); break; case HCI_SCODATA_PKT: BT_DBG("%s SCO data packet", hdev->name); hci_scodata_packet(hdev, skb); break; case HCI_ISODATA_PKT: BT_DBG("%s ISO data packet", hdev->name); hci_isodata_packet(hdev, skb); break; default: kfree_skb(skb); break; } } } static void hci_cmd_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); struct sk_buff *skb; BT_DBG("%s cmd_cnt %d cmd queued %d", hdev->name, atomic_read(&hdev->cmd_cnt), skb_queue_len(&hdev->cmd_q)); /* Send queued commands */ if (atomic_read(&hdev->cmd_cnt)) { skb = skb_dequeue(&hdev->cmd_q); if (!skb) return; kfree_skb(hdev->sent_cmd); hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); if (hdev->sent_cmd) { int res; if (hci_req_status_pend(hdev)) hci_dev_set_flag(hdev, HCI_CMD_PENDING); atomic_dec(&hdev->cmd_cnt); res = hci_send_frame(hdev, skb); if (res < 0) __hci_cmd_sync_cancel(hdev, -res); rcu_read_lock(); if (test_bit(HCI_RESET, &hdev->flags) || hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) cancel_delayed_work(&hdev->cmd_timer); else queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, HCI_CMD_TIMEOUT); rcu_read_unlock(); } else { skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); } } } |
| 3313 3307 3307 1152 1152 1152 1152 1151 3307 3306 3307 3306 46 3306 3306 3305 3307 3306 3171 1152 1152 3170 3170 3171 1152 1152 3171 3171 3171 3171 3170 3059 2379 2315 412 364 2228 35 3170 1152 1152 1152 1152 1152 3170 3170 35 35 1152 1152 2297 7876 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(struct folio *folio) { return !folio_test_swapbacked(folio); } static inline int page_is_file_lru(struct page *page) { return folio_is_file_lru(page_folio(page)); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment in folio_lru_refs() */ return order_base_2(refs + 1); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); bool workingset = flags & BIT(PG_workingset); /* * Return the number of accesses beyond PG_referenced, i.e., N-1 if the * total number of accesses is N>1, since N=0,1 both map to the first * tier. lru_tier_from_refs() will account for this off-by-one. Also see * the comment on MAX_NR_TIERS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; } static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* * There are four common cases for this page: * 1. If it's hot, i.e., freshly faulted in, add it to the youngest * generation, and it's protected over the rest below. * 2. If it can't be evicted immediately, i.e., a dirty page pending * writeback, add it to the second youngest generation. * 3. If it should be evicted first, e.g., cold and clean from * folio_rotate_reclaimable(), add it to the oldest generation. * 4. Everything else falls between 2 & 3 above and is added to the * second oldest generation if it's considered inactive, or the * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) seq = lrugen->max_seq - 1; else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; else seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( swp_entry_t entry, struct vm_area_struct *dst_vma) { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ pte_marker dstm = srcm & PTE_MARKER_POISONED; /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } #endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. */ static inline void pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { #ifdef CONFIG_PTE_MARKER_UFFD_WP bool arm_uffd_pte = false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); #endif } static inline bool vma_has_recency(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif |
| 206 206 206 206 16 206 206 206 206 206 16 206 16 206 206 1255 45 1255 1255 1255 1255 1255 1255 1255 1255 1255 85 85 85 85 85 85 2 85 85 85 85 85 85 85 45 45 45 45 45 46 46 46 46 45 45 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/migrate.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/memory-tiers.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <linux/pagewalk.h> #include <linux/shmem_fs.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/khugepaged.h> #include <linux/rculist_nulls.h> #include <linux/random.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include <linux/sched/sysctl.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; /* Can active folios be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped folios be reclaimed? */ unsigned int may_unmap:1; /* Can folios be swapped as part of reclaim? */ unsigned int may_swap:1; /* Proactive reclaim invoked by userspace through memory.reclaim */ unsigned int proactive:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file folios on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Always discard instead of demoting to lower tier memory */ unsigned int no_demotion:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate folios for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_folio(_folio, _base, _field) \ do { \ if ((_folio)->lru.prev != _base) { \ struct folio *prev; \ \ prev = lru_to_folio(&(_folio->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_folio(_folio, _base, _field) do { } while (0) #endif /* * From 0 .. 200. Higher means more swappy. */ int vm_swappiness = 60; #ifdef CONFIG_MEMCG /* Returns true for reclaim through cgroup limits or cgroup interfaces. */ static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /* * Returns true for reclaim on the root cgroup. This is true for direct * allocator reclaim and reclaim through cgroup interfaces on the root cgroup. */ static bool root_reclaim(struct scan_control *sc) { return !sc->target_mem_cgroup || mem_cgroup_is_root(sc->target_mem_cgroup); } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_folio_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } #else static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool root_reclaim(struct scan_control *sc) { return true; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } #endif static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } /* * flush_reclaim_state(): add pages reclaimed outside of LRU-based reclaim to * scan_control->nr_reclaimed. */ static void flush_reclaim_state(struct scan_control *sc) { /* * Currently, reclaim_state->reclaimed includes three types of pages * freed outside of vmscan: * (1) Slab pages. * (2) Clean file pages from pruned inodes (on highmem systems). * (3) XFS freed buffer pages. * * For all of these cases, we cannot universally link the pages to a * single memcg. For example, a memcg-aware shrinker can free one object * charged to the target memcg, causing an entire page to be freed. * If we count the entire page as reclaimed from the memcg, we end up * overestimating the reclaimed amount (potentially under-reclaiming). * * Only count such pages for global reclaim to prevent under-reclaiming * from the target memcg; preventing unnecessary retries during memcg * charging and false positives from proactive reclaim. * * For uncommon cases where the freed pages were actually mostly * charged to the target memcg, we end up underestimating the reclaimed * amount. This should be fine. The freed pages will be uncharged * anyway, even if they are not counted here properly, and we will be * able to make forward progress in charging (which is usually in a * retry loop). * * We can go one step further, and report the uncharged objcg pages in * memcg reclaim, to make reporting more accurate and reduce * underestimation, but it's probably not worth the complexity for now. */ if (current->reclaim_state && root_reclaim(sc)) { sc->nr_reclaimed += current->reclaim_state->reclaimed; current->reclaim_state->reclaimed = 0; } } static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) return false; if (sc && sc->no_demotion) return false; if (next_demotion_node(nid) == NUMA_NO_NODE) return false; return true; } static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, int nid, struct scan_control *sc) { if (memcg == NULL) { /* * For non-memcg reclaim, is there * space in any swap device? */ if (get_nr_swap_pages() > 0) return true; } else { /* Is the memcg below its swap limit? */ if (mem_cgroup_get_nr_swap_pages(memcg) > 0) return true; } /* * The page can not be swapped. * * Can it be reclaimed from this node via demotion? */ return can_demote(nid, sc); } /* * This misses isolated folios which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated folios will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES - 1 for the whole LRU list) */ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; for (zid = 0; zid <= zone_idx; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) continue; if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } static unsigned long drop_slab_node(int nid) { unsigned long freed = 0; struct mem_cgroup *memcg = NULL; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); return freed; } void drop_slab(void) { int nid; int shift = 0; unsigned long freed; do { freed = 0; for_each_online_node(nid) { if (fatal_signal_pending(current)) return; freed += drop_slab_node(nid); } } while ((freed >> shift++) > 1); } static int reclaimer_offset(void) { BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != PGDEMOTE_DIRECT - PGDEMOTE_KSWAPD); BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != PGDEMOTE_KHUGEPAGED - PGDEMOTE_KSWAPD); BUILD_BUG_ON(PGSTEAL_DIRECT - PGSTEAL_KSWAPD != PGSCAN_DIRECT - PGSCAN_KSWAPD); BUILD_BUG_ON(PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD != PGSCAN_KHUGEPAGED - PGSCAN_KSWAPD); if (current_is_kswapd()) return 0; if (current_is_khugepaged()) return PGSTEAL_KHUGEPAGED - PGSTEAL_KSWAPD; return PGSTEAL_DIRECT - PGSTEAL_KSWAPD; } static inline int is_page_cache_freeable(struct folio *folio) { /* * A freeable page cache folio is referenced only by the caller * that isolated the folio, the page cache and optional filesystem * private data at folio->private. */ return folio_ref_count(folio) - folio_test_private(folio) == 1 + folio_nr_pages(folio); } /* * We detected a synchronous write error writing a folio out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the folio and once * that folio is locked, the mapping is pinned. * * We're allowed to run sleeping folio_lock() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct folio *folio, int error) { folio_lock(folio); if (folio_mapping(folio) == mapping) mapping_set_error(mapping, error); folio_unlock(folio); } static bool skip_throttle_noprogress(pg_data_t *pgdat) { int reclaimable = 0, write_pending = 0; int i; /* * If kswapd is disabled, reschedule if necessary but do not * throttle as the system is likely near OOM. */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; /* * If there are a lot of dirty/writeback folios then do not * throttle as throttling will occur when the folios cycle * towards the end of the LRU if still under writeback. */ for (i = 0; i < MAX_NR_ZONES; i++) { struct zone *zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; reclaimable += zone_reclaimable_pages(zone); write_pending += zone_page_state_snapshot(zone, NR_ZONE_WRITE_PENDING); } if (2 * write_pending <= reclaimable) return true; return false; } void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long timeout, ret; DEFINE_WAIT(wait); /* * Do not throttle user workers, kthreads other than kswapd or * workqueues. They may be required for reclaim to make * forward progress (e.g. journalling workqueues or kthreads). */ if (!current_is_kswapd() && current->flags & (PF_USER_WORKER|PF_KTHREAD)) { cond_resched(); return; } /* * These figures are pulled out of thin air. * VMSCAN_THROTTLE_ISOLATED is a transient condition based on too many * parallel reclaimers which is a short-lived event so the timeout is * short. Failing to make progress or waiting on writeback are * potentially long-lived events so use a longer timeout. This is shaky * logic as a failure to make progress could be due to anything from * writeback to a slow device to excessive referenced folios at the tail * of the inactive LRU. */ switch(reason) { case VMSCAN_THROTTLE_WRITEBACK: timeout = HZ/10; if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } break; case VMSCAN_THROTTLE_CONGESTED: fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: if (skip_throttle_noprogress(pgdat)) { cond_resched(); return; } timeout = 1; break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; break; default: WARN_ON_ONCE(1); timeout = HZ; break; } prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); if (reason == VMSCAN_THROTTLE_WRITEBACK) atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), reason); } /* * Account for folios written if tasks are throttled waiting on dirty * folios to clean. If enough folios have been cleaned since throttling * started then wakeup the throttled tasks. */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled) { unsigned long nr_written; node_stat_add_folio(folio, NR_THROTTLED_WRITTEN); /* * This is an inaccurate read as the per-cpu deltas may not * be synchronised. However, given that the system is * writeback throttled, it is not worth taking the penalty * of getting an accurate count. At worst, the throttle * timeout guarantees forward progress. */ nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - READ_ONCE(pgdat->nr_reclaim_start); if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); } /* possible outcome of pageout() */ typedef enum { /* failed to write folio out, folio is locked */ PAGE_KEEP, /* move folio to the active list, folio is locked */ PAGE_ACTIVATE, /* folio has been sent to the disk successfully, folio is unlocked */ PAGE_SUCCESS, /* folio is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_folio_list() for each dirty folio. * Calls ->writepage(). */ static pageout_t pageout(struct folio *folio, struct address_space *mapping, struct swap_iocb **plug) { /* * If the folio is dirty, only perform writeback if that write * will be non-blocking. To prevent this allocation from being * stalled by pagecache activity. But note that there may be * stalls if we need to run get_block(). We could test * PagePrivate for that. * * If this process is currently in __generic_file_write_iter() against * this folio's queue, we can perform writeback even if that * will block. * * If the folio is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(folio)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned folios can have * folio->mapping == NULL while being dirty with clean buffers. */ if (folio_test_private(folio)) { if (try_to_free_buffers(folio)) { folio_clear_dirty(folio); pr_info("%s: orphaned folio\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; if (folio_clear_dirty_for_io(folio)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, .swap_plug = plug, }; folio_set_reclaim(folio); res = mapping->a_ops->writepage(&folio->page, &wbc); if (res < 0) handle_write_error(mapping, folio, res); if (res == AOP_WRITEPAGE_ACTIVATE) { folio_clear_reclaim(folio); return PAGE_ACTIVATE; } if (!folio_test_writeback(folio)) { /* synchronous write or broken a_ops? */ folio_clear_reclaim(folio); } trace_mm_vmscan_write_folio(folio); node_stat_add_folio(folio, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the folio is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct folio *folio, bool reclaimed, struct mem_cgroup *target_memcg) { int refcount; void *shadow = NULL; BUG_ON(!folio_test_locked(folio)); BUG_ON(mapping != folio_mapping(folio)); if (!folio_test_swapcache(folio)) spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); /* * The non racy check for a busy folio. * * Must be careful with the order of the tests. When someone has * a ref to the folio, it may be possible that they dirty it then * drop the reference. So if the dirty flag is tested before the * refcount here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !folio_test_dirty(folio) [good] * folio_set_dirty(folio); * folio_put(folio); * !refcount(folio) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the folio->flags * load is not satisfied before that of folio->_refcount. * * Note that if the dirty flag is always set via folio_mark_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + folio_nr_pages(folio); if (!folio_ref_freeze(folio, refcount)) goto cannot_free; /* note: atomic_cmpxchg in folio_ref_freeze provides the smp_rmb */ if (unlikely(folio_test_dirty(folio))) { folio_ref_unfreeze(folio, refcount); goto cannot_free; } if (folio_test_swapcache(folio)) { swp_entry_t swap = folio->swap; if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(folio, target_memcg); __delete_from_swap_cache(folio, swap, shadow); mem_cgroup_swapout(folio, swap); xa_unlock_irq(&mapping->i_pages); put_swap_folio(folio, swap); } else { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache folios found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && folio_is_file_lru(folio) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(folio, target_memcg); __filemap_remove_folio(folio, shadow); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); if (free_folio) free_folio(folio); } return 1; cannot_free: xa_unlock_irq(&mapping->i_pages); if (!folio_test_swapcache(folio)) spin_unlock(&mapping->host->i_lock); return 0; } /** * remove_mapping() - Attempt to remove a folio from its mapping. * @mapping: The address space. * @folio: The folio to remove. * * If the folio is dirty, under writeback or if someone else has a ref * on it, removal will fail. * Return: The number of pages removed from the mapping. 0 if the folio * could not be removed. * Context: The caller should have a single refcount on the folio and * hold its lock. */ long remove_mapping(struct address_space *mapping, struct folio *folio) { if (__remove_mapping(mapping, folio, false, NULL)) { /* * Unfreezing the refcount with 1 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ folio_ref_unfreeze(folio, 1); return folio_nr_pages(folio); } return 0; } /** * folio_putback_lru - Put previously isolated folio onto appropriate LRU list. * @folio: Folio to be returned to an LRU list. * * Add previously isolated @folio to appropriate LRU list. * The folio may still be unevictable for other reasons. * * Context: lru_lock must not be held, interrupts must be enabled. */ void folio_putback_lru(struct folio *folio) { folio_add_lru(folio); folio_put(folio); /* drop ref from isolate */ } enum folio_references { FOLIOREF_RECLAIM, FOLIOREF_RECLAIM_CLEAN, FOLIOREF_KEEP, FOLIOREF_ACTIVATE, }; static enum folio_references folio_check_references(struct folio *folio, struct scan_control *sc) { int referenced_ptes, referenced_folio; unsigned long vm_flags; referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup, &vm_flags); referenced_folio = folio_test_clear_referenced(folio); /* * The supposedly reclaimable folio was found to be in a VM_LOCKED vma. * Let the folio, now marked Mlocked, be moved to the unevictable list. */ if (vm_flags & VM_LOCKED) return FOLIOREF_ACTIVATE; /* rmap lock contention: rotate */ if (referenced_ptes == -1) return FOLIOREF_KEEP; if (referenced_ptes) { /* * All mapped folios start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file/anon folio is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated folios as well * so that recently deactivated but used folios are * quickly recovered. */ folio_set_referenced(folio); if (referenced_folio || referenced_ptes > 1) return FOLIOREF_ACTIVATE; /* * Activate file-backed executable folios after first usage. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) return FOLIOREF_ACTIVATE; return FOLIOREF_KEEP; } /* Reclaim if clean, defer dirty folios to writeback */ if (referenced_folio && folio_is_file_lru(folio)) return FOLIOREF_RECLAIM_CLEAN; return FOLIOREF_RECLAIM; } /* Check if a folio is dirty or under writeback */ static void folio_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous folios are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them. * MADV_FREE anonymous folios are put into inactive file list too. * They could be mistakenly treated as file lru. So further anon * test is needed. */ if (!folio_is_file_lru(folio) || (folio_test_anon(folio) && !folio_test_swapbacked(folio))) { *dirty = false; *writeback = false; return; } /* By default assume that the folio flags are accurate */ *dirty = folio_test_dirty(folio); *writeback = folio_test_writeback(folio); /* Verify dirty/writeback state if the filesystem supports it */ if (!folio_test_private(folio)) return; mapping = folio_mapping(folio); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(folio, dirty, writeback); } static struct folio *alloc_demote_folio(struct folio *src, unsigned long private) { struct folio *dst; nodemask_t *allowed_mask; struct migration_target_control *mtc; mtc = (struct migration_target_control *)private; allowed_mask = mtc->nmask; /* * make sure we allocate from the target node first also trying to * demote or reclaim pages from the target node via kswapd if we are * low on free memory on target node. If we don't do this and if * we have free memory on the slower(lower) memtier, we would start * allocating pages from slower(lower) memory tiers without even forcing * a demotion of cold pages from the target memtier. This can result * in the kernel placing hot pages in slower(lower) memory tiers. */ mtc->nmask = NULL; mtc->gfp_mask |= __GFP_THISNODE; dst = alloc_migration_target(src, (unsigned long)mtc); if (dst) return dst; mtc->gfp_mask &= ~__GFP_THISNODE; mtc->nmask = allowed_mask; return alloc_migration_target(src, (unsigned long)mtc); } /* * Take folios on @demote_folios and attempt to demote them to another node. * Folios which are not demoted are left on @demote_folios. */ static unsigned int demote_folio_list(struct list_head *demote_folios, struct pglist_data *pgdat) { int target_nid = next_demotion_node(pgdat->node_id); unsigned int nr_succeeded; nodemask_t allowed_mask; struct migration_target_control mtc = { /* * Allocate from 'node', or fail quickly and quietly. * When this happens, 'page' will likely just be discarded * instead of migrated. */ .gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) | __GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT, .nid = target_nid, .nmask = &allowed_mask }; if (list_empty(demote_folios)) return 0; if (target_nid == NUMA_NO_NODE) return 0; node_get_allowed_targets(pgdat, &allowed_mask); /* Demotion ignores all cpuset and mempolicy settings */ migrate_pages(demote_folios, alloc_demote_folio, NULL, (unsigned long)&mtc, MIGRATE_ASYNC, MR_DEMOTION, &nr_succeeded); mod_node_page_state(pgdat, PGDEMOTE_KSWAPD + reclaimer_offset(), nr_succeeded); return nr_succeeded; } static bool may_enter_fs(struct folio *folio, gfp_t gfp_mask) { if (gfp_mask & __GFP_FS) return true; if (!folio_test_swapcache(folio) || !(gfp_mask & __GFP_IO)) return false; /* * We can "enter_fs" for swap-cache with only __GFP_IO * providing this isn't SWP_FS_OPS. * ->flags can be updated non-atomicially (scan_swap_map_slots), * but that will never affect SWP_FS_OPS, so the data_race * is safe. */ return !data_race(folio_swap_flags(folio) & SWP_FS_OPS); } /* * shrink_folio_list() returns the number of reclaimed pages */ static unsigned int shrink_folio_list(struct list_head *folio_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { LIST_HEAD(ret_folios); LIST_HEAD(free_folios); LIST_HEAD(demote_folios); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; memset(stat, 0, sizeof(*stat)); cond_resched(); do_demote_pass = can_demote(pgdat->node_id, sc); retry: while (!list_empty(folio_list)) { struct address_space *mapping; struct folio *folio; enum folio_references references = FOLIOREF_RECLAIM; bool dirty, writeback; unsigned int nr_pages; cond_resched(); folio = lru_to_folio(folio_list); list_del(&folio->lru); if (!folio_trylock(folio)) goto keep; VM_BUG_ON_FOLIO(folio_test_active(folio), folio); nr_pages = folio_nr_pages(folio); /* Account the number of base pages */ sc->nr_scanned += nr_pages; if (unlikely(!folio_evictable(folio))) goto activate_locked; if (!sc->may_unmap && folio_mapped(folio)) goto keep_locked; /* folio_update_gen() tried to promote this page? */ if (lru_gen_enabled() && !ignore_references && folio_mapped(folio) && folio_test_referenced(folio)) goto keep_locked; /* * The number of dirty pages determines if a node is marked * reclaim_congested. kswapd will stall and start writing * folios if the tail of the LRU is all dirty unqueued folios. */ folio_check_dirty_writeback(folio, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty += nr_pages; if (dirty && !writeback) stat->nr_unqueued_dirty += nr_pages; /* * Treat this folio as congested if folios are cycling * through the LRU so quickly that the folios marked * for immediate reclaim are making it to the end of * the LRU a second time. */ if (writeback && folio_test_reclaim(folio)) stat->nr_congested += nr_pages; /* * If a folio at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number * of folios under writeback and this folio has both * the writeback and reclaim flags set, then it * indicates that folios are being queued for I/O but * are being recycled through the LRU before the I/O * can complete. Waiting on the folio itself risks an * indefinite stall if it is impossible to writeback * the folio due to I/O error or disconnected storage * so instead note that the LRU is being scanned too * quickly and the caller can stall after the folio * list has been processed. * * 2) Global or new memcg reclaim encounters a folio that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs). In this case mark the folio for immediate * reclaim and continue scanning. * * Require may_enter_fs() because we would wait on fs, which * may not have submitted I/O yet. And the loop driver might * enter reclaim, and deadlock if it waits on a folio for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a folio that already has the * reclaim flag set. memcg does not have any dirty folio * throttling so we could easily OOM just because too many * folios are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the folios to get them out of * the way while we continue scanning for clean folios on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (folio_test_writeback(folio)) { /* Case 1 above */ if (current_is_kswapd() && folio_test_reclaim(folio) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate += nr_pages; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !folio_test_reclaim(folio) || !may_enter_fs(folio, sc->gfp_mask)) { /* * This is slightly racy - * folio_end_writeback() might have * just cleared the reclaim flag, then * setting the reclaim flag here ends up * interpreted as the readahead flag - but * that does not matter enough to care. * What we do want is for this folio to * have the reclaim flag set next time * memcg reclaim reaches the tests above, * so it will then wait for writeback to * avoid OOM; and it's also appropriate * in global reclaim. */ folio_set_reclaim(folio); stat->nr_writeback += nr_pages; goto activate_locked; /* Case 3 above */ } else { folio_unlock(folio); folio_wait_writeback(folio); /* then go back and try same folio again */ list_add_tail(&folio->lru, folio_list); continue; } } if (!ignore_references) references = folio_check_references(folio, sc); switch (references) { case FOLIOREF_ACTIVATE: goto activate_locked; case FOLIOREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case FOLIOREF_RECLAIM: case FOLIOREF_RECLAIM_CLEAN: ; /* try to reclaim the folio below */ } /* * Before reclaiming the folio, try to relocate * its contents to another node. */ if (do_demote_pass && (thp_migration_supported() || !folio_test_large(folio))) { list_add(&folio->lru, &demote_folios); folio_unlock(folio); continue; } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree folio could be freed directly */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) { if (!folio_test_swapcache(folio)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (folio_maybe_dma_pinned(folio)) goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ if (!can_split_folio(folio, NULL)) goto activate_locked; /* * Split folios without a PMD map right * away. Chances are some or all of the * tail pages can be freed without IO. */ if (!folio_entire_mapcount(folio) && split_folio_to_list(folio, folio_list)) goto activate_locked; } if (!add_to_swap(folio)) { if (!folio_test_large(folio)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_folio_to_list(folio, folio_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE count_memcg_folio_events(folio, THP_SWPOUT_FALLBACK, 1); count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(folio)) goto activate_locked_split; } } } else if (folio_test_swapbacked(folio) && folio_test_large(folio)) { /* Split shmem folio */ if (split_folio_to_list(folio, folio_list)) goto keep_locked; } /* * If the folio was split above, the tail pages will make * their own pass through this function and be accounted * then. */ if ((nr_pages > 1) && !folio_test_large(folio)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The folio is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (folio_mapped(folio)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = folio_test_swapbacked(folio); if (folio_test_pmd_mappable(folio)) flags |= TTU_SPLIT_HUGE_PMD; try_to_unmap(folio, flags); if (folio_mapped(folio)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && folio_test_swapbacked(folio)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } /* * Folio is unmapped now so it cannot be newly pinned anymore. * No point in trying to reclaim folio if it is pinned. * Furthermore we don't want to reclaim underlying fs metadata * if the folio is pinned and thus potentially modified by the * pinning process as that may upset the filesystem. */ if (folio_maybe_dma_pinned(folio)) goto activate_locked; mapping = folio_mapping(folio); if (folio_test_dirty(folio)) { /* * Only kswapd can writeback filesystem folios * to avoid risk of stack overflow. But avoid * injecting inefficient single-folio I/O into * flusher writeback as much as possible: only * write folios when we've encountered many * dirty folios, and when we've already scanned * the rest of the LRU for clean folios and see * the same dirty folios again (with the reclaim * flag set). */ if (folio_is_file_lru(folio) && (!current_is_kswapd() || !folio_test_reclaim(folio) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principle to folio_deactivate() * except we already have the folio isolated * and know it's dirty */ node_stat_mod_folio(folio, NR_VMSCAN_IMMEDIATE, nr_pages); folio_set_reclaim(folio); goto activate_locked; } if (references == FOLIOREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs(folio, sc->gfp_mask)) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Folio is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after I/O * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(folio, mapping, &plug)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: stat->nr_pageout += nr_pages; if (folio_test_writeback(folio)) goto keep; if (folio_test_dirty(folio)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the folio. */ if (!folio_trylock(folio)) goto keep; if (folio_test_dirty(folio) || folio_test_writeback(folio)) goto keep_locked; mapping = folio_mapping(folio); fallthrough; case PAGE_CLEAN: ; /* try to free the folio below */ } } /* * If the folio has buffers, try to free the buffer * mappings associated with this folio. If we succeed * we try to free the folio as well. * * We do this even if the folio is dirty. * filemap_release_folio() does not perform I/O, but it * is possible for a folio to have the dirty flag set, * but it is actually clean (all its buffers are clean). * This happens if the buffers were written out directly, * with submit_bh(). ext3 will do this, as well as * the blockdev mapping. filemap_release_folio() will * discover that cleanness and will drop the buffers * and mark the folio clean - it can be freed. * * Rarely, folios can have buffers and no ->mapping. * These are the folios which were not successfully * invalidated in truncate_cleanup_folio(). We try to * drop those buffers here and if that worked, and the * folio is no longer mapped into process address space * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ if (folio_needs_release(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { folio_unlock(folio); if (folio_put_testzero(folio)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this folio shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed += nr_pages; continue; } } } if (folio_test_anon(folio) && !folio_test_swapbacked(folio)) { /* follow __remove_mapping for reference */ if (!folio_ref_freeze(folio, 1)) goto keep_locked; /* * The folio has only one reference left, which is * from the isolation. After the caller puts the * folio back on the lru and drops the reference, the * folio will be freed anyway. It doesn't matter * which lru it goes on. So we don't bother checking * the dirty flag here. */ count_vm_events(PGLAZYFREED, nr_pages); count_memcg_folio_events(folio, PGLAZYFREED, nr_pages); } else if (!mapping || !__remove_mapping(mapping, folio, true, sc->target_mem_cgroup)) goto keep_locked; folio_unlock(folio); free_it: /* * Folio may get swapped out as a whole, need to account * all pages in it. */ nr_reclaimed += nr_pages; /* * Is there need to periodically free_folio_list? It would * appear not as the counts should be low */ if (unlikely(folio_test_large(folio))) destroy_large_folio(folio); else list_add(&folio->lru, &free_folios); continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (folio_test_swapcache(folio) && (mem_cgroup_swap_full(folio) || folio_test_mlocked(folio))) folio_free_swap(folio); VM_BUG_ON_FOLIO(folio_test_active(folio), folio); if (!folio_test_mlocked(folio)) { int type = folio_is_file_lru(folio); folio_set_active(folio); stat->nr_activate[type] += nr_pages; count_memcg_folio_events(folio, PGACTIVATE, nr_pages); } keep_locked: folio_unlock(folio); keep: list_add(&folio->lru, &ret_folios); VM_BUG_ON_FOLIO(folio_test_lru(folio) || folio_test_unevictable(folio), folio); } /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ nr_reclaimed += demote_folio_list(&demote_folios, pgdat); /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ list_splice_init(&demote_folios, folio_list); /* * goto retry to reclaim the undemoted folios in folio_list if * desired. * * Reclaiming directly from top tier nodes is not often desired * due to it breaking the LRU ordering: in general memory * should be reclaimed from lower tier nodes and demoted from * top tier nodes. * * However, disabling reclaim from top tier nodes entirely * would cause ooms in edge scenarios where lower tier memory * is unreclaimable for whatever reason, eg memory being * mlocked or too hot to reclaim. We can disable reclaim * from top tier nodes in proactive reclaim though as that is * not real memory pressure. */ if (!sc->proactive) { do_demote_pass = false; goto retry; } } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_list(&free_folios); try_to_unmap_flush(); free_unref_page_list(&free_folios); list_splice(&ret_folios, folio_list); count_vm_events(PGACTIVATE, pgactivate); if (plug) swap_write_unplug(plug); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct folio *folio, *next; LIST_HEAD(clean_folios); unsigned int noreclaim_flag; list_for_each_entry_safe(folio, next, folio_list, lru) { if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) && !folio_test_dirty(folio) && !__folio_test_movable(folio) && !folio_test_unevictable(folio)) { folio_clear_active(folio); list_move(&folio->lru, &clean_folios); } } /* * We should be safe here since we are only dealing with file pages and * we are not kswapd and therefore cannot write dirty file pages. But * call memalloc_noreclaim_save() anyway, just in case these conditions * change in the future. */ noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_folio_list(&clean_folios, zone->zone_pgdat, &sc, &stat, true); memalloc_noreclaim_restore(noreclaim_flag); list_splice(&clean_folios, folio_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } #ifdef CONFIG_CMA /* * It is waste of effort to scan and reclaim CMA pages if it is not available * for current allocation context. Kswapd can not be enrolled as it can not * distinguish this scenario by using sc->gfp_mask = GFP_KERNEL */ static bool skip_cma(struct folio *folio, struct scan_control *sc) { return !current_is_kswapd() && gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE && folio_migratetype(folio) == MIGRATE_CMA; } #else static bool skip_cma(struct folio *folio, struct scan_control *sc) { return false; } #endif /* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Lru_lock must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; LIST_HEAD(folios_skipped); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct list_head *move_to = src; struct folio *folio; folio = lru_to_folio(src); prefetchw_prev_lru_folio(folio, src, flags); nr_pages = folio_nr_pages(folio); total_scan += nr_pages; if (folio_zonenum(folio) > sc->reclaim_idx || skip_cma(folio, sc)) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; goto move; } /* * Do not count skipped folios because that makes the function * return with no isolated folios if the LRU mostly contains * ineligible folios. This causes the VM to not reclaim any * folios, triggering a premature OOM. * Account all pages in a folio. */ scan += nr_pages; if (!folio_test_lru(folio)) goto move; if (!sc->may_unmap && folio_mapped(folio)) goto move; /* * Be careful not to clear the lru flag until after we're * sure the folio is not being freed elsewhere -- the * folio release code relies on it. */ if (unlikely(!folio_try_get(folio))) goto move; if (!folio_test_clear_lru(folio)) { /* Another thread is already isolating this folio */ folio_put(folio); goto move; } nr_taken += nr_pages; nr_zone_taken[folio_zonenum(folio)] += nr_pages; move_to = dst; move: list_move(&folio->lru, move_to); } /* * Splice any skipped folios to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same folios to skip and waste lots * of cpu cycles. */ if (!list_empty(&folios_skipped)) { int zid; list_splice(&folios_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * folio_isolate_lru() - Try to isolate a folio from its LRU list. * @folio: Folio to isolate from its LRU list. * * Isolate a @folio from an LRU list and adjust the vmstat statistic * corresponding to whatever LRU list the folio was on. * * The folio will have its LRU flag cleared. If it was found on the * active list, it will have the Active flag set. If it was found on the * unevictable list, it will have the Unevictable flag set. These flags * may need to be cleared by the caller before letting the page go. * * Context: * * (1) Must be called with an elevated refcount on the folio. This is a * fundamental difference from isolate_lru_folios() (which is called * without a stable reference). * (2) The lru_lock must not be held. * (3) Interrupts must be enabled. * * Return: true if the folio was removed from an LRU list. * false if the folio was not on an LRU list. */ bool folio_isolate_lru(struct folio *folio) { bool ret = false; VM_BUG_ON_FOLIO(!folio_ref_count(folio), folio); if (folio_test_clear_lru(folio)) { struct lruvec *lruvec; folio_get(folio); lruvec = folio_lruvec_lock_irq(folio); lruvec_del_folio(lruvec, folio); unlock_page_lruvec_irq(lruvec); ret = true; } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; bool too_many; if (current_is_kswapd()) return 0; if (!writeback_throttling_sane(sc)) return 0; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if (gfp_has_io_fs(sc->gfp_mask)) inactive >>= 3; too_many = isolated > inactive; /* Wake up tasks throttled due to too_many_isolated. */ if (!too_many) wake_throttle_isolated(pgdat); return too_many; } /* * move_folios_to_lru() moves folios from private @list to appropriate LRU list. * On return, @list is reused as a list of folios to be freed by the caller. * * Returns the number of pages moved to the given lruvec. */ static unsigned int move_folios_to_lru(struct lruvec *lruvec, struct list_head *list) { int nr_pages, nr_moved = 0; LIST_HEAD(folios_to_free); while (!list_empty(list)) { struct folio *folio = lru_to_folio(list); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { spin_unlock_irq(&lruvec->lru_lock); folio_putback_lru(folio); spin_lock_irq(&lruvec->lru_lock); continue; } /* * The folio_set_lru needs to be kept here for list integrity. * Otherwise: * #0 move_folios_to_lru #1 release_pages * if (!folio_put_testzero()) * if (folio_put_testzero()) * !lru //skip lru_lock * folio_set_lru() * list_add(&folio->lru,) * list_add(&folio->lru,) */ folio_set_lru(folio); if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); if (unlikely(folio_test_large(folio))) { spin_unlock_irq(&lruvec->lru_lock); destroy_large_folio(folio); spin_lock_irq(&lruvec->lru_lock); } else list_add(&folio->lru, &folios_to_free); continue; } /* * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ VM_BUG_ON_FOLIO(!folio_matches_lruvec(folio, lruvec), folio); lruvec_add_folio(lruvec, folio); nr_pages = folio_nr_pages(folio); nr_moved += nr_pages; if (folio_test_active(folio)) workingset_age_nonresident(lruvec, nr_pages); } /* * To save our caller's stack, now use input list for pages to free. */ list_splice(&folios_to_free, list); return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services a backing * device by writing to the page cache it sets PF_LOCAL_THROTTLE. In this case * we should not throttle. Otherwise it is safe to do so. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(folio_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ stalled = true; reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &folio_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = PGSCAN_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_folio_list(&folio_list, pgdat, sc, &stat, false); spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &folio_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&lruvec->lru_lock); lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed); mem_cgroup_uncharge_list(&folio_list); free_unref_page_list(&folio_list); /* * If dirty folios are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty folios to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty folios grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) { wakeup_flusher_threads(WB_REASON_VMSCAN); /* * For cgroupv1 dirty throttling is achieved by waking up * the kernel flusher here and later waiting on folios * which are in writeback to finish (see shrink_folio_list()). * * Flusher may not be able to issue writeback quickly * enough for cgroupv1 writeback throttling to work * on a large system. */ if (!writeback_throttling_sane(sc)) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } /* * shrink_active_list() moves folios from the active LRU to the inactive LRU. * * We move them the other way if the folio is referenced by one or more * processes. * * If the folios are mostly unmapped, the processing is fast and it is * appropriate to hold lru_lock across the whole operation. But if * the folios are mapped, the processing is slow (folio_referenced()), so * we should drop lru_lock around each folio. It's impossible to balance * this, so instead we remove the folios from the LRU while processing them. * It is safe to rely on the active flag against the non-LRU folios in here * because nobody will play with that bit on a non-LRU folio. * * The downside is that we have to touch folio->_refcount against each folio. * But we had to alter folio->flags anyway. */ static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The folios which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; int file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&lruvec->lru_lock); nr_taken = isolate_lru_folios(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&lruvec->lru_lock); while (!list_empty(&l_hold)) { struct folio *folio; cond_resched(); folio = lru_to_folio(&l_hold); list_del(&folio->lru); if (unlikely(!folio_evictable(folio))) { folio_putback_lru(folio); continue; } if (unlikely(buffer_heads_over_limit)) { if (folio_needs_release(folio) && folio_trylock(folio)) { filemap_release_folio(folio, 0); folio_unlock(folio); } } /* Referenced or rmap lock contention: rotate */ if (folio_referenced(folio, 0, sc->target_mem_cgroup, &vm_flags) != 0) { /* * Identify referenced, file-backed active folios and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon folios * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC folios, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && folio_is_file_lru(folio)) { nr_rotated += folio_nr_pages(folio); list_add(&folio->lru, &l_active); continue; } } folio_clear_active(folio); /* we are de-activating */ folio_set_workingset(folio); list_add(&folio->lru, &l_inactive); } /* * Move folios back to the lru list. */ spin_lock_irq(&lruvec->lru_lock); nr_activate = move_folios_to_lru(lruvec, &l_active); nr_deactivate = move_folios_to_lru(lruvec, &l_inactive); /* Keep all free folios in l_active list */ list_splice(&l_inactive, &l_active); __count_vm_events(PGDEACTIVATE, nr_deactivate); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&lruvec->lru_lock); if (nr_rotated) lru_note_cost(lruvec, file, 0, nr_rotated); mem_cgroup_uncharge_list(&l_active); free_unref_page_list(&l_active); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } static unsigned int reclaim_folio_list(struct list_head *folio_list, struct pglist_data *pgdat) { struct reclaim_stat dummy_stat; unsigned int nr_reclaimed; struct folio *folio; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .no_demotion = 1, }; nr_reclaimed = shrink_folio_list(folio_list, pgdat, &sc, &dummy_stat, false); while (!list_empty(folio_list)) { folio = lru_to_folio(folio_list); list_del(&folio->lru); folio_putback_lru(folio); } return nr_reclaimed; } unsigned long reclaim_pages(struct list_head *folio_list) { int nid; unsigned int nr_reclaimed = 0; LIST_HEAD(node_folio_list); unsigned int noreclaim_flag; if (list_empty(folio_list)) return nr_reclaimed; noreclaim_flag = memalloc_noreclaim_save(); nid = folio_nid(lru_to_folio(folio_list)); do { struct folio *folio = lru_to_folio(folio_list); if (nid == folio_nid(folio)) { folio_clear_active(folio); list_move(&folio->lru, &node_folio_list); continue; } nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); nid = folio_nid(lru_to_folio(folio_list)); } while (!list_empty(folio_list)); nr_reclaimed += reclaim_folio_list(&node_folio_list, NODE_DATA(nid)); memalloc_noreclaim_restore(noreclaim_flag); return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * folio has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE folios * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the folios are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; static void prepare_scan_control(pg_data_t *pgdat, struct scan_control *sc) { unsigned long file; struct lruvec *target_lruvec; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); /* * Flush the memory cgroup stats, so that we read accurate per-memcg * lruvec stats for heuristics. */ mem_cgroup_flush_stats(sc->target_mem_cgroup); /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&target_lruvec->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&target_lruvec->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[WORKINGSET_ANON] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[WORKINGSET_FILE] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } } /* * Determine how aggressively the anon and file LRU lists should be * scanned. * * nr[0] = anon inactive folios to scan; nr[1] = anon active folios to scan * nr[2] = file inactive folios to scan; nr[3] = file active folios to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; int swappiness = mem_cgroup_swappiness(memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; unsigned long ap, fp; enum lru_list lru; /* If we have no swap space, do not bother scanning anon folios. */ if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (200 - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[0] = ap; fraction[1] = fp; denominator = ap + fp; out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } /* * Anonymous LRU management is a waste if there is * ultimately no way to reclaim the memory. */ static bool can_age_anon_pages(struct pglist_data *pgdat, struct scan_control *sc) { /* Aging the anon LRU is valuable if swap is present: */ if (total_swap_pages > 0) return true; /* Also valuable if anon pages can be demoted: */ return can_demote(pgdat->node_id, sc); } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_likely(&lru_gen_caps[cap]) #else DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS); #define get_cap(cap) static_branch_unlikely(&lru_gen_caps[cap]) #endif static bool should_walk_mmu(void) { return arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK); } static bool should_clear_pmd_young(void) { return arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG); } /****************************************************************************** * shorthand helpers ******************************************************************************/ #define LRU_REFS_FLAGS (BIT(PG_referenced) | BIT(PG_workingset)) #define DEFINE_MAX_SEQ(lruvec) \ unsigned long max_seq = READ_ONCE((lruvec)->lrugen.max_seq) #define DEFINE_MIN_SEQ(lruvec) \ unsigned long min_seq[ANON_AND_FILE] = { \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_ANON]), \ READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]), \ } #define for_each_gen_type_zone(gen, type, zone) \ for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++) \ for ((type) = 0; (type) < ANON_AND_FILE; (type)++) \ for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++) #define get_memcg_gen(seq) ((seq) % MEMCG_NR_GENS) #define get_memcg_bin(bin) ((bin) % MEMCG_NR_BINS) static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid) { struct pglist_data *pgdat = NODE_DATA(nid); #ifdef CONFIG_MEMCG if (memcg) { struct lruvec *lruvec = &memcg->nodeinfo[nid]->lruvec; /* see the comment in mem_cgroup_lruvec() */ if (!lruvec->pgdat) lruvec->pgdat = pgdat; return lruvec; } #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &pgdat->__lruvec; } static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); if (!sc->may_swap) return 0; if (!can_demote(pgdat->node_id, sc) && mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) return 0; return mem_cgroup_swappiness(memcg); } static int get_nr_gens(struct lruvec *lruvec, int type) { return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1; } static bool __maybe_unused seq_is_valid(struct lruvec *lruvec) { /* see the comment on lru_gen_folio */ return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS && get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) && get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS; } /****************************************************************************** * Bloom filters ******************************************************************************/ /* * Bloom filters with m=1<<15, k=2 and the false positive rates of ~1/5 when * n=10,000 and ~1/2 when n=20,000, where, conventionally, m is the number of * bits in a bitmap, k is the number of hash functions and n is the number of * inserted items. * * Page table walkers use one of the two filters to reduce their search space. * To get rid of non-leaf entries that no longer have enough leaf entries, the * aging uses the double-buffering technique to flip to the other filter each * time it produces a new generation. For non-leaf entries that have enough * leaf entries, the aging carries them over to the next generation in * walk_pmd_range(); the eviction also report them when walking the rmap * in lru_gen_look_around(). * * For future optimizations: * 1. It's not necessary to keep both filters all the time. The spare one can be * freed after the RCU grace period and reallocated if needed again. * 2. And when reallocating, it's worth scaling its size according to the number * of inserted entries in the other filter, to reduce the memory overhead on * small systems and false positives on large systems. * 3. Jenkins' hash function is an alternative to Knuth's. */ #define BLOOM_FILTER_SHIFT 15 static inline int filter_gen_from_seq(unsigned long seq) { return seq % NR_BLOOM_FILTERS; } static void get_item_key(void *item, int *key) { u32 hash = hash_ptr(item, BLOOM_FILTER_SHIFT * 2); BUILD_BUG_ON(BLOOM_FILTER_SHIFT * 2 > BITS_PER_TYPE(u32)); key[0] = hash & (BIT(BLOOM_FILTER_SHIFT) - 1); key[1] = hash >> BLOOM_FILTER_SHIFT; } static bool test_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return true; get_item_key(item, key); return test_bit(key[0], filter) && test_bit(key[1], filter); } static void update_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq, void *item) { int key[2]; unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = READ_ONCE(mm_state->filters[gen]); if (!filter) return; get_item_key(item, key); if (!test_bit(key[0], filter)) set_bit(key[0], filter); if (!test_bit(key[1], filter)) set_bit(key[1], filter); } static void reset_bloom_filter(struct lru_gen_mm_state *mm_state, unsigned long seq) { unsigned long *filter; int gen = filter_gen_from_seq(seq); filter = mm_state->filters[gen]; if (filter) { bitmap_clear(filter, 0, BIT(BLOOM_FILTER_SHIFT)); return; } filter = bitmap_zalloc(BIT(BLOOM_FILTER_SHIFT), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); WRITE_ONCE(mm_state->filters[gen], filter); } /****************************************************************************** * mm_struct list ******************************************************************************/ #ifdef CONFIG_LRU_GEN_WALKS_MMU static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { static struct lru_gen_mm_list mm_list = { .fifo = LIST_HEAD_INIT(mm_list.fifo), .lock = __SPIN_LOCK_UNLOCKED(mm_list.lock), }; #ifdef CONFIG_MEMCG if (memcg) return &memcg->mm_list; #endif VM_WARN_ON_ONCE(!mem_cgroup_disabled()); return &mm_list; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return &lruvec->mm_state; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { int key; struct mm_struct *mm; struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); mm = list_entry(mm_state->head, struct mm_struct, lru_gen.list); key = pgdat->node_id % BITS_PER_TYPE(mm->lru_gen.bitmap); if (!walk->force_scan && !test_bit(key, &mm->lru_gen.bitmap)) return NULL; clear_bit(key, &mm->lru_gen.bitmap); return mmget_not_zero(mm) ? mm : NULL; } void lru_gen_add_mm(struct mm_struct *mm) { int nid; struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(!list_empty(&mm->lru_gen.list)); #ifdef CONFIG_MEMCG VM_WARN_ON_ONCE(mm->lru_gen.memcg); mm->lru_gen.memcg = memcg; #endif spin_lock(&mm_list->lock); for_each_node_state(nid, N_MEMORY) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* the first addition since the last iteration */ if (mm_state->tail == &mm_list->fifo) mm_state->tail = &mm->lru_gen.list; } list_add_tail(&mm->lru_gen.list, &mm_list->fifo); spin_unlock(&mm_list->lock); } void lru_gen_del_mm(struct mm_struct *mm) { int nid; struct lru_gen_mm_list *mm_list; struct mem_cgroup *memcg = NULL; if (list_empty(&mm->lru_gen.list)) return; #ifdef CONFIG_MEMCG memcg = mm->lru_gen.memcg; #endif mm_list = get_mm_list(memcg); spin_lock(&mm_list->lock); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* where the current iteration continues after */ if (mm_state->head == &mm->lru_gen.list) mm_state->head = mm_state->head->prev; /* where the last iteration ended before */ if (mm_state->tail == &mm->lru_gen.list) mm_state->tail = mm_state->tail->next; } list_del_init(&mm->lru_gen.list); spin_unlock(&mm_list->lock); #ifdef CONFIG_MEMCG mem_cgroup_put(mm->lru_gen.memcg); mm->lru_gen.memcg = NULL; #endif } #ifdef CONFIG_MEMCG void lru_gen_migrate_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; struct task_struct *task = rcu_dereference_protected(mm->owner, true); VM_WARN_ON_ONCE(task->mm != mm); lockdep_assert_held(&task->alloc_lock); /* for mm_update_next_owner() */ if (mem_cgroup_disabled()) return; /* migration can happen before addition */ if (!mm->lru_gen.memcg) return; rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); lru_gen_add_mm(mm); } #endif #else /* !CONFIG_LRU_GEN_WALKS_MMU */ static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg) { return NULL; } static struct lru_gen_mm_state *get_mm_state(struct lruvec *lruvec) { return NULL; } static struct mm_struct *get_next_mm(struct lru_gen_mm_walk *walk) { return NULL; } #endif static void reset_mm_stats(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, bool last) { int i; int hist; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lockdep_assert_held(&get_mm_list(lruvec_memcg(lruvec))->lock); if (walk) { hist = lru_hist_from_seq(walk->max_seq); for (i = 0; i < NR_MM_STATS; i++) { WRITE_ONCE(mm_state->stats[hist][i], mm_state->stats[hist][i] + walk->mm_stats[i]); walk->mm_stats[i] = 0; } } if (NR_HIST_GENS > 1 && last) { hist = lru_hist_from_seq(mm_state->seq + 1); for (i = 0; i < NR_MM_STATS; i++) WRITE_ONCE(mm_state->stats[hist][i], 0); } } static bool iterate_mm_list(struct lruvec *lruvec, struct lru_gen_mm_walk *walk, struct mm_struct **iter) { bool first = false; bool last = false; struct mm_struct *mm = NULL; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); /* * mm_state->seq is incremented after each iteration of mm_list. There * are three interesting cases for this page table walker: * 1. It tries to start a new iteration with a stale max_seq: there is * nothing left to do. * 2. It started the next iteration: it needs to reset the Bloom filter * so that a fresh set of PTE tables can be recorded. * 3. It ended the current iteration: it needs to reset the mm stats * counters and tell its caller to increment max_seq. */ spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < walk->max_seq); if (walk->max_seq <= mm_state->seq) goto done; if (!mm_state->head) mm_state->head = &mm_list->fifo; if (mm_state->head == &mm_list->fifo) first = true; do { mm_state->head = mm_state->head->next; if (mm_state->head == &mm_list->fifo) { WRITE_ONCE(mm_state->seq, mm_state->seq + 1); last = true; break; } /* force scan for those added after the last iteration */ if (!mm_state->tail || mm_state->tail == mm_state->head) { mm_state->tail = mm_state->head->next; walk->force_scan = true; } } while (!(mm = get_next_mm(walk))); done: if (*iter || last) reset_mm_stats(lruvec, walk, last); spin_unlock(&mm_list->lock); if (mm && first) reset_bloom_filter(mm_state, walk->max_seq + 1); if (*iter) mmput_async(*iter); *iter = mm; return last; } static bool iterate_mm_list_nowalk(struct lruvec *lruvec, unsigned long max_seq) { bool success = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct lru_gen_mm_list *mm_list = get_mm_list(memcg); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); spin_lock(&mm_list->lock); VM_WARN_ON_ONCE(mm_state->seq + 1 < max_seq); if (max_seq > mm_state->seq) { mm_state->head = NULL; mm_state->tail = NULL; WRITE_ONCE(mm_state->seq, mm_state->seq + 1); reset_mm_stats(lruvec, NULL, true); success = true; } spin_unlock(&mm_list->lock); return success; } /****************************************************************************** * PID controller ******************************************************************************/ /* * A feedback loop based on Proportional-Integral-Derivative (PID) controller. * * The P term is refaulted/(evicted+protected) from a tier in the generation * currently being evicted; the I term is the exponential moving average of the * P term over the generations previously evicted, using the smoothing factor * 1/2; the D term isn't supported. * * The setpoint (SP) is always the first tier of one type; the process variable * (PV) is either any tier of the other type or any other tier of the same * type. * * The error is the difference between the SP and the PV; the correction is to * turn off protection when SP>PV or turn on protection when SP<PV. * * For future optimizations: * 1. The D term may discount the other two terms over time so that long-lived * generations can resist stale information. */ struct ctrl_pos { unsigned long refaulted; unsigned long total; int gain; }; static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain, struct ctrl_pos *pos) { struct lru_gen_folio *lrugen = &lruvec->lrugen; int hist = lru_hist_from_seq(lrugen->min_seq[type]); pos->refaulted = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); pos->total = lrugen->avg_total[type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) pos->total += lrugen->protected[hist][type][tier - 1]; pos->gain = gain; } static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover) { int hist, tier; struct lru_gen_folio *lrugen = &lruvec->lrugen; bool clear = carryover ? NR_HIST_GENS == 1 : NR_HIST_GENS > 1; unsigned long seq = carryover ? lrugen->min_seq[type] : lrugen->max_seq + 1; lockdep_assert_held(&lruvec->lru_lock); if (!carryover && !clear) return; hist = lru_hist_from_seq(seq); for (tier = 0; tier < MAX_NR_TIERS; tier++) { if (carryover) { unsigned long sum; sum = lrugen->avg_refaulted[type][tier] + atomic_long_read(&lrugen->refaulted[hist][type][tier]); WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2); sum = lrugen->avg_total[type][tier] + atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) sum += lrugen->protected[hist][type][tier - 1]; WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2); } if (clear) { atomic_long_set(&lrugen->refaulted[hist][type][tier], 0); atomic_long_set(&lrugen->evicted[hist][type][tier], 0); if (tier) WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0); } } } static bool positive_ctrl_err(struct ctrl_pos *sp, struct ctrl_pos *pv) { /* * Return true if the PV has a limited number of refaults or a lower * refaulted/total than the SP. */ return pv->refaulted < MIN_LRU_BATCH || pv->refaulted * (sp->total + MIN_LRU_BATCH) * sp->gain <= (sp->refaulted + 1) * pv->total * pv->gain; } /****************************************************************************** * the aging ******************************************************************************/ /* promote pages accessed through page tables */ static int folio_update_gen(struct folio *folio, int gen) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(!rcu_read_lock_held()); do { /* lru_gen_del_folio() has isolated this page? */ if (!(old_flags & LRU_GEN_MASK)) { /* for shrink_folio_list() */ new_flags = old_flags | BIT(PG_referenced); continue; } new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); new_flags |= (gen + 1UL) << LRU_GEN_PGOFF; } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } /* protect pages accessed multiple times through file descriptors */ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { int type = folio_is_file_lru(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); unsigned long new_flags, old_flags = READ_ONCE(folio->flags); VM_WARN_ON_ONCE_FOLIO(!(old_flags & LRU_GEN_MASK), folio); do { new_gen = ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; /* folio_update_gen() has promoted this page? */ if (new_gen >= 0 && new_gen != old_gen) return new_gen; new_gen = (old_gen + 1) % MAX_NR_GENS; new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS); new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF; /* for folio_end_writeback() */ if (reclaiming) new_flags |= BIT(PG_reclaim); } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); lru_gen_update_size(lruvec, folio, old_gen, new_gen); return new_gen; } static void update_batch_size(struct lru_gen_mm_walk *walk, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE(old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen >= MAX_NR_GENS); walk->batched++; walk->nr_pages[old_gen][type][zone] -= delta; walk->nr_pages[new_gen][type][zone] += delta; } static void reset_batch_size(struct lruvec *lruvec, struct lru_gen_mm_walk *walk) { int gen, type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; walk->batched = 0; for_each_gen_type_zone(gen, type, zone) { enum lru_list lru = type * LRU_INACTIVE_FILE; int delta = walk->nr_pages[gen][type][zone]; if (!delta) continue; walk->nr_pages[gen][type][zone] = 0; WRITE_ONCE(lrugen->nr_pages[gen][type][zone], lrugen->nr_pages[gen][type][zone] + delta); if (lru_gen_is_active(lruvec, gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); } } static int should_skip_vma(unsigned long start, unsigned long end, struct mm_walk *args) { struct address_space *mapping; struct vm_area_struct *vma = args->vma; struct lru_gen_mm_walk *walk = args->private; if (!vma_is_accessible(vma)) return true; if (is_vm_hugetlb_page(vma)) return true; if (!vma_has_recency(vma)) return true; if (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) return true; if (vma == get_gate_vma(vma->vm_mm)) return true; if (vma_is_anonymous(vma)) return !walk->can_swap; if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping)) return true; mapping = vma->vm_file->f_mapping; if (mapping_unevictable(mapping)) return true; if (shmem_mapping(mapping)) return !walk->can_swap; /* to exclude special mappings like dax, etc. */ return !mapping->a_ops->read_folio; } /* * Some userspace memory allocators map many single-page VMAs. Instead of * returning back to the PGD table for each of such VMAs, finish an entire PMD * table to reduce zigzags and improve cache performance. */ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk *args, unsigned long *vm_start, unsigned long *vm_end) { unsigned long start = round_up(*vm_end, size); unsigned long end = (start | ~mask) + 1; VMA_ITERATOR(vmi, args->mm, start); VM_WARN_ON_ONCE(mask & size); VM_WARN_ON_ONCE((start & mask) != (*vm_start & mask)); for_each_vma(vmi, args->vma) { if (end && end <= args->vma->vm_start) return false; if (should_skip_vma(args->vma->vm_start, args->vma->vm_end, args)) continue; *vm_start = max(start, args->vma->vm_start); *vm_end = min(end - 1, args->vma->vm_end - 1) + 1; return true; } return false; } static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr) { unsigned long pfn = pte_pfn(pte); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pte_present(pte) || is_zero_pfn(pfn)) return -1; if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte))) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; return pfn; } static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr) { unsigned long pfn = pmd_pfn(pmd); VM_WARN_ON_ONCE(addr < vma->vm_start || addr >= vma->vm_end); if (!pmd_present(pmd) || is_huge_zero_pmd(pmd)) return -1; if (WARN_ON_ONCE(pmd_devmap(pmd))) return -1; if (WARN_ON_ONCE(!pfn_valid(pfn))) return -1; return pfn; } static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg, struct pglist_data *pgdat, bool can_swap) { struct folio *folio; /* try to avoid unnecessary memory loads */ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) return NULL; folio = pfn_folio(pfn); if (folio_nid(folio) != pgdat->node_id) return NULL; if (folio_memcg_rcu(folio) != memcg) return NULL; /* file VMAs can contain anon pages from COW */ if (!folio_is_file_lru(folio) && !can_swap) return NULL; return folio; } static bool suitable_to_scan(int total, int young) { int n = clamp_t(int, cache_line_size() / sizeof(pte_t), 2, 8); /* suitable if the average number of young PTEs per cacheline is >=1 */ return young * n >= total; } static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pte_t *pte; spinlock_t *ptl; unsigned long addr; int total = 0; int young = 0; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(walk->max_seq); pte = pte_offset_map_nolock(args->mm, pmd, start & PMD_MASK, &ptl); if (!pte) return false; if (!spin_trylock(ptl)) { pte_unmap(pte); return false; } arch_enter_lazy_mmu_mode(); restart: for (i = pte_index(start), addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; struct folio *folio; pte_t ptent = ptep_get(pte + i); total++; walk->mm_stats[MM_LEAF_TOTAL]++; pfn = get_pte_pfn(ptent, args->vma, addr); if (pfn == -1) continue; if (!pte_young(ptent)) { walk->mm_stats[MM_LEAF_OLD]++; continue; } folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) continue; if (!ptep_test_and_clear_young(args->vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; walk->mm_stats[MM_LEAF_YOUNG]++; if (pte_dirty(ptent) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); } if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end)) goto restart; arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte, ptl); return suitable_to_scan(total, young); } static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area_struct *vma, struct mm_walk *args, unsigned long *bitmap, unsigned long *first) { int i; pmd_t *pmd; spinlock_t *ptl; struct lru_gen_mm_walk *walk = args->private; struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); int old_gen, new_gen = lru_gen_from_seq(walk->max_seq); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* try to batch at most 1+MIN_LRU_BATCH+1 entries */ if (*first == -1) { *first = addr; bitmap_zero(bitmap, MIN_LRU_BATCH); return; } i = addr == -1 ? 0 : pmd_index(addr) - pmd_index(*first); if (i && i <= MIN_LRU_BATCH) { __set_bit(i - 1, bitmap); return; } pmd = pmd_offset(pud, *first); ptl = pmd_lockptr(args->mm, pmd); if (!spin_trylock(ptl)) goto done; arch_enter_lazy_mmu_mode(); do { unsigned long pfn; struct folio *folio; /* don't round down the first address */ addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first; pfn = get_pmd_pfn(pmd[i], vma, addr); if (pfn == -1) goto next; if (!pmd_trans_huge(pmd[i])) { if (should_clear_pmd_young()) pmdp_test_and_clear_young(vma, addr, pmd + i); goto next; } folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap); if (!folio) goto next; if (!pmdp_test_and_clear_young(vma, addr, pmd + i)) goto next; walk->mm_stats[MM_LEAF_YOUNG]++; if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); next: i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1; } while (i <= MIN_LRU_BATCH); arch_leave_lazy_mmu_mode(); spin_unlock(ptl); done: *first = -1; } static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pmd_t *pmd; unsigned long next; unsigned long addr; struct vm_area_struct *vma; DECLARE_BITMAP(bitmap, MIN_LRU_BATCH); unsigned long first = -1; struct lru_gen_mm_walk *walk = args->private; struct lru_gen_mm_state *mm_state = get_mm_state(walk->lruvec); VM_WARN_ON_ONCE(pud_leaf(*pud)); /* * Finish an entire PMD in two passes: the first only reaches to PTE * tables to avoid taking the PMD lock; the second, if necessary, takes * the PMD lock to clear the accessed bit in PMD entries. */ pmd = pmd_offset(pud, start & PUD_MASK); restart: /* walk_pte_range() may call get_next_vma() */ vma = args->vma; for (i = pmd_index(start), addr = start; addr != end; i++, addr = next) { pmd_t val = pmdp_get_lockless(pmd + i); next = pmd_addr_end(addr, end); if (!pmd_present(val) || is_huge_zero_pmd(val)) { walk->mm_stats[MM_LEAF_TOTAL]++; continue; } if (pmd_trans_huge(val)) { unsigned long pfn = pmd_pfn(val); struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec); walk->mm_stats[MM_LEAF_TOTAL]++; if (!pmd_young(val)) { walk->mm_stats[MM_LEAF_OLD]++; continue; } /* try to avoid unnecessary memory loads */ if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); continue; } walk->mm_stats[MM_NONLEAF_TOTAL]++; if (should_clear_pmd_young()) { if (!pmd_young(val)) continue; walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first); } if (!walk->force_scan && !test_bloom_filter(mm_state, walk->max_seq, pmd + i)) continue; walk->mm_stats[MM_NONLEAF_FOUND]++; if (!walk_pte_range(&val, addr, next, args)) continue; walk->mm_stats[MM_NONLEAF_ADDED]++; /* carry over to the next generation */ update_bloom_filter(mm_state, walk->max_seq + 1, pmd + i); } walk_pmd_range_locked(pud, -1, vma, args, bitmap, &first); if (i < PTRS_PER_PMD && get_next_vma(PUD_MASK, PMD_SIZE, args, &start, &end)) goto restart; } static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end, struct mm_walk *args) { int i; pud_t *pud; unsigned long addr; unsigned long next; struct lru_gen_mm_walk *walk = args->private; VM_WARN_ON_ONCE(p4d_leaf(*p4d)); pud = pud_offset(p4d, start & P4D_MASK); restart: for (i = pud_index(start), addr = start; addr != end; i++, addr = next) { pud_t val = READ_ONCE(pud[i]); next = pud_addr_end(addr, end); if (!pud_present(val) || WARN_ON_ONCE(pud_leaf(val))) continue; walk_pmd_range(&val, addr, next, args); if (need_resched() || walk->batched >= MAX_LRU_BATCH) { end = (addr | ~PUD_MASK) + 1; goto done; } } if (i < PTRS_PER_PUD && get_next_vma(P4D_MASK, PUD_SIZE, args, &start, &end)) goto restart; end = round_up(end, P4D_SIZE); done: if (!end || !args->vma) return 1; walk->next_addr = max(end, args->vma->vm_start); return -EAGAIN; } static void walk_mm(struct lruvec *lruvec, struct mm_struct *mm, struct lru_gen_mm_walk *walk) { static const struct mm_walk_ops mm_walk_ops = { .test_walk = should_skip_vma, .p4d_entry = walk_pud_range, .walk_lock = PGWALK_RDLOCK, }; int err; struct mem_cgroup *memcg = lruvec_memcg(lruvec); walk->next_addr = FIRST_USER_ADDRESS; do { DEFINE_MAX_SEQ(lruvec); err = -EBUSY; /* another thread might have called inc_max_seq() */ if (walk->max_seq != max_seq) break; /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) break; /* the caller might be holding the lock for write */ if (mmap_read_trylock(mm)) { err = walk_page_range(mm, walk->next_addr, ULONG_MAX, &mm_walk_ops, walk); mmap_read_unlock(mm); } mem_cgroup_unlock_pages(); if (walk->batched) { spin_lock_irq(&lruvec->lru_lock); reset_batch_size(lruvec, walk); spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while (err == -EAGAIN); } static struct lru_gen_mm_walk *set_mm_walk(struct pglist_data *pgdat, bool force_alloc) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; if (pgdat && current_is_kswapd()) { VM_WARN_ON_ONCE(walk); walk = &pgdat->mm_walk; } else if (!walk && force_alloc) { VM_WARN_ON_ONCE(current_is_kswapd()); walk = kzalloc(sizeof(*walk), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); } current->reclaim_state->mm_walk = walk; return walk; } static void clear_mm_walk(void) { struct lru_gen_mm_walk *walk = current->reclaim_state->mm_walk; VM_WARN_ON_ONCE(walk && memchr_inv(walk->nr_pages, 0, sizeof(walk->nr_pages))); VM_WARN_ON_ONCE(walk && memchr_inv(walk->mm_stats, 0, sizeof(walk->mm_stats))); current->reclaim_state->mm_walk = NULL; if (!current_is_kswapd()) kfree(walk); } static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap) { int zone; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]); if (type == LRU_GEN_ANON && !can_swap) goto done; /* prevent cold/hot inversion if force_scan is true */ for (zone = 0; zone < MAX_NR_ZONES; zone++) { struct list_head *head = &lrugen->folios[old_gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); new_gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]); if (!--remaining) return false; } } done: reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], lrugen->min_seq[type] + 1); return true; } static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap) { int gen, type, zone; bool success = false; struct lru_gen_folio *lrugen = &lruvec->lrugen; DEFINE_MIN_SEQ(lruvec); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); /* find the oldest populated generation */ for (type = !can_swap; type < ANON_AND_FILE; type++) { while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) { gen = lru_gen_from_seq(min_seq[type]); for (zone = 0; zone < MAX_NR_ZONES; zone++) { if (!list_empty(&lrugen->folios[gen][type][zone])) goto next; } min_seq[type]++; } next: ; } /* see the comment on lru_gen_folio */ if (can_swap) { min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]); min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]); } for (type = !can_swap; type < ANON_AND_FILE; type++) { if (min_seq[type] == lrugen->min_seq[type]) continue; reset_ctrl_pos(lruvec, type, true); WRITE_ONCE(lrugen->min_seq[type], min_seq[type]); success = true; } return success; } static bool inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, bool can_swap, bool force_scan) { bool success; int prev, next; int type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; restart: if (max_seq < READ_ONCE(lrugen->max_seq)) return false; spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); success = max_seq == lrugen->max_seq; if (!success) goto unlock; for (type = ANON_AND_FILE - 1; type >= 0; type--) { if (get_nr_gens(lruvec, type) != MAX_NR_GENS) continue; VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap)); if (inc_min_seq(lruvec, type, can_swap)) continue; spin_unlock_irq(&lruvec->lru_lock); cond_resched(); goto restart; } /* * Update the active/inactive LRU sizes for compatibility. Both sides of * the current max_seq need to be covered, since max_seq+1 can overlap * with min_seq[LRU_GEN_ANON] if swapping is constrained. And if they do * overlap, cold/hot inversion happens. */ prev = lru_gen_from_seq(lrugen->max_seq - 1); next = lru_gen_from_seq(lrugen->max_seq + 1); for (type = 0; type < ANON_AND_FILE; type++) { for (zone = 0; zone < MAX_NR_ZONES; zone++) { enum lru_list lru = type * LRU_INACTIVE_FILE; long delta = lrugen->nr_pages[prev][type][zone] - lrugen->nr_pages[next][type][zone]; if (!delta) continue; __update_lru_size(lruvec, lru, zone, delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, -delta); } } for (type = 0; type < ANON_AND_FILE; type++) reset_ctrl_pos(lruvec, type, false); WRITE_ONCE(lrugen->timestamps[next], jiffies); /* make sure preceding modifications appear */ smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1); unlock: spin_unlock_irq(&lruvec->lru_lock); return success; } static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq, struct scan_control *sc, bool can_swap, bool force_scan) { bool success; struct lru_gen_mm_walk *walk; struct mm_struct *mm = NULL; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(max_seq > READ_ONCE(lrugen->max_seq)); if (!mm_state) return inc_max_seq(lruvec, max_seq, can_swap, force_scan); /* see the comment in iterate_mm_list() */ if (max_seq <= READ_ONCE(mm_state->seq)) return false; /* * If the hardware doesn't automatically set the accessed bit, fallback * to lru_gen_look_around(), which only clears the accessed bit in a * handful of PTEs. Spreading the work out over a period of time usually * is less efficient, but it avoids bursty page faults. */ if (!should_walk_mmu()) { success = iterate_mm_list_nowalk(lruvec, max_seq); goto done; } walk = set_mm_walk(NULL, true); if (!walk) { success = iterate_mm_list_nowalk(lruvec, max_seq); goto done; } walk->lruvec = lruvec; walk->max_seq = max_seq; walk->can_swap = can_swap; walk->force_scan = force_scan; do { success = iterate_mm_list(lruvec, walk, &mm); if (mm) walk_mm(lruvec, mm, walk); } while (mm); done: if (success) { success = inc_max_seq(lruvec, max_seq, can_swap, force_scan); WARN_ON_ONCE(!success); } return success; } /****************************************************************************** * working set protection ******************************************************************************/ static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { int gen, type, zone; unsigned long total = 0; bool can_swap = get_swappiness(lruvec, sc); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); for (type = !can_swap; type < ANON_AND_FILE; type++) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); } } /* whether the size is big enough to be helpful */ return mem_cgroup_online(memcg) ? (total >> sc->priority) : total; } static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc, unsigned long min_ttl) { int gen; unsigned long birth; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); /* see the comment on lru_gen_folio */ gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); if (time_is_after_jiffies(birth + min_ttl)) return false; if (!lruvec_is_sizable(lruvec, sc)) return false; mem_cgroup_calculate_protection(NULL, memcg); return !mem_cgroup_below_min(NULL, memcg); } /* to protect the working set of the last N jiffies */ static unsigned long lru_gen_min_ttl __read_mostly; static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); VM_WARN_ON_ONCE(!current_is_kswapd()); /* check the order to exclude compaction-induced reclaim */ if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); if (lruvec_is_reclaimable(lruvec, sc, min_ttl)) { mem_cgroup_iter_break(NULL, memcg); return; } cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); /* * The main goal is to OOM kill if every generation from all memcgs is * younger than min_ttl. However, another possibility is all memcgs are * either too small or below min. */ if (mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; out_of_memory(&oc); mutex_unlock(&oom_lock); } } /****************************************************************************** * rmap/PT walk feedback ******************************************************************************/ /* * This function exploits spatial locality when shrink_folio_list() walks the * rmap. It scans the adjacent PTEs of a young PTE and promotes hot pages. If * the scan was done cacheline efficiently, it adds the PMD entry pointing to * the PTE table to the Bloom filter. This forms a feedback loop between the * eviction and the aging. */ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { int i; unsigned long start; unsigned long end; struct lru_gen_mm_walk *walk; int young = 0; pte_t *pte = pvmw->pte; unsigned long addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; struct folio *folio = pfn_folio(pvmw->pfn); bool can_swap = !folio_is_file_lru(folio); struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = folio_pgdat(folio); struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); DEFINE_MAX_SEQ(lruvec); int old_gen, new_gen = lru_gen_from_seq(max_seq); lockdep_assert_held(pvmw->ptl); VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio); if (spin_is_contended(pvmw->ptl)) return; /* exclude special VMAs containing anon pages from COW */ if (vma->vm_flags & VM_SPECIAL) return; /* avoid taking the LRU lock under the PTL when possible */ walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL; start = max(addr & PMD_MASK, vma->vm_start); end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1; if (end - start > MIN_LRU_BATCH * PAGE_SIZE) { if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2) end = start + MIN_LRU_BATCH * PAGE_SIZE; else if (end - addr < MIN_LRU_BATCH * PAGE_SIZE / 2) start = end - MIN_LRU_BATCH * PAGE_SIZE; else { start = addr - MIN_LRU_BATCH * PAGE_SIZE / 2; end = addr + MIN_LRU_BATCH * PAGE_SIZE / 2; } } /* folio_update_gen() requires stable folio_memcg() */ if (!mem_cgroup_trylock_pages(memcg)) return; arch_enter_lazy_mmu_mode(); pte -= (addr - start) / PAGE_SIZE; for (i = 0, addr = start; addr != end; i++, addr += PAGE_SIZE) { unsigned long pfn; pte_t ptent = ptep_get(pte + i); pfn = get_pte_pfn(ptent, vma, addr); if (pfn == -1) continue; if (!pte_young(ptent)) continue; folio = get_pfn_folio(pfn, memcg, pgdat, can_swap); if (!folio) continue; if (!ptep_test_and_clear_young(vma, addr, pte + i)) VM_WARN_ON_ONCE(true); young++; if (pte_dirty(ptent) && !folio_test_dirty(folio) && !(folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_test_swapcache(folio))) folio_mark_dirty(folio); if (walk) { old_gen = folio_update_gen(folio, new_gen); if (old_gen >= 0 && old_gen != new_gen) update_batch_size(walk, folio, old_gen, new_gen); continue; } old_gen = folio_lru_gen(folio); if (old_gen < 0) folio_set_referenced(folio); else if (old_gen != new_gen) folio_activate(folio); } arch_leave_lazy_mmu_mode(); mem_cgroup_unlock_pages(); /* feedback from rmap walkers to page table walkers */ if (mm_state && suitable_to_scan(i, young)) update_bloom_filter(mm_state, max_seq, pvmw->pmd); } /****************************************************************************** * memcg LRU ******************************************************************************/ /* see the comment on MEMCG_NR_GENS */ enum { MEMCG_LRU_NOP, MEMCG_LRU_HEAD, MEMCG_LRU_TAIL, MEMCG_LRU_OLD, MEMCG_LRU_YOUNG, }; static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) { int seg; int old, new; unsigned long flags; int bin = get_random_u32_below(MEMCG_NR_BINS); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irqsave(&pgdat->memcg_lru.lock, flags); VM_WARN_ON_ONCE(hlist_nulls_unhashed(&lruvec->lrugen.list)); seg = 0; new = old = lruvec->lrugen.gen; /* see the comment on MEMCG_NR_GENS */ if (op == MEMCG_LRU_HEAD) seg = MEMCG_LRU_HEAD; else if (op == MEMCG_LRU_TAIL) seg = MEMCG_LRU_TAIL; else if (op == MEMCG_LRU_OLD) new = get_memcg_gen(pgdat->memcg_lru.seq); else if (op == MEMCG_LRU_YOUNG) new = get_memcg_gen(pgdat->memcg_lru.seq + 1); else VM_WARN_ON_ONCE(true); WRITE_ONCE(lruvec->lrugen.seg, seg); WRITE_ONCE(lruvec->lrugen.gen, new); hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) hlist_nulls_add_head_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); else hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[new][bin]); pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); spin_unlock_irqrestore(&pgdat->memcg_lru.lock, flags); } #ifdef CONFIG_MEMCG void lru_gen_online_memcg(struct mem_cgroup *memcg) { int gen; int nid; int bin = get_random_u32_below(MEMCG_NR_BINS); for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); VM_WARN_ON_ONCE(!hlist_nulls_unhashed(&lruvec->lrugen.list)); gen = get_memcg_gen(pgdat->memcg_lru.seq); lruvec->lrugen.gen = gen; hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_offline_memcg(struct mem_cgroup *memcg) { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); lru_gen_rotate_memcg(lruvec, MEMCG_LRU_OLD); } } void lru_gen_release_memcg(struct mem_cgroup *memcg) { int gen; int nid; for_each_node(nid) { struct pglist_data *pgdat = NODE_DATA(nid); struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&pgdat->memcg_lru.lock); if (hlist_nulls_unhashed(&lruvec->lrugen.list)) goto unlock; gen = lruvec->lrugen.gen; hlist_nulls_del_init_rcu(&lruvec->lrugen.list); pgdat->memcg_lru.nr_memcgs[gen]--; if (!pgdat->memcg_lru.nr_memcgs[gen] && gen == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); unlock: spin_unlock_irq(&pgdat->memcg_lru.lock); } } void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_HEAD) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_HEAD); } #endif /* CONFIG_MEMCG */ /****************************************************************************** * the eviction ******************************************************************************/ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc, int tier_idx) { bool success; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); int refs = folio_lru_refs(folio); int tier = lru_tier_from_refs(refs); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio); /* unevictable */ if (!folio_evictable(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, delta); return true; } /* dirty lazyfree */ if (type == LRU_GEN_FILE && folio_test_anon(folio) && folio_test_dirty(folio)) { success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); folio_set_swapbacked(folio); lruvec_add_folio_tail(lruvec, folio); return true; } /* promoted */ if (gen != lru_gen_from_seq(lrugen->min_seq[type])) { list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* protected */ if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); WRITE_ONCE(lrugen->protected[hist][type][tier - 1], lrugen->protected[hist][type][tier - 1] + delta); return true; } /* ineligible */ if (zone > sc->reclaim_idx || skip_cma(folio, sc)) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } /* waiting for writeback */ if (folio_test_locked(folio) || folio_test_writeback(folio) || (type == LRU_GEN_FILE && folio_test_dirty(folio))) { gen = folio_inc_gen(lruvec, folio, true); list_move(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } return false; } static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct scan_control *sc) { bool success; /* swapping inhibited */ if (!(sc->gfp_mask & __GFP_IO) && (folio_test_dirty(folio) || (folio_test_anon(folio) && !folio_test_swapcache(folio)))) return false; /* raced with release_pages() */ if (!folio_try_get(folio)) return false; /* raced with another isolation */ if (!folio_test_clear_lru(folio)) { folio_put(folio); return false; } /* see the comment on MAX_NR_TIERS */ if (!folio_test_referenced(folio)) set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); /* for shrink_folio_list() */ folio_clear_reclaim(folio); folio_clear_referenced(folio); success = lru_gen_del_folio(lruvec, folio, true); VM_WARN_ON_ONCE_FOLIO(!success, folio); return true; } static int scan_folios(struct lruvec *lruvec, struct scan_control *sc, int type, int tier, struct list_head *list) { int i; int gen; enum vm_event_item item; int sorted = 0; int scanned = 0; int isolated = 0; int skipped = 0; int remaining = MAX_LRU_BATCH; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); VM_WARN_ON_ONCE(!list_empty(list)); if (get_nr_gens(lruvec, type) == MIN_NR_GENS) return 0; gen = lru_gen_from_seq(lrugen->min_seq[type]); for (i = MAX_NR_ZONES; i > 0; i--) { LIST_HEAD(moved); int skipped_zone = 0; int zone = (sc->reclaim_idx + i) % MAX_NR_ZONES; struct list_head *head = &lrugen->folios[gen][type][zone]; while (!list_empty(head)) { struct folio *folio = lru_to_folio(head); int delta = folio_nr_pages(folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); scanned += delta; if (sort_folio(lruvec, folio, sc, tier)) sorted += delta; else if (isolate_folio(lruvec, folio, sc)) { list_add(&folio->lru, list); isolated += delta; } else { list_move(&folio->lru, &moved); skipped_zone += delta; } if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH) break; } if (skipped_zone) { list_splice(&moved, head); __count_zid_vm_events(PGSCAN_SKIP, zone, skipped_zone); skipped += skipped_zone; } if (!remaining || isolated >= MIN_LRU_BATCH) break; } item = PGSCAN_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) { __count_vm_events(item, isolated); __count_vm_events(PGREFILL, sorted); } __count_memcg_events(memcg, item, isolated); __count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); /* * There might not be eligible folios due to reclaim_idx. Check the * remaining to prevent livelock if it's not making progress. */ return isolated || !remaining ? scanned : 0; } static int get_tier_idx(struct lruvec *lruvec, int type) { int tier; struct ctrl_pos sp, pv; /* * To leave a margin for fluctuations, use a larger gain factor (1:2). * This value is chosen because any other tier would have at least twice * as many refaults as the first tier. */ read_ctrl_pos(lruvec, type, 0, 1, &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, 2, &pv); if (!positive_ctrl_err(&sp, &pv)) break; } return tier - 1; } static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx) { int type, tier; struct ctrl_pos sp, pv; int gain[ANON_AND_FILE] = { swappiness, 200 - swappiness }; /* * Compare the first tier of anon with that of file to determine which * type to scan. Also need to compare other tiers of the selected type * with the first tier of the other type to determine the last tier (of * the selected type) to evict. */ read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp); read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv); type = positive_ctrl_err(&sp, &pv); read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp); for (tier = 1; tier < MAX_NR_TIERS; tier++) { read_ctrl_pos(lruvec, type, tier, gain[type], &pv); if (!positive_ctrl_err(&sp, &pv)) break; } *tier_idx = tier - 1; return type; } static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness, int *type_scanned, struct list_head *list) { int i; int type; int scanned; int tier = -1; DEFINE_MIN_SEQ(lruvec); /* * Try to make the obvious choice first. When anon and file are both * available from the same generation, interpret swappiness 1 as file * first and 200 as anon first. */ if (!swappiness) type = LRU_GEN_FILE; else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE]) type = LRU_GEN_ANON; else if (swappiness == 1) type = LRU_GEN_FILE; else if (swappiness == 200) type = LRU_GEN_ANON; else type = get_type_to_scan(lruvec, swappiness, &tier); for (i = !swappiness; i < ANON_AND_FILE; i++) { if (tier < 0) tier = get_tier_idx(lruvec, type); scanned = scan_folios(lruvec, sc, type, tier, list); if (scanned) break; type = !type; tier = -1; } *type_scanned = type; return scanned; } static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness) { int type; int scanned; int reclaimed; LIST_HEAD(list); LIST_HEAD(clean); struct folio *folio; struct folio *next; enum vm_event_item item; struct reclaim_stat stat; struct lru_gen_mm_walk *walk; bool skip_retry = false; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); spin_lock_irq(&lruvec->lru_lock); scanned = isolate_folios(lruvec, sc, swappiness, &type, &list); scanned += try_to_inc_min_seq(lruvec, swappiness); if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS) scanned = 0; spin_unlock_irq(&lruvec->lru_lock); if (list_empty(&list)) return scanned; retry: reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); sc->nr_reclaimed += reclaimed; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, scanned, reclaimed, &stat, sc->priority, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); list_for_each_entry_safe_reverse(folio, next, &list, lru) { if (!folio_evictable(folio)) { list_del(&folio->lru); folio_putback_lru(folio); continue; } if (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* restore LRU_REFS_FLAGS cleared by isolate_folio() */ if (folio_test_workingset(folio)) folio_set_referenced(folio); continue; } if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) || folio_mapped(folio) || folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_writeback(folio)) { /* don't add rejected folios to the oldest generation */ set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, BIT(PG_active)); continue; } /* retry folios that may have missed folio_rotate_reclaimable() */ list_move(&folio->lru, &clean); sc->nr_scanned -= folio_nr_pages(folio); } spin_lock_irq(&lruvec->lru_lock); move_folios_to_lru(lruvec, &list); walk = current->reclaim_state->mm_walk; if (walk && walk->batched) reset_batch_size(lruvec, walk); item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); __count_memcg_events(memcg, item, reclaimed); __count_vm_events(PGSTEAL_ANON + type, reclaimed); spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_list(&list); free_unref_page_list(&list); INIT_LIST_HEAD(&list); list_splice_init(&clean, &list); if (!list_empty(&list)) { skip_retry = true; goto retry; } return scanned; } static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, struct scan_control *sc, bool can_swap, unsigned long *nr_to_scan) { int gen, type, zone; unsigned long old = 0; unsigned long young = 0; unsigned long total = 0; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); /* whether this lruvec is completely out of cold folios */ if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) { *nr_to_scan = 0; return true; } for (type = !can_swap; type < ANON_AND_FILE; type++) { unsigned long seq; for (seq = min_seq[type]; seq <= max_seq; seq++) { unsigned long size = 0; gen = lru_gen_from_seq(seq); for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); total += size; if (seq == max_seq) young += size; else if (seq + MIN_NR_GENS == max_seq) old += size; } } /* try to scrape all its memory if this memcg was deleted */ if (!mem_cgroup_online(memcg)) { *nr_to_scan = total; return false; } *nr_to_scan = total >> sc->priority; /* * The aging tries to be lazy to reduce the overhead, while the eviction * stalls when the number of generations reaches MIN_NR_GENS. Hence, the * ideal number of generations is MIN_NR_GENS+1. */ if (min_seq[!can_swap] + MIN_NR_GENS < max_seq) return false; /* * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1) * of the total number of pages for each generation. A reasonable range * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The * aging cares about the upper bound of hot pages, while the eviction * cares about the lower bound of cold pages. */ if (young * MIN_NR_GENS > total) return true; if (old * (MIN_NR_GENS + 2) < total) return true; return false; } /* * For future optimizations: * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg * reclaim. */ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap) { unsigned long nr_to_scan; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) return -1; if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan)) return nr_to_scan; /* skip the aging path at the default priority */ if (sc->priority == DEF_PRIORITY) return nr_to_scan; /* skip this lruvec as it's low on cold folios */ return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0; } static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { int i; enum zone_watermarks mark; /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) return false; if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) return true; /* check the order to exclude compaction-induced reclaim */ if (!current_is_kswapd() || sc->order) return false; mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? WMARK_PROMO : WMARK_HIGH; for (i = 0; i <= sc->reclaim_idx; i++) { struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) return false; } /* kswapd should abort if all eligible zones are safe */ return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; int swappiness = get_swappiness(lruvec, sc); /* clean file folios are more likely to exist */ if (swappiness && !(sc->gfp_mask & __GFP_IO)) swappiness = 1; while (true) { int delta; nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness); if (nr_to_scan <= 0) break; delta = evict_folios(lruvec, sc, swappiness); if (!delta) break; scanned += delta; if (scanned >= nr_to_scan) break; if (should_abort_scan(lruvec, sc)) break; cond_resched(); } /* whether this lruvec should be rotated */ return nr_to_scan < 0; } static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) { bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(NULL, memcg)) return MEMCG_LRU_YOUNG; if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ if (READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); } success = try_to_shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); flush_reclaim_state(sc); if (success && mem_cgroup_online(memcg)) return MEMCG_LRU_YOUNG; if (!success && lruvec_is_sizable(lruvec, sc)) return 0; /* one retry if offlined or too small */ return READ_ONCE(lruvec->lrugen.seg) != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) { int op; int gen; int bin; int first_bin; struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; struct hlist_nulls_node *pos; gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; rcu_read_lock(); hlist_nulls_for_each_entry_rcu(lrugen, pos, &pgdat->memcg_lru.fifo[gen][bin], list) { if (op) { lru_gen_rotate_memcg(lruvec, op); op = 0; } mem_cgroup_put(memcg); memcg = NULL; if (gen != READ_ONCE(lrugen->gen)) continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); if (!mem_cgroup_tryget(memcg)) { lru_gen_release_memcg(memcg); memcg = NULL; continue; } rcu_read_unlock(); op = shrink_one(lruvec, sc); rcu_read_lock(); if (should_abort_scan(lruvec, sc)) break; } rcu_read_unlock(); if (op) lru_gen_rotate_memcg(lruvec, op); mem_cgroup_put(memcg); if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ if (gen != get_nulls_value(pos)) goto restart; /* try the rest of the bins of the current generation */ bin = get_memcg_bin(bin + 1); if (bin != first_bin) goto restart; } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { struct blk_plug plug; VM_WARN_ON_ONCE(root_reclaim(sc)); VM_WARN_ON_ONCE(!sc->may_writepage || !sc->may_unmap); lru_add_drain(); blk_start_plug(&plug); set_mm_walk(NULL, sc->proactive); if (try_to_shrink_lruvec(lruvec, sc)) lru_gen_rotate_memcg(lruvec, MEMCG_LRU_YOUNG); clear_mm_walk(); blk_finish_plug(&plug); } static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) { int priority; unsigned long reclaimable; struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* * Determine the initial priority based on * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_swappiness(lruvec, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); sc->priority = clamp(priority, 0, DEF_PRIORITY); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { struct blk_plug plug; unsigned long reclaimed = sc->nr_reclaimed; VM_WARN_ON_ONCE(!root_reclaim(sc)); /* * Unmapped clean folios are already prioritized. Scanning for more of * them is likely futile and can cause high reclaim latency when there * is a large number of memcgs. */ if (!sc->may_writepage || !sc->may_unmap) goto done; lru_add_drain(); blk_start_plug(&plug); set_mm_walk(pgdat, sc->proactive); set_initial_priority(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed = 0; if (mem_cgroup_disabled()) shrink_one(&pgdat->__lruvec, sc); else shrink_many(pgdat, sc); if (current_is_kswapd()) sc->nr_reclaimed += reclaimed; clear_mm_walk(); blk_finish_plug(&plug); done: /* kswapd should never fail */ pgdat->kswapd_failures = 0; } /****************************************************************************** * state change ******************************************************************************/ static bool __maybe_unused state_is_valid(struct lruvec *lruvec) { struct lru_gen_folio *lrugen = &lruvec->lrugen; if (lrugen->enabled) { enum lru_list lru; for_each_evictable_lru(lru) { if (!list_empty(&lruvec->lists[lru])) return false; } } else { int gen, type, zone; for_each_gen_type_zone(gen, type, zone) { if (!list_empty(&lrugen->folios[gen][type][zone])) return false; } } return true; } static bool fill_evictable(struct lruvec *lruvec) { enum lru_list lru; int remaining = MAX_LRU_BATCH; for_each_evictable_lru(lru) { int type = is_file_lru(lru); bool active = is_active_lru(lru); struct list_head *head = &lruvec->lists[lru]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio); lruvec_del_folio(lruvec, folio); success = lru_gen_add_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); if (!--remaining) return false; } } return true; } static bool drain_evictable(struct lruvec *lruvec) { int gen, type, zone; int remaining = MAX_LRU_BATCH; for_each_gen_type_zone(gen, type, zone) { struct list_head *head = &lruvec->lrugen.folios[gen][type][zone]; while (!list_empty(head)) { bool success; struct folio *folio = lru_to_folio(head); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio); VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio); success = lru_gen_del_folio(lruvec, folio, false); VM_WARN_ON_ONCE(!success); lruvec_add_folio(lruvec, folio); if (!--remaining) return false; } } return true; } static void lru_gen_change_state(bool enabled) { static DEFINE_MUTEX(state_mutex); struct mem_cgroup *memcg; cgroup_lock(); cpus_read_lock(); get_online_mems(); mutex_lock(&state_mutex); if (enabled == lru_gen_enabled()) goto unlock; if (enabled) static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); else static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); spin_lock_irq(&lruvec->lru_lock); VM_WARN_ON_ONCE(!seq_is_valid(lruvec)); VM_WARN_ON_ONCE(!state_is_valid(lruvec)); lruvec->lrugen.enabled = enabled; while (!(enabled ? fill_evictable(lruvec) : drain_evictable(lruvec))) { spin_unlock_irq(&lruvec->lru_lock); cond_resched(); spin_lock_irq(&lruvec->lru_lock); } spin_unlock_irq(&lruvec->lru_lock); } cond_resched(); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); unlock: mutex_unlock(&state_mutex); put_online_mems(); cpus_read_unlock(); cgroup_unlock(); } /****************************************************************************** * sysfs interface ******************************************************************************/ static ssize_t min_ttl_ms_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl))); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t min_ttl_ms_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned int msecs; if (kstrtouint(buf, 0, &msecs)) return -EINVAL; WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs)); return len; } static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR_RW(min_ttl_ms); static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { unsigned int caps = 0; if (get_cap(LRU_GEN_CORE)) caps |= BIT(LRU_GEN_CORE); if (should_walk_mmu()) caps |= BIT(LRU_GEN_MM_WALK); if (should_clear_pmd_young()) caps |= BIT(LRU_GEN_NONLEAF_YOUNG); return sysfs_emit(buf, "0x%04x\n", caps); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { int i; unsigned int caps; if (tolower(*buf) == 'n') caps = 0; else if (tolower(*buf) == 'y') caps = -1; else if (kstrtouint(buf, 0, &caps)) return -EINVAL; for (i = 0; i < NR_LRU_GEN_CAPS; i++) { bool enabled = caps & BIT(i); if (i == LRU_GEN_CORE) lru_gen_change_state(enabled); else if (enabled) static_branch_enable(&lru_gen_caps[i]); else static_branch_disable(&lru_gen_caps[i]); } return len; } static struct kobj_attribute lru_gen_enabled_attr = __ATTR_RW(enabled); static struct attribute *lru_gen_attrs[] = { &lru_gen_min_ttl_attr.attr, &lru_gen_enabled_attr.attr, NULL }; static const struct attribute_group lru_gen_attr_group = { .name = "lru_gen", .attrs = lru_gen_attrs, }; /****************************************************************************** * debugfs interface ******************************************************************************/ static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos) { struct mem_cgroup *memcg; loff_t nr_to_skip = *pos; m->private = kvmalloc(PATH_MAX, GFP_KERNEL); if (!m->private) return ERR_PTR(-ENOMEM); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { int nid; for_each_node_state(nid, N_MEMORY) { if (!nr_to_skip--) return get_lruvec(memcg, nid); } } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); return NULL; } static void lru_gen_seq_stop(struct seq_file *m, void *v) { if (!IS_ERR_OR_NULL(v)) mem_cgroup_iter_break(NULL, lruvec_memcg(v)); kvfree(m->private); m->private = NULL; } static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos) { int nid = lruvec_pgdat(v)->node_id; struct mem_cgroup *memcg = lruvec_memcg(v); ++*pos; nid = next_memory_node(nid); if (nid == MAX_NUMNODES) { memcg = mem_cgroup_iter(NULL, memcg, NULL); if (!memcg) return NULL; nid = first_memory_node; } return get_lruvec(memcg, nid); } static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec, unsigned long max_seq, unsigned long *min_seq, unsigned long seq) { int i; int type, tier; int hist = lru_hist_from_seq(seq); struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); for (tier = 0; tier < MAX_NR_TIERS; tier++) { seq_printf(m, " %10d", tier); for (type = 0; type < ANON_AND_FILE; type++) { const char *s = " "; unsigned long n[3] = {}; if (seq == max_seq) { s = "RT "; n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]); n[1] = READ_ONCE(lrugen->avg_total[type][tier]); } else if (seq == min_seq[type] || NR_HIST_GENS > 1) { s = "rep"; n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]); n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]); if (tier) n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]); } for (i = 0; i < 3; i++) seq_printf(m, " %10lu%c", n[i], s[i]); } seq_putc(m, '\n'); } if (!mm_state) return; seq_puts(m, " "); for (i = 0; i < NR_MM_STATS; i++) { const char *s = " "; unsigned long n = 0; if (seq == max_seq && NR_HIST_GENS == 1) { s = "LOYNFA"; n = READ_ONCE(mm_state->stats[hist][i]); } else if (seq != max_seq && NR_HIST_GENS > 1) { s = "loynfa"; n = READ_ONCE(mm_state->stats[hist][i]); } seq_printf(m, " %10lu%c", n, s[i]); } seq_putc(m, '\n'); } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static int lru_gen_seq_show(struct seq_file *m, void *v) { unsigned long seq; bool full = !debugfs_real_fops(m->file)->write; struct lruvec *lruvec = v; struct lru_gen_folio *lrugen = &lruvec->lrugen; int nid = lruvec_pgdat(lruvec)->node_id; struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (nid == first_memory_node) { const char *path = memcg ? m->private : ""; #ifdef CONFIG_MEMCG if (memcg) cgroup_path(memcg->css.cgroup, m->private, PATH_MAX); #endif seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path); } seq_printf(m, " node %5d\n", nid); if (!full) seq = min_seq[LRU_GEN_ANON]; else if (max_seq >= MAX_NR_GENS) seq = max_seq - MAX_NR_GENS + 1; else seq = 0; for (; seq <= max_seq; seq++) { int type, zone; int gen = lru_gen_from_seq(seq); unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth)); for (type = 0; type < ANON_AND_FILE; type++) { unsigned long size = 0; char mark = full && seq < min_seq[type] ? 'x' : ' '; for (zone = 0; zone < MAX_NR_ZONES; zone++) size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L); seq_printf(m, " %10lu%c", size, mark); } seq_putc(m, '\n'); if (full) lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq); } return 0; } static const struct seq_operations lru_gen_seq_ops = { .start = lru_gen_seq_start, .stop = lru_gen_seq_stop, .next = lru_gen_seq_next, .show = lru_gen_seq_show, }; static int run_aging(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, bool can_swap, bool force_scan) { DEFINE_MAX_SEQ(lruvec); DEFINE_MIN_SEQ(lruvec); if (seq < max_seq) return 0; if (seq > max_seq) return -EINVAL; if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq) return -ERANGE; try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, force_scan); return 0; } static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long nr_to_reclaim) { DEFINE_MAX_SEQ(lruvec); if (seq + MIN_NR_GENS > max_seq) return -EINVAL; sc->nr_reclaimed = 0; while (!signal_pending(current)) { DEFINE_MIN_SEQ(lruvec); if (seq < min_seq[!swappiness]) return 0; if (sc->nr_reclaimed >= nr_to_reclaim) return 0; if (!evict_folios(lruvec, sc, swappiness)) return 0; cond_resched(); } return -EINTR; } static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq, struct scan_control *sc, int swappiness, unsigned long opt) { struct lruvec *lruvec; int err = -EINVAL; struct mem_cgroup *memcg = NULL; if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY)) return -EINVAL; if (!mem_cgroup_disabled()) { rcu_read_lock(); memcg = mem_cgroup_from_id(memcg_id); if (!mem_cgroup_tryget(memcg)) memcg = NULL; rcu_read_unlock(); if (!memcg) return -EINVAL; } if (memcg_id != mem_cgroup_id(memcg)) goto done; lruvec = get_lruvec(memcg, nid); if (swappiness < 0) swappiness = get_swappiness(lruvec, sc); else if (swappiness > 200) goto done; switch (cmd) { case '+': err = run_aging(lruvec, seq, sc, swappiness, opt); break; case '-': err = run_eviction(lruvec, seq, sc, swappiness, opt); break; } done: mem_cgroup_put(memcg); return err; } /* see Documentation/admin-guide/mm/multigen_lru.rst for details */ static ssize_t lru_gen_seq_write(struct file *file, const char __user *src, size_t len, loff_t *pos) { void *buf; char *cur, *next; unsigned int flags; struct blk_plug plug; int err = -EINVAL; struct scan_control sc = { .may_writepage = true, .may_unmap = true, .may_swap = true, .reclaim_idx = MAX_NR_ZONES - 1, .gfp_mask = GFP_KERNEL, }; buf = kvmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_user(buf, src, len)) { kvfree(buf); return -EFAULT; } set_task_reclaim_state(current, &sc.reclaim_state); flags = memalloc_noreclaim_save(); blk_start_plug(&plug); if (!set_mm_walk(NULL, true)) { err = -ENOMEM; goto done; } next = buf; next[len] = '\0'; while ((cur = strsep(&next, ",;\n"))) { int n; int end; char cmd; unsigned int memcg_id; unsigned int nid; unsigned long seq; unsigned int swappiness = -1; unsigned long opt = -1; cur = skip_spaces(cur); if (!*cur) continue; n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid, &seq, &end, &swappiness, &end, &opt, &end); if (n < 4 || cur[end]) { err = -EINVAL; break; } err = run_cmd(cmd, memcg_id, nid, seq, &sc, swappiness, opt); if (err) break; } done: clear_mm_walk(); blk_finish_plug(&plug); memalloc_noreclaim_restore(flags); set_task_reclaim_state(current, NULL); kvfree(buf); return err ? : len; } static int lru_gen_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &lru_gen_seq_ops); } static const struct file_operations lru_gen_rw_fops = { .open = lru_gen_seq_open, .read = seq_read, .write = lru_gen_seq_write, .llseek = seq_lseek, .release = seq_release, }; static const struct file_operations lru_gen_ro_fops = { .open = lru_gen_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; /****************************************************************************** * initialization ******************************************************************************/ void lru_gen_init_pgdat(struct pglist_data *pgdat) { int i, j; spin_lock_init(&pgdat->memcg_lru.lock); for (i = 0; i < MEMCG_NR_GENS; i++) { for (j = 0; j < MEMCG_NR_BINS; j++) INIT_HLIST_NULLS_HEAD(&pgdat->memcg_lru.fifo[i][j], i); } } void lru_gen_init_lruvec(struct lruvec *lruvec) { int i; int gen, type, zone; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); lrugen->max_seq = MIN_NR_GENS + 1; lrugen->enabled = lru_gen_enabled(); for (i = 0; i <= MIN_NR_GENS + 1; i++) lrugen->timestamps[i] = jiffies; for_each_gen_type_zone(gen, type, zone) INIT_LIST_HEAD(&lrugen->folios[gen][type][zone]); if (mm_state) mm_state->seq = MIN_NR_GENS; } #ifdef CONFIG_MEMCG void lru_gen_init_memcg(struct mem_cgroup *memcg) { struct lru_gen_mm_list *mm_list = get_mm_list(memcg); if (!mm_list) return; INIT_LIST_HEAD(&mm_list->fifo); spin_lock_init(&mm_list->lock); } void lru_gen_exit_memcg(struct mem_cgroup *memcg) { int i; int nid; struct lru_gen_mm_list *mm_list = get_mm_list(memcg); VM_WARN_ON_ONCE(mm_list && !list_empty(&mm_list->fifo)); for_each_node(nid) { struct lruvec *lruvec = get_lruvec(memcg, nid); struct lru_gen_mm_state *mm_state = get_mm_state(lruvec); VM_WARN_ON_ONCE(memchr_inv(lruvec->lrugen.nr_pages, 0, sizeof(lruvec->lrugen.nr_pages))); lruvec->lrugen.list.next = LIST_POISON1; if (!mm_state) continue; for (i = 0; i < NR_BLOOM_FILTERS; i++) { bitmap_free(mm_state->filters[i]); mm_state->filters[i] = NULL; } } } #endif /* CONFIG_MEMCG */ static int __init init_lru_gen(void) { BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS); BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS); if (sysfs_create_group(mm_kobj, &lru_gen_attr_group)) pr_err("lru_gen: failed to create sysfs group\n"); debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops); debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops); return 0; }; late_initcall(init_lru_gen); #else /* !CONFIG_LRU_GEN */ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { BUILD_BUG(); } static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { BUILD_BUG(); } #endif /* CONFIG_LRU_GEN */ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; bool proportional_reclaim; struct blk_plug plug; if (lru_gen_enabled() && !root_reclaim(sc)) { lru_gen_shrink_lruvec(lruvec, sc); return; } get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || proportional_reclaim) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (can_age_anon_pages(lruvec_pgdat(lruvec), sc) && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone), sc->reclaim_idx, 0)) return false; if (compaction_suitable(zone, sc->order, sc->reclaim_idx)) return false; } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup *memcg; memcg = mem_cgroup_iter(target_memcg, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(target_memcg, memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(target_memcg, memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { unsigned long nr_reclaimed, nr_scanned, nr_node_reclaimed; struct lruvec *target_lruvec; bool reclaimable = false; if (lru_gen_enabled() && root_reclaim(sc)) { lru_gen_shrink_node(pgdat, sc); return; } target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; prepare_scan_control(pgdat, sc); shrink_node_memcgs(pgdat, sc); flush_reclaim_state(sc); nr_node_reclaimed = sc->nr_reclaimed - nr_reclaimed; /* Record the subtree's reclaim efficiency */ if (!sc->proactive) vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, nr_node_reclaimed); if (nr_node_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so forcibly stall * until some pages complete writeback. */ if (sc->nr.immediate) reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); } /* * Tag a node/memcg as congested if all the dirty pages were marked * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in reclaim_throttle(). */ if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested) { if (cgroup_reclaim(sc) && writeback_throttling_sane(sc)) set_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags); if (current_is_kswapd()) set_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags); } /* * Stall direct reclaim for IO completions if the lruvec is * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && (test_bit(LRUVEC_CGROUP_CONGESTED, &target_lruvec->flags) || test_bit(LRUVEC_NODE_CONGESTED, &target_lruvec->flags))) reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, nr_node_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; /* Allocation can already succeed, nothing to do */ if (zone_watermark_ok(zone, sc->order, min_wmark_pages(zone), sc->reclaim_idx, 0)) return true; /* Compaction cannot yet proceed. Do reclaim. */ if (!compaction_suitable(zone, sc->order, sc->reclaim_idx)) return false; /* * Compaction is already possible, but it takes time to run and there * are potentially other callers using the pages just freed. So proceed * with reclaim to make a buffer of free pages available to give * compaction a reasonable chance of completing and allocating the page. * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone) + compact_gap(sc->order); return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) { /* * If reclaim is making progress greater than 12% efficiency then * wake all the NOPROGRESS throttled tasks. */ if (sc->nr_reclaimed > (sc->nr_scanned >> 3)) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; if (waitqueue_active(wqh)) wake_up(wqh); return; } /* * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages * under writeback and marked for immediate reclaim at the tail of the * LRU. */ if (current_is_kswapd() || cgroup_reclaim(sc)) return; /* Throttle if making no progress at high prioities. */ if (sc->priority == 1 && !sc->nr_reclaimed) reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } if (!first_pgdat) first_pgdat = zone->zone_pgdat; /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } if (first_pgdat) consider_reclaim_throttle(first_pgdat, sc); /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; if (lru_gen_enabled()) return; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[WORKINGSET_ANON] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[WORKINGSET_FILE] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { if (!sc->proactive) vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!managed_zone(zone)) continue; if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state_snapshot(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); else /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_PAGE_ORDER >= S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (lru_gen_enabled()) { lru_gen_age_node(pgdat, sc); return; } if (!can_age_anon_pages(pgdat, sc)) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) mark = wmark_pages(zone, WMARK_PROMO); else mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* * If a node has no managed zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_NODE_CONGESTED, &lruvec->flags); clear_bit(LRUVEC_CGROUP_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; return sc->nr_scanned >= sc->nr_to_reclaim; } /* Page allocator PCP high watermark is lowered if reclaim is active. */ static inline void update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) { int i; struct zone *zone; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (active) set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); else clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); } } static inline void set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, true); } static inline void clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) { update_reclaim_active(pgdat, highest_zoneidx, false); } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(_THIS_IP_); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging, to give pages a chance to be * referenced before reclaiming. All pages are rotated * regardless of classzone as this is about consistent aging. */ kswapd_age_node(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(_THIS_IP_); ret = try_to_freeze(); __fs_reclaim_acquire(_THIS_IP_); if (ret || kthread_should_stop()) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: clear_reclaim_active(pgdat, highest_zoneidx); /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(_THIS_IP_); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t *)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool ret; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (ret) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. */ void __meminit kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); pgdat_kswapd_lock(pgdat); if (!pgdat->kswapd) { pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ pr_err("Failed to start kswapd on node %d，ret=%ld\n", nid, PTR_ERR(pgdat->kswapd)); BUG_ON(system_state < SYSTEM_RUNNING); pgdat->kswapd = NULL; } } pgdat_kswapd_unlock(pgdat); } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * be holding mem_hotplug_begin/done(). */ void __meminit kswapd_stop(int nid) { pg_data_t *pgdat = NODE_DATA(nid); struct task_struct *kswapd; pgdat_kswapd_lock(pgdat); kswapd = pgdat->kswapd; if (kswapd) { kthread_stop(kswapd); pgdat->kswapd = NULL; } pgdat_kswapd_unlock(pgdat); } static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; unsigned long pflags; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); psi_memstall_enter(&pflags); delayacct_freepages_start(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP */ noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages || node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) > pgdat->min_slab_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); psi_memstall_leave(&pflags); delayacct_freepages_end(); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (!ret) count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif /** * check_move_unevictable_folios - Move evictable folios to appropriate zone * lru list * @fbatch: Batch of lru folios to check. * * Checks folios for evictability, if an evictable folio is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru folios. */ void check_move_unevictable_folios(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < fbatch->nr; i++) { struct folio *folio = fbatch->folios[i]; int nr_pages = folio_nr_pages(folio); pgscanned += nr_pages; /* block memcg migration while the folio moves between lrus */ if (!folio_test_clear_lru(folio)) continue; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_evictable(folio) && folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); pgrescued += nr_pages; } folio_set_lru(folio); } if (lruvec) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); unlock_page_lruvec_irq(lruvec); } else if (pgscanned) { count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); } } EXPORT_SYMBOL_GPL(check_move_unevictable_folios); |
| 36 36 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for logging packets to userspace via * nfetlink. * * (C) 2005 by Harald Welte <laforge@netfilter.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * Based on the old ipv4-only ipt_ULOG.c: * (C) 2000-2004 by Harald Welte <laforge@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/netfilter_bridge.h> #include <net/netlink.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_log.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/spinlock.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/list.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netfilter/nf_log.h> #include <net/netns/generic.h> #include <linux/atomic.h> #include <linux/refcount.h> #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include "../bridge/br_private.h" #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif #define NFULNL_COPY_DISABLED 0xff #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ /* max packet size is limited by 16-bit struct nfattr nfa_len field */ #define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN) #define PRINTR(x, args...) do { if (net_ratelimit()) \ printk(x, ## args); } while (0); struct nfulnl_instance { struct hlist_node hlist; /* global list of instances */ spinlock_t lock; refcount_t use; /* use count */ unsigned int qlen; /* number of nlmsgs in skb */ struct sk_buff *skb; /* pre-allocatd skb */ struct timer_list timer; struct net *net; netns_tracker ns_tracker; struct user_namespace *peer_user_ns; /* User namespace of the peer process */ u32 peer_portid; /* PORTID of the peer process */ /* configurable parameters */ unsigned int flushtimeout; /* timeout until queue flush */ unsigned int nlbufsiz; /* netlink buffer allocation size */ unsigned int qthreshold; /* threshold of the queue */ u_int32_t copy_range; u_int32_t seq; /* instance-local sequential counter */ u_int16_t group_num; /* number of this queue */ u_int16_t flags; u_int8_t copy_mode; struct rcu_head rcu; }; #define INSTANCE_BUCKETS 16 static unsigned int nfnl_log_net_id __read_mostly; struct nfnl_log_net { spinlock_t instances_lock; struct hlist_head instance_table[INSTANCE_BUCKETS]; atomic_t global_seq; }; static struct nfnl_log_net *nfnl_log_pernet(struct net *net) { return net_generic(net, nfnl_log_net_id); } static inline u_int8_t instance_hashfn(u_int16_t group_num) { return ((group_num & 0xff) % INSTANCE_BUCKETS); } static struct nfulnl_instance * __instance_lookup(const struct nfnl_log_net *log, u16 group_num) { const struct hlist_head *head; struct nfulnl_instance *inst; head = &log->instance_table[instance_hashfn(group_num)]; hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->group_num == group_num) return inst; } return NULL; } static inline void instance_get(struct nfulnl_instance *inst) { refcount_inc(&inst->use); } static struct nfulnl_instance * instance_lookup_get_rcu(const struct nfnl_log_net *log, u16 group_num) { struct nfulnl_instance *inst; inst = __instance_lookup(log, group_num); if (inst && !refcount_inc_not_zero(&inst->use)) inst = NULL; return inst; } static struct nfulnl_instance * instance_lookup_get(const struct nfnl_log_net *log, u16 group_num) { struct nfulnl_instance *inst; rcu_read_lock(); inst = instance_lookup_get_rcu(log, group_num); rcu_read_unlock(); return inst; } static void nfulnl_instance_free_rcu(struct rcu_head *head) { struct nfulnl_instance *inst = container_of(head, struct nfulnl_instance, rcu); put_net_track(inst->net, &inst->ns_tracker); kfree(inst); module_put(THIS_MODULE); } static void instance_put(struct nfulnl_instance *inst) { if (inst && refcount_dec_and_test(&inst->use)) call_rcu(&inst->rcu, nfulnl_instance_free_rcu); } static void nfulnl_timer(struct timer_list *t); static struct nfulnl_instance * instance_create(struct net *net, u_int16_t group_num, u32 portid, struct user_namespace *user_ns) { struct nfulnl_instance *inst; struct nfnl_log_net *log = nfnl_log_pernet(net); int err; spin_lock_bh(&log->instances_lock); if (__instance_lookup(log, group_num)) { err = -EEXIST; goto out_unlock; } inst = kzalloc(sizeof(*inst), GFP_ATOMIC); if (!inst) { err = -ENOMEM; goto out_unlock; } if (!try_module_get(THIS_MODULE)) { kfree(inst); err = -EAGAIN; goto out_unlock; } INIT_HLIST_NODE(&inst->hlist); spin_lock_init(&inst->lock); /* needs to be two, since we _put() after creation */ refcount_set(&inst->use, 2); timer_setup(&inst->timer, nfulnl_timer, 0); inst->net = get_net_track(net, &inst->ns_tracker, GFP_ATOMIC); inst->peer_user_ns = user_ns; inst->peer_portid = portid; inst->group_num = group_num; inst->qthreshold = NFULNL_QTHRESH_DEFAULT; inst->flushtimeout = NFULNL_TIMEOUT_DEFAULT; inst->nlbufsiz = NFULNL_NLBUFSIZ_DEFAULT; inst->copy_mode = NFULNL_COPY_PACKET; inst->copy_range = NFULNL_COPY_RANGE_MAX; hlist_add_head_rcu(&inst->hlist, &log->instance_table[instance_hashfn(group_num)]); spin_unlock_bh(&log->instances_lock); return inst; out_unlock: spin_unlock_bh(&log->instances_lock); return ERR_PTR(err); } static void __nfulnl_flush(struct nfulnl_instance *inst); /* called with BH disabled */ static void __instance_destroy(struct nfulnl_instance *inst) { /* first pull it out of the global list */ hlist_del_rcu(&inst->hlist); /* then flush all pending packets from skb */ spin_lock(&inst->lock); /* lockless readers wont be able to use us */ inst->copy_mode = NFULNL_COPY_DISABLED; if (inst->skb) __nfulnl_flush(inst); spin_unlock(&inst->lock); /* and finally put the refcount */ instance_put(inst); } static inline void instance_destroy(struct nfnl_log_net *log, struct nfulnl_instance *inst) { spin_lock_bh(&log->instances_lock); __instance_destroy(inst); spin_unlock_bh(&log->instances_lock); } static int nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, unsigned int range) { int status = 0; spin_lock_bh(&inst->lock); switch (mode) { case NFULNL_COPY_NONE: case NFULNL_COPY_META: inst->copy_mode = mode; inst->copy_range = 0; break; case NFULNL_COPY_PACKET: inst->copy_mode = mode; if (range == 0) range = NFULNL_COPY_RANGE_MAX; inst->copy_range = min_t(unsigned int, range, NFULNL_COPY_RANGE_MAX); break; default: status = -EINVAL; break; } spin_unlock_bh(&inst->lock); return status; } static int nfulnl_set_nlbufsiz(struct nfulnl_instance *inst, u_int32_t nlbufsiz) { int status; spin_lock_bh(&inst->lock); if (nlbufsiz < NFULNL_NLBUFSIZ_DEFAULT) status = -ERANGE; else if (nlbufsiz > 131072) status = -ERANGE; else { inst->nlbufsiz = nlbufsiz; status = 0; } spin_unlock_bh(&inst->lock); return status; } static void nfulnl_set_timeout(struct nfulnl_instance *inst, u_int32_t timeout) { spin_lock_bh(&inst->lock); inst->flushtimeout = timeout; spin_unlock_bh(&inst->lock); } static void nfulnl_set_qthresh(struct nfulnl_instance *inst, u_int32_t qthresh) { spin_lock_bh(&inst->lock); inst->qthreshold = qthresh; spin_unlock_bh(&inst->lock); } static int nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags) { spin_lock_bh(&inst->lock); inst->flags = flags; spin_unlock_bh(&inst->lock); return 0; } static struct sk_buff * nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size, unsigned int pkt_size) { struct sk_buff *skb; unsigned int n; /* alloc skb which should be big enough for a whole multipart * message. WARNING: has to be <= 128k due to slab restrictions */ n = max(inst_size, pkt_size); skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN); if (!skb) { if (n > pkt_size) { /* try to allocate only as much as we need for current * packet */ skb = alloc_skb(pkt_size, GFP_ATOMIC); } } return skb; } static void __nfulnl_send(struct nfulnl_instance *inst) { if (inst->qlen > 1) { struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0, NLMSG_DONE, sizeof(struct nfgenmsg), 0); if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n", inst->skb->len, skb_tailroom(inst->skb))) { kfree_skb(inst->skb); goto out; } } nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid); out: inst->qlen = 0; inst->skb = NULL; } static void __nfulnl_flush(struct nfulnl_instance *inst) { /* timer holds a reference */ if (del_timer(&inst->timer)) instance_put(inst); if (inst->skb) __nfulnl_send(inst); } static void nfulnl_timer(struct timer_list *t) { struct nfulnl_instance *inst = from_timer(inst, t, timer); spin_lock_bh(&inst->lock); if (inst->skb) __nfulnl_send(inst); spin_unlock_bh(&inst->lock); instance_put(inst); } static u32 nfulnl_get_bridge_size(const struct sk_buff *skb) { u32 size = 0; if (!skb_mac_header_was_set(skb)) return 0; if (skb_vlan_tag_present(skb)) { size += nla_total_size(0); /* nested */ size += nla_total_size(sizeof(u16)); /* id */ size += nla_total_size(sizeof(u16)); /* tag */ } if (skb->network_header > skb->mac_header) size += nla_total_size(skb->network_header - skb->mac_header); return size; } static int nfulnl_put_bridge(struct nfulnl_instance *inst, const struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) return 0; if (skb_vlan_tag_present(skb)) { struct nlattr *nest; nest = nla_nest_start(inst->skb, NFULA_VLAN); if (!nest) goto nla_put_failure; if (nla_put_be16(inst->skb, NFULA_VLAN_TCI, htons(skb->vlan_tci)) || nla_put_be16(inst->skb, NFULA_VLAN_PROTO, skb->vlan_proto)) goto nla_put_failure; nla_nest_end(inst->skb, nest); } if (skb->mac_header < skb->network_header) { int len = (int)(skb->network_header - skb->mac_header); if (nla_put(inst->skb, NFULA_L2HDR, len, skb_mac_header(skb))) goto nla_put_failure; } return 0; nla_put_failure: return -1; } /* This is an inline function, we don't really care about a long * list of arguments */ static inline int __build_packet_message(struct nfnl_log_net *log, struct nfulnl_instance *inst, const struct sk_buff *skb, unsigned int data_len, u_int8_t pf, unsigned int hooknum, const struct net_device *indev, const struct net_device *outdev, const char *prefix, unsigned int plen, const struct nfnl_ct_hook *nfnl_ct, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { struct nfulnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; sk_buff_data_t old_tail = inst->skb->tail; struct sock *sk; const unsigned char *hwhdrp; nlh = nfnl_msg_put(inst->skb, 0, 0, nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET), 0, pf, NFNETLINK_V0, htons(inst->group_num)); if (!nlh) return -1; memset(&pmsg, 0, sizeof(pmsg)); pmsg.hw_protocol = skb->protocol; pmsg.hook = hooknum; if (nla_put(inst->skb, NFULA_PACKET_HDR, sizeof(pmsg), &pmsg)) goto nla_put_failure; if (prefix && nla_put(inst->skb, NFULA_PREFIX, plen, prefix)) goto nla_put_failure; if (indev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; #else if (pf == PF_BRIDGE) { /* Case 1: outdev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; physinif = nf_bridge_get_physinif(skb); if (physinif && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, htonl(physinif))) goto nla_put_failure; } #endif } if (outdev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; #else if (pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) goto nla_put_failure; } else { struct net_device *physoutdev; /* Case 2: indev is a bridge group, we need to look * for physical device (when called from ipv4) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; physoutdev = nf_bridge_get_physoutdev(skb); if (physoutdev && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, htonl(physoutdev->ifindex))) goto nla_put_failure; } #endif } if (skb->mark && nla_put_be32(inst->skb, NFULA_MARK, htonl(skb->mark))) goto nla_put_failure; if (indev && skb->dev && skb_mac_header_was_set(skb) && skb_mac_header_len(skb) != 0) { struct nfulnl_msg_packet_hw phw; int len; memset(&phw, 0, sizeof(phw)); len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { phw.hw_addrlen = htons(len); if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw)) goto nla_put_failure; } } if (indev && skb_mac_header_was_set(skb)) { if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || nla_put_be16(inst->skb, NFULA_HWLEN, htons(skb->dev->hard_header_len))) goto nla_put_failure; hwhdrp = skb_mac_header(skb); if (skb->dev->type == ARPHRD_SIT) hwhdrp -= ETH_HLEN; if (hwhdrp >= skb->head && nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, hwhdrp)) goto nla_put_failure; } if (hooknum <= NF_INET_FORWARD) { struct timespec64 kts = ktime_to_timespec64(skb_tstamp_cond(skb, true)); struct nfulnl_msg_packet_timestamp ts; ts.sec = cpu_to_be64(kts.tv_sec); ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); if (nla_put(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts)) goto nla_put_failure; } /* UID */ sk = skb->sk; if (sk && sk_fullsock(sk)) { read_lock_bh(&sk->sk_callback_lock); if (sk->sk_socket && sk->sk_socket->file) { struct file *file = sk->sk_socket->file; const struct cred *cred = file->f_cred; struct user_namespace *user_ns = inst->peer_user_ns; __be32 uid = htonl(from_kuid_munged(user_ns, cred->fsuid)); __be32 gid = htonl(from_kgid_munged(user_ns, cred->fsgid)); read_unlock_bh(&sk->sk_callback_lock); if (nla_put_be32(inst->skb, NFULA_UID, uid) || nla_put_be32(inst->skb, NFULA_GID, gid)) goto nla_put_failure; } else read_unlock_bh(&sk->sk_callback_lock); } /* local sequence number */ if ((inst->flags & NFULNL_CFG_F_SEQ) && nla_put_be32(inst->skb, NFULA_SEQ, htonl(inst->seq++))) goto nla_put_failure; /* global sequence number */ if ((inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) && nla_put_be32(inst->skb, NFULA_SEQ_GLOBAL, htonl(atomic_inc_return(&log->global_seq)))) goto nla_put_failure; if (ct && nfnl_ct->build(inst->skb, ct, ctinfo, NFULA_CT, NFULA_CT_INFO) < 0) goto nla_put_failure; if ((pf == NFPROTO_NETDEV || pf == NFPROTO_BRIDGE) && nfulnl_put_bridge(inst, skb) < 0) goto nla_put_failure; if (data_len) { struct nlattr *nla; int size = nla_attr_size(data_len); if (skb_tailroom(inst->skb) < nla_total_size(data_len)) goto nla_put_failure; nla = skb_put(inst->skb, nla_total_size(data_len)); nla->nla_type = NFULA_PAYLOAD; nla->nla_len = size; if (skb_copy_bits(skb, 0, nla_data(nla), data_len)) BUG(); } nlh->nlmsg_len = inst->skb->tail - old_tail; return 0; nla_put_failure: PRINTR(KERN_ERR "nfnetlink_log: error creating log nlmsg\n"); return -1; } static const struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_ULOG, .u = { .ulog = { .copy_len = 0xffff, .group = 0, .qthreshold = 1, }, }, }; /* log handler for internal netfilter logging api */ static void nfulnl_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *li_user, const char *prefix) { size_t size; unsigned int data_len; struct nfulnl_instance *inst; const struct nf_loginfo *li; unsigned int qthreshold; unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; enum ip_conntrack_info ctinfo = 0; struct nf_conn *ct = NULL; if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; else li = &default_loginfo; inst = instance_lookup_get_rcu(log, li->u.ulog.group); if (!inst) return; if (prefix) plen = strlen(prefix) + 1; /* FIXME: do we want to make the size calculation conditional based on * what is actually present? way more branches and checks, but more * memory efficient... */ size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfulnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + nla_total_size(sizeof(u_int32_t)) /* uid */ + nla_total_size(sizeof(u_int32_t)) /* gid */ + nla_total_size(plen) /* prefix */ + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)) + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { size += nla_total_size(skb->dev->hard_header_len) + nla_total_size(sizeof(u_int16_t)) /* hwtype */ + nla_total_size(sizeof(u_int16_t)); /* hwlen */ } spin_lock_bh(&inst->lock); if (inst->flags & NFULNL_CFG_F_SEQ) size += nla_total_size(sizeof(u_int32_t)); if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) size += nla_total_size(sizeof(u_int32_t)); #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (inst->flags & NFULNL_CFG_F_CONNTRACK) { nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfnl_ct != NULL) { ct = nf_ct_get(skb, &ctinfo); if (ct != NULL) size += nfnl_ct->build_size(ct); } } #endif if (pf == NFPROTO_NETDEV || pf == NFPROTO_BRIDGE) size += nfulnl_get_bridge_size(skb); qthreshold = inst->qthreshold; /* per-rule qthreshold overrides per-instance */ if (li->u.ulog.qthreshold) if (qthreshold > li->u.ulog.qthreshold) qthreshold = li->u.ulog.qthreshold; switch (inst->copy_mode) { case NFULNL_COPY_META: case NFULNL_COPY_NONE: data_len = 0; break; case NFULNL_COPY_PACKET: data_len = inst->copy_range; if ((li->u.ulog.flags & NF_LOG_F_COPY_LEN) && (li->u.ulog.copy_len < data_len)) data_len = li->u.ulog.copy_len; if (data_len > skb->len) data_len = skb->len; size += nla_total_size(data_len); break; case NFULNL_COPY_DISABLED: default: goto unlock_and_release; } if (inst->skb && size > skb_tailroom(inst->skb)) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ __nfulnl_flush(inst); } if (!inst->skb) { inst->skb = nfulnl_alloc_skb(net, inst->peer_portid, inst->nlbufsiz, size); if (!inst->skb) goto alloc_failure; } inst->qlen++; __build_packet_message(log, inst, skb, data_len, pf, hooknum, in, out, prefix, plen, nfnl_ct, ct, ctinfo); if (inst->qlen >= qthreshold) __nfulnl_flush(inst); /* timer_pending always called within inst->lock, so there * is no chance of a race here */ else if (!timer_pending(&inst->timer)) { instance_get(inst); inst->timer.expires = jiffies + (inst->flushtimeout*HZ/100); add_timer(&inst->timer); } unlock_and_release: spin_unlock_bh(&inst->lock); instance_put(inst); return; alloc_failure: /* FIXME: statistics */ goto unlock_and_release; } static int nfulnl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netlink_notify *n = ptr; struct nfnl_log_net *log = nfnl_log_pernet(n->net); if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; /* destroy all instances for this portid */ spin_lock_bh(&log->instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *t2; struct nfulnl_instance *inst; struct hlist_head *head = &log->instance_table[i]; hlist_for_each_entry_safe(inst, t2, head, hlist) { if (n->portid == inst->peer_portid) __instance_destroy(inst); } } spin_unlock_bh(&log->instances_lock); } return NOTIFY_DONE; } static struct notifier_block nfulnl_rtnl_notifier = { .notifier_call = nfulnl_rcv_nl_event, }; static int nfulnl_recv_unsupp(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfula[]) { return -ENOTSUPP; } static struct nf_logger nfulnl_logger __read_mostly = { .name = "nfnetlink_log", .type = NF_LOG_TYPE_ULOG, .logfn = nfulnl_log_packet, .me = THIS_MODULE, }; static const struct nla_policy nfula_cfg_policy[NFULA_CFG_MAX+1] = { [NFULA_CFG_CMD] = { .len = sizeof(struct nfulnl_msg_config_cmd) }, [NFULA_CFG_MODE] = { .len = sizeof(struct nfulnl_msg_config_mode) }, [NFULA_CFG_TIMEOUT] = { .type = NLA_U32 }, [NFULA_CFG_QTHRESH] = { .type = NLA_U32 }, [NFULA_CFG_NLBUFSIZ] = { .type = NLA_U32 }, [NFULA_CFG_FLAGS] = { .type = NLA_U16 }, }; static int nfulnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfula[]) { struct nfnl_log_net *log = nfnl_log_pernet(info->net); u_int16_t group_num = ntohs(info->nfmsg->res_id); struct nfulnl_msg_config_cmd *cmd = NULL; struct nfulnl_instance *inst; u16 flags = 0; int ret = 0; if (nfula[NFULA_CFG_CMD]) { u_int8_t pf = info->nfmsg->nfgen_family; cmd = nla_data(nfula[NFULA_CFG_CMD]); /* Commands without queue context */ switch (cmd->command) { case NFULNL_CFG_CMD_PF_BIND: return nf_log_bind_pf(info->net, pf, &nfulnl_logger); case NFULNL_CFG_CMD_PF_UNBIND: nf_log_unbind_pf(info->net, pf); return 0; } } inst = instance_lookup_get(log, group_num); if (inst && inst->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto out_put; } /* Check if we support these flags in first place, dependencies should * be there too not to break atomicity. */ if (nfula[NFULA_CFG_FLAGS]) { flags = ntohs(nla_get_be16(nfula[NFULA_CFG_FLAGS])); if ((flags & NFULNL_CFG_F_CONNTRACK) && !rcu_access_pointer(nfnl_ct_hook)) { #ifdef CONFIG_MODULES nfnl_unlock(NFNL_SUBSYS_ULOG); request_module("ip_conntrack_netlink"); nfnl_lock(NFNL_SUBSYS_ULOG); if (rcu_access_pointer(nfnl_ct_hook)) { ret = -EAGAIN; goto out_put; } #endif ret = -EOPNOTSUPP; goto out_put; } } if (cmd != NULL) { switch (cmd->command) { case NFULNL_CFG_CMD_BIND: if (inst) { ret = -EBUSY; goto out_put; } inst = instance_create(info->net, group_num, NETLINK_CB(skb).portid, sk_user_ns(NETLINK_CB(skb).sk)); if (IS_ERR(inst)) { ret = PTR_ERR(inst); goto out; } break; case NFULNL_CFG_CMD_UNBIND: if (!inst) { ret = -ENODEV; goto out; } instance_destroy(log, inst); goto out_put; default: ret = -ENOTSUPP; goto out_put; } } else if (!inst) { ret = -ENODEV; goto out; } if (nfula[NFULA_CFG_MODE]) { struct nfulnl_msg_config_mode *params = nla_data(nfula[NFULA_CFG_MODE]); nfulnl_set_mode(inst, params->copy_mode, ntohl(params->copy_range)); } if (nfula[NFULA_CFG_TIMEOUT]) { __be32 timeout = nla_get_be32(nfula[NFULA_CFG_TIMEOUT]); nfulnl_set_timeout(inst, ntohl(timeout)); } if (nfula[NFULA_CFG_NLBUFSIZ]) { __be32 nlbufsiz = nla_get_be32(nfula[NFULA_CFG_NLBUFSIZ]); nfulnl_set_nlbufsiz(inst, ntohl(nlbufsiz)); } if (nfula[NFULA_CFG_QTHRESH]) { __be32 qthresh = nla_get_be32(nfula[NFULA_CFG_QTHRESH]); nfulnl_set_qthresh(inst, ntohl(qthresh)); } if (nfula[NFULA_CFG_FLAGS]) nfulnl_set_flags(inst, flags); out_put: instance_put(inst); out: return ret; } static const struct nfnl_callback nfulnl_cb[NFULNL_MSG_MAX] = { [NFULNL_MSG_PACKET] = { .call = nfulnl_recv_unsupp, .type = NFNL_CB_MUTEX, .attr_count = NFULA_MAX, }, [NFULNL_MSG_CONFIG] = { .call = nfulnl_recv_config, .type = NFNL_CB_MUTEX, .attr_count = NFULA_CFG_MAX, .policy = nfula_cfg_policy }, }; static const struct nfnetlink_subsystem nfulnl_subsys = { .name = "log", .subsys_id = NFNL_SUBSYS_ULOG, .cb_count = NFULNL_MSG_MAX, .cb = nfulnl_cb, }; #ifdef CONFIG_PROC_FS struct iter_state { struct seq_net_private p; unsigned int bucket; }; static struct hlist_node *get_first(struct net *net, struct iter_state *st) { struct nfnl_log_net *log; if (!st) return NULL; log = nfnl_log_pernet(net); for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) { struct hlist_head *head = &log->instance_table[st->bucket]; if (!hlist_empty(head)) return rcu_dereference(hlist_first_rcu(head)); } return NULL; } static struct hlist_node *get_next(struct net *net, struct iter_state *st, struct hlist_node *h) { h = rcu_dereference(hlist_next_rcu(h)); while (!h) { struct nfnl_log_net *log; struct hlist_head *head; if (++st->bucket >= INSTANCE_BUCKETS) return NULL; log = nfnl_log_pernet(net); head = &log->instance_table[st->bucket]; h = rcu_dereference(hlist_first_rcu(head)); } return h; } static struct hlist_node *get_idx(struct net *net, struct iter_state *st, loff_t pos) { struct hlist_node *head; head = get_first(net, st); if (head) while (pos && (head = get_next(net, st, head))) pos--; return pos ? NULL : head; } static void *seq_start(struct seq_file *s, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return get_idx(seq_file_net(s), s->private, *pos); } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { (*pos)++; return get_next(seq_file_net(s), s->private, v); } static void seq_stop(struct seq_file *s, void *v) __releases(rcu) { rcu_read_unlock(); } static int seq_show(struct seq_file *s, void *v) { const struct nfulnl_instance *inst = v; seq_printf(s, "%5u %6u %5u %1u %5u %6u %2u\n", inst->group_num, inst->peer_portid, inst->qlen, inst->copy_mode, inst->copy_range, inst->flushtimeout, refcount_read(&inst->use)); return 0; } static const struct seq_operations nful_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ static int __net_init nfnl_log_net_init(struct net *net) { unsigned int i; struct nfnl_log_net *log = nfnl_log_pernet(net); #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc; kuid_t root_uid; kgid_t root_gid; #endif for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&log->instance_table[i]); spin_lock_init(&log->instances_lock); #ifdef CONFIG_PROC_FS proc = proc_create_net("nfnetlink_log", 0440, net->nf.proc_netfilter, &nful_seq_ops, sizeof(struct iter_state)); if (!proc) return -ENOMEM; root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); #endif return 0; } static void __net_exit nfnl_log_net_exit(struct net *net) { struct nfnl_log_net *log = nfnl_log_pernet(net); unsigned int i; #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter); #endif nf_log_unset(net, &nfulnl_logger); for (i = 0; i < INSTANCE_BUCKETS; i++) WARN_ON_ONCE(!hlist_empty(&log->instance_table[i])); } static struct pernet_operations nfnl_log_net_ops = { .init = nfnl_log_net_init, .exit = nfnl_log_net_exit, .id = &nfnl_log_net_id, .size = sizeof(struct nfnl_log_net), }; static int __init nfnetlink_log_init(void) { int status; status = register_pernet_subsys(&nfnl_log_net_ops); if (status < 0) { pr_err("failed to register pernet ops\n"); goto out; } netlink_register_notifier(&nfulnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfulnl_subsys); if (status < 0) { pr_err("failed to create netlink socket\n"); goto cleanup_netlink_notifier; } status = nf_log_register(NFPROTO_UNSPEC, &nfulnl_logger); if (status < 0) { pr_err("failed to register logger\n"); goto cleanup_subsys; } return status; cleanup_subsys: nfnetlink_subsys_unregister(&nfulnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfulnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_log_net_ops); out: return status; } static void __exit nfnetlink_log_fini(void) { nfnetlink_subsys_unregister(&nfulnl_subsys); netlink_unregister_notifier(&nfulnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_log_net_ops); nf_log_unregister(&nfulnl_logger); } MODULE_DESCRIPTION("netfilter userspace logging"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); MODULE_ALIAS_NF_LOGGER(AF_INET, 1); MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */ MODULE_ALIAS_NF_LOGGER(5, 1); /* NFPROTO_NETDEV */ module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); |
| 404 404 403 404 25 25 3 3 25 25 25 25 135 295 93 311 25 25 25 25 25 428 427 429 539 539 3 3 3 539 539 539 404 404 404 404 25 25 25 25 428 428 429 429 429 429 404 404 429 429 429 429 429 429 429 428 39 3 36 1 1 34 34 35 35 34 1 38 39 1 35 1 927 927 538 927 25 404 404 4 400 49 49 49 49 49 49 927 926 927 905 25 927 1040 1041 429 428 429 539 539 539 539 404 404 365 366 274 274 274 82 44 38 971 971 2134 2134 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: Internet Group Management Protocol [IGMP] * * This code implements the IGMP protocol as defined in RFC1112. There has * been a further revision of this protocol since which is now supported. * * If you have trouble with this module be careful what gcc you have used, * the older version didn't come out right using gcc 2.5.8, the newer one * seems to fall out with gcc 2.6.2. * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * Alan Cox : Added lots of __inline__ to optimise * the memory usage of all the tiny little * functions. * Alan Cox : Dumped the header building experiment. * Alan Cox : Minor tweaks ready for multicast routing * and extended IGMP protocol. * Alan Cox : Removed a load of inline directives. Gcc 2.5.8 * writes utterly bogus code otherwise (sigh) * fixed IGMP loopback to behave in the manner * desired by mrouted, fixed the fact it has been * broken since 1.3.6 and cleaned up a few minor * points. * * Chih-Jen Chang : Tried to revise IGMP to Version 2 * Tsu-Sheng Tsao E-mail: chihjenc@scf.usc.edu and tsusheng@scf.usc.edu * The enhancements are mainly based on Steve Deering's * ipmulti-3.5 source code. * Chih-Jen Chang : Added the igmp_get_mrouter_info and * Tsu-Sheng Tsao igmp_set_mrouter_info to keep track of * the mrouted version on that device. * Chih-Jen Chang : Added the max_resp_time parameter to * Tsu-Sheng Tsao igmp_heard_query(). Using this parameter * to identify the multicast router version * and do what the IGMP version 2 specified. * Chih-Jen Chang : Added a timer to revert to IGMP V2 router * Tsu-Sheng Tsao if the specified time expired. * Alan Cox : Stop IGMP from 0.0.0.0 being accepted. * Alan Cox : Use GFP_ATOMIC in the right places. * Christian Daudt : igmp timer wasn't set for local group * memberships but was being deleted, * which caused a "del_timer() called * from %p with timer not initialized\n" * message (960131). * Christian Daudt : removed del_timer from * igmp_timer_expire function (960205). * Christian Daudt : igmp_heard_report now only calls * igmp_timer_expire if tm->running is * true (960216). * Malcolm Beattie : ttl comparison wrong in igmp_rcv made * igmp_heard_query never trigger. Expiry * miscalculation fixed in igmp_heard_query * and random() made to return unsigned to * prevent negative expiry times. * Alexey Kuznetsov: Wrong group leaving behaviour, backport * fix from pending 2.1.x patches. * Alan Cox: Forget to enable FDDI support earlier. * Alexey Kuznetsov: Fixed leaving groups on device down. * Alexey Kuznetsov: Accordance to igmp-v2-06 draft. * David L Stevens: IGMPv3 support, with help from * Vinay Kulkarni */ #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> #include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/arp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/sock.h> #include <net/checksum.h> #include <net/inet_common.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #endif #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) #define IGMP_INITIAL_REPORT_DELAY (1) /* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs! * IGMP specs require to report membership immediately after * joining a group, but we delay the first report by a * small interval. It seems more natural and still does not * contradict to specs provided this delay is small enough. */ #define IGMP_V1_SEEN(in_dev) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) static int unsolicited_report_interval(struct in_device *in_dev) { int interval_ms, interval_jiffies; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV2_UNSOLICITED_REPORT_INTERVAL); else /* v3 */ interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV3_UNSOLICITED_REPORT_INTERVAL); interval_jiffies = msecs_to_jiffies(interval_ms); /* _timer functions can't handle a delay of 0 jiffies so ensure * we always return a positive value. */ if (interval_jiffies <= 0) interval_jiffies = 1; return interval_jiffies; } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); #endif static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); static void ip_ma_put(struct ip_mc_list *im) { if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } } #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rcu_dereference(pmc->next_rcu)) #define for_each_pmc_rtnl(in_dev, pmc) \ for (pmc = rtnl_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { next = psf->sf_next; kfree(psf); psf = next; } } #ifdef CONFIG_IP_MULTICAST /* * Timer management */ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; spin_unlock_bh(&im->lock); } /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { int tv = get_random_u32_below(max_delay); im->tm_running = 1; if (refcount_inc_not_zero(&im->refcnt)) { if (mod_timer(&im->timer, jiffies + tv + 2)) ip_ma_put(im); } } static void igmp_gq_start_timer(struct in_device *in_dev) { int tv = get_random_u32_below(in_dev->mr_maxdelay); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && time_after_eq(exp, (in_dev->mr_gq_timer).expires)) return; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, exp)) in_dev_hold(in_dev); } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { int tv = get_random_u32_below(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (del_timer(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); im->tm_running = 1; spin_unlock_bh(&im->lock); return; } refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); } /* * Send an IGMP report. */ #define IGMP_SIZE (sizeof(struct igmphdr)+sizeof(struct iphdr)+4) static int is_in(struct ip_mc_list *pmc, struct ip_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; if (!(pmc->gsquery && !psf->sf_gsresp)) { if (pmc->sfmode == MCAST_INCLUDE) return 1; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == IGMPV3_MODE_IS_INCLUDE; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return 0; case IGMPV3_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; return psf->sf_count[MCAST_INCLUDE] != 0; case IGMPV3_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return 0; if (pmc->sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return 0; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case IGMPV3_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return 0; return (pmc->sfmode == MCAST_INCLUDE) ^ sdeleted; case IGMPV3_BLOCK_OLD_SOURCES: if (pmc->sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return 0; } static int igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct ip_sf_list *psf; int scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } /* source address selection per RFC 3376 section 4.2.13 */ static __be32 igmpv3_get_srcaddr(struct net_device *dev, const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); const struct in_ifaddr *ifa; if (!in_dev) return htonl(INADDR_ANY); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } return htonl(INADDR_ANY); } static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int size; size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; size >>= 1; if (size < 256) return NULL; } skb->priority = TC_PRIO_CONTROL; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) { kfree_skb(skb); return NULL; } skb_dst_set(skb, &rt->dst); skb->dev = dev; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); pip->version = 4; pip->ihl = (sizeof(struct iphdr)+4)>>2; pip->tos = 0xc0; pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); rcu_read_unlock(); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); pig = igmpv3_report_hdr(skb); pig->type = IGMPV3_HOST_MEMBERSHIP_REPORT; pig->resv1 = 0; pig->csum = 0; pig->resv2 = 0; pig->ngrec = 0; return skb; } static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) { return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc, type, gdel, sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; if (!skb) { skb = igmpv3_newpack(dev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->multiaddr; pih = igmpv3_report_hdr(skb); pih->ngrec = htons(ntohs(pih->ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV4_MIN_MTU) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || type == IGMPV3_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->tomb : &pmc->sources; if (!*psf_list) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pih && pih->ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); } } first = 1; psf_prev = NULL; for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; continue; } /* Based on RFC3376 5.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->crcount)) && (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(__be32) + first*sizeof(struct igmpv3_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *psf_list = psf->sf_next; kfree(psf); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) { igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->gsquery = 0; /* clear query state on report */ return skb; } static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } if (!skb) return 0; return igmpv3_sendpack(skb); } /* * remove zero-count source records from a source filter list */ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *ppsf = psf->sf_next; kfree(psf); } else psf_prev = psf; } } static void kfree_pmc(struct ip_mc_list *pmc) { ip_sf_list_clear_all(pmc->sources); ip_sf_list_clear_all(pmc->tomb); kfree(pmc); } static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0); skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) { type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } pmc->crcount--; if (pmc->crcount == 0) { igmpv3_clear_zeros(&pmc->tomb); igmpv3_clear_zeros(&pmc->sources); } } if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { if (pmc_prev) pmc_prev->next = pmc_next; else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); kfree_pmc(pmc); } else pmc_prev = pmc; } spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_ALLOW_NEW_SOURCES; } else { type = IGMPV3_ALLOW_NEW_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ /* filter mode changes */ if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) type = IGMPV3_CHANGE_TO_EXCLUDE; else type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); pmc->crcount--; } spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); if (!skb) return; (void) igmpv3_sendpack(skb); } static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, int type) { struct sk_buff *skb; struct iphdr *iph; struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; rt = ip_route_output_ports(net, &fl4, NULL, dst, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) return -1; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (!skb) { ip_rt_put(rt); return -1; } skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); iph->version = 4; iph->ihl = (sizeof(struct iphdr)+4)>>2; iph->tos = 0xc0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_gq_timer); in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); in_dev_put(in_dev); } static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); u32 mr_ifc_count; igmpv3_send_cr(in_dev); restart: mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); if (mr_ifc_count) { if (cmpxchg(&in_dev->mr_ifc_count, mr_ifc_count, mr_ifc_count - 1) != mr_ifc_count) goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } static void igmp_timer_expire(struct timer_list *t) { struct ip_mc_list *im = from_timer(im, t, timer); struct in_device *in_dev = im->interface; spin_lock(&im->lock); im->tm_running = 0; if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); im->reporter = 1; spin_unlock(&im->lock); if (IGMP_V1_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); else if (IGMP_V2_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); else igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); ip_ma_put(im); } /* mark EXCLUDE-mode sources */ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (srcs[i] == psf->sf_inaddr) { scount++; break; } } } pmc->gsquery = 0; if (scount == nsrcs) /* all sources excluded */ return 0; return 1; } static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; if (pmc->sfmode == MCAST_EXCLUDE) return igmp_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) if (srcs[i] == psf->sf_inaddr) { psf->sf_gsresp = 1; scount++; break; } } if (!scount) { pmc->gsquery = 0; return 0; } pmc->gsquery = 1; return 1; } /* return true if packet was dropped */ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } rcu_read_unlock(); return false; } /* return true if packet was dropped */ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int len) { struct igmphdr *ih = igmp_hdr(skb); struct igmpv3_query *ih3 = igmpv3_query_hdr(skb); struct ip_mc_list *im; __be32 group = ih->group; int max_delay; int mark = 0; struct net *net = dev_net(in_dev->dev); if (len == 8) { if (ih->code == 0) { /* Alas, old v1 router presents here. */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; } /* cancel the interface change timer */ WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ igmpv3_clear_delrec(in_dev); } else if (len < 12) { return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; group = 0; } else if (IGMP_V2_SEEN(in_dev)) { /* this is a v3 query with v2 queriers present; * Interpretation of the max_delay code is problematic here. * A real v2 host would use ih_code directly, while v3 has a * different encoding. We use the v3 encoding as more likely * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return true; ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) + ntohs(ih3->nsrcs)*sizeof(__be32))) return true; ih3 = igmpv3_query_hdr(skb); } max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently * received value was zero, use the default or statically * configured value. */ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: * The number of seconds represented by the [Query Response * Interval] must be less than the [Query Interval]. */ if (in_dev->mr_qri >= in_dev->mr_qi) in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ igmp_gq_start_timer(in_dev); return false; } /* mark sources to include, if group & source-specific */ mark = ih3->nsrcs != 0; } /* * - Start the timers in all of our membership records * that the query applies to for the interface on * which the query arrived excl. those that belong * to a "local" group (224.0.0.X) * - For timers already running check if they need to * be reset. * - Use the igmp->igmp_code field as the maximum * delay possible */ rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; else im->gsquery = mark; changed = !im->gsquery || igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); spin_unlock_bh(&im->lock); if (changed) igmp_mod_timer(im, max_delay); } rcu_read_unlock(); return false; } /* called in rcu_read_lock() section */ int igmp_rcv(struct sk_buff *skb) { /* This basically follows the spec line by line -- see RFC1112 */ struct igmphdr *ih; struct net_device *dev = skb->dev; struct in_device *in_dev; int len = skb->len; bool dropped = true; if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif); if (!dev) goto drop; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; if (skb_checksum_simple_validate(skb)) goto drop; ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_QUERY: dropped = igmp_heard_query(in_dev, skb, len); break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST) dropped = igmp_heard_report(in_dev, ih->group); break; case IGMP_PIM: #ifdef CONFIG_IP_PIMSM_V1 return pim_rcv_v1(skb); #endif case IGMPV3_HOST_MEMBERSHIP_REPORT: case IGMP_DVMRP: case IGMP_TRACE: case IGMP_HOST_LEAVE_MESSAGE: case IGMP_MTRACE: case IGMP_MTRACE_RESP: break; default: break; } drop: if (dropped) kfree_skb(skb); else consume_skb(skb); return 0; } #endif /* * Add a filter to a device */ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } /* * Remove a filter from a device */ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST /* * deleted ip_mc_list manipulation */ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); spin_lock_bh(&in_dev->mc_tomb_lock); pmc->next = in_dev->mc_tomb; in_dev->mc_tomb = pmc; spin_unlock_bh(&in_dev->mc_tomb_lock); } /* * restore ip_mc_list deleted records */ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) pmc_prev->next = pmc->next; else in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } /* * flush ip_mc_list deleted records */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; spin_lock_bh(&in_dev->mc_tomb_lock); pmc = in_dev->mc_tomb; in_dev->mc_tomb = NULL; spin_unlock_bh(&in_dev->mc_tomb_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } rcu_read_unlock(); } #endif static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); int reporter; #endif if (im->loaded) { im->loaded = 0; ip_mc_filter_del(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; igmp_stop_timer(im); if (!in_dev->dead) { if (IGMP_V1_SEEN(in_dev)) return; if (IGMP_V2_SEEN(in_dev)) { if (reporter) igmp_send_report(in_dev, im, IGMP_HOST_LEAVE_MESSAGE); return; } /* IGMPv3 */ igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } static void igmp_group_dropped(struct ip_mc_list *im) { __igmp_group_dropped(im, GFP_KERNEL); } static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); #endif if (im->loaded == 0) { im->loaded = 1; ip_mc_filter_add(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); spin_unlock_bh(&im->lock); return; } /* else, v3 */ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should * not send filter-mode change record as the mode should be from * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif } /* * Multicast list managers */ static u32 ip_mc_hash(const struct ip_mc_list *im) { return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG); } static void ip_mc_hash_add(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash; u32 hash; mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; rcu_assign_pointer(mc_hash[hash], im); return; } /* do not use a hash table for small number of items */ if (in_dev->mc_count < 4) return; mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG, GFP_KERNEL); if (!mc_hash) return; for_each_pmc_rtnl(in_dev, im) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; RCU_INIT_POINTER(mc_hash[hash], im); } rcu_assign_pointer(in_dev->mc_hash, mc_hash); } static void ip_mc_hash_remove(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash); struct ip_mc_list *aux; if (!mc_hash) return; mc_hash += ip_mc_hash(im); while ((aux = rtnl_dereference(*mc_hash)) != im) mc_hash = &aux->next_hash; *mc_hash = im->next_hash; } /* * A socket has joined a multicast group on device dev. */ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode, gfp_t gfp) { struct ip_mc_list *im; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } } im = kzalloc(sizeof(*im), gfp); if (!im) goto out; im->users = 1; im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); #endif im->next_rcu = in_dev->mc_list; in_dev->mc_count++; rcu_assign_pointer(in_dev->mc_list, im); ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); } EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) { const struct iphdr *iph; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) return -EINVAL; offset += ip_hdrlen(skb) - sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; len = skb_network_offset(skb) + ntohs(iph->tot_len); if (skb->len < len || len < offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct igmpv3_report); return ip_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ip_mc_check_igmp_query(struct sk_buff *skb) { unsigned int transport_len = ip_transport_len(skb); unsigned int len; /* IGMPv{1,2}? */ if (transport_len != sizeof(struct igmphdr)) { /* or IGMPv3? */ if (transport_len < sizeof(struct igmpv3_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct igmpv3_query); if (!ip_mc_may_pull(skb, len)) return -EINVAL; } /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer * all-systems destination addresses (224.0.0.1) for general queries */ if (!igmp_hdr(skb)->group && ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) return -EINVAL; return 0; } static int ip_mc_check_igmp_msg(struct sk_buff *skb) { switch (igmp_hdr(skb)->type) { case IGMP_HOST_LEAVE_MESSAGE: case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: return 0; case IGMPV3_HOST_MEMBERSHIP_REPORT: return ip_mc_check_igmp_reportv3(skb); case IGMP_HOST_MEMBERSHIP_QUERY: return ip_mc_check_igmp_query(skb); default: return -ENOMSG; } } static __sum16 ip_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_simple_validate(skb); } static int ip_mc_check_igmp_csum(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); unsigned int transport_len = ip_transport_len(skb); struct sk_buff *skb_chk; if (!ip_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ip_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); if (ret < 0) return ret; if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; ret = ip_mc_check_igmp_csum(skb); if (ret < 0) return ret; return ip_mc_check_igmp_msg(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); /* * Resend IGMP JOIN report; used by netdev notifier. */ static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches * must be notified immediately */ if (IGMP_V1_SEEN(in_dev)) type = IGMP_HOST_MEMBERSHIP_REPORT; else if (IGMP_V2_SEEN(in_dev)) type = IGMPV2_HOST_MEMBERSHIP_REPORT; else type = IGMPV3_HOST_MEMBERSHIP_REPORT; igmp_send_report(in_dev, im, type); } #endif } /* * A socket has left a multicast group on device dev */ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; ASSERT_RTNL(); for (ip = &in_dev->mc_list; (i = rtnl_dereference(*ip)) != NULL; ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); ip_mc_clear_src(i); if (!in_dev->dead) ip_rt_multicast_event(in_dev); ip_ma_put(i); return; } break; } } } EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ void ip_mc_unmap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; if (del_timer(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } #ifdef CONFIG_IP_MULTICAST static void ip_mc_reset(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) { } #endif void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); #endif ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } /* Device going up */ void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* * Device is about to be destroyed: clean up. */ void ip_mc_destroy_dev(struct in_device *in_dev) { struct ip_mc_list *i; ASSERT_RTNL(); /* Deactivate timers */ ip_mc_down(in_dev); #ifdef CONFIG_IP_MULTICAST igmpv3_clear_delrec(in_dev); #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; ip_mc_clear_src(i); ip_ma_put(i); } } /* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct net_device *dev = NULL; struct in_device *idev = NULL; if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); return idev; } if (imr->imr_address.s_addr) { dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; } if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, 0, 0, 0); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); } } if (dev) { imr->imr_ifindex = dev->ifindex; idev = __in_dev_get_rtnl(dev); } return idev; } /* * Join a socket to a group */ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ if (psf_prev) psf_prev->sf_next = psf->sf_next; else pmc->sources = psf->sf_next; #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; } else #endif kfree(psf); } return rv; } #ifndef CONFIG_IP_MULTICAST #define igmp_ifc_event(x) do { } while (0) #endif static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int changerec = 0; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif if (!delta) { err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; pmc->sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->sfmode == MCAST_EXCLUDE && pmc->sfcount[MCAST_EXCLUDE] == 0 && pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { igmp_ifc_event(pmc->interface); #endif } out_unlock: spin_unlock_bh(&pmc->lock); return err; } /* * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; } else pmc->sources = psf; } psf->sf_count[sfmode]++; if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } return 0; } #ifdef CONFIG_IP_MULTICAST static void sf_markstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } static int sf_setstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf, *dpsf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; int qrv = pmc->interface->mr_qrv; int new_in, rv; rv = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { if (prev) prev->sf_next = dpsf->sf_next; else pmc->tomb = dpsf->sf_next; kfree(dpsf); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ dpsf->sf_next = pmc->tomb; pmc->tomb = dpsf; } dpsf->sf_crcount = qrv; rv++; } } return rv; } #endif /* * Add multicast source filter list to the interface list */ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int isexclude; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) pmc->sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->sfcount[sfmode]--; for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif /* filter mode change */ if (pmc->sfcount[MCAST_EXCLUDE]) pmc->sfmode = MCAST_EXCLUDE; else if (pmc->sfcount[MCAST_INCLUDE]) pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { igmp_ifc_event(in_dev); #endif } spin_unlock_bh(&pmc->lock); return err; } static void ip_mc_clear_src(struct ip_mc_list *pmc) { struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; pmc->tomb = NULL; sources = pmc->sources; pmc->sources = NULL; pmc->sfmode = MCAST_EXCLUDE; pmc->sfcount[MCAST_INCLUDE] = 0; pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); ip_sf_list_clear_all(sources); } /* Join a multicast group */ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; int err; ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRINUSE; ifindex = imr->imr_ifindex; for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; count++; } err = -ENOBUFS; if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; } /* Join ASM (Any-Source Multicast) group */ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ip_mc_join_group); /* Join SSM (Source-Specific Multicast) group */ int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { return __ip_mc_join_group(sk, imr, mode); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psf, sl_addr, psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; ASSERT_RTNL(); in_dev = ip_mc_find_dev(net, imr); if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) { ret = -ENODEV; goto out; } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { if (iml->multi.imr_ifindex != ifindex) continue; } else if (imr->imr_address.s_addr && imr->imr_address.s_addr != iml->multi.imr_address.s_addr) continue; (void) ip_mc_leave_src(sk, iml, in_dev); *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } out: return ret; } EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex) { int err; struct ip_mreqn imr; __be32 addr = mreqs->imr_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 0, NULL, 0); ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip_sf_socklist *newpsl; int count = IP_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv == 0) /* address already there is an error */ goto done; for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; err = 0; /* update the interface list */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { int err = 0; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; if (msf->imsf_fmode != MCAST_INCLUDE && msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (msf->imsf_fmode == MCAST_INCLUDE && msf->imsf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (msf->imsf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, msf->imsf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; memcpy(newpsl->sl_addr, msf->imsf_slist_flex, flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } } else { newpsl = NULL; (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen) { int err, len, count, copycount, msf_size; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); if (!psl) { count = 0; } else { count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; msf_size = IP_MSFILTER_SIZE(copycount); if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) || copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && copy_to_sockptr_offset(optval, offsetof(struct ip_msfilter, imsf_slist_flex), psl->sl_addr, len)) return -EFAULT; return 0; done: return err; } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { int i, count, copycount; struct sockaddr_in *psin; __be32 addr; struct ip_mc_socklist *pmc; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; ASSERT_RTNL(); psin = (struct sockaddr_in *)&gsf->gf_group; if (psin->sin_family != AF_INET) return -EINVAL; addr = psin->sin_addr.s_addr; if (!ipv4_is_multicast(addr)) return -EINVAL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif, int sdif) { const struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; struct ip_sf_socklist *psl; int i; int ret; ret = 1; if (!ipv4_is_multicast(loc_addr)) goto out; rcu_read_lock(); for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && (pmc->multi.imr_ifindex == dif || (sdif && pmc->multi.imr_ifindex == sdif))) break; } ret = inet_test_bit(MC_ALL, sk); if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } ret = 0; if (pmc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) goto unlock; if (pmc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) goto unlock; ret = 1; unlock: rcu_read_unlock(); out: return ret; } /* * A socket is closing. */ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct net *net = sock_net(sk); if (!inet->mc_list) return; rtnl_lock(); while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); } rtnl_unlock(); } /* called with rcu_read_lock() */ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; struct ip_sf_list *psf; int rv = 0; mc_hash = rcu_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG); for (im = rcu_dereference(mc_hash[hash]); im != NULL; im = rcu_dereference(im->next_hash)) { if (im->multiaddr == mc_addr) break; } } else { for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } } if (im && proto == IPPROTO_IGMP) { rv = 1; } else if (im) { if (src_addr) { spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } return rv; } #if defined(CONFIG_PROC_FS) struct igmp_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *in_dev; }; #define igmp_mc_seq_private(seq) ((struct igmp_mc_iter_state *)(seq)->private) static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_mc_list *im = NULL; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } } return im; } static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = rcu_dereference(im->next_rcu); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; im = rcu_dereference(state->in_dev->mc_list); } return im; } static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ip_mc_list *im = igmp_mc_get_first(seq); if (im) while (pos && (im = igmp_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_mc_list *im; if (v == SEQ_START_TOKEN) im = igmp_mc_get_first(seq); else im = igmp_mc_get_next(seq, v); ++*pos; return im; } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Idx\tDevice : Count Querier\tGroup Users Timer\tReporter\n"); else { struct ip_mc_list *im = v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; long delta; #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : "V3"; #else querier = "NONE"; #endif if (rcu_access_pointer(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, im->tm_running, im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; } static const struct seq_operations igmp_mc_seq_ops = { .start = igmp_mc_seq_start, .next = igmp_mc_seq_next, .stop = igmp_mc_seq_stop, .show = igmp_mc_seq_show, }; struct igmp_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *idev; struct ip_mc_list *im; }; #define igmp_mcf_seq_private(seq) ((struct igmp_mcf_iter_state *)(seq)->private) static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_sf_list *psf = NULL; struct ip_mc_list *im = NULL; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; if (likely(psf)) { state->im = im; state->idev = idev; break; } spin_unlock_bh(&im->lock); } } return psf; } static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_list *psf) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); psf = psf->sf_next; while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); psf = state->im->sources; } out: return psf; } static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip_sf_list *psf = igmp_mcf_get_first(seq); if (psf) while (pos && (psf = igmp_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp_mcf_get_first(seq); else psf = igmp_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) { struct ip_sf_list *psf = v; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device MCA SRC INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s 0x%08x " "0x%08x %6lu %6lu\n", state->dev->ifindex, state->dev->name, ntohl(state->im->multiaddr), ntohl(psf->sf_inaddr), psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp_mcf_seq_ops = { .start = igmp_mcf_seq_start, .next = igmp_mcf_seq_next, .stop = igmp_mcf_seq_stop, .show = igmp_mcf_seq_show, }; static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; int err; pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops, sizeof(struct igmp_mc_iter_state)); if (!pde) goto out_igmp; pde = proc_create_net("mcfilter", 0444, net->proc_net, &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); if (!pde) goto out_mcfilter; err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, SOCK_DGRAM, 0, net); if (err < 0) { pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", err); goto out_sock; } return 0; out_sock: remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; #endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; switch (event) { case NETDEV_RESEND_IGMP: in_dev = __in_dev_get_rtnl(dev); if (in_dev) ip_mc_rejoin_groups(in_dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; int __init igmp_mc_init(void) { #if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); if (err) return err; err = register_netdevice_notifier(&igmp_notifier); if (err) goto reg_notif_fail; return 0; reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; #else return register_netdevice_notifier(&igmp_notifier); #endif } |
| 4298 3453 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Kernel Electric-Fence (KFENCE). For more info please see * Documentation/dev-tools/kfence.rst. * * Copyright (C) 2020, Google LLC. */ #ifndef MM_KFENCE_KFENCE_H #define MM_KFENCE_KFENCE_H #include <linux/mm.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/types.h> #include "../slab.h" /* for struct kmem_cache */ /* * Get the canary byte pattern for @addr. Use a pattern that varies based on the * lower 3 bits of the address, to detect memory corruptions with higher * probability, where similar constants are used. */ #define KFENCE_CANARY_PATTERN_U8(addr) ((u8)0xaa ^ (u8)((unsigned long)(addr) & 0x7)) /* * Define a continuous 8-byte canary starting from a multiple of 8. The canary * of each byte is only related to the lowest three bits of its address, so the * canary of every 8 bytes is the same. 64-bit memory can be filled and checked * at a time instead of byte by byte to improve performance. */ #define KFENCE_CANARY_PATTERN_U64 ((u64)0xaaaaaaaaaaaaaaaa ^ (u64)(le64_to_cpu(0x0706050403020100))) /* Maximum stack depth for reports. */ #define KFENCE_STACK_DEPTH 64 /* KFENCE object states. */ enum kfence_object_state { KFENCE_OBJECT_UNUSED, /* Object is unused. */ KFENCE_OBJECT_ALLOCATED, /* Object is currently allocated. */ KFENCE_OBJECT_FREED, /* Object was allocated, and then freed. */ }; /* Alloc/free tracking information. */ struct kfence_track { pid_t pid; int cpu; u64 ts_nsec; int num_stack_entries; unsigned long stack_entries[KFENCE_STACK_DEPTH]; }; /* KFENCE metadata per guarded allocation. */ struct kfence_metadata { struct list_head list; /* Freelist node; access under kfence_freelist_lock. */ struct rcu_head rcu_head; /* For delayed freeing. */ /* * Lock protecting below data; to ensure consistency of the below data, * since the following may execute concurrently: __kfence_alloc(), * __kfence_free(), kfence_handle_page_fault(). However, note that we * cannot grab the same metadata off the freelist twice, and multiple * __kfence_alloc() cannot run concurrently on the same metadata. */ raw_spinlock_t lock; /* The current state of the object; see above. */ enum kfence_object_state state; /* * Allocated object address; cannot be calculated from size, because of * alignment requirements. * * Invariant: ALIGN_DOWN(addr, PAGE_SIZE) is constant. */ unsigned long addr; /* * The size of the original allocation. */ size_t size; /* * The kmem_cache cache of the last allocation; NULL if never allocated * or the cache has already been destroyed. */ struct kmem_cache *cache; /* * In case of an invalid access, the page that was unprotected; we * optimistically only store one address. */ unsigned long unprotected_page; /* Allocation and free stack information. */ struct kfence_track alloc_track; struct kfence_track free_track; /* For updating alloc_covered on frees. */ u32 alloc_stack_hash; #ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif }; #define KFENCE_METADATA_SIZE PAGE_ALIGN(sizeof(struct kfence_metadata) * \ CONFIG_KFENCE_NUM_OBJECTS) extern struct kfence_metadata *kfence_metadata; static inline struct kfence_metadata *addr_to_metadata(unsigned long addr) { long index; /* The checks do not affect performance; only called from slow-paths. */ if (!is_kfence_address((void *)addr)) return NULL; /* * May be an invalid index if called with an address at the edge of * __kfence_pool, in which case we would report an "invalid access" * error. */ index = (addr - (unsigned long)__kfence_pool) / (PAGE_SIZE * 2) - 1; if (index < 0 || index >= CONFIG_KFENCE_NUM_OBJECTS) return NULL; return &kfence_metadata[index]; } /* KFENCE error types for report generation. */ enum kfence_error_type { KFENCE_ERROR_OOB, /* Detected a out-of-bounds access. */ KFENCE_ERROR_UAF, /* Detected a use-after-free access. */ KFENCE_ERROR_CORRUPTION, /* Detected a memory corruption on free. */ KFENCE_ERROR_INVALID, /* Invalid access of unknown type. */ KFENCE_ERROR_INVALID_FREE, /* Invalid free. */ }; void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *regs, const struct kfence_metadata *meta, enum kfence_error_type type); void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *meta); #endif /* MM_KFENCE_KFENCE_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __FIRMWARE_LOADER_H #define __FIRMWARE_LOADER_H #include <linux/bitops.h> #include <linux/firmware.h> #include <linux/types.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/completion.h> /** * enum fw_opt - options to control firmware loading behaviour * * @FW_OPT_UEVENT: Enables the fallback mechanism to send a kobject uevent * when the firmware is not found. Userspace is in charge to load the * firmware using the sysfs loading facility. * @FW_OPT_NOWAIT: Used to describe the firmware request is asynchronous. * @FW_OPT_USERHELPER: Enable the fallback mechanism, in case the direct * filesystem lookup fails at finding the firmware. For details refer to * firmware_fallback_sysfs(). * @FW_OPT_NO_WARN: Quiet, avoid printing warning messages. * @FW_OPT_NOCACHE: Disables firmware caching. Firmware caching is used to * cache the firmware upon suspend, so that upon resume races against the * firmware file lookup on storage is avoided. Used for calls where the * file may be too big, or where the driver takes charge of its own * firmware caching mechanism. * @FW_OPT_NOFALLBACK_SYSFS: Disable the sysfs fallback mechanism. Takes * precedence over &FW_OPT_UEVENT and &FW_OPT_USERHELPER. * @FW_OPT_FALLBACK_PLATFORM: Enable fallback to device fw copy embedded in * the platform's main firmware. If both this fallback and the sysfs * fallback are enabled, then this fallback will be tried first. * @FW_OPT_PARTIAL: Allow partial read of firmware instead of needing to read * entire file. */ enum fw_opt { FW_OPT_UEVENT = BIT(0), FW_OPT_NOWAIT = BIT(1), FW_OPT_USERHELPER = BIT(2), FW_OPT_NO_WARN = BIT(3), FW_OPT_NOCACHE = BIT(4), FW_OPT_NOFALLBACK_SYSFS = BIT(5), FW_OPT_FALLBACK_PLATFORM = BIT(6), FW_OPT_PARTIAL = BIT(7), }; enum fw_status { FW_STATUS_UNKNOWN, FW_STATUS_LOADING, FW_STATUS_DONE, FW_STATUS_ABORTED, }; /* * Concurrent request_firmware() for the same firmware need to be * serialized. struct fw_state is simple state machine which hold the * state of the firmware loading. */ struct fw_state { struct completion completion; enum fw_status status; }; struct fw_priv { struct kref ref; struct list_head list; struct firmware_cache *fwc; struct fw_state fw_st; void *data; size_t size; size_t allocated_size; size_t offset; u32 opt_flags; #ifdef CONFIG_FW_LOADER_PAGED_BUF bool is_paged_buf; struct page **pages; int nr_pages; int page_array_size; #endif #ifdef CONFIG_FW_LOADER_USER_HELPER bool need_uevent; struct list_head pending_list; #endif const char *fw_name; }; extern struct mutex fw_lock; extern struct firmware_cache fw_cache; extern bool fw_load_abort_all; static inline bool __fw_state_check(struct fw_priv *fw_priv, enum fw_status status) { struct fw_state *fw_st = &fw_priv->fw_st; return fw_st->status == status; } static inline int __fw_state_wait_common(struct fw_priv *fw_priv, long timeout) { struct fw_state *fw_st = &fw_priv->fw_st; long ret; ret = wait_for_completion_killable_timeout(&fw_st->completion, timeout); if (ret != 0 && fw_st->status == FW_STATUS_ABORTED) return -ENOENT; if (!ret) return -ETIMEDOUT; return ret < 0 ? ret : 0; } static inline void __fw_state_set(struct fw_priv *fw_priv, enum fw_status status) { struct fw_state *fw_st = &fw_priv->fw_st; WRITE_ONCE(fw_st->status, status); if (status == FW_STATUS_DONE || status == FW_STATUS_ABORTED) { #ifdef CONFIG_FW_LOADER_USER_HELPER /* * Doing this here ensures that the fw_priv is deleted from * the pending list in all abort/done paths. */ list_del_init(&fw_priv->pending_list); #endif complete_all(&fw_st->completion); } } static inline void fw_state_aborted(struct fw_priv *fw_priv) { __fw_state_set(fw_priv, FW_STATUS_ABORTED); } static inline bool fw_state_is_aborted(struct fw_priv *fw_priv) { return __fw_state_check(fw_priv, FW_STATUS_ABORTED); } static inline void fw_state_start(struct fw_priv *fw_priv) { __fw_state_set(fw_priv, FW_STATUS_LOADING); } static inline void fw_state_done(struct fw_priv *fw_priv) { __fw_state_set(fw_priv, FW_STATUS_DONE); } static inline bool fw_state_is_done(struct fw_priv *fw_priv) { return __fw_state_check(fw_priv, FW_STATUS_DONE); } static inline bool fw_state_is_loading(struct fw_priv *fw_priv) { return __fw_state_check(fw_priv, FW_STATUS_LOADING); } int alloc_lookup_fw_priv(const char *fw_name, struct firmware_cache *fwc, struct fw_priv **fw_priv, void *dbuf, size_t size, size_t offset, u32 opt_flags); int assign_fw(struct firmware *fw, struct device *device); void free_fw_priv(struct fw_priv *fw_priv); void fw_state_init(struct fw_priv *fw_priv); #ifdef CONFIG_FW_LOADER bool firmware_is_builtin(const struct firmware *fw); bool firmware_request_builtin_buf(struct firmware *fw, const char *name, void *buf, size_t size); #else /* module case */ static inline bool firmware_is_builtin(const struct firmware *fw) { return false; } static inline bool firmware_request_builtin_buf(struct firmware *fw, const char *name, void *buf, size_t size) { return false; } #endif #ifdef CONFIG_FW_LOADER_PAGED_BUF void fw_free_paged_buf(struct fw_priv *fw_priv); int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed); int fw_map_paged_buf(struct fw_priv *fw_priv); bool fw_is_paged_buf(struct fw_priv *fw_priv); #else static inline void fw_free_paged_buf(struct fw_priv *fw_priv) {} static inline int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; } static inline int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; } static inline bool fw_is_paged_buf(struct fw_priv *fw_priv) { return false; } #endif #endif /* __FIRMWARE_LOADER_H */ |
| 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM smc #if !defined(_TRACE_SMC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SMC_H #include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/tracepoint.h> #include <net/ipv6.h> #include "smc.h" #include "smc_core.h" TRACE_EVENT(smc_switch_to_fallback, TP_PROTO(const struct smc_sock *smc, int fallback_rsn), TP_ARGS(smc, fallback_rsn), TP_STRUCT__entry( __field(const void *, sk) __field(const void *, clcsk) __field(u64, net_cookie) __field(int, fallback_rsn) ), TP_fast_assign( const struct sock *sk = &smc->sk; const struct sock *clcsk = smc->clcsock->sk; __entry->sk = sk; __entry->clcsk = clcsk; __entry->net_cookie = sock_net(sk)->net_cookie; __entry->fallback_rsn = fallback_rsn; ), TP_printk("sk=%p clcsk=%p net=%llu fallback_rsn=%d", __entry->sk, __entry->clcsk, __entry->net_cookie, __entry->fallback_rsn) ); DECLARE_EVENT_CLASS(smc_msg_event, TP_PROTO(const struct smc_sock *smc, size_t len), TP_ARGS(smc, len), TP_STRUCT__entry( __field(const void *, smc) __field(u64, net_cookie) __field(size_t, len) __string(name, smc->conn.lnk->ibname) ), TP_fast_assign( const struct sock *sk = &smc->sk; __entry->smc = smc; __entry->net_cookie = sock_net(sk)->net_cookie; __entry->len = len; __assign_str(name, smc->conn.lnk->ibname); ), TP_printk("smc=%p net=%llu len=%zu dev=%s", __entry->smc, __entry->net_cookie, __entry->len, __get_str(name)) ); DEFINE_EVENT(smc_msg_event, smc_tx_sendmsg, TP_PROTO(const struct smc_sock *smc, size_t len), TP_ARGS(smc, len) ); DEFINE_EVENT(smc_msg_event, smc_rx_recvmsg, TP_PROTO(const struct smc_sock *smc, size_t len), TP_ARGS(smc, len) ); TRACE_EVENT(smcr_link_down, TP_PROTO(const struct smc_link *lnk, void *location), TP_ARGS(lnk, location), TP_STRUCT__entry( __field(const void *, lnk) __field(const void *, lgr) __field(u64, net_cookie) __field(int, state) __string(name, lnk->ibname) __field(void *, location) ), TP_fast_assign( const struct smc_link_group *lgr = lnk->lgr; __entry->lnk = lnk; __entry->lgr = lgr; __entry->net_cookie = lgr->net->net_cookie; __entry->state = lnk->state; __assign_str(name, lnk->ibname); __entry->location = location; ), TP_printk("lnk=%p lgr=%p net=%llu state=%d dev=%s location=%pS", __entry->lnk, __entry->lgr, __entry->net_cookie, __entry->state, __get_str(name), __entry->location) ); #endif /* _TRACE_SMC_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE smc_tracepoint #include <trace/define_trace.h> |
| 21 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct skb_array' datastructure. * * Author: * Michael S. Tsirkin <mst@redhat.com> * * Copyright (C) 2016 Red Hat, Inc. * * Limited-size FIFO of skbs. Can be used more or less whenever * sk_buff_head can be used, except you need to know the queue size in * advance. * Implemented as a type-safe wrapper around ptr_ring. */ #ifndef _LINUX_SKB_ARRAY_H #define _LINUX_SKB_ARRAY_H 1 #ifdef __KERNEL__ #include <linux/ptr_ring.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> #endif struct skb_array { struct ptr_ring ring; }; /* Might be slightly faster than skb_array_full below, but callers invoking * this in a loop must use a compiler barrier, for example cpu_relax(). */ static inline bool __skb_array_full(struct skb_array *a) { return __ptr_ring_full(&a->ring); } static inline bool skb_array_full(struct skb_array *a) { return ptr_ring_full(&a->ring); } static inline int skb_array_produce(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce(&a->ring, skb); } static inline int skb_array_produce_irq(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_irq(&a->ring, skb); } static inline int skb_array_produce_bh(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_bh(&a->ring, skb); } static inline int skb_array_produce_any(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_any(&a->ring, skb); } /* Might be slightly faster than skb_array_empty below, but only safe if the * array is never resized. Also, callers invoking this in a loop must take care * to use a compiler barrier, for example cpu_relax(). */ static inline bool __skb_array_empty(struct skb_array *a) { return __ptr_ring_empty(&a->ring); } static inline struct sk_buff *__skb_array_peek(struct skb_array *a) { return __ptr_ring_peek(&a->ring); } static inline bool skb_array_empty(struct skb_array *a) { return ptr_ring_empty(&a->ring); } static inline bool skb_array_empty_bh(struct skb_array *a) { return ptr_ring_empty_bh(&a->ring); } static inline bool skb_array_empty_irq(struct skb_array *a) { return ptr_ring_empty_irq(&a->ring); } static inline bool skb_array_empty_any(struct skb_array *a) { return ptr_ring_empty_any(&a->ring); } static inline struct sk_buff *__skb_array_consume(struct skb_array *a) { return __ptr_ring_consume(&a->ring); } static inline struct sk_buff *skb_array_consume(struct skb_array *a) { return ptr_ring_consume(&a->ring); } static inline int skb_array_consume_batched(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_irq(struct skb_array *a) { return ptr_ring_consume_irq(&a->ring); } static inline int skb_array_consume_batched_irq(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_irq(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_any(struct skb_array *a) { return ptr_ring_consume_any(&a->ring); } static inline int skb_array_consume_batched_any(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_any(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_bh(struct skb_array *a) { return ptr_ring_consume_bh(&a->ring); } static inline int skb_array_consume_batched_bh(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_bh(&a->ring, (void **)array, n); } static inline int __skb_array_len_with_tag(struct sk_buff *skb) { if (likely(skb)) { int len = skb->len; if (skb_vlan_tag_present(skb)) len += VLAN_HLEN; return len; } else { return 0; } } static inline int skb_array_peek_len(struct skb_array *a) { return PTR_RING_PEEK_CALL(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_irq(struct skb_array *a) { return PTR_RING_PEEK_CALL_IRQ(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_bh(struct skb_array *a) { return PTR_RING_PEEK_CALL_BH(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_any(struct skb_array *a) { return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_init(&a->ring, size, gfp); } static void __skb_array_destroy_skb(void *ptr) { kfree_skb(ptr); } static inline void skb_array_unconsume(struct skb_array *a, struct sk_buff **skbs, int n) { ptr_ring_unconsume(&a->ring, (void **)skbs, n, __skb_array_destroy_skb); } static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } static inline int skb_array_resize_multiple(struct skb_array **rings, int nrings, unsigned int size, gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); return ptr_ring_resize_multiple((struct ptr_ring **)rings, nrings, size, gfp, __skb_array_destroy_skb); } static inline void skb_array_cleanup(struct skb_array *a) { ptr_ring_cleanup(&a->ring, __skb_array_destroy_skb); } #endif /* _LINUX_SKB_ARRAY_H */ |
| 27 27 27 6 6 6 1 4 2 6 6 6 5 1 4 6 6 6 6 6 21 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Generic INET6 transport hashtables * * Authors: Lotsa people, from code originally in tcp, generalised here * by Arnaldo Carvalho de Melo <acme@mandriva.com> */ #include <linux/module.h> #include <linux/random.h> #include <net/addrconf.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/secure_seq.h> #include <net/ip.h> #include <net/sock_reuseport.h> u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { static u32 inet6_ehash_secret __read_mostly; static u32 ipv6_hash_secret __read_mostly; u32 lhash, fhash; net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); } EXPORT_SYMBOL_GPL(inet6_ehashfn); /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM * * The sockhash lock must be held as a reader here. */ struct sock *__inet6_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif) { struct sock *sk; const struct hlist_nulls_node *node; const __portpair ports = INET_COMBINED_PORTS(sport, hnum); /* Optimize here for direct hit, only listening connections can * have wildcards anyways. */ unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport); unsigned int slot = hash & hashinfo->ehash_mask; struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) continue; if (!inet6_match(net, sk, saddr, daddr, ports, dif, sdif)) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!inet6_match(net, sk, saddr, daddr, ports, dif, sdif))) { sock_gen_put(sk); goto begin; } goto found; } if (get_nulls_value(node) != slot) goto begin; out: sk = NULL; found: return sk; } EXPORT_SYMBOL(__inet6_lookup_established); static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const struct in6_addr *daddr, const int dif, const int sdif) { int score = -1; if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && sk->sk_family == PF_INET6) { if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return -1; score = sk->sk_bound_dev_if ? 2 : 1; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; } /** * inet6_lookup_reuseport() - execute reuseport logic on AF_INET6 socket if necessary. * @net: network namespace. * @sk: AF_INET6 socket, must be in TCP_LISTEN state for TCP or TCP_CLOSE for UDP. * @skb: context for a potential SK_REUSEPORT program. * @doff: header offset. * @saddr: source address. * @sport: source port. * @daddr: destination address. * @hnum: destination port in host byte order. * @ehashfn: hash function used to generate the fallback hash. * * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, inet6_ehashfn_t *ehashfn) { struct sock *reuse_sk = NULL; u32 phash; if (sk->sk_reuseport) { phash = INDIRECT_CALL_INET(ehashfn, udp6_ehashfn, inet6_ehashfn, net, daddr, hnum, saddr, sport); reuse_sk = reuseport_select_sock(sk, phash, skb, doff); } return reuse_sk; } EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ static struct sock *inet6_lhash2_lookup(struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { struct sock *sk, *result = NULL; struct hlist_nulls_node *node; int score, hiscore = 0; sk_nulls_for_each_rcu(sk, node, &ilb2->nulls_head) { score = compute_score(sk, net, hnum, daddr, dif, sdif); if (score > hiscore) { result = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, inet6_ehashfn); if (result) return result; result = sk; hiscore = score; } } return result; } struct sock *inet6_lookup_run_sk_lookup(struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool no_reuseport; no_reuseport = bpf_sk_lookup_run_v6(net, protocol, saddr, sport, daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, hnum, ehashfn); if (reuse_sk) sk = reuse_sk; return sk; } EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { struct inet_listen_hashbucket *ilb2; struct sock *result = NULL; unsigned int hash2; /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled) && hashinfo == net->ipv4.tcp_death_row.hashinfo) { result = inet6_lookup_run_sk_lookup(net, IPPROTO_TCP, skb, doff, saddr, sport, daddr, hnum, dif, inet6_ehashfn); if (result) goto done; } hash2 = ipv6_portaddr_hash(net, daddr, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet6_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, daddr, hnum, dif, sdif); if (result) goto done; /* Lookup lhash2 with in6addr_any */ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet6_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, &in6addr_any, hnum, dif, sdif); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(inet6_lookup_listener); struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif) { struct sock *sk; bool refcounted; sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif, 0, &refcounted); if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } EXPORT_SYMBOL_GPL(inet6_lookup); static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk, const __u16 lport, struct inet_timewait_sock **twp) { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; const struct in6_addr *saddr = &sk->sk_v6_daddr; const int dif = sk->sk_bound_dev_if; struct net *net = sock_net(sk); const int sdif = l3mdev_master_ifindex_by_index(net, dif); const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; spin_lock(lock); sk_nulls_for_each(sk2, node, &head->chain) { if (sk2->sk_hash != hash) continue; if (likely(inet6_match(net, sk2, saddr, daddr, ports, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) break; } goto not_unique; } } /* Must record num and sport now. Otherwise we will see * in hash table socket with a funny identity. */ inet->inet_num = lport; inet->inet_sport = htons(lport); sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { sk_nulls_del_node_init_rcu((struct sock *)tw); __NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule_put(tw); } return 0; not_unique: spin_unlock(lock); return -EADDRNOTAVAIL; } static u64 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_dport); } int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet6_sk_port_offset(sk); return __inet_hash_connect(death_row, sk, port_offset, __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); int inet6_hash(struct sock *sk) { int err = 0; if (sk->sk_state != TCP_CLOSE) err = __inet_hash(sk, NULL); return err; } EXPORT_SYMBOL_GPL(inet6_hash); |
| 107 83 25 25 4 4 4 4 4 2 23 67 68 68 4 52 52 11 41 52 52 8 48 5 4 10 55 55 55 55 84 44 55 55 55 55 22 3 19 1 11 11 1 10 28 26 2 21 21 1 1 10 29 29 1 27 26 23 8 7 2 2 19 21 3 2 22 3 2 45 1 10 1 3 36 16 9 15 23 23 23 23 134 134 69 93 41 4 133 6 1 1 3 1 4 1 3 4 109 108 109 96 14 109 175 86 26 4 14 67 10 21 85 20 6 99 99 99 99 99 99 99 31 1 62 3 1 2 65 5 60 2 4 1 1 115 51 7 2 151 11 44 113 89 68 149 149 2 8 36 73 24 3 1 44 94 136 135 4 134 80 28 28 100 6 2 101 64 172 172 56 56 56 56 56 56 56 56 56 45 10 55 80 80 64 13 75 75 16 1 1 10 10 3 9 2 2 8 2 6 4 2 3 1 4 4 8 1 1 56 107 1 28 1 3 1 1 3 10 1 1 1 1 1 1 2 1 1 1 3 1 1 4 1 1 2 1 1 2 2 8 1 6 6 1 1 1 31 1 29 1 1 1 1 1 1 1 1 6 1 1 2 2132 2132 2132 111 8 35 84 2132 135 133 1 9 9 2 1 1 7 1 4 5 5 1 4 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PACKET - implements raw packet sockets. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Alan Cox : verify_area() now used correctly * Alan Cox : new skbuff lists, look ma no backlogs! * Alan Cox : tidied skbuff lists. * Alan Cox : Now uses generic datagram routines I * added. Also fixed the peek/read crash * from all old Linux datagram code. * Alan Cox : Uses the improved datagram code. * Alan Cox : Added NULL's for socket options. * Alan Cox : Re-commented the code. * Alan Cox : Use new kernel side addressing * Rob Janssen : Correct MTU usage. * Dave Platt : Counter leaks caused by incorrect * interrupt locking and some slightly * dubious gcc output. Can you read * compiler: it said _VOLATILE_ * Richard Kooijman : Timestamp fixes. * Alan Cox : New buffers. Use sk->mac.raw. * Alan Cox : sendmsg/recvmsg support. * Alan Cox : Protocol setting support * Alexey Kuznetsov : Untied from IPv4 stack. * Cyrus Durgin : Fixed kerneld for kmod. * Michal Ostrowski : Module initialization cleanup. * Ulises Alonso : Frame number limit removal and * packet_set_ring memory leak. * Eric Biederman : Allow for > 8 byte hardware addresses. * The convention is that longer addresses * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. * Johann Baudy : Added TX RING. * Chetan Loke : Implemented TPACKET_V3 block abstraction * layer. * Copyright (C) 2011, <lokec@ccs.neu.edu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/if_vlan.h> #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> #include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif #include <linux/bpf.h> #include <net/compat.h> #include <linux/netfilter_netdev.h> #include "internal.h" /* Assumptions: - If the device has no dev->header_ops->create, there is no LL header visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. For example, a WiFi driver pretending to be an Ethernet driver should set its hard_header_len to be the Ethernet header length, and set its needed_headroom to be (the real WiFi header length - the fake Ethernet header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. On transmit: ------------ dev_has_header(dev) == true mac_header -> ll header data -> ll header dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data We should set network_header on output to the correct position, packet classifier depends on it. */ /* Private packet socket structures. */ /* identical to struct packet_mreq except it has * a longer address field. */ struct packet_mreq_max { int mr_ifindex; unsigned short mr_type; unsigned short mr_alen; unsigned char mr_address[MAX_ADDR_LEN]; }; union tpacket_uhdr { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; struct tpacket3_hdr *h3; void *raw; }; static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); #define V3_ALIGNMENT (8) #define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) #define BLK_PLUS_PRIV(sz_of_priv) \ (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT)) #define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status) #define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts) #define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt) #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status); static void packet_increment_head(struct packet_ring_buffer *buff); static int prb_curr_blk_in_use(struct tpacket_block_desc *); static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, struct packet_sock *); static void prb_retire_current_block(struct tpacket_kbdq_core *, struct packet_sock *, unsigned int status); static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); static void prb_retire_rx_blk_timer_expired(struct timer_list *); static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { struct sockaddr_pkt pkt; union { /* Trick: alias skb original length with * ll.sll_family and ll.protocol in order * to save room. */ unsigned int origlen; struct sockaddr_ll ll; }; } sa; }; #define vio_le() virtio_legacy_is_little_endian() #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) #define GET_PBLOCK_DESC(x, bid) \ ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer)) #define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \ ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer)) #define GET_NEXT_PRB_BLK_NUM(x) \ (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \ ((x)->kactive_blk_num+1) : 0) static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); #ifdef CONFIG_NETFILTER_EGRESS static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) { struct sk_buff *next, *head = NULL, *tail; int rc; rcu_read_lock(); for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); if (!nf_hook_egress(skb, &rc, skb->dev)) continue; if (!head) head = skb; else tail->next = skb; tail = skb; } rcu_read_unlock(); return head; } #endif static int packet_xmit(const struct packet_sock *po, struct sk_buff *skb) { if (!packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS)) return dev_queue_xmit(skb); #ifdef CONFIG_NETFILTER_EGRESS if (nf_hook_egress_active()) { skb = nf_hook_direct_egress(skb); if (!skb) return NET_XMIT_DROP; } #endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) { struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(po->cached_dev); dev_hold(dev); rcu_read_unlock(); return dev; } static void packet_cached_dev_assign(struct packet_sock *po, struct net_device *dev) { rcu_assign_pointer(po->cached_dev, dev); } static void packet_cached_dev_reset(struct packet_sock *po) { RCU_INIT_POINTER(po->cached_dev, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; int cpu = raw_smp_processor_id(); u16 queue_index; #ifdef CONFIG_XPS skb->sender_cpu = cpu + 1; #endif skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb, NULL); queue_index = netdev_cap_txqueue(dev, queue_index); } else { queue_index = netdev_pick_tx(dev, skb, NULL); } return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); if (!packet_sock_flag(po, PACKET_SOCK_RUNNING)) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); sock_hold(sk); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 1); } } static void register_prot_hook(struct sock *sk) { lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); __register_prot_hook(sk); } /* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the * callers responsibility to take care of this. */ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); lockdep_assert_held_once(&po->bind_lock); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 0); if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); __sock_put(sk); if (sync) { spin_unlock(&po->bind_lock); synchronize_net(); spin_lock(&po->bind_lock); } } static void unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) __unregister_prot_hook(sk, sync); } static inline struct page * __pure pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); return virt_to_page(addr); } static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } smp_wmb(); } static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; smp_rmb(); /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); return 0; } } static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, unsigned int flags) { struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); if (shhwtstamps && (flags & SOF_TIMESTAMPING_RAW_HARDWARE) && ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; if ((flags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb_tstamp(skb), ts)) return TP_STATUS_TS_SOFTWARE; return 0; } static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, struct sk_buff *skb) { union tpacket_uhdr h; struct timespec64 ts; __u32 ts_status; if (!(ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp)))) return 0; h.raw = frame; /* * versions 1 through 3 overflow the timestamps in y2106, since they * all store the seconds in a 32-bit unsigned integer. * If we create a version 4, that should have a 64-bit timestamp, * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit * nanoseconds. */ switch (po->tp_version) { case TPACKET_V1: h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; break; case TPACKET_V2: h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; break; case TPACKET_V3: h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } /* one flush is safe, as both fields always lie on the same cacheline */ flush_dcache_page(pgv_to_page(&h.h1->tp_sec)); smp_wmb(); return ts_status; } static void *packet_lookup_frame(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int position, int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; pg_vec_pos = position / rb->frames_per_block; frame_offset = position % rb->frames_per_block; h.raw = rb->pg_vec[pg_vec_pos].buffer + (frame_offset * rb->frame_size); if (status != __packet_get_status(po, h.raw)) return NULL; return h.raw; } static void *packet_current_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { return packet_lookup_frame(po, rb, rb->head, status); } static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } static void prb_setup_retire_blk_timer(struct packet_sock *po) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired, 0); pkc->retire_blk_timer.expires = jiffies; } static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); if (unlikely(!dev)) { rtnl_unlock(); return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); if (err) return DEFAULT_PRB_RETIRE_TOV; /* If the link speed is so slow you don't really * need to worry about perf anyways */ if (ecmd.base.speed < SPEED_1000 || ecmd.base.speed == SPEED_UNKNOWN) return DEFAULT_PRB_RETIRE_TOV; div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; if (div) return mbits + 1; return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, union tpacket_req_u *req_u) { p1->feature_req_word = req_u->req3.tp_feature_req_word; } static void init_prb_bdqc(struct packet_sock *po, struct packet_ring_buffer *rb, struct pgv *pg_vec, union tpacket_req_u *req_u) { struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd; memset(p1, 0x0, sizeof(*p1)); p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; p1->last_kactive_blk_num = 0; po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov; else p1->retire_blk_tov = prb_calc_retire_blk_tmo(po, req_u->req3.tp_block_size); p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po); prb_open_block(p1, pbd); } /* Do NOT update the last_blk_num first. * Assumes sk_buff_head lock is held. */ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) { mod_timer(&pkc->retire_blk_timer, jiffies + pkc->tov_in_jiffies); pkc->last_kactive_blk_num = pkc->kactive_blk_num; } /* * Timer logic: * 1) We refresh the timer only when we open a block. * By doing this we don't waste cycles refreshing the timer * on packet-by-packet basis. * * With a 1MB block-size, on a 1Gbps line, it will take * i) ~8 ms to fill a block + ii) memcpy etc. * In this cut we are not accounting for the memcpy time. * * So, if the user sets the 'tmo' to 10ms then the timer * will never fire while the block is still getting filled * (which is what we want). However, the user could choose * to close a block early and that's fine. * * But when the timer does fire, we check whether or not to refresh it. * Since the tmo granularity is in msecs, it is not too expensive * to refresh the timer, lets say every '8' msecs. * Either the user can set the 'tmo' or we can derive it based on * a) line-speed and b) block-size. * prb_calc_retire_blk_tmo() calculates the tmo. * */ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) { struct packet_sock *po = from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; spin_lock(&po->sk.sk_receive_queue.lock); frozen = prb_queue_frozen(pkc); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); if (unlikely(pkc->delete_blk_timer)) goto out; /* We only need to plug the race when the block is partially filled. * tpacket_rcv: * lock(); increment BLOCK_NUM_PKTS; unlock() * copy_bits() is in progress ... * timer fires on other cpu: * we can't retire the current block because copy_bits * is in progress. * */ if (BLOCK_NUM_PKTS(pbd)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) { if (!frozen) { if (!BLOCK_NUM_PKTS(pbd)) { /* An empty block. Just refresh the timer. */ goto refresh_timer; } prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); if (!prb_dispatch_next_block(pkc, po)) goto refresh_timer; else goto out; } else { /* Case 1. Queue was frozen because user-space was * lagging behind. */ if (prb_curr_blk_in_use(pbd)) { /* * Ok, user-space is still behind. * So just refresh the timer. */ goto refresh_timer; } else { /* Case 2. queue was frozen,user-space caught up, * now the link went idle && the timer fired. * We don't have a block to close.So we open this * block and restart the timer. * opening a block thaws the queue,restarts timer * Thawing/timer-refresh is a side effect. */ prb_open_block(pkc, pbd); goto out; } } } refresh_timer: _prb_refresh_rx_retire_blk_timer(pkc); out: spin_unlock(&po->sk.sk_receive_queue.lock); } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, __u32 status) { /* Flush everything minus the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 u8 *start, *end; start = (u8 *)pbd1; /* Skip the block header(we know header WILL fit in 4K) */ start += PAGE_SIZE; end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end); for (; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif /* Now update the block status. */ BLOCK_STATUS(pbd1) = status; /* Flush the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 start = (u8 *)pbd1; flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif } /* * Side effect: * * 1) flush the block * 2) Increment active_blk_num * * Note:We DONT refresh the timer on purpose. * Because almost always the next block will be opened. */ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, struct packet_sock *po, unsigned int stat) { __u32 status = TP_STATUS_USER | stat; struct tpacket3_hdr *last_pkt; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; last_pkt->tp_next_offset = 0; /* Get the ts of the last pkt */ if (BLOCK_NUM_PKTS(pbd1)) { h1->ts_last_pkt.ts_sec = last_pkt->tp_sec; h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec; } else { /* Ok, we tmo'd - so get the current time. * * It shouldn't really happen as we don't close empty * blocks. See prb_retire_rx_blk_timer_expired(). */ struct timespec64 ts; ktime_get_real_ts64(&ts); h1->ts_last_pkt.ts_sec = ts.tv_sec; h1->ts_last_pkt.ts_nsec = ts.tv_nsec; } smp_wmb(); /* Flush the block */ prb_flush_block(pkc1, pbd1, status); sk->sk_data_ready(sk); pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1); } static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) { pkc->reset_pending_on_curr_blk = 0; } /* * Side effect of opening a block: * * 1) prb_queue is thawed. * 2) retire_blk_timer is refreshed. * */ static void prb_open_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1) { struct timespec64 ts; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; smp_rmb(); /* We could have just memset this but we will lose the * flexibility of making the priv area sticky */ BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; BLOCK_NUM_PKTS(pbd1) = 0; BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); ktime_get_real_ts64(&ts); h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; pkc1->prev = pkc1->nxt_offset; pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; prb_thaw_queue(pkc1); _prb_refresh_rx_retire_blk_timer(pkc1); smp_wmb(); } /* * Queue freeze logic: * 1) Assume tp_block_nr = 8 blocks. * 2) At time 't0', user opens Rx ring. * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7 * 4) user-space is either sleeping or processing block '0'. * 5) tpacket_rcv is currently filling block '7', since there is no space left, * it will close block-7,loop around and try to fill block '0'. * call-flow: * __packet_lookup_frame_in_block * prb_retire_current_block() * prb_dispatch_next_block() * |->(BLOCK_STATUS == USER) evaluates to true * 5.1) Since block-0 is currently in-use, we just freeze the queue. * 6) Now there are two cases: * 6.1) Link goes idle right after the queue is frozen. * But remember, the last open_block() refreshed the timer. * When this timer expires,it will refresh itself so that we can * re-open block-0 in near future. * 6.2) Link is busy and keeps on receiving packets. This is a simple * case and __packet_lookup_frame_in_block will check if block-0 * is free and can now be re-used. */ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { pkc->reset_pending_on_curr_blk = 1; po->stats.stats3.tp_freeze_q_cnt++; } #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) /* * If the next block is free then we will dispatch it * and return a good offset. * Else, we will freeze the queue. * So, caller must check the return value. */ static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { struct tpacket_block_desc *pbd; smp_rmb(); /* 1. Get current block num */ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* 2. If this block is currently in_use then freeze the queue */ if (TP_STATUS_USER & BLOCK_STATUS(pbd)) { prb_freeze_queue(pkc, po); return NULL; } /* * 3. * open this block and return the offset where the first packet * needs to get stored. */ prb_open_block(pkc, pbd); return (void *)pkc->nxt_offset; } static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po, unsigned int status) { struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* retire/close the current block */ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) { /* * Plug the case where copy_bits() is in progress on * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't * have space to copy the pkt in the current block and * called prb_retire_current_block() * * We don't need to worry about the TMO case because * the timer-handler already handled this case. */ if (!(status & TP_STATUS_BLK_TMO)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } prb_close_block(pkc, pbd, po, status); return; } } static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd) { return TP_STATUS_USER & BLOCK_STATUS(pbd); } static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) { return pkc->reset_pending_on_curr_blk; } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); read_unlock(&pkc->blk_fill_in_prog_lock); } static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = 0; } static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) prb_fill_rxhash(pkc, ppd); else prb_clear_rxhash(pkc, ppd); } static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; ppd = (struct tpacket3_hdr *)curr; ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len); pkc->prev = curr; pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_NUM_PKTS(pbd) += 1; read_lock(&pkc->blk_fill_in_prog_lock); prb_run_all_ft_ops(pkc, ppd); } /* Assumes caller has the sk->rx_queue.lock */ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct sk_buff *skb, unsigned int len ) { struct tpacket_kbdq_core *pkc; struct tpacket_block_desc *pbd; char *curr, *end; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ if (prb_queue_frozen(pkc)) { /* * Check if that last block which caused the queue to freeze, * is still in_use by user-space. */ if (prb_curr_blk_in_use(pbd)) { /* Can't record this packet */ return NULL; } else { /* * Ok, the block was released by user-space. * Now let's open that block. * opening a block also thaws the queue. * Thawing is a side effect. */ prb_open_block(pkc, pbd); } } smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* Ok, close the current block */ prb_retire_current_block(pkc, po, 0); /* Now, try to dispatch the next block */ curr = (char *)prb_dispatch_next_block(pkc, po); if (curr) { pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* * No free blocks are available.user_space hasn't caught up yet. * Queue was just frozen and now this packet will get dropped. */ return NULL; } static void *packet_current_rx_frame(struct packet_sock *po, struct sk_buff *skb, int status, unsigned int len) { char *curr = NULL; switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: curr = packet_lookup_frame(po, &po->rx_ring, po->rx_ring.head, status); return curr; case TPACKET_V3: return __packet_lookup_frame_in_block(po, skb, len); default: WARN(1, "TPACKET version not supported\n"); BUG(); return NULL; } } static void *prb_lookup_block(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int idx, int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); if (status != BLOCK_STATUS(pbd)) return NULL; return pbd; } static int prb_previous_blk_num(struct packet_ring_buffer *rb) { unsigned int prev; if (rb->prb_bdqc.kactive_blk_num) prev = rb->prb_bdqc.kactive_blk_num-1; else prev = rb->prb_bdqc.knum_blocks-1; return prev; } /* Assumes caller has held the rx_queue.lock */ static void *__prb_previous_block(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = prb_previous_blk_num(rb); return prb_lookup_block(po, rb, previous, status); } static void *packet_previous_rx_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { if (po->tp_version <= TPACKET_V2) return packet_previous_frame(po, rb, status); return __prb_previous_block(po, rb, status); } static void packet_increment_rx_head(struct packet_sock *po, struct packet_ring_buffer *rb) { switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: return packet_increment_head(rb); case TPACKET_V3: default: WARN(1, "TPACKET version not supported.\n"); BUG(); return; } } static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; return packet_lookup_frame(po, rb, previous, status); } static void packet_increment_head(struct packet_ring_buffer *buff) { buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } static void packet_inc_pending(struct packet_ring_buffer *rb) { this_cpu_inc(*rb->pending_refcnt); } static void packet_dec_pending(struct packet_ring_buffer *rb) { this_cpu_dec(*rb->pending_refcnt); } static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) { unsigned int refcnt = 0; int cpu; /* We don't use pending refcount in rx_ring. */ if (rb->pending_refcnt == NULL) return 0; for_each_possible_cpu(cpu) refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); return refcnt; } static int packet_alloc_pending(struct packet_sock *po) { po->rx_ring.pending_refcnt = NULL; po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); if (unlikely(po->tx_ring.pending_refcnt == NULL)) return -ENOBUFS; return 0; } static void packet_free_pending(struct packet_sock *po) { free_percpu(po->tx_ring.pending_refcnt); } #define ROOM_POW_OFF 2 #define ROOM_NONE 0x0 #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.frame_max) + 1; idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static int __packet_rcv_has_room(const struct packet_sock *po, const struct sk_buff *skb) { const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { int rcvbuf = READ_ONCE(sk->sk_rcvbuf); int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) - (skb ? skb->truesize : 0); if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; else return ROOM_NONE; } if (po->tp_version == TPACKET_V3) { if (__tpacket_v3_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_v3_has_room(po, 0)) ret = ROOM_LOW; } else { if (__tpacket_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_has_room(po, 0)) ret = ROOM_LOW; } return ret; } static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { bool pressure; int ret; ret = __packet_rcv_has_room(po, skb); pressure = ret != ROOM_NORMAL; if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) != pressure) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, pressure); return ret; } static void packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); return; } } static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) { u32 *history = po->rollover->history; u32 victim, rxhash; int i, count = 0; rxhash = skb_get_hash(skb); for (i = 0; i < ROLLOVER_HLEN; i++) if (READ_ONCE(history[i]) == rxhash) count++; victim = get_random_u32_below(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) WRITE_ONCE(history[victim], rxhash); return count > (ROLLOVER_HLEN >> 1); } static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { unsigned int val = atomic_inc_return(&f->rr_cur); return val % num; } static unsigned int fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return smp_processor_id() % num; } static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return get_random_u32_below(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct sk_buff *skb, unsigned int idx, bool try_self, unsigned int num) { struct packet_sock *po, *po_next, *po_skip = NULL; unsigned int i, j, room = ROOM_NONE; po = pkt_sk(rcu_dereference(f->arr[idx])); if (try_self) { room = packet_rcv_has_room(po, skb); if (room == ROOM_NORMAL || (room == ROOM_LOW && !fanout_flow_is_huge(po, skb))) return idx; po_skip = po; } i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(rcu_dereference(f->arr[i])); if (po_next != po_skip && !packet_sock_flag(po_next, PACKET_SOCK_PRESSURE) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; atomic_long_inc(&po->rollover->num); if (room == ROOM_LOW) atomic_long_inc(&po->rollover->num_huge); return i; } if (++i == num) i = 0; } while (i != j); atomic_long_inc(&po->rollover->num_failed); return idx; } static unsigned int fanout_demux_qm(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return skb_get_queue_mapping(skb) % num; } static unsigned int fanout_demux_bpf(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { struct bpf_prog *prog; unsigned int ret = 0; rcu_read_lock(); prog = rcu_dereference(f->bpf_prog); if (prog) ret = bpf_prog_run_clear_cb(prog, skb) % num; rcu_read_unlock(); return ret; } static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); } static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct packet_fanout *f = pt->af_packet_priv; unsigned int num = READ_ONCE(f->num_members); struct net *net = read_pnet(&f->net); struct packet_sock *po; unsigned int idx; if (!net_eq(dev_net(dev), net) || !num) { kfree_skb(skb); return 0; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } switch (f->type) { case PACKET_FANOUT_HASH: default: idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: idx = fanout_demux_lb(f, skb, num); break; case PACKET_FANOUT_CPU: idx = fanout_demux_cpu(f, skb, num); break; case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; case PACKET_FANOUT_QM: idx = fanout_demux_qm(f, skb, num); break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, false, num); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: idx = fanout_demux_bpf(f, skb, num); break; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) idx = fanout_demux_rollover(f, skb, idx, true, num); po = pkt_sk(rcu_dereference(f->arr[idx])); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } DEFINE_MUTEX(fanout_mutex); EXPORT_SYMBOL_GPL(fanout_mutex); static LIST_HEAD(fanout_list); static u16 fanout_next_id; static void __fanout_link(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; spin_lock(&f->lock); rcu_assign_pointer(f->arr[f->num_members], sk); smp_wmb(); f->num_members++; if (f->num_members == 1) dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } static void __fanout_unlink(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; int i; spin_lock(&f->lock); for (i = 0; i < f->num_members; i++) { if (rcu_dereference_protected(f->arr[i], lockdep_is_held(&f->lock)) == sk) break; } BUG_ON(i >= f->num_members); rcu_assign_pointer(f->arr[i], rcu_dereference_protected(f->arr[f->num_members - 1], lockdep_is_held(&f->lock))); f->num_members--; if (f->num_members == 0) __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { if (sk->sk_family != PF_PACKET) return false; return ptype->af_packet_priv == pkt_sk(sk)->fanout; } static void fanout_init_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_LB: atomic_set(&f->rr_cur, 0); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: RCU_INIT_POINTER(f->bpf_prog, NULL); break; } } static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) { struct bpf_prog *old; spin_lock(&f->lock); old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock)); rcu_assign_pointer(f->bpf_prog, new); spin_unlock(&f->lock); if (old) { synchronize_net(); bpf_prog_destroy(old); } } static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; struct sock_fprog fprog; int ret; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; ret = copy_bpf_fprog_from_user(&fprog, data, len); if (ret) return ret; ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) return ret; __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; u32 fd; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; if (len != sizeof(fd)) return -EINVAL; if (copy_from_sockptr(&fd, data, len)) return -EFAULT; new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(new)) return PTR_ERR(new); __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data(struct packet_sock *po, sockptr_t data, unsigned int len) { switch (po->fanout->type) { case PACKET_FANOUT_CBPF: return fanout_set_data_cbpf(po, data, len); case PACKET_FANOUT_EBPF: return fanout_set_data_ebpf(po, data, len); default: return -EINVAL; } } static void fanout_release_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: __fanout_set_data_bpf(f, NULL); } } static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id) { struct packet_fanout *f; list_for_each_entry(f, &fanout_list, list) { if (f->id == candidate_id && read_pnet(&f->net) == sock_net(sk)) { return false; } } return true; } static bool fanout_find_new_id(struct sock *sk, u16 *new_id) { u16 id = fanout_next_id; do { if (__fanout_id_is_free(sk, id)) { *new_id = id; fanout_next_id = id + 1; return true; } id++; } while (id != fanout_next_id); return false; } static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; u16 id = args->id; int err; switch (type) { case PACKET_FANOUT_ROLLOVER: if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) return -EINVAL; break; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: case PACKET_FANOUT_QM: case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: break; default: return -EINVAL; } mutex_lock(&fanout_mutex); err = -EALREADY; if (po->fanout) goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { err = -ENOMEM; rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); if (!rollover) goto out; atomic_long_set(&rollover->num, 0); atomic_long_set(&rollover->num_huge, 0); atomic_long_set(&rollover->num_failed, 0); } if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) { if (id != 0) { err = -EINVAL; goto out; } if (!fanout_find_new_id(sk, &id)) { err = -ENOMEM; goto out; } /* ephemeral flag for the first socket in the group: drop it */ flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8); } match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && read_pnet(&f->net) == sock_net(sk)) { match = f; break; } } err = -EINVAL; if (match) { if (match->flags != flags) goto out; if (args->max_num_members && args->max_num_members != match->max_num_members) goto out; } else { if (args->max_num_members > PACKET_FANOUT_MAX) goto out; if (!args->max_num_members) /* legacy PACKET_FANOUT_MAX */ args->max_num_members = 256; err = -ENOMEM; match = kvzalloc(struct_size(match, arr, args->max_num_members), GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); match->id = id; match->type = type; match->flags = flags; INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); refcount_set(&match->sk_ref, 0); fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING) && match->type == type && match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { __dev_remove_pack(&po->prot_hook); /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ WRITE_ONCE(po->fanout, match); po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); __fanout_link(sk, po); err = 0; } } spin_unlock(&po->bind_lock); if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); kvfree(match); } out: kfree(rollover); mutex_unlock(&fanout_mutex); return err; } /* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. * It is the responsibility of the caller to call fanout_release_data() and * free the returned packet_fanout (after synchronize_net()) */ static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; mutex_lock(&fanout_mutex); f = po->fanout; if (f) { po->fanout = NULL; if (refcount_dec_and_test(&f->sk_ref)) list_del(&f->list); else f = NULL; } mutex_unlock(&fanout_mutex); return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, struct sk_buff *skb) { /* Earlier code assumed this would be a VLAN pkt, double-check * this now that we have the actual packet in hand. We can only * do this check on Ethernet devices. */ if (unlikely(dev->type != ARPHRD_ETHER)) return false; skb_reset_mac_header(skb); return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); } static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_pkt *spkt; /* * When we registered the protocol we saved the socket in the data * field for just this event. */ sk = pt->af_packet_priv; /* * Yank back the headers [hope the device set this * right or kerboom...] * * Incoming packets have ll header pulled, * push it back. * * For outgoing ones skb->data == skb_mac_header(skb) * so that this procedure is noop. */ if (skb->pkt_type == PACKET_LOOPBACK) goto out; if (!net_eq(dev_net(dev), sock_net(sk))) goto out; skb = skb_share_check(skb, GFP_ATOMIC); if (skb == NULL) goto oom; /* drop any routing info */ skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; skb_push(skb, skb->data - skb_mac_header(skb)); /* * The SOCK_PACKET socket receives _all_ frames. */ spkt->spkt_family = dev->type; strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* * Charge the memory to the socket. This is done specifically * to prevent sockets using all the memory up. */ if (sock_queue_rcv_skb(sk, skb) == 0) return 0; out: kfree_skb(skb); oom: return 0; } static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } /* * Output a raw packet to a device layer. This bypasses all the other * protocol layers and you must therefore supply it with a complete frame */ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; int err; int extra_len = 0; /* * Get and verify the address. */ if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) return -EINVAL; if (msg->msg_namelen == sizeof(struct sockaddr_pkt)) proto = saddr->spkt_protocol; } else return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it */ saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0; retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_unlock; /* * You may not queue a frame bigger than the mtu. This is the lowest level * raw protocol and you must do your own fragmentation at this level. */ if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { size_t reserved = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; /* FIXME: Save some space for broken drivers that write a hard * header at transmission time by themselves. PPP is the notable * one here. This should really be fixed at the driver level. */ skb_reserve(skb, reserved); skb_reset_network_header(skb); /* Try to align data part correctly */ if (hhlen) { skb->data -= hhlen; skb->tail -= hhlen; if (len < hhlen) skb_reset_network_header(skb); } err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err) goto out_free; goto retry; } if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); dev_queue_xmit(skb); rcu_read_unlock(); return len; out_unlock: rcu_read_unlock(); out_free: kfree_skb(skb); return err; } static unsigned int run_filter(struct sk_buff *skb, const struct sock *sk, unsigned int res) { struct sk_filter *filter; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = bpf_prog_run_clear_cb(filter->prog, skb); rcu_read_unlock(); return res; } static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, size_t *len, int vnet_hdr_sz) { struct virtio_net_hdr_mrg_rxbuf vnet_hdr = { .num_buffers = 0 }; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr, vio_le(), true, 0)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_sz); } /* * This function makes lazy skb cloning in hope that most of packets * are discarded by BPF. * * Note tricky part: we DO mangle shared skb! skb->data, skb->len * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; skb->dev = dev; if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * * Otherwise, the device hides details of its frame * structure, so that corresponding packet head is * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb->len; res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; if (snaplen > res) snaplen = res; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (nskb == NULL) goto drop_n_acct; if (skb_head != skb->data) { skb->data = skb_head; skb->len = skb_len; } consume_skb(skb); skb = nskb; } sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8); sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; sll->sll_halen = dev_parse_header(skb, sll->sll_addr); /* sll->sll_family and sll->sll_protocol are set in packet_recvmsg(). * Use their space for storing the original skb length. */ PACKET_SKB_CB(skb)->sa.origlen = skb->len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; skb_set_owner_r(skb, sk); skb->dev = NULL; skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; sock_skb_set_dropcount(sk, skb); skb_clear_delivery_time(skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); return 0; drop_n_acct: atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: kfree_skb_reason(skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; unsigned short macoff, hdrlen; unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; unsigned int slot_id = 0; int vnet_hdr_sz = 0; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. * We may add members to them until current aligned size without forcing * userspace to call getsockopt(..., PACKET_HDRLEN, ...). */ BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb->len; res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; /* If we are flooded, just give up */ if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 + po->tp_reserve; } else { unsigned int maclen = skb_network_offset(skb); netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); if (vnet_hdr_sz) netoff += vnet_hdr_sz; macoff = netoff - maclen; } if (netoff > USHRT_MAX) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { copy_skb = skb_get(skb); skb_head = skb->data; } if (copy_skb) { memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { snaplen = 0; vnet_hdr_sz = 0; } } } else if (unlikely(macoff + snaplen > GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { u32 nval; nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", snaplen, nval, macoff); snaplen = nval; if (unlikely((int)snaplen < 0)) { snaplen = 0; macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; vnet_hdr_sz = 0; } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; if (po->tp_version <= TPACKET_V2) { slot_id = po->rx_ring.head; if (test_bit(slot_id, po->rx_ring.rx_owner_map)) goto drop_n_account; __set_bit(slot_id, po->rx_ring.rx_owner_map); } if (vnet_hdr_sz && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), vio_le(), true, 0)) { if (po->tp_version == TPACKET_V3) prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* * LOSING will be reported till you read the stats, * because it's COR - Clear On Read. * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; skb_clear_delivery_time(copy_skb); __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); /* Always timestamp; prefer an existing software timestamp taken * closer to the time of capture. */ ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp) | SOF_TIMESTAMPING_SOFTWARE); if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; switch (po->tp_version) { case TPACKET_V1: h.h1->tp_len = skb->len; h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; hdrlen = sizeof(*h.h1); break; case TPACKET_V2: h.h2->tp_len = skb->len; h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; if (skb_vlan_tag_present(skb)) { h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; } memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: /* tp_nxt_offset,vlan are already populated above. * So DONT clear those fields here */ h.h3->tp_status |= status; h.h3->tp_len = skb->len; h.h3->tp_snaplen = snaplen; h.h3->tp_mac = macoff; h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: BUG(); } sll = h.raw + TPACKET_ALIGN(hdrlen); sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; sll->sll_protocol = skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; smp_mb(); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 if (po->tp_version <= TPACKET_V2) { u8 *start, *end; end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + macoff + snaplen); for (start = h.raw; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); } smp_wmb(); #endif if (po->tp_version <= TPACKET_V2) { spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: kfree_skb_reason(skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); kfree_skb_reason(copy_skb, drop_reason); goto drop_n_restore; } static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); if (likely(po->tx_ring.pg_vec)) { void *ph; __u32 ts; ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); if (!packet_read_pending(&po->tx_ring)) complete(&po->skb_completion); } sock_wfree(skb); } static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len) { if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && (__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 > __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len))) vnet_hdr->hdr_len = __cpu_to_virtio16(vio_le(), __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2); if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len) return -EINVAL; return 0; } static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, struct virtio_net_hdr *vnet_hdr, int vnet_hdr_sz) { int ret; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; ret = __packet_snd_vnet_parse(vnet_hdr, *len); if (ret) return ret; /* move iter to point to the start of mac header */ if (vnet_hdr_sz != sizeof(struct virtio_net_hdr)) iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(struct virtio_net_hdr)); return 0; } static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; int to_write, offset, len, nr_frags, len_max; struct socket *sock = po->sk.sk_socket; struct page *page; int err; ph.raw = frame; skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); to_write = tp_len; if (sock->type == SOCK_DGRAM) { err = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, tp_len); if (unlikely(err < 0)) return -EINVAL; } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); skb_push(skb, dev->hard_header_len); skb_put(skb, copylen - dev->hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; if (!dev_validate_header(dev, skb->data, hdrlen)) return -EINVAL; data += hdrlen; to_write -= hdrlen; } offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { pr_err("Packet exceed the number of skb frags(%u)\n", (unsigned int)MAX_SKB_FRAGS); return -EFAULT; } page = pgv_to_page(data); data += len; flush_dcache_page(page); get_page(page); skb_fill_page_desc(skb, nr_frags, page, offset, len); to_write -= len; offset = 0; len_max = PAGE_SIZE; len = ((to_write > len_max) ? len_max : to_write); } packet_parse_headers(skb, sock); return tp_len; } static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; int tp_len, off; ph.raw = frame; switch (po->tp_version) { case TPACKET_V3: if (ph.h3->tp_next_offset != 0) { pr_warn_once("variable sized slot not supported"); return -EINVAL; } tp_len = ph.h3->tp_len; break; case TPACKET_V2: tp_len = ph.h2->tp_len; break; default: tp_len = ph.h1->tp_len; break; } if (unlikely(tp_len > size_max)) { pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); return -EMSGSIZE; } if (unlikely(packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF))) { int off_min, off_max; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); off_max = po->tx_ring.frame_size - tp_len; if (po->sk.sk_type == SOCK_DGRAM) { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_net; break; case TPACKET_V2: off = ph.h2->tp_net; break; default: off = ph.h1->tp_net; break; } } else { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_mac; break; case TPACKET_V2: off = ph.h2->tp_mac; break; default: off = ph.h1->tp_mac; break; } } if (unlikely((off < off_min) || (off_max < off))) return -EINVAL; } else { off = po->tp_hdrlen - sizeof(struct sockaddr_ll); } *data = frame + off; return tp_len; } static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; __be16 proto; int err, reserve = 0; void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); unsigned char *addr = NULL; int tp_len, size_max; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; long timeo = 0; mutex_lock(&po->pg_vec_lock); /* packet_sendmsg() check on tx_ring.pg_vec was lockless, * we need to confirm it under protection of pg_vec_lock. */ if (unlikely(!po->tx_ring.pg_vec)) { err = -EBUSY; goto out; } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (po->sk.sk_socket->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_put; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; sockcm_init(&sockc, &po->sk); if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) goto out_put; } if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz) size_max = dev->mtu + reserve + VLAN_HLEN; reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { if (need_wait && skb) { timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } } /* check for additional frames */ continue; } skb = NULL; tp_len = tpacket_parse_header(po, ph, size_max, &data); if (tp_len < 0) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { vnet_hdr = data; data += vnet_hdr_sz; tp_len -= vnet_hdr_sz; if (tp_len < 0 || __packet_snd_vnet_parse(vnet_hdr, tp_len)) { tp_len = -EINVAL; goto tpacket_error; } copylen = __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len); } copylen = max_t(int, copylen, dev->hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + (copylen - dev->hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { /* we assume the socket was initially writeable ... */ if (likely(len_sum > 0)) err = len_sum; goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, addr, hlen, copylen, &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && !packet_extra_vlan_len_allowed(dev, skb)) tp_len = -EMSGSIZE; if (unlikely(tp_len < 0)) { tpacket_error: if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS)) { __packet_set_status(po, ph, TP_STATUS_AVAILABLE); packet_increment_head(&po->tx_ring); kfree_skb(skb); continue; } else { status = TP_STATUS_WRONG_FORMAT; err = tp_len; goto out_status; } } if (vnet_hdr_sz) { if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { tp_len = -EINVAL; goto tpacket_error; } virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ skb = NULL; goto out_status; } /* * skb was dropped but not destructed yet; * let's treat it like congestion or err < 0 */ err = 0; } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || /* Note: packet_read_pending() might be slow if we have * to call it as it's per_cpu variable, but in fast-path * we already short-circuit the loop with the first * condition, and luckily don't have to go that path * anyway. */ (need_wait && packet_read_pending(&po->tx_ring)))); err = len_sum; goto out_put; out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; } static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, size_t reserve, size_t len, size_t linear, int noblock, int *err) { struct sk_buff *skb; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE || !linear) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return NULL; skb_reserve(skb, reserve); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); int hlen, tlen, linear; int extra_len = 0; /* * Get and verify the address. */ if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (sock->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_unlock; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out_unlock; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; sockcm_init(&sockc, sk); sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) goto out_unlock; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len)) goto out_unlock; err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); linear = max(linear, min_t(int, len, dev->hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; skb_reset_network_header(skb); err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } /* Returns -EFAULT on error */ err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); if (err) goto out_free; if ((sock->type == SOCK_RAW && !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } skb_setup_tx_timestamp(skb, sockc.tsflags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_free; } skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); if (vnet_hdr_sz) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; len += vnet_hdr_sz; virtio_net_hdr_set_proto(skb, &vnet_hdr); } err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err) goto out_unlock; } dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: dev_put(dev); out: return err; } static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. * tpacket_snd() will redo the check safely. */ if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); return packet_snd(sock, msg, len); } /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. */ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; if (!sk) return 0; net = sock_net(sk); po = pkt_sk(sk); mutex_lock(&net->packet.sklist_lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); packet_flush_mclist(sk); lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); } if (po->tx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } release_sock(sk); f = fanout_release(sk); synchronize_net(); kfree(po->rollover); if (f) { fanout_release_data(f); kvfree(f); } /* * Now the socket is dead. No more input will appear. */ sock_orphan(sk); sock->sk = NULL; /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); packet_free_pending(po); sock_put(sk); return 0; } /* * Attach a packet hook. */ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, __be16 proto) { struct packet_sock *po = pkt_sk(sk); struct net_device *dev = NULL; bool unlisted = false; bool need_rehook; int ret = 0; lock_sock(sk); spin_lock(&po->bind_lock); if (!proto) proto = po->num; rcu_read_lock(); if (po->fanout) { ret = -EINVAL; goto out_unlock; } if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { ret = -ENODEV; goto out_unlock; } } else if (ifindex) { dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (!dev) { ret = -ENODEV; goto out_unlock; } } need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev; if (need_rehook) { dev_hold(dev); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { rcu_read_unlock(); /* prevents packet_notifier() from calling * register_prot_hook() */ WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(packet_sock_flag(po, PACKET_SOCK_RUNNING)); WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); if (unlikely(unlisted)) { po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { netdev_hold(dev, &po->prot_hook.dev_tracker, GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } dev_put(dev); } if (proto == 0 || !need_rehook) goto out_unlock; if (!unlisted && (!dev || (dev->flags & IFF_UP))) { register_prot_hook(sk); } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } out_unlock: rcu_read_unlock(); spin_unlock(&po->bind_lock); release_sock(sk); return ret; } /* * Bind a packet socket to a device */ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality */ if (addr_len != sizeof(struct sockaddr)) return -EINVAL; /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; struct sock *sk = sock->sk; /* * Check legality */ if (addr_len < sizeof(struct sockaddr_ll)) return -EINVAL; if (sll->sll_family != AF_PACKET) return -EINVAL; return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { .name = "PACKET", .owner = THIS_MODULE, .obj_size = sizeof(struct packet_sock), }; /* * Create a packet of type SOCK_PACKET. */ static int packet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct packet_sock *po; __be16 proto = (__force __be16)protocol; /* weird, but documented */ int err; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW && sock->type != SOCK_PACKET) return -ESOCKTNOSUPPORT; sock->state = SS_UNCONNECTED; err = -ENOBUFS; sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern); if (sk == NULL) goto out; sock->ops = &packet_ops; if (sock->type == SOCK_PACKET) sock->ops = &packet_ops_spkt; sock_init_data(sock, sk); po = pkt_sk(sk); init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; err = packet_alloc_pending(po); if (err) goto out2; packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; /* * Attach a protocol block */ spin_lock_init(&po->bind_lock); mutex_init(&po->pg_vec_lock); po->rollover = NULL; po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, &packet_proto, 1); return 0; out2: sk_free(sk); out: return err; } /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. */ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; int vnet_hdr_len = READ_ONCE(pkt_sk(sk)->vnet_hdr_sz); unsigned int origlen = 0; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE)) goto out; #if 0 /* What error should we return now? EUNATTACH? */ if (pkt_sk(sk)->ifindex < 0) return -ENODEV; #endif if (flags & MSG_ERRQUEUE) { err = sock_recv_errqueue(sk, msg, len, SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } /* * Call the generic datagram receiver. This handles all sorts * of horrible races and re-entrancy so we can forget about it * in the protocol layers. * * Now it will return ENETDOWN, if device have just gone down, * but then it will block. */ skb = skb_recv_datagram(sk, flags, &err); /* * An error occurred so return it. Because skb_recv_datagram() * handles the blocking we don't see and worry about blocking * retries. */ if (skb == NULL) goto out; packet_rcv_try_clear_pressure(pkt_sk(sk)); if (vnet_hdr_len) { err = packet_rcv_vnet(msg, skb, &len, vnet_hdr_len); if (err) goto out_free; } /* You lose any data beyond the buffer you gave. If it worries * a user program they can ask the device for its MTU * anyway. */ copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; if (sock->type != SOCK_PACKET) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; sll->sll_protocol = skb->protocol; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { const size_t max_len = min(sizeof(skb->cb), sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); copy_len = msg->msg_namelen; } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); copy_len = msg->msg_namelen; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) { memset(msg->msg_name + offsetof(struct sockaddr_ll, sll_addr), 0, sizeof(sll->sll_addr)); msg->msg_namelen = sizeof(struct sockaddr_ll); } } if (WARN_ON_ONCE(copy_len > max_len)) { copy_len = max_len; msg->msg_namelen = copy_len; } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); if (skb_vlan_tag_present(skb)) { aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. */ err = vnet_hdr_len + ((flags&MSG_TRUNC) ? skb->len : copied); out_free: skb_free_datagram(sk, skb); out: return err; } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; if (peer) return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); int ifindex; if (peer) return -EOPNOTSUPP; ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; /* Let __fortify_memcpy_chk() know the actual buffer size. */ memcpy(((struct sockaddr_storage *)sll)->__data + offsetof(struct sockaddr_ll, sll_addr) - offsetofend(struct sockaddr_ll, sll_family), dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; } rcu_read_unlock(); return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what) { switch (i->type) { case PACKET_MR_MULTICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_mc_add(dev, i->addr); else return dev_mc_del(dev, i->addr); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); case PACKET_MR_UNICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_uc_add(dev, i->addr); else return dev_uc_del(dev, i->addr); break; default: break; } return 0; } static void packet_dev_mclist_delete(struct net_device *dev, struct packet_mclist **mlp) { struct packet_mclist *ml; while ((ml = *mlp) != NULL) { if (ml->ifindex == dev->ifindex) { packet_dev_mc(dev, ml, -1); *mlp = ml->next; kfree(ml); } else mlp = &ml->next; } } static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml, *i; struct net_device *dev; int err; rtnl_lock(); err = -ENODEV; dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex); if (!dev) goto done; err = -EINVAL; if (mreq->mr_alen > dev->addr_len) goto done; err = -ENOBUFS; i = kmalloc(sizeof(*i), GFP_KERNEL); if (i == NULL) goto done; err = 0; for (ml = po->mclist; ml; ml = ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { ml->count++; /* Free the new element ... */ kfree(i); goto done; } } i->type = mreq->mr_type; i->ifindex = mreq->mr_ifindex; i->alen = mreq->mr_alen; memcpy(i->addr, mreq->mr_address, i->alen); memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen); i->count = 1; i->next = po->mclist; po->mclist = i; err = packet_dev_mc(dev, i, 1); if (err) { po->mclist = i->next; kfree(i); } done: rtnl_unlock(); return err; } static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_mclist *ml, **mlp; rtnl_lock(); for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev) packet_dev_mc(dev, ml, -1); kfree(ml); } break; } } rtnl_unlock(); return 0; } static void packet_flush_mclist(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml; if (!po->mclist) return; rtnl_lock(); while ((ml = po->mclist) != NULL) { struct net_device *dev; po->mclist = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev != NULL) packet_dev_mc(dev, ml, -1); kfree(ml); } rtnl_unlock(); } static int packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); int ret; if (level != SOL_PACKET) return -ENOPROTOOPT; switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { struct packet_mreq_max mreq; int len = optlen; memset(&mreq, 0, sizeof(mreq)); if (len < sizeof(struct packet_mreq)) return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); if (copy_from_sockptr(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; if (optname == PACKET_ADD_MEMBERSHIP) ret = packet_mc_add(sk, &mreq); else ret = packet_mc_drop(sk, &mreq); return ret; } case PACKET_RX_RING: case PACKET_TX_RING: { union tpacket_req_u req_u; int len; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: len = sizeof(req_u.req); break; case TPACKET_V3: default: len = sizeof(req_u.req3); break; } if (optlen < len) { ret = -EINVAL; } else { if (copy_from_sockptr(&req_u.req, optval, len)) ret = -EFAULT; else ret = packet_set_ring(sk, &req_u, 0, optname == PACKET_TX_RING); } release_sock(sk); return ret; } case PACKET_COPY_THRESH: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; pkt_sk(sk)->copy_thresh = val; return 0; } case PACKET_VERSION: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: break; default: return -EINVAL; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_version = val; ret = 0; } release_sock(sk); return ret; } case PACKET_RESERVE: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_reserve = val; ret = 0; } release_sock(sk); return ret; } case PACKET_LOSS: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { packet_sock_flag_set(po, PACKET_SOCK_TP_LOSS, val); ret = 0; } release_sock(sk); return ret; } case PACKET_AUXDATA: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: case PACKET_VNET_HDR_SZ: { int val, hdr_len; if (sock->type != SOCK_RAW) return -EINVAL; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (optname == PACKET_VNET_HDR_SZ) { if (val && val != sizeof(struct virtio_net_hdr) && val != sizeof(struct virtio_net_hdr_mrg_rxbuf)) return -EINVAL; hdr_len = val; } else { hdr_len = val ? sizeof(struct virtio_net_hdr) : 0; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { WRITE_ONCE(po->vnet_hdr_sz, hdr_len); ret = 0; } release_sock(sk); return ret; } case PACKET_TIMESTAMP: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(po->tp_tstamp, val); return 0; } case PACKET_FANOUT: { struct fanout_args args = { 0 }; if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { /* Paired with the WRITE_ONCE() in fanout_add() */ if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); } case PACKET_IGNORE_OUTGOING: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val < 0 || val > 1) return -EINVAL; po->prot_hook.ignore_outgoing = !!val; return 0; } case PACKET_TX_HAS_OFF: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) packet_sock_flag_set(po, PACKET_SOCK_TX_HAS_OFF, val); release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_QDISC_BYPASS, val); return 0; } default: return -ENOPROTOOPT; } } static int packet_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { int len; int val, lv = sizeof(val); struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case PACKET_STATISTICS: spin_lock_bh(&sk->sk_receive_queue.lock); memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); st.stats3.tp_drops = drops; st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); st.stats1.tp_drops = drops; st.stats1.tp_packets += drops; data = &st.stats1; } break; case PACKET_AUXDATA: val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = !!READ_ONCE(po->vnet_hdr_sz); break; case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; case PACKET_VERSION: val = po->tp_version; break; case PACKET_HDRLEN: if (len > sizeof(int)) len = sizeof(int); if (len < sizeof(int)) return -EINVAL; if (copy_from_user(&val, optval, len)) return -EFAULT; switch (val) { case TPACKET_V1: val = sizeof(struct tpacket_hdr); break; case TPACKET_V2: val = sizeof(struct tpacket2_hdr); break; case TPACKET_V3: val = sizeof(struct tpacket3_hdr); break; default: return -EINVAL; } break; case PACKET_RESERVE: val = po->tp_reserve; break; case PACKET_LOSS: val = packet_sock_flag(po, PACKET_SOCK_TP_LOSS); break; case PACKET_TIMESTAMP: val = READ_ONCE(po->tp_tstamp); break; case PACKET_FANOUT: val = (po->fanout ? ((u32)po->fanout->id | ((u32)po->fanout->type << 16) | ((u32)po->fanout->flags << 24)) : 0); break; case PACKET_IGNORE_OUTGOING: val = po->prot_hook.ignore_outgoing; break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; rstats.tp_all = atomic_long_read(&po->rollover->num); rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); data = &rstats; lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF); break; case PACKET_QDISC_BYPASS: val = packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS); break; default: return -ENOPROTOOPT; } if (len > lv) len = lv; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, data, len)) return -EFAULT; return 0; } static int packet_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct sock *sk; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); rcu_read_lock(); sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist); fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); } break; case NETDEV_UP: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (po->num) register_prot_hook(sk); spin_unlock(&po->bind_lock); } break; } } rcu_read_unlock(); return NOTIFY_DONE; } static int packet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } #ifdef CONFIG_INET case SIOCADDRT: case SIOCDELRT: case SIOCDARP: case SIOCGARP: case SIOCSARP: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: return inet_dgram_ops.ioctl(sock, cmd, arg); #endif default: return -ENOIOCTLCMD; } return 0; } static __poll_t packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { if (!packet_previous_rx_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) mask |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } /* Dirty? Well, I still did not learn better way to account * for user mmaps. */ static void packet_mm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; static void free_pg_vec(struct pgv *pg_vec, unsigned int order, unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { if (is_vmalloc_addr(pg_vec[i].buffer)) vfree(pg_vec[i].buffer); else free_pages((unsigned long)pg_vec[i].buffer, order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); if (buffer) return buffer; /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* complete and utter failure */ return NULL; } static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; struct pgv *pg_vec; int i; pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; for (i = 0; i < block_nr; i++) { pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } out: return pg_vec; out_free_pgvec: free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring) { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; int err; /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; err = -EBUSY; if (!closing) { if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; } if (req->tp_block_nr) { unsigned int min_frame_size; /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V1: po->tp_hdrlen = TPACKET_HDRLEN; break; case TPACKET_V2: po->tp_hdrlen = TPACKET2_HDRLEN; break; case TPACKET_V3: po->tp_hdrlen = TPACKET3_HDRLEN; break; } err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && req->tp_block_size < BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V3: /* Block transmit is not supported yet */ if (!tx_ring) { init_prb_bdqc(po, rb, pg_vec, req_u); } else { struct tpacket_req3 *req3 = &req_u->req3; if (req3->tp_retire_blk_tov || req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; goto out_free_pg_vec; } } break; default: if (!tx_ring) { rx_owner_map = bitmap_alloc(req->tp_frame_nr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); if (!rx_owner_map) goto out_free_pg_vec; } break; } } /* Done */ else { err = -EINVAL; if (unlikely(req->tp_frame_nr)) goto out; } /* Detach socket from network */ spin_lock(&po->bind_lock); was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING); num = po->num; if (was_running) { WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); synchronize_net(); err = -EBUSY; mutex_lock(&po->pg_vec_lock); if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); if (po->tp_version <= TPACKET_V2) swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); if (was_running) { WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } out_free_pg_vec: if (pg_vec) { bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); } out: return err; } static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); unsigned long size, expected_size; struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; if (vma->vm_pgoff) return -EINVAL; mutex_lock(&po->pg_vec_lock); expected_size = 0; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec) { expected_size += rb->pg_vec_len * rb->pg_vec_pages * PAGE_SIZE; } } if (expected_size == 0) goto out; size = vma->vm_end - vma->vm_start; if (size != expected_size) goto out; start = vma->vm_start; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec == NULL) continue; for (i = 0; i < rb->pg_vec_len; i++) { struct page *page; void *kaddr = rb->pg_vec[i].buffer; int pg_num; for (pg_num = 0; pg_num < rb->pg_vec_pages; pg_num++) { page = pgv_to_page(kaddr); err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; start += PAGE_SIZE; kaddr += PAGE_SIZE; } } } atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; out: mutex_unlock(&po->pg_vec_lock); return err; } static const struct proto_ops packet_ops_spkt = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind_spkt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname_spkt, .poll = datagram_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, }; static const struct proto_ops packet_ops = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname, .poll = packet_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, .getsockopt = packet_getsockopt, .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, }; static const struct net_proto_family packet_family_ops = { .family = PF_PACKET, .create = packet_create, .owner = THIS_MODULE, }; static struct notifier_block packet_netdev_notifier = { .notifier_call = packet_notifier, }; #ifdef CONFIG_PROC_FS static void *packet_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); rcu_read_lock(); return seq_hlist_start_head_rcu(&net->packet.sklist, *pos); } static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); return seq_hlist_next_rcu(v, &net->packet.sklist, pos); } static void packet_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int packet_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%*sRefCnt Type Proto Iface R Rmem User Inode\n", IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk"); else { struct sock *s = sk_entry(v); const struct packet_sock *po = pkt_sk(s); seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), READ_ONCE(po->ifindex), packet_sock_flag(po, PACKET_SOCK_RUNNING), atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), sock_i_ino(s)); } return 0; } static const struct seq_operations packet_seq_ops = { .start = packet_seq_start, .next = packet_seq_next, .stop = packet_seq_stop, .show = packet_seq_show, }; #endif static int __net_init packet_net_init(struct net *net) { mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); #ifdef CONFIG_PROC_FS if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; #endif /* CONFIG_PROC_FS */ return 0; } static void __net_exit packet_net_exit(struct net *net) { remove_proc_entry("packet", net->proc_net); WARN_ON_ONCE(!hlist_empty(&net->packet.sklist)); } static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, }; static void __exit packet_exit(void) { sock_unregister(PF_PACKET); proto_unregister(&packet_proto); unregister_netdevice_notifier(&packet_netdev_notifier); unregister_pernet_subsys(&packet_net_ops); } static int __init packet_init(void) { int rc; rc = register_pernet_subsys(&packet_net_ops); if (rc) goto out; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; rc = proto_register(&packet_proto, 0); if (rc) goto out_notifier; rc = sock_register(&packet_family_ops); if (rc) goto out_proto; return 0; out_proto: proto_unregister(&packet_proto); out_notifier: unregister_netdevice_notifier(&packet_netdev_notifier); out_pernet: unregister_pernet_subsys(&packet_net_ops); out: return rc; } module_init(packet_init); module_exit(packet_exit); MODULE_DESCRIPTION("Packet socket support (AF_PACKET)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PACKET); |
| 8 8 8 8 77 77 77 77 77 62 62 62 62 77 77 76 77 77 77 77 62 62 62 62 10 10 10 10 10 10 10 10 10 10 10 10 77 77 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 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "send.h" #include "main.h" #include <linux/atomic.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/workqueue.h> #include "distributed-arp-table.h" #include "fragmentation.h" #include "gateway_client.h" #include "hard-interface.h" #include "log.h" #include "network-coding.h" #include "originator.h" #include "routing.h" #include "soft-interface.h" #include "translation-table.h" static void batadv_send_outstanding_bcast_packet(struct work_struct *work); /** * batadv_send_skb_packet() - send an already prepared packet * @skb: the packet to send * @hard_iface: the interface to use to send the broadcast packet * @dst_addr: the payload destination * * Send out an already prepared packet to the given neighbor or broadcast it * using the specified interface. Either hard_iface or neigh_node must be not * NULL. * If neigh_node is NULL, then the packet is broadcasted using hard_iface, * otherwise it is sent as unicast to the given neighbor. * * Regardless of the return value, the skb is consumed. * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_skb_packet(struct sk_buff *skb, struct batadv_hard_iface *hard_iface, const u8 *dst_addr) { struct batadv_priv *bat_priv; struct ethhdr *ethhdr; int ret; bat_priv = netdev_priv(hard_iface->soft_iface); if (hard_iface->if_status != BATADV_IF_ACTIVE) goto send_skb_err; if (unlikely(!hard_iface->net_dev)) goto send_skb_err; if (!(hard_iface->net_dev->flags & IFF_UP)) { pr_warn("Interface %s is not up - can't send packet via that interface!\n", hard_iface->net_dev->name); goto send_skb_err; } /* push to the ethernet header. */ if (batadv_skb_head_push(skb, ETH_HLEN) < 0) goto send_skb_err; skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); ether_addr_copy(ethhdr->h_source, hard_iface->net_dev->dev_addr); ether_addr_copy(ethhdr->h_dest, dst_addr); ethhdr->h_proto = htons(ETH_P_BATMAN); skb_set_network_header(skb, ETH_HLEN); skb->protocol = htons(ETH_P_BATMAN); skb->dev = hard_iface->net_dev; /* Save a clone of the skb to use when decoding coded packets */ batadv_nc_skb_store_for_decoding(bat_priv, skb); /* dev_queue_xmit() returns a negative result on error. However on * congestion and traffic shaping, it drops and returns NET_XMIT_DROP * (which is > 0). This will not be treated as an error. */ ret = dev_queue_xmit(skb); return net_xmit_eval(ret); send_skb_err: kfree_skb(skb); return NET_XMIT_DROP; } /** * batadv_send_broadcast_skb() - Send broadcast packet via hard interface * @skb: packet to be transmitted (with batadv header and no outer eth header) * @hard_iface: outgoing interface * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_broadcast_skb(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { return batadv_send_skb_packet(skb, hard_iface, batadv_broadcast_addr); } /** * batadv_send_unicast_skb() - Send unicast packet to neighbor * @skb: packet to be transmitted (with batadv header and no outer eth header) * @neigh: neighbor which is used as next hop to destination * * Return: A negative errno code is returned on a failure. A success does not * guarantee the frame will be transmitted as it may be dropped due * to congestion or traffic shaping. */ int batadv_send_unicast_skb(struct sk_buff *skb, struct batadv_neigh_node *neigh) { #ifdef CONFIG_BATMAN_ADV_BATMAN_V struct batadv_hardif_neigh_node *hardif_neigh; #endif int ret; ret = batadv_send_skb_packet(skb, neigh->if_incoming, neigh->addr); #ifdef CONFIG_BATMAN_ADV_BATMAN_V hardif_neigh = batadv_hardif_neigh_get(neigh->if_incoming, neigh->addr); if (hardif_neigh && ret != NET_XMIT_DROP) hardif_neigh->bat_v.last_unicast_tx = jiffies; batadv_hardif_neigh_put(hardif_neigh); #endif return ret; } /** * batadv_send_skb_to_orig() - Lookup next-hop and transmit skb. * @skb: Packet to be transmitted. * @orig_node: Final destination of the packet. * @recv_if: Interface used when receiving the packet (can be NULL). * * Looks up the best next-hop towards the passed originator and passes the * skb on for preparation of MAC header. If the packet originated from this * host, NULL can be passed as recv_if and no interface alternating is * attempted. * * Return: negative errno code on a failure, -EINPROGRESS if the skb is * buffered for later transmit or the NET_XMIT status returned by the * lower routine if the packet has been passed down. */ int batadv_send_skb_to_orig(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_hard_iface *recv_if) { struct batadv_priv *bat_priv = orig_node->bat_priv; struct batadv_neigh_node *neigh_node; int ret; /* batadv_find_router() increases neigh_nodes refcount if found. */ neigh_node = batadv_find_router(bat_priv, orig_node, recv_if); if (!neigh_node) { ret = -EINVAL; goto free_skb; } /* Check if the skb is too large to send in one piece and fragment * it if needed. */ if (atomic_read(&bat_priv->fragmentation) && skb->len > neigh_node->if_incoming->net_dev->mtu) { /* Fragment and send packet. */ ret = batadv_frag_send_packet(skb, orig_node, neigh_node); /* skb was consumed */ skb = NULL; goto put_neigh_node; } /* try to network code the packet, if it is received on an interface * (i.e. being forwarded). If the packet originates from this node or if * network coding fails, then send the packet as usual. */ if (recv_if && batadv_nc_skb_forward(skb, neigh_node)) ret = -EINPROGRESS; else ret = batadv_send_unicast_skb(skb, neigh_node); /* skb was consumed */ skb = NULL; put_neigh_node: batadv_neigh_node_put(neigh_node); free_skb: kfree_skb(skb); return ret; } /** * batadv_send_skb_push_fill_unicast() - extend the buffer and initialize the * common fields for unicast packets * @skb: the skb carrying the unicast header to initialize * @hdr_size: amount of bytes to push at the beginning of the skb * @orig_node: the destination node * * Return: false if the buffer extension was not possible or true otherwise. */ static bool batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node) { struct batadv_unicast_packet *unicast_packet; u8 ttvn = (u8)atomic_read(&orig_node->last_ttvn); if (batadv_skb_head_push(skb, hdr_size) < 0) return false; unicast_packet = (struct batadv_unicast_packet *)skb->data; unicast_packet->version = BATADV_COMPAT_VERSION; /* batman packet type: unicast */ unicast_packet->packet_type = BATADV_UNICAST; /* set unicast ttl */ unicast_packet->ttl = BATADV_TTL; /* copy the destination for faster routing */ ether_addr_copy(unicast_packet->dest, orig_node->orig); /* set the destination tt version number */ unicast_packet->ttvn = ttvn; return true; } /** * batadv_send_skb_prepare_unicast() - encapsulate an skb with a unicast header * @skb: the skb containing the payload to encapsulate * @orig_node: the destination node * * Return: false if the payload could not be encapsulated or true otherwise. */ static bool batadv_send_skb_prepare_unicast(struct sk_buff *skb, struct batadv_orig_node *orig_node) { size_t uni_size = sizeof(struct batadv_unicast_packet); return batadv_send_skb_push_fill_unicast(skb, uni_size, orig_node); } /** * batadv_send_skb_prepare_unicast_4addr() - encapsulate an skb with a * unicast 4addr header * @bat_priv: the bat priv with all the soft interface information * @skb: the skb containing the payload to encapsulate * @orig: the destination node * @packet_subtype: the unicast 4addr packet subtype to use * * Return: false if the payload could not be encapsulated or true otherwise. */ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node *orig, int packet_subtype) { struct batadv_hard_iface *primary_if; struct batadv_unicast_4addr_packet *uc_4addr_packet; bool ret = false; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) goto out; /* Pull the header space and fill the unicast_packet substructure. * We can do that because the first member of the uc_4addr_packet * is of type struct unicast_packet */ if (!batadv_send_skb_push_fill_unicast(skb, sizeof(*uc_4addr_packet), orig)) goto out; uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR; ether_addr_copy(uc_4addr_packet->src, primary_if->net_dev->dev_addr); uc_4addr_packet->subtype = packet_subtype; uc_4addr_packet->reserved = 0; ret = true; out: batadv_hardif_put(primary_if); return ret; } /** * batadv_send_skb_unicast() - encapsulate and send an skb via unicast * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @orig_node: the originator to send the packet to * @vid: the vid to be used to search the translation table * * Wrap the given skb into a batman-adv unicast or unicast-4addr header * depending on whether BATADV_UNICAST or BATADV_UNICAST_4ADDR was supplied * as packet_type. Then send this frame to the given orig_node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, struct batadv_orig_node *orig_node, unsigned short vid) { struct batadv_unicast_packet *unicast_packet; struct ethhdr *ethhdr; int ret = NET_XMIT_DROP; if (!orig_node) goto out; switch (packet_type) { case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It * should never be invoked with any other packet type */ goto out; } /* skb->data might have been reallocated by * batadv_send_skb_prepare_unicast{,_4addr}() */ ethhdr = eth_hdr(skb); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route * for this client. The destination will receive this packet and will * try to reroute it because the ttvn contained in the header is less * than the current one */ if (batadv_tt_global_client_is_roaming(bat_priv, ethhdr->h_dest, vid)) unicast_packet->ttvn = unicast_packet->ttvn - 1; ret = batadv_send_skb_to_orig(skb, orig_node, NULL); /* skb was consumed */ skb = NULL; out: kfree_skb(skb); return ret; } /** * batadv_send_skb_via_tt_generic() - send an skb via TT lookup * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @packet_type: the batman unicast packet type to use * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast * 4addr packets) * @dst_hint: can be used to override the destination contained in the skb * @vid: the vid to be used to search the translation table * * Look up the recipient node for the destination address in the ethernet * header via the translation table. Wrap the given skb into a batman-adv * unicast or unicast-4addr header depending on whether BATADV_UNICAST or * BATADV_UNICAST_4ADDR was supplied as packet_type. Then send this frame * to the according destination node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv, struct sk_buff *skb, int packet_type, int packet_subtype, u8 *dst_hint, unsigned short vid) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct batadv_orig_node *orig_node; u8 *src, *dst; int ret; src = ethhdr->h_source; dst = ethhdr->h_dest; /* if we got an hint! let's send the packet to this client (if any) */ if (dst_hint) { src = NULL; dst = dst_hint; } orig_node = batadv_transtable_search(bat_priv, src, dst, vid); ret = batadv_send_skb_unicast(bat_priv, skb, packet_type, packet_subtype, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_send_skb_via_gw() - send an skb via gateway lookup * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @vid: the vid to be used to search the translation table * * Look up the currently selected gateway. Wrap the given skb into a batman-adv * unicast header and send this frame to this gateway node. * * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. */ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { struct batadv_orig_node *orig_node; int ret; orig_node = batadv_gw_get_selected_orig(bat_priv); ret = batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST_4ADDR, BATADV_P_DATA, orig_node, vid); batadv_orig_node_put(orig_node); return ret; } /** * batadv_forw_packet_free() - free a forwarding packet * @forw_packet: The packet to free * @dropped: whether the packet is freed because is dropped * * This frees a forwarding packet and releases any resources it might * have claimed. */ void batadv_forw_packet_free(struct batadv_forw_packet *forw_packet, bool dropped) { if (dropped) kfree_skb(forw_packet->skb); else consume_skb(forw_packet->skb); batadv_hardif_put(forw_packet->if_incoming); batadv_hardif_put(forw_packet->if_outgoing); if (forw_packet->queue_left) atomic_inc(forw_packet->queue_left); kfree(forw_packet); } /** * batadv_forw_packet_alloc() - allocate a forwarding packet * @if_incoming: The (optional) if_incoming to be grabbed * @if_outgoing: The (optional) if_outgoing to be grabbed * @queue_left: The (optional) queue counter to decrease * @bat_priv: The bat_priv for the mesh of this forw_packet * @skb: The raw packet this forwarding packet shall contain * * Allocates a forwarding packet and tries to get a reference to the * (optional) if_incoming, if_outgoing and queue_left. If queue_left * is NULL then bat_priv is optional, too. * * Return: An allocated forwarding packet on success, NULL otherwise. */ struct batadv_forw_packet * batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming, struct batadv_hard_iface *if_outgoing, atomic_t *queue_left, struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_forw_packet *forw_packet; const char *qname; if (queue_left && !batadv_atomic_dec_not_zero(queue_left)) { qname = "unknown"; if (queue_left == &bat_priv->bcast_queue_left) qname = "bcast"; if (queue_left == &bat_priv->batman_queue_left) qname = "batman"; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s queue is full\n", qname); return NULL; } forw_packet = kmalloc(sizeof(*forw_packet), GFP_ATOMIC); if (!forw_packet) goto err; if (if_incoming) kref_get(&if_incoming->refcount); if (if_outgoing) kref_get(&if_outgoing->refcount); INIT_HLIST_NODE(&forw_packet->list); INIT_HLIST_NODE(&forw_packet->cleanup_list); forw_packet->skb = skb; forw_packet->queue_left = queue_left; forw_packet->if_incoming = if_incoming; forw_packet->if_outgoing = if_outgoing; forw_packet->num_packets = 0; return forw_packet; err: if (queue_left) atomic_inc(queue_left); return NULL; } /** * batadv_forw_packet_was_stolen() - check whether someone stole this packet * @forw_packet: the forwarding packet to check * * This function checks whether the given forwarding packet was claimed by * someone else for free(). * * Return: True if someone stole it, false otherwise. */ static bool batadv_forw_packet_was_stolen(struct batadv_forw_packet *forw_packet) { return !hlist_unhashed(&forw_packet->cleanup_list); } /** * batadv_forw_packet_steal() - claim a forw_packet for free() * @forw_packet: the forwarding packet to steal * @lock: a key to the store to steal from (e.g. forw_{bat,bcast}_list_lock) * * This function tries to steal a specific forw_packet from global * visibility for the purpose of getting it for free(). That means * the caller is *not* allowed to requeue it afterwards. * * Return: True if stealing was successful. False if someone else stole it * before us. */ bool batadv_forw_packet_steal(struct batadv_forw_packet *forw_packet, spinlock_t *lock) { /* did purging routine steal it earlier? */ spin_lock_bh(lock); if (batadv_forw_packet_was_stolen(forw_packet)) { spin_unlock_bh(lock); return false; } hlist_del_init(&forw_packet->list); /* Just to spot misuse of this function */ hlist_add_fake(&forw_packet->cleanup_list); spin_unlock_bh(lock); return true; } /** * batadv_forw_packet_list_steal() - claim a list of forward packets for free() * @forw_list: the to be stolen forward packets * @cleanup_list: a backup pointer, to be able to dispose the packet later * @hard_iface: the interface to steal forward packets from * * This function claims responsibility to free any forw_packet queued on the * given hard_iface. If hard_iface is NULL forwarding packets on all hard * interfaces will be claimed. * * The packets are being moved from the forw_list to the cleanup_list. This * makes it possible for already running threads to notice the claim. */ static void batadv_forw_packet_list_steal(struct hlist_head *forw_list, struct hlist_head *cleanup_list, const struct batadv_hard_iface *hard_iface) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, forw_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ if (hard_iface && forw_packet->if_incoming != hard_iface && forw_packet->if_outgoing != hard_iface) continue; hlist_del(&forw_packet->list); hlist_add_head(&forw_packet->cleanup_list, cleanup_list); } } /** * batadv_forw_packet_list_free() - free a list of forward packets * @head: a list of to be freed forw_packets * * This function cancels the scheduling of any packet in the provided list, * waits for any possibly running packet forwarding thread to finish and * finally, safely frees this forward packet. * * This function might sleep. */ static void batadv_forw_packet_list_free(struct hlist_head *head) { struct batadv_forw_packet *forw_packet; struct hlist_node *safe_tmp_node; hlist_for_each_entry_safe(forw_packet, safe_tmp_node, head, cleanup_list) { cancel_delayed_work_sync(&forw_packet->delayed_work); hlist_del(&forw_packet->cleanup_list); batadv_forw_packet_free(forw_packet, true); } } /** * batadv_forw_packet_queue() - try to queue a forwarding packet * @forw_packet: the forwarding packet to queue * @lock: a key to the store (e.g. forw_{bat,bcast}_list_lock) * @head: the shelve to queue it on (e.g. forw_{bat,bcast}_list) * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a forwarding packet. Requeuing * is prevented if the according interface is shutting down * (e.g. if batadv_forw_packet_list_steal() was called for this * packet earlier). * * Calling batadv_forw_packet_queue() after a call to * batadv_forw_packet_steal() is forbidden! * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_queue(struct batadv_forw_packet *forw_packet, spinlock_t *lock, struct hlist_head *head, unsigned long send_time) { spin_lock_bh(lock); /* did purging routine steal it from us? */ if (batadv_forw_packet_was_stolen(forw_packet)) { /* If you got it for free() without trouble, then * don't get back into the queue after stealing... */ WARN_ONCE(hlist_fake(&forw_packet->cleanup_list), "Requeuing after batadv_forw_packet_steal() not allowed!\n"); spin_unlock_bh(lock); return; } hlist_del_init(&forw_packet->list); hlist_add_head(&forw_packet->list, head); queue_delayed_work(batadv_event_workqueue, &forw_packet->delayed_work, send_time - jiffies); spin_unlock_bh(lock); } /** * batadv_forw_packet_bcast_queue() - try to queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue a broadcast packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ static void batadv_forw_packet_bcast_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bcast_list_lock, &bat_priv->forw_bcast_list, send_time); } /** * batadv_forw_packet_ogmv1_queue() - try to queue an OGMv1 packet * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the forwarding packet to queue * @send_time: timestamp (jiffies) when the packet is to be sent * * This function tries to (re)queue an OGMv1 packet. * * Caller needs to ensure that forw_packet->delayed_work was initialized. */ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet, unsigned long send_time) { batadv_forw_packet_queue(forw_packet, &bat_priv->forw_bat_list_lock, &bat_priv->forw_bat_list, send_time); } /** * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to queue on * * Adds a broadcast packet to the queue and sets up timers. Broadcast packets * are sent multiple times to increase probability for being received. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { struct batadv_forw_packet *forw_packet; unsigned long send_time = jiffies; struct sk_buff *newskb; newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) goto err; forw_packet = batadv_forw_packet_alloc(if_in, if_out, &bat_priv->bcast_queue_left, bat_priv, newskb); if (!forw_packet) goto err_packet_free; forw_packet->own = own_packet; INIT_DELAYED_WORK(&forw_packet->delayed_work, batadv_send_outstanding_bcast_packet); send_time += delay ? delay : msecs_to_jiffies(5); batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return NETDEV_TX_OK; err_packet_free: kfree_skb(newskb); err: return NETDEV_TX_BUSY; } /** * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * @if_in: the interface where the packet was received on * @if_out: the outgoing interface to forward to * * Transmits a broadcast packet on the specified interface either immediately * or if a delay is given after that. Furthermore, queues additional * retransmissions if this interface is a wireless one. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the original skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet, struct batadv_hard_iface *if_in, struct batadv_hard_iface *if_out) { unsigned int num_bcasts = if_out->num_bcasts; struct sk_buff *newskb; int ret = NETDEV_TX_OK; if (!delay) { newskb = skb_clone(skb, GFP_ATOMIC); if (!newskb) return NETDEV_TX_BUSY; batadv_send_broadcast_skb(newskb, if_out); num_bcasts--; } /* delayed broadcast or rebroadcasts? */ if (num_bcasts >= 1) { BATADV_SKB_CB(skb)->num_bcasts = num_bcasts; ret = batadv_forw_bcast_packet_to_list(bat_priv, skb, delay, own_packet, if_in, if_out); } return ret; } /** * batadv_send_no_broadcast() - check whether (re)broadcast is necessary * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to check * @own_packet: true if it is a self-generated broadcast packet * @if_out: the outgoing interface checked and considered for (re)broadcast * * Return: False if a packet needs to be (re)broadcasted on the given interface, * true otherwise. */ static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv, struct sk_buff *skb, bool own_packet, struct batadv_hard_iface *if_out) { struct batadv_hardif_neigh_node *neigh_node = NULL; struct batadv_bcast_packet *bcast_packet; u8 *orig_neigh; u8 *neigh_addr; char *type; int ret; if (!own_packet) { neigh_addr = eth_hdr(skb)->h_source; neigh_node = batadv_hardif_neigh_get(if_out, neigh_addr); } bcast_packet = (struct batadv_bcast_packet *)skb->data; orig_neigh = neigh_node ? neigh_node->orig : NULL; ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig, orig_neigh); batadv_hardif_neigh_put(neigh_node); /* ok, may broadcast */ if (!ret) return false; /* no broadcast */ switch (ret) { case BATADV_HARDIF_BCAST_NORECIPIENT: type = "no neighbor"; break; case BATADV_HARDIF_BCAST_DUPFWD: type = "single neighbor is source"; break; case BATADV_HARDIF_BCAST_DUPORIG: type = "single neighbor is originator"; break; default: type = "unknown"; } batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n", bcast_packet->orig, if_out->net_dev->name, type); return true; } /** * __batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * This call clones the given skb, hence the caller needs to take into * account that the data segment of the given skb might not be * modifiable anymore. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { struct batadv_hard_iface *hard_iface; struct batadv_hard_iface *primary_if; int ret = NETDEV_TX_OK; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if) return NETDEV_TX_BUSY; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != bat_priv->soft_iface) continue; if (!kref_get_unless_zero(&hard_iface->refcount)) continue; if (batadv_send_no_broadcast(bat_priv, skb, own_packet, hard_iface)) { batadv_hardif_put(hard_iface); continue; } ret = batadv_forw_bcast_packet_if(bat_priv, skb, delay, own_packet, primary_if, hard_iface); batadv_hardif_put(hard_iface); if (ret == NETDEV_TX_BUSY) break; } rcu_read_unlock(); batadv_hardif_put(primary_if); return ret; } /** * batadv_forw_bcast_packet() - forward and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { return __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); } /** * batadv_send_bcast_packet() - send and queue a broadcast packet * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet * * Transmits a broadcast packet either immediately or if a delay is given * after that. Furthermore, queues additional retransmissions on wireless * interfaces. * * Consumes the provided skb. */ void batadv_send_bcast_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned long delay, bool own_packet) { __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); consume_skb(skb); } /** * batadv_forw_packet_bcasts_left() - check if a retransmission is necessary * @forw_packet: the forwarding packet to check * * Checks whether a given packet has any (re)transmissions left on the provided * interface. * * hard_iface may be NULL: In that case the number of transmissions this skb had * so far is compared with the maximum amount of retransmissions independent of * any interface instead. * * Return: True if (re)transmissions are left, false otherwise. */ static bool batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet) { return BATADV_SKB_CB(forw_packet->skb)->num_bcasts; } /** * batadv_forw_packet_bcasts_dec() - decrement retransmission counter of a * packet * @forw_packet: the packet to decrease the counter for */ static void batadv_forw_packet_bcasts_dec(struct batadv_forw_packet *forw_packet) { BATADV_SKB_CB(forw_packet->skb)->num_bcasts--; } /** * batadv_forw_packet_is_rebroadcast() - check packet for previous transmissions * @forw_packet: the packet to check * * Return: True if this packet was transmitted before, false otherwise. */ bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet) { unsigned char num_bcasts = BATADV_SKB_CB(forw_packet->skb)->num_bcasts; return num_bcasts != forw_packet->if_outgoing->num_bcasts; } /** * batadv_send_outstanding_bcast_packet() - transmit a queued broadcast packet * @work: work queue item * * Transmits a queued broadcast packet and if necessary reschedules it. */ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) { unsigned long send_time = jiffies + msecs_to_jiffies(5); struct batadv_forw_packet *forw_packet; struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct sk_buff *skb1; bool dropped = false; delayed_work = to_delayed_work(work); forw_packet = container_of(delayed_work, struct batadv_forw_packet, delayed_work); bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) { dropped = true; goto out; } if (batadv_dat_drop_broadcast_packet(bat_priv, forw_packet)) { dropped = true; goto out; } /* send a copy of the saved skb */ skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); if (!skb1) goto out; batadv_send_broadcast_skb(skb1, forw_packet->if_outgoing); batadv_forw_packet_bcasts_dec(forw_packet); if (batadv_forw_packet_bcasts_left(forw_packet)) { batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return; } out: /* do we get something for free()? */ if (batadv_forw_packet_steal(forw_packet, &bat_priv->forw_bcast_list_lock)) batadv_forw_packet_free(forw_packet, dropped); } /** * batadv_purge_outstanding_packets() - stop/purge scheduled bcast/OGMv1 packets * @bat_priv: the bat priv with all the soft interface information * @hard_iface: the hard interface to cancel and purge bcast/ogm packets on * * This method cancels and purges any broadcast and OGMv1 packet on the given * hard_iface. If hard_iface is NULL, broadcast and OGMv1 packets on all hard * interfaces will be canceled and purged. * * This function might sleep. */ void batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface) { struct hlist_head head = HLIST_HEAD_INIT; if (hard_iface) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s(): %s\n", __func__, hard_iface->net_dev->name); else batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s()\n", __func__); /* claim bcast list for free() */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bcast_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bcast_list_lock); /* claim batman packet list for free() */ spin_lock_bh(&bat_priv->forw_bat_list_lock); batadv_forw_packet_list_steal(&bat_priv->forw_bat_list, &head, hard_iface); spin_unlock_bh(&bat_priv->forw_bat_list_lock); /* then cancel or wait for packet workers to finish and free */ batadv_forw_packet_list_free(&head); } |
| 256 1144 1144 152 1066 1145 1066 152 1123 668 669 46 625 669 77 77 77 77 36 58 84 84 36 72 72 12 12 803 794 49 794 794 49 794 803 803 803 803 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 | // SPDX-License-Identifier: GPL-2.0-only /* * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> #include <linux/cpu.h> #include <asm/sections.h> /* mutex to protect coming/going of the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); void jump_label_lock(void) { mutex_lock(&jump_label_mutex); } void jump_label_unlock(void) { mutex_unlock(&jump_label_mutex); } static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; const struct jump_entry *jeb = b; /* * Entrires are sorted by key. */ if (jump_entry_key(jea) < jump_entry_key(jeb)) return -1; if (jump_entry_key(jea) > jump_entry_key(jeb)) return 1; /* * In the batching mode, entries should also be sorted by the code * inside the already sorted list of entries, enabling a bsearch in * the vector. */ if (jump_entry_code(jea) < jump_entry_code(jeb)) return -1; if (jump_entry_code(jea) > jump_entry_code(jeb)) return 1; return 0; } static void jump_label_swap(void *a, void *b, int size) { long delta = (unsigned long)a - (unsigned long)b; struct jump_entry *jea = a; struct jump_entry *jeb = b; struct jump_entry tmp = *jea; jea->code = jeb->code - delta; jea->target = jeb->target - delta; jea->key = jeb->key - delta; jeb->code = tmp.code + delta; jeb->target = tmp.target + delta; jeb->key = tmp.key + delta; } static void jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; void *swapfn = NULL; if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE)) swapfn = jump_label_swap; size = (((unsigned long)stop - (unsigned long)start) / sizeof(struct jump_entry)); sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn); } static void jump_label_update(struct static_key *key); /* * There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h. * The use of 'atomic_read()' requires atomic.h and its problematic for some * kernel headers such as kernel.h and others. Since static_key_count() is not * used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok * to have it be a function here. Similarly, for 'static_key_enable()' and * 'static_key_disable()', which require bug.h. This should allow jump_label.h * to be included from most/all places for CONFIG_JUMP_LABEL. */ int static_key_count(struct static_key *key) { /* * -1 means the first static_key_slow_inc() is in progress. * static_key_enabled() must return true, so return 1 here. */ int n = atomic_read(&key->enabled); return n >= 0 ? n : 1; } EXPORT_SYMBOL_GPL(static_key_count); /* * static_key_fast_inc_not_disabled - adds a user for a static key * @key: static key that must be already enabled * * The caller must make sure that the static key can't get disabled while * in this function. It doesn't patch jump labels, only adds a user to * an already enabled static key. * * Returns true if the increment was done. Unlike refcount_t the ref counter * is not saturated, but will fail to increment on overflow. */ bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Negative key->enabled has a special meaning: it sends * static_key_slow_inc() down the slow path, and it is non-zero * so it counts as "enabled" in jump_label_update(). Note that * atomic_inc_unless_negative() checks >= 0, so roll our own. */ v = atomic_read(&key->enabled); do { if (v <= 0 || (v + 1) < 0) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled); bool static_key_slow_inc_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc() calls; * later calls must wait for the first one to _finish_ the * jump_label_update() process. At the same time, however, * the jump_label_update() call below wants to see * static_key_enabled(&key) for jumps to be updated properly. */ if (static_key_fast_inc_not_disabled(key)) return true; jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * Ensure that if the above cmpxchg loop observes our positive * value, it must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); } else { if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) { jump_label_unlock(); return false; } } jump_label_unlock(); return true; } bool static_key_slow_inc(struct static_key *key) { bool ret; cpus_read_lock(); ret = static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * See static_key_slow_inc(). */ atomic_set_release(&key->enabled, 1); } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked); void static_key_enable(struct static_key *key) { cpus_read_lock(); static_key_enable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } jump_label_lock(); if (atomic_cmpxchg(&key->enabled, 1, 0)) jump_label_update(key); jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked); void static_key_disable(struct static_key *key) { cpus_read_lock(); static_key_disable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable); static bool static_key_slow_try_dec(struct static_key *key) { int val; val = atomic_fetch_add_unless(&key->enabled, -1, 1); if (val == 1) return false; /* * The negative count check is valid even when a negative * key->enabled is in use by static_key_slow_inc(); a * __static_key_slow_dec() before the first static_key_slow_inc() * returns is unbalanced, because all other static_key_slow_inc() * instances block while the update is in progress. */ WARN(val < 0, "jump label: negative count!\n"); return true; } static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); if (static_key_slow_try_dec(key)) return; jump_label_lock(); if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); jump_label_unlock(); } static void __static_key_slow_dec(struct static_key *key) { cpus_read_lock(); __static_key_slow_dec_cpuslocked(key); cpus_read_unlock(); } void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); __static_key_slow_dec(&key->key); } EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(key); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec_cpuslocked(key); } void __static_key_slow_dec_deferred(struct static_key *key, struct delayed_work *work, unsigned long timeout) { STATIC_KEY_CHECK_USE(key); if (static_key_slow_try_dec(key)) return; schedule_delayed_work(work, timeout); } EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); flush_delayed_work(work); } EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { STATIC_KEY_CHECK_USE(key); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { if (jump_entry_code(entry) <= (unsigned long)end && jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start) return 1; return 0; } static int __jump_label_text_reserved(struct jump_entry *iter_start, struct jump_entry *iter_stop, void *start, void *end, bool init) { struct jump_entry *iter; iter = iter_start; while (iter < iter_stop) { if (init || !jump_entry_is_init(iter)) { if (addr_conflict(iter, start, end)) return 1; } iter++; } return 0; } #ifndef arch_jump_label_transform_static static void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { /* nothing to do on most architectures */ } #endif static inline struct jump_entry *static_key_entries(struct static_key *key) { WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED); return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK); } static inline bool static_key_type(struct static_key *key) { return key->type & JUMP_TYPE_TRUE; } static inline bool static_key_linked(struct static_key *key) { return key->type & JUMP_TYPE_LINKED; } static inline void static_key_clear_linked(struct static_key *key) { key->type &= ~JUMP_TYPE_LINKED; } static inline void static_key_set_linked(struct static_key *key) { key->type |= JUMP_TYPE_LINKED; } /*** * A 'struct static_key' uses a union such that it either points directly * to a table of 'struct jump_entry' or to a linked list of modules which in * turn point to 'struct jump_entry' tables. * * The two lower bits of the pointer are used to keep track of which pointer * type is in use and to store the initial branch direction, we use an access * function which preserves these bits. */ static void static_key_set_entries(struct static_key *key, struct jump_entry *entries) { unsigned long type; WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->entries = entries; key->type |= type; } static enum jump_label_type jump_label_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool enabled = static_key_enabled(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return enabled ^ branch; } static bool jump_label_can_update(struct jump_entry *entry, bool init) { /* * Cannot update code that was in an init text area. */ if (!init && jump_entry_is_init(entry)) return false; if (!kernel_text_address(jump_entry_code(entry))) { /* * This skips patching built-in __exit, which * is part of init_section_contains() but is * not part of kernel_text_address(). * * Skipping built-in __exit is fine since it * will never be executed. */ WARN_ONCE(!jump_entry_is_init(entry), "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); return false; } return true; } #ifndef HAVE_JUMP_LABEL_BATCH static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (jump_label_can_update(entry, init)) arch_jump_label_transform(entry, jump_label_type(entry)); } } #else static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (!jump_label_can_update(entry, init)) continue; if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) { /* * Queue is full: Apply the current queue and try again. */ arch_jump_label_transform_apply(); BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry))); } } arch_jump_label_transform_apply(); } #endif void __init jump_label_init(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct static_key *key = NULL; struct jump_entry *iter; /* * Since we are initializing the static_key.enabled field with * with the 'raw' int values (to avoid pulling in atomic.h) in * jump_label.h, let's make sure that is safe. There are only two * cases to check since we initialize to 0 or 1. */ BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0); BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1); if (static_key_initialized) return; cpus_read_lock(); jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; /* rewrite NOPs */ if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); in_init = init_section_contains((void *)jump_entry_code(iter), 1); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; static_key_set_entries(key, iter); } static_key_initialized = true; jump_label_unlock(); cpus_read_unlock(); } #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool type = static_key_type(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return type ^ branch; } struct static_key_mod { struct static_key_mod *next; struct jump_entry *entries; struct module *mod; }; static inline struct static_key_mod *static_key_mod(struct static_key *key) { WARN_ON_ONCE(!static_key_linked(key)); return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK); } /*** * key->type and key->next are the same via union. * This sets key->next and preserves the type bits. * * See additional comments above static_key_set_entries(). */ static void static_key_set_mod(struct static_key *key, struct static_key_mod *mod) { unsigned long type; WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->next = mod; key->type |= type; } static int __jump_label_mod_text_reserved(void *start, void *end) { struct module *mod; int ret; preempt_disable(); mod = __module_text_address((unsigned long)start); WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); if (!try_module_get(mod)) mod = NULL; preempt_enable(); if (!mod) return 0; ret = __jump_label_text_reserved(mod->jump_entries, mod->jump_entries + mod->num_jump_entries, start, end, mod->state == MODULE_STATE_COMING); module_put(mod); return ret; } static void __jump_label_mod_update(struct static_key *key) { struct static_key_mod *mod; for (mod = static_key_mod(key); mod; mod = mod->next) { struct jump_entry *stop; struct module *m; /* * NULL if the static_key is defined in a module * that does not use it */ if (!mod->entries) continue; m = mod->mod; if (!m) stop = __stop___jump_table; else stop = m->jump_entries + m->num_jump_entries; __jump_label_update(key, mod->entries, stop, m && m->state == MODULE_STATE_COMING); } } static int jump_label_add_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, *jlm2; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) return 0; jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; in_init = within_module_init(jump_entry_code(iter), mod); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; if (within_module((unsigned long)key, mod)) { static_key_set_entries(key, iter); continue; } jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; if (!static_key_linked(key)) { jlm2 = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm2) { kfree(jlm); return -ENOMEM; } preempt_disable(); jlm2->mod = __module_address((unsigned long)key); preempt_enable(); jlm2->entries = static_key_entries(key); jlm2->next = NULL; static_key_set_mod(key, jlm2); static_key_set_linked(key); } jlm->mod = mod; jlm->entries = iter; jlm->next = static_key_mod(key); static_key_set_mod(key, jlm); static_key_set_linked(key); /* Only update if we've changed from our initial state */ if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } return 0; } static void jump_label_del_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, **prev; for (iter = iter_start; iter < iter_stop; iter++) { if (jump_entry_key(iter) == key) continue; key = jump_entry_key(iter); if (within_module((unsigned long)key, mod)) continue; /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; prev = &key->next; jlm = static_key_mod(key); while (jlm && jlm->mod != mod) { prev = &jlm->next; jlm = jlm->next; } /* No memory during module load */ if (WARN_ON(!jlm)) continue; if (prev == &key->next) static_key_set_mod(key, jlm->next); else *prev = jlm->next; kfree(jlm); jlm = static_key_mod(key); /* if only one etry is left, fold it back into the static_key */ if (jlm->next == NULL) { static_key_set_entries(key, jlm->entries); static_key_clear_linked(key); kfree(jlm); } } } static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; int ret = 0; cpus_read_lock(); jump_label_lock(); switch (val) { case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; case MODULE_STATE_GOING: jump_label_del_module(mod); break; } jump_label_unlock(); cpus_read_unlock(); return notifier_from_errno(ret); } static struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, .priority = 1, /* higher than tracepoints */ }; static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ /*** * jump_label_text_reserved - check if addr range is reserved * @start: start text addr * @end: end text addr * * checks if the text addr located between @start and @end * overlaps with any of the jump label patch addresses. Code * that wants to modify kernel text should first verify that * it does not overlap with any of the jump label addresses. * Caller must hold jump_label_mutex. * * returns 1 if there is an overlap, 0 otherwise */ int jump_label_text_reserved(void *start, void *end) { bool init = system_state < SYSTEM_RUNNING; int ret = __jump_label_text_reserved(__start___jump_table, __stop___jump_table, start, end, init); if (ret) return ret; #ifdef CONFIG_MODULES ret = __jump_label_mod_text_reserved(start, end); #endif return ret; } static void jump_label_update(struct static_key *key) { struct jump_entry *stop = __stop___jump_table; bool init = system_state < SYSTEM_RUNNING; struct jump_entry *entry; #ifdef CONFIG_MODULES struct module *mod; if (static_key_linked(key)) { __jump_label_mod_update(key); return; } preempt_disable(); mod = __module_address((unsigned long)key); if (mod) { stop = mod->jump_entries + mod->num_jump_entries; init = mod->state == MODULE_STATE_COMING; } preempt_enable(); #endif entry = static_key_entries(key); /* if there are no users, entry can be NULL */ if (entry) __jump_label_update(key, entry, stop, init); } #ifdef CONFIG_STATIC_KEYS_SELFTEST static DEFINE_STATIC_KEY_TRUE(sk_true); static DEFINE_STATIC_KEY_FALSE(sk_false); static __init int jump_label_test(void) { int i; for (i = 0; i < 2; i++) { WARN_ON(static_key_enabled(&sk_true.key) != true); WARN_ON(static_key_enabled(&sk_false.key) != false); WARN_ON(!static_branch_likely(&sk_true)); WARN_ON(!static_branch_unlikely(&sk_true)); WARN_ON(static_branch_likely(&sk_false)); WARN_ON(static_branch_unlikely(&sk_false)); static_branch_disable(&sk_true); static_branch_enable(&sk_false); WARN_ON(static_key_enabled(&sk_true.key) == true); WARN_ON(static_key_enabled(&sk_false.key) == false); WARN_ON(static_branch_likely(&sk_true)); WARN_ON(static_branch_unlikely(&sk_true)); WARN_ON(!static_branch_likely(&sk_false)); WARN_ON(!static_branch_unlikely(&sk_false)); static_branch_enable(&sk_true); static_branch_disable(&sk_false); } return 0; } early_initcall(jump_label_test); #endif /* STATIC_KEYS_SELFTEST */ |
| 179 166 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/if_vlan.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/tc_act/tc_vlan.h> #include <net/tc_act/tc_vlan.h> static struct tc_action_ops act_vlan_ops; TC_INDIRECT_SCOPE int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_vlan *v = to_vlan(a); struct tcf_vlan_params *p; int action; int err; u16 tci; tcf_lastuse_update(&v->tcf_tm); tcf_action_update_bstats(&v->common, skb); /* Ensure 'data' points at mac_header prior calling vlan manipulating * functions. */ if (skb_at_tc_ingress(skb)) skb_push_rcsum(skb, skb->mac_len); action = READ_ONCE(v->tcf_action); p = rcu_dereference_bh(v->vlan_p); switch (p->tcfv_action) { case TCA_VLAN_ACT_POP: err = skb_vlan_pop(skb); if (err) goto drop; break; case TCA_VLAN_ACT_PUSH: err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid | (p->tcfv_push_prio << VLAN_PRIO_SHIFT)); if (err) goto drop; break; case TCA_VLAN_ACT_MODIFY: /* No-op if no vlan tag (either hw-accel or in-payload) */ if (!skb_vlan_tagged(skb)) goto out; /* extract existing tag (and guarantee no hw-accel tag) */ if (skb_vlan_tag_present(skb)) { tci = skb_vlan_tag_get(skb); __vlan_hwaccel_clear_tag(skb); } else { /* in-payload vlan tag, pop it */ err = __skb_vlan_pop(skb, &tci); if (err) goto drop; } /* replace the vid */ tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid; /* replace prio bits, if tcfv_push_prio specified */ if (p->tcfv_push_prio_exists) { tci &= ~VLAN_PRIO_MASK; tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT; } /* put updated tci as hwaccel tag */ __vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci); break; case TCA_VLAN_ACT_POP_ETH: err = skb_eth_pop(skb); if (err) goto drop; break; case TCA_VLAN_ACT_PUSH_ETH: err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src); if (err) goto drop; break; default: BUG(); } out: if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); return action; drop: tcf_action_inc_drop_qstats(&v->common); return TC_ACT_SHOT; } static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { [TCA_VLAN_UNSPEC] = { .strict_start_type = TCA_VLAN_PUSH_ETH_DST }, [TCA_VLAN_PARMS] = { .len = sizeof(struct tc_vlan) }, [TCA_VLAN_PUSH_VLAN_ID] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PROTOCOL] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PRIORITY] = { .type = NLA_U8 }, [TCA_VLAN_PUSH_ETH_DST] = NLA_POLICY_ETH_ADDR, [TCA_VLAN_PUSH_ETH_SRC] = NLA_POLICY_ETH_ADDR, }; static int tcf_vlan_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_vlan_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_VLAN_MAX + 1]; struct tcf_chain *goto_ch = NULL; bool push_prio_exists = false; struct tcf_vlan_params *p; struct tc_vlan *parm; struct tcf_vlan *v; int action; u16 push_vid = 0; __be16 push_proto = 0; u8 push_prio = 0; bool exists = false; int ret = 0, err; u32 index; if (!nla) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_VLAN_MAX, nla, vlan_policy, NULL); if (err < 0) return err; if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; switch (parm->v_action) { case TCA_VLAN_ACT_POP: break; case TCA_VLAN_ACT_PUSH: case TCA_VLAN_ACT_MODIFY: if (!tb[TCA_VLAN_PUSH_VLAN_ID]) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); if (push_vid >= VLAN_VID_MASK) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -ERANGE; } if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) { push_proto = nla_get_be16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]); switch (push_proto) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): break; default: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EPROTONOSUPPORT; } } else { push_proto = htons(ETH_P_8021Q); } push_prio_exists = !!tb[TCA_VLAN_PUSH_VLAN_PRIORITY]; if (push_prio_exists) push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]); break; case TCA_VLAN_ACT_POP_ETH: break; case TCA_VLAN_ACT_PUSH_ETH: if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } break; default: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } action = parm->v_action; if (!exists) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_vlan_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else 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 release_idr; v = to_vlan(*a); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) { err = -ENOMEM; goto put_chain; } p->tcfv_action = action; p->tcfv_push_vid = push_vid; p->tcfv_push_prio = push_prio; p->tcfv_push_prio_exists = push_prio_exists || action == TCA_VLAN_ACT_PUSH; p->tcfv_push_proto = push_proto; if (action == TCA_VLAN_ACT_PUSH_ETH) { nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST], ETH_ALEN); nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC], ETH_ALEN); } spin_lock_bh(&v->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock)); spin_unlock_bh(&v->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) kfree_rcu(p, rcu); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static void tcf_vlan_cleanup(struct tc_action *a) { struct tcf_vlan *v = to_vlan(a); struct tcf_vlan_params *p; p = rcu_dereference_protected(v->vlan_p, 1); if (p) kfree_rcu(p, rcu); } static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_vlan *v = to_vlan(a); struct tcf_vlan_params *p; struct tc_vlan opt = { .index = v->tcf_index, .refcnt = refcount_read(&v->tcf_refcnt) - ref, .bindcnt = atomic_read(&v->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&v->tcf_lock); opt.action = v->tcf_action; p = rcu_dereference_protected(v->vlan_p, lockdep_is_held(&v->tcf_lock)); opt.v_action = p->tcfv_action; if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if ((p->tcfv_action == TCA_VLAN_ACT_PUSH || p->tcfv_action == TCA_VLAN_ACT_MODIFY) && (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, p->tcfv_push_proto) || (p->tcfv_push_prio_exists && nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, p->tcfv_push_prio)))) goto nla_put_failure; if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) { if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN, p->tcfv_push_dst)) goto nla_put_failure; if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN, p->tcfv_push_src)) goto nla_put_failure; } tcf_tm_dump(&t, &v->tcf_tm); if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD)) goto nla_put_failure; spin_unlock_bh(&v->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&v->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_vlan *v = to_vlan(a); struct tcf_t *tm = &v->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static size_t tcf_vlan_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_vlan)) + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */ + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */ + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ } static int tcf_vlan_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; switch (tcf_vlan_action(act)) { case TCA_VLAN_ACT_PUSH: entry->id = FLOW_ACTION_VLAN_PUSH; entry->vlan.vid = tcf_vlan_push_vid(act); entry->vlan.proto = tcf_vlan_push_proto(act); entry->vlan.prio = tcf_vlan_push_prio(act); break; case TCA_VLAN_ACT_POP: entry->id = FLOW_ACTION_VLAN_POP; break; case TCA_VLAN_ACT_MODIFY: entry->id = FLOW_ACTION_VLAN_MANGLE; entry->vlan.vid = tcf_vlan_push_vid(act); entry->vlan.proto = tcf_vlan_push_proto(act); entry->vlan.prio = tcf_vlan_push_prio(act); break; case TCA_VLAN_ACT_POP_ETH: entry->id = FLOW_ACTION_VLAN_POP_ETH; break; case TCA_VLAN_ACT_PUSH_ETH: entry->id = FLOW_ACTION_VLAN_PUSH_ETH; tcf_vlan_push_eth(entry->vlan_push_eth.src, entry->vlan_push_eth.dst, act); break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported vlan action mode offload"); return -EOPNOTSUPP; } *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; switch (tcf_vlan_action(act)) { case TCA_VLAN_ACT_PUSH: fl_action->id = FLOW_ACTION_VLAN_PUSH; break; case TCA_VLAN_ACT_POP: fl_action->id = FLOW_ACTION_VLAN_POP; break; case TCA_VLAN_ACT_MODIFY: fl_action->id = FLOW_ACTION_VLAN_MANGLE; break; case TCA_VLAN_ACT_POP_ETH: fl_action->id = FLOW_ACTION_VLAN_POP_ETH; break; case TCA_VLAN_ACT_PUSH_ETH: fl_action->id = FLOW_ACTION_VLAN_PUSH_ETH; break; default: return -EOPNOTSUPP; } } return 0; } static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .id = TCA_ID_VLAN, .owner = THIS_MODULE, .act = tcf_vlan_act, .dump = tcf_vlan_dump, .init = tcf_vlan_init, .cleanup = tcf_vlan_cleanup, .stats_update = tcf_vlan_stats_update, .get_fill_size = tcf_vlan_get_fill_size, .offload_act_setup = tcf_vlan_offload_act_setup, .size = sizeof(struct tcf_vlan), }; static __net_init int vlan_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_vlan_ops.net_id); return tc_action_net_init(net, tn, &act_vlan_ops); } static void __net_exit vlan_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_vlan_ops.net_id); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit_batch = vlan_exit_net, .id = &act_vlan_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init vlan_init_module(void) { return tcf_register_action(&act_vlan_ops, &vlan_net_ops); } static void __exit vlan_cleanup_module(void) { tcf_unregister_action(&act_vlan_ops, &vlan_net_ops); } module_init(vlan_init_module); module_exit(vlan_cleanup_module); MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>"); MODULE_DESCRIPTION("vlan manipulation actions"); MODULE_LICENSE("GPL v2"); |
| 7 7 3 3 1 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * GRE GSO support */ #include <linux/skbuff.h> #include <linux/init.h> #include <net/protocol.h> #include <net/gre.h> #include <net/gro.h> #include <net/gso.h> static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool need_csum, offload_csum, gso_partial, need_ipsec; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; if (!skb->encapsulation) goto out; if (unlikely(tnl_hlen < sizeof(struct gre_base_hdr))) goto out; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; /* setup inner skb. */ skb->encapsulation = 0; SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = skb->inner_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM); skb->encap_hdr_csum = need_csum; features &= skb->dev->hw_enc_features; if (need_csum) features &= ~NETIF_F_SCTP_CRC; need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && (skb->dev->features & NETIF_F_HW_CSUM)); /* segment inner packet. */ segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, mac_len); goto out; } gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); outer_hlen = skb_tnl_header_len(skb); gre_offset = outer_hlen - tnl_hlen; skb = segs; do { struct gre_base_hdr *greh; __sum16 *pcsum; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb->mac_len = mac_len; skb->protocol = protocol; __skb_push(skb, outer_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, gre_offset); if (!need_csum) continue; greh = (struct gre_base_hdr *)skb_transport_header(skb); pcsum = (__sum16 *)(greh + 1); if (gso_partial && skb_is_gso(skb)) { unsigned int partial_adj; /* Adjust checksum to account for the fact that * the partial checksum is based on actual size * whereas headers should be based on MSS size. */ partial_adj = skb->len + skb_headroom(skb) - SKB_GSO_CB(skb)->data_offset - skb_shinfo(skb)->gso_size; *pcsum = ~csum_fold((__force __wsum)htonl(partial_adj)); } else { *pcsum = 0; } *(pcsum + 1) = 0; if (skb->encapsulation || !offload_csum) { *pcsum = gso_make_checksum(skb, 0); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = sizeof(*greh); } } while ((skb = skb->next)); out: return segs; } static struct sk_buff *gre_gro_receive(struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct sk_buff *p; const struct gre_base_hdr *greh; unsigned int hlen, grehlen; unsigned int off; int flush = 1; struct packet_offload *ptype; __be16 type; if (NAPI_GRO_CB(skb)->encap_mark) goto out; NAPI_GRO_CB(skb)->encap_mark = 1; off = skb_gro_offset(skb); hlen = off + sizeof(*greh); greh = skb_gro_header(skb, hlen, off); if (unlikely(!greh)) goto out; /* Only support version 0 and K (key), C (csum) flags. Note that * although the support for the S (seq#) flag can be added easily * for GRO, this is problematic for GSO hence can not be enabled * here because a GRO pkt may end up in the forwarding path, thus * requiring GSO support to break it up correctly. */ if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0) goto out; /* We can only support GRE_CSUM if we can track the location of * the GRE header. In the case of FOU/GUE we cannot because the * outer UDP header displaces the GRE header leaving us in a state * of limbo. */ if ((greh->flags & GRE_CSUM) && NAPI_GRO_CB(skb)->is_fou) goto out; type = greh->protocol; ptype = gro_find_receive_by_type(type); if (!ptype) goto out; grehlen = GRE_HEADER_SECTION; if (greh->flags & GRE_KEY) grehlen += GRE_HEADER_SECTION; if (greh->flags & GRE_CSUM) grehlen += GRE_HEADER_SECTION; hlen = off + grehlen; if (skb_gro_header_hard(skb, hlen)) { greh = skb_gro_header_slow(skb, hlen, off); if (unlikely(!greh)) goto out; } /* Don't bother verifying checksum if we're going to flush anyway. */ if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush) { if (skb_gro_checksum_simple_validate(skb)) goto out; skb_gro_checksum_try_convert(skb, IPPROTO_GRE, null_compute_pseudo); } list_for_each_entry(p, head, list) { const struct gre_base_hdr *greh2; if (!NAPI_GRO_CB(p)->same_flow) continue; /* The following checks are needed to ensure only pkts * from the same tunnel are considered for aggregation. * The criteria for "the same tunnel" includes: * 1) same version (we only support version 0 here) * 2) same protocol (we only support ETH_P_IP for now) * 3) same set of flags * 4) same key if the key field is present. */ greh2 = (struct gre_base_hdr *)(p->data + off); if (greh2->flags != greh->flags || greh2->protocol != greh->protocol) { NAPI_GRO_CB(p)->same_flow = 0; continue; } if (greh->flags & GRE_KEY) { /* compare keys */ if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } } skb_gro_pull(skb, grehlen); /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ skb_gro_postpull_rcsum(skb, greh, grehlen); pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final(skb, pp, flush); return pp; } static int gre_gro_complete(struct sk_buff *skb, int nhoff) { struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff); struct packet_offload *ptype; unsigned int grehlen = sizeof(*greh); int err = -ENOENT; __be16 type; skb->encapsulation = 1; skb_shinfo(skb)->gso_type = SKB_GSO_GRE; type = greh->protocol; if (greh->flags & GRE_KEY) grehlen += GRE_HEADER_SECTION; if (greh->flags & GRE_CSUM) grehlen += GRE_HEADER_SECTION; ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); skb_set_inner_mac_header(skb, nhoff + grehlen); return err; } static const struct net_offload gre_offload = { .callbacks = { .gso_segment = gre_gso_segment, .gro_receive = gre_gro_receive, .gro_complete = gre_gro_complete, }, }; static int __init gre_offload_init(void) { int err; err = inet_add_offload(&gre_offload, IPPROTO_GRE); #if IS_ENABLED(CONFIG_IPV6) if (err) return err; err = inet6_add_offload(&gre_offload, IPPROTO_GRE); if (err) inet_del_offload(&gre_offload, IPPROTO_GRE); #endif return err; } device_initcall(gre_offload_init); |
| 3103 3104 3102 3104 2062 2062 9857 6725 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* CPU control. * (C) 2001, 2002, 2003, 2004 Rusty Russell * * This code is licenced under the GPL. */ #include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> #include <linux/stop_machine.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> #include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> #include <linux/cc_platform.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS #include <trace/events/cpuhp.h> #include "smpboot.h" /** * struct cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state * @fail: Current CPU hotplug callback state * @thread: Pointer to the hotplug thread * @should_run: Thread should execute * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector * @cpu: CPU number * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation * @ap_sync_state: State for AP synchronization * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; bool rollback; bool single; bool bringup; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; atomic_t ap_sync_state; struct completion done_up; struct completion done_down; #endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; #ifdef CONFIG_SMP cpumask_t cpus_booted_once_mask; #endif #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else static inline void cpuhp_lock_acquire(bool bringup) { } static inline void cpuhp_lock_release(bool bringup) { } #endif /** * struct cpuhp_step - Hotplug state machine step * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step * @cant_stop: Bringup/teardown can't be stopped at this step * @multi_instance: State has multiple instances which get added afterwards */ struct cpuhp_step { const char *name; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } startup; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } teardown; /* private: */ struct hlist_head list; /* public: */ bool cant_stop; bool multi_instance; }; static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_hp_states[]; static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { return cpuhp_hp_states + state; } static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step) { return bringup ? !step->startup.single : !step->teardown.single; } /** * cpuhp_invoke_callback - Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked * @node: For multi-instance, do a single entry callback for install/remove * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. * * Return: %0 on success or a negative errno code */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node, struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); int ret, cnt; if (st->fail == state) { st->fail = CPUHP_INVALID; return -EAGAIN; } if (cpuhp_step_empty(bringup, step)) { WARN_ON_ONCE(1); return 0; } if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; trace_cpuhp_enter(cpu, st->target, state, cb); ret = cb(cpu); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } cbm = bringup ? step->startup.multi : step->teardown.multi; /* Single invocation for instance add/remove */ if (node) { WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { if (lastp && node == *lastp) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); if (ret) { if (!lastp) goto err; *lastp = node; return ret; } cnt++; } if (lastp) *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ cbm = !bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return ret; hlist_for_each(node, &step->list) { if (!cnt--) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); /* * Rollback must not fail, */ WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { /* * The extra check for CPUHP_TEARDOWN_CPU is only for documentation * purposes as that state is handled explicitly in cpu_down. */ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; wait_for_completion(done); } static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; complete(done); } /* * The former STARTING/DYING states, ran with IRQs disabled and must not fail. */ static bool cpuhp_is_atomic_state(enum cpuhp_state state) { return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } /* Synchronization state management */ enum cpuhp_sync_state { SYNC_STATE_DEAD, SYNC_STATE_KICKED, SYNC_STATE_SHOULD_DIE, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE, SYNC_STATE_ONLINE, }; #ifdef CONFIG_HOTPLUG_CORE_SYNC /** * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown * @state: The synchronization state to set * * No synchronization point. Just update of the synchronization state, but implies * a full barrier so that the AP changes are visible before the control CPU proceeds. */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); (void)atomic_xchg(st, state); } void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); } static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state, enum cpuhp_sync_state next_state) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); ktime_t now, end, start = ktime_get(); int sync; end = start + 10ULL * NSEC_PER_SEC; sync = atomic_read(st); while (1) { if (sync == state) { if (!atomic_try_cmpxchg(st, &sync, next_state)) continue; return true; } now = ktime_get(); if (now > end) { /* Timeout. Leave the state unchanged */ return false; } else if (now - start < NSEC_PER_MSEC) { /* Poll for one millisecond */ arch_cpuhp_sync_state_poll(); } else { usleep_range_state(USEC_PER_MSEC, 2 * USEC_PER_MSEC, TASK_UNINTERRUPTIBLE); } sync = atomic_read(st); } return true; } #else /* CONFIG_HOTPLUG_CORE_SYNC */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD /** * cpuhp_ap_report_dead - Update synchronization state to DEAD * * No synchronization point. Just update of the synchronization state. */ void cpuhp_ap_report_dead(void) { cpuhp_ap_update_sync_state(SYNC_STATE_DEAD); } void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } /* * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down * because the AP cannot issue complete() at this stage. */ static void cpuhp_bp_sync_dead(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); do { /* CPU can have reported dead already. Don't overwrite that! */ if (sync == SYNC_STATE_DEAD) break; } while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE)); if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) { /* CPU reached dead state. Invoke the cleanup function */ arch_cpuhp_cleanup_dead_cpu(cpu); return; } /* No further action possible. Emit message and give up. */ pr_err("CPU%u failed to report dead state\n", cpu); } #else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */ static inline void cpuhp_bp_sync_dead(unsigned int cpu) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL /** * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive * * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits * for the BP to release it. */ void cpuhp_ap_sync_alive(void) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE); /* Wait for the control CPU to release it. */ while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE) cpu_relax(); } static bool cpuhp_can_boot_ap(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); again: switch (sync) { case SYNC_STATE_DEAD: /* CPU is properly dead */ break; case SYNC_STATE_KICKED: /* CPU did not come up in previous attempt */ break; case SYNC_STATE_ALIVE: /* CPU is stuck cpuhp_ap_sync_alive(). */ break; default: /* CPU failed to report online or dead and is in limbo state. */ return false; } /* Prepare for booting */ if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED)) goto again; return true; } void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { } /* * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up * because the AP cannot issue complete() so early in the bringup. */ static int cpuhp_bp_sync_alive(unsigned int cpu) { int ret = 0; if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL)) return 0; if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) { pr_err("CPU%u failed to report alive state\n", cpu); ret = -EIO; } /* Let the architecture cleanup the kick alive mechanics. */ arch_cpuhp_cleanup_kick_cpu(cpu); return ret; } #else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */ static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; } static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */ /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } /* * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_lock); int cpus_read_trylock(void) { return percpu_down_read_trylock(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_trylock); void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_unlock); void cpus_write_lock(void) { percpu_down_write(&cpu_hotplug_lock); } void cpus_write_unlock(void) { percpu_up_write(&cpu_hotplug_lock); } void lockdep_assert_cpus_held(void) { /* * We can't have hotplug operations before userspace starts running, * and some init codepaths will knowingly not take the hotplug lock. * This is all valid, so mute lockdep until it makes sense to report * unheld locks. */ if (system_state < SYSTEM_RUNNING) return; percpu_rwsem_assert_held(&cpu_hotplug_lock); } #ifdef CONFIG_LOCKDEP int lockdep_is_cpus_held(void) { return percpu_rwsem_is_held(&cpu_hotplug_lock); } #endif static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_); } static void lockdep_release_cpus_lock(void) { rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the * hotplug path before performing hotplug operations. So acquiring that lock * guarantees mutual exclusion from any currently running hotplug operations. */ void cpu_hotplug_disable(void) { cpu_maps_update_begin(); cpu_hotplug_disabled++; cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_disable); static void __cpu_hotplug_enable(void) { if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n")) return; cpu_hotplug_disabled--; } void cpu_hotplug_enable(void) { cpu_maps_update_begin(); __cpu_hotplug_enable(); cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #else static void lockdep_acquire_cpus_lock(void) { } static void lockdep_release_cpus_lock(void) { } #endif /* CONFIG_HOTPLUG_CPU */ /* * Architectures that need SMT-specific errata handling during SMT hotplug * should override this. */ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; static unsigned int cpu_smt_max_threads __ro_after_init; unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX; void __init cpu_smt_disable(bool force) { if (!cpu_smt_possible()) return; if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } cpu_smt_num_threads = 1; } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ void __init cpu_smt_set_num_threads(unsigned int num_threads, unsigned int max_threads) { WARN_ON(!num_threads || (num_threads > max_threads)); if (max_threads == 1) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; cpu_smt_max_threads = max_threads; /* * If SMT has been disabled via the kernel command line or SMT is * not supported, set cpu_smt_num_threads to 1 for consistency. * If enabled, take the architecture requested number of threads * to bring up into account. */ if (cpu_smt_control != CPU_SMT_ENABLED) cpu_smt_num_threads = 1; else if (num_threads < cpu_smt_num_threads) cpu_smt_num_threads = num_threads; } static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); /* * For Archicture supporting partial SMT states check if the thread is allowed. * Otherwise this has already been checked through cpu_smt_max_threads when * setting the SMT level. */ static inline bool cpu_smt_thread_allowed(unsigned int cpu) { #ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC return topology_smt_thread_allowed(cpu); #else return true; #endif } static inline bool cpu_bootable(unsigned int cpu) { if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) return true; /* All CPUs are bootable if controls are not configured */ if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED) return true; /* All CPUs are bootable if CPU is not SMT capable */ if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return true; if (topology_is_primary_thread(cpu)) return true; /* * On x86 it's required to boot all logical CPUs at least once so * that the init code can get a chance to set CR4.MCE on each * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } /* Returns true if SMT is supported and not forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else static inline bool cpu_bootable(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; st->rollback = false; st->last = NULL; st->target = target; st->single = false; st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); return prev_state; } static inline void cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) { bool bringup = !st->bringup; st->target = prev_state; /* * Already rolling back. No need invert the bringup value or to change * the current state. */ if (st->rollback) return; st->rollback = true; /* * If we have st->last we need to undo partial multi_instance of this * state first. Otherwise start undo at the previous state. */ if (!st->last) { if (st->bringup) st->state--; else st->state++; } st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) { if (!st->single && st->state == st->target) return; st->result = 0; /* * Make sure the above stores are visible before should_run becomes * true. Paired with the mb() above in cpuhp_thread_fun() */ smp_mb(); st->should_run = true; wake_up_process(st->thread); wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } return ret; } static int bringup_wait_for_ap_online(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the * cpu_bootable() check will now return false if this is not the * primary sibling. */ if (!cpu_bootable(cpu)) return -ECANCELED; return 0; } #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP static int cpuhp_kick_ap_alive(unsigned int cpu) { if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu)); } static int cpuhp_bringup_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. */ irq_lock_sparse(); ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #else static int bringup_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle = idle_thread_get(cpu); int ret; if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * * Prevent irq alloc/free across the bringup by acquiring the * sparse irq lock. Hold it until the upcoming CPU completes the * startup in cpuhp_online_idle() which allows to avoid * intermediate synchronization points in the architecture code. */ irq_lock_sparse(); ret = __cpu_up(cpu, idle); if (ret) goto out_unlock; ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #endif static int finish_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); struct mm_struct *mm = idle->active_mm; /* * idle_task_exit() will have switched to &init_mm, now * clean up any remaining active_mm state. */ if (mm != &init_mm) idle->active_mm = &init_mm; mmdrop_lazy_tlb(mm); return 0; } /* * Hotplug state machine related functions */ /* * Get the next state to run. Empty ones will be skipped. Returns true if a * state must be run. * * st->state will be modified ahead of time, to match state_to_run, as if it * has already ran. */ static bool cpuhp_next_state(bool bringup, enum cpuhp_state *state_to_run, struct cpuhp_cpu_state *st, enum cpuhp_state target) { do { if (bringup) { if (st->state >= target) return false; *state_to_run = ++st->state; } else { if (st->state <= target) return false; *state_to_run = st->state--; } if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run))) break; } while (true); return true; } static int __cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target, bool nofail) { enum cpuhp_state state; int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { int err; err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); if (!err) continue; if (nofail) { pr_warn("CPU %u %s state %s (%d) failed (%d)\n", cpu, bringup ? "UP" : "DOWN", cpuhp_get_step(st->state)->name, st->state, err); ret = -1; } else { ret = err; break; } } return ret; } static inline int cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); } static inline void cpuhp_invoke_callback_range_nofail(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) { if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; /* * When CPU hotplug is disabled, then taking the CPU down is not * possible because takedown_cpu() and the architecture and * subsystem specific mechanisms are not available. So the CPU * which would be completely unplugged again needs to stay around * in the current state. */ return st->state <= CPUHP_BRINGUP_CPU; } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(true, cpu, st, target); if (ret) { pr_debug("CPU UP failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); } return ret; } /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); return st->should_run; } /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. * * Each invocation of this function by the smpboot thread does a single AP * state callback. * * It has 3 modes of operation: * - single: runs st->cb_state * - up: runs ++st->state, while st->state < st->target * - down: runs st->state--, while st->state > st->target * * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); bool bringup = st->bringup; enum cpuhp_state state; if (WARN_ON_ONCE(!st->should_run)) return; /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); /* * The BP holds the hotplug lock, but we're now running on the AP, * ensure that anybody asserting the lock is held, will actually find * it so. */ lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; st->should_run = false; } else { st->should_run = cpuhp_next_state(bringup, &state, st, st->target); if (!st->should_run) goto end; } WARN_ON_ONCE(!cpuhp_is_ap_state(state)); if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); local_irq_enable(); /* * STARTING/DYING must not fail! */ WARN_ON_ONCE(st->result); } else { st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); } if (st->result) { /* * If we fail on a rollback, we're up a creek without no * paddle, no way forward, no way back. We loose, thanks for * playing. */ WARN_ON_ONCE(st->rollback); st->should_run = false; } end: cpuhp_lock_release(bringup); lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; if (!cpu_online(cpu)) return 0; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->rollback = false; st->last = NULL; st->node = node; st->bringup = bringup; st->cb_state = state; st->single = true; __cpuhp_kick_ap(st); /* * If we failed and did a partial, do a rollback. */ if ((ret = st->result) && st->last) { st->rollback = true; st->bringup = !bringup; __cpuhp_kick_ap(st); } /* * Clean up the leftovers so the next hotplug operation wont use stale * data. */ st->node = st->last = NULL; return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state prev_state = st->state; int ret; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; } static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; static __init void cpuhp_init_state(void) { struct cpuhp_cpu_state *st; int cpu; for_each_possible_cpu(cpu) { st = per_cpu_ptr(&cpuhp_state, cpu); init_completion(&st->done_up); init_completion(&st->done_down); } } void __init cpuhp_threads_init(void) { cpuhp_init_state(); BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } /* * * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock * protected region. * * The operation is still serialized against concurrent CPU hotplug via * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ * serialized against other hotplug related activity like adding or * removing of state callbacks and state instances, which invoke either the * startup or the teardown callback of the affected state. * * This is required for subsystems which are unfixable vs. CPU hotplug and * evade lock inversion problems by scheduling work which has to be * completed _before_ cpu_up()/_cpu_down() returns. * * Don't even think about adding anything to this for any new code or even * drivers. It's only purpose is to keep existing lock order trainwrecks * working. * * For cpu_down() there might be valid reasons to finish cleanups which are * not required to be done under cpu_hotplug_lock, but that's a different * story and would be not invoked via this. */ static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) { /* * cpusets delegate hotplug operations to a worker to "solve" the * lock order problems. Wait for the worker, but only if tasks are * _not_ frozen (suspend, hibernate) as that would wait forever. * * The wait is required because otherwise the hotplug operation * returns with inconsistent state, which could even be observed in * user space when a new CPU is brought up. The CPU plug uevent * would be delivered and user space reacting on it would fail to * move tasks to the newly plugged CPU up to the point where the * work has finished because up to that point the newly plugged CPU * is not assignable in cpusets/cgroups. On unplug that's not * necessarily a visible issue, but it is still inconsistent state, * which is the real problem which needs to be "fixed". This can't * prevent the transient state between scheduling the work and * returning from waiting for it. */ if (!tasks_frozen) cpuset_wait_for_hotplug(); } #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) #endif /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id * * This function walks all processes, finds a valid mm struct for each one and * then clears a corresponding bit in mm's cpumask. While this all sounds * trivial, there are various non-obvious corner cases, which this function * tries to solve in a safe manner. * * Also note that the function uses a somewhat relaxed locking scheme, so it may * be called only for an already offlined CPU. */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; /* * This function is called after the cpu is taken down and marked * offline, so its not like new tasks will ever get this cpu set in * their mm mask. -- Peter Zijlstra * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; /* * Main thread might exit, but other threads may still have * a valid mm. Find one. */ t = find_lock_task_mm(p); if (!t) continue; arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); } /* Take this CPU down. */ static int take_cpu_down(void *_param) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; /* * Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going * down, that the current state is CPUHP_TEARDOWN_CPU - 1. */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); /* * Invoke the former CPU_DYING callbacks. DYING must not fail! */ cpuhp_invoke_callback_range_nofail(false, cpu, st, target); /* Give up timekeeping duties */ tick_handover_do_timer(); /* Remove CPU from timer broadcasting */ tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; } static int takedown_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* Park the smpboot threads */ kthread_park(st->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. */ irq_lock_sparse(); /* * So now all preempt/rcu users must observe !cpu_active(). */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ kthread_unpark(st->thread); return err; } BUG_ON(cpu_online(cpu)); /* * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. */ wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); cpuhp_bp_sync_dead(cpu); tick_cleanup_dead_cpu(cpu); /* * Callbacks must be re-integrated right away to the RCU state machine. * Otherwise an RCU callback could block a further teardown function * waiting for its completion. */ rcutree_migrate_callbacks(cpu); return 0; } static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); rcutree_report_cpu_dead(); st->state = CPUHP_AP_IDLE_DEAD; /* * We cannot call complete after rcutree_report_cpu_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), cpuhp_complete_idle_dead, st, 0); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(false, cpu, st, target); if (ret) { pr_debug("CPU DOWN failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, prev_state)); } return ret; } /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; if (num_online_cpus() == 1) return -EBUSY; if (!cpu_present(cpu)) return -EINVAL; cpus_write_lock(); cpuhp_tasks_frozen = tasks_frozen; prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; /* * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); } } out: cpus_write_unlock(); /* * Do post unplug cleanup. This is still protected against * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); arch_smt_update(); cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } struct cpu_down_work { unsigned int cpu; enum cpuhp_state target; }; static long __cpu_down_maps_locked(void *arg) { struct cpu_down_work *work = arg; return _cpu_down(work->cpu, 0, work->target); } static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { struct cpu_down_work work = { .cpu = cpu, .target = target, }; /* * If the platform does not support hotplug, report it explicitly to * differentiate it from a transient offlining failure. */ if (cc_platform_has(CC_ATTR_HOTPLUG_DISABLED)) return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; /* * Ensure that the control task does not run on the to be offlined * CPU to prevent a deadlock against cfs_b->period_timer. * Also keep at least one housekeeping cpu onlined to avoid generating * an empty sched_domain span. */ for_each_cpu_and(cpu, cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) { if (cpu != work.cpu) return work_on_cpu(cpu, __cpu_down_maps_locked, &work); } return -EBUSY; } static int cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } /** * cpu_device_down - Bring down a cpu device * @dev: Pointer to the cpu device to offline * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use remove_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_down(struct device *dev) { return cpu_down(dev->id, CPUHP_OFFLINE); } int remove_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_offline(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(remove_cpu); void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { unsigned int cpu; int error; cpu_maps_update_begin(); /* * Make certain the cpu I'm about to reboot on is online. * * This is inline to what migrate_to_reboot_cpu() already do. */ if (!cpu_online(primary_cpu)) primary_cpu = cpumask_first(cpu_online_mask); for_each_online_cpu(cpu) { if (cpu == primary_cpu) continue; error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (error) { pr_err("Failed to offline CPU%d - error=%d", cpu, error); break; } } /* * Ensure all but the reboot CPU are offline. */ BUG_ON(num_online_cpus() > 1); /* * Make sure the CPUs won't be enabled by someone else after this * point. Kexec will reboot to a new kernel shortly resetting * everything along the way. */ cpu_hotplug_disabled++; cpu_maps_update_done(); } #else #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started * * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); /* * STARTING must not fail! */ cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* * Called from the idle task. Wake up the controlling task which brings the * hotplug thread of the upcoming CPU up and then delegates the rest of the * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE); /* * Unpark the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; int ret = 0; cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } /* * The caller of cpu_up() might have raced with another * caller. Nothing to do. */ if (st->state >= target) goto out; if (st->state == CPUHP_OFFLINE) { /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); goto out; } /* * Reset stale stack state from the last time this CPU was online. */ scs_task_reset(idle); kasan_unpoison_task_stack(idle); } cpuhp_tasks_frozen = tasks_frozen; cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; } /* * Try to reach the target state. We max out on the BP at * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); arch_smt_update(); cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } static int cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); return -EINVAL; } err = try_online_node(cpu_to_node(cpu)); if (err) return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { err = -EBUSY; goto out; } if (!cpu_bootable(cpu)) { err = -EPERM; goto out; } err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } /** * cpu_device_up - Bring up a cpu device * @dev: Pointer to the cpu device to online * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use add_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_up(struct device *dev) { return cpu_up(dev->id, CPUHP_ONLINE); } int add_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_online(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_cpu); /** * bringup_hibernate_cpu - Bring up the CPU that we hibernated on * @sleep_cpu: The cpu we hibernated on and should be brought up. * * On some architectures like arm64, we can hibernate on any CPU, but on * wake up the CPU we hibernated on might be offline as a side effect of * using maxcpus= for example. * * Return: %0 on success or a negative errno code */ int bringup_hibernate_cpu(unsigned int sleep_cpu) { int ret; if (!cpu_online(sleep_cpu)) { pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); ret = cpu_up(sleep_cpu, CPUHP_ONLINE); if (ret) { pr_err("Failed to bring hibernate-CPU up!\n"); return ret; } } return 0; } static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus, enum cpuhp_state target) { unsigned int cpu; for_each_cpu(cpu, mask) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); if (cpu_up(cpu, target) && can_rollback_cpu(st)) { /* * If this failed then cpu_up() might have only * rolled back to CPUHP_BP_KICK_AP for the final * online. Clean it up. NOOP if already rolled back. */ WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE)); } if (!--ncpus) break; } } #ifdef CONFIG_HOTPLUG_PARALLEL static bool __cpuhp_parallel_bringup __ro_after_init = true; static int __init parallel_bringup_parse_param(char *arg) { return kstrtobool(arg, &__cpuhp_parallel_bringup); } early_param("cpuhp.parallel", parallel_bringup_parse_param); static inline bool cpuhp_smt_aware(void) { return cpu_smt_max_threads > 1; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_primary_thread_mask; } /* * On architectures which have enabled parallel bringup this invokes all BP * prepare states for each of the to be onlined APs first. The last state * sends the startup IPI to the APs. The APs proceed through the low level * bringup code in parallel and then wait for the control CPU to release * them one by one for the final onlining procedure. * * This avoids waiting for each AP to respond to the startup IPI in * CPUHP_BRINGUP_CPU. */ static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) { const struct cpumask *mask = cpu_present_mask; if (__cpuhp_parallel_bringup) __cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup(); if (!__cpuhp_parallel_bringup) return false; if (cpuhp_smt_aware()) { const struct cpumask *pmask = cpuhp_get_primary_thread_mask(); static struct cpumask tmp_mask __initdata; /* * X86 requires to prevent that SMT siblings stopped while * the primary thread does a microcode update for various * reasons. Bring the primary threads up first. */ cpumask_and(&tmp_mask, mask, pmask); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE); /* Account for the online CPUs */ ncpus -= num_online_cpus(); if (!ncpus) return true; /* Create the mask for secondary CPUs */ cpumask_andnot(&tmp_mask, mask, pmask); mask = &tmp_mask; } /* Bring the not-yet started CPUs up */ cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE); return true; } #else static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } #endif /* CONFIG_HOTPLUG_PARALLEL */ void __init bringup_nonboot_cpus(unsigned int setup_max_cpus) { /* Try parallel bringup optimization if enabled */ if (cpuhp_bringup_cpus_parallel(setup_max_cpus)) return; /* Full per CPU serialized bringup */ cpuhp_bringup_mask(cpu_present_mask, setup_max_cpus, CPUHP_ONLINE); } #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; int freeze_secondary_cpus(int primary) { int cpu, error = 0; cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); if (!housekeeping_cpu(primary, HK_TYPE_TIMER)) primary = housekeeping_any_cpu(HK_TYPE_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); } /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); for_each_online_cpu(cpu) { if (cpu == primary) continue; if (pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; } trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { pr_err("Error taking CPU%d down: %d\n", cpu, error); break; } } if (!error) BUG_ON(num_online_cpus() > 1); else pr_err("Non-boot CPUs are not disabled\n"); /* * Make sure the CPUs won't be enabled by someone else. We need to do * this even in case of failure as all freeze_secondary_cpus() users are * supposed to do thaw_secondary_cpus() on the failure path. */ cpu_hotplug_disabled++; cpu_maps_update_done(); return error; } void __weak arch_thaw_secondary_cpus_begin(void) { } void __weak arch_thaw_secondary_cpus_end(void) { } void thaw_secondary_cpus(void) { int cpu, error; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); __cpu_hotplug_enable(); if (cpumask_empty(frozen_cpus)) goto out; pr_info("Enabling non-boot CPUs ...\n"); arch_thaw_secondary_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); } arch_thaw_secondary_cpus_end(); cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; return 0; } core_initcall(alloc_frozen_cpus); /* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the * duration* of the execution of the callbacks. * Hence we need to prevent the freezer from racing with regular CPU hotplug. * * This synchronization is implemented by mutually excluding regular CPU * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ * Hibernate notifications. */ static int cpu_hotplug_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: cpu_hotplug_enable(); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int __init cpu_hotplug_pm_sync_init(void) { /* * cpu_hotplug_pm_callback has higher priority than x86 * bsp_pm_callback which depends on cpu_hotplug_pm_callback * to disable cpu hotplug to avoid cpu hotplug race. */ pm_notifier(cpu_hotplug_pm_callback, 0); return 0; } core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ int __boot_cpu_id; #endif /* CONFIG_SMP */ /* Boot processor state steps */ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_OFFLINE] = { .name = "offline", .startup.single = NULL, .teardown.single = NULL, }, #ifdef CONFIG_SMP [CPUHP_CREATE_THREADS]= { .name = "threads:prepare", .startup.single = smpboot_create_threads, .teardown.single = NULL, .cant_stop = true, }, [CPUHP_PERF_PREPARE] = { .name = "perf:prepare", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_RANDOM_PREPARE] = { .name = "random:prepare", .startup.single = random_prepare_cpu, .teardown.single = NULL, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, .teardown.single = NULL, }, [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", .startup.single = smpcfd_prepare_cpu, .teardown.single = smpcfd_dead_cpu, }, [CPUHP_RELAY_PREPARE] = { .name = "relay:prepare", .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, .teardown.single = rcutree_dead_cpu, }, /* * On the tear-down path, timers_dead_cpu() must be invoked * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP /* * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until * the next step will release it. */ [CPUHP_BP_KICK_AP] = { .name = "cpu:kick_ap", .startup.single = cpuhp_kick_ap_alive, }, /* * Waits for the AP to reach cpuhp_ap_sync_alive() and then * releases it for the complete bringup. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = cpuhp_bringup_ap, .teardown.single = finish_cpu, .cant_stop = true, }, #else /* * All-in-one CPU bringup state which includes the kick alive. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, #endif /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", }, /* * Last state before CPU enters the idle loop to die. Transient state * for synchronization. */ [CPUHP_AP_OFFLINE] = { .name = "ap:offline", .cant_stop = true, }, /* First state is scheduler control. Interrupts are disabled */ [CPUHP_AP_SCHED_STARTING] = { .name = "sched:starting", .startup.single = sched_cpu_starting, .teardown.single = sched_cpu_dying, }, [CPUHP_AP_RCUTREE_DYING] = { .name = "RCU/tree:dying", .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, [CPUHP_AP_HRTIMERS_DYING] = { .name = "hrtimers:dying", .startup.single = NULL, .teardown.single = hrtimers_cpu_dying, }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { .name = "ap:online", }, /* * Handled on control processor until the plugged processor manages * this itself. */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup.single = NULL, .teardown.single = takedown_cpu, .cant_stop = true, }, [CPUHP_AP_SCHED_WAIT_EMPTY] = { .name = "sched:waitempty", .startup.single = NULL, .teardown.single = sched_cpu_wait_empty, }, /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", .startup.single = irq_affinity_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_AP_WATCHDOG_ONLINE] = { .name = "lockup_detector:online", .startup.single = lockup_detector_online_cpu, .teardown.single = lockup_detector_offline_cpu, }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, [CPUHP_AP_RANDOM_ONLINE] = { .name = "random:online", .startup.single = random_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, .teardown.single = rcutree_offline_cpu, }, #endif /* * The dynamically registered state space is here */ #ifdef CONFIG_SMP /* Last state is scheduler control setting the cpu active */ [CPUHP_AP_ACTIVE] = { .name = "sched:active", .startup.single = sched_cpu_activate, .teardown.single = sched_cpu_deactivate, }, #endif /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup.single = NULL, .teardown.single = NULL, }, }; /* Sanity check for callbacks */ static int cpuhp_cb_check(enum cpuhp_state state) { if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) return -EINVAL; return 0; } /* * Returns a free for dynamic slot assignment of the Online state. The states * are protected by the cpuhp_slot_states mutex and an empty slot is identified * by having no name assigned. */ static int cpuhp_reserve_state(enum cpuhp_state state) { enum cpuhp_state i, end; struct cpuhp_step *step; switch (state) { case CPUHP_AP_ONLINE_DYN: step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN; end = CPUHP_AP_ONLINE_DYN_END; break; case CPUHP_BP_PREPARE_DYN: step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; default: return -EINVAL; } for (i = state; i <= end; i++, step++) { if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); return -ENOSPC; } static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { /* (Un)Install the callbacks for further cpu hotplug operations */ struct cpuhp_step *sp; int ret = 0; /* * If name is NULL, then the state gets removed. * * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; state = ret; } sp = cpuhp_get_step(state); if (name && sp->name) return -EBUSY; sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); return ret; } static void *cpuhp_get_teardown_cb(enum cpuhp_state state) { return cpuhp_get_step(state)->teardown.single; } /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. */ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_step *sp = cpuhp_get_step(state); int ret; /* * If there's nothing to do, we done. * Relies on the union for multi_instance. */ if (cpuhp_step_empty(bringup, sp)) return 0; /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ #ifdef CONFIG_SMP if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; } /* * Called from __cpuhp_setup_state on a recoverable failure. * * Note: The teardown callbacks for rollback are not allowed to fail! */ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, struct hlist_node *node) { int cpu; /* Roll back the already executed steps on the other cpus */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpu >= failedcpu) break; /* Did we invoke the startup call on that cpu ? */ if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } } int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp; int cpu; int ret; lockdep_assert_cpus_held(); sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, node); if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); goto unlock; } } add_node: ret = 0; hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); return ret; } int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { int ret; cpus_read_lock(); ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @name: Name of the step * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state * @startup: startup callback function * @teardown: teardown callback function * @multi_instance: State is set up for multiple instances which get * added afterwards. * * The caller needs to hold cpus read locked while calling this function. * Return: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN; * 0 for all other states * On failure: proper (negative) error code */ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int cpu, ret = 0; bool dynstate; lockdep_assert_cpus_held(); if (cpuhp_cb_check(state) || !name) return -EINVAL; mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); dynstate = state == CPUHP_AP_ONLINE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; } if (ret || !invoke || !startup) goto out; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, NULL); if (ret) { if (teardown) cpuhp_rollback_install(cpu, state, NULL); cpuhp_store_callbacks(state, NULL, NULL, NULL, false); goto out; } } out: mutex_unlock(&cpuhp_state_mutex); /* * If the requested state is CPUHP_AP_ONLINE_DYN, return the * dynamically allocated state in case of success. */ if (!ret && dynstate) return state; return ret; } EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int ret; cpus_read_lock(); ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, teardown, multi_instance); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); if (!sp->multi_instance) return -EINVAL; cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", state); goto remove; } if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, NULL); } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); } EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) { cpus_read_lock(); __cpuhp_remove_state_cpuslocked(state, invoke); cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); #ifdef CONFIG_HOTPLUG_SMT static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = true; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = false; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; cpu_maps_update_begin(); for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; /* * Disable can be called with CPU_SMT_ENABLED when changing * from a higher to lower number of SMT threads per core. */ if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; /* * As this needs to hold the cpu maps lock it's impossible * to call device_offline() because that ends up calling * cpu_down() which takes cpu maps lock. cpu maps lock * needs to be held as this might race against in kernel * abusers of the hotplug machinery (thermal management). * * So nothing would update device:offline state. That would * leave the sysfs entry stale and prevent onlining after * smt control has been changed to 'off' again. This is * called under the sysfs hotplug lock, so it is properly * serialized against the regular offline usage. */ cpuhp_offline_cpu_device(cpu); } if (!ret) cpu_smt_control = ctrlval; cpu_maps_update_done(); return ret; } int cpuhp_smt_enable(void) { int cpu, ret = 0; cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; if (!cpu_smt_thread_allowed(cpu)) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; /* See comment in cpuhp_smt_disable() */ cpuhp_online_cpu_device(cpu); } cpu_maps_update_done(); return ret; } #endif #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->state); } static DEVICE_ATTR_RO(state); static ssize_t target_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int target, ret; ret = kstrtoint(buf, 10, &target); if (ret) return ret; #ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) return -EINVAL; #else if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) return -EINVAL; #endif ret = lock_device_hotplug_sysfs(); if (ret) return ret; mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(target); ret = !sp->name || sp->cant_stop ? -EINVAL : 0; mutex_unlock(&cpuhp_state_mutex); if (ret) goto out; if (st->state < target) ret = cpu_up(dev->id, target); else if (st->state > target) ret = cpu_down(dev->id, target); else if (WARN_ON(st->target != target)) st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; } static ssize_t target_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->target); } static DEVICE_ATTR_RW(target); static ssize_t fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int fail, ret; ret = kstrtoint(buf, 10, &fail); if (ret) return ret; if (fail == CPUHP_INVALID) { st->fail = fail; return count; } if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) return -EINVAL; /* * Cannot fail STARTING/DYING callbacks. */ if (cpuhp_is_atomic_state(fail)) return -EINVAL; /* * DEAD callbacks cannot fail... * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter * triggering STARTING callbacks, a failure in this state would * hinder rollback. */ if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU) return -EINVAL; /* * Cannot fail anything that doesn't have callbacks. */ mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(fail); if (!sp->startup.single && !sp->teardown.single) ret = -EINVAL; mutex_unlock(&cpuhp_state_mutex); if (ret) return ret; st->fail = fail; return count; } static ssize_t fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->fail); } static DEVICE_ATTR_RW(fail); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, &dev_attr_fail.attr, NULL }; static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", NULL }; static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) { ssize_t cur, res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { cur = sprintf(buf, "%3d: %s\n", i, sp->name); buf += cur; res += cur; } } mutex_unlock(&cpuhp_state_mutex); return res; } static DEVICE_ATTR_RO(states); static struct attribute *cpuhp_cpu_root_attrs[] = { &dev_attr_states.attr, NULL }; static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", NULL }; #ifdef CONFIG_HOTPLUG_SMT static bool cpu_smt_num_threads_valid(unsigned int threads) { if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC)) return threads >= 1 && threads <= cpu_smt_max_threads; return threads == 1 || threads == cpu_smt_max_threads; } static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ctrlval, ret, num_threads, orig_threads; bool force_off; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; if (sysfs_streq(buf, "on")) { ctrlval = CPU_SMT_ENABLED; num_threads = cpu_smt_max_threads; } else if (sysfs_streq(buf, "off")) { ctrlval = CPU_SMT_DISABLED; num_threads = 1; } else if (sysfs_streq(buf, "forceoff")) { ctrlval = CPU_SMT_FORCE_DISABLED; num_threads = 1; } else if (kstrtoint(buf, 10, &num_threads) == 0) { if (num_threads == 1) ctrlval = CPU_SMT_DISABLED; else if (cpu_smt_num_threads_valid(num_threads)) ctrlval = CPU_SMT_ENABLED; else return -EINVAL; } else { return -EINVAL; } ret = lock_device_hotplug_sysfs(); if (ret) return ret; orig_threads = cpu_smt_num_threads; cpu_smt_num_threads = num_threads; force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED; if (num_threads > orig_threads) ret = cpuhp_smt_enable(); else if (num_threads < orig_threads || force_off) ret = cpuhp_smt_disable(ctrlval); unlock_device_hotplug(); return ret ? ret : count; } #else /* !CONFIG_HOTPLUG_SMT */ static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return -ENODEV; } #endif /* CONFIG_HOTPLUG_SMT */ static const char *smt_states[] = { [CPU_SMT_ENABLED] = "on", [CPU_SMT_DISABLED] = "off", [CPU_SMT_FORCE_DISABLED] = "forceoff", [CPU_SMT_NOT_SUPPORTED] = "notsupported", [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", }; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *state = smt_states[cpu_smt_control]; #ifdef CONFIG_HOTPLUG_SMT /* * If SMT is enabled but not all threads are enabled then show the * number of threads. If all threads are enabled show "on". Otherwise * show the state name. */ if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_num_threads != cpu_smt_max_threads) return sysfs_emit(buf, "%d\n", cpu_smt_num_threads); #endif return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return __store_smt_control(dev, attr, buf, count); } static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); static struct attribute *cpuhp_smt_attrs[] = { &dev_attr_control.attr, &dev_attr_active.attr, NULL }; static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", NULL }; static int __init cpu_smt_sysfs_init(void) { struct device *dev_root; int ret = -ENODEV; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_smt_attr_group); put_device(dev_root); } return ret; } static int __init cpuhp_sysfs_init(void) { struct device *dev_root; int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_cpu_root_attr_group); put_device(dev_root); if (ret) return ret; } for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); if (!dev) continue; ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); if (ret) return ret; } return 0; } device_initcall(cpuhp_sysfs_init); #endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ /* cpu_bit_bitmap[0] is empty - so we can back into it */ #define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x)) #define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) #define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) #define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { MASK_DECLARE_8(0), MASK_DECLARE_8(8), MASK_DECLARE_8(16), MASK_DECLARE_8(24), #if BITS_PER_LONG > 32 MASK_DECLARE_8(32), MASK_DECLARE_8(40), MASK_DECLARE_8(48), MASK_DECLARE_8(56), #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE struct cpumask __cpu_possible_mask __read_mostly = {CPU_BITS_ALL}; #else struct cpumask __cpu_possible_mask __read_mostly; #endif EXPORT_SYMBOL(__cpu_possible_mask); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); struct cpumask __cpu_dying_mask __read_mostly; EXPORT_SYMBOL(__cpu_dying_mask); atomic_t __num_online_cpus __read_mostly; EXPORT_SYMBOL(__num_online_cpus); void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); } void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); } void init_cpu_online(const struct cpumask *src) { cpumask_copy(&__cpu_online_mask, src); } void set_cpu_online(unsigned int cpu, bool online) { /* * atomic_inc/dec() is required to handle the horrid abuse of this * function by the reboot and kexec code which invoke it from * IPI/NMI broadcasts when shutting down CPUs. Invocation from * regular CPU hotplug is properly serialized. * * Note, that the fact that __num_online_cpus is of type atomic_t * does not protect readers which are not serialized against * concurrent hotplug operations. */ if (online) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) atomic_inc(&__num_online_cpus); } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) atomic_dec(&__num_online_cpus); } } /* * Activate the first processor. */ void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); #ifdef CONFIG_SMP __boot_cpu_id = cpu; #endif } /* * Must be called _AFTER_ setting up the per_cpu areas */ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, CPU_MITIGATIONS_AUTO, CPU_MITIGATIONS_AUTO_NOSMT, }; static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) cpu_mitigations = CPU_MITIGATIONS_OFF; else if (!strcmp(arg, "auto")) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; else pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); return 0; } early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) { return cpu_mitigations == CPU_MITIGATIONS_OFF; } EXPORT_SYMBOL_GPL(cpu_mitigations_off); /* mitigations=auto,nosmt */ bool cpu_mitigations_auto_nosmt(void) { return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); |
| 13 13 13 13 13 13 13 13 13 2 11 13 1 11 9 1 13 154 154 154 83 27 26 26 4 25 25 25 22 22 11 11 11 220 41 41 40 40 43 37 164 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Device handling code * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/netpoll.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/list.h> #include <linux/netfilter_bridge.h> #include <linux/uaccess.h> #include "br_private.h" #define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \ NETIF_F_GSO_MASK | NETIF_F_HW_CSUM) const struct nf_br_ops __rcu *nf_br_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_br_ops); /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct net_bridge_mcast_port *pmctx_null = NULL; struct net_bridge *br = netdev_priv(dev); struct net_bridge_mcast *brmctx = &br->multicast_ctx; struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; const struct nf_br_ops *nf_ops; u8 state = BR_STATE_FORWARDING; struct net_bridge_vlan *vlan; const unsigned char *dest; u16 vid = 0; memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); br_tc_skb_miss_set(skb, false); rcu_read_lock(); nf_ops = rcu_dereference(nf_br_ops); if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) { rcu_read_unlock(); return NETDEV_TX_OK; } dev_sw_netstats_tx_add(dev, 1, skb->len); br_switchdev_frame_unmark(skb); BR_INPUT_SKB_CB(skb)->brdev = dev; BR_INPUT_SKB_CB(skb)->frag_max_size = 0; skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid, &state, &vlan)) goto out; if (IS_ENABLED(CONFIG_INET) && (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) || eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); } else if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *msg, _msg; msg = br_is_nd_neigh_msg(skb, &_msg); if (msg) br_do_suppress_nd(skb, br, vid, NULL, msg); } dest = eth_hdr(skb)->h_dest; if (is_broadcast_ether_addr(dest)) { br_flood(br, skb, BR_PKT_BROADCAST, false, true, vid); } else if (is_multicast_ether_addr(dest)) { if (unlikely(netpoll_tx_running(dev))) { br_flood(br, skb, BR_PKT_MULTICAST, false, true, vid); goto out; } if (br_multicast_rcv(&brmctx, &pmctx_null, vlan, skb, vid)) { kfree_skb(skb); goto out; } mdst = br_mdb_entry_skb_get(brmctx, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && br_multicast_querier_exists(brmctx, eth_hdr(skb), mdst)) br_multicast_flood(mdst, skb, brmctx, false, true); else br_flood(br, skb, BR_PKT_MULTICAST, false, true, vid); } else if ((dst = br_fdb_find_rcu(br, dest, vid)) != NULL) { br_forward(dst->dst, skb, false, true); } else { br_flood(br, skb, BR_PKT_UNICAST, false, true, vid); } out: rcu_read_unlock(); return NETDEV_TX_OK; } static struct lock_class_key bridge_netdev_addr_lock_key; static void br_set_lockdep_class(struct net_device *dev) { lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); } static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); int err; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; err = br_fdb_hash_init(br); if (err) { free_percpu(dev->tstats); return err; } err = br_mdb_hash_init(br); if (err) { free_percpu(dev->tstats); br_fdb_hash_fini(br); return err; } err = br_vlan_init(br); if (err) { free_percpu(dev->tstats); br_mdb_hash_fini(br); br_fdb_hash_fini(br); return err; } err = br_multicast_init_stats(br); if (err) { free_percpu(dev->tstats); br_vlan_flush(br); br_mdb_hash_fini(br); br_fdb_hash_fini(br); } br_set_lockdep_class(dev); return err; } static void br_dev_uninit(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); br_multicast_dev_del(br); br_multicast_uninit_stats(br); br_vlan_flush(br); br_mdb_hash_fini(br); br_fdb_hash_fini(br); free_percpu(dev->tstats); } static int br_dev_open(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); netdev_update_features(dev); netif_start_queue(dev); br_stp_enable_bridge(br); br_multicast_open(br); if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) br_multicast_join_snoopers(br); return 0; } static void br_dev_set_multicast_list(struct net_device *dev) { } static void br_dev_change_rx_flags(struct net_device *dev, int change) { if (change & IFF_PROMISC) br_manage_promisc(netdev_priv(dev)); } static int br_dev_stop(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); br_stp_disable_bridge(br); br_multicast_stop(br); if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) br_multicast_leave_snoopers(br); netif_stop_queue(dev); return 0; } static int br_change_mtu(struct net_device *dev, int new_mtu) { struct net_bridge *br = netdev_priv(dev); dev->mtu = new_mtu; /* this flag will be cleared if the MTU was automatically adjusted */ br_opt_toggle(br, BROPT_MTU_SET_BY_USER, true); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* remember the MTU in the rtable for PMTU */ dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu); #endif return 0; } /* Allow setting mac address to any valid ethernet address. */ static int br_set_mac_address(struct net_device *dev, void *p) { struct net_bridge *br = netdev_priv(dev); struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; /* dev_set_mac_addr() can be called by a master device on bridge's * NETDEV_UNREGISTER, but since it's being destroyed do nothing */ if (dev->reg_state != NETREG_REGISTERED) return -EBUSY; spin_lock_bh(&br->lock); if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { /* Mac address will be changed in br_stp_change_bridge_id(). */ br_stp_change_bridge_id(br, addr->sa_data); } spin_unlock_bh(&br->lock); return 0; } static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, "bridge", sizeof(info->driver)); strscpy(info->version, BR_VERSION, sizeof(info->version)); strscpy(info->fw_version, "N/A", sizeof(info->fw_version)); strscpy(info->bus_info, "N/A", sizeof(info->bus_info)); } static int br_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; cmd->base.speed = SPEED_UNKNOWN; list_for_each_entry(p, &br->port_list, list) { struct ethtool_link_ksettings ecmd; struct net_device *pdev = p->dev; if (!netif_running(pdev) || !netif_oper_up(pdev)) continue; if (__ethtool_get_link_ksettings(pdev, &ecmd)) continue; if (ecmd.base.speed == (__u32)SPEED_UNKNOWN) continue; if (cmd->base.speed == (__u32)SPEED_UNKNOWN || cmd->base.speed < ecmd.base.speed) cmd->base.speed = ecmd.base.speed; } return 0; } static netdev_features_t br_fix_features(struct net_device *dev, netdev_features_t features) { struct net_bridge *br = netdev_priv(dev); return br_features_recompute(br, features); } #ifdef CONFIG_NET_POLL_CONTROLLER static void br_poll_controller(struct net_device *br_dev) { } static void br_netpoll_cleanup(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) br_netpoll_disable(p); } static int __br_netpoll_enable(struct net_bridge_port *p) { struct netpoll *np; int err; np = kzalloc(sizeof(*p->np), GFP_KERNEL); if (!np) return -ENOMEM; err = __netpoll_setup(np, p->dev); if (err) { kfree(np); return err; } p->np = np; return err; } int br_netpoll_enable(struct net_bridge_port *p) { if (!p->br->dev->npinfo) return 0; return __br_netpoll_enable(p); } static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p; int err = 0; list_for_each_entry(p, &br->port_list, list) { if (!p->dev) continue; err = __br_netpoll_enable(p); if (err) goto fail; } out: return err; fail: br_netpoll_cleanup(dev); goto out; } void br_netpoll_disable(struct net_bridge_port *p) { struct netpoll *np = p->np; if (!np) return; p->np = NULL; __netpoll_free(np); } #endif static int br_add_slave(struct net_device *dev, struct net_device *slave_dev, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); return br_add_if(br, slave_dev, extack); } static int br_del_slave(struct net_device *dev, struct net_device *slave_dev) { struct net_bridge *br = netdev_priv(dev); return br_del_if(br, slave_dev); } static int br_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct net_bridge_fdb_entry *f; struct net_bridge_port *dst; struct net_bridge *br; if (netif_is_bridge_port(ctx->dev)) return -1; br = netdev_priv(ctx->dev); br_vlan_fill_forward_path_pvid(br, ctx, path); f = br_fdb_find_rcu(br, ctx->daddr, path->bridge.vlan_id); if (!f || !f->dst) return -1; dst = READ_ONCE(f->dst); if (!dst) return -1; if (br_vlan_fill_forward_path_mode(br, dst, path)) return -1; path->type = DEV_PATH_BRIDGE; path->dev = dst->br->dev; ctx->dev = dst->dev; switch (path->bridge.vlan_mode) { case DEV_PATH_BR_VLAN_TAG: if (ctx->num_vlans >= ARRAY_SIZE(ctx->vlan)) return -ENOSPC; ctx->vlan[ctx->num_vlans].id = path->bridge.vlan_id; ctx->vlan[ctx->num_vlans].proto = path->bridge.vlan_proto; ctx->num_vlans++; break; case DEV_PATH_BR_VLAN_UNTAG_HW: case DEV_PATH_BR_VLAN_UNTAG: ctx->num_vlans--; break; case DEV_PATH_BR_VLAN_KEEP: break; } return 0; } static const struct ethtool_ops br_ethtool_ops = { .get_drvinfo = br_getinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = br_get_link_ksettings, }; static const struct net_device_ops br_netdev_ops = { .ndo_open = br_dev_open, .ndo_stop = br_dev_stop, .ndo_init = br_dev_init, .ndo_uninit = br_dev_uninit, .ndo_start_xmit = br_dev_xmit, .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = br_set_mac_address, .ndo_set_rx_mode = br_dev_set_multicast_list, .ndo_change_rx_flags = br_dev_change_rx_flags, .ndo_change_mtu = br_change_mtu, .ndo_siocdevprivate = br_dev_siocdevprivate, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = br_netpoll_setup, .ndo_netpoll_cleanup = br_netpoll_cleanup, .ndo_poll_controller = br_poll_controller, #endif .ndo_add_slave = br_add_slave, .ndo_del_slave = br_del_slave, .ndo_fix_features = br_fix_features, .ndo_fdb_add = br_fdb_add, .ndo_fdb_del = br_fdb_delete, .ndo_fdb_del_bulk = br_fdb_delete_bulk, .ndo_fdb_dump = br_fdb_dump, .ndo_fdb_get = br_fdb_get, .ndo_mdb_add = br_mdb_add, .ndo_mdb_del = br_mdb_del, .ndo_mdb_del_bulk = br_mdb_del_bulk, .ndo_mdb_dump = br_mdb_dump, .ndo_mdb_get = br_mdb_get, .ndo_bridge_getlink = br_getlink, .ndo_bridge_setlink = br_setlink, .ndo_bridge_dellink = br_dellink, .ndo_features_check = passthru_features_check, .ndo_fill_forward_path = br_fill_forward_path, }; static struct device_type br_type = { .name = "bridge", }; void br_dev_setup(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); eth_hw_addr_random(dev); ether_setup(dev); dev->netdev_ops = &br_netdev_ops; dev->needs_free_netdev = true; dev->ethtool_ops = &br_ethtool_ops; SET_NETDEV_DEVTYPE(dev, &br_type); dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE; dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->vlan_features = COMMON_FEATURES; br->dev = dev; spin_lock_init(&br->lock); INIT_LIST_HEAD(&br->port_list); INIT_HLIST_HEAD(&br->fdb_list); INIT_HLIST_HEAD(&br->frame_type_list); #if IS_ENABLED(CONFIG_BRIDGE_MRP) INIT_HLIST_HEAD(&br->mrp_list); #endif #if IS_ENABLED(CONFIG_BRIDGE_CFM) INIT_HLIST_HEAD(&br->mep_list); #endif spin_lock_init(&br->hash_lock); br->bridge_id.prio[0] = 0x80; br->bridge_id.prio[1] = 0x00; ether_addr_copy(br->group_addr, eth_stp_addr); br->stp_enabled = BR_NO_STP; br->group_fwd_mask = BR_GROUPFWD_DEFAULT; br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT; br->designated_root = br->bridge_id; br->bridge_max_age = br->max_age = 20 * HZ; br->bridge_hello_time = br->hello_time = 2 * HZ; br->bridge_forward_delay = br->forward_delay = 15 * HZ; br->bridge_ageing_time = br->ageing_time = BR_DEFAULT_AGEING_TIME; dev->max_mtu = ETH_MAX_MTU; br_netfilter_rtable_init(br); br_stp_timer_init(br); br_multicast_init(br); INIT_DELAYED_WORK(&br->gc_work, br_fdb_cleanup); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NOSPEC_BRANCH_H_ #define _ASM_X86_NOSPEC_BRANCH_H_ #include <linux/static_key.h> #include <linux/objtool.h> #include <linux/linkage.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> #include <asm/current.h> /* * Call depth tracking for Intel SKL CPUs to address the RSB underflow * issue in software. * * The tracking does not use a counter. It uses uses arithmetic shift * right on call entry and logical shift left on return. * * The depth tracking variable is initialized to 0x8000.... when the call * depth is zero. The arithmetic shift right sign extends the MSB and * saturates after the 12th call. The shift count is 5 for both directions * so the tracking covers 12 nested calls. * * Call * 0: 0x8000000000000000 0x0000000000000000 * 1: 0xfc00000000000000 0xf000000000000000 * ... * 11: 0xfffffffffffffff8 0xfffffffffffffc00 * 12: 0xffffffffffffffff 0xffffffffffffffe0 * * After a return buffer fill the depth is credited 12 calls before the * next stuffing has to take place. * * There is a inaccuracy for situations like this: * * 10 calls * 5 returns * 3 calls * 4 returns * 3 calls * .... * * The shift count might cause this to be off by one in either direction, * but there is still a cushion vs. the RSB depth. The algorithm does not * claim to be perfect and it can be speculated around by the CPU, but it * is considered that it obfuscates the problem enough to make exploitation * extremely difficult. */ #define RET_DEPTH_SHIFT 5 #define RSB_RET_STUFF_LOOPS 16 #define RET_DEPTH_INIT 0x8000000000000000ULL #define RET_DEPTH_INIT_FROM_CALL 0xfc00000000000000ULL #define RET_DEPTH_CREDIT 0xffffffffffffffffULL #ifdef CONFIG_CALL_THUNKS_DEBUG # define CALL_THUNKS_DEBUG_INC_CALLS \ incq %gs:__x86_call_count; # define CALL_THUNKS_DEBUG_INC_RETS \ incq %gs:__x86_ret_count; # define CALL_THUNKS_DEBUG_INC_STUFFS \ incq %gs:__x86_stuffs_count; # define CALL_THUNKS_DEBUG_INC_CTXSW \ incq %gs:__x86_ctxsw_count; #else # define CALL_THUNKS_DEBUG_INC_CALLS # define CALL_THUNKS_DEBUG_INC_RETS # define CALL_THUNKS_DEBUG_INC_STUFFS # define CALL_THUNKS_DEBUG_INC_CTXSW #endif #if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) #include <asm/asm-offsets.h> #define CREDIT_CALL_DEPTH \ movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); #define ASM_CREDIT_CALL_DEPTH \ movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); #define RESET_CALL_DEPTH \ xor %eax, %eax; \ bts $63, %rax; \ movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); #define RESET_CALL_DEPTH_FROM_CALL \ movb $0xfc, %al; \ shl $56, %rax; \ movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #define INCREMENT_CALL_DEPTH \ sarq $5, %gs:pcpu_hot + X86_call_depth; \ CALL_THUNKS_DEBUG_INC_CALLS #define ASM_INCREMENT_CALL_DEPTH \ sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #else #define CREDIT_CALL_DEPTH #define ASM_CREDIT_CALL_DEPTH #define RESET_CALL_DEPTH #define INCREMENT_CALL_DEPTH #define ASM_INCREMENT_CALL_DEPTH #define RESET_CALL_DEPTH_FROM_CALL #endif /* * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to * eliminate potentially bogus entries from the RSB, and sometimes * purely to ensure that it doesn't get empty, which on some CPUs would * allow predictions from other (unwanted!) sources to be used. * * We define a CPP macro such that it can be used from both .S files and * inline assembly. It's possible to do a .macro and then include that * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. */ #define RETPOLINE_THUNK_SIZE 32 #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. */ #define __FILL_RETURN_SLOT \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 772f; \ int3; \ 772: /* * Stuff the entire RSB. * * Google experimented with loop-unrolling and this turned out to be * the optimal version - two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ #ifdef CONFIG_X86_64 #define __FILL_RETURN_BUFFER(reg, nr) \ mov $(nr/2), reg; \ 771: \ __FILL_RETURN_SLOT \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ dec reg; \ jnz 771b; \ /* barrier for jnz misprediction */ \ lfence; \ ASM_CREDIT_CALL_DEPTH \ CALL_THUNKS_DEBUG_INC_CTXSW #else /* * i386 doesn't unconditionally have LFENCE, as such it can't * do a loop. */ #define __FILL_RETURN_BUFFER(reg, nr) \ .rept nr; \ __FILL_RETURN_SLOT; \ .endr; \ add $(BITS_PER_LONG/8) * nr, %_ASM_SP; #endif /* * Stuff a single RSB slot. * * To mitigate Post-Barrier RSB speculation, one CALL instruction must be * forced to retire before letting a RET instruction execute. * * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed * before this point. */ #define __FILL_ONE_RETURN \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; #ifdef __ASSEMBLY__ /* * This should be used immediately before an indirect jump/call. It tells * objtool the subsequent indirect jump/call is vouched safe for retpoline * builds. */ .macro ANNOTATE_RETPOLINE_SAFE .Lhere_\@: .pushsection .discard.retpoline_safe .long .Lhere_\@ .popsection .endm /* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. */ #define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE /* * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should * eventually turn into its own annotation. */ .macro VALIDATE_UNRET_END #if defined(CONFIG_NOINSTR_VALIDATION) && \ (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif .endm /* * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call * to the retpoline thunk with a CS prefix when the register requires * a RAX prefix byte to encode. Also see apply_retpolines(). */ .macro __CS_PREFIX reg:req .irp rs,r8,r9,r10,r11,r12,r13,r14,r15 .ifc \reg,\rs .byte 0x2e .endif .endr .endm /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. * * NOTE: these do not take kCFI into account and are thus not comparable to C * indirect calls, take care when using. The target of these should be an ENDBR * instruction irrespective of kCFI. */ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE __CS_PREFIX \reg jmp __x86_indirect_thunk_\reg #else jmp *%\reg int3 #endif .endm .macro CALL_NOSPEC reg:req #ifdef CONFIG_RETPOLINE __CS_PREFIX \reg call __x86_indirect_thunk_\reg #else call *%\reg #endif .endm /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ __stringify(nop;nop;__FILL_ONE_RETURN), \ftr2 .Lskip_rsb_\@: .endm #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) #define CALL_UNTRAIN_RET "call entry_untrain_ret" #else #define CALL_UNTRAIN_RET "" #endif /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * * While retbleed_untrain_ret() doesn't clobber anything but requires stack, * entry_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns #if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY) VALIDATE_UNRET_END ALTERNATIVE_3 "", \ CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ "call entry_ibpb", \ibpb_feature, \ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif .endm #define UNTRAIN_RET \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH) #define UNTRAIN_RET_VM \ __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH) #define UNTRAIN_RET_FROM_CALL \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL) .macro CALL_DEPTH_ACCOUNT #ifdef CONFIG_CALL_DEPTH_TRACKING ALTERNATIVE "", \ __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif .endm #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ ".long 999b\n\t" \ ".popsection\n\t" typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; #ifdef CONFIG_RETHUNK extern void __x86_return_thunk(void); #else static inline void __x86_return_thunk(void) {} #endif #ifdef CONFIG_CPU_UNRET_ENTRY extern void retbleed_return_thunk(void); #else static inline void retbleed_return_thunk(void) {} #endif #ifdef CONFIG_CPU_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); #else static inline void srso_return_thunk(void) {} static inline void srso_alias_return_thunk(void) {} #endif extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); extern void (*x86_return_thunk)(void); #ifdef CONFIG_CALL_DEPTH_TRACKING extern void call_depth_return_thunk(void); #define CALL_DEPTH_ACCOUNT \ ALTERNATIVE("", \ __stringify(INCREMENT_CALL_DEPTH), \ X86_FEATURE_CALL_DEPTH) #ifdef CONFIG_CALL_THUNKS_DEBUG DECLARE_PER_CPU(u64, __x86_call_count); DECLARE_PER_CPU(u64, __x86_ret_count); DECLARE_PER_CPU(u64, __x86_stuffs_count); DECLARE_PER_CPU(u64, __x86_ctxsw_count); #endif #else /* !CONFIG_CALL_DEPTH_TRACKING */ static inline void call_depth_return_thunk(void) {} #define CALL_DEPTH_ACCOUNT "" #endif /* CONFIG_CALL_DEPTH_TRACKING */ #ifdef CONFIG_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_call_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_jump_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #ifdef CONFIG_X86_64 /* * Inline asm uses the %V modifier which is only in newer GCC * which is ensured when CONFIG_RETPOLINE is defined. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ "call __x86_indirect_thunk_%V[thunk_target]\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "r" (addr) #else /* CONFIG_X86_32 */ /* * For i386 we use the original ret-equivalent retpoline, because * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ " jmp 904f;\n" \ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ "904: call 901b;\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif #else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, SPECTRE_V2_RETPOLINE, SPECTRE_V2_LFENCE, SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, SPECTRE_V2_IBRS, }; /* The indirect branch speculation control variants */ enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, SPECTRE_V2_USER_STRICT_PREFERRED, SPECTRE_V2_USER_PRCTL, SPECTRE_V2_USER_SECCOMP, }; /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, SPEC_STORE_BYPASS_DISABLE, SPEC_STORE_BYPASS_PRCTL, SPEC_STORE_BYPASS_SECCOMP, }; static __always_inline void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) { asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)), [feature] "i" (feature) : "memory"); } extern u64 x86_pred_cmd; static inline void indirect_branch_prediction_barrier(void) { alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); extern void update_spec_ctrl_cond(u64 val); extern u64 spec_ctrl_current(void); /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. * * (Implemented as CPP macros due to header hell.) */ #define firmware_restrict_branch_speculation_start() \ do { \ preempt_disable(); \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); #include <asm/segment.h> /** * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; /* * Has to be the memory-operand variant because only that * guarantees the CPU buffer flush functionality according to * documentation. The register-operand variant does not. * Works with any segment selector, but a valid writable * data segment is the fastest variant. * * "cc" clobber is required because VERW modifies ZF. */ asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); } /** * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static __always_inline void mds_user_clear_cpu_buffers(void) { if (static_branch_likely(&mds_user_clear)) mds_clear_cpu_buffers(); } /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static __always_inline void mds_idle_clear_cpu_buffers(void) { if (static_branch_likely(&mds_idle_clear)) mds_clear_cpu_buffers(); } #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ |
| 350 1485 1485 1143 350 350 49 49 43 43 43 43 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004 IBM Corporation * * Author: Serge Hallyn <serue@us.ibm.com> */ #include <linux/export.h> #include <linux/uts.h> #include <linux/utsname.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/sched/task.h> static struct kmem_cache *uts_ns_cache __ro_after_init; static struct ucounts *inc_uts_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_UTS_NAMESPACES); } static void dec_uts_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_UTS_NAMESPACES); } static struct uts_namespace *create_uts_ns(void) { struct uts_namespace *uts_ns; uts_ns = kmem_cache_alloc(uts_ns_cache, GFP_KERNEL); if (uts_ns) refcount_set(&uts_ns->ns.count, 1); return uts_ns; } /* * Clone a new ns copying an original utsname, setting refcount to 1 * @old_ns: namespace to clone * Return ERR_PTR(-ENOMEM) on error (failure to allocate), new ns otherwise */ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns, struct uts_namespace *old_ns) { struct uts_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; ucounts = inc_uts_namespaces(user_ns); if (!ucounts) goto fail; err = -ENOMEM; ns = create_uts_ns(); if (!ns) goto fail_dec; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free; ns->ucounts = ucounts; ns->ns.ops = &utsns_operations; down_read(&uts_sem); memcpy(&ns->name, &old_ns->name, sizeof(ns->name)); ns->user_ns = get_user_ns(user_ns); up_read(&uts_sem); return ns; fail_free: kmem_cache_free(uts_ns_cache, ns); fail_dec: dec_uts_namespaces(ucounts); fail: return ERR_PTR(err); } /* * Copy task tsk's utsname namespace, or clone it if flags * specifies CLONE_NEWUTS. In latter case, changes to the * utsname of this process won't be seen by parent, and vice * versa. */ struct uts_namespace *copy_utsname(unsigned long flags, struct user_namespace *user_ns, struct uts_namespace *old_ns) { struct uts_namespace *new_ns; BUG_ON(!old_ns); get_uts_ns(old_ns); if (!(flags & CLONE_NEWUTS)) return old_ns; new_ns = clone_uts_ns(user_ns, old_ns); put_uts_ns(old_ns); return new_ns; } void free_uts_ns(struct uts_namespace *ns) { dec_uts_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kmem_cache_free(uts_ns_cache, ns); } static inline struct uts_namespace *to_uts_ns(struct ns_common *ns) { return container_of(ns, struct uts_namespace, ns); } static struct ns_common *utsns_get(struct task_struct *task) { struct uts_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->uts_ns; get_uts_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void utsns_put(struct ns_common *ns) { put_uts_ns(to_uts_ns(ns)); } static int utsns_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct uts_namespace *ns = to_uts_ns(new); if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; get_uts_ns(ns); put_uts_ns(nsproxy->uts_ns); nsproxy->uts_ns = ns; return 0; } static struct user_namespace *utsns_owner(struct ns_common *ns) { return to_uts_ns(ns)->user_ns; } const struct proc_ns_operations utsns_operations = { .name = "uts", .type = CLONE_NEWUTS, .get = utsns_get, .put = utsns_put, .install = utsns_install, .owner = utsns_owner, }; void __init uts_ns_init(void) { uts_ns_cache = kmem_cache_create_usercopy( "uts_namespace", sizeof(struct uts_namespace), 0, SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct uts_namespace, name), sizeof_field(struct uts_namespace, name), NULL); } |
| 11 11 11 4 10 4 1 9 2 7 9 7 7 6 1 7 2 2 2 2 2 19 19 2 29 27 2 2 49 39 10 129 129 129 176 49 129 19 19 19 99 80 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { put_pid(filp->f_owner.pid); filp->f_owner.pid = get_pid(pid); filp->f_owner.pid_type = type; if (pid) { const struct cred *cred = current_cred(); filp->f_owner.uid = cred->uid; filp->f_owner.euid = cred->euid; } } write_unlock_irq(&filp->f_owner.lock); } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { security_file_set_fowner(filp); f_modown(filp, pid, type, force); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, int who, int force) { enum pid_type type; struct pid *pid = NULL; int ret = 0; type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { f_modown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { pid = pid_vnr(filp->f_owner.pid); if (filp->f_owner.pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&filp->f_owner.lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) owner.pid = pid_vnr(filp->f_owner.pid); rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } read_unlock_irq(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); uid_t __user *dst = (void __user *)arg; uid_t src[2]; int err; read_lock_irq(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); read_unlock_irq(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(enum rw_hint hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; enum rw_hint hint; u64 h; switch (cmd) { case F_GET_RW_HINT: h = inode->i_write_hint; if (copy_to_user(argp, &h, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: if (copy_from_user(&h, argp, sizeof(h))) return -EFAULT; hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; inode_lock(inode); inode->i_write_hint = hint; inode_unlock(inode); return 0; default: return -EINVAL; } } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; int argi = (int)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_DUPFD: err = f_dupfd(argi, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, argi & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, argi); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, argi, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = filp->f_owner.signum; break; case F_SETSIG: /* arg == 0 restores default behaviour. */ if (!valid_signal(argi)) { break; } err = 0; filp->f_owner.signum = argi; break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, argi); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, argi); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, argi); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, argi); break; case F_GET_RW_HINT: case F_SET_RW_HINT: err = fcntl_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget_raw(fd); long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, f.file); out1: fdput(f); out: return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; struct fd f = fdget_raw(fd); struct flock64 flock; long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out1; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(f.file, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, f.file, cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out1: fdput(f); out: return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { struct fd f = fdget_raw(fd); struct flock flock; long err = -EBADF; if (!f.file) return err; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out_put; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out_put; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out_put: fdput(f); return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct fown_struct *fown) { struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __ro_after_init; static void fasync_free_rcu(struct rcu_head *head) { kmem_cache_free(fasync_cache, container_of(head, struct fasync_struct, fa_rcu)); } /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; call_rcu(&fa->fa_rcu, fasync_free_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = &fa->fa_file->f_owner; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 3 3 1 1 1 2 3 3 12 12 12 12 12 12 11 5 3 6 12 3 6 7 7 4 3 7 6 4 3 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 | // SPDX-License-Identifier: GPL-2.0-or-later /* * udp_diag.c Module for monitoring UDP transport protocols sockets. * * Authors: Pavel Emelyanov, <xemul@parallels.com> */ #include <linux/module.h> #include <linux/inet_diag.h> #include <linux/udp.h> #include <net/udp.h> #include <net/udplite.h> #include <linux/sock_diag.h> static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *req, struct nlattr *bc, bool net_admin) { if (!inet_diag_bc_sk(bc, sk)) return 0; return inet_sk_diag_fill(sk, NULL, skb, cb, req, NLM_F_MULTI, net_admin); } static int udp_dump_one(struct udp_table *tbl, struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { struct sk_buff *in_skb = cb->skb; int err; struct sock *sk = NULL; struct sk_buff *rep; struct net *net = sock_net(in_skb->sk); rcu_read_lock(); if (req->sdiag_family == AF_INET) /* src and dst are swapped for historical reasons */ sk = __udp4_lib_lookup(net, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_if, 0, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) sk = __udp6_lib_lookup(net, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, req->id.idiag_if, 0, tbl, NULL); #endif if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); err = -ENOENT; if (!sk) goto out_nosk; err = sock_diag_check_cookie(sk, req->id.idiag_cookie); if (err) goto out; err = -ENOMEM; rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + inet_diag_msg_attrs_size() + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) goto out; err = inet_sk_diag_fill(sk, NULL, rep, cb, req, 0, netlink_net_capable(in_skb, CAP_NET_ADMIN)); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); goto out; } err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid); out: if (sk) sock_put(sk); out_nosk: return err; } static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN); struct net *net = sock_net(skb->sk); struct inet_diag_dump_data *cb_data; int num, s_num, slot, s_slot; struct nlattr *bc; cb_data = cb->data; bc = cb_data->inet_diag_nla_bc; s_slot = cb->args[0]; num = s_num = cb->args[1]; for (slot = s_slot; slot <= table->mask; s_num = 0, slot++) { struct udp_hslot *hslot = &table->hash[slot]; struct sock *sk; num = 0; if (hlist_empty(&hslot->head)) continue; spin_lock_bh(&hslot->lock); sk_for_each(sk, &hslot->head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) goto next; if (!(r->idiag_states & (1 << sk->sk_state))) goto next; if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next; if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next; if (r->id.idiag_dport != inet->inet_dport && r->id.idiag_dport) goto next; if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) { spin_unlock_bh(&hslot->lock); goto done; } next: num++; } spin_unlock_bh(&hslot->lock); } done: cb->args[0] = slot; cb->args[1] = num; } static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { udp_dump(sock_net(cb->skb->sk)->ipv4.udp_table, skb, cb, r); } static int udp_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { return udp_dump_one(sock_net(cb->skb->sk)->ipv4.udp_table, cb, req); } static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, void *info) { r->idiag_rqueue = udp_rqueue_get(sk); r->idiag_wqueue = sk_wmem_alloc_get(sk); } #ifdef CONFIG_INET_DIAG_DESTROY static int __udp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req, struct udp_table *tbl) { struct net *net = sock_net(in_skb->sk); struct sock *sk; int err; rcu_read_lock(); if (req->sdiag_family == AF_INET) sk = __udp4_lib_lookup(net, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); #if IS_ENABLED(CONFIG_IPV6) else if (req->sdiag_family == AF_INET6) { if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) sk = __udp4_lib_lookup(net, req->id.idiag_dst[3], req->id.idiag_dport, req->id.idiag_src[3], req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); else sk = __udp6_lib_lookup(net, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, (struct in6_addr *)req->id.idiag_src, req->id.idiag_sport, req->id.idiag_if, 0, tbl, NULL); } #endif else { rcu_read_unlock(); return -EINVAL; } if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; rcu_read_unlock(); if (!sk) return -ENOENT; if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) { sock_put(sk); return -ENOENT; } err = sock_diag_destroy(sk, ECONNABORTED); sock_put(sk); return err; } static int udp_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { return __udp_diag_destroy(in_skb, req, sock_net(in_skb->sk)->ipv4.udp_table); } static int udplite_diag_destroy(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req) { return __udp_diag_destroy(in_skb, req, &udplite_table); } #endif static const struct inet_diag_handler udp_diag_handler = { .dump = udp_diag_dump, .dump_one = udp_diag_dump_one, .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDP, .idiag_info_size = 0, #ifdef CONFIG_INET_DIAG_DESTROY .destroy = udp_diag_destroy, #endif }; static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r) { udp_dump(&udplite_table, skb, cb, r); } static int udplite_diag_dump_one(struct netlink_callback *cb, const struct inet_diag_req_v2 *req) { return udp_dump_one(&udplite_table, cb, req); } static const struct inet_diag_handler udplite_diag_handler = { .dump = udplite_diag_dump, .dump_one = udplite_diag_dump_one, .idiag_get_info = udp_diag_get_info, .idiag_type = IPPROTO_UDPLITE, .idiag_info_size = 0, #ifdef CONFIG_INET_DIAG_DESTROY .destroy = udplite_diag_destroy, #endif }; static int __init udp_diag_init(void) { int err; err = inet_diag_register(&udp_diag_handler); if (err) goto out; err = inet_diag_register(&udplite_diag_handler); if (err) goto out_lite; out: return err; out_lite: inet_diag_unregister(&udp_diag_handler); goto out; } static void __exit udp_diag_exit(void) { inet_diag_unregister(&udplite_diag_handler); inet_diag_unregister(&udp_diag_handler); } module_init(udp_diag_init); module_exit(udp_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("UDP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_H #define _ASM_X86_UACCESS_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/instrumented.h> #include <linux/kasan-checks.h> #include <linux/mm_types.h> #include <linux/string.h> #include <linux/mmap_lock.h> #include <asm/asm.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/extable.h> #include <asm/tlbflush.h> #ifdef CONFIG_X86_32 # include <asm/uaccess_32.h> #else # include <asm/uaccess_64.h> #endif #include <asm-generic/access_ok.h> extern int __get_user_1(void); extern int __get_user_2(void); extern int __get_user_4(void); extern int __get_user_8(void); extern int __get_user_nocheck_1(void); extern int __get_user_nocheck_2(void); extern int __get_user_nocheck_4(void); extern int __get_user_nocheck_8(void); extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() #define __uaccess_begin_nospec() \ ({ \ stac(); \ barrier_nospec(); \ }) /* * This is the smallest unsigned integer type that can fit a value * (up to 'long long') */ #define __inttype(x) __typeof__( \ __typefits(x,char, \ __typefits(x,short, \ __typefits(x,int, \ __typefits(x,long,0ULL))))) #define __typefits(x,type,not) \ __builtin_choose_expr(sizeof(x)<=sizeof(type),(unsigned type)0,not) /* * This is used for both get_user() and __get_user() to expand to * the proper special function call that has odd calling conventions * due to returning both a value and an error, and that depends on * the size of the pointer passed in. * * Careful: we have to cast the result to the type of the pointer * for sign reasons. * * The use of _ASM_DX as the register specifier is a bit of a * simplification, as gcc only cares about it as the starting point * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits * (%ecx being the next register in gcc's x86 register sequence), and * %rdx on 64 bits. * * Clang/LLVM cares about the size of the register, but still wants * the base register for something that ends up being a pair. */ #define do_get_user_call(fn,x,ptr) \ ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ asm volatile("call __" #fn "_%P4" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ instrument_get_user(__val_gu); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ }) /** * get_user - Get a simple variable from user space. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define get_user(x,ptr) ({ might_fault(); do_get_user_call(get_user,x,ptr); }) /** * __get_user - Get a simple variable from user space, with less checking. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define __get_user(x,ptr) do_get_user_call(get_user_nocheck,x,ptr) #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ asm goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ _ASM_EXTABLE_UA(2b, %l2) \ : : "A" (x), "r" (addr) \ : : label) #else #define __put_user_goto_u64(x, ptr, label) \ __put_user_goto(x, ptr, "q", "er", label) #endif extern void __put_user_bad(void); /* * Strange magic calling convention: pointer in %ecx, * value in %eax(:%edx), return value in %ecx. clobbers %rbx */ extern void __put_user_1(void); extern void __put_user_2(void); extern void __put_user_4(void); extern void __put_user_8(void); extern void __put_user_nocheck_1(void); extern void __put_user_nocheck_2(void); extern void __put_user_nocheck_4(void); extern void __put_user_nocheck_8(void); /* * ptr must be evaluated and assigned to the temporary __ptr_pu before * the assignment of x to __val_pu, to avoid any function calls * involved in the ptr expression (possibly implicitly generated due * to KASAN) from clobbering %ax. */ #define do_put_user_call(fn,x,ptr) \ ({ \ int __ret_pu; \ void __user *__ptr_pu; \ register __typeof__(*(ptr)) __val_pu asm("%"_ASM_AX); \ __typeof__(*(ptr)) __x = (x); /* eval x once */ \ __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \ __chk_user_ptr(__ptr); \ __ptr_pu = __ptr; \ __val_pu = __x; \ asm volatile("call __" #fn "_%P[size]" \ : "=c" (__ret_pu), \ ASM_CALL_CONSTRAINT \ : "0" (__ptr_pu), \ "r" (__val_pu), \ [size] "i" (sizeof(*(ptr))) \ :"ebx"); \ instrument_put_user(__x, __ptr, sizeof(*(ptr))); \ __builtin_expect(__ret_pu, 0); \ }) /** * put_user - Write a simple value into user space. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Return: zero on success, or -EFAULT on error. */ #define put_user(x, ptr) ({ might_fault(); do_put_user_call(put_user,x,ptr); }) /** * __put_user - Write a simple value into user space, with less checking. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. */ #define __put_user(x, ptr) do_put_user_call(put_user_nocheck,x,ptr) #define __put_user_size(x, ptr, size, label) \ do { \ __typeof__(*(ptr)) __x = (x); /* eval x once */ \ __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \ __chk_user_ptr(__ptr); \ switch (size) { \ case 1: \ __put_user_goto(__x, __ptr, "b", "iq", label); \ break; \ case 2: \ __put_user_goto(__x, __ptr, "w", "ir", label); \ break; \ case 4: \ __put_user_goto(__x, __ptr, "l", "ir", label); \ break; \ case 8: \ __put_user_goto_u64(__x, __ptr, label); \ break; \ default: \ __put_user_bad(); \ } \ instrument_put_user(__x, __ptr, size); \ } while (0) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, label) do { \ unsigned int __gu_low, __gu_high; \ const unsigned int __user *__gu_ptr; \ __gu_ptr = (const void __user *)(ptr); \ __get_user_asm(__gu_low, __gu_ptr, "l", "=r", label); \ __get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label); \ (x) = ((unsigned long long)__gu_high << 32) | __gu_low; \ } while (0) #else #define __get_user_asm_u64(x, ptr, label) \ __get_user_asm(x, ptr, "q", "=r", label) #endif #define __get_user_size(x, ptr, size, label) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: { \ unsigned char x_u8__; \ __get_user_asm(x_u8__, ptr, "b", "=q", label); \ (x) = x_u8__; \ break; \ } \ case 2: \ __get_user_asm(x, ptr, "w", "=r", label); \ break; \ case 4: \ __get_user_asm(x, ptr, "l", "=r", label); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, label); \ break; \ default: \ (x) = __get_user_bad(); \ } \ instrument_get_user(x); \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ asm_goto_output("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ : [umem] "m" (__m(addr)) \ : : label) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, retval) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ asm volatile("\n" \ "1: movl %[lowbits],%%eax\n" \ "2: movl %[highbits],%%edx\n" \ "3:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG | \ EX_FLAG_CLEAR_AX_DX, \ %[errout]) \ _ASM_EXTABLE_TYPE_REG(2b, 3b, EX_TYPE_EFAULT_REG | \ EX_FLAG_CLEAR_AX_DX, \ %[errout]) \ : [errout] "=r" (retval), \ [output] "=&A"(x) \ : [lowbits] "m" (__m(__ptr)), \ [highbits] "m" __m(((u32 __user *)(__ptr)) + 1), \ "0" (retval)); \ }) #else #define __get_user_asm_u64(x, ptr, retval) \ __get_user_asm(x, ptr, retval, "q") #endif #define __get_user_size(x, ptr, size, retval) \ do { \ unsigned char x_u8__; \ \ retval = 0; \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __get_user_asm(x_u8__, ptr, retval, "b"); \ (x) = x_u8__; \ break; \ case 2: \ __get_user_asm(x, ptr, retval, "w"); \ break; \ case 4: \ __get_user_asm(x, ptr, retval, "l"); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, retval); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, err, itype) \ asm volatile("\n" \ "1: mov"itype" %[umem],%[output]\n" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG | \ EX_FLAG_CLEAR_AX, \ %[errout]) \ : [errout] "=r" (err), \ [output] "=a" (x) \ : [umem] "m" (__m(addr)), \ "0" (err)) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_goto_output("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #endif // CONFIG_X86_32 #else // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ int __err = 0; \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ CC_SET(z) \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ %[errout]) \ : CC_OUT(z) (success), \ [errout] "+r" (__err), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory"); \ if (unlikely(__err)) \ goto label; \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 /* * Unlike the normal CMPXCHG, use output GPR for both success/fail and error. * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses * both ESI and EDI for the memory operand, compilation will fail if the error * is an input+output as there will be no register available for input. */ #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ int __result; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ "mov $0, %[result]\n\t" \ "setz %b[result]\n" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ %[result]) \ : [result] "=q" (__result), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory", "cc"); \ if (unlikely(__result < 0)) \ goto label; \ if (unlikely(!__result)) \ *_old = __old; \ likely(__result); }) #endif // CONFIG_X86_32 #endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; #define __m(x) (*(struct __large_struct __user *)(x)) /* * Tell gcc we read from memory instead of writing: this is because * we do not write to any memory gcc knows about, so there are no * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ asm goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ : : label) extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); extern __must_check long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); #ifdef CONFIG_ARCH_HAS_COPY_MC unsigned long __must_check copy_mc_to_kernel(void *to, const void *from, unsigned len); #define copy_mc_to_kernel copy_mc_to_kernel unsigned long __must_check copy_mc_to_user(void __user *to, const void *from, unsigned len); #endif /* * movsl can be slow when source and dest are not both 8-byte aligned */ #ifdef CONFIG_X86_INTEL_USERCOPY extern struct movsl_mask { int mask; } ____cacheline_aligned_in_smp movsl_mask; #endif #define ARCH_HAS_NOCACHE_UACCESS 1 /* * The "unsafe" user accesses aren't really "unsafe", but the naming * is a big fat warning: you have to not only do the access_ok() * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr,len))) return 0; __uaccess_begin_nospec(); return 1; } #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() #define user_access_save() smap_save() #define user_access_restore(x) smap_restore(x) #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), err_label); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT extern void __try_cmpxchg_user_wrong_size(void); #ifndef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label) \ __try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label) #endif /* * Force the pointer to u<size> to match the size expected by the asm helper. * clang/LLVM compiles all cases and only discards the unused paths after * processing errors, which breaks i386 if the pointer is an 8-byte value. */ #define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ bool __ret; \ __chk_user_ptr(_ptr); \ switch (sizeof(*(_ptr))) { \ case 1: __ret = __try_cmpxchg_user_asm("b", "q", \ (__force u8 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 2: __ret = __try_cmpxchg_user_asm("w", "r", \ (__force u16 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 4: __ret = __try_cmpxchg_user_asm("l", "r", \ (__force u32 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 8: __ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\ (_nval), _label); \ break; \ default: __try_cmpxchg_user_wrong_size(); \ } \ __ret; }) /* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */ #define __try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ int __ret = -EFAULT; \ __uaccess_begin_nospec(); \ __ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label); \ _label: \ __uaccess_end(); \ __ret; \ }) /* * We want the unsafe accessors to always be inlined and use * the error labels - thus the macro games. */ #define unsafe_copy_loop(dst, src, len, type, label) \ while (len >= sizeof(type)) { \ unsafe_put_user(*(type *)(src),(type __user *)(dst),label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } #define unsafe_copy_to_user(_dst,_src,_len,label) \ do { \ char __user *__ucu_dst = (_dst); \ const char *__ucu_src = (_src); \ size_t __ucu_len = (_len); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ } while (0) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ sizeof(type), err_label) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ int __kr_err; \ \ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ sizeof(type), __kr_err); \ if (unlikely(__kr_err)) \ goto err_label; \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __put_kernel_nofault(dst, src, type, err_label) \ __put_user_size(*((type *)(src)), (__force type __user *)(dst), \ sizeof(type), err_label) #endif /* _ASM_X86_UACCESS_H */ |
| 9910 9909 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGALLOC_TRACK_H #define _LINUX_PGALLOC_TRACK_H #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pgd_none(*pgd))) { if (__p4d_alloc(mm, pgd, address)) return NULL; *mod_mask |= PGTBL_PGD_MODIFIED; } return p4d_offset(pgd, address); } static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(p4d_none(*p4d))) { if (__pud_alloc(mm, p4d, address)) return NULL; *mod_mask |= PGTBL_P4D_MODIFIED; } return pud_offset(p4d, address); } static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pud_none(*pud))) { if (__pmd_alloc(mm, pud, address)) return NULL; *mod_mask |= PGTBL_PUD_MODIFIED; } return pmd_offset(pud, address); } #endif /* CONFIG_MMU */ #define pte_alloc_kernel_track(pmd, address, mask) \ ((unlikely(pmd_none(*(pmd))) && \ (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ NULL: pte_offset_kernel(pmd, address)) #endif /* _LINUX_PGALLOC_TRACK_H */ |
| 1 1 1 5 4 2 2 7 1 6 2 2 2 1 1 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2017 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/if.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/kernel.h> #include <linux/openvswitch.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <net/netlink.h> #include <net/genetlink.h> #include "datapath.h" #include "meter.h" static const struct nla_policy meter_policy[OVS_METER_ATTR_MAX + 1] = { [OVS_METER_ATTR_ID] = { .type = NLA_U32, }, [OVS_METER_ATTR_KBPS] = { .type = NLA_FLAG }, [OVS_METER_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) }, [OVS_METER_ATTR_BANDS] = { .type = NLA_NESTED }, [OVS_METER_ATTR_USED] = { .type = NLA_U64 }, [OVS_METER_ATTR_CLEAR] = { .type = NLA_FLAG }, [OVS_METER_ATTR_MAX_METERS] = { .type = NLA_U32 }, [OVS_METER_ATTR_MAX_BANDS] = { .type = NLA_U32 }, }; static const struct nla_policy band_policy[OVS_BAND_ATTR_MAX + 1] = { [OVS_BAND_ATTR_TYPE] = { .type = NLA_U32, }, [OVS_BAND_ATTR_RATE] = { .type = NLA_U32, }, [OVS_BAND_ATTR_BURST] = { .type = NLA_U32, }, [OVS_BAND_ATTR_STATS] = { .len = sizeof(struct ovs_flow_stats) }, }; static u32 meter_hash(struct dp_meter_instance *ti, u32 id) { return id % ti->n_meters; } static void ovs_meter_free(struct dp_meter *meter) { if (!meter) return; kfree_rcu(meter, rcu); } /* Call with ovs_mutex or RCU read lock. */ static struct dp_meter *lookup_meter(const struct dp_meter_table *tbl, u32 meter_id) { struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); u32 hash = meter_hash(ti, meter_id); struct dp_meter *meter; meter = rcu_dereference_ovsl(ti->dp_meters[hash]); if (meter && likely(meter->id == meter_id)) return meter; return NULL; } static struct dp_meter_instance *dp_meter_instance_alloc(const u32 size) { struct dp_meter_instance *ti; ti = kvzalloc(struct_size(ti, dp_meters, size), GFP_KERNEL); if (!ti) return NULL; ti->n_meters = size; return ti; } static void dp_meter_instance_free(struct dp_meter_instance *ti) { kvfree(ti); } static void dp_meter_instance_free_rcu(struct rcu_head *rcu) { struct dp_meter_instance *ti; ti = container_of(rcu, struct dp_meter_instance, rcu); kvfree(ti); } static int dp_meter_instance_realloc(struct dp_meter_table *tbl, u32 size) { struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); int n_meters = min(size, ti->n_meters); struct dp_meter_instance *new_ti; int i; new_ti = dp_meter_instance_alloc(size); if (!new_ti) return -ENOMEM; for (i = 0; i < n_meters; i++) if (rcu_dereference_ovsl(ti->dp_meters[i])) new_ti->dp_meters[i] = ti->dp_meters[i]; rcu_assign_pointer(tbl->ti, new_ti); call_rcu(&ti->rcu, dp_meter_instance_free_rcu); return 0; } static void dp_meter_instance_insert(struct dp_meter_instance *ti, struct dp_meter *meter) { u32 hash; hash = meter_hash(ti, meter->id); rcu_assign_pointer(ti->dp_meters[hash], meter); } static void dp_meter_instance_remove(struct dp_meter_instance *ti, struct dp_meter *meter) { u32 hash; hash = meter_hash(ti, meter->id); RCU_INIT_POINTER(ti->dp_meters[hash], NULL); } static int attach_meter(struct dp_meter_table *tbl, struct dp_meter *meter) { struct dp_meter_instance *ti = rcu_dereference_ovsl(tbl->ti); u32 hash = meter_hash(ti, meter->id); int err; /* In generally, slots selected should be empty, because * OvS uses id-pool to fetch a available id. */ if (unlikely(rcu_dereference_ovsl(ti->dp_meters[hash]))) return -EBUSY; dp_meter_instance_insert(ti, meter); /* That function is thread-safe. */ tbl->count++; if (tbl->count >= tbl->max_meters_allowed) { err = -EFBIG; goto attach_err; } if (tbl->count >= ti->n_meters && dp_meter_instance_realloc(tbl, ti->n_meters * 2)) { err = -ENOMEM; goto attach_err; } return 0; attach_err: dp_meter_instance_remove(ti, meter); tbl->count--; return err; } static int detach_meter(struct dp_meter_table *tbl, struct dp_meter *meter) { struct dp_meter_instance *ti; ASSERT_OVSL(); if (!meter) return 0; ti = rcu_dereference_ovsl(tbl->ti); dp_meter_instance_remove(ti, meter); tbl->count--; /* Shrink the meter array if necessary. */ if (ti->n_meters > DP_METER_ARRAY_SIZE_MIN && tbl->count <= (ti->n_meters / 4)) { int half_size = ti->n_meters / 2; int i; /* Avoid hash collision, don't move slots to other place. * Make sure there are no references of meters in array * which will be released. */ for (i = half_size; i < ti->n_meters; i++) if (rcu_dereference_ovsl(ti->dp_meters[i])) goto out; if (dp_meter_instance_realloc(tbl, half_size)) goto shrink_err; } out: return 0; shrink_err: dp_meter_instance_insert(ti, meter); tbl->count++; return -ENOMEM; } static struct sk_buff * ovs_meter_cmd_reply_start(struct genl_info *info, u8 cmd, struct ovs_header **ovs_reply_header) { struct sk_buff *skb; struct ovs_header *ovs_header = genl_info_userhdr(info); skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return ERR_PTR(-ENOMEM); *ovs_reply_header = genlmsg_put(skb, info->snd_portid, info->snd_seq, &dp_meter_genl_family, 0, cmd); if (!*ovs_reply_header) { nlmsg_free(skb); return ERR_PTR(-EMSGSIZE); } (*ovs_reply_header)->dp_ifindex = ovs_header->dp_ifindex; return skb; } static int ovs_meter_cmd_reply_stats(struct sk_buff *reply, u32 meter_id, struct dp_meter *meter) { struct nlattr *nla; struct dp_meter_band *band; u16 i; if (nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id)) goto error; if (nla_put(reply, OVS_METER_ATTR_STATS, sizeof(struct ovs_flow_stats), &meter->stats)) goto error; if (nla_put_u64_64bit(reply, OVS_METER_ATTR_USED, meter->used, OVS_METER_ATTR_PAD)) goto error; nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS); if (!nla) goto error; band = meter->bands; for (i = 0; i < meter->n_bands; ++i, ++band) { struct nlattr *band_nla; band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC); if (!band_nla || nla_put(reply, OVS_BAND_ATTR_STATS, sizeof(struct ovs_flow_stats), &band->stats)) goto error; nla_nest_end(reply, band_nla); } nla_nest_end(reply, nla); return 0; error: return -EMSGSIZE; } static int ovs_meter_cmd_features(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr *nla, *band_nla; struct sk_buff *reply; struct datapath *dp; int err = -EMSGSIZE; reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_FEATURES, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto exit_unlock; } if (nla_put_u32(reply, OVS_METER_ATTR_MAX_METERS, dp->meter_tbl.max_meters_allowed)) goto exit_unlock; ovs_unlock(); if (nla_put_u32(reply, OVS_METER_ATTR_MAX_BANDS, DP_MAX_BANDS)) goto nla_put_failure; nla = nla_nest_start_noflag(reply, OVS_METER_ATTR_BANDS); if (!nla) goto nla_put_failure; band_nla = nla_nest_start_noflag(reply, OVS_BAND_ATTR_UNSPEC); if (!band_nla) goto nla_put_failure; /* Currently only DROP band type is supported. */ if (nla_put_u32(reply, OVS_BAND_ATTR_TYPE, OVS_METER_BAND_TYPE_DROP)) goto nla_put_failure; nla_nest_end(reply, band_nla); nla_nest_end(reply, nla); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_unlock: ovs_unlock(); nla_put_failure: nlmsg_free(reply); return err; } static struct dp_meter *dp_meter_create(struct nlattr **a) { struct nlattr *nla; int rem; u16 n_bands = 0; struct dp_meter *meter; struct dp_meter_band *band; int err; /* Validate attributes, count the bands. */ if (!a[OVS_METER_ATTR_BANDS]) return ERR_PTR(-EINVAL); nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) if (++n_bands > DP_MAX_BANDS) return ERR_PTR(-EINVAL); /* Allocate and set up the meter before locking anything. */ meter = kzalloc(struct_size(meter, bands, n_bands), GFP_KERNEL_ACCOUNT); if (!meter) return ERR_PTR(-ENOMEM); meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]); meter->used = div_u64(ktime_get_ns(), 1000 * 1000); meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0; meter->keep_stats = !a[OVS_METER_ATTR_CLEAR]; spin_lock_init(&meter->lock); if (meter->keep_stats && a[OVS_METER_ATTR_STATS]) { meter->stats = *(struct ovs_flow_stats *) nla_data(a[OVS_METER_ATTR_STATS]); } meter->n_bands = n_bands; /* Set up meter bands. */ band = meter->bands; nla_for_each_nested(nla, a[OVS_METER_ATTR_BANDS], rem) { struct nlattr *attr[OVS_BAND_ATTR_MAX + 1]; u32 band_max_delta_t; err = nla_parse_deprecated((struct nlattr **)&attr, OVS_BAND_ATTR_MAX, nla_data(nla), nla_len(nla), band_policy, NULL); if (err) goto exit_free_meter; if (!attr[OVS_BAND_ATTR_TYPE] || !attr[OVS_BAND_ATTR_RATE] || !attr[OVS_BAND_ATTR_BURST]) { err = -EINVAL; goto exit_free_meter; } band->type = nla_get_u32(attr[OVS_BAND_ATTR_TYPE]); band->rate = nla_get_u32(attr[OVS_BAND_ATTR_RATE]); if (band->rate == 0) { err = -EINVAL; goto exit_free_meter; } band->burst_size = nla_get_u32(attr[OVS_BAND_ATTR_BURST]); /* Figure out max delta_t that is enough to fill any bucket. * Keep max_delta_t size to the bucket units: * pkts => 1/1000 packets, kilobits => bits. * * Start with a full bucket. */ band->bucket = band->burst_size * 1000ULL; band_max_delta_t = div_u64(band->bucket, band->rate); if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; band++; } return meter; exit_free_meter: kfree(meter); return ERR_PTR(err); } static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct dp_meter *meter, *old_meter; struct sk_buff *reply; struct ovs_header *ovs_reply_header; struct ovs_header *ovs_header = genl_info_userhdr(info); struct dp_meter_table *meter_tbl; struct datapath *dp; int err; u32 meter_id; bool failed; if (!a[OVS_METER_ATTR_ID]) return -EINVAL; meter = dp_meter_create(a); if (IS_ERR(meter)) return PTR_ERR(meter); reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET, &ovs_reply_header); if (IS_ERR(reply)) { err = PTR_ERR(reply); goto exit_free_meter; } ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto exit_unlock; } meter_tbl = &dp->meter_tbl; meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); old_meter = lookup_meter(meter_tbl, meter_id); err = detach_meter(meter_tbl, old_meter); if (err) goto exit_unlock; err = attach_meter(meter_tbl, meter); if (err) goto exit_free_old_meter; ovs_unlock(); /* Build response with the meter_id and stats from * the old meter, if any. */ failed = nla_put_u32(reply, OVS_METER_ATTR_ID, meter_id); WARN_ON(failed); if (old_meter) { spin_lock_bh(&old_meter->lock); if (old_meter->keep_stats) { err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter); WARN_ON(err); } spin_unlock_bh(&old_meter->lock); ovs_meter_free(old_meter); } genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_free_old_meter: ovs_meter_free(old_meter); exit_unlock: ovs_unlock(); nlmsg_free(reply); exit_free_meter: kfree(meter); return err; } static int ovs_meter_cmd_get(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr **a = info->attrs; struct dp_meter *meter; struct sk_buff *reply; struct datapath *dp; u32 meter_id; int err; if (!a[OVS_METER_ATTR_ID]) return -EINVAL; meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_GET, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto exit_unlock; } /* Locate meter, copy stats. */ meter = lookup_meter(&dp->meter_tbl, meter_id); if (!meter) { err = -ENOENT; goto exit_unlock; } spin_lock_bh(&meter->lock); err = ovs_meter_cmd_reply_stats(reply, meter_id, meter); spin_unlock_bh(&meter->lock); if (err) goto exit_unlock; ovs_unlock(); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_unlock: ovs_unlock(); nlmsg_free(reply); return err; } static int ovs_meter_cmd_del(struct sk_buff *skb, struct genl_info *info) { struct ovs_header *ovs_header = genl_info_userhdr(info); struct ovs_header *ovs_reply_header; struct nlattr **a = info->attrs; struct dp_meter *old_meter; struct sk_buff *reply; struct datapath *dp; u32 meter_id; int err; if (!a[OVS_METER_ATTR_ID]) return -EINVAL; reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_DEL, &ovs_reply_header); if (IS_ERR(reply)) return PTR_ERR(reply); ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); if (!dp) { err = -ENODEV; goto exit_unlock; } meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); old_meter = lookup_meter(&dp->meter_tbl, meter_id); if (old_meter) { spin_lock_bh(&old_meter->lock); err = ovs_meter_cmd_reply_stats(reply, meter_id, old_meter); WARN_ON(err); spin_unlock_bh(&old_meter->lock); err = detach_meter(&dp->meter_tbl, old_meter); if (err) goto exit_unlock; } ovs_unlock(); ovs_meter_free(old_meter); genlmsg_end(reply, ovs_reply_header); return genlmsg_reply(reply, info); exit_unlock: ovs_unlock(); nlmsg_free(reply); return err; } /* Meter action execution. * * Return true 'meter_id' drop band is triggered. The 'skb' should be * dropped by the caller'. */ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, u32 meter_id) { long long int now_ms = div_u64(ktime_get_ns(), 1000 * 1000); long long int long_delta_ms; struct dp_meter_band *band; struct dp_meter *meter; int i, band_exceeded_max = -1; u32 band_exceeded_rate = 0; u32 delta_ms; u32 cost; meter = lookup_meter(&dp->meter_tbl, meter_id); /* Do not drop the packet when there is no meter. */ if (!meter) return false; /* Lock the meter while using it. */ spin_lock(&meter->lock); long_delta_ms = (now_ms - meter->used); /* ms */ if (long_delta_ms < 0) { /* This condition means that we have several threads fighting * for a meter lock, and the one who received the packets a * bit later wins. Assuming that all racing threads received * packets at the same time to avoid overflow. */ long_delta_ms = 0; } /* Make sure delta_ms will not be too large, so that bucket will not * wrap around below. */ delta_ms = (long_delta_ms > (long long int)meter->max_delta_t) ? meter->max_delta_t : (u32)long_delta_ms; /* Update meter statistics. */ meter->used = now_ms; meter->stats.n_packets += 1; meter->stats.n_bytes += skb->len; /* Bucket rate is either in kilobits per second, or in packets per * second. We maintain the bucket in the units of either bits or * 1/1000th of a packet, correspondingly. * Then, when rate is multiplied with milliseconds, we get the * bucket units: * msec * kbps = bits, and * msec * packets/sec = 1/1000 packets. * * 'cost' is the number of bucket units in this packet. */ cost = (meter->kbps) ? skb->len * 8 : 1000; /* Update all bands and find the one hit with the highest rate. */ for (i = 0; i < meter->n_bands; ++i) { long long int max_bucket_size; band = &meter->bands[i]; max_bucket_size = band->burst_size * 1000LL; band->bucket += delta_ms * band->rate; if (band->bucket > max_bucket_size) band->bucket = max_bucket_size; if (band->bucket >= cost) { band->bucket -= cost; } else if (band->rate > band_exceeded_rate) { band_exceeded_rate = band->rate; band_exceeded_max = i; } } if (band_exceeded_max >= 0) { /* Update band statistics. */ band = &meter->bands[band_exceeded_max]; band->stats.n_packets += 1; band->stats.n_bytes += skb->len; /* Drop band triggered, let the caller drop the 'skb'. */ if (band->type == OVS_METER_BAND_TYPE_DROP) { spin_unlock(&meter->lock); return true; } } spin_unlock(&meter->lock); return false; } static const struct genl_small_ops dp_meter_genl_ops[] = { { .cmd = OVS_METER_CMD_FEATURES, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_meter_cmd_features }, { .cmd = OVS_METER_CMD_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ .doit = ovs_meter_cmd_set, }, { .cmd = OVS_METER_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = 0, /* OK for unprivileged users. */ .doit = ovs_meter_cmd_get, }, { .cmd = OVS_METER_CMD_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN * privilege. */ .doit = ovs_meter_cmd_del }, }; static const struct genl_multicast_group ovs_meter_multicast_group = { .name = OVS_METER_MCGROUP, }; struct genl_family dp_meter_genl_family __ro_after_init = { .hdrsize = sizeof(struct ovs_header), .name = OVS_METER_FAMILY, .version = OVS_METER_VERSION, .maxattr = OVS_METER_ATTR_MAX, .policy = meter_policy, .netnsok = true, .parallel_ops = true, .small_ops = dp_meter_genl_ops, .n_small_ops = ARRAY_SIZE(dp_meter_genl_ops), .resv_start_op = OVS_METER_CMD_GET + 1, .mcgrps = &ovs_meter_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, }; int ovs_meters_init(struct datapath *dp) { struct dp_meter_table *tbl = &dp->meter_tbl; struct dp_meter_instance *ti; unsigned long free_mem_bytes; ti = dp_meter_instance_alloc(DP_METER_ARRAY_SIZE_MIN); if (!ti) return -ENOMEM; /* Allow meters in a datapath to use ~3.12% of physical memory. */ free_mem_bytes = nr_free_buffer_pages() * (PAGE_SIZE >> 5); tbl->max_meters_allowed = min(free_mem_bytes / sizeof(struct dp_meter), DP_METER_NUM_MAX); if (!tbl->max_meters_allowed) goto out_err; rcu_assign_pointer(tbl->ti, ti); tbl->count = 0; return 0; out_err: dp_meter_instance_free(ti); return -ENOMEM; } void ovs_meters_exit(struct datapath *dp) { struct dp_meter_table *tbl = &dp->meter_tbl; struct dp_meter_instance *ti = rcu_dereference_raw(tbl->ti); int i; for (i = 0; i < ti->n_meters; i++) ovs_meter_free(rcu_dereference_raw(ti->dp_meters[i])); dp_meter_instance_free(ti); } |
| 45 5 40 1 1 1 1 74 39 75 75 74 74 39 39 39 39 39 39 39 40 72 72 40 1 42 40 40 36 40 40 41 40 40 40 40 40 39 39 85 85 44 44 44 44 42 164 144 16 122 36 1 2 85 63 63 63 63 63 63 34 63 63 220 153 67 62 1 1 17 1 40 39 2 37 39 38 38 36 29 34 38 38 35 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Userspace interface * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/netpoll.h> #include <linux/ethtool.h> #include <linux/if_arp.h> #include <linux/module.h> #include <linux/init.h> #include <linux/rtnetlink.h> #include <linux/if_ether.h> #include <linux/slab.h> #include <net/dsa.h> #include <net/sock.h> #include <linux/if_vlan.h> #include <net/switchdev.h> #include <net/net_namespace.h> #include "br_private.h" /* * Determine initial path cost based on speed. * using recommendations from 802.1d standard * * Since driver might sleep need to not be holding any locks. */ static int port_cost(struct net_device *dev) { struct ethtool_link_ksettings ecmd; if (!__ethtool_get_link_ksettings(dev, &ecmd)) { switch (ecmd.base.speed) { case SPEED_10000: return 2; case SPEED_5000: return 3; case SPEED_2500: return 4; case SPEED_1000: return 5; case SPEED_100: return 19; case SPEED_10: return 100; case SPEED_UNKNOWN: return 100; default: if (ecmd.base.speed > SPEED_10000) return 1; } } /* Old silly heuristics based on name */ if (!strncmp(dev->name, "lec", 3)) return 7; if (!strncmp(dev->name, "plip", 4)) return 2500; return 100; /* assume old 10Mbps */ } /* Check for port carrier transitions. */ void br_port_carrier_check(struct net_bridge_port *p, bool *notified) { struct net_device *dev = p->dev; struct net_bridge *br = p->br; if (!(p->flags & BR_ADMIN_COST) && netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev); *notified = false; if (!netif_running(br->dev)) return; spin_lock_bh(&br->lock); if (netif_running(dev) && netif_oper_up(dev)) { if (p->state == BR_STATE_DISABLED) { br_stp_enable_port(p); *notified = true; } } else { if (p->state != BR_STATE_DISABLED) { br_stp_disable_port(p); *notified = true; } } spin_unlock_bh(&br->lock); } static void br_port_set_promisc(struct net_bridge_port *p) { int err = 0; if (br_promisc_port(p)) return; err = dev_set_promiscuity(p->dev, 1); if (err) return; br_fdb_unsync_static(p->br, p); p->flags |= BR_PROMISC; } static void br_port_clear_promisc(struct net_bridge_port *p) { int err; /* Check if the port is already non-promisc or if it doesn't * support UNICAST filtering. Without unicast filtering support * we'll end up re-enabling promisc mode anyway, so just check for * it here. */ if (!br_promisc_port(p) || !(p->dev->priv_flags & IFF_UNICAST_FLT)) return; /* Since we'll be clearing the promisc mode, program the port * first so that we don't have interruption in traffic. */ err = br_fdb_sync_static(p->br, p); if (err) return; dev_set_promiscuity(p->dev, -1); p->flags &= ~BR_PROMISC; } /* When a port is added or removed or when certain port flags * change, this function is called to automatically manage * promiscuity setting of all the bridge ports. We are always called * under RTNL so can skip using rcu primitives. */ void br_manage_promisc(struct net_bridge *br) { struct net_bridge_port *p; bool set_all = false; /* If vlan filtering is disabled or bridge interface is placed * into promiscuous mode, place all ports in promiscuous mode. */ if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br->dev)) set_all = true; list_for_each_entry(p, &br->port_list, list) { if (set_all) { br_port_set_promisc(p); } else { /* If the number of auto-ports is <= 1, then all other * ports will have their output configuration * statically specified through fdbs. Since ingress * on the auto-port becomes forwarding/egress to other * ports and egress configuration is statically known, * we can say that ingress configuration of the * auto-port is also statically known. * This lets us disable promiscuous mode and write * this config to hw. */ if ((p->dev->priv_flags & IFF_UNICAST_FLT) && (br->auto_cnt == 0 || (br->auto_cnt == 1 && br_auto_port(p)))) br_port_clear_promisc(p); else br_port_set_promisc(p); } } } int nbp_backup_change(struct net_bridge_port *p, struct net_device *backup_dev) { struct net_bridge_port *old_backup = rtnl_dereference(p->backup_port); struct net_bridge_port *backup_p = NULL; ASSERT_RTNL(); if (backup_dev) { if (!netif_is_bridge_port(backup_dev)) return -ENOENT; backup_p = br_port_get_rtnl(backup_dev); if (backup_p->br != p->br) return -EINVAL; } if (p == backup_p) return -EINVAL; if (old_backup == backup_p) return 0; /* if the backup link is already set, clear it */ if (old_backup) old_backup->backup_redirected_cnt--; if (backup_p) backup_p->backup_redirected_cnt++; rcu_assign_pointer(p->backup_port, backup_p); return 0; } static void nbp_backup_clear(struct net_bridge_port *p) { nbp_backup_change(p, NULL); if (p->backup_redirected_cnt) { struct net_bridge_port *cur_p; list_for_each_entry(cur_p, &p->br->port_list, list) { struct net_bridge_port *backup_p; backup_p = rtnl_dereference(cur_p->backup_port); if (backup_p == p) nbp_backup_change(cur_p, NULL); } } WARN_ON(rcu_access_pointer(p->backup_port) || p->backup_redirected_cnt); } static void nbp_update_port_count(struct net_bridge *br) { struct net_bridge_port *p; u32 cnt = 0; list_for_each_entry(p, &br->port_list, list) { if (br_auto_port(p)) cnt++; } if (br->auto_cnt != cnt) { br->auto_cnt = cnt; br_manage_promisc(br); } } static void nbp_delete_promisc(struct net_bridge_port *p) { /* If port is currently promiscuous, unset promiscuity. * Otherwise, it is a static port so remove all addresses * from it. */ dev_set_allmulti(p->dev, -1); if (br_promisc_port(p)) dev_set_promiscuity(p->dev, -1); else br_fdb_unsync_static(p->br, p); } static void release_nbp(struct kobject *kobj) { struct net_bridge_port *p = container_of(kobj, struct net_bridge_port, kobj); kfree(p); } static void brport_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { struct net_bridge_port *p = kobj_to_brport(kobj); net_ns_get_ownership(dev_net(p->dev), uid, gid); } static const struct kobj_type brport_ktype = { #ifdef CONFIG_SYSFS .sysfs_ops = &brport_sysfs_ops, #endif .release = release_nbp, .get_ownership = brport_get_ownership, }; static void destroy_nbp(struct net_bridge_port *p) { struct net_device *dev = p->dev; p->br = NULL; p->dev = NULL; netdev_put(dev, &p->dev_tracker); kobject_put(&p->kobj); } static void destroy_nbp_rcu(struct rcu_head *head) { struct net_bridge_port *p = container_of(head, struct net_bridge_port, rcu); destroy_nbp(p); } static unsigned get_max_headroom(struct net_bridge *br) { unsigned max_headroom = 0; struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { unsigned dev_headroom = netdev_get_fwd_headroom(p->dev); if (dev_headroom > max_headroom) max_headroom = dev_headroom; } return max_headroom; } static void update_headroom(struct net_bridge *br, int new_hr) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) netdev_set_rx_headroom(p->dev, new_hr); br->dev->needed_headroom = new_hr; } /* Delete port(interface) from bridge is done in two steps. * via RCU. First step, marks device as down. That deletes * all the timers and stops new packets from flowing through. * * Final cleanup doesn't occur until after all CPU's finished * processing packets. * * Protected from multiple admin operations by RTNL mutex */ static void del_nbp(struct net_bridge_port *p) { struct net_bridge *br = p->br; struct net_device *dev = p->dev; sysfs_remove_link(br->ifobj, p->dev->name); nbp_delete_promisc(p); spin_lock_bh(&br->lock); br_stp_disable_port(p); spin_unlock_bh(&br->lock); br_mrp_port_del(br, p); br_cfm_port_del(br, p); br_ifinfo_notify(RTM_DELLINK, NULL, p); list_del_rcu(&p->list); if (netdev_get_fwd_headroom(dev) == br->dev->needed_headroom) update_headroom(br, get_max_headroom(br)); netdev_reset_rx_headroom(dev); nbp_vlan_flush(p); br_fdb_delete_by_port(br, p, 0, 1); switchdev_deferred_process(); nbp_backup_clear(p); nbp_update_port_count(br); netdev_upper_dev_unlink(dev, br->dev); dev->priv_flags &= ~IFF_BRIDGE_PORT; netdev_rx_handler_unregister(dev); br_multicast_del_port(p); kobject_uevent(&p->kobj, KOBJ_REMOVE); kobject_del(&p->kobj); br_netpoll_disable(p); call_rcu(&p->rcu, destroy_nbp_rcu); } /* Delete bridge device */ void br_dev_delete(struct net_device *dev, struct list_head *head) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p, *n; list_for_each_entry_safe(p, n, &br->port_list, list) { del_nbp(p); } br_recalculate_neigh_suppress_enabled(br); br_fdb_delete_by_port(br, NULL, 0, 1); cancel_delayed_work_sync(&br->gc_work); br_sysfs_delbr(br->dev); unregister_netdevice_queue(br->dev, head); } /* find an available port number */ static int find_portno(struct net_bridge *br) { int index; struct net_bridge_port *p; unsigned long *inuse; inuse = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!inuse) return -ENOMEM; __set_bit(0, inuse); /* zero is reserved */ list_for_each_entry(p, &br->port_list, list) __set_bit(p->port_no, inuse); index = find_first_zero_bit(inuse, BR_MAX_PORTS); bitmap_free(inuse); return (index >= BR_MAX_PORTS) ? -EXFULL : index; } /* called with RTNL but without bridge lock */ static struct net_bridge_port *new_nbp(struct net_bridge *br, struct net_device *dev) { struct net_bridge_port *p; int index, err; index = find_portno(br); if (index < 0) return ERR_PTR(index); p = kzalloc(sizeof(*p), GFP_KERNEL); if (p == NULL) return ERR_PTR(-ENOMEM); p->br = br; netdev_hold(dev, &p->dev_tracker, GFP_KERNEL); p->dev = dev; p->path_cost = port_cost(dev); p->priority = 0x8000 >> BR_PORT_BITS; p->port_no = index; p->flags = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | BR_BCAST_FLOOD; br_init_port(p); br_set_state(p, BR_STATE_DISABLED); br_stp_port_timer_init(p); err = br_multicast_add_port(p); if (err) { netdev_put(dev, &p->dev_tracker); kfree(p); p = ERR_PTR(err); } return p; } int br_add_bridge(struct net *net, const char *name) { struct net_device *dev; int res; dev = alloc_netdev(sizeof(struct net_bridge), name, NET_NAME_UNKNOWN, br_dev_setup); if (!dev) return -ENOMEM; dev_net_set(dev, net); dev->rtnl_link_ops = &br_link_ops; res = register_netdevice(dev); if (res) free_netdev(dev); return res; } int br_del_bridge(struct net *net, const char *name) { struct net_device *dev; int ret = 0; dev = __dev_get_by_name(net, name); if (dev == NULL) ret = -ENXIO; /* Could not find device */ else if (!netif_is_bridge_master(dev)) { /* Attempt to delete non bridge device! */ ret = -EPERM; } else if (dev->flags & IFF_UP) { /* Not shutdown yet. */ ret = -EBUSY; } else br_dev_delete(dev, NULL); return ret; } /* MTU of the bridge pseudo-device: ETH_DATA_LEN or the minimum of the ports */ static int br_mtu_min(const struct net_bridge *br) { const struct net_bridge_port *p; int ret_mtu = 0; list_for_each_entry(p, &br->port_list, list) if (!ret_mtu || ret_mtu > p->dev->mtu) ret_mtu = p->dev->mtu; return ret_mtu ? ret_mtu : ETH_DATA_LEN; } void br_mtu_auto_adjust(struct net_bridge *br) { ASSERT_RTNL(); /* if the bridge MTU was manually configured don't mess with it */ if (br_opt_get(br, BROPT_MTU_SET_BY_USER)) return; /* change to the minimum MTU and clear the flag which was set by * the bridge ndo_change_mtu callback */ dev_set_mtu(br->dev, br_mtu_min(br)); br_opt_toggle(br, BROPT_MTU_SET_BY_USER, false); } static void br_set_gso_limits(struct net_bridge *br) { unsigned int tso_max_size = TSO_MAX_SIZE; const struct net_bridge_port *p; u16 tso_max_segs = TSO_MAX_SEGS; list_for_each_entry(p, &br->port_list, list) { tso_max_size = min(tso_max_size, p->dev->tso_max_size); tso_max_segs = min(tso_max_segs, p->dev->tso_max_segs); } netif_set_tso_max_size(br->dev, tso_max_size); netif_set_tso_max_segs(br->dev, tso_max_segs); } /* * Recomputes features using slave's features */ netdev_features_t br_features_recompute(struct net_bridge *br, netdev_features_t features) { struct net_bridge_port *p; netdev_features_t mask; if (list_empty(&br->port_list)) return features; mask = features; features &= ~NETIF_F_ONE_FOR_ALL; list_for_each_entry(p, &br->port_list, list) { features = netdev_increment_features(features, p->dev->features, mask); } features = netdev_add_tso_features(features, mask); return features; } /* called with RTNL */ int br_add_if(struct net_bridge *br, struct net_device *dev, struct netlink_ext_ack *extack) { struct net_bridge_port *p; int err = 0; unsigned br_hr, dev_hr; bool changed_addr, fdb_synced = false; /* Don't allow bridging non-ethernet like devices. */ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) return -EINVAL; /* No bridging of bridges */ if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) { NL_SET_ERR_MSG(extack, "Can not enslave a bridge to a bridge"); return -ELOOP; } /* Device has master upper dev */ if (netdev_master_upper_dev_get(dev)) return -EBUSY; /* No bridging devices that dislike that (e.g. wireless) */ if (dev->priv_flags & IFF_DONT_BRIDGE) { NL_SET_ERR_MSG(extack, "Device does not allow enslaving to a bridge"); return -EOPNOTSUPP; } p = new_nbp(br, dev); if (IS_ERR(p)) return PTR_ERR(p); call_netdevice_notifiers(NETDEV_JOIN, dev); err = dev_set_allmulti(dev, 1); if (err) { br_multicast_del_port(p); netdev_put(dev, &p->dev_tracker); kfree(p); /* kobject not yet init'd, manually free */ goto err1; } err = kobject_init_and_add(&p->kobj, &brport_ktype, &(dev->dev.kobj), SYSFS_BRIDGE_PORT_ATTR); if (err) goto err2; err = br_sysfs_addif(p); if (err) goto err2; err = br_netpoll_enable(p); if (err) goto err3; err = netdev_rx_handler_register(dev, br_get_rx_handler(dev), p); if (err) goto err4; dev->priv_flags |= IFF_BRIDGE_PORT; err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL, extack); if (err) goto err5; dev_disable_lro(dev); list_add_rcu(&p->list, &br->port_list); nbp_update_port_count(br); if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) { /* When updating the port count we also update all ports' * promiscuous mode. * A port leaving promiscuous mode normally gets the bridge's * fdb synced to the unicast filter (if supported), however, * `br_port_clear_promisc` does not distinguish between * non-promiscuous ports and *new* ports, so we need to * sync explicitly here. */ fdb_synced = br_fdb_sync_static(br, p) == 0; if (!fdb_synced) netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n"); } netdev_update_features(br->dev); br_hr = br->dev->needed_headroom; dev_hr = netdev_get_fwd_headroom(dev); if (br_hr < dev_hr) update_headroom(br, dev_hr); else netdev_set_rx_headroom(dev, br_hr); if (br_fdb_add_local(br, p, dev->dev_addr, 0)) netdev_err(dev, "failed insert local address bridge forwarding table\n"); if (br->dev->addr_assign_type != NET_ADDR_SET) { /* Ask for permission to use this MAC address now, even if we * don't end up choosing it below. */ err = dev_pre_changeaddr_notify(br->dev, dev->dev_addr, extack); if (err) goto err6; } err = nbp_vlan_init(p, extack); if (err) { netdev_err(dev, "failed to initialize vlan filtering on this port\n"); goto err6; } spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); if (netif_running(dev) && netif_oper_up(dev) && (br->dev->flags & IFF_UP)) br_stp_enable_port(p); spin_unlock_bh(&br->lock); br_ifinfo_notify(RTM_NEWLINK, NULL, p); if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); br_mtu_auto_adjust(br); br_set_gso_limits(br); kobject_uevent(&p->kobj, KOBJ_ADD); return 0; err6: if (fdb_synced) br_fdb_unsync_static(br, p); list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); netdev_upper_dev_unlink(dev, br->dev); err5: dev->priv_flags &= ~IFF_BRIDGE_PORT; netdev_rx_handler_unregister(dev); err4: br_netpoll_disable(p); err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: br_multicast_del_port(p); netdev_put(dev, &p->dev_tracker); kobject_put(&p->kobj); dev_set_allmulti(dev, -1); err1: return err; } /* called with RTNL */ int br_del_if(struct net_bridge *br, struct net_device *dev) { struct net_bridge_port *p; bool changed_addr; p = br_port_get_rtnl(dev); if (!p || p->br != br) return -EINVAL; /* Since more than one interface can be attached to a bridge, * there still maybe an alternate path for netconsole to use; * therefore there is no reason for a NETDEV_RELEASE event. */ del_nbp(p); br_mtu_auto_adjust(br); br_set_gso_limits(br); spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); netdev_update_features(br->dev); return 0; } void br_port_flags_change(struct net_bridge_port *p, unsigned long mask) { struct net_bridge *br = p->br; if (mask & BR_AUTO_MASK) nbp_update_port_count(br); if (mask & (BR_NEIGH_SUPPRESS | BR_NEIGH_VLAN_SUPPRESS)) br_recalculate_neigh_suppress_enabled(br); } bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag) { struct net_bridge_port *p; p = br_port_get_rtnl_rcu(dev); if (!p) return false; return p->flags & flag; } EXPORT_SYMBOL_GPL(br_port_flag_is_set); |
| 561 91 173 173 81 91 94 94 94 94 94 93 94 94 94 94 94 561 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2002 International Business Machines, Corp. * * This file is part of the SCTP kernel implementation * * These functions are the methods for accessing the SCTP inqueue. * * An SCTP inqueue is a queue into which you push SCTP packets * (which might be bundles or fragments of chunks) and out of which you * pop SCTP whole chunks. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <linux/interrupt.h> #include <linux/slab.h> /* Initialize an SCTP inqueue. */ void sctp_inq_init(struct sctp_inq *queue) { INIT_LIST_HEAD(&queue->in_chunk_list); queue->in_progress = NULL; /* Create a task for delivering data. */ INIT_WORK(&queue->immediate, NULL); } /* Properly release the chunk which is being worked on. */ static inline void sctp_inq_chunk_free(struct sctp_chunk *chunk) { if (chunk->head_skb) chunk->skb = chunk->head_skb; sctp_chunk_free(chunk); } /* Release the memory associated with an SCTP inqueue. */ void sctp_inq_free(struct sctp_inq *queue) { struct sctp_chunk *chunk, *tmp; /* Empty the queue. */ list_for_each_entry_safe(chunk, tmp, &queue->in_chunk_list, list) { list_del_init(&chunk->list); sctp_chunk_free(chunk); } /* If there is a packet which is currently being worked on, * free it as well. */ if (queue->in_progress) { sctp_inq_chunk_free(queue->in_progress); queue->in_progress = NULL; } } /* Put a new packet in an SCTP inqueue. * We assume that packet->sctp_hdr is set and in host byte order. */ void sctp_inq_push(struct sctp_inq *q, struct sctp_chunk *chunk) { /* Directly call the packet handling routine. */ if (chunk->rcvr->dead) { sctp_chunk_free(chunk); return; } /* We are now calling this either from the soft interrupt * or from the backlog processing. * Eventually, we should clean up inqueue to not rely * on the BH related data structures. */ list_add_tail(&chunk->list, &q->in_chunk_list); if (chunk->asoc) chunk->asoc->stats.ipackets++; q->immediate.func(&q->immediate); } /* Peek at the next chunk on the inqeue. */ struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *queue) { struct sctp_chunk *chunk; struct sctp_chunkhdr *ch = NULL; chunk = queue->in_progress; /* If there is no more chunks in this packet, say so */ if (chunk->singleton || chunk->end_of_packet || chunk->pdiscard) return NULL; ch = (struct sctp_chunkhdr *)chunk->chunk_end; return ch; } /* Extract a chunk from an SCTP inqueue. * * WARNING: If you need to put the chunk on another queue, you need to * make a shallow copy (clone) of it. */ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) { struct sctp_chunk *chunk; struct sctp_chunkhdr *ch = NULL; /* The assumption is that we are safe to process the chunks * at this time. */ chunk = queue->in_progress; if (chunk) { /* There is a packet that we have been working on. * Any post processing work to do before we move on? */ if (chunk->singleton || chunk->end_of_packet || chunk->pdiscard) { if (chunk->head_skb == chunk->skb) { chunk->skb = skb_shinfo(chunk->skb)->frag_list; goto new_skb; } if (chunk->skb->next) { chunk->skb = chunk->skb->next; goto new_skb; } sctp_inq_chunk_free(chunk); chunk = queue->in_progress = NULL; } else { /* Nothing to do. Next chunk in the packet, please. */ ch = (struct sctp_chunkhdr *)chunk->chunk_end; /* Force chunk->skb->data to chunk->chunk_end. */ skb_pull(chunk->skb, chunk->chunk_end - chunk->skb->data); /* We are guaranteed to pull a SCTP header. */ } } /* Do we need to take the next packet out of the queue to process? */ if (!chunk) { struct list_head *entry; next_chunk: /* Is the queue empty? */ entry = sctp_list_dequeue(&queue->in_chunk_list); if (!entry) return NULL; chunk = list_entry(entry, struct sctp_chunk, list); if (skb_is_gso(chunk->skb) && skb_is_gso_sctp(chunk->skb)) { /* GSO-marked skbs but without frags, handle * them normally */ if (skb_shinfo(chunk->skb)->frag_list) chunk->head_skb = chunk->skb; /* skbs with "cover letter" */ if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) chunk->skb = skb_shinfo(chunk->skb)->frag_list; if (WARN_ON(!chunk->skb)) { __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); sctp_chunk_free(chunk); goto next_chunk; } } if (chunk->asoc) sock_rps_save_rxhash(chunk->asoc->base.sk, chunk->skb); queue->in_progress = chunk; new_skb: /* This is the first chunk in the packet. */ ch = (struct sctp_chunkhdr *)chunk->skb->data; chunk->singleton = 1; chunk->data_accepted = 0; chunk->pdiscard = 0; chunk->auth = 0; chunk->has_asconf = 0; chunk->end_of_packet = 0; if (chunk->head_skb) { struct sctp_input_cb *cb = SCTP_INPUT_CB(chunk->skb), *head_cb = SCTP_INPUT_CB(chunk->head_skb); cb->chunk = head_cb->chunk; cb->af = head_cb->af; } } chunk->chunk_hdr = ch; chunk->chunk_end = ((__u8 *)ch) + SCTP_PAD4(ntohs(ch->length)); skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { /* Discard inside state machine. */ chunk->pdiscard = 1; chunk->chunk_end = skb_tail_pointer(chunk->skb); } else { /* We are at the end of the packet, so mark the chunk * in case we need to send a SACK. */ chunk->end_of_packet = 1; } pr_debug("+++sctp_inq_pop+++ chunk:%p[%s], length:%d, skb->len:%d\n", chunk, sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)), ntohs(chunk->chunk_hdr->length), chunk->skb->len); return chunk; } /* Set a top-half handler. * * Originally, we the top-half handler was scheduled as a BH. We now * call the handler directly in sctp_inq_push() at a time that * we know we are lock safe. * The intent is that this routine will pull stuff out of the * inqueue and process it. */ void sctp_inq_set_th_handler(struct sctp_inq *q, work_func_t callback) { INIT_WORK(&q->immediate, callback); } |
| 1666 7 9 14 3 2 2 7 1 1 1 1 3 3 1665 1666 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 | // SPDX-License-Identifier: GPL-2.0 /* * Encryption policy functions for per-file encryption support. * * Copyright (C) 2015, Google, Inc. * Copyright (C) 2015, Motorola Mobility. * * Originally written by Michael Halcrow, 2015. * Modified by Jaegeuk Kim, 2015. * Modified by Eric Biggers, 2019 for v2 policy support. */ #include <linux/fs_context.h> #include <linux/random.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/mount.h> #include "fscrypt_private.h" /** * fscrypt_policies_equal() - check whether two encryption policies are the same * @policy1: the first policy * @policy2: the second policy * * Return: %true if equal, else %false */ bool fscrypt_policies_equal(const union fscrypt_policy *policy1, const union fscrypt_policy *policy2) { if (policy1->version != policy2->version) return false; return !memcmp(policy1, policy2, fscrypt_policy_size(policy1)); } int fscrypt_policy_to_key_spec(const union fscrypt_policy *policy, struct fscrypt_key_specifier *key_spec) { switch (policy->version) { case FSCRYPT_POLICY_V1: key_spec->type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR; memcpy(key_spec->u.descriptor, policy->v1.master_key_descriptor, FSCRYPT_KEY_DESCRIPTOR_SIZE); return 0; case FSCRYPT_POLICY_V2: key_spec->type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; memcpy(key_spec->u.identifier, policy->v2.master_key_identifier, FSCRYPT_KEY_IDENTIFIER_SIZE); return 0; default: WARN_ON_ONCE(1); return -EINVAL; } } const union fscrypt_policy *fscrypt_get_dummy_policy(struct super_block *sb) { if (!sb->s_cop->get_dummy_policy) return NULL; return sb->s_cop->get_dummy_policy(sb); } /* * Return %true if the given combination of encryption modes is supported for v1 * (and later) encryption policies. * * Do *not* add anything new here, since v1 encryption policies are deprecated. * New combinations of modes should go in fscrypt_valid_enc_modes_v2() only. */ static bool fscrypt_valid_enc_modes_v1(u32 contents_mode, u32 filenames_mode) { if (contents_mode == FSCRYPT_MODE_AES_256_XTS && filenames_mode == FSCRYPT_MODE_AES_256_CTS) return true; if (contents_mode == FSCRYPT_MODE_AES_128_CBC && filenames_mode == FSCRYPT_MODE_AES_128_CTS) return true; if (contents_mode == FSCRYPT_MODE_ADIANTUM && filenames_mode == FSCRYPT_MODE_ADIANTUM) return true; return false; } static bool fscrypt_valid_enc_modes_v2(u32 contents_mode, u32 filenames_mode) { if (contents_mode == FSCRYPT_MODE_AES_256_XTS && filenames_mode == FSCRYPT_MODE_AES_256_HCTR2) return true; if (contents_mode == FSCRYPT_MODE_SM4_XTS && filenames_mode == FSCRYPT_MODE_SM4_CTS) return true; return fscrypt_valid_enc_modes_v1(contents_mode, filenames_mode); } static bool supported_direct_key_modes(const struct inode *inode, u32 contents_mode, u32 filenames_mode) { const struct fscrypt_mode *mode; if (contents_mode != filenames_mode) { fscrypt_warn(inode, "Direct key flag not allowed with different contents and filenames modes"); return false; } mode = &fscrypt_modes[contents_mode]; if (mode->ivsize < offsetofend(union fscrypt_iv, nonce)) { fscrypt_warn(inode, "Direct key flag not allowed with %s", mode->friendly_name); return false; } return true; } static bool supported_iv_ino_lblk_policy(const struct fscrypt_policy_v2 *policy, const struct inode *inode) { const char *type = (policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) ? "IV_INO_LBLK_64" : "IV_INO_LBLK_32"; struct super_block *sb = inode->i_sb; /* * IV_INO_LBLK_* exist only because of hardware limitations, and * currently the only known use case for them involves AES-256-XTS. * That's also all we test currently. For these reasons, for now only * allow AES-256-XTS here. This can be relaxed later if a use case for * IV_INO_LBLK_* with other encryption modes arises. */ if (policy->contents_encryption_mode != FSCRYPT_MODE_AES_256_XTS) { fscrypt_warn(inode, "Can't use %s policy with contents mode other than AES-256-XTS", type); return false; } /* * It's unsafe to include inode numbers in the IVs if the filesystem can * potentially renumber inodes, e.g. via filesystem shrinking. */ if (!sb->s_cop->has_stable_inodes || !sb->s_cop->has_stable_inodes(sb)) { fscrypt_warn(inode, "Can't use %s policy on filesystem '%s' because it doesn't have stable inode numbers", type, sb->s_id); return false; } /* * IV_INO_LBLK_64 and IV_INO_LBLK_32 both require that inode numbers fit * in 32 bits. In principle, IV_INO_LBLK_32 could support longer inode * numbers because it hashes the inode number; however, currently the * inode number is gotten from inode::i_ino which is 'unsigned long'. * So for now the implementation limit is 32 bits. */ if (!sb->s_cop->has_32bit_inodes) { fscrypt_warn(inode, "Can't use %s policy on filesystem '%s' because its inode numbers are too long", type, sb->s_id); return false; } /* * IV_INO_LBLK_64 and IV_INO_LBLK_32 both require that file data unit * indices fit in 32 bits. */ if (fscrypt_max_file_dun_bits(sb, fscrypt_policy_v2_du_bits(policy, inode)) > 32) { fscrypt_warn(inode, "Can't use %s policy on filesystem '%s' because its maximum file size is too large", type, sb->s_id); return false; } return true; } static bool fscrypt_supported_v1_policy(const struct fscrypt_policy_v1 *policy, const struct inode *inode) { if (!fscrypt_valid_enc_modes_v1(policy->contents_encryption_mode, policy->filenames_encryption_mode)) { fscrypt_warn(inode, "Unsupported encryption modes (contents %d, filenames %d)", policy->contents_encryption_mode, policy->filenames_encryption_mode); return false; } if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK | FSCRYPT_POLICY_FLAG_DIRECT_KEY)) { fscrypt_warn(inode, "Unsupported encryption flags (0x%02x)", policy->flags); return false; } if ((policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) && !supported_direct_key_modes(inode, policy->contents_encryption_mode, policy->filenames_encryption_mode)) return false; if (IS_CASEFOLDED(inode)) { /* With v1, there's no way to derive dirhash keys. */ fscrypt_warn(inode, "v1 policies can't be used on casefolded directories"); return false; } return true; } static bool fscrypt_supported_v2_policy(const struct fscrypt_policy_v2 *policy, const struct inode *inode) { int count = 0; if (!fscrypt_valid_enc_modes_v2(policy->contents_encryption_mode, policy->filenames_encryption_mode)) { fscrypt_warn(inode, "Unsupported encryption modes (contents %d, filenames %d)", policy->contents_encryption_mode, policy->filenames_encryption_mode); return false; } if (policy->flags & ~(FSCRYPT_POLICY_FLAGS_PAD_MASK | FSCRYPT_POLICY_FLAG_DIRECT_KEY | FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 | FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) { fscrypt_warn(inode, "Unsupported encryption flags (0x%02x)", policy->flags); return false; } count += !!(policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY); count += !!(policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64); count += !!(policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32); if (count > 1) { fscrypt_warn(inode, "Mutually exclusive encryption flags (0x%02x)", policy->flags); return false; } if (policy->log2_data_unit_size) { if (!inode->i_sb->s_cop->supports_subblock_data_units) { fscrypt_warn(inode, "Filesystem does not support configuring crypto data unit size"); return false; } if (policy->log2_data_unit_size > inode->i_blkbits || policy->log2_data_unit_size < SECTOR_SHIFT /* 9 */) { fscrypt_warn(inode, "Unsupported log2_data_unit_size in encryption policy: %d", policy->log2_data_unit_size); return false; } if (policy->log2_data_unit_size != inode->i_blkbits && (policy->flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) { /* * Not safe to enable yet, as we need to ensure that DUN * wraparound can only occur on a FS block boundary. */ fscrypt_warn(inode, "Sub-block data units not yet supported with IV_INO_LBLK_32"); return false; } } if ((policy->flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) && !supported_direct_key_modes(inode, policy->contents_encryption_mode, policy->filenames_encryption_mode)) return false; if ((policy->flags & (FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 | FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) && !supported_iv_ino_lblk_policy(policy, inode)) return false; if (memchr_inv(policy->__reserved, 0, sizeof(policy->__reserved))) { fscrypt_warn(inode, "Reserved bits set in encryption policy"); return false; } return true; } /** * fscrypt_supported_policy() - check whether an encryption policy is supported * @policy_u: the encryption policy * @inode: the inode on which the policy will be used * * Given an encryption policy, check whether all its encryption modes and other * settings are supported by this kernel on the given inode. (But we don't * currently don't check for crypto API support here, so attempting to use an * algorithm not configured into the crypto API will still fail later.) * * Return: %true if supported, else %false */ bool fscrypt_supported_policy(const union fscrypt_policy *policy_u, const struct inode *inode) { switch (policy_u->version) { case FSCRYPT_POLICY_V1: return fscrypt_supported_v1_policy(&policy_u->v1, inode); case FSCRYPT_POLICY_V2: return fscrypt_supported_v2_policy(&policy_u->v2, inode); } return false; } /** * fscrypt_new_context() - create a new fscrypt_context * @ctx_u: output context * @policy_u: input policy * @nonce: nonce to use * * Create an fscrypt_context for an inode that is being assigned the given * encryption policy. @nonce must be a new random nonce. * * Return: the size of the new context in bytes. */ static int fscrypt_new_context(union fscrypt_context *ctx_u, const union fscrypt_policy *policy_u, const u8 nonce[FSCRYPT_FILE_NONCE_SIZE]) { memset(ctx_u, 0, sizeof(*ctx_u)); switch (policy_u->version) { case FSCRYPT_POLICY_V1: { const struct fscrypt_policy_v1 *policy = &policy_u->v1; struct fscrypt_context_v1 *ctx = &ctx_u->v1; ctx->version = FSCRYPT_CONTEXT_V1; ctx->contents_encryption_mode = policy->contents_encryption_mode; ctx->filenames_encryption_mode = policy->filenames_encryption_mode; ctx->flags = policy->flags; memcpy(ctx->master_key_descriptor, policy->master_key_descriptor, sizeof(ctx->master_key_descriptor)); memcpy(ctx->nonce, nonce, FSCRYPT_FILE_NONCE_SIZE); return sizeof(*ctx); } case FSCRYPT_POLICY_V2: { const struct fscrypt_policy_v2 *policy = &policy_u->v2; struct fscrypt_context_v2 *ctx = &ctx_u->v2; ctx->version = FSCRYPT_CONTEXT_V2; ctx->contents_encryption_mode = policy->contents_encryption_mode; ctx->filenames_encryption_mode = policy->filenames_encryption_mode; ctx->flags = policy->flags; ctx->log2_data_unit_size = policy->log2_data_unit_size; memcpy(ctx->master_key_identifier, policy->master_key_identifier, sizeof(ctx->master_key_identifier)); memcpy(ctx->nonce, nonce, FSCRYPT_FILE_NONCE_SIZE); return sizeof(*ctx); } } BUG(); } /** * fscrypt_policy_from_context() - convert an fscrypt_context to * an fscrypt_policy * @policy_u: output policy * @ctx_u: input context * @ctx_size: size of input context in bytes * * Given an fscrypt_context, build the corresponding fscrypt_policy. * * Return: 0 on success, or -EINVAL if the fscrypt_context has an unrecognized * version number or size. * * This does *not* validate the settings within the policy itself, e.g. the * modes, flags, and reserved bits. Use fscrypt_supported_policy() for that. */ int fscrypt_policy_from_context(union fscrypt_policy *policy_u, const union fscrypt_context *ctx_u, int ctx_size) { memset(policy_u, 0, sizeof(*policy_u)); if (!fscrypt_context_is_valid(ctx_u, ctx_size)) return -EINVAL; switch (ctx_u->version) { case FSCRYPT_CONTEXT_V1: { const struct fscrypt_context_v1 *ctx = &ctx_u->v1; struct fscrypt_policy_v1 *policy = &policy_u->v1; policy->version = FSCRYPT_POLICY_V1; policy->contents_encryption_mode = ctx->contents_encryption_mode; policy->filenames_encryption_mode = ctx->filenames_encryption_mode; policy->flags = ctx->flags; memcpy(policy->master_key_descriptor, ctx->master_key_descriptor, sizeof(policy->master_key_descriptor)); return 0; } case FSCRYPT_CONTEXT_V2: { const struct fscrypt_context_v2 *ctx = &ctx_u->v2; struct fscrypt_policy_v2 *policy = &policy_u->v2; policy->version = FSCRYPT_POLICY_V2; policy->contents_encryption_mode = ctx->contents_encryption_mode; policy->filenames_encryption_mode = ctx->filenames_encryption_mode; policy->flags = ctx->flags; policy->log2_data_unit_size = ctx->log2_data_unit_size; memcpy(policy->__reserved, ctx->__reserved, sizeof(policy->__reserved)); memcpy(policy->master_key_identifier, ctx->master_key_identifier, sizeof(policy->master_key_identifier)); return 0; } } /* unreachable */ return -EINVAL; } /* Retrieve an inode's encryption policy */ static int fscrypt_get_policy(struct inode *inode, union fscrypt_policy *policy) { const struct fscrypt_inode_info *ci; union fscrypt_context ctx; int ret; ci = fscrypt_get_inode_info(inode); if (ci) { /* key available, use the cached policy */ *policy = ci->ci_policy; return 0; } if (!IS_ENCRYPTED(inode)) return -ENODATA; ret = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); if (ret < 0) return (ret == -ERANGE) ? -EINVAL : ret; return fscrypt_policy_from_context(policy, &ctx, ret); } static int set_encryption_policy(struct inode *inode, const union fscrypt_policy *policy) { u8 nonce[FSCRYPT_FILE_NONCE_SIZE]; union fscrypt_context ctx; int ctxsize; int err; if (!fscrypt_supported_policy(policy, inode)) return -EINVAL; switch (policy->version) { case FSCRYPT_POLICY_V1: /* * The original encryption policy version provided no way of * verifying that the correct master key was supplied, which was * insecure in scenarios where multiple users have access to the * same encrypted files (even just read-only access). The new * encryption policy version fixes this and also implies use of * an improved key derivation function and allows non-root users * to securely remove keys. So as long as compatibility with * old kernels isn't required, it is recommended to use the new * policy version for all new encrypted directories. */ pr_warn_once("%s (pid %d) is setting deprecated v1 encryption policy; recommend upgrading to v2.\n", current->comm, current->pid); break; case FSCRYPT_POLICY_V2: err = fscrypt_verify_key_added(inode->i_sb, policy->v2.master_key_identifier); if (err) return err; if (policy->v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) pr_warn_once("%s (pid %d) is setting an IV_INO_LBLK_32 encryption policy. This should only be used if there are certain hardware limitations.\n", current->comm, current->pid); break; default: WARN_ON_ONCE(1); return -EINVAL; } get_random_bytes(nonce, FSCRYPT_FILE_NONCE_SIZE); ctxsize = fscrypt_new_context(&ctx, policy, nonce); return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, NULL); } int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg) { union fscrypt_policy policy; union fscrypt_policy existing_policy; struct inode *inode = file_inode(filp); u8 version; int size; int ret; if (get_user(policy.version, (const u8 __user *)arg)) return -EFAULT; size = fscrypt_policy_size(&policy); if (size <= 0) return -EINVAL; /* * We should just copy the remaining 'size - 1' bytes here, but a * bizarre bug in gcc 7 and earlier (fixed by gcc r255731) causes gcc to * think that size can be 0 here (despite the check above!) *and* that * it's a compile-time constant. Thus it would think copy_from_user() * is passed compile-time constant ULONG_MAX, causing the compile-time * buffer overflow check to fail, breaking the build. This only occurred * when building an i386 kernel with -Os and branch profiling enabled. * * Work around it by just copying the first byte again... */ version = policy.version; if (copy_from_user(&policy, arg, size)) return -EFAULT; policy.version = version; if (!inode_owner_or_capable(&nop_mnt_idmap, inode)) return -EACCES; ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); ret = fscrypt_get_policy(inode, &existing_policy); if (ret == -ENODATA) { if (!S_ISDIR(inode->i_mode)) ret = -ENOTDIR; else if (IS_DEADDIR(inode)) ret = -ENOENT; else if (!inode->i_sb->s_cop->empty_dir(inode)) ret = -ENOTEMPTY; else ret = set_encryption_policy(inode, &policy); } else if (ret == -EINVAL || (ret == 0 && !fscrypt_policies_equal(&policy, &existing_policy))) { /* The file already uses a different encryption policy. */ ret = -EEXIST; } inode_unlock(inode); mnt_drop_write_file(filp); return ret; } EXPORT_SYMBOL(fscrypt_ioctl_set_policy); /* Original ioctl version; can only get the original policy version */ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg) { union fscrypt_policy policy; int err; err = fscrypt_get_policy(file_inode(filp), &policy); if (err) return err; if (policy.version != FSCRYPT_POLICY_V1) return -EINVAL; if (copy_to_user(arg, &policy, sizeof(policy.v1))) return -EFAULT; return 0; } EXPORT_SYMBOL(fscrypt_ioctl_get_policy); /* Extended ioctl version; can get policies of any version */ int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *uarg) { struct fscrypt_get_policy_ex_arg arg; union fscrypt_policy *policy = (union fscrypt_policy *)&arg.policy; size_t policy_size; int err; /* arg is policy_size, then policy */ BUILD_BUG_ON(offsetof(typeof(arg), policy_size) != 0); BUILD_BUG_ON(offsetofend(typeof(arg), policy_size) != offsetof(typeof(arg), policy)); BUILD_BUG_ON(sizeof(arg.policy) != sizeof(*policy)); err = fscrypt_get_policy(file_inode(filp), policy); if (err) return err; policy_size = fscrypt_policy_size(policy); if (copy_from_user(&arg, uarg, sizeof(arg.policy_size))) return -EFAULT; if (policy_size > arg.policy_size) return -EOVERFLOW; arg.policy_size = policy_size; if (copy_to_user(uarg, &arg, sizeof(arg.policy_size) + policy_size)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(fscrypt_ioctl_get_policy_ex); /* FS_IOC_GET_ENCRYPTION_NONCE: retrieve file's encryption nonce for testing */ int fscrypt_ioctl_get_nonce(struct file *filp, void __user *arg) { struct inode *inode = file_inode(filp); union fscrypt_context ctx; int ret; ret = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); if (ret < 0) return ret; if (!fscrypt_context_is_valid(&ctx, ret)) return -EINVAL; if (copy_to_user(arg, fscrypt_context_nonce(&ctx), FSCRYPT_FILE_NONCE_SIZE)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(fscrypt_ioctl_get_nonce); /** * fscrypt_has_permitted_context() - is a file's encryption policy permitted * within its directory? * * @parent: inode for parent directory * @child: inode for file being looked up, opened, or linked into @parent * * Filesystems must call this before permitting access to an inode in a * situation where the parent directory is encrypted (either before allowing * ->lookup() to succeed, or for a regular file before allowing it to be opened) * and before any operation that involves linking an inode into an encrypted * directory, including link, rename, and cross rename. It enforces the * constraint that within a given encrypted directory tree, all files use the * same encryption policy. The pre-access check is needed to detect potentially * malicious offline violations of this constraint, while the link and rename * checks are needed to prevent online violations of this constraint. * * Return: 1 if permitted, 0 if forbidden. */ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) { union fscrypt_policy parent_policy, child_policy; int err, err1, err2; /* No restrictions on file types which are never encrypted */ if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) && !S_ISLNK(child->i_mode)) return 1; /* No restrictions if the parent directory is unencrypted */ if (!IS_ENCRYPTED(parent)) return 1; /* Encrypted directories must not contain unencrypted files */ if (!IS_ENCRYPTED(child)) return 0; /* * Both parent and child are encrypted, so verify they use the same * encryption policy. Compare the cached policies if the keys are * available, otherwise retrieve and compare the fscrypt_contexts. * * Note that the fscrypt_context retrieval will be required frequently * when accessing an encrypted directory tree without the key. * Performance-wise this is not a big deal because we already don't * really optimize for file access without the key (to the extent that * such access is even possible), given that any attempted access * already causes a fscrypt_context retrieval and keyring search. * * In any case, if an unexpected error occurs, fall back to "forbidden". */ err = fscrypt_get_encryption_info(parent, true); if (err) return 0; err = fscrypt_get_encryption_info(child, true); if (err) return 0; err1 = fscrypt_get_policy(parent, &parent_policy); err2 = fscrypt_get_policy(child, &child_policy); /* * Allow the case where the parent and child both have an unrecognized * encryption policy, so that files with an unrecognized encryption * policy can be deleted. */ if (err1 == -EINVAL && err2 == -EINVAL) return 1; if (err1 || err2) return 0; return fscrypt_policies_equal(&parent_policy, &child_policy); } EXPORT_SYMBOL(fscrypt_has_permitted_context); /* * Return the encryption policy that new files in the directory will inherit, or * NULL if none, or an ERR_PTR() on error. If the directory is encrypted, also * ensure that its key is set up, so that the new filename can be encrypted. */ const union fscrypt_policy *fscrypt_policy_to_inherit(struct inode *dir) { int err; if (IS_ENCRYPTED(dir)) { err = fscrypt_require_key(dir); if (err) return ERR_PTR(err); return &dir->i_crypt_info->ci_policy; } return fscrypt_get_dummy_policy(dir->i_sb); } /** * fscrypt_context_for_new_inode() - create an encryption context for a new inode * @ctx: where context should be written * @inode: inode from which to fetch policy and nonce * * Given an in-core "prepared" (via fscrypt_prepare_new_inode) inode, * generate a new context and write it to ctx. ctx _must_ be at least * FSCRYPT_SET_CONTEXT_MAX_SIZE bytes. * * Return: size of the resulting context or a negative error code. */ int fscrypt_context_for_new_inode(void *ctx, struct inode *inode) { struct fscrypt_inode_info *ci = inode->i_crypt_info; BUILD_BUG_ON(sizeof(union fscrypt_context) != FSCRYPT_SET_CONTEXT_MAX_SIZE); /* fscrypt_prepare_new_inode() should have set up the key already. */ if (WARN_ON_ONCE(!ci)) return -ENOKEY; return fscrypt_new_context(ctx, &ci->ci_policy, ci->ci_nonce); } EXPORT_SYMBOL_GPL(fscrypt_context_for_new_inode); /** * fscrypt_set_context() - Set the fscrypt context of a new inode * @inode: a new inode * @fs_data: private data given by FS and passed to ->set_context() * * This should be called after fscrypt_prepare_new_inode(), generally during a * filesystem transaction. Everything here must be %GFP_NOFS-safe. * * Return: 0 on success, -errno on failure */ int fscrypt_set_context(struct inode *inode, void *fs_data) { struct fscrypt_inode_info *ci = inode->i_crypt_info; union fscrypt_context ctx; int ctxsize; ctxsize = fscrypt_context_for_new_inode(&ctx, inode); if (ctxsize < 0) return ctxsize; /* * This may be the first time the inode number is available, so do any * delayed key setup that requires the inode number. */ if (ci->ci_policy.version == FSCRYPT_POLICY_V2 && (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) fscrypt_hash_inode_number(ci, ci->ci_master_key); return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, fs_data); } EXPORT_SYMBOL_GPL(fscrypt_set_context); /** * fscrypt_parse_test_dummy_encryption() - parse the test_dummy_encryption mount option * @param: the mount option * @dummy_policy: (input/output) the place to write the dummy policy that will * result from parsing the option. Zero-initialize this. If a policy is * already set here (due to test_dummy_encryption being given multiple * times), then this function will verify that the policies are the same. * * Return: 0 on success; -EINVAL if the argument is invalid; -EEXIST if the * argument conflicts with one already specified; or -ENOMEM. */ int fscrypt_parse_test_dummy_encryption(const struct fs_parameter *param, struct fscrypt_dummy_policy *dummy_policy) { const char *arg = "v2"; union fscrypt_policy *policy; int err; if (param->type == fs_value_is_string && *param->string) arg = param->string; policy = kzalloc(sizeof(*policy), GFP_KERNEL); if (!policy) return -ENOMEM; if (!strcmp(arg, "v1")) { policy->version = FSCRYPT_POLICY_V1; policy->v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS; policy->v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS; memset(policy->v1.master_key_descriptor, 0x42, FSCRYPT_KEY_DESCRIPTOR_SIZE); } else if (!strcmp(arg, "v2")) { policy->version = FSCRYPT_POLICY_V2; policy->v2.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS; policy->v2.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS; err = fscrypt_get_test_dummy_key_identifier( policy->v2.master_key_identifier); if (err) goto out; } else { err = -EINVAL; goto out; } if (dummy_policy->policy) { if (fscrypt_policies_equal(policy, dummy_policy->policy)) err = 0; else err = -EEXIST; goto out; } dummy_policy->policy = policy; policy = NULL; err = 0; out: kfree(policy); return err; } EXPORT_SYMBOL_GPL(fscrypt_parse_test_dummy_encryption); /** * fscrypt_dummy_policies_equal() - check whether two dummy policies are equal * @p1: the first test dummy policy (may be unset) * @p2: the second test dummy policy (may be unset) * * Return: %true if the dummy policies are both set and equal, or both unset. */ bool fscrypt_dummy_policies_equal(const struct fscrypt_dummy_policy *p1, const struct fscrypt_dummy_policy *p2) { if (!p1->policy && !p2->policy) return true; if (!p1->policy || !p2->policy) return false; return fscrypt_policies_equal(p1->policy, p2->policy); } EXPORT_SYMBOL_GPL(fscrypt_dummy_policies_equal); /** * fscrypt_show_test_dummy_encryption() - show '-o test_dummy_encryption' * @seq: the seq_file to print the option to * @sep: the separator character to use * @sb: the filesystem whose options are being shown * * Show the test_dummy_encryption mount option, if it was specified. * This is mainly used for /proc/mounts. */ void fscrypt_show_test_dummy_encryption(struct seq_file *seq, char sep, struct super_block *sb) { const union fscrypt_policy *policy = fscrypt_get_dummy_policy(sb); int vers; if (!policy) return; vers = policy->version; if (vers == FSCRYPT_POLICY_V1) /* Handle numbering quirk */ vers = 1; seq_printf(seq, "%ctest_dummy_encryption=v%d", sep, vers); } EXPORT_SYMBOL_GPL(fscrypt_show_test_dummy_encryption); |
| 66 41 20 13 17 12 13 13 6 15 23 1 23 2 13 20 21 31 31 34 1 5 2 31 31 17 18 13 3 18 9 26 2 24 22 10 12 4 8 1 8 4 11 1 2 1 1 6 2 2 39 39 5 18 18 25 18 11 7 10 10 10 10 33 13 33 12 33 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Longest prefix match list implementation * * Copyright (c) 2016,2017 Daniel Mack * Copyright (c) 2016 David Herrmann */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <net/ipv6.h> #include <uapi/linux/btf.h> #include <linux/btf_ids.h> /* Intermediate node */ #define LPM_TREE_NODE_FLAG_IM BIT(0) struct lpm_trie_node; struct lpm_trie_node { struct rcu_head rcu; struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; u8 data[]; }; struct lpm_trie { struct bpf_map map; struct lpm_trie_node __rcu *root; size_t n_entries; size_t max_prefixlen; size_t data_size; spinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to * match IP addresses to a stored set of ranges. * * Data stored in @data of struct bpf_lpm_key and struct lpm_trie_node is * interpreted as big endian, so data[0] stores the most significant byte. * * Match ranges are internally stored in instances of struct lpm_trie_node * which each contain their prefix length as well as two pointers that may * lead to more nodes containing more specific matches. Each node also stores * a value that is defined by and returned to userspace via the update_elem * and lookup functions. * * For instance, let's start with a trie that was created with a prefix length * of 32, so it can be used for IPv4 addresses, and one single element that * matches 192.168.0.0/16. The data array would hence contain * [0xc0, 0xa8, 0x00, 0x00] in big-endian notation. This documentation will * stick to IP-address notation for readability though. * * As the trie is empty initially, the new node (1) will be places as root * node, denoted as (R) in the example below. As there are no other node, both * child pointers are %NULL. * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * * Next, let's add a new node (2) matching 192.168.0.0/24. As there is already * a node with the same data and a smaller prefix (ie, a less specific one), * node (2) will become a child of (1). In child index depends on the next bit * that is outside of what (1) matches, and that bit is 0, so (2) will be * child[0] of (1): * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | * +----------------+ * | (2) | * | 192.168.0.0/24 | * | value: 2 | * | [0] [1] | * +----------------+ * * The child[1] slot of (1) could be filled with another node which has bit #17 * (the next bit after the ones that (1) matches on) set to 1. For instance, * 192.168.128.0/24: * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | | * +----------------+ +------------------+ * | (2) | | (3) | * | 192.168.0.0/24 | | 192.168.128.0/24 | * | value: 2 | | value: 3 | * | [0] [1] | | [0] [1] | * +----------------+ +------------------+ * * Let's add another node (4) to the game for 192.168.1.0/24. In order to place * it, node (1) is looked at first, and because (4) of the semantics laid out * above (bit #17 is 0), it would normally be attached to (1) as child[0]. * However, that slot is already allocated, so a new node is needed in between. * That node does not have a value attached to it and it will never be * returned to users as result of a lookup. It is only there to differentiate * the traversal further. It will get a prefix as wide as necessary to * distinguish its two children: * * +----------------+ * | (1) (R) | * | 192.168.0.0/16 | * | value: 1 | * | [0] [1] | * +----------------+ * | | * +----------------+ +------------------+ * | (4) (I) | | (3) | * | 192.168.0.0/23 | | 192.168.128.0/24 | * | value: --- | | value: 3 | * | [0] [1] | | [0] [1] | * +----------------+ +------------------+ * | | * +----------------+ +----------------+ * | (2) | | (5) | * | 192.168.0.0/24 | | 192.168.1.0/24 | * | value: 2 | | value: 5 | * | [0] [1] | | [0] [1] | * +----------------+ +----------------+ * * 192.168.1.1/32 would be a child of (5) etc. * * An intermediate node will be turned into a 'real' node on demand. In the * example above, (4) would be re-used if 192.168.0.0/23 is added to the trie. * * A fully populated trie would have a height of 32 nodes, as the trie was * created with a prefix length of 32. * * The lookup starts at the root node. If the current node matches and if there * is a child that can be used to become more specific, the trie is traversed * downwards. The last node in the traversal that is a non-intermediate one is * returned. */ static inline int extract_bit(const u8 *data, size_t index) { return !!(data[index / 8] & (1 << (7 - (index % 8)))); } /** * longest_prefix_match() - determine the longest prefix * @trie: The trie to get internal sizes from * @node: The node to operate on * @key: The key to compare to @node * * Determine the longest prefix of @node that matches the bits in @key. */ static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, const struct bpf_lpm_trie_key *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) /* data_size >= 16 has very small probability. * We do not use a loop for optimal code generation. */ if (trie->data_size >= 8) { u64 diff = be64_to_cpu(*(__be64 *)node->data ^ *(__be64 *)key->data); prefixlen = 64 - fls64(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i = 8; } #endif while (trie->data_size >= i + 4) { u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^ *(__be32 *)&key->data[i]); prefixlen += 32 - fls(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i += 4; } if (trie->data_size >= i + 2) { u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^ *(__be16 *)&key->data[i]); prefixlen += 16 - fls(diff); if (prefixlen >= limit) return limit; if (diff) return prefixlen; i += 2; } if (trie->data_size >= i + 1) { prefixlen += 8 - fls(node->data[i] ^ key->data[i]); if (prefixlen >= limit) return limit; } return prefixlen; } /* Called from syscall or from eBPF program */ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *found = NULL; struct bpf_lpm_trie_key *key = _key; if (key->prefixlen > trie->max_prefixlen) return NULL; /* Start walking the trie from the root node ... */ for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held()); node;) { unsigned int next_bit; size_t matchlen; /* Determine the longest prefix of @node that matches @key. * If it's the maximum possible prefix for this trie, we have * an exact match and can return it directly. */ matchlen = longest_prefix_match(trie, node, key); if (matchlen == trie->max_prefixlen) { found = node; break; } /* If the number of bits that match is smaller than the prefix * length of @node, bail out and return the node we have seen * last in the traversal (ie, the parent). */ if (matchlen < node->prefixlen) break; /* Consider this node as return candidate unless it is an * artificially added intermediate one. */ if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) found = node; /* If the node match is fully satisfied, let's see if we can * become more specific. Determine the next bit in the key and * traverse down. */ next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference_check(node->child[next_bit], rcu_read_lock_bh_held()); } if (!found) return NULL; return found->data + trie->data_size; } static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, const void *value) { struct lpm_trie_node *node; size_t size = sizeof(struct lpm_trie_node) + trie->data_size; if (value) size += trie->map.value_size; node = bpf_map_kmalloc_node(&trie->map, size, GFP_NOWAIT | __GFP_NOWARN, trie->map.numa_node); if (!node) return NULL; node->flags = 0; if (value) memcpy(node->data + trie->data_size, value, trie->map.value_size); return node; } /* Called from syscall or from eBPF program */ static long trie_update_elem(struct bpf_map *map, void *_key, void *value, u64 flags) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; struct lpm_trie_node __rcu **slot; struct bpf_lpm_trie_key *key = _key; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; int ret = 0; if (unlikely(flags > BPF_EXIST)) return -EINVAL; if (key->prefixlen > trie->max_prefixlen) return -EINVAL; spin_lock_irqsave(&trie->lock, irq_flags); /* Allocate and fill a new node */ if (trie->n_entries == trie->map.max_entries) { ret = -ENOSPC; goto out; } new_node = lpm_trie_node_alloc(trie, value); if (!new_node) { ret = -ENOMEM; goto out; } trie->n_entries++; new_node->prefixlen = key->prefixlen; RCU_INIT_POINTER(new_node->child[0], NULL); RCU_INIT_POINTER(new_node->child[1], NULL); memcpy(new_node->data, key->data, trie->data_size); /* Now find a slot to attach the new node. To do that, walk the tree * from the root and match as many bits as possible for each node until * we either find an empty slot or a slot that needs to be replaced by * an intermediate node. */ slot = &trie->root; while ((node = rcu_dereference_protected(*slot, lockdep_is_held(&trie->lock)))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen || node->prefixlen == trie->max_prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); slot = &node->child[next_bit]; } /* If the slot is empty (a free child pointer or an empty root), * simply assign the @new_node to that slot and be done. */ if (!node) { rcu_assign_pointer(*slot, new_node); goto out; } /* If the slot we picked already exists, replace it with @new_node * which already has the correct data array set. */ if (node->prefixlen == matchlen) { new_node->child[0] = node->child[0]; new_node->child[1] = node->child[1]; if (!(node->flags & LPM_TREE_NODE_FLAG_IM)) trie->n_entries--; rcu_assign_pointer(*slot, new_node); kfree_rcu(node, rcu); goto out; } /* If the new node matches the prefix completely, it must be inserted * as an ancestor. Simply insert it between @node and *@slot. */ if (matchlen == key->prefixlen) { next_bit = extract_bit(node->data, matchlen); rcu_assign_pointer(new_node->child[next_bit], node); rcu_assign_pointer(*slot, new_node); goto out; } im_node = lpm_trie_node_alloc(trie, NULL); if (!im_node) { ret = -ENOMEM; goto out; } im_node->prefixlen = matchlen; im_node->flags |= LPM_TREE_NODE_FLAG_IM; memcpy(im_node->data, node->data, trie->data_size); /* Now determine which child to install in which slot */ if (extract_bit(key->data, matchlen)) { rcu_assign_pointer(im_node->child[0], node); rcu_assign_pointer(im_node->child[1], new_node); } else { rcu_assign_pointer(im_node->child[0], new_node); rcu_assign_pointer(im_node->child[1], node); } /* Finally, assign the intermediate node to the determined slot */ rcu_assign_pointer(*slot, im_node); out: if (ret) { if (new_node) trie->n_entries--; kfree(new_node); kfree(im_node); } spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } /* Called from syscall or from eBPF program */ static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; int ret = 0; if (key->prefixlen > trie->max_prefixlen) return -EINVAL; spin_lock_irqsave(&trie->lock, irq_flags); /* Walk the tree looking for an exact key/length match and keeping * track of the path we traverse. We will need to know the node * we wish to delete, and the slot that points to the node we want * to delete. We may also need to know the nodes parent and the * slot that contains it. */ trim = &trie->root; trim2 = trim; parent = NULL; while ((node = rcu_dereference_protected( *trim, lockdep_is_held(&trie->lock)))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; parent = node; trim2 = trim; next_bit = extract_bit(key->data, node->prefixlen); trim = &node->child[next_bit]; } if (!node || node->prefixlen != key->prefixlen || node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) { ret = -ENOENT; goto out; } trie->n_entries--; /* If the node we are removing has two children, simply mark it * as intermediate and we are done. */ if (rcu_access_pointer(node->child[0]) && rcu_access_pointer(node->child[1])) { node->flags |= LPM_TREE_NODE_FLAG_IM; goto out; } /* If the parent of the node we are about to delete is an intermediate * node, and the deleted node doesn't have any children, we can delete * the intermediate parent as well and promote its other child * up the tree. Doing this maintains the invariant that all * intermediate nodes have exactly 2 children and that there are no * unnecessary intermediate nodes in the tree. */ if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) && !node->child[0] && !node->child[1]) { if (node == rcu_access_pointer(parent->child[0])) rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[1])); else rcu_assign_pointer( *trim2, rcu_access_pointer(parent->child[0])); kfree_rcu(parent, rcu); kfree_rcu(node, rcu); goto out; } /* The node we are removing has either zero or one child. If there * is a child, move it into the removed node's slot then delete * the node. Otherwise just clear the slot and delete the node. */ if (node->child[0]) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0])); else if (node->child[1]) rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); else RCU_INIT_POINTER(*trim, NULL); kfree_rcu(node, rcu); out: spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } #define LPM_DATA_SIZE_MAX 256 #define LPM_DATA_SIZE_MIN 1 #define LPM_VAL_SIZE_MAX (KMALLOC_MAX_SIZE - LPM_DATA_SIZE_MAX - \ sizeof(struct lpm_trie_node)) #define LPM_VAL_SIZE_MIN 1 #define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key) + (X)) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) #define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ BPF_F_ACCESS_MASK) static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; /* check sanity of attributes */ if (attr->max_entries == 0 || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->map_flags & ~LPM_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags) || attr->key_size < LPM_KEY_SIZE_MIN || attr->key_size > LPM_KEY_SIZE_MAX || attr->value_size < LPM_VAL_SIZE_MIN || attr->value_size > LPM_VAL_SIZE_MAX) return ERR_PTR(-EINVAL); trie = bpf_map_area_alloc(sizeof(*trie), NUMA_NO_NODE); if (!trie) return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; spin_lock_init(&trie->lock); return &trie->map; } static void trie_free(struct bpf_map *map) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node __rcu **slot; struct lpm_trie_node *node; /* Always start at the root and walk down to a node that has no * children. Then free that node, nullify its reference in the parent * and start over. */ for (;;) { slot = &trie->root; for (;;) { node = rcu_dereference_protected(*slot, 1); if (!node) goto out; if (rcu_access_pointer(node->child[0])) { slot = &node->child[0]; continue; } if (rcu_access_pointer(node->child[1])) { slot = &node->child[1]; continue; } kfree(node); RCU_INIT_POINTER(*slot, NULL); break; } } out: bpf_map_area_free(trie); } static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root; struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key *key = _key, *next_key = _next_key; struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; size_t matchlen; /* The get_next_key follows postorder. For the 4 node example in * the top of this file, the trie_get_next_key() returns the following * one after another: * 192.168.0.0/24 * 192.168.1.0/24 * 192.168.128.0/24 * 192.168.0.0/16 * * The idea is to return more specific keys before less specific ones. */ /* Empty trie */ search_root = rcu_dereference(trie->root); if (!search_root) return -ENOENT; /* For invalid key, find the leftmost node in the trie */ if (!key || key->prefixlen > trie->max_prefixlen) goto find_leftmost; node_stack = kmalloc_array(trie->max_prefixlen, sizeof(struct lpm_trie_node *), GFP_ATOMIC | __GFP_NOWARN); if (!node_stack) return -ENOMEM; /* Try to find the exact node for the given key */ for (node = search_root; node;) { node_stack[++stack_ptr] = node; matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; next_bit = extract_bit(key->data, node->prefixlen); node = rcu_dereference(node->child[next_bit]); } if (!node || node->prefixlen != key->prefixlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) goto find_leftmost; /* The node with the exactly-matching key has been found, * find the first node in postorder after the matched node. */ node = node_stack[stack_ptr]; while (stack_ptr > 0) { parent = node_stack[stack_ptr - 1]; if (rcu_dereference(parent->child[0]) == node) { search_root = rcu_dereference(parent->child[1]); if (search_root) goto find_leftmost; } if (!(parent->flags & LPM_TREE_NODE_FLAG_IM)) { next_node = parent; goto do_copy; } node = parent; stack_ptr--; } /* did not find anything */ err = -ENOENT; goto free_stack; find_leftmost: /* Find the leftmost non-intermediate node, all intermediate nodes * have exact two children, so this function will never return NULL. */ for (node = search_root; node;) { if (node->flags & LPM_TREE_NODE_FLAG_IM) { node = rcu_dereference(node->child[0]); } else { next_node = node; node = rcu_dereference(node->child[0]); if (!node) node = rcu_dereference(next_node->child[1]); } } do_copy: next_key->prefixlen = next_node->prefixlen; memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data), next_node->data, trie->data_size); free_stack: kfree(node_stack); return err; } static int trie_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { /* Keys must have struct bpf_lpm_trie_key embedded. */ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? -EINVAL : 0; } static u64 trie_mem_usage(const struct bpf_map *map) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); u64 elem_size; elem_size = sizeof(struct lpm_trie_node) + trie->data_size + trie->map.value_size; return elem_size * READ_ONCE(trie->n_entries); } BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie) const struct bpf_map_ops trie_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = trie_alloc, .map_free = trie_free, .map_get_next_key = trie_get_next_key, .map_lookup_elem = trie_lookup_elem, .map_update_elem = trie_update_elem, .map_delete_elem = trie_delete_elem, .map_lookup_batch = generic_map_lookup_batch, .map_update_batch = generic_map_update_batch, .map_delete_batch = generic_map_delete_batch, .map_check_btf = trie_check_btf, .map_mem_usage = trie_mem_usage, .map_btf_id = &trie_map_btf_ids[0], }; |
| 9678 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ipi #if !defined(_TRACE_IPI_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IPI_H #include <linux/tracepoint.h> /** * ipi_raise - called when a smp cross call is made * * @mask: mask of recipient CPUs for the IPI * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string. */ TRACE_EVENT(ipi_raise, TP_PROTO(const struct cpumask *mask, const char *reason), TP_ARGS(mask, reason), TP_STRUCT__entry( __bitmask(target_cpus, nr_cpumask_bits) __field(const char *, reason) ), TP_fast_assign( __assign_bitmask(target_cpus, cpumask_bits(mask), nr_cpumask_bits); __entry->reason = reason; ), TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) ); TRACE_EVENT(ipi_send_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback), TP_ARGS(cpu, callsite, callback), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpu=%u callsite=%pS callback=%pS", __entry->cpu, __entry->callsite, __entry->callback) ); TRACE_EVENT(ipi_send_cpumask, TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback), TP_ARGS(cpumask, callsite, callback), TP_STRUCT__entry( __cpumask(cpumask) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __assign_cpumask(cpumask, cpumask_bits(cpumask)); __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpumask=%s callsite=%pS callback=%pS", __get_cpumask(cpumask), __entry->callsite, __entry->callback) ); DECLARE_EVENT_CLASS(ipi_handler, TP_PROTO(const char *reason), TP_ARGS(reason), TP_STRUCT__entry( __field(const char *, reason) ), TP_fast_assign( __entry->reason = reason; ), TP_printk("(%s)", __entry->reason) ); /** * ipi_entry - called immediately before the IPI handler * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise * for that IPI. */ DEFINE_EVENT(ipi_handler, ipi_entry, TP_PROTO(const char *reason), TP_ARGS(reason) ); /** * ipi_exit - called immediately after the IPI handler returns * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise for * that IPI. */ DEFINE_EVENT(ipi_handler, ipi_exit, TP_PROTO(const char *reason), TP_ARGS(reason) ); #endif /* _TRACE_IPI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 3 308 309 3 3 10 1 344 147 7 1 6 7 7 2 1 1 1 2 1 1 1 204 205 205 205 205 145 14 15 109 48 181 40 157 157 155 2 3 508 148 141 132 223 93 37 279 55 3 3 4 178 147 207 461 495 462 45 2 493 493 11 451 335 5 331 4 239 196 208 254 254 15 8 246 234 17 242 242 37 213 157 157 168 168 124 168 168 174 174 169 174 174 174 51 168 4 4 4 4 141 177 66 80 138 135 135 135 8 2 4 1 146 154 229 57 57 83 83 335 2 29 1 11 4 1 20 2 17 29 6 2 2 1 1 25 26 26 24 24 24 22 7 7 22 1 2 3 5 2 13 10 10 1 1 6 10 23 2 28 3 26 25 486 486 446 217 217 455 104 73 73 73 73 10 10 10 10 10 10 153 152 122 31 7 31 18 153 153 151 2 2 142 10 10 142 142 52 53 7 551 552 551 551 98 92 20 85 12 92 3 98 98 98 97 98 98 98 5 5 2 2 2 2 13 6 7 7 7 4 1 3 1 1 1 2 2 2 3 1 2 1 2 2 2 4 1 1 138 2 10 2 8 8 5 3 115 3 4 3 4 2 2 2 6 6 2 3 1 2 1 1 1 2 2 1 2 3 3 1 4 4 2 13 9 4 2 4 4 3 2 6 2 1 1 2 175 37 137 4 8 34 32 2 9 2 9 2 9 11 11 11 11 11 11 8 6 11 200 200 201 201 194 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> * * Fixes: * Alan Cox : Numerous verify_area() calls * Alan Cox : Set the ACK bit on a reset * Alan Cox : Stopped it crashing if it closed while * sk->inuse=1 and was trying to connect * (tcp_err()). * Alan Cox : All icmp error handling was broken * pointers passed where wrong and the * socket was looked up backwards. Nobody * tested any icmp error code obviously. * Alan Cox : tcp_err() now handled properly. It * wakes people on errors. poll * behaves and the icmp error race * has gone by moving it into sock.c * Alan Cox : tcp_send_reset() fixed to work for * everything not just packets for * unknown sockets. * Alan Cox : tcp option processing. * Alan Cox : Reset tweaked (still not 100%) [Had * syn rule wrong] * Herp Rosmanith : More reset fixes * Alan Cox : No longer acks invalid rst frames. * Acking any kind of RST is right out. * Alan Cox : Sets an ignore me flag on an rst * receive otherwise odd bits of prattle * escape still * Alan Cox : Fixed another acking RST frame bug. * Should stop LAN workplace lockups. * Alan Cox : Some tidyups using the new skb list * facilities * Alan Cox : sk->keepopen now seems to work * Alan Cox : Pulls options out correctly on accepts * Alan Cox : Fixed assorted sk->rqueue->next errors * Alan Cox : PSH doesn't end a TCP read. Switched a * bit to skb ops. * Alan Cox : Tidied tcp_data to avoid a potential * nasty. * Alan Cox : Added some better commenting, as the * tcp is hard to follow * Alan Cox : Removed incorrect check for 20 * psh * Michael O'Reilly : ack < copied bug fix. * Johannes Stille : Misc tcp fixes (not all in yet). * Alan Cox : FIN with no memory -> CRASH * Alan Cox : Added socket option proto entries. * Also added awareness of them to accept. * Alan Cox : Added TCP options (SOL_TCP) * Alan Cox : Switched wakeup calls to callbacks, * so the kernel can layer network * sockets. * Alan Cox : Use ip_tos/ip_ttl settings. * Alan Cox : Handle FIN (more) properly (we hope). * Alan Cox : RST frames sent on unsynchronised * state ack error. * Alan Cox : Put in missing check for SYN bit. * Alan Cox : Added tcp_select_window() aka NET2E * window non shrink trick. * Alan Cox : Added a couple of small NET2E timer * fixes * Charles Hedrick : TCP fixes * Toomas Tamm : TCP window fixes * Alan Cox : Small URG fix to rlogin ^C ack fight * Charles Hedrick : Rewrote most of it to actually work * Linus : Rewrote tcp_read() and URG handling * completely * Gerhard Koerting: Fixed some missing timer handling * Matthew Dillon : Reworked TCP machine states as per RFC * Gerhard Koerting: PC/TCP workarounds * Adam Caldwell : Assorted timer/timing errors * Matthew Dillon : Fixed another RST bug * Alan Cox : Move to kernel side addressing changes. * Alan Cox : Beginning work on TCP fastpathing * (not yet usable) * Arnt Gulbrandsen: Turbocharged tcp_check() routine. * Alan Cox : TCP fast path debugging * Alan Cox : Window clamping * Michael Riepe : Bug in tcp_check() * Matt Dillon : More TCP improvements and RST bug fixes * Matt Dillon : Yet more small nasties remove from the * TCP code (Be very nice to this man if * tcp finally works 100%) 8) * Alan Cox : BSD accept semantics. * Alan Cox : Reset on closedown bug. * Peter De Schrijver : ENOTCONN check missing in tcp_sendto(). * Michael Pall : Handle poll() after URG properly in * all cases. * Michael Pall : Undo the last fix in tcp_read_urg() * (multi URG PUSH broke rlogin). * Michael Pall : Fix the multi URG PUSH problem in * tcp_readable(), poll() after URG * works now. * Michael Pall : recv(...,MSG_OOB) never blocks in the * BSD api. * Alan Cox : Changed the semantics of sk->socket to * fix a race and a signal problem with * accept() and async I/O. * Alan Cox : Relaxed the rules on tcp_sendto(). * Yury Shevchuk : Really fixed accept() blocking problem. * Craig I. Hagan : Allow for BSD compatible TIME_WAIT for * clients/servers which listen in on * fixed ports. * Alan Cox : Cleaned the above up and shrank it to * a sensible code size. * Alan Cox : Self connect lockup fix. * Alan Cox : No connect to multicast. * Ross Biro : Close unaccepted children on master * socket close. * Alan Cox : Reset tracing code. * Alan Cox : Spurious resets on shutdown. * Alan Cox : Giant 15 minute/60 second timer error * Alan Cox : Small whoops in polling before an * accept. * Alan Cox : Kept the state trace facility since * it's handy for debugging. * Alan Cox : More reset handler fixes. * Alan Cox : Started rewriting the code based on * the RFC's for other useful protocol * references see: Comer, KA9Q NOS, and * for a reference on the difference * between specifications and how BSD * works see the 4.4lite source. * A.N.Kuznetsov : Don't time wait on completion of tidy * close. * Linus Torvalds : Fin/Shutdown & copied_seq changes. * Linus Torvalds : Fixed BSD port reuse to work first syn * Alan Cox : Reimplemented timers as per the RFC * and using multiple timers for sanity. * Alan Cox : Small bug fixes, and a lot of new * comments. * Alan Cox : Fixed dual reader crash by locking * the buffers (much like datagram.c) * Alan Cox : Fixed stuck sockets in probe. A probe * now gets fed up of retrying without * (even a no space) answer. * Alan Cox : Extracted closing code better * Alan Cox : Fixed the closing state machine to * resemble the RFC. * Alan Cox : More 'per spec' fixes. * Jorge Cwik : Even faster checksumming. * Alan Cox : tcp_data() doesn't ack illegal PSH * only frames. At least one pc tcp stack * generates them. * Alan Cox : Cache last socket. * Alan Cox : Per route irtt. * Matt Day : poll()->select() match BSD precisely on error * Alan Cox : New buffers * Marc Tamsky : Various sk->prot->retransmits and * sk->retransmits misupdating fixed. * Fixed tcp_write_timeout: stuck close, * and TCP syn retries gets used now. * Mark Yarvis : In tcp_read_wakeup(), don't send an * ack if state is TCP_CLOSED. * Alan Cox : Look up device on a retransmit - routes may * change. Doesn't yet cope with MSS shrink right * but it's a start! * Marc Tamsky : Closing in closing fixes. * Mike Shaver : RFC1122 verifications. * Alan Cox : rcv_saddr errors. * Alan Cox : Block double connect(). * Alan Cox : Small hooks for enSKIP. * Alexey Kuznetsov: Path MTU discovery. * Alan Cox : Support soft errors. * Alan Cox : Fix MTU discovery pathological case * when the remote claims no mtu! * Marc Tamsky : TCP_CLOSE fix. * Colin (G3TNE) : Send a reset on syn ack replies in * window but wrong (fixes NT lpd problems) * Pedro Roque : Better TCP window handling, delayed ack. * Joerg Reuter : No modification of locked buffers in * tcp_do_retransmit() * Eric Schenk : Changed receiver side silly window * avoidance algorithm to BSD style * algorithm. This doubles throughput * against machines running Solaris, * and seems to result in general * improvement. * Stefan Magdalinski : adjusted tcp_readable() to fix FIONREAD * Willy Konynenberg : Transparent proxying support. * Mike McLagan : Routing by source * Keith Owens : Do proper merging with partial SKB's in * tcp_do_sendmsg to avoid burstiness. * Eric Schenk : Fix fast close down bug with * shutdown() followed by close(). * Andi Kleen : Make poll agree with SIGIO * Salvatore Sanfilippo : Support SO_LINGER with linger == 1 and * lingertime == 0 (RFC 793 ABORT Call) * Hirokazu Takahashi : Use copy_from_user() instead of * csum_and_copy_from_user() if possible. * * Description of States: * * TCP_SYN_SENT sent a connection request, waiting for ack * * TCP_SYN_RECV received a connection request, sent ack, * waiting for final ack in three-way handshake. * * TCP_ESTABLISHED connection established * * TCP_FIN_WAIT1 our side has shutdown, waiting to complete * transmission of remaining buffered data * * TCP_FIN_WAIT2 all buffered data sent, waiting for remote * to shutdown * * TCP_CLOSING both sides have shutdown but we still have * data we have to finish sending * * TCP_TIME_WAIT timeout to catch resent junk before entering * closed, can only be entered from FIN_WAIT2 * or CLOSING. Required because the other end * may not have gotten our last ACK causing it * to retransmit the data packet (which we ignore) * * TCP_CLOSE_WAIT remote side has shutdown and is waiting for * us to finish writing our data and to shutdown * (we have to close() to move on to LAST_ACK) * * TCP_LAST_ACK out side has shutdown after remote has * shutdown. There may still be data in our * buffer that we have to finish sending * * TCP_CLOSE socket is finished */ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/hash.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/inet_diag.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> #include <linux/scatterlist.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/random.h> #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/errqueue.h> #include <linux/static_key.h> #include <linux/btf.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/tcp.h> #include <net/mptcp.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/sock.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> /* Track pending CMSGs. */ enum { TCP_CMSG_INQ = 1, TCP_CMSG_TS = 2 }; DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); #if IS_ENABLED(CONFIG_SMC) DEFINE_STATIC_KEY_FALSE(tcp_have_smc); EXPORT_SYMBOL(tcp_have_smc); #endif /* * Current number of TCP sockets. */ struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; EXPORT_SYMBOL(tcp_sockets_allocated); /* * TCP splice context */ struct tcp_splice_state { struct pipe_inode_info *pipe; size_t len; unsigned int flags; }; /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long tcp_memory_pressure __read_mostly; EXPORT_SYMBOL_GPL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; if (!val) val--; if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); } EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, jiffies_to_msecs(jiffies - val)); } EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) { u8 res = 0; if (seconds > 0) { int period = timeout; res = 1; while (seconds > period && res < 255) { res++; timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return res; } /* Convert retransmits to seconds based on initial and max timeout */ static int retrans_to_secs(u8 retrans, int timeout, int rto_max) { int period = 0; if (retrans > 0) { period = timeout; while (--retrans) { timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return period; } static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp) { u32 rate = READ_ONCE(tp->rate_delivered); u32 intv = READ_ONCE(tp->rate_interval_us); u64 rate64 = 0; if (rate && intv) { rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; do_div(rate64, intv); } return rate64; } /* Address-family independent initialization for a tcp_sock. * * NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ void tcp_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); tp->out_of_order_queue = RB_ROOT; sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ tcp_snd_cwnd_set(tp, TCP_INIT_CWND); /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; tp->rack.reo_wnd_steps = 1; sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); icsk->icsk_sync_mss = tcp_sync_mss; WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); tcp_scaling_ratio_init(sk); set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); } EXPORT_SYMBOL(tcp_init_sock); static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); sock_tx_timestamp(sk, tsflags, &shinfo->tx_flags); if (tsflags & SOF_TIMESTAMPING_TX_ACK) tcb->txstamp_ack = 1; if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; } } static bool tcp_stream_is_readable(struct sock *sk, int target) { if (tcp_epollin_ready(sk, target)) return true; return sk_is_readable(sk); } /* * Wait for a TCP event. * * Note that we don't need to lock the socket, as the upper poll layers * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); u8 shutdown; int state; sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events * by poll logic and correct handling of state changes * made by other threads is impossible in any case. */ mask = 0; /* * EPOLLHUP is certainly not done right. But poll() doesn't * have a notion of HUP in just one direction, and for a * socket the read side is more interesting. * * Some poll() documentation says that EPOLLHUP is incompatible * with the EPOLLOUT/POLLWR flags, so somebody should check this * all. But careful, it tends to be safer to return too many * bits than too few, and you can easily break real applications * if you don't tell them that something has hung up! * * Check-me. * * Check number 1. EPOLLHUP is _UNMASKABLE_ event (see UNIX98 and * our fs/select.c). It means that after we received EOF, * poll always returns immediately, making impossible poll() on write() * in state CLOSE_WAIT. One solution is evident --- to set EPOLLHUP * if and only if shutdown has been made in both directions. * Actually, it is interesting to look how Solaris and DUX * solve this dilemma. I would prefer, if EPOLLHUP were maskable, * then we could set it on SND_SHUTDOWN. BTW examples given * in Stevens' books assume exactly this behaviour, it explains * why EPOLLHUP is incompatible with EPOLLOUT. --ANK * * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); u16 urg_data = READ_ONCE(tp->urg_data); if (unlikely(urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE)) target++; if (tcp_stream_is_readable(sk, target)) mask |= EPOLLIN | EPOLLRDNORM; if (!(shutdown & SEND_SHUTDOWN)) { if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after * wspace test but before the flags are set, * IO signal will be lost. Memory barrier * pairs with the input side. */ smp_mb__after_atomic(); if (__sk_stream_is_writeable(sk, 1)) mask |= EPOLLOUT | EPOLLWRNORM; } } else mask |= EPOLLOUT | EPOLLWRNORM; if (urg_data & TCP_URG_VALID) mask |= EPOLLPRI; } else if (state == TCP_SYN_SENT && inet_test_bit(DEFER_CONNECT, sk)) { /* Active TCP fastopen socket with defer_connect * Return EPOLLOUT so application can call write() * in order for kernel to generate SYN+data */ mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); if (READ_ONCE(sk->sk_err) || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR; return mask; } EXPORT_SYMBOL(tcp_poll); int tcp_ioctl(struct sock *sk, int cmd, int *karg) { struct tcp_sock *tp = tcp_sk(sk); int answ; bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; slow = lock_sock_fast(sk); answ = tcp_inq(sk); unlock_sock_fast(sk, slow); break; case SIOCATMARK: answ = READ_ONCE(tp->urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; } *karg = answ; return 0; } EXPORT_SYMBOL(tcp_ioctl); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; tp->pushed_seq = tp->write_seq; } static inline bool forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } void tcp_skb_entail(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->seq = tcb->end_seq = tp->write_seq; tcb->tcp_flags = TCPHDR_ACK; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) { if (flags & MSG_OOB) tp->snd_up = tp->write_seq; } /* If a not yet filled skb is pushed, do not send it if * we have data packets in Qdisc or NIC queues : * Because TX completion will happen shortly, it gives a chance * to coalesce future sendmsg() payload into this skb, without * need for a timer, and with no latency trade off. * As packets containing data payload have a bigger truesize * than pure acks (dataless) packets, the last checks prevent * autocorking if we only have an ACK in Qdisc/NIC queues, * or if TX completion was delayed after we processed ACK packet. */ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, int size_goal) { return skb->len < size_goal && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) && !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize && tcp_skb_can_collapse_to(skb); } void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; skb = tcp_write_queue_tail(sk); if (!skb) return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); tcp_mark_urg(tp, flags); if (tcp_should_autocork(sk, skb, size_goal)) { /* avoid atomic op if TSQ_THROTTLED bit is already set */ if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. */ if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize) return; } if (flags & MSG_MORE) nonagle = TCP_NAGLE_CORK; __tcp_push_pending_frames(sk, mss_now, nonagle); } static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len) { struct tcp_splice_state *tss = rd_desc->arg.data; int ret; ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, min(rd_desc->count, len), tss->flags); if (ret > 0) rd_desc->count -= ret; return ret; } static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss) { /* Store TCP splice context information in read_descriptor_t. */ read_descriptor_t rd_desc = { .arg.data = tss, .count = tss->len, }; return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv); } /** * tcp_splice_read - splice data from TCP socket to a pipe * @sock: socket to splice from * @ppos: position (not valid) * @pipe: pipe to splice to * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will read pages from given socket and fill them into a pipe. * **/ ssize_t tcp_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 tcp_splice_state tss = { .pipe = pipe, .len = len, .flags = flags, }; long timeo; ssize_t spliced; int ret; sock_rps_record_flow(sk); /* * We can't seek on a socket input */ if (unlikely(*ppos)) return -ESPIPE; ret = spliced = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK); while (tss.len) { ret = __tcp_splice_read(sk, &tss); if (ret < 0) break; else if (!ret) { if (spliced) break; if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { ret = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* * This occurs when user tries to read * from never connected socket. */ ret = -ENOTCONN; break; } if (!timeo) { ret = -EAGAIN; break; } /* if __tcp_splice_read() got nothing while we have * an skb in receive queue, we do not want to loop. * This might happen with URG data. */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; ret = sk_wait_data(sk, &timeo, NULL); if (ret < 0) break; if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; } continue; } tss.len -= ret; spliced += ret; if (!tss.len || !timeo) break; release_sock(sk); lock_sock(sk); if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } release_sock(sk); if (spliced) return spliced; return ret; } EXPORT_SYMBOL(tcp_splice_read); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule) { struct sk_buff *skb; skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp); if (likely(skb)) { bool mem_scheduled; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); } else { mem_scheduled = sk_wmem_schedule(sk, skb->truesize); } if (likely(mem_scheduled)) { skb_reserve(skb, MAX_TCP_HEADER); skb->ip_summed = CHECKSUM_PARTIAL; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); } else { sk->sk_prot->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return NULL; } static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, int large_allowed) { struct tcp_sock *tp = tcp_sk(sk); u32 new_size_goal, size_goal; if (!large_allowed) return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size); /* We try hard to avoid divides here */ size_goal = tp->gso_segs * mss_now; if (unlikely(new_size_goal < size_goal || new_size_goal >= size_goal + mss_now)) { tp->gso_segs = min_t(u16, new_size_goal / mss_now, sk->sk_gso_max_segs); size_goal = tp->gso_segs * mss_now; } return max(size_goal, mss_now); } int tcp_send_mss(struct sock *sk, int *size_goal, int flags) { int mss_now; mss_now = tcp_current_mss(sk); *size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB)); return mss_now; } /* In some cases, sendmsg() could have added an skb to the write queue, * but failed adding payload on it. We need to remove it to consume less * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger * epoll() users. Another reason is that tcp_write_xmit() does not like * finding an empty skb in the write queue. */ void tcp_remove_empty_skb(struct sock *sk) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (skb && TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { tcp_unlink_write_queue(skb, sk); if (tcp_write_queue_empty(sk)) tcp_chrono_stop(sk, TCP_CHRONO_BUSY); tcp_wmem_free_skb(sk, skb); } } /* skb changing from pure zc to mixed, must charge zc */ static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb) { if (unlikely(skb_zcopy_pure(skb))) { u32 extra = skb->truesize - SKB_TRUESIZE(skb_end_offset(skb)); if (!sk_wmem_schedule(sk, extra)) return -ENOMEM; sk_mem_charge(sk, extra); skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; } return 0; } int tcp_wmem_schedule(struct sock *sk, int copy) { int left; if (likely(sk_wmem_schedule(sk, copy))) return copy; /* We could be in trouble if we have nothing queued. * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0] * to guarantee some progress. */ left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued; if (left > 0) sk_forced_mem_schedule(sk, min(left, copy)); return min(copy, sk->sk_forward_alloc); } void tcp_free_fastopen_req(struct tcp_sock *tp) { if (tp->fastopen_req) { kfree(tp->fastopen_req); tp->fastopen_req = NULL; } } int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sockaddr *uaddr = msg->msg_name; int err, flags; if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; if (tp->fastopen_req) return -EALREADY; /* Another Fast Open is in progress */ tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), sk->sk_allocation); if (unlikely(!tp->fastopen_req)) return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; tp->fastopen_req->uarg = uarg; if (inet_test_bit(DEFER_CONNECT, sk)) { err = tcp_connect(sk); /* Same failure procedure as in tcp_v4/6_connect */ if (err) { tcp_set_state(sk, TCP_CLOSE); inet->inet_dport = 0; sk->sk_route_caps = 0; } } flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, uaddr, msg->msg_namelen, flags, 1); /* fastopen_req could already be freed in __inet_stream_connect * if the connection times out or gets rst */ if (tp->fastopen_req) { *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); } return err; } int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) { struct tcp_sock *tp = tcp_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; int process_backlog = 0; int zc = 0; long timeo; flags = msg->msg_flags; if ((flags & MSG_ZEROCOPY) && size) { if (msg->msg_ubuf) { uarg = msg->msg_ubuf; if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_ZEROCOPY; } else if (sock_flag(sk, SOCK_ZEROCOPY)) { skb = tcp_write_queue_tail(sk); uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; goto out_err; } if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_ZEROCOPY; else uarg_to_msgzc(uarg)->zerocopy = 0; } } else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) { if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_SPLICE_PAGES; } if (unlikely(flags & MSG_FASTOPEN || inet_test_bit(DEFER_CONNECT, sk)) && !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) goto out_err; } timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { err = sk_stream_wait_connect(sk, &timeo); if (err != 0) goto do_error; } if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { copied = tcp_send_rcvq(sk, msg, size); goto out_nopush; } err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out_err; /* 'common' sending to sendq */ } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) { err = -EINVAL; goto out_err; } } /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* Ok commence sending. */ copied = 0; restart: mss_now = tcp_send_mss(sk, &size_goal, flags); err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; while (msg_data_left(msg)) { ssize_t copy = 0; skb = tcp_write_queue_tail(sk); if (skb) copy = size_goal - skb->len; if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_space; if (unlikely(process_backlog >= 16)) { process_backlog = 0; if (sk_flush_backlog(sk)) goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = tcp_stream_alloc_skb(sk, sk->sk_allocation, first_skb); if (!skb) goto wait_for_space; process_backlog++; tcp_skb_entail(sk, skb); copy = size_goal; /* All packets are restored as if they have * already been sent. skb_mstamp_ns isn't set to * avoid wrong rtt estimation. */ if (tp->repair) TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ if (copy > msg_data_left(msg)) copy = msg_data_left(msg); if (zc == 0) { 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_space; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { if (i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } merge = false; } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) { if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; skb_zcopy_downgrade_managed(skb); } copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, pfrag->offset, copy); if (err) goto do_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); page_ref_inc(pfrag->page); } pfrag->offset += copy; } else if (zc == MSG_ZEROCOPY) { /* First append to a fragless skb builds initial * pure zerocopy skb */ if (!skb->len) skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; if (!skb_zcopy_pure(skb)) { copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; } err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); goto new_segment; } if (err < 0) goto do_error; copy = err; } else if (zc == MSG_SPLICE_PAGES) { /* Splice in data if we can; copy if we can't. */ if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) { if (err == -EMSGSIZE) { tcp_mark_push(tp, skb); goto new_segment; } goto do_error; } copy = err; if (!(flags & MSG_NO_SHARED_FRAGS)) skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); } if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); copied += copy; if (!msg_data_left(msg)) { if (unlikely(flags & MSG_EOR)) TCP_SKB_CB(skb)->eor = 1; goto out; } if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { tcp_mark_push(tp, skb); __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); } else if (skb == tcp_send_head(sk)) tcp_push_one(sk, mss_now); continue; wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); tcp_remove_empty_skb(sk); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); err = sk_stream_wait_memory(sk, &timeo); if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); } out: if (copied) { tcp_tx_timestamp(sk, sockc.tsflags); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put(uarg); return copied + copied_syn; do_error: tcp_remove_empty_skb(sk); if (copied + copied_syn) goto out; out_err: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } return err; } EXPORT_SYMBOL_GPL(tcp_sendmsg_locked); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { int ret; lock_sock(sk); ret = tcp_sendmsg_locked(sk, msg, size); release_sock(sk); return ret; } EXPORT_SYMBOL(tcp_sendmsg); void tcp_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; if (!tcp_write_queue_tail(sk)) return; lock_sock(sk); mss_now = tcp_send_mss(sk, &size_goal, 0); tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); release_sock(sk); } EXPORT_SYMBOL_GPL(tcp_splice_eof); /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) */ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) { struct tcp_sock *tp = tcp_sk(sk); /* No URG data to read. */ if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || tp->urg_data == TCP_URG_READ) return -EINVAL; /* Yes this is right ! */ if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE)) return -ENOTCONN; if (tp->urg_data & TCP_URG_VALID) { int err = 0; char c = tp->urg_data; if (!(flags & MSG_PEEK)) WRITE_ONCE(tp->urg_data, TCP_URG_READ); /* Read urgent data. */ msg->msg_flags |= MSG_OOB; if (len > 0) { if (!(flags & MSG_TRUNC)) err = memcpy_to_msg(msg, &c, 1); len = 1; } else msg->msg_flags |= MSG_TRUNC; return err ? -EFAULT : len; } if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) return 0; /* Fixed the recv(..., MSG_OOB) behaviour. BSD docs and * the available implementations agree in this case: * this call should never block, independent of the * blocking state of the socket. * Mike <pall@rz.uni-karlsruhe.de> */ return -EAGAIN; } static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) { struct sk_buff *skb; int copied = 0, err = 0; /* XXX -- need to support SO_PEEK_OFF */ skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) return err; copied += skb->len; } skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) break; copied += skb->len; } return err ?: copied; } /* Clean up the receive buffer for full frames taken by the user, * then send an ACK if necessary. COPIED is the number of bytes * tcp_recvmsg has given to the user so far, it speeds up the * calculation of whether or not we must ACK for the sake of * a window update. */ void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); if (/* Once-per-two-segments ACK was not sent by tcp_input.c */ tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss || /* * If this read emptied read buffer, we send ACK, if * connection is not bidirectional, user drained * receive buffer and there was a small segment * in queue. */ (copied > 0 && ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !inet_csk_in_pingpong_mode(sk))) && !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = true; } /* We send an ACK if we can now advertise a non-zero window * which has been raised "significantly". * * Even if window raised up to infinity, do not send window open ACK * in states, where we will not receive more. It is useless. */ if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) { __u32 rcv_window_now = tcp_receive_window(tp); /* Optimize, __tcp_select_window() is not cheap. */ if (2*rcv_window_now <= tp->window_clamp) { __u32 new_window = __tcp_select_window(sk); /* Send ACK now, if this read freed lots of space * in our buffer. Certainly, new_window is new window. * We can advertise it now, if it is not less than current one. * "Lots" means "at least twice" here. */ if (new_window && new_window >= 2 * rcv_window_now) time_to_ack = true; } } if (time_to_ack) tcp_send_ack(sk); } void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); struct tcp_sock *tp = tcp_sk(sk); WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); __tcp_cleanup_rbuf(sk, copied); } static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); if (likely(skb->destructor == sock_rfree)) { sock_rfree(skb); skb->destructor = NULL; skb->sk = NULL; return skb_attempt_defer_free(skb); } __kfree_skb(skb); } struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) { *off = offset; return skb; } /* This looks weird, but this can happen if TCP collapsing * splitted a fat GRO packet, while we released socket lock * in skb_splice_bits() */ tcp_eat_recv_skb(sk, skb); } return NULL; } EXPORT_SYMBOL(tcp_recv_skb); /* * This routine provides an alternative to tcp_recvmsg() for routines * that would like to handle copying from skbuffs directly in 'sendfile' * fashion. * Note: * - It is assumed that the socket was locked by the caller. * - The routine does not block. * - At present, there is no support for reading OOB data * or for 'peeking' the socket using this routine * (although both would be easy to implement). */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor) { struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; u32 offset; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { if (offset < skb->len) { int used; size_t len; len = skb->len - offset; /* Stop reading if we hit a patch of urgent data */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - seq; if (urg_offset < len) len = urg_offset; if (!len) break; } used = recv_actor(desc, skb, offset, len); if (used <= 0) { if (!copied) copied = used; break; } if (WARN_ON_ONCE(used > len)) used = len; seq += used; copied += used; offset += used; /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ skb = tcp_recv_skb(sk, seq - 1, &offset); if (!skb) break; /* TCP coalescing might have appended data to the skb. * Try to splice more frags */ if (offset + 1 != skb->len) continue; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); if (!desc->count) break; WRITE_ONCE(tp->copied_seq, seq); } WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (copied > 0) { tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); } return copied; } EXPORT_SYMBOL(tcp_read_sock); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; __skb_unlink(skb, &sk->sk_receive_queue); WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); if (used < 0) { if (!copied) copied = used; break; } copied += used; if (tcp_flags & TCPHDR_FIN) break; } return copied; } EXPORT_SYMBOL(tcp_read_skb); void tcp_read_done(struct sock *sk, size_t len) { struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; struct sk_buff *skb; size_t left; u32 offset; if (sk->sk_state == TCP_LISTEN) return; left = len; while (left && (skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { int used; used = min_t(size_t, skb->len - offset, left); seq += used; left -= used; if (skb->len > offset + used) break; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); } WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (left != len) tcp_cleanup_rbuf(sk, len - left); } EXPORT_SYMBOL(tcp_read_done); int tcp_peek_len(struct socket *sock) { return tcp_inq(sock->sk); } EXPORT_SYMBOL(tcp_peek_len); /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ int tcp_set_rcvlowat(struct sock *sk, int val) { int space, cap; if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; val = min(val, cap); WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) return 0; space = tcp_space_from_win(sk, val); if (space > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, space); tcp_sk(sk)->window_clamp = val; } return 0; } EXPORT_SYMBOL(tcp_set_rcvlowat); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss) { if (skb->tstamp) tss->ts[0] = ktime_to_timespec64(skb->tstamp); else tss->ts[0] = (struct timespec64) {0}; if (skb_hwtstamps(skb)->hwtstamp) tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); else tss->ts[2] = (struct timespec64) {0}; } #ifdef CONFIG_MMU static const struct vm_operations_struct tcp_vm_ops = { }; int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { if (vma->vm_flags & (VM_WRITE | VM_EXEC)) return -EPERM; vm_flags_clear(vma, VM_MAYWRITE | VM_MAYEXEC); /* Instruct vm_insert_page() to not mmap_read_lock(mm) */ vm_flags_set(vma, VM_MIXEDMAP); vma->vm_ops = &tcp_vm_ops; return 0; } EXPORT_SYMBOL(tcp_mmap); static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, u32 *offset_frag) { skb_frag_t *frag; if (unlikely(offset_skb >= skb->len)) return NULL; offset_skb -= skb_headlen(skb); if ((int)offset_skb < 0 || skb_has_frag_list(skb)) return NULL; frag = skb_shinfo(skb)->frags; while (offset_skb) { if (skb_frag_size(frag) > offset_skb) { *offset_frag = offset_skb; return frag; } offset_skb -= skb_frag_size(frag); ++frag; } *offset_frag = 0; return frag; } static bool can_map_frag(const skb_frag_t *frag) { struct page *page; if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) return false; page = skb_frag_page(frag); if (PageCompound(page) || page->mapping) return false; return true; } static int find_next_mappable_frag(const skb_frag_t *frag, int remaining_in_skb) { int offset = 0; if (likely(can_map_frag(frag))) return 0; while (offset < remaining_in_skb && !can_map_frag(frag)) { offset += skb_frag_size(frag); ++frag; } return offset; } static void tcp_zerocopy_set_hint_for_skb(struct sock *sk, struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 offset) { u32 frag_offset, partial_frag_remainder = 0; int mappable_offset; skb_frag_t *frag; /* worst case: skip to next skb. try to improve on this case below */ zc->recv_skip_hint = skb->len - offset; /* Find the frag containing this offset (and how far into that frag) */ frag = skb_advance_to_frag(skb, offset, &frag_offset); if (!frag) return; if (frag_offset) { struct skb_shared_info *info = skb_shinfo(skb); /* We read part of the last frag, must recvmsg() rest of skb. */ if (frag == &info->frags[info->nr_frags - 1]) return; /* Else, we must at least read the remainder in this frag. */ partial_frag_remainder = skb_frag_size(frag) - frag_offset; zc->recv_skip_hint -= partial_frag_remainder; ++frag; } /* partial_frag_remainder: If part way through a frag, must read rest. * mappable_offset: Bytes till next mappable frag, *not* counting bytes * in partial_frag_remainder. */ mappable_offset = find_next_mappable_frag(frag, zc->recv_skip_hint); zc->recv_skip_hint = mappable_offset + partial_frag_remainder; } static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags); static int receive_fallback_to_copy(struct sock *sk, struct tcp_zerocopy_receive *zc, int inq, struct scm_timestamping_internal *tss) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; int err; zc->length = 0; zc->recv_skip_hint = 0; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_ubuf(ITER_DEST, (void __user *)copy_address, inq, &msg.msg_iter); if (err) return err; err = tcp_recvmsg_locked(sk, &msg, inq, MSG_DONTWAIT, tss, &zc->msg_flags); if (err < 0) return err; zc->copybuf_len = err; if (likely(zc->copybuf_len)) { struct sk_buff *skb; u32 offset; skb = tcp_recv_skb(sk, tcp_sk(sk)->copied_seq, &offset); if (skb) tcp_zerocopy_set_hint_for_skb(sk, zc, skb, offset); } return 0; } static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; int err; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_ubuf(ITER_DEST, (void __user *)copy_address, copylen, &msg.msg_iter); if (err) return err; err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); if (err) return err; zc->recv_skip_hint -= copylen; *offset += copylen; *seq += copylen; return (__s32)copylen; } static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc, struct sock *sk, struct sk_buff *skb, u32 *seq, s32 copybuf_len, struct scm_timestamping_internal *tss) { u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); if (!copylen) return 0; /* skb is null if inq < PAGE_SIZE. */ if (skb) { offset = *seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, *seq, &offset); if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } } zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, seq); return zc->copybuf_len < 0 ? 0 : copylen; } static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, struct page **pending_pages, unsigned long pages_remaining, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map, int err) { /* At least one page did not map. Try zapping if we skipped earlier. */ if (err == -EBUSY && zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) { u32 maybe_zap_len; maybe_zap_len = total_bytes_to_map - /* All bytes to map */ *length + /* Mapped or pending */ (pages_remaining * PAGE_SIZE); /* Failed map. */ zap_page_range_single(vma, *address, maybe_zap_len, NULL); err = 0; } if (!err) { unsigned long leftover_pages = pages_remaining; int bytes_mapped; /* We called zap_page_range_single, try to reinsert. */ err = vm_insert_pages(vma, *address, pending_pages, &pages_remaining); bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining); *seq += bytes_mapped; *address += bytes_mapped; } if (err) { /* Either we were unable to zap, OR we zapped, retried an * insert, and still had an issue. Either ways, pages_remaining * is the number of pages we were unable to map, and we unroll * some state we speculatively touched before. */ const int bytes_not_mapped = PAGE_SIZE * pages_remaining; *length -= bytes_not_mapped; zc->recv_skip_hint += bytes_not_mapped; } return err; } static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, unsigned int pages_to_map, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map) { unsigned long pages_remaining = pages_to_map; unsigned int pages_mapped; unsigned int bytes_mapped; int err; err = vm_insert_pages(vma, *address, pages, &pages_remaining); pages_mapped = pages_to_map - (unsigned int)pages_remaining; bytes_mapped = PAGE_SIZE * pages_mapped; /* Even if vm_insert_pages fails, it may have partially succeeded in * mapping (some but not all of the pages). */ *seq += bytes_mapped; *address += bytes_mapped; if (likely(!err)) return 0; /* Error: maybe zap and retry + rollback state for failed inserts. */ return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped, pages_remaining, address, length, seq, zc, total_bytes_to_map, err); } #define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) static void tcp_zc_finalize_rx_tstamp(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { unsigned long msg_control_addr; struct msghdr cmsg_dummy; msg_control_addr = (unsigned long)zc->msg_control; cmsg_dummy.msg_control_user = (void __user *)msg_control_addr; cmsg_dummy.msg_controllen = (__kernel_size_t)zc->msg_controllen; cmsg_dummy.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; cmsg_dummy.msg_control_is_user = true; zc->msg_flags = 0; if (zc->msg_control == msg_control_addr && zc->msg_controllen == cmsg_dummy.msg_controllen) { tcp_recv_timestamp(&cmsg_dummy, sk, tss); zc->msg_control = (__u64) ((uintptr_t)cmsg_dummy.msg_control_user); zc->msg_controllen = (__u64)cmsg_dummy.msg_controllen; zc->msg_flags = (__u32)cmsg_dummy.msg_flags; } } static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm, unsigned long address, bool *mmap_locked) { struct vm_area_struct *vma = lock_vma_under_rcu(mm, address); if (vma) { if (vma->vm_ops != &tcp_vm_ops) { vma_end_read(vma); return NULL; } *mmap_locked = false; return vma; } mmap_read_lock(mm); vma = vma_lookup(mm, address); if (!vma || vma->vm_ops != &tcp_vm_ops) { mmap_read_unlock(mm); return NULL; } *mmap_locked = true; return vma; } #define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE]; s32 copybuf_len = zc->copybuf_len; struct tcp_sock *tp = tcp_sk(sk); const skb_frag_t *frags = NULL; unsigned int pages_to_map = 0; struct vm_area_struct *vma; struct sk_buff *skb = NULL; u32 seq = tp->copied_seq; u32 total_bytes_to_map; int inq = tcp_inq(sk); bool mmap_locked; int ret; zc->copybuf_len = 0; zc->msg_flags = 0; if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; sock_rps_record_flow(sk); if (inq && inq <= copybuf_len) return receive_fallback_to_copy(sk, zc, inq, tss); if (inq < PAGE_SIZE) { zc->length = 0; zc->recv_skip_hint = inq; if (!inq && sock_flag(sk, SOCK_DONE)) return -EIO; return 0; } vma = find_tcp_vma(current->mm, address, &mmap_locked); if (!vma) return -EINVAL; vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); avail_len = min_t(u32, vma_len, inq); total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1); if (total_bytes_to_map) { if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT)) zap_page_range_single(vma, address, total_bytes_to_map, NULL); zc->length = total_bytes_to_map; zc->recv_skip_hint = 0; } else { zc->length = avail_len; zc->recv_skip_hint = avail_len; } ret = 0; while (length + PAGE_SIZE <= zc->length) { int mappable_offset; struct page *page; if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; if (skb) { if (zc->recv_skip_hint > 0) break; skb = skb->next; offset = seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, seq, &offset); } if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } zc->recv_skip_hint = skb->len - offset; frags = skb_advance_to_frag(skb, offset, &offset_frag); if (!frags || offset_frag) break; } mappable_offset = find_next_mappable_frag(frags, zc->recv_skip_hint); if (mappable_offset) { zc->recv_skip_hint = mappable_offset; break; } page = skb_frag_page(frags); prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; zc->recv_skip_hint -= PAGE_SIZE; frags++; if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE || zc->recv_skip_hint < PAGE_SIZE) { /* Either full batch, or we're about to go to next skb * (and we cannot unroll failed ops across skbs). */ ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); if (ret) goto out; pages_to_map = 0; } } if (pages_to_map) { ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); } out: if (mmap_locked) mmap_read_unlock(current->mm); else vma_end_read(vma); /* Try to copy straggler data. */ if (!ret) copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss); if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, length + copylen); ret = 0; if (length == zc->length) zc->recv_skip_hint = 0; } else { if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE)) ret = -EIO; } zc->length = length; return ret; } #endif /* Similar to __sock_recv_timestamp, but does not require an skb */ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_timespec kts = { .tv_sec = tss->ts[0].tv_sec, .tv_nsec = tss->ts[0].tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(kts), &kts); } else { struct __kernel_old_timespec ts_old = { .tv_sec = tss->ts[0].tv_sec, .tv_nsec = tss->ts[0].tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts_old), &ts_old); } } else { if (new_tstamp) { struct __kernel_sock_timeval stv = { .tv_sec = tss->ts[0].tv_sec, .tv_usec = tss->ts[0].tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(stv), &stv); } else { struct __kernel_old_timeval tv = { .tv_sec = tss->ts[0].tv_sec, .tv_usec = tss->ts[0].tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } } if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE) has_timestamping = true; else tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE) has_timestamping = true; else tss->ts[2] = (struct timespec64) {0}; } if (has_timestamping) { tss->ts[1] = (struct timespec64) {0}; if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, tss); else put_cmsg_scm_timestamping(msg, tss); } } static int tcp_inq_hint(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u32 copied_seq = READ_ONCE(tp->copied_seq); u32 rcv_nxt = READ_ONCE(tp->rcv_nxt); int inq; inq = rcv_nxt - copied_seq; if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) { lock_sock(sk); inq = tp->rcv_nxt - tp->copied_seq; release_sock(sk); } /* After receiving a FIN, tell the user-space to continue reading * by returning a non-zero inq. */ if (inq == 0 && sock_flag(sk, SOCK_DONE)) inq = 1; return inq; } /* * This routine copies from a sock struct into the user buffer. * * Technical note: in 2.3 we work on _locked_ socket, so that * tricks with *seq access order and skb->users are not required. * Probably, code can be easily improved even more. */ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); int copied = 0; u32 peek_seq; u32 *seq; unsigned long used; int err; int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; u32 urg_hole = 0; err = -ENOTCONN; if (sk->sk_state == TCP_LISTEN) goto out; if (tp->recvmsg_inq) { *cmsg_flags = TCP_CMSG_INQ; msg->msg_get_inq = 1; } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); /* Urgent data needs to be handled specially. */ if (flags & MSG_OOB) goto recv_urg; if (unlikely(tp->repair)) { err = -EPERM; if (!(flags & MSG_PEEK)) goto out; if (tp->repair_queue == TCP_SEND_QUEUE) goto recv_sndq; err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out; /* 'common' recv queue MSG_PEEK-ing */ } seq = &tp->copied_seq; if (flags & MSG_PEEK) { peek_seq = tp->copied_seq; seq = &peek_seq; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); do { u32 offset; /* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */ if (unlikely(tp->urg_data) && tp->urg_seq == *seq) { if (copied) break; if (signal_pending(current)) { copied = timeo ? sock_intr_errno(timeo) : -EAGAIN; break; } } /* Next get a buffer. */ last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { last = skb; /* Now that we have two receive queues this * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags)) break; offset = *seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len) goto found_ok_skb; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; WARN(!(flags & MSG_PEEK), "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { if (!timeo || sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } else { if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* This occurs when user tries to read * from never connected socket. */ copied = -ENOTCONN; break; } if (!timeo) { copied = -EAGAIN; break; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); break; } } if (copied >= target) { /* Do not sleep, just process backlog. */ __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); err = sk_wait_data(sk, &timeo, last); if (err < 0) { err = copied ? : err; goto out; } } if ((flags & MSG_PEEK) && (peek_seq - copied - urg_hole != tp->copied_seq)) { net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); peek_seq = tp->copied_seq; } continue; found_ok_skb: /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) used = len; /* Do we have urgent data here? */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - *seq; if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; if (!used) goto skip_copy; } } else used = urg_offset; } } if (!(flags & MSG_TRUNC)) { err = skb_copy_datagram_msg(skb, offset, msg, used); if (err) { /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } } WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; tcp_rcv_space_adjust(sk); skip_copy: if (unlikely(tp->urg_data) && after(tp->copied_seq, tp->urg_seq)) { WRITE_ONCE(tp->urg_data, 0); tcp_fast_path_check(sk); } if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); *cmsg_flags |= TCP_CMSG_TS; } if (used + offset < skb->len) continue; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); continue; found_fin_ok: /* Process the FIN. */ WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); break; } while (len > 0); /* According to UNIX98, msg_name/msg_namelen are ignored * on connected socket. I was just happy when found this 8) --ANK */ /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); return copied; out: return err; recv_urg: err = tcp_recv_urg(sk, msg, len, flags); goto out; recv_sndq: err = tcp_peek_sndq(sk, msg, len); goto out; } int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { int cmsg_flags = 0, ret; struct scm_timestamping_internal tss; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && sk->sk_state == TCP_ESTABLISHED) sk_busy_loop(sk, flags & MSG_DONTWAIT); lock_sock(sk); ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags); release_sock(sk); if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); if (msg->msg_get_inq) { msg->msg_inq = tcp_inq_hint(sk); if (cmsg_flags & TCP_CMSG_INQ) put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(msg->msg_inq), &msg->msg_inq); } } return ret; } EXPORT_SYMBOL(tcp_recvmsg); void tcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; /* We defined a new enum for TCP states that are exported in BPF * so as not force the internal TCP states to be frozen. The * following checks will detect if an internal state value ever * differs from the BPF value. If this ever happens, then we will * need to remap the internal value to the BPF value before calling * tcp_call_bpf_2arg. */ BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED); BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT); BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2); BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT); BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE); BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT); BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK); BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE); BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); /* bpf uapi header bpf.h defines an anonymous enum with values * BPF_TCP_* used by bpf programs. Currently gcc built vmlinux * is able to emit this enum in DWARF due to the above BUILD_BUG_ON. * But clang built vmlinux does not have this enum in DWARF * since clang removes the above code before generating IR/debuginfo. * Let us explicitly emit the type debuginfo to ensure the * above-mentioned anonymous enum in the vmlinux DWARF and hence BTF * regardless of which compiler is used. */ BTF_TYPE_EMIT_ENUM(BPF_TCP_ESTABLISHED); if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG)) tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state); switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE: if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); if (inet_csk(sk)->icsk_bind_hash && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); fallthrough; default: if (oldstate == TCP_ESTABLISHED) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); } /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ inet_sk_state_store(sk, state); } EXPORT_SYMBOL_GPL(tcp_set_state); /* * State processing on a close. This implements the state shift for * sending our FIN frame. Note that we only send a FIN for some * states. A shutdown() may have already sent the FIN, or we may be * closed. */ static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_SYN_SENT] = TCP_CLOSE, [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, [TCP_TIME_WAIT] = TCP_CLOSE, [TCP_CLOSE] = TCP_CLOSE, [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, [TCP_LAST_ACK] = TCP_LAST_ACK, [TCP_LISTEN] = TCP_CLOSE, [TCP_CLOSING] = TCP_CLOSING, [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int tcp_close_state(struct sock *sk) { int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; tcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } /* * Shutdown the sending side of a connection. Much like close except * that we don't receive shut down or sock_set_flag(sk, SOCK_DEAD). */ void tcp_shutdown(struct sock *sk, int how) { /* We need to grab some memory, and put together a FIN, * and then put it into the queue to be sent. * Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92. */ if (!(how & SEND_SHUTDOWN)) return; /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); } } EXPORT_SYMBOL(tcp_shutdown); int tcp_orphan_count_sum(void) { int i, total = 0; for_each_possible_cpu(i) total += per_cpu(tcp_orphan_count, i); return max(total, 0); } static int tcp_orphan_cache; static struct timer_list tcp_orphan_timer; #define TCP_ORPHAN_TIMER_PERIOD msecs_to_jiffies(100) static void tcp_orphan_update(struct timer_list *unused) { WRITE_ONCE(tcp_orphan_cache, tcp_orphan_count_sum()); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); } static bool tcp_too_many_orphans(int shift) { return READ_ONCE(tcp_orphan_cache) << shift > READ_ONCE(sysctl_tcp_max_orphans); } bool tcp_check_oom(struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; too_many_orphans = tcp_too_many_orphans(shift); out_of_socket_memory = tcp_out_of_memory(sk); if (too_many_orphans) net_info_ratelimited("too many orphaned sockets\n"); if (out_of_socket_memory) net_info_ratelimited("out of memory -- consider tuning tcp_mem\n"); return too_many_orphans || out_of_socket_memory; } void __tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; int data_was_unread = 0; int state; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); /* Special case. */ inet_csk_listen_stop(sk); goto adjudge_to_death; } /* We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the * reader process may not have drained the data yet! */ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) len--; data_was_unread += len; __kfree_skb(skb); } /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */ if (sk->sk_state == TCP_CLOSE) goto adjudge_to_death; /* As outlined in RFC 2525, section 2.17, we send a RST here because * data was lost. To witness the awful effects of the old behavior of * always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk * GET in an FTP client, suspend the process, wait for the client to * advertise a zero window, then kill -9 the FTP client, wheee... * Note: timeout is always zero in such a case. */ if (unlikely(tcp_sk(sk)->repair)) { sk->sk_prot->disconnect(sk, 0); } else if (data_was_unread) { /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, sk->sk_allocation); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); } else if (tcp_close_state(sk)) { /* We FIN if the application ate all the data before * zapping the connection. */ /* RED-PEN. Formally speaking, we have broken TCP state * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), * rather than queued out of window. Purists blame. * * F.e. "RFC state" is ESTABLISHED, * if Linux state is FIN-WAIT-1, but FIN is still not sent. * * The visible declinations are that sometimes * we enter time-wait state, when it is not required really * (harmless), do not send active resets, when they are * required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when * they look as CLOSING or LAST_ACK for Linux) * Probably, I missed some more holelets. * --ANK * XXX (TFO) - To start off we don't support SYN+ACK+FIN * in a single packet! (May consider it later but will * probably need API support or TCP_CORK SYN-ACK until * data is written and socket is closed.) */ tcp_send_fin(sk); } sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); local_bh_disable(); bh_lock_sock(sk); /* remove backlog if any, without releasing ownership. */ __release_sock(sk); this_cpu_inc(tcp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) goto out; /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. * * Nope, it was not mistake. It is really desired behaviour * f.e. on http servers, when such sockets are useless, but * consume significant resources. Let's do it with special * linger2 option. --ANK */ if (sk->sk_state == TCP_FIN_WAIT2) { struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { const int tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto out; } } } if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_set_state(sk, TCP_CLOSE); } } if (sk->sk_state == TCP_CLOSE) { struct request_sock *req; req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. */ if (req) reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); } /* Otherwise, socket is reprieved until protocol close. */ out: bh_unlock_sock(sk); local_bh_enable(); } void tcp_close(struct sock *sk, long timeout) { lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); /* These states need RST on ABORT according to RFC793 */ static inline bool tcp_need_reset(int state) { return (1 << state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); /* Since we are deleting whole queue, no need to * list_del(&skb->tcp_tsorted_anchor) */ tcp_rtx_queue_unlink(skb, sk); tcp_wmem_free_skb(sk, skb); } } void tcp_write_queue_purge(struct sock *sk) { struct sk_buff *skb; tcp_chrono_stop(sk, TCP_CHRONO_BUSY); while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { tcp_skb_tsorted_anchor_cleanup(skb); tcp_wmem_free_skb(sk, skb); } tcp_rtx_queue_purge(sk); INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); /* ABORT function of RFC793 */ if (old_state == TCP_LISTEN) { inet_csk_listen_stop(sk); } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state) || (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ tcp_send_active_reset(sk, gfp_any()); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); WRITE_ONCE(tp->urg_data, 0); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; inet_bhash2_reset_saddr(sk); WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; seq = tp->write_seq + tp->max_window + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_probes_tstamp = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_snd_cwnd_set(tp, TCP_INIT_CWND); tp->snd_cwnd_cnt = 0; tp->is_cwnd_limited = 0; tp->max_packets_out = 0; tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; if (icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); icsk->icsk_ca_initialized = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); tp->total_retrans = 0; inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL)); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; tp->segs_out = 0; tp->bytes_sent = 0; tp->bytes_acked = 0; tp->bytes_received = 0; tp->bytes_retrans = 0; tp->data_segs_in = 0; tp->data_segs_out = 0; tp->duplicate_sack[0].start_seq = 0; tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; tp->reord_seen = 0; tp->retrans_out = 0; tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; tp->rack.mstamp = 0; tp->rack.advanced = 0; tp->rack.reo_wnd_steps = 1; tp->rack.last_delivered = 0; tp->rack.reo_wnd_persist = 0; tp->rack.dsack_seen = 0; tp->syn_data_acked = 0; tp->rx_opt.saw_tstamp = 0; tp->rx_opt.dsack = 0; tp->rx_opt.num_sacks = 0; tp->rcv_ooopack = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; } sk_error_report(sk); return 0; } EXPORT_SYMBOL(tcp_disconnect); static inline bool tcp_can_repair_sock(const struct sock *sk) { return sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && (sk->sk_state != TCP_LISTEN); } static int tcp_repair_set_window(struct tcp_sock *tp, sockptr_t optbuf, int len) { struct tcp_repair_window opt; if (!tp->repair) return -EPERM; if (len != sizeof(opt)) return -EINVAL; if (copy_from_sockptr(&opt, optbuf, sizeof(opt))) return -EFAULT; if (opt.max_window < opt.snd_wnd) return -EINVAL; if (after(opt.snd_wl1, tp->rcv_nxt + opt.rcv_wnd)) return -EINVAL; if (after(opt.rcv_wup, tp->rcv_nxt)) return -EINVAL; tp->snd_wl1 = opt.snd_wl1; tp->snd_wnd = opt.snd_wnd; tp->max_window = opt.max_window; tp->rcv_wnd = opt.rcv_wnd; tp->rcv_wup = opt.rcv_wup; return 0; } static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_repair_opt opt; size_t offset = 0; while (len >= sizeof(opt)) { if (copy_from_sockptr_offset(&opt, optbuf, offset, sizeof(opt))) return -EFAULT; offset += sizeof(opt); len -= sizeof(opt); switch (opt.opt_code) { case TCPOPT_MSS: tp->rx_opt.mss_clamp = opt.opt_val; tcp_mtup_init(sk); break; case TCPOPT_WINDOW: { u16 snd_wscale = opt.opt_val & 0xFFFF; u16 rcv_wscale = opt.opt_val >> 16; if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE) return -EFBIG; tp->rx_opt.snd_wscale = snd_wscale; tp->rx_opt.rcv_wscale = rcv_wscale; tp->rx_opt.wscale_ok = 1; } break; case TCPOPT_SACK_PERM: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.sack_ok |= TCP_SACK_SEEN; break; case TCPOPT_TIMESTAMP: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.tstamp_ok = 1; break; } } return 0; } DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); EXPORT_SYMBOL(tcp_tx_delay_enabled); static void tcp_enable_tx_delay(void) { if (!static_branch_unlikely(&tcp_tx_delay_enabled)) { static int __tcp_tx_delay_enabled = 0; if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) { static_branch_enable(&tcp_tx_delay_enabled); pr_info("TCP_TX_DELAY enabled\n"); } } } /* When set indicates to always queue non-full frames. Later the user clears * this option and we transmit any pending partial frames in the queue. This is * meant to be used alongside sendfile() to get properly filled frames when the * user (for example) must write out headers with a write() call first and then * use sendfile to send out the data parts. * * TCP_CORK can be set together with TCP_NODELAY and it is stronger than * TCP_NODELAY. */ void __tcp_sock_set_cork(struct sock *sk, bool on) { struct tcp_sock *tp = tcp_sk(sk); if (on) { tp->nonagle |= TCP_NAGLE_CORK; } else { tp->nonagle &= ~TCP_NAGLE_CORK; if (tp->nonagle & TCP_NAGLE_OFF) tp->nonagle |= TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } } void tcp_sock_set_cork(struct sock *sk, bool on) { lock_sock(sk); __tcp_sock_set_cork(sk, on); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_cork); /* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is * remembered, but it is not activated until cork is cleared. * * However, when TCP_NODELAY is set we make an explicit push, which overrides * even TCP_CORK for currently queued segments. */ void __tcp_sock_set_nodelay(struct sock *sk, bool on) { if (on) { tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } else { tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF; } } void tcp_sock_set_nodelay(struct sock *sk) { lock_sock(sk); __tcp_sock_set_nodelay(sk, true); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_nodelay); static void __tcp_sock_set_quickack(struct sock *sk, int val) { if (!val) { inet_csk_enter_pingpong_mode(sk); return; } inet_csk_exit_pingpong_mode(sk); if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && inet_csk_ack_scheduled(sk)) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_PUSHED; tcp_cleanup_rbuf(sk, 1); if (!(val & 1)) inet_csk_enter_pingpong_mode(sk); } } void tcp_sock_set_quickack(struct sock *sk, int val) { lock_sock(sk); __tcp_sock_set_quickack(sk, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_quickack); int tcp_sock_set_syncnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_SYNCNT) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_syncnt); int tcp_sock_set_user_timeout(struct sock *sk, int val) { /* Cap the max time in ms TCP will retry or probe the window * before giving up and aborting (ETIMEDOUT) a connection. */ if (val < 0) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_user_timeout); int tcp_sock_set_keepidle_locked(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; /* Paired with WRITE_ONCE() in keepalive_time_when() */ WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); if (tp->keepalive_time > elapsed) elapsed = tp->keepalive_time - elapsed; else elapsed = 0; inet_csk_reset_keepalive_timer(sk, elapsed); } return 0; } int tcp_sock_set_keepidle(struct sock *sk, int val) { int err; lock_sock(sk); err = tcp_sock_set_keepidle_locked(sk, val); release_sock(sk); return err; } EXPORT_SYMBOL(tcp_sock_set_keepidle); int tcp_sock_set_keepintvl(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPINTVL) return -EINVAL; WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepintvl); int tcp_sock_set_keepcnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPCNT) return -EINVAL; /* Paired with READ_ONCE() in keepalive_probes() */ WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepcnt); int tcp_set_window_clamp(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; tp->window_clamp = 0; } else { u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? SOCK_MIN_RCVBUF / 2 : val; if (new_window_clamp == old_window_clamp) return 0; tp->window_clamp = new_window_clamp; if (new_window_clamp < old_window_clamp) { /* need to apply the reserved mem provisioning only * when shrinking the window clamp */ __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); } else { new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); tp->rcv_ssthresh = max(new_rcv_ssthresh, tp->rcv_ssthresh); } } return 0; } /* * Socket option code for TCP. */ int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); int val; int err = 0; /* These are data/string values, all the others are ints */ switch (optname) { case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_CA_NAME_MAX-1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_congestion_control(sk, name, !has_current_bpf_ctx(), sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); sockopt_release_sock(sk); return err; } case TCP_ULP: { char name[TCP_ULP_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_ULP_NAME_MAX - 1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_ulp(sk, name); sockopt_release_sock(sk); return err; } case TCP_FASTOPEN_KEY: { __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; __u8 *backup_key = NULL; /* Allow a backup key as well to facilitate key rotation * First key is the active one. */ if (optlen != TCP_FASTOPEN_KEY_LENGTH && optlen != TCP_FASTOPEN_KEY_BUF_LENGTH) return -EINVAL; if (copy_from_sockptr(key, optval, optlen)) return -EFAULT; if (optlen == TCP_FASTOPEN_KEY_BUF_LENGTH) backup_key = key + TCP_FASTOPEN_KEY_LENGTH; return tcp_fastopen_reset_cipher(net, sk, key, backup_key); } default: /* fallthru */ break; } if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; /* Handle options that can be set without locking the socket. */ switch (optname) { case TCP_SYNCNT: return tcp_sock_set_syncnt(sk, val); case TCP_USER_TIMEOUT: return tcp_sock_set_user_timeout(sk, val); case TCP_KEEPINTVL: return tcp_sock_set_keepintvl(sk, val); case TCP_KEEPCNT: return tcp_sock_set_keepcnt(sk, val); case TCP_LINGER2: if (val < 0) WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else WRITE_ONCE(tp->linger2, val * HZ); return 0; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ)); return 0; } sockopt_lock_sock(sk); switch (optname) { case TCP_MAXSEG: /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { err = -EINVAL; break; } tp->rx_opt.user_mss = val; break; case TCP_NODELAY: __tcp_sock_set_nodelay(sk, val); break; case TCP_THIN_LINEAR_TIMEOUTS: if (val < 0 || val > 1) err = -EINVAL; else tp->thin_lto = val; break; case TCP_THIN_DUPACK: if (val < 0 || val > 1) err = -EINVAL; break; case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; else if (val == TCP_REPAIR_ON) { tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; } else if (val == TCP_REPAIR_OFF) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; tcp_send_window_probe(sk); } else if (val == TCP_REPAIR_OFF_NO_WP) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; } else err = -EINVAL; break; case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; break; case TCP_QUEUE_SEQ: if (sk->sk_state != TCP_CLOSE) { err = -EPERM; } else if (tp->repair_queue == TCP_SEND_QUEUE) { if (!tcp_rtx_queue_empty(sk)) err = -EPERM; else WRITE_ONCE(tp->write_seq, val); } else if (tp->repair_queue == TCP_RECV_QUEUE) { if (tp->rcv_nxt != tp->copied_seq) { err = -EPERM; } else { WRITE_ONCE(tp->rcv_nxt, val); WRITE_ONCE(tp->copied_seq, val); } } else { err = -EINVAL; } break; case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; break; case TCP_CORK: __tcp_sock_set_cork(sk, val); break; case TCP_KEEPIDLE: err = tcp_sock_set_keepidle_locked(sk, val); break; case TCP_SAVE_SYN: /* 0: disable, 1: enable, 2: start from ether_header */ if (val < 0 || val > 2) err = -EINVAL; else tp->save_syn = val; break; case TCP_WINDOW_CLAMP: err = tcp_set_window_clamp(sk, val); break; case TCP_QUICKACK: __tcp_sock_set_quickack(sk, val); break; case TCP_AO_REPAIR: if (!tcp_can_repair_sock(sk)) { err = -EPERM; break; } err = tcp_ao_set_repair(sk, optval, optlen); break; #ifdef CONFIG_TCP_AO case TCP_AO_ADD_KEY: case TCP_AO_DEL_KEY: case TCP_AO_INFO: { /* If this is the first TCP-AO setsockopt() on the socket, * sk_state has to be LISTEN or CLOSE. Allow TCP_REPAIR * in any state. */ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) goto ao_parse; if (rcu_dereference_protected(tcp_sk(sk)->ao_info, lockdep_sock_is_held(sk))) goto ao_parse; if (tp->repair) goto ao_parse; err = -EISCONN; break; ao_parse: err = tp->af_specific->ao_parse(sk, optname, optval, optlen); break; } #endif #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { tcp_fastopen_init_key_once(net); fastopen_queue_tune(sk, val); } else { err = -EINVAL; } break; case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else err = -EINVAL; } else { err = -EOPNOTSUPP; } break; case TCP_FASTOPEN_NO_COOKIE: if (val > 1 || val < 0) err = -EINVAL; else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) err = -EINVAL; else tp->fastopen_no_cookie = val; break; case TCP_TIMESTAMP: if (!tp->repair) { err = -EPERM; break; } /* val is an opaque field, * and low order bit contains usec_ts enable bit. * Its a best effort, and we do not care if user makes an error. */ tp->tcp_usec_ts = val & 1; WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts)); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: if (val > 1 || val < 0) err = -EINVAL; else tp->recvmsg_inq = val; break; case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; break; } sockopt_release_sock(sk); return err; } int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { const struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->setsockopt(sk, level, optname, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(tcp_setsockopt); static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, struct tcp_info *info) { u64 stats[__TCP_CHRONO_MAX], total = 0; enum tcp_chrono i; for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { stats[i] = tp->chrono_stat[i - 1]; if (i == tp->chrono_type) stats[i] += tcp_jiffies32 - tp->chrono_start; stats[i] *= USEC_PER_SEC / HZ; total += stats[i]; } info->tcpi_busy_time = total; info->tcpi_rwnd_limited = stats[TCP_CHRONO_RWND_LIMITED]; info->tcpi_sndbuf_limited = stats[TCP_CHRONO_SNDBUF_LIMITED]; } /* Return information about state of tcp endpoint in API format. */ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); unsigned long rate; u32 now; u64 rate64; bool slow; memset(info, 0, sizeof(*info)); if (sk->sk_type != SOCK_STREAM) return; info->tcpi_state = inet_sk_state_load(sk); /* Report meaningful fields for all TCP states, including listeners */ rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_pacing_rate = rate64; rate = READ_ONCE(sk->sk_max_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_max_pacing_rate = rate64; info->tcpi_reordering = tp->reordering; info->tcpi_snd_cwnd = tcp_snd_cwnd(tp); if (info->tcpi_state == TCP_LISTEN) { /* listeners aliased fields : * tcpi_unacked -> Number of children ready for accept() * tcpi_sacked -> max backlog */ info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog); info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog); return; } slow = lock_sock_fast(sk); info->tcpi_ca_state = icsk->icsk_ca_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; info->tcpi_backoff = icsk->icsk_backoff; if (tp->rx_opt.tstamp_ok) info->tcpi_options |= TCPI_OPT_TIMESTAMPS; if (tcp_is_sack(tp)) info->tcpi_options |= TCPI_OPT_SACK; if (tp->rx_opt.wscale_ok) { info->tcpi_options |= TCPI_OPT_WSCALE; info->tcpi_snd_wscale = tp->rx_opt.snd_wscale; info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale; } if (tp->ecn_flags & TCP_ECN_OK) info->tcpi_options |= TCPI_OPT_ECN; if (tp->ecn_flags & TCP_ECN_SEEN) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; if (tp->tcp_usec_ts) info->tcpi_options |= TCPI_OPT_USEC_TS; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, tcp_delack_max(sk))); info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; info->tcpi_unacked = tp->packets_out; info->tcpi_sacked = tp->sacked_out; info->tcpi_lost = tp->lost_out; info->tcpi_retrans = tp->retrans_out; now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; info->tcpi_rtt = tp->srtt_us >> 3; info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_advmss = tp->advmss; info->tcpi_rcv_rtt = tp->rcv_rtt_est.rtt_us >> 3; info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; info->tcpi_bytes_acked = tp->bytes_acked; info->tcpi_bytes_received = tp->bytes_received; info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt); tcp_get_info_chrono_stats(tp, info); info->tcpi_segs_out = tp->segs_out; /* segs_in and data_segs_in can be updated from tcp_segs_in() from BH */ info->tcpi_segs_in = READ_ONCE(tp->segs_in); info->tcpi_data_segs_in = READ_ONCE(tp->data_segs_in); info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_out = tp->data_segs_out; info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; rate64 = tcp_compute_delivery_rate(tp); if (rate64) info->tcpi_delivery_rate = rate64; info->tcpi_delivered = tp->delivered; info->tcpi_delivered_ce = tp->delivered_ce; info->tcpi_bytes_sent = tp->bytes_sent; info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_dsack_dups = tp->dsack_dups; info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; info->tcpi_rcv_wnd = tp->rcv_wnd; info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; info->tcpi_total_rto = tp->total_rto; info->tcpi_total_rto_recoveries = tp->total_rto_recoveries; info->tcpi_total_rto_time = tp->total_rto_time; if (tp->rto_stamp) info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); static size_t tcp_opt_stats_get_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */ nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */ nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */ nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */ 0; } /* Returns TTL or hop limit of an incoming packet from skb. */ static u8 tcp_skb_ttl_or_hop_limit(const struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return ip_hdr(skb)->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) return ipv6_hdr(skb)->hop_limit; else return 0; } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb, const struct sk_buff *ack_skb) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; struct tcp_info info; unsigned long rate; u64 rate64; stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC); if (!stats) return NULL; tcp_get_info_chrono_stats(tp, &info); nla_put_u64_64bit(stats, TCP_NLA_BUSY, info.tcpi_busy_time, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED, info.tcpi_rwnd_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED, info.tcpi_sndbuf_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT, tp->data_segs_out, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS, tp->total_retrans, TCP_NLA_PAD); rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; nla_put_u64_64bit(stats, TCP_NLA_PACING_RATE, rate64, TCP_NLA_PAD); rate64 = tcp_compute_delivery_rate(tp); nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp)); nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering); nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp)); nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, max_t(int, 0, tp->write_seq - tp->snd_nxt)); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, TCP_NLA_PAD); if (ack_skb) nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash); return stats; } int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); int val, len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, sizeof(int)); if (len < 0) return -EINVAL; switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; if (tp->rx_opt.user_mss && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; break; case TCP_NODELAY: val = !!(tp->nonagle&TCP_NAGLE_OFF); break; case TCP_CORK: val = !!(tp->nonagle&TCP_NAGLE_CORK); break; case TCP_KEEPIDLE: val = keepalive_time_when(tp) / HZ; break; case TCP_KEEPINTVL: val = keepalive_intvl_when(tp) / HZ; break; case TCP_KEEPCNT: val = keepalive_probes(tp); break; case TCP_SYNCNT: val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; break; case TCP_INFO: { struct tcp_info info; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; tcp_get_info(sk, &info); len = min_t(unsigned int, len, sizeof(info)); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_CC_INFO: { const struct tcp_congestion_ops *ca_ops; union tcp_cc_info info; size_t sz = 0; int attr; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; ca_ops = icsk->icsk_ca_ops; if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_QUICKACK: val = !inet_csk_in_pingpong_mode(sk); break; case TCP_CONGESTION: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_ULP_NAME_MAX); if (!icsk->icsk_ulp_ops) { len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ulp_ops->name, len)) return -EFAULT; return 0; case TCP_FASTOPEN_KEY: { u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)]; unsigned int key_len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; key_len = tcp_fastopen_get_cipher(net, icsk, key) * TCP_FASTOPEN_KEY_LENGTH; len = min_t(unsigned int, len, key_len); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, key, len)) return -EFAULT; return 0; } case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; case TCP_THIN_DUPACK: val = 0; break; case TCP_REPAIR: val = tp->repair; break; case TCP_REPAIR_QUEUE: if (tp->repair) val = tp->repair_queue; else return -EINVAL; break; case TCP_REPAIR_WINDOW: { struct tcp_repair_window opt; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len != sizeof(opt)) return -EINVAL; if (!tp->repair) return -EPERM; opt.snd_wl1 = tp->snd_wl1; opt.snd_wnd = tp->snd_wnd; opt.max_window = tp->max_window; opt.rcv_wnd = tp->rcv_wnd; opt.rcv_wup = tp->rcv_wup; if (copy_to_sockptr(optval, &opt, len)) return -EFAULT; return 0; } case TCP_QUEUE_SEQ: if (tp->repair_queue == TCP_SEND_QUEUE) val = tp->write_seq; else if (tp->repair_queue == TCP_RECV_QUEUE) val = tp->rcv_nxt; else return -EINVAL; break; case TCP_USER_TIMEOUT: val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: val = tp->fastopen_connect; break; case TCP_FASTOPEN_NO_COOKIE: val = tp->fastopen_no_cookie; break; case TCP_TX_DELAY: val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset); if (tp->tcp_usec_ts) val |= 1; else val &= ~1; break; case TCP_NOTSENT_LOWAT: val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; break; case TCP_SAVE_SYN: val = tp->save_syn; break; case TCP_SAVED_SYN: { if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; sockopt_lock_sock(sk); if (tp->saved_syn) { if (len < tcp_saved_syn_len(tp->saved_syn)) { len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } sockopt_release_sock(sk); return -EINVAL; } len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } if (copy_to_sockptr(optval, tp->saved_syn->data, len)) { sockopt_release_sock(sk); return -EFAULT; } tcp_saved_syn_free(tp); sockopt_release_sock(sk); } else { sockopt_release_sock(sk); len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } return 0; } #ifdef CONFIG_MMU case TCP_ZEROCOPY_RECEIVE: { struct scm_timestamping_internal tss; struct tcp_zerocopy_receive zc = {}; int err; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0 || len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; if (unlikely(len > sizeof(zc))) { err = check_zeroed_sockptr(optval, sizeof(zc), len - sizeof(zc)); if (err < 1) return err == 0 ? -EINVAL : err; len = sizeof(zc); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } if (copy_from_sockptr(&zc, optval, len)) return -EFAULT; if (zc.reserved) return -EINVAL; if (zc.msg_flags & ~(TCP_VALID_ZC_MSG_FLAGS)) return -EINVAL; sockopt_lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc, &tss); err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, &zc, &len, err); sockopt_release_sock(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) goto zerocopy_rcv_cmsg; switch (len) { case offsetofend(struct tcp_zerocopy_receive, msg_flags): goto zerocopy_rcv_cmsg; case offsetofend(struct tcp_zerocopy_receive, msg_controllen): case offsetofend(struct tcp_zerocopy_receive, msg_control): case offsetofend(struct tcp_zerocopy_receive, flags): case offsetofend(struct tcp_zerocopy_receive, copybuf_len): case offsetofend(struct tcp_zerocopy_receive, copybuf_address): case offsetofend(struct tcp_zerocopy_receive, err): goto zerocopy_rcv_sk_err; case offsetofend(struct tcp_zerocopy_receive, inq): goto zerocopy_rcv_inq; case offsetofend(struct tcp_zerocopy_receive, length): default: goto zerocopy_rcv_out; } zerocopy_rcv_cmsg: if (zc.msg_flags & TCP_CMSG_TS) tcp_zc_finalize_rx_tstamp(sk, &zc, &tss); else zc.msg_flags = 0; zerocopy_rcv_sk_err: if (!err) zc.err = sock_error(sk); zerocopy_rcv_inq: zc.inq = tcp_inq_hint(sk); zerocopy_rcv_out: if (!err && copy_to_sockptr(optval, &zc, len)) err = -EFAULT; return err; } #endif case TCP_AO_REPAIR: if (!tcp_can_repair_sock(sk)) return -EPERM; return tcp_ao_get_repair(sk, optval, optlen); case TCP_AO_GET_KEYS: case TCP_AO_INFO: { int err; sockopt_lock_sock(sk); if (optname == TCP_AO_GET_KEYS) err = tcp_ao_get_mkts(sk, optval, optlen); else err = tcp_ao_get_sock_info(sk, optval, optlen); sockopt_release_sock(sk); return err; } default: return -ENOPROTOOPT; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, len)) return -EFAULT; return 0; } bool tcp_bpf_bypass_getsockopt(int level, int optname) { /* TCP do_tcp_getsockopt has optimized getsockopt implementation * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. */ if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) return true; return false; } EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->getsockopt(sk, level, optname, optval, optlen); return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } EXPORT_SYMBOL(tcp_getsockopt); #ifdef CONFIG_TCP_MD5SIG int tcp_md5_sigpool_id = -1; EXPORT_SYMBOL_GPL(tcp_md5_sigpool_id); int tcp_md5_alloc_sigpool(void) { size_t scratch_size; int ret; scratch_size = sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr); ret = tcp_sigpool_alloc_ahash("md5", scratch_size); if (ret >= 0) { /* As long as any md5 sigpool was allocated, the return * id would stay the same. Re-write the id only for the case * when previously all MD5 keys were deleted and this call * allocates the first MD5 key, which may return a different * sigpool id than was used previously. */ WRITE_ONCE(tcp_md5_sigpool_id, ret); /* Avoids the compiler potentially being smart here */ return 0; } return ret; } void tcp_md5_release_sigpool(void) { tcp_sigpool_release(READ_ONCE(tcp_md5_sigpool_id)); } void tcp_md5_add_sigpool(void) { tcp_sigpool_get(READ_ONCE(tcp_md5_sigpool_id)); } int tcp_md5_hash_key(struct tcp_sigpool *hp, const struct tcp_md5sig_key *key) { u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; sg_init_one(&sg, key->key, keylen); ahash_request_set_crypt(hp->req, &sg, NULL, keylen); /* We use data_race() because tcp_md5_do_add() might change * key->key under us */ return data_race(crypto_ahash_update(hp->req)); } EXPORT_SYMBOL(tcp_md5_hash_key); /* Called with rcu_read_lock() */ enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) { /* This gets called for each TCP segment that has TCP-MD5 option. * We have 3 drop cases: * o No MD5 hash and one expected. * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; u8 newhash[16]; int genhash; key = tcp_md5_do_lookup(sk, l3index, saddr, family); if (!key && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); tcp_hash_fail("Unexpected MD5 Hash found", family, skb, ""); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } /* Check the signature. * To support dual stack listeners, we need to handle * IPv4-mapped case. */ if (family == AF_INET) genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else genhash = tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); if (family == AF_INET) { tcp_hash_fail("MD5 Hash failed", AF_INET, skb, "%s L3 index %d", genhash ? "tcp_v4_calc_md5_hash failed" : "", l3index); } else { if (genhash) { tcp_hash_fail("MD5 Hash failed", AF_INET6, skb, "L3 index %d", l3index); } else { tcp_hash_fail("MD5 Hash mismatch", AF_INET6, skb, "L3 index %d", l3index); } } return SKB_DROP_REASON_TCP_MD5FAILURE; } return SKB_NOT_DROPPED_YET; } EXPORT_SYMBOL(tcp_inbound_md5_hash); #endif void tcp_done(struct sock *sk) { struct request_sock *req; /* We might be called with a new socket, after * inet_csk_prepare_forced_close() has been called * so we can not use lockdep_sock_is_held(sk) */ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); if (req) reqsk_fastopen_remove(sk, req, false); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else inet_csk_destroy_sock(sk); } EXPORT_SYMBOL_GPL(tcp_done); int tcp_abort(struct sock *sk, int err) { int state = inet_sk_state_load(sk); if (state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); local_bh_disable(); inet_csk_reqsk_queue_drop(req->rsk_listener, req); local_bh_enable(); return 0; } if (state == TCP_TIME_WAIT) { struct inet_timewait_sock *tw = inet_twsk(sk); refcount_inc(&tw->tw_refcnt); local_bh_disable(); inet_twsk_deschedule_put(tw); local_bh_enable(); return 0; } /* BPF context ensures sock locking. */ if (!has_current_bpf_ctx()) /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); } /* Don't race with BH socket closes such as inet_csk_listen_stop. */ local_bh_disable(); bh_lock_sock(sk); if (!sock_flag(sk, SOCK_DEAD)) { WRITE_ONCE(sk->sk_err, err); /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); sk_error_report(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); } bh_unlock_sock(sk); local_bh_enable(); tcp_write_queue_purge(sk); if (!has_current_bpf_ctx()) release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; static int __init set_thash_entries(char *str) { ssize_t ret; if (!str) return 0; ret = kstrtoul(str, 0, &thash_entries); if (ret) return 0; return 1; } __setup("thash_entries=", set_thash_entries); static void __init tcp_init_mem(void) { unsigned long limit = nr_free_buffer_pages() / 16; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; /* 4.68 % */ sysctl_tcp_mem[1] = limit; /* 6.25 % */ sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } static void __init tcp_struct_check(void) { /* TX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, max_window); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, rcv_ssthresh); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40); /* TXRX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, mss_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_cwnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32); /* RX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rcv_tstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, retrans_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, advmss); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, urg_data); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, lost); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69); /* TX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, data_segs_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, bytes_sent); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, snd_sml); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_start); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_stat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, write_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, pushed_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_clock_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, window_clamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, srtt_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, packets_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 76); /* RX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, data_segs_in); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_wup); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, max_packets_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, cwnd_usage_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99); } void __init tcp_init(void) { int max_rshare, max_wshare, cnt; unsigned long limit; unsigned int i; BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof_field(struct sk_buff, cb)); tcp_struct_check(); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", thash_entries, 21, /* one slot per 2 MB*/ 0, 64 * 1024); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); tcp_hashinfo.bind2_bucket_cachep = kmem_cache_create("tcp_bind2_bucket", sizeof(struct inet_bind2_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); /* Size and allocate the main established and bind bucket * hash tables. * * The methodology is similar to that of the buffer cache. */ tcp_hashinfo.ehash = alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, 17, /* one slot per 128 KB of memory */ 0, NULL, &tcp_hashinfo.ehash_mask, 0, thash_entries ? 0 : 512 * 1024); for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", 2 * sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, 17, /* one slot per 128 KB of memory */ 0, &tcp_hashinfo.bhash_size, NULL, 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; tcp_hashinfo.bhash2 = tcp_hashinfo.bhash + tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); spin_lock_init(&tcp_hashinfo.bhash2[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain); } tcp_hashinfo.pernet = false; cnt = tcp_hashinfo.ehash_mask + 1; sysctl_tcp_max_orphans = cnt / 2; tcp_init_mem(); /* Set per-socket limits to no more than 1/128 the pressure threshold */ limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_wshare = min(4UL*1024*1024, limit); max_rshare = min(6UL*1024*1024, limit); init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare); init_net.ipv4.sysctl_tcp_rmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_rmem[1] = 131072; init_net.ipv4.sysctl_tcp_rmem[2] = max(131072, max_rshare); pr_info("Hash tables configured (established %u bind %u)\n", tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_v4_init(); tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); mptcp_init(); } |
| 274 273 303 303 257 274 81 140 135 120 5 5 4 5 13 5 5 120 119 120 120 120 120 120 120 133 97 50 47 47 120 120 120 120 120 24 168 83 173 15 15 6 23 25 25 25 25 25 139 139 23 139 139 139 139 139 139 37 37 37 37 37 37 37 37 37 23 23 37 37 37 37 37 37 37 37 23 37 37 37 37 37 37 1 1 37 37 37 37 37 37 1 22 37 37 25 2 24 1 24 256 256 1 13 152 23 61 39 285 285 170 170 4 162 161 39 23 39 39 39 39 38 38 22 38 38 136 24 1 104 13 18 18 444 445 15 15 15 2 21 1 20 20 20 11 13 13 13 1 8 1 4 4 12 20 3 18 81 81 160 160 100 81 100 103 78 160 81 100 100 100 160 160 100 81 81 81 20 85 85 85 85 165 93 46 73 73 73 183 136 285 67 89 89 89 97 24 73 73 73 73 105 105 105 105 105 105 97 97 112 112 35 16 73 107 107 9 107 95 112 112 35 91 105 20 112 20 105 112 214 214 214 197 17 81 3 81 81 57 25 136 165 165 165 165 165 105 140 140 140 140 17 139 139 443 445 1 1 1 1 433 139 435 47 136 136 47 176 110 5 5 2 2 2 8 1 2 3 2 252 252 252 252 252 252 252 29 55 214 252 55 214 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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 <linux/module.h> #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/atomic.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> #endif #include <net/mptcp.h> #include <net/xfrm.h> #include <asm/ioctls.h> #include "protocol.h" #include "mib.h" #define CREATE_TRACE_POINTS #include <trace/events/mptcp.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) struct mptcp6_sock { struct mptcp_sock msk; struct ipv6_pinfo np; }; #endif enum { MPTCP_CMSG_TS = BIT(0), MPTCP_CMSG_INQ = BIT(1), }; static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp; static void __mptcp_destroy_sock(struct sock *sk); static void mptcp_check_send_data_fin(struct sock *sk); DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); static struct net_device mptcp_napi_dev; /* Returns end sequence number of the receiver's advertised window */ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) { return READ_ONCE(msk->wnd_end); } static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (sk->sk_prot == &tcpv6_prot) return &inet6_stream_ops; #endif WARN_ON_ONCE(sk->sk_prot != &tcp_prot); return &inet_stream_ops; } static int __mptcp_socket_create(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; struct socket *ssock; int err; err = mptcp_subflow_create_socket(sk, sk->sk_family, &ssock); if (err) return err; msk->scaling_ratio = tcp_sk(ssock->sk)->scaling_ratio; WRITE_ONCE(msk->first, ssock->sk); subflow = mptcp_subflow_ctx(ssock->sk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); subflow->request_mptcp = 1; subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); iput(SOCK_INODE(ssock)); return 0; } /* If the MPC handshake is not started, returns the first subflow, * eventually allocating it. */ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; int ret; if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) return ERR_PTR(-EINVAL); if (!msk->first) { ret = __mptcp_socket_create(msk); if (ret) return ERR_PTR(ret); } return msk->first; } static void mptcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); __kfree_skb(skb); } static void mptcp_rmem_fwd_alloc_add(struct sock *sk, int size) { WRITE_ONCE(mptcp_sk(sk)->rmem_fwd_alloc, mptcp_sk(sk)->rmem_fwd_alloc + size); } static void mptcp_rmem_charge(struct sock *sk, int size) { mptcp_rmem_fwd_alloc_add(sk, -size); } static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, struct sk_buff *from) { bool fragstolen; int delta; if (MPTCP_SKB_CB(from)->offset || !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; pr_debug("colesced seq %llx into %llx new len %d new end seq %llx", MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, to->len, MPTCP_SKB_CB(from)->end_seq); MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; /* note the fwd memory can reach a negative value after accounting * for the delta, but the later skb free will restore a non * negative one */ atomic_add(delta, &sk->sk_rmem_alloc); mptcp_rmem_charge(sk, delta); kfree_skb_partial(from, fragstolen); return true; } static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, struct sk_buff *from) { if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq) return false; return mptcp_try_coalesce((struct sock *)msk, to, from); } static void __mptcp_rmem_reclaim(struct sock *sk, int amount) { amount >>= PAGE_SHIFT; mptcp_rmem_charge(sk, amount << PAGE_SHIFT); __sk_mem_reduce_allocated(sk, amount); } static void mptcp_rmem_uncharge(struct sock *sk, int size) { struct mptcp_sock *msk = mptcp_sk(sk); int reclaimable; mptcp_rmem_fwd_alloc_add(sk, size); reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk); /* see sk_mem_uncharge() for the rationale behind the following schema */ if (unlikely(reclaimable >= PAGE_SIZE)) __mptcp_rmem_reclaim(sk, reclaimable); } static void mptcp_rfree(struct sk_buff *skb) { unsigned int len = skb->truesize; struct sock *sk = skb->sk; atomic_sub(len, &sk->sk_rmem_alloc); mptcp_rmem_uncharge(sk, len); } void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk) { skb_orphan(skb); skb->sk = sk; skb->destructor = mptcp_rfree; atomic_add(skb->truesize, &sk->sk_rmem_alloc); mptcp_rmem_charge(sk, skb->truesize); } /* "inspired" by tcp_data_queue_ofo(), main differences: * - use mptcp seqs * - don't cope with sacks */ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) { struct sock *sk = (struct sock *)msk; struct rb_node **p, *parent; u64 seq, end_seq, max_seq; struct sk_buff *skb1; seq = MPTCP_SKB_CB(skb)->map_seq; end_seq = MPTCP_SKB_CB(skb)->end_seq; max_seq = atomic64_read(&msk->rcv_wnd_sent); pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq, RB_EMPTY_ROOT(&msk->out_of_order_queue)); if (after64(end_seq, max_seq)) { /* out of window */ mptcp_drop(sk, skb); pr_debug("oow by %lld, rcv_wnd_sent %llu\n", (unsigned long long)end_seq - (unsigned long)max_seq, (unsigned long long)atomic64_read(&msk->rcv_wnd_sent)); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW); return; } p = &msk->out_of_order_queue.rb_node; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE); if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) { rb_link_node(&skb->rbnode, NULL, p); rb_insert_color(&skb->rbnode, &msk->out_of_order_queue); msk->ooo_last_skb = skb; goto end; } /* with 2 subflows, adding at end of ooo queue is quite likely * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL); return; } /* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL); parent = &msk->ooo_last_skb->rbnode; p = &parent->rb_right; goto insert; } /* Find place to insert this segment. Handle overlaps on the way. */ parent = NULL; while (*p) { parent = *p; skb1 = rb_to_skb(parent); if (before64(seq, MPTCP_SKB_CB(skb1)->map_seq)) { p = &parent->rb_left; continue; } if (before64(seq, MPTCP_SKB_CB(skb1)->end_seq)) { if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ mptcp_drop(sk, skb); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); return; } if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) { /* partial overlap: * | skb | * | skb1 | * continue traversing */ } else { /* skb's seq == skb1's seq and skb covers skb1. * Replace skb1 with skb. */ rb_replace_node(&skb1->rbnode, &skb->rbnode, &msk->out_of_order_queue); mptcp_drop(sk, skb1); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); goto merge_right; } } else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE); return; } p = &parent->rb_right; } insert: /* Insert segment into RB tree. */ rb_link_node(&skb->rbnode, parent, p); rb_insert_color(&skb->rbnode, &msk->out_of_order_queue); merge_right: /* Remove other segments covered by skb. */ while ((skb1 = skb_rb_next(skb)) != NULL) { if (before64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) break; rb_erase(&skb1->rbnode, &msk->out_of_order_queue); mptcp_drop(sk, skb1); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); } /* If there is no skb after us, we are the last_skb ! */ if (!skb1) msk->ooo_last_skb = skb; end: skb_condense(skb); mptcp_set_owner_r(skb, sk); } static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size) { struct mptcp_sock *msk = mptcp_sk(sk); int amt, amount; if (size <= msk->rmem_fwd_alloc) return true; size -= msk->rmem_fwd_alloc; amt = sk_mem_pages(size); amount = amt << PAGE_SHIFT; if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV)) return false; mptcp_rmem_fwd_alloc_add(sk, amount); return true; } static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, struct sk_buff *skb, unsigned int offset, size_t copy_len) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; struct sk_buff *tail; bool has_rxtstamp; __skb_unlink(skb, &ssk->sk_receive_queue); skb_ext_reset(skb); skb_orphan(skb); /* try to fetch required memory from subflow */ if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) goto drop; has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; /* the skb map_seq accounts for the skb offset: * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq * value */ MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow); MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len; MPTCP_SKB_CB(skb)->offset = offset; MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp; if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ msk->bytes_received += copy_len; WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); tail = skb_peek_tail(&sk->sk_receive_queue); if (tail && mptcp_try_coalesce(sk, tail, skb)) return true; mptcp_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); return true; } else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) { mptcp_data_queue_ofo(msk, skb); return false; } /* old data, keep it simple and drop the whole pkt, sender * will retransmit as needed, if needed. */ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); drop: mptcp_drop(sk, skb); return false; } static void mptcp_stop_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); sk_stop_timer(sk, &icsk->icsk_retransmit_timer); mptcp_sk(sk)->timer_ival = 0; } static void mptcp_close_wake_up(struct sock *sk) { if (sock_flag(sk, SOCK_DEAD)) return; sk->sk_state_change(sk); if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); else sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } static bool mptcp_pending_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); return ((1 << sk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) && msk->write_seq == READ_ONCE(msk->snd_una); } static void mptcp_check_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); /* Look for an acknowledged DATA_FIN */ if (mptcp_pending_data_fin_ack(sk)) { WRITE_ONCE(msk->snd_data_fin_enable, 0); switch (sk->sk_state) { case TCP_FIN_WAIT1: mptcp_set_state(sk, TCP_FIN_WAIT2); break; case TCP_CLOSING: case TCP_LAST_ACK: mptcp_set_state(sk, TCP_CLOSE); break; } mptcp_close_wake_up(sk); } } static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) { struct mptcp_sock *msk = mptcp_sk(sk); if (READ_ONCE(msk->rcv_data_fin) && ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) { u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq); if (msk->ack_seq == rcv_data_fin_seq) { if (seq) *seq = rcv_data_fin_seq; return true; } } return false; } static void mptcp_set_datafin_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 retransmits; retransmits = min_t(u32, icsk->icsk_retransmits, ilog2(TCP_RTO_MAX / TCP_RTO_MIN)); mptcp_sk(sk)->timer_ival = TCP_RTO_MIN << retransmits; } static void __mptcp_set_timeout(struct sock *sk, long tout) { mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; } static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subflow) { const struct sock *ssk = mptcp_subflow_tcp_sock(subflow); return inet_csk(ssk)->icsk_pending && !subflow->stale_count ? inet_csk(ssk)->icsk_timeout - jiffies : 0; } static void mptcp_set_timeout(struct sock *sk) { struct mptcp_subflow_context *subflow; long tout = 0; mptcp_for_each_subflow(mptcp_sk(sk), subflow) tout = max(tout, mptcp_timeout_from_subflow(subflow)); __mptcp_set_timeout(sk, tout); } static inline bool tcp_can_send_ack(const struct sock *ssk) { return !((1 << inet_sk_state_load(ssk)) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN)); } void __mptcp_subflow_send_ack(struct sock *ssk) { if (tcp_can_send_ack(ssk)) tcp_send_ack(ssk); } static void mptcp_subflow_send_ack(struct sock *ssk) { bool slow; slow = lock_sock_fast(ssk); __mptcp_subflow_send_ack(ssk); unlock_sock_fast(ssk, slow); } static void mptcp_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; mptcp_for_each_subflow(msk, subflow) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) tcp_cleanup_rbuf(ssk, 1); unlock_sock_fast(ssk, slow); } static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) { const struct inet_connection_sock *icsk = inet_csk(ssk); u8 ack_pending = READ_ONCE(icsk->icsk_ack.pending); const struct tcp_sock *tp = tcp_sk(ssk); return (ack_pending & ICSK_ACK_SCHED) && ((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) > READ_ONCE(icsk->icsk_ack.rcv_mss)) || (rx_empty && ack_pending & (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; int space = __mptcp_space(sk); bool cleanup, rx_empty; cleanup = (space > 0) && (space >= (old_space << 1)); rx_empty = !__mptcp_rmem(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) mptcp_subflow_cleanup_rbuf(ssk); } } static bool mptcp_check_data_fin(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); u64 rcv_data_fin_seq; bool ret = false; /* Need to ack a DATA_FIN received from a peer while this side * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2. * msk->rcv_data_fin was set when parsing the incoming options * at the subflow level and the msk lock was not held, so this * is the first opportunity to act on the DATA_FIN and change * the msk state. * * If we are caught up to the sequence number of the incoming * DATA_FIN, send the DATA_ACK now and do state transition. If * not caught up, do nothing and let the recv code send DATA_ACK * when catching up. */ if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) { WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ switch (sk->sk_state) { case TCP_ESTABLISHED: mptcp_set_state(sk, TCP_CLOSE_WAIT); break; case TCP_FIN_WAIT1: mptcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: mptcp_set_state(sk, TCP_CLOSE); break; default: /* Other states not expected */ WARN_ON_ONCE(1); break; } ret = true; if (!__mptcp_check_fallback(msk)) mptcp_send_ack(msk); mptcp_close_wake_up(sk); } return ret; } static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct sock *ssk, unsigned int *bytes) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; unsigned int moved = 0; bool more_data_avail; struct tcp_sock *tp; bool done = false; int sk_rbuf; sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) { WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf); sk_rbuf = ssk_rbuf; } } pr_debug("msk=%p ssk=%p", msk, ssk); tp = tcp_sk(ssk); do { u32 map_remaining, offset; u32 seq = tp->copied_seq; struct sk_buff *skb; bool fin; /* try to move as much data as available */ map_remaining = subflow->map_data_len - mptcp_subflow_get_map_offset(subflow); skb = skb_peek(&ssk->sk_receive_queue); if (!skb) { /* With racing move_skbs_to_msk() and __mptcp_move_skbs(), * a different CPU can have already processed the pending * data, stop here or we can enter an infinite loop */ if (!moved) done = true; break; } if (__mptcp_check_fallback(msk)) { /* Under fallback skbs have no MPTCP extension and TCP could * collapse them between the dummy map creation and the * current dequeue. Be sure to adjust the map size. */ map_remaining = skb->len; subflow->map_data_len = skb->len; } offset = seq - TCP_SKB_CB(skb)->seq; fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (fin) { done = true; seq++; } if (offset < skb->len) { size_t len = skb->len - offset; if (tp->urg_data) done = true; if (__mptcp_move_skb(msk, ssk, skb, offset, len)) moved += len; seq += len; if (WARN_ON_ONCE(map_remaining < len)) break; } else { WARN_ON_ONCE(!fin); sk_eat_skb(ssk, skb); done = true; } WRITE_ONCE(tp->copied_seq, seq); more_data_avail = mptcp_subflow_data_available(ssk); if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) { done = true; break; } } while (more_data_avail); *bytes += moved; return done; } static bool __mptcp_ofo_queue(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; struct sk_buff *skb, *tail; bool moved = false; struct rb_node *p; u64 end_seq; p = rb_first(&msk->out_of_order_queue); pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); while (p) { skb = rb_to_skb(p); if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) break; p = rb_next(p); rb_erase(&skb->rbnode, &msk->out_of_order_queue); if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq, msk->ack_seq))) { mptcp_drop(sk, skb); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); continue; } end_seq = MPTCP_SKB_CB(skb)->end_seq; tail = skb_peek_tail(&sk->sk_receive_queue); if (!tail || !mptcp_ooo_try_coalesce(msk, tail, skb)) { int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; /* skip overlapping data, if any */ pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d", MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq, delta); MPTCP_SKB_CB(skb)->offset += delta; MPTCP_SKB_CB(skb)->map_seq += delta; __skb_queue_tail(&sk->sk_receive_queue, skb); } msk->bytes_received += end_seq - msk->ack_seq; msk->ack_seq = end_seq; moved = true; } return moved; } static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) { int err = sock_error(ssk); int ssk_state; if (!err) return false; /* only propagate errors on fallen-back sockets or * on MPC connect */ if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) return false; /* We need to propagate only transition to CLOSE state. * Orphaned socket will see such state change via * subflow_sched_work_if_closed() and that path will properly * destroy the msk as needed. */ ssk_state = inet_sk_state_load(ssk); if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) mptcp_set_state(sk, ssk_state); WRITE_ONCE(sk->sk_err, -err); /* This barrier is coupled with smp_rmb() in mptcp_poll() */ smp_wmb(); sk_error_report(sk); return true; } void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); mptcp_for_each_subflow(msk, subflow) if (__mptcp_subflow_error_report(sk, mptcp_subflow_tcp_sock(subflow))) break; } /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); if (unlikely(ssk->sk_err)) { if (!sock_owned_by_user(sk)) __mptcp_error_report(sk); else __set_bit(MPTCP_ERROR_REPORT, &msk->cb_flags); } /* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but * this is not a good place to change state. Let the workqueue * do it. */ if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); return moved > 0; } void mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); int sk_rbuf, ssk_rbuf; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing * more data to the msk receive queue */ if (unlikely(subflow->disposable)) return; ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ if (__mptcp_rmem(sk) > sk_rbuf) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); return; } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); mptcp_data_unlock(sk); } static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk) { mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq); WRITE_ONCE(msk->allow_infinite_fallback, false); mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); } static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; if (sk->sk_state != TCP_ESTABLISHED) return false; /* attach to msk socket only after we are sure we will deal with it * at close time */ if (sk->sk_socket && !ssk->sk_socket) mptcp_sock_graft(ssk, sk->sk_socket); mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); mptcp_stop_tout_timer(sk); __mptcp_propagate_sndbuf(sk, ssk); return true; } static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list) { struct mptcp_subflow_context *tmp, *subflow; struct mptcp_sock *msk = mptcp_sk(sk); list_for_each_entry_safe(subflow, tmp, join_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); list_move_tail(&subflow->node, &msk->conn_list); if (!__mptcp_finish_join(msk, ssk)) mptcp_subflow_reset(ssk); unlock_sock_fast(ssk, slow); } } static bool mptcp_rtx_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); } static void mptcp_reset_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long tout; /* prevent rescheduling on close */ if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE)) return; tout = mptcp_sk(sk)->timer_ival; sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout); } bool mptcp_schedule_work(struct sock *sk) { if (inet_sk_state_load(sk) != TCP_CLOSE && schedule_work(&mptcp_sk(sk)->work)) { /* each subflow already holds a reference to the sk, and the * workqueue is invoked by a subflow, so sk can't go away here. */ sock_hold(sk); return true; } return false; } static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; msk_owned_by_me(msk); mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->data_avail)) return mptcp_subflow_tcp_sock(subflow); } return NULL; } static bool mptcp_skb_can_collapse_to(u64 write_seq, const struct sk_buff *skb, const struct mptcp_ext *mpext) { if (!tcp_skb_can_collapse_to(skb)) return false; /* can collapse only if MPTCP level sequence is in order and this * mapping has not been xmitted yet */ return mpext && mpext->data_seq + mpext->data_len == write_seq && !mpext->frozen; } /* we can append data to the given data frag if: * - there is space available in the backing page_frag * - the data frag tail matches the current page_frag free offset * - the data frag end sequence number matches the current write seq */ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, const struct page_frag *pfrag, const struct mptcp_data_frag *df) { return df && pfrag->page == df->page && pfrag->size - pfrag->offset > 0 && pfrag->offset == (df->offset + df->data_len) && df->data_seq + df->data_len == msk->write_seq; } static void dfrag_uncharge(struct sock *sk, int len) { sk_mem_uncharge(sk, len); sk_wmem_queued_add(sk, -len); } static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag) { int len = dfrag->data_len + dfrag->overhead; list_del(&dfrag->list); dfrag_uncharge(sk, len); put_page(dfrag->page); } static void __mptcp_clean_una(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; u64 snd_una; snd_una = msk->snd_una; list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) { if (after64(dfrag->data_seq + dfrag->data_len, snd_una)) break; if (unlikely(dfrag == msk->first_pending)) { /* in recovery mode can see ack after the current snd head */ if (WARN_ON_ONCE(!msk->recovery)) break; WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); } dfrag_clear(sk, dfrag); } dfrag = mptcp_rtx_head(sk); if (dfrag && after64(snd_una, dfrag->data_seq)) { u64 delta = snd_una - dfrag->data_seq; /* prevent wrap around in recovery mode */ if (unlikely(delta > dfrag->already_sent)) { if (WARN_ON_ONCE(!msk->recovery)) goto out; if (WARN_ON_ONCE(delta > dfrag->data_len)) goto out; dfrag->already_sent += delta - dfrag->already_sent; } dfrag->data_seq += delta; dfrag->offset += delta; dfrag->data_len -= delta; dfrag->already_sent -= delta; dfrag_uncharge(sk, delta); } /* all retransmitted data acked, recovery completed */ if (unlikely(msk->recovery) && after64(msk->snd_una, msk->recovery_snd_nxt)) msk->recovery = false; out: if (snd_una == READ_ONCE(msk->snd_nxt) && snd_una == READ_ONCE(msk->write_seq)) { if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) mptcp_stop_rtx_timer(sk); } else { mptcp_reset_rtx_timer(sk); } } static void __mptcp_clean_una_wakeup(struct sock *sk) { lockdep_assert_held_once(&sk->sk_lock.slock); __mptcp_clean_una(sk); mptcp_write_space(sk); } static void mptcp_clean_una_wakeup(struct sock *sk) { mptcp_data_lock(sk); __mptcp_clean_una_wakeup(sk); mptcp_data_unlock(sk); } static void mptcp_enter_memory_pressure(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool first = true; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (first) tcp_enter_memory_pressure(ssk); sk_stream_moderate_sndbuf(ssk); first = false; } __mptcp_sync_sndbuf(sk); } /* ensure we get enough memory for the frag hdr, beyond some minimal amount of * data */ static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag) { if (likely(skb_page_frag_refill(32U + sizeof(struct mptcp_data_frag), pfrag, sk->sk_allocation))) return true; mptcp_enter_memory_pressure(sk); return false; } static struct mptcp_data_frag * mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag, int orig_offset) { int offset = ALIGN(orig_offset, sizeof(long)); struct mptcp_data_frag *dfrag; dfrag = (struct mptcp_data_frag *)(page_to_virt(pfrag->page) + offset); dfrag->data_len = 0; dfrag->data_seq = msk->write_seq; dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag); dfrag->offset = offset + sizeof(struct mptcp_data_frag); dfrag->already_sent = 0; dfrag->page = pfrag->page; return dfrag; } struct mptcp_sendmsg_info { int mss_now; int size_goal; u16 limit; u16 sent; unsigned int flags; bool data_lock_held; }; static int mptcp_check_allowed_size(const struct mptcp_sock *msk, struct sock *ssk, u64 data_seq, int avail_size) { u64 window_end = mptcp_wnd_end(msk); u64 mptcp_snd_wnd; if (__mptcp_check_fallback(msk)) return avail_size; mptcp_snd_wnd = window_end - data_seq; avail_size = min_t(unsigned int, mptcp_snd_wnd, avail_size); if (unlikely(tcp_sk(ssk)->snd_wnd < mptcp_snd_wnd)) { tcp_sk(ssk)->snd_wnd = min_t(u64, U32_MAX, mptcp_snd_wnd); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_SNDWNDSHARED); } return avail_size; } static bool __mptcp_add_ext(struct sk_buff *skb, gfp_t gfp) { struct skb_ext *mpext = __skb_ext_alloc(gfp); if (!mpext) return false; __skb_ext_set(skb, SKB_EXT_MPTCP, mpext); return true; } static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp) { struct sk_buff *skb; skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp); if (likely(skb)) { if (likely(__mptcp_add_ext(skb, gfp))) { skb_reserve(skb, MAX_TCP_HEADER); skb->ip_summed = CHECKSUM_PARTIAL; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); } else { mptcp_enter_memory_pressure(sk); } return NULL; } static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) { struct sk_buff *skb; skb = __mptcp_do_alloc_tx_skb(sk, gfp); if (!skb) return NULL; if (likely(sk_wmem_schedule(ssk, skb->truesize))) { tcp_skb_entail(ssk, skb); return skb; } tcp_skb_tsorted_anchor_cleanup(skb); kfree_skb(skb); return NULL; } static struct sk_buff *mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held) { gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation; return __mptcp_alloc_tx_skb(sk, ssk, gfp); } /* note: this always recompute the csum on the whole skb, even * if we just appended a single frag. More status info needed */ static void mptcp_update_data_checksum(struct sk_buff *skb, int added) { struct mptcp_ext *mpext = mptcp_get_ext(skb); __wsum csum = ~csum_unfold(mpext->csum); int offset = skb->len - added; mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset)); } static void mptcp_update_infinite_map(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_ext *mpext) { if (!mpext) return; mpext->infinite_map = 1; mpext->data_len = 0; MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX); mptcp_subflow_ctx(ssk)->send_infinite_map = 0; pr_fallback(msk); mptcp_do_fallback(ssk); } #define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1)) static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_data_frag *dfrag, struct mptcp_sendmsg_info *info) { u64 data_seq = dfrag->data_seq + info->sent; int offset = dfrag->offset + info->sent; struct mptcp_sock *msk = mptcp_sk(sk); bool zero_window_probe = false; struct mptcp_ext *mpext = NULL; bool can_coalesce = false; bool reuse_skb = true; struct sk_buff *skb; size_t copy; int i; pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u", msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent); if (WARN_ON_ONCE(info->sent > info->limit || info->limit > dfrag->data_len)) return 0; if (unlikely(!__tcp_can_send(ssk))) return -EAGAIN; /* compute send limit */ if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE)) ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE; info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); copy = info->size_goal; skb = tcp_write_queue_tail(ssk); if (skb && copy > skb->len) { /* Limit the write to the size available in the * current skb, if any, so that we create at most a new skb. * Explicitly tells TCP internals to avoid collapsing on later * queue management operation, to avoid breaking the ext <-> * SSN association set here */ mpext = mptcp_get_ext(skb); if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) { TCP_SKB_CB(skb)->eor = 1; goto alloc_skb; } i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset); if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) { tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } copy -= skb->len; } else { alloc_skb: skb = mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held); if (!skb) return -ENOMEM; i = skb_shinfo(skb)->nr_frags; reuse_skb = false; mpext = mptcp_get_ext(skb); } /* Zero window and all data acked? Probe. */ copy = mptcp_check_allowed_size(msk, ssk, data_seq, copy); if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { tcp_remove_empty_skb(ssk); return 0; } zero_window_probe = true; data_seq = snd_una - 1; copy = 1; } copy = min_t(size_t, copy, info->limit - info->sent); if (!sk_wmem_schedule(ssk, copy)) { tcp_remove_empty_skb(ssk); return -ENOMEM; } if (can_coalesce) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { get_page(dfrag->page); skb_fill_page_desc(skb, i, dfrag->page, offset, copy); } skb->len += copy; skb->data_len += copy; skb->truesize += copy; sk_wmem_queued_add(ssk, copy); sk_mem_charge(ssk, copy); WRITE_ONCE(tcp_sk(ssk)->write_seq, tcp_sk(ssk)->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); /* on skb reuse we just need to update the DSS len */ if (reuse_skb) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; mpext->data_len += copy; goto out; } memset(mpext, 0, sizeof(*mpext)); mpext->data_seq = data_seq; mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq; mpext->data_len = copy; mpext->use_map = 1; mpext->dsn64 = 1; pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d", mpext->data_seq, mpext->subflow_seq, mpext->data_len, mpext->dsn64); if (zero_window_probe) { mptcp_subflow_ctx(ssk)->rel_write_seq += copy; mpext->frozen = 1; if (READ_ONCE(msk->csum_enabled)) mptcp_update_data_checksum(skb, copy); tcp_push_pending_frames(ssk); return 0; } out: if (READ_ONCE(msk->csum_enabled)) mptcp_update_data_checksum(skb, copy); if (mptcp_subflow_ctx(ssk)->send_infinite_map) mptcp_update_infinite_map(msk, ssk, mpext); trace_mptcp_sendmsg_frag(mpext); mptcp_subflow_ctx(ssk)->rel_write_seq += copy; return copy; } #define MPTCP_SEND_BURST_SIZE ((1 << 16) - \ sizeof(struct tcphdr) - \ MAX_TCP_OPTION_SPACE - \ sizeof(struct ipv6hdr) - \ sizeof(struct frag_hdr)) struct subflow_send_info { struct sock *ssk; u64 linger_time; }; void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow) { if (!subflow->stale) return; subflow->stale = 0; MPTCP_INC_STATS(sock_net(mptcp_subflow_tcp_sock(subflow)), MPTCP_MIB_SUBFLOWRECOVER); } bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) { if (unlikely(subflow->stale)) { u32 rcv_tstamp = READ_ONCE(tcp_sk(mptcp_subflow_tcp_sock(subflow))->rcv_tstamp); if (subflow->stale_rcv_tstamp == rcv_tstamp) return false; mptcp_subflow_set_active(subflow); } return __mptcp_subflow_active(subflow); } #define SSK_MODE_ACTIVE 0 #define SSK_MODE_BACKUP 1 #define SSK_MODE_MAX 2 /* implement the mptcp packet scheduler; * returns the subflow that will transmit the next DSS * additionally updates the rtx timeout */ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) { struct subflow_send_info send_info[SSK_MODE_MAX]; struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; u32 pace, burst, wmem; int i, nr_active = 0; struct sock *ssk; u64 linger_time; long tout = 0; /* pick the subflow with the lower wmem/wspace ratio */ for (i = 0; i < SSK_MODE_MAX; ++i) { send_info[i].ssk = NULL; send_info[i].linger_time = -1; } mptcp_for_each_subflow(msk, subflow) { trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); nr_active += !subflow->backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ subflow->avg_pacing_rate = READ_ONCE(ssk->sk_pacing_rate); pace = subflow->avg_pacing_rate; if (!pace) continue; } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); if (linger_time < send_info[subflow->backup].linger_time) { send_info[subflow->backup].ssk = ssk; send_info[subflow->backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); /* pick the best backup if no other subflow is active */ if (!nr_active) send_info[SSK_MODE_ACTIVE].ssk = send_info[SSK_MODE_BACKUP].ssk; /* According to the blest algorithm, to avoid HoL blocking for the * faster flow, we need to: * - estimate the faster flow linger time * - use the above to estimate the amount of byte transferred * by the faster flow * - check that the amount of queued data is greter than the above, * otherwise do not use the picked, slower, subflow * We select the subflow with the shorter estimated time to flush * the queued mem, which basically ensure the above. We just need * to check that subflow has a non empty cwin. */ ssk = send_info[SSK_MODE_ACTIVE].ssk; if (!ssk || !sk_stream_memory_free(ssk)) return NULL; burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt); wmem = READ_ONCE(ssk->sk_wmem_queued); if (!burst) return ssk; subflow = mptcp_subflow_ctx(ssk); subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem + READ_ONCE(ssk->sk_pacing_rate) * burst, burst + wmem); msk->snd_burst = burst; return ssk; } static void mptcp_push_release(struct sock *ssk, struct mptcp_sendmsg_info *info) { tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal); release_sock(ssk); } static void mptcp_update_post_push(struct mptcp_sock *msk, struct mptcp_data_frag *dfrag, u32 sent) { u64 snd_nxt_new = dfrag->data_seq; dfrag->already_sent += sent; msk->snd_burst -= sent; snd_nxt_new += dfrag->already_sent; /* snd_nxt_new can be smaller than snd_nxt in case mptcp * is recovering after a failover. In that event, this re-sends * old segments. * * Thus compute snd_nxt_new candidate based on * the dfrag->data_seq that was sent and the data * that has been handed to the subflow for transmission * and skip update in case it was old dfrag. */ if (likely(after64(snd_nxt_new, msk->snd_nxt))) { msk->bytes_sent += snd_nxt_new - msk->snd_nxt; msk->snd_nxt = snd_nxt_new; } } void mptcp_check_and_set_pending(struct sock *sk) { if (mptcp_send_head(sk)) { mptcp_data_lock(sk); mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); mptcp_data_unlock(sk); } } static int __subflow_push_pending(struct sock *sk, struct sock *ssk, struct mptcp_sendmsg_info *info) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dfrag; int len, copied = 0, err = 0; while ((dfrag = mptcp_send_head(sk))) { info->sent = dfrag->already_sent; info->limit = dfrag->data_len; len = dfrag->data_len - dfrag->already_sent; while (len > 0) { int ret = 0; ret = mptcp_sendmsg_frag(sk, ssk, dfrag, info); if (ret <= 0) { err = copied ? : ret; goto out; } info->sent += ret; copied += ret; len -= ret; mptcp_update_post_push(msk, dfrag, ret); } WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); if (msk->snd_burst <= 0 || !sk_stream_memory_free(ssk) || !mptcp_subflow_active(mptcp_subflow_ctx(ssk))) { err = copied; goto out; } mptcp_set_timeout(sk); } err = copied; out: return err; } void __mptcp_push_pending(struct sock *sk, unsigned int flags) { struct sock *prev_ssk = NULL, *ssk = NULL; struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = { .flags = flags, }; bool do_check_data_fin = false; int push_count = 1; while (mptcp_send_head(sk) && (push_count > 0)) { struct mptcp_subflow_context *subflow; int ret = 0; if (mptcp_sched_get_send(msk)) break; push_count = 0; mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { mptcp_subflow_set_scheduled(subflow, false); prev_ssk = ssk; ssk = mptcp_subflow_tcp_sock(subflow); if (ssk != prev_ssk) { /* First check. If the ssk has changed since * the last round, release prev_ssk */ if (prev_ssk) mptcp_push_release(prev_ssk, &info); /* Need to lock the new subflow only if different * from the previous one, otherwise we are still * helding the relevant lock */ lock_sock(ssk); } push_count++; ret = __subflow_push_pending(sk, ssk, &info); if (ret <= 0) { if (ret != -EAGAIN || (1 << ssk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSE)) push_count--; continue; } do_check_data_fin = true; } } } /* at this point we held the socket lock for the last subflow we used */ if (ssk) mptcp_push_release(ssk, &info); /* ensure the rtx timer is running */ if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); if (do_check_data_fin) mptcp_check_send_data_fin(sk); } static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = { .data_lock_held = true, }; bool keep_pushing = true; struct sock *xmit_ssk; int copied = 0; info.flags = 0; while (mptcp_send_head(sk) && keep_pushing) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); int ret = 0; /* check for a different subflow usage only after * spooling the first chunk of data */ if (first) { mptcp_subflow_set_scheduled(subflow, false); ret = __subflow_push_pending(sk, ssk, &info); first = false; if (ret <= 0) break; copied += ret; continue; } if (mptcp_sched_get_send(msk)) goto out; if (READ_ONCE(subflow->scheduled)) { mptcp_subflow_set_scheduled(subflow, false); ret = __subflow_push_pending(sk, ssk, &info); if (ret <= 0) keep_pushing = false; copied += ret; } mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { xmit_ssk = mptcp_subflow_tcp_sock(subflow); if (xmit_ssk != ssk) { mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_SEND); keep_pushing = false; } } } } out: /* __mptcp_alloc_tx_skb could have released some wmem and we are * not going to flush it via release_sock() */ if (copied) { tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); if (msk->snd_data_fin_enable && msk->snd_nxt + 1 == msk->write_seq) mptcp_schedule_work(sk); } } static void mptcp_set_nospace(struct sock *sk) { /* enable autotune */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* will be cleared on avail space */ set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags); } static int mptcp_disconnect(struct sock *sk, int flags); static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, size_t len, int *copied_syn) { unsigned int saved_flags = msg->msg_flags; struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; int ret; /* on flags based fastopen the mptcp is supposed to create the * first subflow right now. Otherwise we are in the defer_connect * path, and the first subflow must be already present. * Since the defer_connect flag is cleared after the first succsful * fastopen attempt, no need to check for additional subflow status. */ if (msg->msg_flags & MSG_FASTOPEN) { ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) return PTR_ERR(ssk); } if (!msk->first) return -EINVAL; ssk = msk->first; lock_sock(ssk); msg->msg_flags |= MSG_DONTWAIT; msk->fastopening = 1; ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); msk->fastopening = 0; msg->msg_flags = saved_flags; release_sock(ssk); /* do the blocking bits of inet_stream_connect outside the ssk socket lock */ if (ret == -EINPROGRESS && !(msg->msg_flags & MSG_DONTWAIT)) { ret = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, msg->msg_flags, 1); /* Keep the same behaviour of plain TCP: zero the copied bytes in * case of any error, except timeout or signal */ if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR) *copied_syn = 0; } else if (ret && ret != -EINPROGRESS) { /* The disconnect() op called by tcp_sendmsg_fastopen()/ * __inet_stream_connect() can fail, due to looking check, * see mptcp_disconnect(). * Attempt it again outside the problematic scope. */ if (!mptcp_disconnect(sk, 0)) sk->sk_socket->state = SS_UNCONNECTED; } inet_clear_bit(DEFER_CONNECT, sk); return ret; } static int do_copy_data_nocache(struct sock *sk, int copy, struct iov_iter *from, char *to) { if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; } else if (!copy_from_iter_full(to, copy, from)) { return -EFAULT; } return 0; } static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); struct page_frag *pfrag; size_t copied = 0; int ret = 0; long timeo; /* silently ignore everything else */ msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_FASTOPEN; lock_sock(sk); if (unlikely(inet_test_bit(DEFER_CONNECT, sk) || msg->msg_flags & MSG_FASTOPEN)) { int copied_syn = 0; ret = mptcp_sendmsg_fastopen(sk, msg, len, &copied_syn); copied += copied_syn; if (ret == -EINPROGRESS && copied_syn > 0) goto out; else if (ret) goto do_error; } timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { ret = sk_stream_wait_connect(sk, &timeo); if (ret) goto do_error; } ret = -EPIPE; if (unlikely(sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))) goto do_error; pfrag = sk_page_frag(sk); while (msg_data_left(msg)) { int total_ts, frag_truesize = 0; struct mptcp_data_frag *dfrag; bool dfrag_collapsed; size_t psize, offset; /* reuse tail pfrag, if possible, or carve a new one from the * page allocator */ dfrag = mptcp_pending_tail(sk); dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag); if (!dfrag_collapsed) { if (!sk_stream_memory_free(sk)) goto wait_for_memory; if (!mptcp_page_frag_refill(sk, pfrag)) goto wait_for_memory; dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset); frag_truesize = dfrag->overhead; } /* we do not bound vs wspace, to allow a single packet. * memory accounting will prevent execessive memory usage * anyway */ offset = dfrag->offset + dfrag->data_len; psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); total_ts = psize + frag_truesize; if (!sk_wmem_schedule(sk, total_ts)) goto wait_for_memory; ret = do_copy_data_nocache(sk, psize, &msg->msg_iter, page_address(dfrag->page) + offset); if (ret) goto do_error; /* data successfully copied into the write queue */ sk_forward_alloc_add(sk, -total_ts); copied += psize; dfrag->data_len += psize; frag_truesize += psize; pfrag->offset += frag_truesize; WRITE_ONCE(msk->write_seq, msk->write_seq + psize); /* charge data on mptcp pending queue to the msk socket * Note: we charge such data both to sk and ssk */ sk_wmem_queued_add(sk, frag_truesize); if (!dfrag_collapsed) { get_page(dfrag->page); list_add_tail(&dfrag->list, &msk->rtx_queue); if (!msk->first_pending) WRITE_ONCE(msk->first_pending, dfrag); } pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk, dfrag->data_seq, dfrag->data_len, dfrag->already_sent, !dfrag_collapsed); continue; wait_for_memory: mptcp_set_nospace(sk); __mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) goto do_error; } if (copied) __mptcp_push_pending(sk, msg->msg_flags); out: release_sock(sk); return copied; do_error: if (copied) goto out; copied = sk_stream_error(sk, msg->msg_flags, ret); goto out; } static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct sk_buff *skb, *tmp; int copied = 0; skb_queue_walk_safe(&msk->receive_queue, skb, tmp) { u32 offset = MPTCP_SKB_CB(skb)->offset; u32 data_len = skb->len - offset; u32 count = min_t(size_t, len - copied, data_len); int err; if (!(flags & MSG_TRUNC)) { err = skb_copy_datagram_msg(skb, offset, msg, count); if (unlikely(err < 0)) { if (!copied) return err; break; } } if (MPTCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); *cmsg_flags |= MPTCP_CMSG_TS; } copied += count; if (count < data_len) { if (!(flags & MSG_PEEK)) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; msk->bytes_consumed += count; } break; } if (!(flags & MSG_PEEK)) { /* we will bulk release the skb memory later */ skb->destructor = NULL; WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); msk->bytes_consumed += count; } if (copied >= len) break; } return copied; } /* receive buffer autotuning. See tcp_rcv_space_adjust for more information. * * Only difference: Use highest rtt estimate of the subflows in use. */ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; u8 scaling_ratio = U8_MAX; u32 time, advmss = 1; u64 rtt_us, mstamp; msk_owned_by_me(msk); if (copied <= 0) return; if (!msk->rcvspace_init) mptcp_rcv_space_init(msk, msk->first); msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); time = tcp_stamp_us_delta(mstamp, msk->rcvq_space.time); rtt_us = msk->rcvq_space.rtt_us; if (rtt_us && time < (rtt_us >> 3)) return; rtt_us = 0; mptcp_for_each_subflow(msk, subflow) { const struct tcp_sock *tp; u64 sf_rtt_us; u32 sf_advmss; tp = tcp_sk(mptcp_subflow_tcp_sock(subflow)); sf_rtt_us = READ_ONCE(tp->rcv_rtt_est.rtt_us); sf_advmss = READ_ONCE(tp->advmss); rtt_us = max(sf_rtt_us, rtt_us); advmss = max(sf_advmss, advmss); scaling_ratio = min(tp->scaling_ratio, scaling_ratio); } msk->rcvq_space.rtt_us = rtt_us; msk->scaling_ratio = scaling_ratio; if (time < (rtt_us >> 3) || rtt_us == 0) return; if (msk->rcvq_space.copied <= msk->rcvq_space.space) goto new_measure; if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { u64 rcvwin, grow; int rcvbuf; rcvwin = ((u64)msk->rcvq_space.copied << 1) + 16 * advmss; grow = rcvwin * (msk->rcvq_space.copied - msk->rcvq_space.space); do_div(grow, msk->rcvq_space.space); rcvwin += (grow << 1); rcvbuf = min_t(u64, __tcp_space_from_win(scaling_ratio, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); if (rcvbuf > sk->sk_rcvbuf) { u32 window_clamp; window_clamp = __tcp_win_from_space(scaling_ratio, rcvbuf); WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make subflows follow along. If we do not do this, we * get drops at subflow level if skbs can't be moved to * the mptcp rx queue fast enough (announced rcv_win can * exceed ssk->sk_rcvbuf). */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk; bool slow; ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); tcp_sk(ssk)->window_clamp = window_clamp; tcp_cleanup_rbuf(ssk, 1); unlock_sock_fast(ssk, slow); } } } msk->rcvq_space.space = msk->rcvq_space.copied; new_measure: msk->rcvq_space.copied = 0; msk->rcvq_space.time = mstamp; } static void __mptcp_update_rmem(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); if (!msk->rmem_released) return; atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc); mptcp_rmem_uncharge(sk, msk->rmem_released); WRITE_ONCE(msk->rmem_released, 0); } static void __mptcp_splice_receive_queue(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue); } static bool __mptcp_move_skbs(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; bool ret, done; do { struct sock *ssk = mptcp_subflow_recv_lookup(msk); bool slowpath; /* we can have data pending in the subflows only if the msk * receive buffer was full at subflow_data_ready() time, * that is an unlikely slow path. */ if (likely(!ssk)) break; slowpath = lock_sock_fast(ssk); mptcp_data_lock(sk); __mptcp_update_rmem(sk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); if (unlikely(ssk->sk_err)) __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); } while (!done); /* acquire the data lock only if some input data is pending */ ret = moved > 0; if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) || !skb_queue_empty_lockless(&sk->sk_receive_queue)) { mptcp_data_lock(sk); __mptcp_update_rmem(sk); ret |= __mptcp_ofo_queue(msk); __mptcp_splice_receive_queue(sk); mptcp_data_unlock(sk); } if (ret) mptcp_check_data_fin((struct sock *)msk); return !skb_queue_empty(&msk->receive_queue); } static unsigned int mptcp_inq_hint(const struct sock *sk) { const struct mptcp_sock *msk = mptcp_sk(sk); const struct sk_buff *skb; skb = skb_peek(&msk->receive_queue); if (skb) { u64 hint_val = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; if (hint_val >= INT_MAX) return INT_MAX; return (unsigned int)hint_val; } if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) return 1; return 0; } static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); struct scm_timestamping_internal tss; int copied = 0, cmsg_flags = 0; int target; long timeo; /* MSG_ERRQUEUE is really a no-op till we support IP_RECVERR */ if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); lock_sock(sk); if (unlikely(sk->sk_state == TCP_LISTEN)) { copied = -ENOTCONN; goto out_err; } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); len = min_t(size_t, len, INT_MAX); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); if (unlikely(msk->recvmsg_inq)) cmsg_flags = MPTCP_CMSG_INQ; while (copied < len) { int bytes_read; bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; goto out_err; } copied += bytes_read; /* be sure to advertise window change */ mptcp_cleanup_rbuf(msk); if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; /* only the master socket status is relevant here. The exit * conditions mirror closely tcp_recvmsg() */ if (copied >= target) break; if (copied) { if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo || signal_pending(current)) break; } else { if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) { /* race breaker: the shutdown could be after the * previous receive queue check */ if (__mptcp_move_skbs(msk)) continue; break; } if (sk->sk_state == TCP_CLOSE) { copied = -ENOTCONN; break; } if (!timeo) { copied = -EAGAIN; break; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); break; } } pr_debug("block timeout %ld", timeo); sk_wait_data(sk, &timeo, NULL); } out_err: if (cmsg_flags && copied >= 0) { if (cmsg_flags & MPTCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); if (cmsg_flags & MPTCP_CMSG_INQ) { unsigned int inq = mptcp_inq_hint(sk); put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); } } pr_debug("msk=%p rx queue empty=%d:%d copied=%d", msk, skb_queue_empty_lockless(&sk->sk_receive_queue), skb_queue_empty(&msk->receive_queue), copied); if (!(flags & MSG_PEEK)) mptcp_rcv_space_adjust(msk, copied); release_sock(sk); return copied; } static void mptcp_retransmit_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_retransmit_timer); struct sock *sk = &icsk->icsk_inet.sk; struct mptcp_sock *msk = mptcp_sk(sk); bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* we need a process context to retransmit */ if (!test_and_set_bit(MPTCP_WORK_RTX, &msk->flags)) mptcp_schedule_work(sk); } else { /* delegate our work to tcp_release_cb() */ __set_bit(MPTCP_RETRANSMIT, &msk->cb_flags); } bh_unlock_sock(sk); sock_put(sk); } static void mptcp_tout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); mptcp_schedule_work(sk); sock_put(sk); } /* Find an idle subflow. Return NULL if there is unacked data at tcp * level. * * A backup subflow is returned only if that is the only kind available. */ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) { struct sock *backup = NULL, *pick = NULL; struct mptcp_subflow_context *subflow; int min_stale_count = INT_MAX; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!__mptcp_subflow_active(subflow)) continue; /* still data outstanding at TCP level? skip this */ if (!tcp_rtx_and_write_queues_empty(ssk)) { mptcp_pm_subflow_chk_stale(msk, ssk); min_stale_count = min_t(int, min_stale_count, subflow->stale_count); continue; } if (subflow->backup) { if (!backup) backup = ssk; continue; } if (!pick) pick = ssk; } if (pick) return pick; /* use backup only if there are no progresses anywhere */ return min_stale_count > 1 ? backup : NULL; } bool __mptcp_retransmit_pending_data(struct sock *sk) { struct mptcp_data_frag *cur, *rtx_head; struct mptcp_sock *msk = mptcp_sk(sk); if (__mptcp_check_fallback(msk)) return false; /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue */ mptcp_data_lock(sk); __mptcp_clean_una_wakeup(sk); rtx_head = mptcp_rtx_head(sk); if (!rtx_head) { mptcp_data_unlock(sk); return false; } msk->recovery_snd_nxt = msk->snd_nxt; msk->recovery = true; mptcp_data_unlock(sk); msk->first_pending = rtx_head; msk->snd_burst = 0; /* be sure to clear the "sent status" on all re-injected fragments */ list_for_each_entry(cur, &msk->rtx_queue, list) { if (!cur->already_sent) break; cur->already_sent = 0; } return true; } /* flags for __mptcp_close_ssk() */ #define MPTCP_CF_PUSH BIT(1) #define MPTCP_CF_FASTCLOSE BIT(2) /* be sure to send a reset only if the caller asked for it, also * clean completely the subflow status when the subflow reaches * TCP_CLOSE state */ static void __mptcp_subflow_disconnect(struct sock *ssk, struct mptcp_subflow_context *subflow, unsigned int flags) { if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || (flags & MPTCP_CF_FASTCLOSE)) { /* The MPTCP code never wait on the subflow sockets, TCP-level * disconnect should never fail */ WARN_ON_ONCE(tcp_disconnect(ssk, 0)); mptcp_subflow_ctx_reset(subflow); } else { tcp_shutdown(ssk, SEND_SHUTDOWN); } } /* subflow sockets can be either outgoing (connect) or incoming * (accept). * * Outgoing subflows use in-kernel sockets. * Incoming subflows do not have their own 'struct socket' allocated, * so we need to use tcp_close() after detaching them from the mptcp * parent socket. */ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow, unsigned int flags) { struct mptcp_sock *msk = mptcp_sk(sk); bool dispose_it, need_push = false; /* If the first subflow moved to a close state before accept, e.g. due * to an incoming reset or listener shutdown, the subflow socket is * already deleted by inet_child_forget() and the mptcp socket can't * survive too. */ if (msk->in_accept_queue && msk->first == ssk && (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ sock_set_flag(sk, SOCK_DEAD); mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1)); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); goto out_release; } dispose_it = msk->free_first || ssk != msk->first; if (dispose_it) list_del(&subflow->node); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_close path * to generate the egress reset */ ssk->sk_lingertime = 0; sock_set_flag(ssk, SOCK_LINGER); subflow->send_fastclose = 1; } need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { __mptcp_subflow_disconnect(ssk, subflow, flags); release_sock(ssk); goto out; } subflow->disposable = 1; /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops * the ssk has been already destroyed, we just need to release the * reference owned by msk; */ if (!inet_csk(ssk)->icsk_ulp_ops) { WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD)); kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ __tcp_close(ssk, 0); /* close acquired an extra ref */ __sock_put(ssk); } out_release: __mptcp_subflow_error_report(sk, ssk); release_sock(ssk); sock_put(ssk); if (ssk == msk->first) WRITE_ONCE(msk->first, NULL); out: __mptcp_sync_sndbuf(sk); if (need_push) __mptcp_push_pending(sk, 0); /* Catch every 'all subflows closed' scenario, including peers silently * closing them, e.g. due to timeout. * For established sockets, allow an additional timeout before closing, * as the protocol can still create more subflows. */ if (list_is_singular(&msk->conn_list) && msk->first && inet_sk_state_load(msk->first) == TCP_CLOSE) { if (sk->sk_state != TCP_ESTABLISHED || msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) { mptcp_set_state(sk, TCP_CLOSE); mptcp_close_wake_up(sk); } else { mptcp_start_tout_timer(sk); } } } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { if (sk->sk_state == TCP_ESTABLISHED) mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); /* subflow aborted before reaching the fully_established status * attempt the creation of the next subflow */ mptcp_pm_subflow_check_next(mptcp_sk(sk), subflow); __mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_PUSH); } static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) { return 0; } static void __mptcp_close_subflow(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); might_sleep(); mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (inet_sk_state_load(ssk) != TCP_CLOSE) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ if (!skb_queue_empty_lockless(&ssk->sk_receive_queue)) continue; mptcp_close_ssk(sk, ssk, subflow); } } static bool mptcp_close_tout_expired(const struct sock *sk) { if (!inet_csk(sk)->icsk_mtup.probe_timestamp || sk->sk_state == TCP_CLOSE) return false; return time_after32(tcp_jiffies32, inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk)); } static void mptcp_check_fastclose(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; if (likely(!READ_ONCE(msk->rcv_fastclose))) return; mptcp_token_destroy(msk); mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); bool slow; slow = lock_sock_fast(tcp_sk); if (tcp_sk->sk_state != TCP_CLOSE) { tcp_send_active_reset(tcp_sk, GFP_ATOMIC); tcp_set_state(tcp_sk, TCP_CLOSE); } unlock_sock_fast(tcp_sk, slow); } /* Mirror the tcp_reset() error propagation */ switch (sk->sk_state) { case TCP_SYN_SENT: WRITE_ONCE(sk->sk_err, ECONNREFUSED); break; case TCP_CLOSE_WAIT: WRITE_ONCE(sk->sk_err, EPIPE); break; case TCP_CLOSE: return; default: WRITE_ONCE(sk->sk_err, ECONNRESET); } mptcp_set_state(sk, TCP_CLOSE); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); /* the calling mptcp_worker will properly destroy the socket */ if (sock_flag(sk, SOCK_DEAD)) return; sk->sk_state_change(sk); sk_error_report(sk); } static void __mptcp_retrans(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; struct mptcp_sendmsg_info info = {}; struct mptcp_data_frag *dfrag; struct sock *ssk; int ret, err; u16 len = 0; mptcp_clean_una_wakeup(sk); /* first check ssk: need to kick "stale" logic */ err = mptcp_sched_get_retrans(msk); dfrag = mptcp_rtx_head(sk); if (!dfrag) { if (mptcp_data_fin_enabled(msk)) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_retransmits++; mptcp_set_datafin_timeout(sk); mptcp_send_ack(msk); goto reset_timer; } if (!mptcp_send_head(sk)) return; goto reset_timer; } if (err) goto reset_timer; mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { u16 copied = 0; mptcp_subflow_set_scheduled(subflow, false); ssk = mptcp_subflow_tcp_sock(subflow); lock_sock(ssk); /* limit retransmission to the bytes already sent on some subflows */ info.sent = 0; info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent; while (info.sent < info.limit) { ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); if (ret <= 0) break; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS); copied += ret; info.sent += ret; } if (copied) { len = max(copied, len); tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); WRITE_ONCE(msk->allow_infinite_fallback, false); } release_sock(ssk); } } msk->bytes_retrans += len; dfrag->already_sent = max(dfrag->already_sent, len); reset_timer: mptcp_check_and_set_pending(sk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); } /* schedule the timeout timer for the relevant event: either close timeout * or mp_fail timeout. The close timeout takes precedence on the mp_fail one */ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) { struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp) return; close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + mptcp_close_timeout(sk); /* the close timeout takes precedence on the fail one, and here at least one of * them is active */ timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout; sk_reset_timer(sk, &sk->sk_timer, timeout); } static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) { struct sock *ssk = msk->first; bool slow; if (!ssk) return; pr_debug("MP_FAIL doesn't respond, reset the subflow"); slow = lock_sock_fast(ssk); mptcp_subflow_reset(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); } static void mptcp_do_fastclose(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); mptcp_set_state(sk, TCP_CLOSE); mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, MPTCP_CF_FASTCLOSE); } static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); struct sock *sk = (struct sock *)msk; unsigned long fail_tout; int state; lock_sock(sk); state = sk->sk_state; if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; mptcp_check_fastclose(msk); mptcp_pm_nl_work(msk); mptcp_check_send_data_fin(sk); mptcp_check_data_fin_ack(sk); mptcp_check_data_fin(sk); if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) __mptcp_close_subflow(sk); if (mptcp_close_tout_expired(sk)) { mptcp_do_fastclose(sk); mptcp_close_wake_up(sk); } if (sock_flag(sk, SOCK_DEAD) && sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); goto unlock; } if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) __mptcp_retrans(sk); fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0; if (fail_tout && time_after(jiffies, fail_tout)) mptcp_mp_fail_no_response(msk); unlock: release_sock(sk); sock_put(sk); } static void __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); INIT_LIST_HEAD(&msk->conn_list); INIT_LIST_HEAD(&msk->join_list); INIT_LIST_HEAD(&msk->rtx_queue); INIT_WORK(&msk->work, mptcp_worker); __skb_queue_head_init(&msk->receive_queue); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->rmem_fwd_alloc = 0; WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); WRITE_ONCE(msk->allow_infinite_fallback, true); msk->recovery = false; msk->subflow_id = 1; mptcp_pm_data_init(msk); /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); timer_setup(&sk->sk_timer, mptcp_tout_timer, 0); } static void mptcp_ca_reset(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_assign_congestion_control(sk); strcpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name); /* no need to keep a reference to the ops, the name will suffice */ tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = NULL; } static int mptcp_init_sock(struct sock *sk) { struct net *net = sock_net(sk); int ret; __mptcp_init_sock(sk); if (!mptcp_is_enabled(net)) return -ENOPROTOOPT; if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net)) return -ENOMEM; ret = mptcp_init_sched(mptcp_sk(sk), mptcp_sched_find(mptcp_get_scheduler(net))); if (ret) return ret; set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will * propagate the correct value */ mptcp_ca_reset(sk); sk_sockets_allocated_inc(sk); sk->sk_rcvbuf = READ_ONCE(net->ipv4.sysctl_tcp_rmem[1]); sk->sk_sndbuf = READ_ONCE(net->ipv4.sysctl_tcp_wmem[1]); return 0; } static void __mptcp_clear_xmit(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; WRITE_ONCE(msk->first_pending, NULL); list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); } void mptcp_cancel_work(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); if (cancel_work_sync(&msk->work)) __sock_put(sk); } void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) { lock_sock(ssk); switch (ssk->sk_state) { case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; fallthrough; case TCP_SYN_SENT: WARN_ON_ONCE(tcp_disconnect(ssk, O_NONBLOCK)); break; default: if (__mptcp_check_fallback(mptcp_sk(sk))) { pr_debug("Fallback"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); /* simulate the data_fin ack reception to let the state * machine move forward */ WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); mptcp_schedule_work(sk); } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); } break; } release_sock(ssk); } void mptcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); break; default: if (oldstate == TCP_ESTABLISHED) MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); } inet_sk_state_store(sk, state); } static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_SYN_SENT] = TCP_CLOSE, [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, [TCP_TIME_WAIT] = TCP_CLOSE, /* should not happen ! */ [TCP_CLOSE] = TCP_CLOSE, [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, [TCP_LAST_ACK] = TCP_LAST_ACK, [TCP_LISTEN] = TCP_CLOSE, [TCP_CLOSING] = TCP_CLOSING, [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int mptcp_close_state(struct sock *sk) { int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; mptcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } static void mptcp_check_send_data_fin(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu", msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk), msk->snd_nxt, msk->write_seq); /* we still need to enqueue subflows or not really shutting down, * skip this */ if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq || mptcp_send_head(sk)) return; WRITE_ONCE(msk->snd_nxt, msk->write_seq); mptcp_for_each_subflow(msk, subflow) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN); } } static void __mptcp_wr_shutdown(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d", msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state, !!mptcp_send_head(sk)); /* will be ignored by fallback sockets */ WRITE_ONCE(msk->write_seq, msk->write_seq + 1); WRITE_ONCE(msk->snd_data_fin_enable, 1); mptcp_check_send_data_fin(sk); } static void __mptcp_destroy_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p", msk); might_sleep(); mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); msk->pm.status = 0; mptcp_release_sched(msk); sk->sk_prot->destroy(sk); WARN_ON_ONCE(msk->rmem_fwd_alloc); WARN_ON_ONCE(msk->rmem_released); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); sock_put(sk); } void __mptcp_unaccepted_force_close(struct sock *sk) { sock_set_flag(sk, SOCK_DEAD); mptcp_do_fastclose(sk); __mptcp_destroy_sock(sk); } static __poll_t mptcp_check_readable(struct sock *sk) { return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0; } static void mptcp_check_listen_stop(struct sock *sk) { struct sock *ssk; if (inet_sk_state_load(sk) != TCP_LISTEN) return; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); ssk = mptcp_sk(sk)->first; if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN)) return; lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); tcp_set_state(ssk, TCP_CLOSE); mptcp_subflow_queue_clean(sk, ssk); inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); release_sock(ssk); } bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; int subflows_alive = 0; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { mptcp_check_listen_stop(sk); mptcp_set_state(sk, TCP_CLOSE); goto cleanup; } if (mptcp_data_avail(msk) || timeout < 0) { /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ mptcp_do_fastclose(sk); timeout = 0; } else if (mptcp_close_state(sk)) { __mptcp_wr_shutdown(sk); } sk_stream_wait_close(sk, timeout); cleanup: /* orphan all the subflows */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); subflows_alive += ssk->sk_state != TCP_CLOSE; /* since the close timeout takes precedence on the fail one, * cancel the latter */ if (ssk == msk->first) subflow->fail_tout = 0; /* detach from the parent socket, but allow data_ready to * push incoming data into the mptcp stack, to properly ack it */ ssk->sk_socket = NULL; ssk->sk_wq = NULL; unlock_sock_fast(ssk, slow); } sock_orphan(sk); /* all the subflows are closed, only timeout can change the msk * state, let's not keep resources busy for no reasons */ if (subflows_alive == 0) mptcp_set_state(sk, TCP_CLOSE); sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); if (sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); do_cancel_work = true; } else { mptcp_start_tout_timer(sk); } return do_cancel_work; } static void mptcp_close(struct sock *sk, long timeout) { bool do_cancel_work; lock_sock(sk); do_cancel_work = __mptcp_close(sk, timeout); release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); sock_put(sk); } static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); struct ipv6_pinfo *msk6 = inet6_sk(msk); msk->sk_v6_daddr = ssk->sk_v6_daddr; msk->sk_v6_rcv_saddr = ssk->sk_v6_rcv_saddr; if (msk6 && ssk6) { msk6->saddr = ssk6->saddr; msk6->flow_label = ssk6->flow_label; } #endif inet_sk(msk)->inet_num = inet_sk(ssk)->inet_num; inet_sk(msk)->inet_dport = inet_sk(ssk)->inet_dport; inet_sk(msk)->inet_sport = inet_sk(ssk)->inet_sport; inet_sk(msk)->inet_daddr = inet_sk(ssk)->inet_daddr; inet_sk(msk)->inet_saddr = inet_sk(ssk)->inet_saddr; inet_sk(msk)->inet_rcv_saddr = inet_sk(ssk)->inet_rcv_saddr; } static int mptcp_disconnect(struct sock *sk, int flags) { struct mptcp_sock *msk = mptcp_sk(sk); /* We are on the fastopen error path. We can't call straight into the * subflows cleanup code due to lock nesting (we are already under * msk->firstsocket lock). */ if (msk->fastopening) return -EBUSY; mptcp_check_listen_stop(sk); mptcp_set_state(sk, TCP_CLOSE); mptcp_stop_rtx_timer(sk); mptcp_stop_tout_timer(sk); if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); /* msk->subflow is still intact, the following will not free the first * subflow */ mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); WRITE_ONCE(msk->flags, 0); msk->cb_flags = 0; msk->recovery = false; msk->can_ack = false; msk->fully_established = false; msk->rcv_data_fin = false; msk->snd_data_fin_enable = false; msk->rcv_fastclose = false; msk->use_64bit_ack = false; msk->bytes_consumed = 0; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); msk->bytes_acked = 0; msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; msk->rcvspace_init = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); return 0; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) { unsigned int offset = sizeof(struct mptcp6_sock) - sizeof(struct ipv6_pinfo); return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } #endif struct sock *mptcp_sk_clone_init(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct sock *ssk, struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; if (!nsk) return NULL; #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (nsk->sk_family == AF_INET6) inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); #endif __mptcp_init_sock(nsk); msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(msk->csum_enabled, true); msk->write_seq = subflow_req->idsn + 1; msk->snd_nxt = msk->write_seq; msk->snd_una = msk->write_seq; msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd; msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; mptcp_init_sched(msk, mptcp_sk(sk)->sched); /* passive msk is created after the first/MPC subflow */ msk->subflow_id = 2; sock_reset_flag(nsk, SOCK_RCU_FREE); security_inet_csk_clone(nsk, req); /* this can't race with mptcp_close(), as the msk is * not yet exposted to user-space */ mptcp_set_state(nsk, TCP_ESTABLISHED); /* The msk maintain a ref to each subflow in the connections list */ WRITE_ONCE(msk->first, ssk); subflow = mptcp_subflow_ctx(ssk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); /* new mpc subflow takes ownership of the newly * created mptcp socket */ mptcp_token_accept(subflow_req, msk); /* set msk addresses early to ensure mptcp_pm_get_local_id() * uses the correct data */ mptcp_copy_inaddrs(nsk, ssk); __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ return nsk; } void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; msk->rcvq_space.time = tp->tcp_mstamp; /* initial rcv_space offering made to peer */ msk->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; } void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; __mptcp_clear_xmit(sk); /* join list will be eventually flushed (with rst) at sock lock release time */ mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags); /* move to sk_receive_queue, sk_stream_kill_queues will purge it */ mptcp_data_lock(sk); skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue); __skb_queue_purge(&sk->sk_receive_queue); skb_rbtree_purge(&msk->out_of_order_queue); mptcp_data_unlock(sk); /* move all the rx fwd alloc into the sk_mem_reclaim_final in * inet_sock_destruct() will dispose it */ sk_forward_alloc_add(sk, msk->rmem_fwd_alloc); WRITE_ONCE(msk->rmem_fwd_alloc, 0); mptcp_token_destroy(msk); mptcp_pm_free_anno_list(msk); mptcp_free_local_addr_list(msk); } static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); /* allow the following to close even the initial subflow */ msk->free_first = 1; mptcp_destroy_common(msk, 0); sk_sockets_allocated_dec(sk); } void __mptcp_data_acked(struct sock *sk) { if (!sock_owned_by_user(sk)) __mptcp_clean_una(sk); else __set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->cb_flags); if (mptcp_pending_data_fin_ack(sk)) mptcp_schedule_work(sk); } void __mptcp_check_push(struct sock *sk, struct sock *ssk) { if (!mptcp_send_head(sk)) return; if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, false); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); } #define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \ BIT(MPTCP_RETRANSMIT) | \ BIT(MPTCP_FLUSH_JOIN_LIST)) /* processes deferred events and flush wmem */ static void mptcp_release_cb(struct sock *sk) __must_hold(&sk->sk_lock.slock) { struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; if (!flags) break; INIT_LIST_HEAD(&join_list); list_splice_init(&msk->join_list, &join_list); /* the following actions acquire the subflow socket lock * * 1) can't be invoked in atomic scope * 2) must avoid ABBA deadlock with msk socket spinlock: the RX * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); if (flags & BIT(MPTCP_FLUSH_JOIN_LIST)) __mptcp_flush_join_list(sk, &join_list); if (flags & BIT(MPTCP_PUSH_PENDING)) __mptcp_push_pending(sk, 0); if (flags & BIT(MPTCP_RETRANSMIT)) __mptcp_retrans(sk); cond_resched(); spin_lock_bh(&sk->sk_lock.slock); } if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); if (unlikely(msk->cb_flags)) { /* be sure to sync the msk state before taking actions * depending on sk_state (MPTCP_ERROR_REPORT) * On sk release avoid actions depending on the first subflow */ if (__test_and_clear_bit(MPTCP_SYNC_STATE, &msk->cb_flags) && msk->first) __mptcp_sync_state(sk, msk->pending_state); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) __mptcp_sync_sndbuf(sk); } __mptcp_update_rmem(sk); } /* MP_JOIN client subflow must wait for 4th ack before sending any data: * TCP can't schedule delack timer before the subflow is fully established. * MPTCP uses the delack timer to do 3rd ack retransmissions */ static void schedule_3rdack_retransmission(struct sock *ssk) { struct inet_connection_sock *icsk = inet_csk(ssk); struct tcp_sock *tp = tcp_sk(ssk); unsigned long timeout; if (mptcp_subflow_ctx(ssk)->fully_established) return; /* reschedule with a timeout above RTT, as we must look only for drop */ if (tp->srtt_us) timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); else timeout = TCP_TIMEOUT_INIT; timeout += jiffies; WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; icsk->icsk_ack.timeout = timeout; sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); } void mptcp_subflow_process_delegated(struct sock *ssk, long status) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; if (status & BIT(MPTCP_DELEGATE_SEND)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, true); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } if (status & BIT(MPTCP_DELEGATE_SNDBUF)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_sync_sndbuf(sk); else __set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); } static int mptcp_hash(struct sock *sk) { /* should never be called, * we hash the TCP subflows not the master socket */ WARN_ON_ONCE(1); return 0; } static void mptcp_unhash(struct sock *sk) { /* called from sk_common_release(), but nothing to do here */ } static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p, ssk=%p", msk, msk->first); if (WARN_ON_ONCE(!msk->first)) return -EINVAL; return inet_csk_get_port(msk->first, snum); } void mptcp_finish_connect(struct sock *ssk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; struct sock *sk; subflow = mptcp_subflow_ctx(ssk); sk = subflow->conn; msk = mptcp_sk(sk); pr_debug("msk=%p, token=%u", sk, subflow->token); subflow->map_seq = subflow->iasn; subflow->map_subflow_seq = 1; /* the socket is not connected yet, no msk/subflow ops can access/race * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); mptcp_pm_new_connection(msk, ssk, 0); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); sk_set_socket(sk, parent); sk->sk_uid = SOCK_INODE(parent)->i_uid; write_unlock_bh(&sk->sk_callback_lock); } bool mptcp_finish_join(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct sock *parent = (void *)msk; bool ret = true; pr_debug("msk=%p, subflow=%p", msk, subflow); /* mptcp socket already closing? */ if (!mptcp_is_fully_established(parent)) { subflow->reset_reason = MPTCP_RST_EMPTCP; return false; } /* active subflow, already present inside the conn_list */ if (!list_empty(&subflow->node)) { mptcp_subflow_joined(msk, ssk); mptcp_propagate_sndbuf(parent, ssk); return true; } if (!mptcp_pm_allow_new_subflow(msk)) goto err_prohibited; /* If we can't acquire msk socket lock here, let the release callback * handle it */ mptcp_data_lock(parent); if (!sock_owned_by_user(parent)) { ret = __mptcp_finish_join(msk, ssk); if (ret) { sock_hold(ssk); list_add_tail(&subflow->node, &msk->conn_list); } } else { sock_hold(ssk); list_add_tail(&subflow->node, &msk->join_list); __set_bit(MPTCP_FLUSH_JOIN_LIST, &msk->cb_flags); } mptcp_data_unlock(parent); if (!ret) { err_prohibited: subflow->reset_reason = MPTCP_RST_EPROHIBIT; return false; } return true; } static void mptcp_shutdown(struct sock *sk, int how) { pr_debug("sk=%p, how=%d", sk, how); if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk)) __mptcp_wr_shutdown(sk); } static int mptcp_forward_alloc_get(const struct sock *sk) { return READ_ONCE(sk->sk_forward_alloc) + READ_ONCE(mptcp_sk(sk)->rmem_fwd_alloc); } static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) { const struct sock *sk = (void *)msk; u64 delta; if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) return 0; delta = msk->write_seq - v; if (__mptcp_check_fallback(msk) && msk->first) { struct tcp_sock *tp = tcp_sk(msk->first); /* the first subflow is disconnected after close - see * __mptcp_close_ssk(). tcp_disconnect() moves the write_seq * so ignore that status, too. */ if (!((1 << msk->first->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))) delta += READ_ONCE(tp->write_seq) - tp->snd_una; } if (delta > INT_MAX) delta = INT_MAX; return (int)delta; } static int mptcp_ioctl(struct sock *sk, int cmd, int *karg) { struct mptcp_sock *msk = mptcp_sk(sk); bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; lock_sock(sk); __mptcp_move_skbs(msk); *karg = mptcp_inq_hint(sk); release_sock(sk); break; case SIOCOUTQ: slow = lock_sock_fast(sk); *karg = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una)); unlock_sock_fast(sk, slow); break; case SIOCOUTQNSD: slow = lock_sock_fast(sk); *karg = mptcp_ioctl_outq(msk, msk->snd_nxt); unlock_sock_fast(sk, slow); break; default: return -ENOIOCTLCMD; } return 0; } static void mptcp_subflow_early_fallback(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow) { subflow->request_mptcp = 0; __mptcp_do_fallback(msk); } static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); int err = -EINVAL; struct sock *ssk; ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) return PTR_ERR(ssk); mptcp_set_state(sk, TCP_SYN_SENT); subflow = mptcp_subflow_ctx(ssk); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ if (rcu_access_pointer(tcp_sk(ssk)->md5sig_info)) mptcp_subflow_early_fallback(msk, subflow); #endif if (subflow->request_mptcp && mptcp_token_new_connect(ssk)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT); mptcp_subflow_early_fallback(msk, subflow); } if (likely(!__mptcp_check_fallback(msk))) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); /* if reaching here via the fastopen/sendmsg path, the caller already * acquired the subflow socket lock, too. */ if (!msk->fastopening) lock_sock(ssk); /* the following mirrors closely a very small chunk of code from * __inet_stream_connect() */ if (ssk->sk_state != TCP_CLOSE) goto out; if (BPF_CGROUP_PRE_CONNECT_ENABLED(ssk)) { err = ssk->sk_prot->pre_connect(ssk, uaddr, addr_len); if (err) goto out; } err = ssk->sk_prot->connect(ssk, uaddr, addr_len); if (err < 0) goto out; inet_assign_bit(DEFER_CONNECT, sk, inet_test_bit(DEFER_CONNECT, ssk)); out: if (!msk->fastopening) release_sock(ssk); /* on successful connect, the msk state will be moved to established by * subflow_finish_connect() */ if (unlikely(err)) { /* avoid leaving a dangling token in an unconnected socket */ mptcp_token_destroy(msk); mptcp_set_state(sk, TCP_CLOSE); return err; } mptcp_copy_inaddrs(sk, ssk); return 0; } static struct proto mptcp_prot = { .name = "MPTCP", .owner = THIS_MODULE, .init = mptcp_init_sock, .connect = mptcp_connect, .disconnect = mptcp_disconnect, .close = mptcp_close, .setsockopt = mptcp_setsockopt, .getsockopt = mptcp_getsockopt, .shutdown = mptcp_shutdown, .destroy = mptcp_destroy, .sendmsg = mptcp_sendmsg, .ioctl = mptcp_ioctl, .recvmsg = mptcp_recvmsg, .release_cb = mptcp_release_cb, .hash = mptcp_hash, .unhash = mptcp_unhash, .get_port = mptcp_get_port, .forward_alloc_get = mptcp_forward_alloc_get, .sockets_allocated = &mptcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .sysctl_mem = sysctl_tcp_mem, .obj_size = sizeof(struct mptcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .no_autobind = true, }; static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *sk = sock->sk; int err = -EINVAL; lock_sock(sk); ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { err = PTR_ERR(ssk); goto unlock; } if (sk->sk_family == AF_INET) err = inet_bind_sk(ssk, uaddr, addr_len); #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (sk->sk_family == AF_INET6) err = inet6_bind_sk(ssk, uaddr, addr_len); #endif if (!err) mptcp_copy_inaddrs(sk, ssk); unlock: release_sock(sk); return err; } static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *sk = sock->sk; struct sock *ssk; int err; pr_debug("msk=%p", msk); lock_sock(sk); err = -EINVAL; if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto unlock; ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { err = PTR_ERR(ssk); goto unlock; } mptcp_set_state(sk, TCP_LISTEN); sock_set_flag(sk, SOCK_RCU_FREE); lock_sock(ssk); err = __inet_listen_sk(ssk, backlog); release_sock(ssk); mptcp_set_state(sk, inet_sk_state_load(ssk)); if (!err) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); mptcp_copy_inaddrs(sk, ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); } unlock: release_sock(sk); return err; } static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *newsk; int err; pr_debug("msk=%p", msk); /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. */ ssk = READ_ONCE(msk->first); if (!ssk) return -EINVAL; pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk)); newsk = inet_csk_accept(ssk, flags, &err, kern); if (!newsk) return err; pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk)); if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; struct sock *new_mptcp_sock; subflow = mptcp_subflow_ctx(newsk); new_mptcp_sock = subflow->conn; /* is_mptcp should be false if subflow->conn is missing, see * subflow_syn_recv_sock() */ if (WARN_ON_ONCE(!new_mptcp_sock)) { tcp_sk(newsk)->is_mptcp = 0; goto tcpfallback; } newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK); newsk->sk_kern_sock = kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); msk = mptcp_sk(newsk); msk->in_accept_queue = 0; /* set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack. */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!ssk->sk_socket) mptcp_sock_graft(ssk, newsock); } /* Do late cleanup for the first subflow as necessary. Also * deal with bad peers not doing a complete shutdown. */ if (unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { __mptcp_close_ssk(newsk, msk->first, mptcp_subflow_ctx(msk->first), 0); if (unlikely(list_is_singular(&msk->conn_list))) mptcp_set_state(newsk, TCP_CLOSE); } } else { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); tcpfallback: newsk->sk_kern_sock = kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); /* we are being invoked after accepting a non-mp-capable * flow: sk is a tcp_sk, not an mptcp one. * * Hand the socket over to tcp so all further socket ops * bypass mptcp. */ WRITE_ONCE(newsock->sk->sk_socket->ops, mptcp_fallback_tcp_ops(newsock->sk)); } release_sock(newsk); return 0; } static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; if (sk_stream_is_writeable(sk)) return EPOLLOUT | EPOLLWRNORM; mptcp_set_nospace(sk); smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */ if (sk_stream_is_writeable(sk)) return EPOLLOUT | EPOLLWRNORM; return 0; } static __poll_t mptcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { struct sock *sk = sock->sk; struct mptcp_sock *msk; __poll_t mask = 0; u8 shutdown; int state; msk = mptcp_sk(sk); sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); if (state == TCP_LISTEN) { struct sock *ssk = READ_ONCE(msk->first); if (WARN_ON_ONCE(!ssk)) return 0; return inet_csk_listen_poll(ssk); } shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(sk); if (shutdown & SEND_SHUTDOWN) mask |= EPOLLOUT | EPOLLWRNORM; else mask |= mptcp_check_writeable(msk); } else if (state == TCP_SYN_SENT && inet_test_bit(DEFER_CONNECT, sk)) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in __mptcp_error_report() */ smp_rmb(); if (READ_ONCE(sk->sk_err)) mask |= EPOLLERR; return mask; } static const struct proto_ops mptcp_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = mptcp_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet_getname, .poll = mptcp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = mptcp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .set_rcvlowat = mptcp_set_rcvlowat, }; static struct inet_protosw mptcp_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_MPTCP, .prot = &mptcp_prot, .ops = &mptcp_stream_ops, .flags = INET_PROTOSW_ICSK, }; static int mptcp_napi_poll(struct napi_struct *napi, int budget) { struct mptcp_delegated_action *delegated; struct mptcp_subflow_context *subflow; int work_done = 0; delegated = container_of(napi, struct mptcp_delegated_action, napi); while ((subflow = mptcp_subflow_delegated_next(delegated)) != NULL) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bh_lock_sock_nested(ssk); if (!sock_owned_by_user(ssk)) { mptcp_subflow_process_delegated(ssk, xchg(&subflow->delegated_status, 0)); } else { /* tcp_release_cb_override already processed * the action or will do at next release_sock(). * In both case must dequeue the subflow here - on the same * CPU that scheduled it. */ smp_wmb(); clear_bit(MPTCP_DELEGATE_SCHEDULED, &subflow->delegated_status); } bh_unlock_sock(ssk); sock_put(ssk); if (++work_done == budget) return budget; } /* always provide a 0 'work_done' argument, so that napi_complete_done * will not try accessing the NULL napi->dev ptr */ napi_complete_done(napi, 0); return work_done; } void __init mptcp_proto_init(void) { struct mptcp_delegated_action *delegated; int cpu; mptcp_prot.h.hashinfo = tcp_prot.h.hashinfo; if (percpu_counter_init(&mptcp_sockets_allocated, 0, GFP_KERNEL)) panic("Failed to allocate MPTCP pcpu counter\n"); init_dummy_netdev(&mptcp_napi_dev); for_each_possible_cpu(cpu) { delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu); INIT_LIST_HEAD(&delegated->head); netif_napi_add_tx(&mptcp_napi_dev, &delegated->napi, mptcp_napi_poll); napi_enable(&delegated->napi); } mptcp_subflow_init(); mptcp_pm_init(); mptcp_sched_init(); mptcp_token_init(); if (proto_register(&mptcp_prot, 1) != 0) panic("Failed to register MPTCP proto.\n"); inet_register_protosw(&mptcp_protosw); BUILD_BUG_ON(sizeof(struct mptcp_skb_cb) > sizeof_field(struct sk_buff, cb)); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static const struct proto_ops mptcp_v6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = mptcp_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet6_getname, .poll = mptcp_poll, .ioctl = inet6_ioctl, .gettstamp = sock_gettstamp, .listen = mptcp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet6_sendmsg, .recvmsg = inet6_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif .set_rcvlowat = mptcp_set_rcvlowat, }; static struct proto mptcp_v6_prot; static struct inet_protosw mptcp_v6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_MPTCP, .prot = &mptcp_v6_prot, .ops = &mptcp_v6_stream_ops, .flags = INET_PROTOSW_ICSK, }; int __init mptcp_proto_v6_init(void) { int err; mptcp_v6_prot = mptcp_prot; strcpy(mptcp_v6_prot.name, "MPTCPv6"); mptcp_v6_prot.slab = NULL; mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np); err = proto_register(&mptcp_v6_prot, 1); if (err) return err; err = inet6_register_protosw(&mptcp_v6_protosw); if (err) proto_unregister(&mptcp_v6_prot); return err; } #endif |
| 19 40 20 70 70 66 66 38 50 50 24 24 37 13 44 13 13 8 40 10 11 40 40 39 20 20 20 20 20 44 7 39 39 10 39 44 65 61 11 44 33 44 44 5 40 44 20 20 33 44 44 48 48 39 24 33 48 5 47 47 33 33 33 33 33 2 20 20 20 33 56 7 55 5 4 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 | /* * net/tipc/group.c: TIPC group messaging code * * Copyright (c) 2017, Ericsson AB * Copyright (c) 2020, Red Hat Inc * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "core.h" #include "addr.h" #include "group.h" #include "bcast.h" #include "topsrv.h" #include "msg.h" #include "socket.h" #include "node.h" #include "name_table.h" #include "subscr.h" #define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1) #define ADV_IDLE ADV_UNIT #define ADV_ACTIVE (ADV_UNIT * 12) enum mbr_state { MBR_JOINING, MBR_PUBLISHED, MBR_JOINED, MBR_PENDING, MBR_ACTIVE, MBR_RECLAIMING, MBR_REMITTED, MBR_LEAVING }; struct tipc_member { struct rb_node tree_node; struct list_head list; struct list_head small_win; struct sk_buff_head deferredq; struct tipc_group *group; u32 node; u32 port; u32 instance; enum mbr_state state; u16 advertised; u16 window; u16 bc_rcv_nxt; u16 bc_syncpt; u16 bc_acked; }; struct tipc_group { struct rb_root members; struct list_head small_win; struct list_head pending; struct list_head active; struct tipc_nlist dests; struct net *net; int subid; u32 type; u32 instance; u32 scope; u32 portid; u16 member_cnt; u16 active_cnt; u16 max_active; u16 bc_snd_nxt; u16 bc_ackers; bool *open; bool loopback; bool events; }; static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, int mtyp, struct sk_buff_head *xmitq); static void tipc_group_open(struct tipc_member *m, bool *wakeup) { *wakeup = false; if (list_empty(&m->small_win)) return; list_del_init(&m->small_win); *m->group->open = true; *wakeup = true; } static void tipc_group_decr_active(struct tipc_group *grp, struct tipc_member *m) { if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING || m->state == MBR_REMITTED) grp->active_cnt--; } static int tipc_group_rcvbuf_limit(struct tipc_group *grp) { int max_active, active_pool, idle_pool; int mcnt = grp->member_cnt + 1; /* Limit simultaneous reception from other members */ max_active = min(mcnt / 8, 64); max_active = max(max_active, 16); grp->max_active = max_active; /* Reserve blocks for active and idle members */ active_pool = max_active * ADV_ACTIVE; idle_pool = (mcnt - max_active) * ADV_IDLE; /* Scale to bytes, considering worst-case truesize/msgsize ratio */ return (active_pool + idle_pool) * FLOWCTL_BLK_SZ * 4; } u16 tipc_group_bc_snd_nxt(struct tipc_group *grp) { return grp->bc_snd_nxt; } static bool tipc_group_is_receiver(struct tipc_member *m) { return m && m->state != MBR_JOINING && m->state != MBR_LEAVING; } static bool tipc_group_is_sender(struct tipc_member *m) { return m && m->state != MBR_JOINING && m->state != MBR_PUBLISHED; } u32 tipc_group_exclude(struct tipc_group *grp) { if (!grp->loopback) return grp->portid; return 0; } struct tipc_group *tipc_group_create(struct net *net, u32 portid, struct tipc_group_req *mreq, bool *group_is_open) { u32 filter = TIPC_SUB_PORTS | TIPC_SUB_NO_STATUS; bool global = mreq->scope != TIPC_NODE_SCOPE; struct tipc_group *grp; u32 type = mreq->type; grp = kzalloc(sizeof(*grp), GFP_ATOMIC); if (!grp) return NULL; tipc_nlist_init(&grp->dests, tipc_own_addr(net)); INIT_LIST_HEAD(&grp->small_win); INIT_LIST_HEAD(&grp->active); INIT_LIST_HEAD(&grp->pending); grp->members = RB_ROOT; grp->net = net; grp->portid = portid; grp->type = type; grp->instance = mreq->instance; grp->scope = mreq->scope; grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; grp->open = group_is_open; *grp->open = false; filter |= global ? TIPC_SUB_CLUSTER_SCOPE : TIPC_SUB_NODE_SCOPE; if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, filter, &grp->subid)) return grp; kfree(grp); return NULL; } void tipc_group_join(struct net *net, struct tipc_group *grp, int *sk_rcvbuf) { struct rb_root *tree = &grp->members; struct tipc_member *m, *tmp; struct sk_buff_head xmitq; __skb_queue_head_init(&xmitq); rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, &xmitq); tipc_group_update_member(m, 0); } tipc_node_distr_xmit(net, &xmitq); *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); } void tipc_group_delete(struct net *net, struct tipc_group *grp) { struct rb_root *tree = &grp->members; struct tipc_member *m, *tmp; struct sk_buff_head xmitq; __skb_queue_head_init(&xmitq); rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq); __skb_queue_purge(&m->deferredq); list_del(&m->list); kfree(m); } tipc_node_distr_xmit(net, &xmitq); tipc_nlist_purge(&grp->dests); tipc_topsrv_kern_unsubscr(net, grp->subid); kfree(grp); } static struct tipc_member *tipc_group_find_member(struct tipc_group *grp, u32 node, u32 port) { struct rb_node *n = grp->members.rb_node; u64 nkey, key = (u64)node << 32 | port; struct tipc_member *m; while (n) { m = container_of(n, struct tipc_member, tree_node); nkey = (u64)m->node << 32 | m->port; if (key < nkey) n = n->rb_left; else if (key > nkey) n = n->rb_right; else return m; } return NULL; } static struct tipc_member *tipc_group_find_dest(struct tipc_group *grp, u32 node, u32 port) { struct tipc_member *m; m = tipc_group_find_member(grp, node, port); if (m && tipc_group_is_receiver(m)) return m; return NULL; } static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, u32 node) { struct tipc_member *m; struct rb_node *n; for (n = rb_first(&grp->members); n; n = rb_next(n)) { m = container_of(n, struct tipc_member, tree_node); if (m->node == node) return m; } return NULL; } static int tipc_group_add_to_tree(struct tipc_group *grp, struct tipc_member *m) { u64 nkey, key = (u64)m->node << 32 | m->port; struct rb_node **n, *parent = NULL; struct tipc_member *tmp; n = &grp->members.rb_node; while (*n) { tmp = container_of(*n, struct tipc_member, tree_node); parent = *n; tmp = container_of(parent, struct tipc_member, tree_node); nkey = (u64)tmp->node << 32 | tmp->port; if (key < nkey) n = &(*n)->rb_left; else if (key > nkey) n = &(*n)->rb_right; else return -EEXIST; } rb_link_node(&m->tree_node, parent, n); rb_insert_color(&m->tree_node, &grp->members); return 0; } static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, u32 node, u32 port, u32 instance, int state) { struct tipc_member *m; int ret; m = kzalloc(sizeof(*m), GFP_ATOMIC); if (!m) return NULL; INIT_LIST_HEAD(&m->list); INIT_LIST_HEAD(&m->small_win); __skb_queue_head_init(&m->deferredq); m->group = grp; m->node = node; m->port = port; m->instance = instance; m->bc_acked = grp->bc_snd_nxt - 1; ret = tipc_group_add_to_tree(grp, m); if (ret < 0) { kfree(m); return NULL; } grp->member_cnt++; tipc_nlist_add(&grp->dests, m->node); m->state = state; return m; } void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port, u32 instance) { tipc_group_create_member(grp, node, port, instance, MBR_PUBLISHED); } static void tipc_group_delete_member(struct tipc_group *grp, struct tipc_member *m) { rb_erase(&m->tree_node, &grp->members); grp->member_cnt--; /* Check if we were waiting for replicast ack from this member */ if (grp->bc_ackers && less(m->bc_acked, grp->bc_snd_nxt - 1)) grp->bc_ackers--; list_del_init(&m->list); list_del_init(&m->small_win); tipc_group_decr_active(grp, m); /* If last member on a node, remove node from dest list */ if (!tipc_group_find_node(grp, m->node)) tipc_nlist_del(&grp->dests, m->node); kfree(m); } struct tipc_nlist *tipc_group_dests(struct tipc_group *grp) { return &grp->dests; } void tipc_group_self(struct tipc_group *grp, struct tipc_service_range *seq, int *scope) { seq->type = grp->type; seq->lower = grp->instance; seq->upper = grp->instance; *scope = grp->scope; } void tipc_group_update_member(struct tipc_member *m, int len) { struct tipc_group *grp = m->group; struct tipc_member *_m, *tmp; if (!tipc_group_is_receiver(m)) return; m->window -= len; if (m->window >= ADV_IDLE) return; list_del_init(&m->small_win); /* Sort member into small_window members' list */ list_for_each_entry_safe(_m, tmp, &grp->small_win, small_win) { if (_m->window > m->window) break; } list_add_tail(&m->small_win, &_m->small_win); } void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack) { u16 prev = grp->bc_snd_nxt - 1; struct tipc_member *m; struct rb_node *n; u16 ackers = 0; for (n = rb_first(&grp->members); n; n = rb_next(n)) { m = container_of(n, struct tipc_member, tree_node); if (tipc_group_is_receiver(m)) { tipc_group_update_member(m, len); m->bc_acked = prev; ackers++; } } /* Mark number of acknowledges to expect, if any */ if (ack) grp->bc_ackers = ackers; grp->bc_snd_nxt++; } bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, int len, struct tipc_member **mbr) { struct sk_buff_head xmitq; struct tipc_member *m; int adv, state; m = tipc_group_find_dest(grp, dnode, dport); if (!tipc_group_is_receiver(m)) { *mbr = NULL; return false; } *mbr = m; if (m->window >= len) return false; *grp->open = false; /* If not fully advertised, do it now to prevent mutual blocking */ adv = m->advertised; state = m->state; if (state == MBR_JOINED && adv == ADV_IDLE) return true; if (state == MBR_ACTIVE && adv == ADV_ACTIVE) return true; if (state == MBR_PENDING && adv == ADV_IDLE) return true; __skb_queue_head_init(&xmitq); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq); tipc_node_distr_xmit(grp->net, &xmitq); return true; } bool tipc_group_bc_cong(struct tipc_group *grp, int len) { struct tipc_member *m = NULL; /* If prev bcast was replicast, reject until all receivers have acked */ if (grp->bc_ackers) { *grp->open = false; return true; } if (list_empty(&grp->small_win)) return false; m = list_first_entry(&grp->small_win, struct tipc_member, small_win); if (m->window >= len) return false; return tipc_group_cong(grp, m->node, m->port, len, &m); } /* tipc_group_sort_msg() - sort msg into queue by bcast sequence number */ static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq) { struct tipc_msg *_hdr, *hdr = buf_msg(skb); u16 bc_seqno = msg_grp_bc_seqno(hdr); struct sk_buff *_skb, *tmp; int mtyp = msg_type(hdr); /* Bcast/mcast may be bypassed by ucast or other bcast, - sort it in */ if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) { skb_queue_walk_safe(defq, _skb, tmp) { _hdr = buf_msg(_skb); if (!less(bc_seqno, msg_grp_bc_seqno(_hdr))) continue; __skb_queue_before(defq, _skb, skb); return; } /* Bcast was not bypassed, - add to tail */ } /* Unicasts are never bypassed, - always add to tail */ __skb_queue_tail(defq, skb); } /* tipc_group_filter_msg() - determine if we should accept arriving message */ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct sk_buff *skb = __skb_dequeue(inputq); bool ack, deliver, update, leave = false; struct sk_buff_head *defq; struct tipc_member *m; struct tipc_msg *hdr; u32 node, port; int mtyp, blks; if (!skb) return; hdr = buf_msg(skb); node = msg_orignode(hdr); port = msg_origport(hdr); if (!msg_in_group(hdr)) goto drop; m = tipc_group_find_member(grp, node, port); if (!tipc_group_is_sender(m)) goto drop; if (less(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) goto drop; TIPC_SKB_CB(skb)->orig_member = m->instance; defq = &m->deferredq; tipc_group_sort_msg(skb, defq); while ((skb = skb_peek(defq))) { hdr = buf_msg(skb); mtyp = msg_type(hdr); blks = msg_blocks(hdr); deliver = true; ack = false; update = false; if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) break; /* Decide what to do with message */ switch (mtyp) { case TIPC_GRP_MCAST_MSG: if (msg_nameinst(hdr) != grp->instance) { update = true; deliver = false; } fallthrough; case TIPC_GRP_BCAST_MSG: m->bc_rcv_nxt++; ack = msg_grp_bc_ack_req(hdr); break; case TIPC_GRP_UCAST_MSG: break; case TIPC_GRP_MEMBER_EVT: if (m->state == MBR_LEAVING) leave = true; if (!grp->events) deliver = false; break; default: break; } /* Execute decisions */ __skb_dequeue(defq); if (deliver) __skb_queue_tail(inputq, skb); else kfree_skb(skb); if (ack) tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq); if (leave) { __skb_queue_purge(defq); tipc_group_delete_member(grp, m); break; } if (!update) continue; tipc_group_update_rcv_win(grp, blks, node, port, xmitq); } return; drop: kfree_skb(skb); } void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq) { struct list_head *active = &grp->active; int max_active = grp->max_active; int reclaim_limit = max_active * 3 / 4; int active_cnt = grp->active_cnt; struct tipc_member *m, *rm, *pm; m = tipc_group_find_member(grp, node, port); if (!m) return; m->advertised -= blks; switch (m->state) { case MBR_JOINED: /* First, decide if member can go active */ if (active_cnt <= max_active) { m->state = MBR_ACTIVE; list_add_tail(&m->list, active); grp->active_cnt++; tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); } else { m->state = MBR_PENDING; list_add_tail(&m->list, &grp->pending); } if (active_cnt < reclaim_limit) break; /* Reclaim from oldest active member, if possible */ if (!list_empty(active)) { rm = list_first_entry(active, struct tipc_member, list); rm->state = MBR_RECLAIMING; list_del_init(&rm->list); tipc_group_proto_xmit(grp, rm, GRP_RECLAIM_MSG, xmitq); break; } /* Nobody to reclaim from; - revert oldest pending to JOINED */ pm = list_first_entry(&grp->pending, struct tipc_member, list); list_del_init(&pm->list); pm->state = MBR_JOINED; tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); break; case MBR_ACTIVE: if (!list_is_last(&m->list, &grp->active)) list_move_tail(&m->list, &grp->active); if (m->advertised > (ADV_ACTIVE * 3 / 4)) break; tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); break; case MBR_REMITTED: if (m->advertised > ADV_IDLE) break; m->state = MBR_JOINED; grp->active_cnt--; if (m->advertised < ADV_IDLE) { pr_warn_ratelimited("Rcv unexpected msg after REMIT\n"); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); } if (list_empty(&grp->pending)) return; /* Set oldest pending member to active and advertise */ pm = list_first_entry(&grp->pending, struct tipc_member, list); pm->state = MBR_ACTIVE; list_move_tail(&pm->list, &grp->active); grp->active_cnt++; tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); break; case MBR_RECLAIMING: case MBR_JOINING: case MBR_LEAVING: default: break; } } static void tipc_group_create_event(struct tipc_group *grp, struct tipc_member *m, u32 event, u16 seqno, struct sk_buff_head *inputq) { u32 dnode = tipc_own_addr(grp->net); struct tipc_event evt; struct sk_buff *skb; struct tipc_msg *hdr; memset(&evt, 0, sizeof(evt)); evt.event = event; evt.found_lower = m->instance; evt.found_upper = m->instance; evt.port.ref = m->port; evt.port.node = m->node; evt.s.seq.type = grp->type; evt.s.seq.lower = m->instance; evt.s.seq.upper = m->instance; skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_GRP_MEMBER_EVT, GROUP_H_SIZE, sizeof(evt), dnode, m->node, grp->portid, m->port, 0); if (!skb) return; hdr = buf_msg(skb); msg_set_nametype(hdr, grp->type); msg_set_grp_evt(hdr, event); msg_set_dest_droppable(hdr, true); msg_set_grp_bc_seqno(hdr, seqno); memcpy(msg_data(hdr), &evt, sizeof(evt)); TIPC_SKB_CB(skb)->orig_member = m->instance; __skb_queue_tail(inputq, skb); } static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, int mtyp, struct sk_buff_head *xmitq) { struct tipc_msg *hdr; struct sk_buff *skb; int adv = 0; skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0, m->node, tipc_own_addr(grp->net), m->port, grp->portid, 0); if (!skb) return; if (m->state == MBR_ACTIVE) adv = ADV_ACTIVE - m->advertised; else if (m->state == MBR_JOINED || m->state == MBR_PENDING) adv = ADV_IDLE - m->advertised; hdr = buf_msg(skb); if (mtyp == GRP_JOIN_MSG) { msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); msg_set_adv_win(hdr, adv); m->advertised += adv; } else if (mtyp == GRP_LEAVE_MSG) { msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); } else if (mtyp == GRP_ADV_MSG) { msg_set_adv_win(hdr, adv); m->advertised += adv; } else if (mtyp == GRP_ACK_MSG) { msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt); } else if (mtyp == GRP_REMIT_MSG) { msg_set_grp_remitted(hdr, m->window); } msg_set_dest_droppable(hdr, true); __skb_queue_tail(xmitq, skb); } void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, struct tipc_msg *hdr, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { u32 node = msg_orignode(hdr); u32 port = msg_origport(hdr); struct tipc_member *m, *pm; u16 remitted, in_flight; if (!grp) return; if (grp->scope == TIPC_NODE_SCOPE && node != tipc_own_addr(grp->net)) return; m = tipc_group_find_member(grp, node, port); switch (msg_type(hdr)) { case GRP_JOIN_MSG: if (!m) m = tipc_group_create_member(grp, node, port, 0, MBR_JOINING); if (!m) return; m->bc_syncpt = msg_grp_bc_syncpt(hdr); m->bc_rcv_nxt = m->bc_syncpt; m->window += msg_adv_win(hdr); /* Wait until PUBLISH event is received if necessary */ if (m->state != MBR_PUBLISHED) return; /* Member can be taken into service */ m->state = MBR_JOINED; tipc_group_open(m, usr_wakeup); tipc_group_update_member(m, 0); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); tipc_group_create_event(grp, m, TIPC_PUBLISHED, m->bc_syncpt, inputq); return; case GRP_LEAVE_MSG: if (!m) return; m->bc_syncpt = msg_grp_bc_syncpt(hdr); list_del_init(&m->list); tipc_group_open(m, usr_wakeup); tipc_group_decr_active(grp, m); m->state = MBR_LEAVING; tipc_group_create_event(grp, m, TIPC_WITHDRAWN, m->bc_syncpt, inputq); return; case GRP_ADV_MSG: if (!m) return; m->window += msg_adv_win(hdr); tipc_group_open(m, usr_wakeup); return; case GRP_ACK_MSG: if (!m) return; m->bc_acked = msg_grp_bc_acked(hdr); if (--grp->bc_ackers) return; list_del_init(&m->small_win); *m->group->open = true; *usr_wakeup = true; tipc_group_update_member(m, 0); return; case GRP_RECLAIM_MSG: if (!m) return; tipc_group_proto_xmit(grp, m, GRP_REMIT_MSG, xmitq); m->window = ADV_IDLE; tipc_group_open(m, usr_wakeup); return; case GRP_REMIT_MSG: if (!m || m->state != MBR_RECLAIMING) return; remitted = msg_grp_remitted(hdr); /* Messages preceding the REMIT still in receive queue */ if (m->advertised > remitted) { m->state = MBR_REMITTED; in_flight = m->advertised - remitted; m->advertised = ADV_IDLE + in_flight; return; } /* This should never happen */ if (m->advertised < remitted) pr_warn_ratelimited("Unexpected REMIT msg\n"); /* All messages preceding the REMIT have been read */ m->state = MBR_JOINED; grp->active_cnt--; m->advertised = ADV_IDLE; /* Set oldest pending member to active and advertise */ if (list_empty(&grp->pending)) return; pm = list_first_entry(&grp->pending, struct tipc_member, list); pm->state = MBR_ACTIVE; list_move_tail(&pm->list, &grp->active); grp->active_cnt++; if (pm->advertised <= (ADV_ACTIVE * 3 / 4)) tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); return; default: pr_warn("Received unknown GROUP_PROTO message\n"); } } /* tipc_group_member_evt() - receive and handle a member up/down event */ void tipc_group_member_evt(struct tipc_group *grp, bool *usr_wakeup, int *sk_rcvbuf, struct tipc_msg *hdr, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct tipc_event *evt = (void *)msg_data(hdr); u32 instance = evt->found_lower; u32 node = evt->port.node; u32 port = evt->port.ref; int event = evt->event; struct tipc_member *m; struct net *net; u32 self; if (!grp) return; net = grp->net; self = tipc_own_addr(net); if (!grp->loopback && node == self && port == grp->portid) return; m = tipc_group_find_member(grp, node, port); switch (event) { case TIPC_PUBLISHED: /* Send and wait for arrival of JOIN message if necessary */ if (!m) { m = tipc_group_create_member(grp, node, port, instance, MBR_PUBLISHED); if (!m) break; tipc_group_update_member(m, 0); tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); break; } if (m->state != MBR_JOINING) break; /* Member can be taken into service */ m->instance = instance; m->state = MBR_JOINED; tipc_group_open(m, usr_wakeup); tipc_group_update_member(m, 0); tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); tipc_group_create_event(grp, m, TIPC_PUBLISHED, m->bc_syncpt, inputq); break; case TIPC_WITHDRAWN: if (!m) break; tipc_group_decr_active(grp, m); m->state = MBR_LEAVING; list_del_init(&m->list); tipc_group_open(m, usr_wakeup); /* Only send event if no LEAVE message can be expected */ if (!tipc_node_is_up(net, node)) tipc_group_create_event(grp, m, TIPC_WITHDRAWN, m->bc_rcv_nxt, inputq); break; default: break; } *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); } int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb) { struct nlattr *group = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_GROUP); if (!group) return -EMSGSIZE; if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID, grp->type) || nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE, grp->instance) || nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, grp->bc_snd_nxt)) goto group_msg_cancel; if (grp->scope == TIPC_NODE_SCOPE) if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_NODE_SCOPE)) goto group_msg_cancel; if (grp->scope == TIPC_CLUSTER_SCOPE) if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE)) goto group_msg_cancel; if (*grp->open) if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_OPEN)) goto group_msg_cancel; nla_nest_end(skb, group); return 0; group_msg_cancel: nla_nest_cancel(skb, group); return -1; } |
| 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner */ #ifndef _NET_BATMAN_ADV_SOFT_INTERFACE_H_ #define _NET_BATMAN_ADV_SOFT_INTERFACE_H_ #include "main.h" #include <linux/kref.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/rtnetlink.h> int batadv_skb_head_push(struct sk_buff *skb, unsigned int len); void batadv_interface_rx(struct net_device *soft_iface, struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node); bool batadv_softif_is_valid(const struct net_device *net_dev); extern struct rtnl_link_ops batadv_link_ops; int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid); void batadv_softif_vlan_release(struct kref *ref); struct batadv_softif_vlan *batadv_softif_vlan_get(struct batadv_priv *bat_priv, unsigned short vid); /** * batadv_softif_vlan_put() - decrease the vlan object refcounter and * possibly release it * @vlan: the vlan object to release */ static inline void batadv_softif_vlan_put(struct batadv_softif_vlan *vlan) { if (!vlan) return; kref_put(&vlan->refcount, batadv_softif_vlan_release); } #endif /* _NET_BATMAN_ADV_SOFT_INTERFACE_H_ */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * llc_output.c - LLC minimal output path * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/export.h> #include <net/llc.h> #include <net/llc_pdu.h> /** * llc_mac_hdr_init - fills MAC header fields * @skb: Address of the frame to initialize its MAC header * @sa: The MAC source address * @da: The MAC destination address * * Fills MAC header fields, depending on MAC type. Returns 0, If MAC type * is a valid type and initialization completes correctly 1, otherwise. */ int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da) { int rc = -EINVAL; switch (skb->dev->type) { case ARPHRD_ETHER: case ARPHRD_LOOPBACK: rc = dev_hard_header(skb, skb->dev, ETH_P_802_2, da, sa, skb->len); if (rc > 0) rc = 0; break; default: break; } return rc; } /** * llc_build_and_send_ui_pkt - unitdata request interface for upper layers * @sap: sap to use * @skb: packet to send * @dmac: destination mac address * @dsap: destination sap * * Upper layers calls this function when upper layer wants to send data * using connection-less mode communication (UI pdu). * * Accept data frame from network layer to be sent using connection- * less mode communication; timeout/retries handled by network layer; * package primitive as an event and send to SAP event handler */ int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, const unsigned char *dmac, unsigned char dsap) { int rc; llc_pdu_header_init(skb, LLC_PDU_TYPE_U, sap->laddr.lsap, dsap, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); rc = llc_mac_hdr_init(skb, skb->dev->dev_addr, dmac); if (likely(!rc)) rc = dev_queue_xmit(skb); else kfree_skb(skb); return rc; } EXPORT_SYMBOL(llc_mac_hdr_init); EXPORT_SYMBOL(llc_build_and_send_ui_pkt); |
| 2 1763 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_RTNETLINK_H #define __LINUX_RTNETLINK_H #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/wait.h> #include <linux/refcount.h> #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); static inline int rtnetlink_maybe_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo) { return !skb ? 0 : rtnetlink_send(skb, net, pid, group, echo); } extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid); extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, const struct nlmsghdr *nlh, gfp_t flags); extern void rtnl_set_sk_err(struct net *net, u32 group, int error); extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics); extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error); void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, gfp_t flags, int *new_nsid, int new_ifindex); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, int new_ifindex, u32 portid, const struct nlmsghdr *nlh); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); /* RTNL is used as a global lock for all changes to network configuration */ extern void rtnl_lock(void); extern void rtnl_unlock(void); extern int rtnl_trylock(void); extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); extern bool refcount_dec_and_rtnl_lock(refcount_t *r); extern wait_queue_head_t netdev_unregistering_wq; extern struct rw_semaphore pernet_ops_rwsem; extern struct rw_semaphore net_rwsem; #ifdef CONFIG_PROVE_LOCKING extern bool lockdep_rtnl_is_held(void); #else static inline bool lockdep_rtnl_is_held(void) { return true; } #endif /* #ifdef CONFIG_PROVE_LOCKING */ /** * rcu_dereference_rtnl - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * * Do an rcu_dereference(p), but check caller either holds rcu_read_lock() * or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference() */ #define rcu_dereference_rtnl(p) \ rcu_dereference_check(p, lockdep_rtnl_is_held()) /** * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL * @p: The pointer to read, prior to dereferencing * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(), because caller holds RTNL. */ #define rtnl_dereference(p) \ rcu_dereference_protected(p, lockdep_rtnl_is_held()) /** * rcu_replace_pointer_rtnl - replace an RCU pointer under rtnl_lock, returning * its old value * @rp: RCU pointer, whose value is returned * @p: regular pointer * * Perform a replacement under rtnl_lock, where @rp is an RCU-annotated * pointer. The old value of @rp is returned, and @rp is set to @p */ #define rcu_replace_pointer_rtnl(rp, p) \ rcu_replace_pointer(rp, p, lockdep_rtnl_is_held()) static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev) { return rtnl_dereference(dev->ingress_queue); } static inline struct netdev_queue *dev_ingress_queue_rcu(struct net_device *dev) { return rcu_dereference(dev->ingress_queue); } struct netdev_queue *dev_ingress_queue_create(struct net_device *dev); #ifdef CONFIG_NET_INGRESS void net_inc_ingress_queue(void); void net_dec_ingress_queue(void); #endif #ifdef CONFIG_NET_EGRESS void net_inc_egress_queue(void); void net_dec_egress_queue(void); void netdev_xmit_skip_txqueue(bool skip); #endif void rtnetlink_init(void); void __rtnl_unlock(void); void rtnl_kfree_skbs(struct sk_buff *head, struct sk_buff *tail); #define ASSERT_RTNL() \ WARN_ONCE(!rtnl_is_locked(), \ "RTNL: assertion failed at %s (%d)\n", __FILE__, __LINE__) extern int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx); extern int ndo_dflt_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags); extern int ndo_dflt_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid); extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode, u32 flags, u32 mask, int nlflags, u32 filter_mask, int (*vlan_fill)(struct sk_buff *skb, struct net_device *dev, u32 filter_mask)); extern void rtnl_offload_xstats_notify(struct net_device *dev); static inline int rtnl_has_listeners(const struct net *net, u32 group) { struct sock *rtnl = net->rtnl; return netlink_has_listeners(rtnl, group); } /** * rtnl_notify_needed - check if notification is needed * @net: Pointer to the net namespace * @nlflags: netlink ingress message flags * @group: rtnl group * * Based on the ingress message flags and rtnl group, returns true * if a notification is needed, false otherwise. */ static inline bool rtnl_notify_needed(const struct net *net, u16 nlflags, u32 group) { return (nlflags & NLM_F_ECHO) || rtnl_has_listeners(net, group); } #endif /* __LINUX_RTNETLINK_H */ |
| 44 262 262 197 40 40 44 44 507 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * net/tipc/msg.h: Include file for TIPC message header routines * * Copyright (c) 2000-2007, 2014-2017 Ericsson AB * Copyright (c) 2005-2008, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_MSG_H #define _TIPC_MSG_H #include <linux/tipc.h> #include "core.h" /* * Constants and routines used to read and write TIPC payload message headers * * Note: Some items are also used with TIPC internal message headers */ #define TIPC_VERSION 2 struct plist; /* * Payload message users are defined in TIPC's public API: * - TIPC_LOW_IMPORTANCE * - TIPC_MEDIUM_IMPORTANCE * - TIPC_HIGH_IMPORTANCE * - TIPC_CRITICAL_IMPORTANCE */ #define TIPC_SYSTEM_IMPORTANCE 4 /* * Payload message types */ #define TIPC_CONN_MSG 0 #define TIPC_MCAST_MSG 1 #define TIPC_NAMED_MSG 2 #define TIPC_DIRECT_MSG 3 #define TIPC_GRP_MEMBER_EVT 4 #define TIPC_GRP_BCAST_MSG 5 #define TIPC_GRP_MCAST_MSG 6 #define TIPC_GRP_UCAST_MSG 7 /* * Internal message users */ #define BCAST_PROTOCOL 5 #define MSG_BUNDLER 6 #define LINK_PROTOCOL 7 #define CONN_MANAGER 8 #define GROUP_PROTOCOL 9 #define TUNNEL_PROTOCOL 10 #define NAME_DISTRIBUTOR 11 #define MSG_FRAGMENTER 12 #define LINK_CONFIG 13 #define MSG_CRYPTO 14 #define SOCK_WAKEUP 14 /* pseudo user */ #define TOP_SRV 15 /* pseudo user */ /* * Message header sizes */ #define SHORT_H_SIZE 24 /* In-cluster basic payload message */ #define BASIC_H_SIZE 32 /* Basic payload message */ #define NAMED_H_SIZE 40 /* Named payload message */ #define MCAST_H_SIZE 44 /* Multicast payload message */ #define GROUP_H_SIZE 44 /* Group payload message */ #define INT_H_SIZE 40 /* Internal messages */ #define MIN_H_SIZE 24 /* Smallest legal TIPC header size */ #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ #define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE) #define TIPC_MEDIA_INFO_OFFSET 5 extern const int one_page_mtu; struct tipc_skb_cb { union { struct { struct sk_buff *tail; unsigned long nxt_retr; unsigned long retr_stamp; u32 bytes_read; u32 orig_member; u16 chain_imp; u16 ackers; u16 retr_cnt; } __packed; #ifdef CONFIG_TIPC_CRYPTO struct { struct tipc_crypto *rx; struct tipc_aead *last; u8 recurs; } tx_clone_ctx __packed; #endif } __packed; union { struct { u8 validated:1; #ifdef CONFIG_TIPC_CRYPTO u8 encrypted:1; u8 decrypted:1; #define SKB_PROBING 1 #define SKB_GRACING 2 u8 xmit_type:2; u8 tx_clone_deferred:1; #endif }; u8 flags; }; u8 reserved; #ifdef CONFIG_TIPC_CRYPTO void *crypto_ctx; #endif } __packed; #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) struct tipc_msg { __be32 hdr[15]; }; /* struct tipc_gap_ack - TIPC Gap ACK block * @ack: seqno of the last consecutive packet in link deferdq * @gap: number of gap packets since the last ack * * E.g: * link deferdq: 1 2 3 4 10 11 13 14 15 20 * --> Gap ACK blocks: <4, 5>, <11, 1>, <15, 4>, <20, 0> */ struct tipc_gap_ack { __be16 ack; __be16 gap; }; /* struct tipc_gap_ack_blks * @len: actual length of the record * @ugack_cnt: number of Gap ACK blocks for unicast (following the broadcast * ones) * @start_index: starting index for "valid" broadcast Gap ACK blocks * @bgack_cnt: number of Gap ACK blocks for broadcast in the record * @gacks: array of Gap ACK blocks * * 31 16 15 0 * +-------------+-------------+-------------+-------------+ * | bgack_cnt | ugack_cnt | len | * +-------------+-------------+-------------+-------------+ - * | gap | ack | | * +-------------+-------------+-------------+-------------+ > bc gacks * : : : | * +-------------+-------------+-------------+-------------+ - * | gap | ack | | * +-------------+-------------+-------------+-------------+ > uc gacks * : : : | * +-------------+-------------+-------------+-------------+ - */ struct tipc_gap_ack_blks { __be16 len; union { u8 ugack_cnt; u8 start_index; }; u8 bgack_cnt; struct tipc_gap_ack gacks[]; }; #define MAX_GAP_ACK_BLKS 128 #define MAX_GAP_ACK_BLKS_SZ (sizeof(struct tipc_gap_ack_blks) + \ sizeof(struct tipc_gap_ack) * MAX_GAP_ACK_BLKS) static inline struct tipc_msg *buf_msg(struct sk_buff *skb) { return (struct tipc_msg *)skb->data; } static inline u32 msg_word(struct tipc_msg *m, u32 pos) { return ntohl(m->hdr[pos]); } static inline void msg_set_word(struct tipc_msg *m, u32 w, u32 val) { m->hdr[w] = htonl(val); } static inline u32 msg_bits(struct tipc_msg *m, u32 w, u32 pos, u32 mask) { return (msg_word(m, w) >> pos) & mask; } static inline void msg_set_bits(struct tipc_msg *m, u32 w, u32 pos, u32 mask, u32 val) { val = (val & mask) << pos; mask = mask << pos; m->hdr[w] &= ~htonl(mask); m->hdr[w] |= htonl(val); } /* * Word 0 */ static inline u32 msg_version(struct tipc_msg *m) { return msg_bits(m, 0, 29, 7); } static inline void msg_set_version(struct tipc_msg *m) { msg_set_bits(m, 0, 29, 7, TIPC_VERSION); } static inline u32 msg_user(struct tipc_msg *m) { return msg_bits(m, 0, 25, 0xf); } static inline u32 msg_isdata(struct tipc_msg *m) { return msg_user(m) <= TIPC_CRITICAL_IMPORTANCE; } static inline void msg_set_user(struct tipc_msg *m, u32 n) { msg_set_bits(m, 0, 25, 0xf, n); } static inline u32 msg_hdr_sz(struct tipc_msg *m) { return msg_bits(m, 0, 21, 0xf) << 2; } static inline void msg_set_hdr_sz(struct tipc_msg *m, u32 n) { msg_set_bits(m, 0, 21, 0xf, n>>2); } static inline u32 msg_size(struct tipc_msg *m) { return msg_bits(m, 0, 0, 0x1ffff); } static inline u32 msg_blocks(struct tipc_msg *m) { return (msg_size(m) / 1024) + 1; } static inline u32 msg_data_sz(struct tipc_msg *m) { return msg_size(m) - msg_hdr_sz(m); } static inline int msg_non_seq(struct tipc_msg *m) { return msg_bits(m, 0, 20, 1); } static inline void msg_set_non_seq(struct tipc_msg *m, u32 n) { msg_set_bits(m, 0, 20, 1, n); } static inline int msg_is_syn(struct tipc_msg *m) { return msg_bits(m, 0, 17, 1); } static inline void msg_set_syn(struct tipc_msg *m, u32 d) { msg_set_bits(m, 0, 17, 1, d); } static inline int msg_dest_droppable(struct tipc_msg *m) { return msg_bits(m, 0, 19, 1); } static inline void msg_set_dest_droppable(struct tipc_msg *m, u32 d) { msg_set_bits(m, 0, 19, 1, d); } static inline int msg_is_keepalive(struct tipc_msg *m) { return msg_bits(m, 0, 19, 1); } static inline void msg_set_is_keepalive(struct tipc_msg *m, u32 d) { msg_set_bits(m, 0, 19, 1, d); } static inline int msg_src_droppable(struct tipc_msg *m) { return msg_bits(m, 0, 18, 1); } static inline void msg_set_src_droppable(struct tipc_msg *m, u32 d) { msg_set_bits(m, 0, 18, 1, d); } static inline int msg_ack_required(struct tipc_msg *m) { return msg_bits(m, 0, 18, 1); } static inline void msg_set_ack_required(struct tipc_msg *m) { msg_set_bits(m, 0, 18, 1, 1); } static inline int msg_nagle_ack(struct tipc_msg *m) { return msg_bits(m, 0, 18, 1); } static inline void msg_set_nagle_ack(struct tipc_msg *m) { msg_set_bits(m, 0, 18, 1, 1); } static inline bool msg_is_rcast(struct tipc_msg *m) { return msg_bits(m, 0, 18, 0x1); } static inline void msg_set_is_rcast(struct tipc_msg *m, bool d) { msg_set_bits(m, 0, 18, 0x1, d); } static inline void msg_set_size(struct tipc_msg *m, u32 sz) { m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz); } static inline unchar *msg_data(struct tipc_msg *m) { return ((unchar *)m) + msg_hdr_sz(m); } static inline struct tipc_msg *msg_inner_hdr(struct tipc_msg *m) { return (struct tipc_msg *)msg_data(m); } /* * Word 1 */ static inline u32 msg_type(struct tipc_msg *m) { return msg_bits(m, 1, 29, 0x7); } static inline void msg_set_type(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 29, 0x7, n); } static inline int msg_in_group(struct tipc_msg *m) { int mtyp = msg_type(m); return mtyp >= TIPC_GRP_MEMBER_EVT && mtyp <= TIPC_GRP_UCAST_MSG; } static inline bool msg_is_grp_evt(struct tipc_msg *m) { return msg_type(m) == TIPC_GRP_MEMBER_EVT; } static inline u32 msg_named(struct tipc_msg *m) { return msg_type(m) == TIPC_NAMED_MSG; } static inline u32 msg_mcast(struct tipc_msg *m) { int mtyp = msg_type(m); return ((mtyp == TIPC_MCAST_MSG) || (mtyp == TIPC_GRP_BCAST_MSG) || (mtyp == TIPC_GRP_MCAST_MSG)); } static inline u32 msg_connected(struct tipc_msg *m) { return msg_type(m) == TIPC_CONN_MSG; } static inline u32 msg_direct(struct tipc_msg *m) { return msg_type(m) == TIPC_DIRECT_MSG; } static inline u32 msg_errcode(struct tipc_msg *m) { return msg_bits(m, 1, 25, 0xf); } static inline void msg_set_errcode(struct tipc_msg *m, u32 err) { msg_set_bits(m, 1, 25, 0xf, err); } static inline void msg_set_bulk(struct tipc_msg *m) { msg_set_bits(m, 1, 28, 0x1, 1); } static inline u32 msg_is_bulk(struct tipc_msg *m) { return msg_bits(m, 1, 28, 0x1); } static inline void msg_set_last_bulk(struct tipc_msg *m) { msg_set_bits(m, 1, 27, 0x1, 1); } static inline u32 msg_is_last_bulk(struct tipc_msg *m) { return msg_bits(m, 1, 27, 0x1); } static inline void msg_set_non_legacy(struct tipc_msg *m) { msg_set_bits(m, 1, 26, 0x1, 1); } static inline u32 msg_is_legacy(struct tipc_msg *m) { return !msg_bits(m, 1, 26, 0x1); } static inline u32 msg_reroute_cnt(struct tipc_msg *m) { return msg_bits(m, 1, 21, 0xf); } static inline void msg_incr_reroute_cnt(struct tipc_msg *m) { msg_set_bits(m, 1, 21, 0xf, msg_reroute_cnt(m) + 1); } static inline u32 msg_lookup_scope(struct tipc_msg *m) { return msg_bits(m, 1, 19, 0x3); } static inline void msg_set_lookup_scope(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 19, 0x3, n); } static inline u16 msg_bcast_ack(struct tipc_msg *m) { return msg_bits(m, 1, 0, 0xffff); } static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n) { msg_set_bits(m, 1, 0, 0xffff, n); } /* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch * link peer session number */ static inline bool msg_dest_session_valid(struct tipc_msg *m) { return msg_bits(m, 1, 16, 0x1); } static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid) { msg_set_bits(m, 1, 16, 0x1, valid); } static inline u16 msg_dest_session(struct tipc_msg *m) { return msg_bits(m, 1, 0, 0xffff); } static inline void msg_set_dest_session(struct tipc_msg *m, u16 n) { msg_set_bits(m, 1, 0, 0xffff, n); } /* * Word 2 */ static inline u16 msg_ack(struct tipc_msg *m) { return msg_bits(m, 2, 16, 0xffff); } static inline void msg_set_ack(struct tipc_msg *m, u16 n) { msg_set_bits(m, 2, 16, 0xffff, n); } static inline u16 msg_seqno(struct tipc_msg *m) { return msg_bits(m, 2, 0, 0xffff); } static inline void msg_set_seqno(struct tipc_msg *m, u16 n) { msg_set_bits(m, 2, 0, 0xffff, n); } /* * Words 3-10 */ static inline u32 msg_importance(struct tipc_msg *m) { int usr = msg_user(m); if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m))) return usr; if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)) return msg_bits(m, 9, 0, 0x7); return TIPC_SYSTEM_IMPORTANCE; } static inline void msg_set_importance(struct tipc_msg *m, u32 i) { int usr = msg_user(m); if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))) msg_set_bits(m, 9, 0, 0x7, i); else if (i < TIPC_SYSTEM_IMPORTANCE) msg_set_user(m, i); else pr_warn("Trying to set illegal importance in message\n"); } static inline u32 msg_prevnode(struct tipc_msg *m) { return msg_word(m, 3); } static inline void msg_set_prevnode(struct tipc_msg *m, u32 a) { msg_set_word(m, 3, a); } static inline u32 msg_origport(struct tipc_msg *m) { if (msg_user(m) == MSG_FRAGMENTER) m = msg_inner_hdr(m); return msg_word(m, 4); } static inline void msg_set_origport(struct tipc_msg *m, u32 p) { msg_set_word(m, 4, p); } static inline u16 msg_named_seqno(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); } static inline void msg_set_named_seqno(struct tipc_msg *m, u16 n) { msg_set_bits(m, 4, 0, 0xffff, n); } static inline u32 msg_destport(struct tipc_msg *m) { return msg_word(m, 5); } static inline void msg_set_destport(struct tipc_msg *m, u32 p) { msg_set_word(m, 5, p); } static inline u32 msg_mc_netid(struct tipc_msg *m) { return msg_word(m, 5); } static inline void msg_set_mc_netid(struct tipc_msg *m, u32 p) { msg_set_word(m, 5, p); } static inline int msg_short(struct tipc_msg *m) { return msg_hdr_sz(m) == SHORT_H_SIZE; } static inline u32 msg_orignode(struct tipc_msg *m) { if (likely(msg_short(m))) return msg_prevnode(m); return msg_word(m, 6); } static inline void msg_set_orignode(struct tipc_msg *m, u32 a) { msg_set_word(m, 6, a); } static inline u32 msg_destnode(struct tipc_msg *m) { return msg_word(m, 7); } static inline void msg_set_destnode(struct tipc_msg *m, u32 a) { msg_set_word(m, 7, a); } static inline u32 msg_nametype(struct tipc_msg *m) { return msg_word(m, 8); } static inline void msg_set_nametype(struct tipc_msg *m, u32 n) { msg_set_word(m, 8, n); } static inline u32 msg_nameinst(struct tipc_msg *m) { return msg_word(m, 9); } static inline u32 msg_namelower(struct tipc_msg *m) { return msg_nameinst(m); } static inline void msg_set_namelower(struct tipc_msg *m, u32 n) { msg_set_word(m, 9, n); } static inline void msg_set_nameinst(struct tipc_msg *m, u32 n) { msg_set_namelower(m, n); } static inline u32 msg_nameupper(struct tipc_msg *m) { return msg_word(m, 10); } static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) { msg_set_word(m, 10, n); } /* * Constants and routines used to read and write TIPC internal message headers */ /* * Connection management protocol message types */ #define CONN_PROBE 0 #define CONN_PROBE_REPLY 1 #define CONN_ACK 2 /* * Name distributor message types */ #define PUBLICATION 0 #define WITHDRAWAL 1 /* * Segmentation message types */ #define FIRST_FRAGMENT 0 #define FRAGMENT 1 #define LAST_FRAGMENT 2 /* * Link management protocol message types */ #define STATE_MSG 0 #define RESET_MSG 1 #define ACTIVATE_MSG 2 /* * Changeover tunnel message types */ #define SYNCH_MSG 0 #define FAILOVER_MSG 1 /* * Config protocol message types */ #define DSC_REQ_MSG 0 #define DSC_RESP_MSG 1 #define DSC_TRIAL_MSG 2 #define DSC_TRIAL_FAIL_MSG 3 /* * Group protocol message types */ #define GRP_JOIN_MSG 0 #define GRP_LEAVE_MSG 1 #define GRP_ADV_MSG 2 #define GRP_ACK_MSG 3 #define GRP_RECLAIM_MSG 4 #define GRP_REMIT_MSG 5 /* Crypto message types */ #define KEY_DISTR_MSG 0 /* * Word 1 */ static inline u32 msg_seq_gap(struct tipc_msg *m) { return msg_bits(m, 1, 16, 0x1fff); } static inline void msg_set_seq_gap(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 16, 0x1fff, n); } static inline u32 msg_node_sig(struct tipc_msg *m) { return msg_bits(m, 1, 0, 0xffff); } static inline void msg_set_node_sig(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 0, 0xffff, n); } static inline u32 msg_node_capabilities(struct tipc_msg *m) { return msg_bits(m, 1, 15, 0x1fff); } static inline void msg_set_node_capabilities(struct tipc_msg *m, u32 n) { msg_set_bits(m, 1, 15, 0x1fff, n); } /* * Word 2 */ static inline u32 msg_dest_domain(struct tipc_msg *m) { return msg_word(m, 2); } static inline void msg_set_dest_domain(struct tipc_msg *m, u32 n) { msg_set_word(m, 2, n); } static inline void msg_set_bcgap_after(struct tipc_msg *m, u32 n) { msg_set_bits(m, 2, 16, 0xffff, n); } static inline u32 msg_bcgap_to(struct tipc_msg *m) { return msg_bits(m, 2, 0, 0xffff); } static inline void msg_set_bcgap_to(struct tipc_msg *m, u32 n) { msg_set_bits(m, 2, 0, 0xffff, n); } /* * Word 4 */ static inline u32 msg_last_bcast(struct tipc_msg *m) { return msg_bits(m, 4, 16, 0xffff); } static inline u32 msg_bc_snd_nxt(struct tipc_msg *m) { return msg_last_bcast(m) + 1; } static inline void msg_set_last_bcast(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 16, 0xffff, n); } static inline u32 msg_nof_fragms(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); } static inline void msg_set_nof_fragms(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 0, 0xffff, n); } static inline u32 msg_fragm_no(struct tipc_msg *m) { return msg_bits(m, 4, 16, 0xffff); } static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n) { msg_set_bits(m, 4, 16, 0xffff, n); } static inline u16 msg_next_sent(struct tipc_msg *m) { return msg_bits(m, 4, 0, 0xffff); } static inline void msg_set_next_sent(struct tipc_msg *m, u16 n) { msg_set_bits(m, 4, 0, 0xffff, n); } static inline u32 msg_bc_netid(struct tipc_msg *m) { return msg_word(m, 4); } static inline void msg_set_bc_netid(struct tipc_msg *m, u32 id) { msg_set_word(m, 4, id); } static inline u32 msg_link_selector(struct tipc_msg *m) { if (msg_user(m) == MSG_FRAGMENTER) m = (void *)msg_data(m); return msg_bits(m, 4, 0, 1); } /* * Word 5 */ static inline u16 msg_session(struct tipc_msg *m) { return msg_bits(m, 5, 16, 0xffff); } static inline void msg_set_session(struct tipc_msg *m, u16 n) { msg_set_bits(m, 5, 16, 0xffff, n); } static inline u32 msg_probe(struct tipc_msg *m) { return msg_bits(m, 5, 0, 1); } static inline void msg_set_probe(struct tipc_msg *m, u32 val) { msg_set_bits(m, 5, 0, 1, val); } static inline char msg_net_plane(struct tipc_msg *m) { return msg_bits(m, 5, 1, 7) + 'A'; } static inline void msg_set_net_plane(struct tipc_msg *m, char n) { msg_set_bits(m, 5, 1, 7, (n - 'A')); } static inline u32 msg_linkprio(struct tipc_msg *m) { return msg_bits(m, 5, 4, 0x1f); } static inline void msg_set_linkprio(struct tipc_msg *m, u32 n) { msg_set_bits(m, 5, 4, 0x1f, n); } static inline u32 msg_bearer_id(struct tipc_msg *m) { return msg_bits(m, 5, 9, 0x7); } static inline void msg_set_bearer_id(struct tipc_msg *m, u32 n) { msg_set_bits(m, 5, 9, 0x7, n); } static inline u32 msg_redundant_link(struct tipc_msg *m) { return msg_bits(m, 5, 12, 0x1); } static inline void msg_set_redundant_link(struct tipc_msg *m, u32 r) { msg_set_bits(m, 5, 12, 0x1, r); } static inline u32 msg_peer_stopping(struct tipc_msg *m) { return msg_bits(m, 5, 13, 0x1); } static inline void msg_set_peer_stopping(struct tipc_msg *m, u32 s) { msg_set_bits(m, 5, 13, 0x1, s); } static inline bool msg_bc_ack_invalid(struct tipc_msg *m) { switch (msg_user(m)) { case BCAST_PROTOCOL: case NAME_DISTRIBUTOR: case LINK_PROTOCOL: return msg_bits(m, 5, 14, 0x1); default: return false; } } static inline void msg_set_bc_ack_invalid(struct tipc_msg *m, bool invalid) { msg_set_bits(m, 5, 14, 0x1, invalid); } static inline char *msg_media_addr(struct tipc_msg *m) { return (char *)&m->hdr[TIPC_MEDIA_INFO_OFFSET]; } static inline u32 msg_bc_gap(struct tipc_msg *m) { return msg_bits(m, 8, 0, 0x3ff); } static inline void msg_set_bc_gap(struct tipc_msg *m, u32 n) { msg_set_bits(m, 8, 0, 0x3ff, n); } /* * Word 9 */ static inline u16 msg_msgcnt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_msgcnt(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u16 msg_syncpt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_syncpt(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u32 msg_conn_ack(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_conn_ack(struct tipc_msg *m, u32 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u16 msg_adv_win(struct tipc_msg *m) { return msg_bits(m, 9, 0, 0xffff); } static inline void msg_set_adv_win(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 0, 0xffff, n); } static inline u32 msg_max_pkt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff) * 4; } static inline void msg_set_max_pkt(struct tipc_msg *m, u32 n) { msg_set_bits(m, 9, 16, 0xffff, (n / 4)); } static inline u32 msg_link_tolerance(struct tipc_msg *m) { return msg_bits(m, 9, 0, 0xffff); } static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) { msg_set_bits(m, 9, 0, 0xffff, n); } static inline u16 msg_grp_bc_syncpt(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_grp_bc_syncpt(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u16 msg_grp_bc_acked(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_grp_bc_acked(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } static inline u16 msg_grp_remitted(struct tipc_msg *m) { return msg_bits(m, 9, 16, 0xffff); } static inline void msg_set_grp_remitted(struct tipc_msg *m, u16 n) { msg_set_bits(m, 9, 16, 0xffff, n); } /* Word 10 */ static inline u16 msg_grp_evt(struct tipc_msg *m) { return msg_bits(m, 10, 0, 0x3); } static inline void msg_set_grp_evt(struct tipc_msg *m, int n) { msg_set_bits(m, 10, 0, 0x3, n); } static inline u16 msg_grp_bc_ack_req(struct tipc_msg *m) { return msg_bits(m, 10, 0, 0x1); } static inline void msg_set_grp_bc_ack_req(struct tipc_msg *m, bool n) { msg_set_bits(m, 10, 0, 0x1, n); } static inline u16 msg_grp_bc_seqno(struct tipc_msg *m) { return msg_bits(m, 10, 16, 0xffff); } static inline void msg_set_grp_bc_seqno(struct tipc_msg *m, u32 n) { msg_set_bits(m, 10, 16, 0xffff, n); } static inline bool msg_peer_link_is_up(struct tipc_msg *m) { if (likely(msg_user(m) != LINK_PROTOCOL)) return true; if (msg_type(m) == STATE_MSG) return true; return false; } static inline bool msg_peer_node_is_up(struct tipc_msg *m) { if (msg_peer_link_is_up(m)) return true; return msg_redundant_link(m); } static inline bool msg_is_reset(struct tipc_msg *hdr) { return (msg_user(hdr) == LINK_PROTOCOL) && (msg_type(hdr) == RESET_MSG); } /* Word 13 */ static inline void msg_set_peer_net_hash(struct tipc_msg *m, u32 n) { msg_set_word(m, 13, n); } static inline u32 msg_peer_net_hash(struct tipc_msg *m) { return msg_word(m, 13); } /* Word 14 */ static inline u32 msg_sugg_node_addr(struct tipc_msg *m) { return msg_word(m, 14); } static inline void msg_set_sugg_node_addr(struct tipc_msg *m, u32 n) { msg_set_word(m, 14, n); } static inline void msg_set_node_id(struct tipc_msg *hdr, u8 *id) { memcpy(msg_data(hdr), id, 16); } static inline u8 *msg_node_id(struct tipc_msg *hdr) { return (u8 *)msg_data(hdr); } struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp); bool tipc_msg_validate(struct sk_buff **_skb); bool tipc_msg_reverse(u32 own_addr, struct sk_buff **skb, int err); void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb, struct sk_buff_head *xmitq); void tipc_msg_init(u32 own_addr, struct tipc_msg *m, u32 user, u32 type, u32 hsize, u32 destnode); struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz, uint data_sz, u32 dnode, u32 onode, u32 dport, u32 oport, int errcode); int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf); bool tipc_msg_try_bundle(struct sk_buff *tskb, struct sk_buff **skb, u32 mss, u32 dnode, bool *new_bundle); bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos); int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr, int pktmax, struct sk_buff_head *frags); int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, int dsz, int mtu, struct sk_buff_head *list); int tipc_msg_append(struct tipc_msg *hdr, struct msghdr *m, int dlen, int mss, struct sk_buff_head *txq); bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err); bool tipc_msg_assemble(struct sk_buff_head *list); bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq); bool tipc_msg_pskb_copy(u32 dst, struct sk_buff_head *msg, struct sk_buff_head *cpy); bool __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno, struct sk_buff *skb); bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy); static inline u16 buf_seqno(struct sk_buff *skb) { return msg_seqno(buf_msg(skb)); } static inline int buf_roundup_len(struct sk_buff *skb) { return (skb->len / 1024 + 1) * 1024; } /* tipc_skb_peek(): peek and reserve first buffer in list * @list: list to be peeked in * Returns pointer to first buffer in list, if any */ static inline struct sk_buff *tipc_skb_peek(struct sk_buff_head *list, spinlock_t *lock) { struct sk_buff *skb; spin_lock_bh(lock); skb = skb_peek(list); if (skb) skb_get(skb); spin_unlock_bh(lock); return skb; } /* tipc_skb_peek_port(): find a destination port, ignoring all destinations * up to and including 'filter'. * Note: ignoring previously tried destinations minimizes the risk of * contention on the socket lock * @list: list to be peeked in * @filter: last destination to be ignored from search * Returns a destination port number, of applicable. */ static inline u32 tipc_skb_peek_port(struct sk_buff_head *list, u32 filter) { struct sk_buff *skb; u32 dport = 0; bool ignore = true; spin_lock_bh(&list->lock); skb_queue_walk(list, skb) { dport = msg_destport(buf_msg(skb)); if (!filter || skb_queue_is_last(list, skb)) break; if (dport == filter) ignore = false; else if (!ignore) break; } spin_unlock_bh(&list->lock); return dport; } /* tipc_skb_dequeue(): unlink first buffer with dest 'dport' from list * @list: list to be unlinked from * @dport: selection criteria for buffer to unlink */ static inline struct sk_buff *tipc_skb_dequeue(struct sk_buff_head *list, u32 dport) { struct sk_buff *_skb, *tmp, *skb = NULL; spin_lock_bh(&list->lock); skb_queue_walk_safe(list, _skb, tmp) { if (msg_destport(buf_msg(_skb)) == dport) { __skb_unlink(_skb, list); skb = _skb; break; } } spin_unlock_bh(&list->lock); return skb; } /* tipc_skb_queue_splice_tail - append an skb list to lock protected list * @list: the new list to append. Not lock protected * @head: target list. Lock protected. */ static inline void tipc_skb_queue_splice_tail(struct sk_buff_head *list, struct sk_buff_head *head) { spin_lock_bh(&head->lock); skb_queue_splice_tail(list, head); spin_unlock_bh(&head->lock); } /* tipc_skb_queue_splice_tail_init - merge two lock protected skb lists * @list: the new list to add. Lock protected. Will be reinitialized * @head: target list. Lock protected. */ static inline void tipc_skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { struct sk_buff_head tmp; __skb_queue_head_init(&tmp); spin_lock_bh(&list->lock); skb_queue_splice_tail_init(list, &tmp); spin_unlock_bh(&list->lock); tipc_skb_queue_splice_tail(&tmp, head); } /* __tipc_skb_dequeue() - dequeue the head skb according to expected seqno * @list: list to be dequeued from * @seqno: seqno of the expected msg * * returns skb dequeued from the list if its seqno is less than or equal to * the expected one, otherwise the skb is still hold * * Note: must be used with appropriate locks held only */ static inline struct sk_buff *__tipc_skb_dequeue(struct sk_buff_head *list, u16 seqno) { struct sk_buff *skb = skb_peek(list); if (skb && less_eq(buf_seqno(skb), seqno)) { __skb_unlink(skb, list); return skb; } return NULL; } #endif |
| 1274 1106 1107 1107 1107 1274 1274 1274 1274 46 884 42 904 904 904 904 1194 156 1107 1107 1107 1107 1107 1107 1107 1107 1211 1 1210 1210 848 1209 1210 1169 1210 1193 1107 1210 1211 1062 1062 1055 1205 1205 1205 1205 1196 1010 904 1 1 1 1482 1482 1481 1482 1482 1482 156 156 156 156 1482 1482 1482 1 1 157 156 156 156 156 1 1185 1185 1185 1185 1184 1185 1185 1185 1185 1168 1168 1168 1168 1168 1015 1164 1164 1168 1168 1168 1168 1168 1168 1570 1570 1570 1431 1431 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ static int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ static unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ static int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ static int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ static unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* consolidated parameters for balance_dirty_pages() and its subroutines */ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *dom; struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ #endif struct bdi_writeback *wb; struct fprop_local_percpu *wb_completions; unsigned long avail; /* dirtyable */ unsigned long dirty; /* file_dirty + write + nfs */ unsigned long thresh; /* dirty threshold */ unsigned long bg_thresh; /* dirty background threshold */ unsigned long wb_dirty; /* per-wb counterparts */ unsigned long wb_thresh; unsigned long wb_bg_thresh; unsigned long pos_ratio; }; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100 * BDI_RATIO_SCALE) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; if (bg_thresh >= thresh) bg_thresh = thresh / 2; tsk = current; if (rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_task(tsk)) dirty += dirty / 4; return dirty; } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } #ifdef CONFIG_SYSCTL static int dirty_background_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } static int dirty_background_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_ratio = 0; return ret; } static int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { writeback_set_ratelimit(); vm_dirty_bytes = 0; } return ret; } static int dirty_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } #endif static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_add(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac, long nr) { __fprop_add_percpu_max(&dom->completions, completions, max_prop_frac, nr); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from __folio_end_writeback(). */ static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr) { struct wb_domain *cgdom; wb_stat_mod(wb, WB_WRITTEN, nr); wb_domain_writeout_add(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac, nr); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_add(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac, nr); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_add(wb, 1); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = from_timer(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { del_timer_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; static int bdi_check_pages_limit(unsigned long pages) { unsigned long max_dirty_pages = global_dirtyable_memory(); if (pages > max_dirty_pages) return -EINVAL; return 0; } static unsigned long bdi_ratio_from_pages(unsigned long pages) { unsigned long background_thresh; unsigned long dirty_thresh; unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; } static u64 bdi_get_bytes(unsigned int ratio) { unsigned long background_thresh; unsigned long dirty_thresh; u64 bytes; global_dirty_limits(&background_thresh, &dirty_thresh); bytes = (dirty_thresh * PAGE_SIZE * ratio) / BDI_RATIO_SCALE / 100; return bytes; } static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { unsigned int delta; int ret = 0; if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { if (min_ratio < bdi->min_ratio) { delta = bdi->min_ratio - min_ratio; bdi_min_ratio -= delta; bdi->min_ratio = min_ratio; } else { delta = min_ratio - bdi->min_ratio; if (bdi_min_ratio + delta < 100 * BDI_RATIO_SCALE) { bdi_min_ratio += delta; bdi->min_ratio = min_ratio; } else { ret = -EINVAL; } } } spin_unlock_bh(&bdi_lock); return ret; } static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { int ret = 0; if (max_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio); } int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio * BDI_RATIO_SCALE); } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio * BDI_RATIO_SCALE); } EXPORT_SYMBOL(bdi_set_max_ratio); u64 bdi_get_min_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->min_ratio); } int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; unsigned long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); return __bdi_set_min_ratio(bdi, min_ratio); } u64 bdi_get_max_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->max_ratio); } int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; unsigned long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit) { if (strict_limit > 1) return -EINVAL; spin_lock_bh(&bdi_lock); if (strict_limit) bdi->capabilities |= BDI_CAP_STRICTLIMIT; else bdi->capabilities &= ~BDI_CAP_STRICTLIMIT; spin_unlock_bh(&bdi_lock); return 0; } static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } /** * __wb_calc_thresh - @wb's share of dirty throttling threshold * @dtc: dirty_throttle_context of interest * * Note that balance_dirty_pages() will only seriously take it as a hard limit * when sleeping max_pause per page is not enough to keep the dirty pages under * control. For example, when the device is completely stalled due to some error * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty and PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; u64 wb_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this BDI's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 * BDI_RATIO_SCALE - bdi_min_ratio)) / (100 * BDI_RATIO_SCALE); wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); if (wb_thresh > (thresh * wb_max_ratio) / (100 * BDI_RATIO_SCALE)) wb_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb), .thresh = thresh }; return __wb_calc_thresh(&gdtc); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 * * * * * * * * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty < 8) { dtc->pos_ratio = min_t(long long, pos_ratio * 2, 2 << RATELIMIT_CALC_SHIFT); return; } if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to folio_redirty_for_writepage(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; WRITE_ONCE(wb->avg_write_bandwidth, avg); } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_dirty_limit(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". * * We rampup dirty_ratelimit forcibly if wb_dirty is low because * it's possible that wb_thresh is close to zero due to inactivity * of backing device. */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; if (dtc->wb_dirty < 8) setpoint = dtc->wb_dirty + 1; else setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL)); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed; unsigned long dirtied; unsigned long written; spin_lock(&wb->list_lock); /* * Lockless checks for elapsed time are racy and delayed update after * IO completion doesn't do it at all (to make sure written pages are * accounted reasonably quickly). Make sure elapsed >= 1 to avoid * division errors. */ elapsed = max(now - wb->bw_time_stamp, 1UL); dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); if (update_ratelimit) { domain_update_dirty_limit(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_dirty_limit(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); wb->dirtied_stamp = dirtied; wb->written_stamp = written; WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, false); } /* Interval after which we consider wb idle and don't estimate bandwidth */ #define WB_BANDWIDTH_IDLE_JIF (HZ) static void wb_bandwidth_estimate_start(struct bdi_writeback *wb) { unsigned long now = jiffies; unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp); if (elapsed > WB_BANDWIDTH_IDLE_JIF && !atomic_read(&wb->writeback_inodes)) { spin_lock(&wb->list_lock); wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED); wb->written_stamp = wb_stat(wb, WB_WRITTEN); WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth)); long lo = ilog2(READ_ONCE(wb->dirty_ratelimit)); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static int balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied, unsigned int flags) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_reclaimable; /* = file_dirty */ long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; bool dirty_exceeded = false; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; int ret = 0; for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; unsigned long m_dirty = 0; /* stop bogus uninit warnings */ unsigned long m_thresh = 0; unsigned long m_bg_thresh = 0; nr_reclaimable = global_node_page_state(NR_FILE_DIRTY); gdtc->avail = global_dirtyable_memory(); gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); domain_dirty_limits(gdtc); if (unlikely(strictlimit)) { wb_dirty_limits(gdtc); dirty = gdtc->wb_dirty; thresh = gdtc->wb_thresh; bg_thresh = gdtc->wb_bg_thresh; } else { dirty = gdtc->dirty; thresh = gdtc->thresh; bg_thresh = gdtc->bg_thresh; } if (mdtc) { unsigned long filepages, headroom, writeback; /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc->dirty += writeback; mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); if (unlikely(strictlimit)) { wb_dirty_limits(mdtc); m_dirty = mdtc->wb_dirty; m_thresh = mdtc->wb_thresh; m_bg_thresh = mdtc->wb_bg_thresh; } else { m_dirty = mdtc->dirty; m_thresh = mdtc->thresh; m_bg_thresh = mdtc->bg_thresh; } } /* * In laptop mode, we wait until hitting the higher threshold * before starting background writeout, and then write out all * the way down to the lower threshold. So slow writers cause * minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (!laptop_mode && nr_reclaimable > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb); /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the wb limits are ramping up in case of !strictlimit. * * In strictlimit case make decision based on the wb counters * and limits. Small writeouts when the wb limits are ramping * up are the price we consciously pay for strictlimit-ing. * * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && (!mdtc || m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { unsigned long intv; unsigned long m_intv; free_running: intv = dirty_poll_interval(dirty, thresh); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = dirty_poll_interval(m_dirty, m_thresh); current->nr_dirtied_pause = min(intv, m_intv); break; } /* Start writeback even when in laptop mode */ if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ if (!strictlimit) { wb_dirty_limits(gdtc); if ((current->flags & PF_LOCAL_THROTTLE) && gdtc->wb_dirty < dirty_freerun_ceiling(gdtc->wb_thresh, gdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be throttled * when below the per-wb freerun ceiling. */ goto free_running; } dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && ((gdtc->dirty > gdtc->thresh) || strictlimit); wb_position_ratio(gdtc); sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ if (!strictlimit) { wb_dirty_limits(mdtc); if ((current->flags & PF_LOCAL_THROTTLE) && mdtc->wb_dirty < dirty_freerun_ceiling(mdtc->wb_thresh, mdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be * throttled when below the per-wb * freerun ceiling. */ goto free_running; } dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && ((mdtc->dirty > mdtc->thresh) || strictlimit); wb_position_ratio(mdtc); if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } if (dirty_exceeded != wb->dirty_exceeded) wb->dirty_exceeded = dirty_exceeded; if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) __wb_update_bandwidth(gdtc, mdtc, true); /* throttle according to the chosen dtc */ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit); task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); if (flags & BDP_ASYNC) { ret = -EAGAIN; break; } __set_current_state(TASK_KILLABLE); bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponsive NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } return ret; } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited_flags - Balance dirty memory state. * @mapping: address_space which was dirtied. * @flags: BDP flags. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * See balance_dirty_pages_ratelimited() for details. * * Return: If @flags contains BDP_ASYNC, it may return -EAGAIN to * indicate that memory is out of balance and the caller must wait * for I/O to complete. Otherwise, it will return 0 to indicate * that either memory was already in balance, or it was able to sleep * until the amount of dirty memory returned to balance. */ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int ret = 0; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return ret; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) ret = balance_dirty_pages(wb, current->nr_dirtied, flags); wb_put(wb); return ret; } EXPORT_SYMBOL_GPL(balance_dirty_pages_ratelimited_flags); /** * balance_dirty_pages_ratelimited - balance dirty memory state. * @mapping: address_space which was dirtied. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * Once we're over the dirty memory limit we decrease the ratelimiting * by a lot, to prevent individual processes from overshooting the limit * by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { balance_dirty_pages_ratelimited_flags(mapping, 0); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; unsigned long reclaimable; unsigned long thresh; /* * Similar to balance_dirty_pages() but ignores pages being written * as we're trying to decide whether to put more under writeback. */ gdtc->avail = global_dirtyable_memory(); gdtc->dirty = global_node_page_state(NR_FILE_DIRTY); domain_dirty_limits(gdtc); if (gdtc->dirty > gdtc->bg_thresh) return true; thresh = wb_calc_thresh(gdtc->wb, gdtc->bg_thresh); if (thresh < 2 * wb_stat_error()) reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); else reclaimable = wb_stat(wb, WB_RECLAIMABLE); if (reclaimable > thresh) return true; if (mdtc) { unsigned long filepages, headroom, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); /* ditto, ignore writeback */ if (mdtc->dirty > mdtc->bg_thresh) return true; thresh = wb_calc_thresh(mdtc->wb, mdtc->bg_thresh); if (thresh < 2 * wb_stat_error()) reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); else reclaimable = wb_stat(wb, WB_RECLAIMABLE); if (reclaimable > thresh) return true; } return false; } #ifdef CONFIG_SYSCTL /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ static int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #endif void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = from_timer(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) del_timer(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } #ifdef CONFIG_SYSCTL /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; static struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", .data = &dirty_background_bytes, .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", .data = &vm_dirty_ratio, .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", .data = &vm_dirty_bytes, .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, .proc_handler = dirty_bytes_handler, .extra1 = (void *)&dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), .mode = 0644, .proc_handler = dirty_writeback_centisecs_handler, }, { .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_HIGHMEM { .procname = "highmem_is_dirtyable", .data = &vm_highmem_is_dirtyable, .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, {} }; #endif /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_page_writeback_sysctls); #endif } /** * tag_pages_for_writeback - tag pages to be written by write_cache_pages * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is * that write_cache_pages (or whoever calls this function) will then use * TOWRITE tag to identify pages eligible for writeback. This mechanism is * used to avoid livelocking of writeback by a process steadily creating new * dirty pages in the file (thus it is important for this function to be quick * so that it can tag pages faster than a dirtying process can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() * and msync() need to guarantee that all the data which was dirty at the time * the call was made get new I/O started against them. If wbc->sync_mode is * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. * * To avoid livelocks (when other process dirties new pages), we first tag * pages which should be written back with TOWRITE tag and only then start * writing them. For data-integrity sync we have to be careful so that we do * not miss some pages (e.g., because some other process has cleared TOWRITE * tag we set). The rule we follow is that TOWRITE tag can be cleared only * by the process clearing the DIRTY tag (and submitting the page for IO). * * To avoid deadlocks between range_cyclic writeback and callers that hold * pages in PageWriteback to aggregate IO until write_cache_pages() returns, * we do not loop back to the start of the file. Doing so causes a page * lock/page writeback access order inversion - we should only ever lock * multiple pages in ascending page->index order, and looping back to the start * of the file violates that rule and causes deadlocks. * * Return: %0 on success, negative error code otherwise */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { int ret = 0; int done = 0; int error; struct folio_batch fbatch; int nr_folios; pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; int range_whole = 0; xa_mark_t tag; folio_batch_init(&fbatch); if (wbc->range_cyclic) { index = mapping->writeback_index; /* prev offset */ end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { tag_pages_for_writeback(mapping, index, end); tag = PAGECACHE_TAG_TOWRITE; } else { tag = PAGECACHE_TAG_DIRTY; } done_index = index; while (!done && (index <= end)) { int i; nr_folios = filemap_get_folios_tag(mapping, &index, end, tag, &fbatch); if (nr_folios == 0) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; unsigned long nr; done_index = folio->index; folio_lock(folio); /* * Page truncated or invalidated. We can freely skip it * then, even for data integrity operations: the page * has disappeared concurrently, so there could be no * real expectation of this data integrity operation * even if there is now a new, dirty page at the same * pagecache address. */ if (unlikely(folio->mapping != mapping)) { continue_unlock: folio_unlock(folio); continue; } if (!folio_test_dirty(folio)) { /* someone wrote it for us */ goto continue_unlock; } if (folio_test_writeback(folio)) { if (wbc->sync_mode != WB_SYNC_NONE) folio_wait_writeback(folio); else goto continue_unlock; } BUG_ON(folio_test_writeback(folio)); if (!folio_clear_dirty_for_io(folio)) goto continue_unlock; trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); error = writepage(folio, wbc, data); nr = folio_nr_pages(folio); if (unlikely(error)) { /* * Handle errors according to the type of * writeback. There's no need to continue for * background writeback. Just push done_index * past this page so media errors won't choke * writeout for the entire file. For integrity * writeback, we must process the entire dirty * set regardless of errors because the fs may * still have state to clear for each page. In * that case we continue processing and return * the first error. */ if (error == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); error = 0; } else if (wbc->sync_mode != WB_SYNC_ALL) { ret = error; done_index = folio->index + nr; done = 1; break; } if (!ret) ret = error; } /* * We stop writing back only if we are not doing * integrity sync. In case of integrity sync we have to * keep going until we have written all the pages * we tagged for writeback prior to entering this loop. */ wbc->nr_to_write -= nr; if (wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; } } folio_batch_release(&fbatch); cond_resched(); } /* * If we hit the last page and there is more work to be done: wrap * back the index back to the start of the file for the next * time we are called. */ if (wbc->range_cyclic && !done) done_index = 0; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; return ret; } EXPORT_SYMBOL(write_cache_pages); static int writepage_cb(struct folio *folio, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; int ret = mapping->a_ops->writepage(&folio->page, wbc); mapping_set_error(mapping, ret); return ret; } int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; struct bdi_writeback *wb; if (wbc->nr_to_write <= 0) return 0; wb = inode_to_wb_wbc(mapping->host, wbc); wb_bandwidth_estimate_start(wb); while (1) { if (mapping->a_ops->writepages) { ret = mapping->a_ops->writepages(mapping, wbc); } else if (mapping->a_ops->writepage) { struct blk_plug plug; blk_start_plug(&plug); ret = write_cache_pages(mapping, wbc, writepage_cb, mapping); blk_finish_plug(&plug); } else { /* deal with chardevs and other special files */ ret = 0; } if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL) break; /* * Lacking an allocation context or the locality or writeback * state of any of the inode's pages, throttle based on * writeback activity on the local node. It's as good a * guess as any. */ reclaim_throttle(NODE_DATA(numa_node_id()), VMSCAN_THROTTLE_WRITEBACK); } /* * Usually few pages are written by now from those we've just submitted * but if there's constant writeback being submitted, this makes sure * writeback bandwidth is updated once in a while. */ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) wb_update_bandwidth(wb); return ret; } /* * For address_spaces which do not use buffers nor write back. */ bool noop_dirty_folio(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return !folio_test_set_dirty(folio); return false; } EXPORT_SYMBOL(noop_dirty_folio); /* * Helper function for set_page_dirty family. * * Caller must hold folio_memcg_lock(). * * NOTE: This relies on being atomic wrt interrupts. */ static void folio_account_dirtied(struct folio *folio, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_folio(folio, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; long nr = folio_nr_pages(folio); inode_attach_wb(inode, folio); wb = inode_to_wb(inode); __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); __node_stat_mod_folio(folio, NR_DIRTIED, nr); wb_stat_mod(wb, WB_RECLAIMABLE, nr); wb_stat_mod(wb, WB_DIRTIED, nr); task_io_account_write(nr * PAGE_SIZE); current->nr_dirtied += nr; __this_cpu_add(bdp_ratelimits, nr); mem_cgroup_track_foreign_dirty(folio, wb); } } /* * Helper function for deaccounting dirty page without writeback. * * Caller must hold folio_memcg_lock(). */ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); task_io_account_cancelled_write(nr * PAGE_SIZE); } /* * Mark the folio dirty, and set it dirty in the page cache, and mark * the inode dirty. * * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * * The caller must hold folio_memcg_lock(). Most callers have the folio * locked. A few have the folio blocked from truncation through other * means (eg zap_vma_pages() has it mapped and is holding the page table * lock). This can also be called from mark_buffer_dirty(), which I * cannot prove is always protected against truncate. */ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); if (folio->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !folio_test_uptodate(folio)); folio_account_dirtied(folio, mapping); __xa_set_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } /** * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads. * @mapping: Address space this folio belongs to. * @folio: Folio to be marked as dirty. * * Filesystems which do not use buffer heads should call this function * from their dirty_folio address space operation. It ignores the * contents of folio_get_private(), so if the filesystem marks individual * blocks as dirty, the filesystem should handle that itself. * * This is also sometimes used by filesystems which use buffer_heads when * a single buffer is being dirtied: we want to set the folio dirty in * that case, but not all the buffers. This is a "bottom-up" dirtying, * whereas block_dirty_folio() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will * simply hold the folio lock, but e.g. zap_pte_range() calls with the * folio mapped and the pte lock held, which also locks out truncation. */ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { folio_memcg_lock(folio); if (folio_test_set_dirty(folio)) { folio_memcg_unlock(folio); return false; } __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); folio_memcg_unlock(folio); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return true; } EXPORT_SYMBOL(filemap_dirty_folio); /** * folio_redirty_for_writepage - Decline to write a dirty folio. * @wbc: The writeback control. * @folio: The folio. * * When a writepage implementation decides that it doesn't want to write * @folio for some reason, it should call this function, unlock @folio and * return 0. * * Return: True if we redirtied the folio. False if someone else dirtied * it first. */ bool folio_redirty_for_writepage(struct writeback_control *wbc, struct folio *folio) { struct address_space *mapping = folio->mapping; long nr = folio_nr_pages(folio); bool ret; wbc->pages_skipped += nr; ret = filemap_dirty_folio(mapping, folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied -= nr; node_stat_mod_folio(folio, NR_DIRTIED, -nr); wb_stat_mod(wb, WB_DIRTIED, -nr); unlocked_inode_to_wb_end(inode, &cookie); } return ret; } EXPORT_SYMBOL(folio_redirty_for_writepage); /** * folio_mark_dirty - Mark a folio as being modified. * @folio: The folio. * * The folio may not be truncated while this function is running. * Holding the folio lock is sufficient to prevent truncation, but some * callers cannot acquire a sleeping lock. These callers instead hold * the page table lock for a page table which contains at least one page * in this folio. Truncation will block on the page table lock as it * unmaps pages before removing the folio from its mapping. * * Return: True if the folio was newly dirtied, false if it was already dirty. */ bool folio_mark_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (likely(mapping)) { /* * readahead/folio_deactivate could remain * PG_readahead/PG_reclaim due to race with folio_end_writeback * About readahead, if the folio is written, the flags would be * reset. So no problem. * About folio_deactivate, if the folio is redirtied, * the flag will be reset. So no problem. but if the * folio is used by readahead it will confuse readahead * and make it restart the size rampup process. But it's * a trivial problem. */ if (folio_test_reclaim(folio)) folio_clear_reclaim(folio); return mapping->a_ops->dirty_folio(mapping, folio); } return noop_dirty_folio(mapping, folio); } EXPORT_SYMBOL(folio_mark_dirty); /* * set_page_dirty() is racy if the caller has no reference against * page->mapping->host, and if the page is unlocked. This is because another * CPU could truncate the page off the mapping and then free the mapping. * * Usually, the page _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the page should be locked before running set_page_dirty(). */ int set_page_dirty_lock(struct page *page) { int ret; lock_page(page); ret = set_page_dirty(page); unlock_page(page); return ret; } EXPORT_SYMBOL(set_page_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __folio_cancel_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; folio_memcg_lock(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie); folio_memcg_unlock(folio); } else { folio_clear_dirty(folio); } } EXPORT_SYMBOL(__folio_cancel_dirty); /* * Clear a folio's dirty flag, while caring for dirty memory accounting. * Returns true if the folio was previously dirty. * * This is for preparing to put the folio under writeout. We leave * the folio tagged as dirty in the xarray so that a concurrent * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk. * The ->writepage implementation will run either folio_start_writeback() * or folio_mark_dirty(), at which stage we bring the folio's dirty flag * and xarray dirty tag back into sync. * * This incoherency between the folio's dirty flag and xarray tag is * unfortunate, but it only exists while the folio is locked. */ bool folio_clear_dirty_for_io(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); bool ret = false; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole folio dirty if it was * dirty in a pagetable. Only to then * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return folio_test_clear_dirty(folio); } EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { atomic_inc(&wb->writeback_inodes); } static void wb_inode_writeback_end(struct bdi_writeback *wb) { unsigned long flags; atomic_dec(&wb->writeback_inodes); /* * Make sure estimate of writeback throughput gets updated after * writeback completed. We delay the update by BANDWIDTH_INTERVAL * (which is the interval other bandwidth updates use for batching) so * that if multiple inodes end writeback at a similar time, they get * batched into one bandwidth update. */ spin_lock_irqsave(&wb->work_lock, flags); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); spin_unlock_irqrestore(&wb->work_lock, flags); } bool __folio_end_writeback(struct folio *folio) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); bool ret; folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, -nr); __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); node_stat_mod_folio(folio, NR_WRITTEN, nr); folio_memcg_unlock(folio); return ret; } void __folio_start_writeback(struct folio *folio, bool keep_write) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); int access_ret; VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; bool on_wblist; xas_lock_irqsave(&xas, flags); xas_load(&xas); folio_test_set_writeback(folio); on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* * We can come through here when swapping anonymous * folios, so we don't necessarily have an inode to * track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { folio_test_set_writeback(folio); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); folio_memcg_unlock(folio); access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_FOLIO(access_ret != 0, folio); } EXPORT_SYMBOL(__folio_start_writeback); /** * folio_wait_writeback - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_writeback(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); folio_wait_bit(folio, PG_writeback); } } EXPORT_SYMBOL_GPL(folio_wait_writeback); /** * folio_wait_writeback_killable - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete or a fatal signal to arrive. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ int folio_wait_writeback_killable(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } return 0; } EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** * folio_wait_stable() - wait for writeback to finish, if necessary. * @folio: The folio to wait on. * * This function determines if the given folio is related to a backing * device that requires folio contents to be held stable during writeback. * If so, then it will wait for any pending writeback to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_stable(struct folio *folio) { if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); |
| 505 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 | /* * net/tipc/bearer.h: Include file for TIPC bearer code * * Copyright (c) 1996-2006, 2013-2016, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_BEARER_H #define _TIPC_BEARER_H #include "netlink.h" #include "core.h" #include "msg.h" #include <net/genetlink.h> #define MAX_MEDIA 3 /* Identifiers associated with TIPC message header media address info * - address info field is 32 bytes long * - the field's actual content and length is defined per media * - remaining unused bytes in the field are set to zero */ #define TIPC_MEDIA_INFO_SIZE 32 #define TIPC_MEDIA_TYPE_OFFSET 3 #define TIPC_MEDIA_ADDR_OFFSET 4 /* * Identifiers of supported TIPC media types */ #define TIPC_MEDIA_TYPE_ETH 1 #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 /* Minimum bearer MTU */ #define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) /* Identifiers for distinguishing between broadcast/multicast and replicast */ #define TIPC_BROADCAST_SUPPORT 1 #define TIPC_REPLICAST_SUPPORT 2 /** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) * @media_id: TIPC media type identifier * @broadcast: non-zero if address is a broadcast address */ struct tipc_media_addr { u8 value[TIPC_MEDIA_INFO_SIZE]; u8 media_id; u8 broadcast; }; struct tipc_bearer; /** * struct tipc_media - Media specific info exposed to generic bearer layer * @send_msg: routine which handles buffer transmission * @enable_media: routine which enables a media * @disable_media: routine which disables a media * @addr2str: convert media address format to string * @addr2msg: convert from media addr format to discovery msg addr format * @msg2addr: convert from discovery msg addr format to media addr format * @raw2addr: convert from raw addr format to media addr format * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure * @min_win: minimum window (in packets) before declaring link congestion * @max_win: maximum window (in packets) before declaring link congestion * @mtu: max packet size bearer can support for media type not dependent on * underlying device MTU * @type_id: TIPC media identifier * @hwaddr_len: TIPC media address len * @name: media name */ struct tipc_media { int (*send_msg)(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); int (*enable_media)(struct net *net, struct tipc_bearer *b, struct nlattr *attr[]); void (*disable_media)(struct tipc_bearer *b); int (*addr2str)(struct tipc_media_addr *addr, char *strbuf, int bufsz); int (*addr2msg)(char *msg, struct tipc_media_addr *addr); int (*msg2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, char *msg); int (*raw2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, const char *raw); u32 priority; u32 tolerance; u32 min_win; u32 max_win; u32 mtu; u32 type_id; u32 hwaddr_len; char name[TIPC_MAX_MEDIA_NAME]; }; /** * struct tipc_bearer - Generic TIPC bearer structure * @media_ptr: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support * @addr: media-specific address associated with bearer * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer * @bcast_addr: media address used in broadcasting * @pt: packet type for bearer * @rcu: rcu struct for tipc_bearer * @priority: default link priority for bearer * @min_win: minimum window (in packets) before declaring link congestion * @max_win: maximum window (in packets) before declaring link congestion * @tolerance: default link tolerance for bearer * @domain: network domain to which links can be established * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * * Note: media-specific code is responsible for initialization of the fields * indicated below when a bearer is enabled; TIPC's generic bearer code takes * care of initializing all other fields. */ struct tipc_bearer { void __rcu *media_ptr; /* initialized by media */ u32 mtu; /* initialized by media */ struct tipc_media_addr addr; /* initialized by media */ char name[TIPC_MAX_BEARER_NAME]; struct tipc_media *media; struct tipc_media_addr bcast_addr; struct packet_type pt; struct rcu_head rcu; u32 priority; u32 min_win; u32 max_win; u32 tolerance; u32 domain; u32 identity; struct tipc_discoverer *disc; char net_plane; u16 encap_hlen; unsigned long up; refcount_t refcnt; }; struct tipc_bearer_names { char media_name[TIPC_MAX_MEDIA_NAME]; char if_name[TIPC_MAX_IF_NAME]; }; /* * TIPC routines available to supported media types */ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b); /* * Routines made available to TIPC by supported media types */ extern struct tipc_media eth_media_info; #ifdef CONFIG_TIPC_MEDIA_IB extern struct tipc_media ib_media_info; #endif #ifdef CONFIG_TIPC_MEDIA_UDP extern struct tipc_media udp_media_info; #endif int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, struct nlattr *attrs[]); bool tipc_bearer_hold(struct tipc_bearer *b); void tipc_bearer_put(struct tipc_bearer *b); void tipc_disable_l2_media(struct tipc_bearer *b); int tipc_l2_send_msg(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest); void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id); struct tipc_media *tipc_media_find(const char *name); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, struct tipc_media_addr *dest); void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq, struct tipc_media_addr *dst, struct tipc_node *__dnode); void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts); int tipc_attach_loopback(struct net *net); void tipc_detach_loopback(struct net *net); static inline void tipc_loopback_trace(struct net *net, struct sk_buff_head *pkts) { if (unlikely(dev_nit_active(net->loopback_dev))) tipc_clone_to_loopback(net, pkts); } /* check if device MTU is too low for tipc headers */ static inline bool tipc_mtu_bad(struct net_device *dev) { if (dev->mtu >= TIPC_MIN_BEARER_MTU) return false; netdev_warn(dev, "MTU too low for tipc bearer\n"); return true; } #endif /* _TIPC_BEARER_H */ |
| 83 83 83 83 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* auditfilter.c -- filtering of audit events * * Copyright 2003-2004 Red Hat, Inc. * Copyright 2005 Hewlett-Packard Development Company, L.P. * Copyright 2005 IBM Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/audit.h> #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/netlink.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <net/net_namespace.h> #include <net/sock.h> #include "audit.h" /* * Locking model: * * audit_filter_mutex: * Synchronizes writes and blocking reads of audit's filterlist * data. Rcu is used to traverse the filterlist and access * contents of structs audit_entry, audit_watch and opaque * LSM rules during filtering. If modified, these structures * must be copied and replace their counterparts in the filterlist. * An audit_parent struct is not accessed during filtering, so may * be written directly provided audit_filter_mutex is held. */ /* Audit filter lists, defined in <linux/audit.h> */ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[0]), LIST_HEAD_INIT(audit_filter_list[1]), LIST_HEAD_INIT(audit_filter_list[2]), LIST_HEAD_INIT(audit_filter_list[3]), LIST_HEAD_INIT(audit_filter_list[4]), LIST_HEAD_INIT(audit_filter_list[5]), LIST_HEAD_INIT(audit_filter_list[6]), LIST_HEAD_INIT(audit_filter_list[7]), #if AUDIT_NR_FILTERS != 8 #error Fix audit_filter_list initialiser #endif }; static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_rules_list[0]), LIST_HEAD_INIT(audit_rules_list[1]), LIST_HEAD_INIT(audit_rules_list[2]), LIST_HEAD_INIT(audit_rules_list[3]), LIST_HEAD_INIT(audit_rules_list[4]), LIST_HEAD_INIT(audit_rules_list[5]), LIST_HEAD_INIT(audit_rules_list[6]), LIST_HEAD_INIT(audit_rules_list[7]), }; DEFINE_MUTEX(audit_filter_mutex); static void audit_free_lsm_field(struct audit_field *f) { switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: kfree(f->lsm_str); security_audit_rule_free(f->lsm_rule); } } static inline void audit_free_rule(struct audit_entry *e) { int i; struct audit_krule *erule = &e->rule; /* some rules don't have associated watches */ if (erule->watch) audit_put_watch(erule->watch); if (erule->fields) for (i = 0; i < erule->field_count; i++) audit_free_lsm_field(&erule->fields[i]); kfree(erule->fields); kfree(erule->filterkey); kfree(e); } void audit_free_rule_rcu(struct rcu_head *head) { struct audit_entry *e = container_of(head, struct audit_entry, rcu); audit_free_rule(e); } /* Initialize an audit filterlist entry. */ static inline struct audit_entry *audit_init_entry(u32 field_count) { struct audit_entry *entry; struct audit_field *fields; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (unlikely(!entry)) return NULL; fields = kcalloc(field_count, sizeof(*fields), GFP_KERNEL); if (unlikely(!fields)) { kfree(entry); return NULL; } entry->rule.fields = fields; return entry; } /* Unpack a filter field's string representation from user-space * buffer. */ char *audit_unpack_string(void **bufp, size_t *remain, size_t len) { char *str; if (!*bufp || (len == 0) || (len > *remain)) return ERR_PTR(-EINVAL); /* Of the currently implemented string fields, PATH_MAX * defines the longest valid length. */ if (len > PATH_MAX) return ERR_PTR(-ENAMETOOLONG); str = kmalloc(len + 1, GFP_KERNEL); if (unlikely(!str)) return ERR_PTR(-ENOMEM); memcpy(str, *bufp, len); str[len] = 0; *bufp += len; *remain -= len; return str; } /* Translate an inode field to kernel representation. */ static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { if ((krule->listnr != AUDIT_FILTER_EXIT && krule->listnr != AUDIT_FILTER_URING_EXIT) || krule->inode_f || krule->watch || krule->tree || (f->op != Audit_equal && f->op != Audit_not_equal)) return -EINVAL; krule->inode_f = f; return 0; } static __u32 *classes[AUDIT_SYSCALL_CLASSES]; int __init audit_register_class(int class, unsigned *list) { __u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL); if (!p) return -ENOMEM; while (*list != ~0U) { unsigned n = *list++; if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) { kfree(p); return -EINVAL; } p[AUDIT_WORD(n)] |= AUDIT_BIT(n); } if (class >= AUDIT_SYSCALL_CLASSES || classes[class]) { kfree(p); return -EINVAL; } classes[class] = p; return 0; } int audit_match_class(int class, unsigned syscall) { if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32)) return 0; if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class])) return 0; return classes[class][AUDIT_WORD(syscall)] & AUDIT_BIT(syscall); } #ifdef CONFIG_AUDITSYSCALL static inline int audit_match_class_bits(int class, u32 *mask) { int i; if (classes[class]) { for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (mask[i] & classes[class][i]) return 0; } return 1; } static int audit_match_signal(struct audit_entry *entry) { struct audit_field *arch = entry->rule.arch_f; if (!arch) { /* When arch is unspecified, we must check both masks on biarch * as syscall number alone is ambiguous. */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask) && audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); } switch (audit_classify_arch(arch->val)) { case 0: /* native */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask)); case 1: /* 32bit on biarch */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); default: return 1; } } #endif /* Common user-space to kernel rule translation. */ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule) { unsigned listnr; struct audit_entry *entry; int i, err; err = -EINVAL; listnr = rule->flags & ~AUDIT_FILTER_PREPEND; switch (listnr) { default: goto exit_err; #ifdef CONFIG_AUDITSYSCALL case AUDIT_FILTER_ENTRY: pr_err("AUDIT_FILTER_ENTRY is deprecated\n"); goto exit_err; case AUDIT_FILTER_EXIT: case AUDIT_FILTER_URING_EXIT: case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: ; } if (unlikely(rule->action == AUDIT_POSSIBLE)) { pr_err("AUDIT_POSSIBLE is deprecated\n"); goto exit_err; } if (rule->action != AUDIT_NEVER && rule->action != AUDIT_ALWAYS) goto exit_err; if (rule->field_count > AUDIT_MAX_FIELDS) goto exit_err; err = -ENOMEM; entry = audit_init_entry(rule->field_count); if (!entry) goto exit_err; entry->rule.flags = rule->flags & AUDIT_FILTER_PREPEND; entry->rule.listnr = listnr; entry->rule.action = rule->action; entry->rule.field_count = rule->field_count; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) entry->rule.mask[i] = rule->mask[i]; for (i = 0; i < AUDIT_SYSCALL_CLASSES; i++) { int bit = AUDIT_BITMASK_SIZE * 32 - i - 1; __u32 *p = &entry->rule.mask[AUDIT_WORD(bit)]; __u32 *class; if (!(*p & AUDIT_BIT(bit))) continue; *p &= ~AUDIT_BIT(bit); class = classes[i]; if (class) { int j; for (j = 0; j < AUDIT_BITMASK_SIZE; j++) entry->rule.mask[j] |= class[j]; } } return entry; exit_err: return ERR_PTR(err); } static u32 audit_ops[] = { [Audit_equal] = AUDIT_EQUAL, [Audit_not_equal] = AUDIT_NOT_EQUAL, [Audit_bitmask] = AUDIT_BIT_MASK, [Audit_bittest] = AUDIT_BIT_TEST, [Audit_lt] = AUDIT_LESS_THAN, [Audit_gt] = AUDIT_GREATER_THAN, [Audit_le] = AUDIT_LESS_THAN_OR_EQUAL, [Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL, }; static u32 audit_to_op(u32 op) { u32 n; for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++) ; return n; } /* check if an audit field is valid */ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) { switch (f->type) { case AUDIT_MSGTYPE: if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE && entry->rule.listnr != AUDIT_FILTER_USER) return -EINVAL; break; case AUDIT_FSTYPE: if (entry->rule.listnr != AUDIT_FILTER_FS) return -EINVAL; break; case AUDIT_PERM: if (entry->rule.listnr == AUDIT_FILTER_URING_EXIT) return -EINVAL; break; } switch (entry->rule.listnr) { case AUDIT_FILTER_FS: switch (f->type) { case AUDIT_FSTYPE: case AUDIT_FILTERKEY: break; default: return -EINVAL; } } /* Check for valid field type and op */ switch (f->type) { case AUDIT_ARG0: case AUDIT_ARG1: case AUDIT_ARG2: case AUDIT_ARG3: case AUDIT_PERS: /* <uapi/linux/personality.h> */ case AUDIT_DEVMINOR: /* all ops are valid */ break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: case AUDIT_PID: case AUDIT_MSGTYPE: case AUDIT_PPID: case AUDIT_DEVMAJOR: case AUDIT_EXIT: case AUDIT_SUCCESS: case AUDIT_INODE: case AUDIT_SESSIONID: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: case AUDIT_SADDR_FAM: /* bit ops are only useful on syscall args */ if (f->op == Audit_bitmask || f->op == Audit_bittest) return -EINVAL; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_WATCH: case AUDIT_DIR: case AUDIT_FILTERKEY: case AUDIT_LOGINUID_SET: case AUDIT_ARCH: case AUDIT_FSTYPE: case AUDIT_PERM: case AUDIT_FILETYPE: case AUDIT_FIELD_COMPARE: case AUDIT_EXE: /* only equal and not equal valid ops */ if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; default: /* field not recognized */ return -EINVAL; } /* Check for select valid field values */ switch (f->type) { case AUDIT_LOGINUID_SET: if ((f->val != 0) && (f->val != 1)) return -EINVAL; break; case AUDIT_PERM: if (f->val & ~15) return -EINVAL; break; case AUDIT_FILETYPE: if (f->val & ~S_IFMT) return -EINVAL; break; case AUDIT_FIELD_COMPARE: if (f->val > AUDIT_MAX_FIELD_COMPARE) return -EINVAL; break; case AUDIT_SADDR_FAM: if (f->val >= AF_MAX) return -EINVAL; break; default: break; } return 0; } /* Translate struct audit_rule_data to kernel's rule representation. */ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, size_t datasz) { int err = 0; struct audit_entry *entry; void *bufp; size_t remain = datasz - sizeof(struct audit_rule_data); int i; char *str; struct audit_fsnotify_mark *audit_mark; entry = audit_to_entry_common(data); if (IS_ERR(entry)) goto exit_nofree; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; u32 f_val; err = -EINVAL; f->op = audit_to_op(data->fieldflags[i]); if (f->op == Audit_bad) goto exit_free; f->type = data->fields[i]; f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } err = audit_field_valid(entry, f); if (err) goto exit_free; err = -EINVAL; switch (f->type) { case AUDIT_LOGINUID: case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; } else if (err) goto exit_free; break; case AUDIT_WATCH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } entry->rule.buflen += f_val; break; case AUDIT_DIR: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; entry->rule.buflen += f_val; break; case AUDIT_INODE: f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; default: f->val = f_val; break; } } if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal) entry->rule.inode_f = NULL; exit_nofree: return entry; exit_free: if (entry->rule.tree) audit_put_tree(entry->rule.tree); /* that's the temporary one */ if (entry->rule.exe) audit_remove_mark(entry->rule.exe); /* that's the template one */ audit_free_rule(entry); return ERR_PTR(err); } /* Pack a filter field's string representation into data block. */ static inline size_t audit_pack_string(void **bufp, const char *str) { size_t len = strlen(str); memcpy(*bufp, str, len); *bufp += len; return len; } /* Translate kernel rule representation to struct audit_rule_data. */ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) { struct audit_rule_data *data; void *bufp; int i; data = kmalloc(struct_size(data, buf, krule->buflen), GFP_KERNEL); if (unlikely(!data)) return NULL; memset(data, 0, sizeof(*data)); data->flags = krule->flags | krule->listnr; data->action = krule->action; data->field_count = krule->field_count; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &krule->fields[i]; data->fields[i] = f->type; data->fieldflags[i] = audit_ops[f->op]; switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: data->buflen += data->values[i] = audit_pack_string(&bufp, f->lsm_str); break; case AUDIT_WATCH: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_watch_path(krule->watch)); break; case AUDIT_DIR: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_tree_path(krule->tree)); break; case AUDIT_FILTERKEY: data->buflen += data->values[i] = audit_pack_string(&bufp, krule->filterkey); break; case AUDIT_EXE: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_mark_path(krule->exe)); break; case AUDIT_LOGINUID_SET: if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { data->fields[i] = AUDIT_LOGINUID; data->values[i] = AUDIT_UID_UNSET; break; } fallthrough; /* if set */ default: data->values[i] = f->val; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) data->mask[i] = krule->mask[i]; return data; } /* Compare two rules in kernel format. Considered success if rules * don't match. */ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) { int i; if (a->flags != b->flags || a->pflags != b->pflags || a->listnr != b->listnr || a->action != b->action || a->field_count != b->field_count) return 1; for (i = 0; i < a->field_count; i++) { if (a->fields[i].type != b->fields[i].type || a->fields[i].op != b->fields[i].op) return 1; switch (a->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: if (strcmp(a->fields[i].lsm_str, b->fields[i].lsm_str)) return 1; break; case AUDIT_WATCH: if (strcmp(audit_watch_path(a->watch), audit_watch_path(b->watch))) return 1; break; case AUDIT_DIR: if (strcmp(audit_tree_path(a->tree), audit_tree_path(b->tree))) return 1; break; case AUDIT_FILTERKEY: /* both filterkeys exist based on above type compare */ if (strcmp(a->filterkey, b->filterkey)) return 1; break; case AUDIT_EXE: /* both paths exist based on above type compare */ if (strcmp(audit_mark_path(a->exe), audit_mark_path(b->exe))) return 1; break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: if (!uid_eq(a->fields[i].uid, b->fields[i].uid)) return 1; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) return 1; break; default: if (a->fields[i].val != b->fields[i].val) return 1; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (a->mask[i] != b->mask[i]) return 1; return 0; } /* Duplicate LSM field information. The lsm_rule is opaque, so must be * re-initialized. */ static inline int audit_dupe_lsm_field(struct audit_field *df, struct audit_field *sf) { int ret = 0; char *lsm_str; /* our own copy of lsm_str */ lsm_str = kstrdup(sf->lsm_str, GFP_KERNEL); if (unlikely(!lsm_str)) return -ENOMEM; df->lsm_str = lsm_str; /* our own (refreshed) copy of lsm_rule */ ret = security_audit_rule_init(df->type, df->op, df->lsm_str, (void **)&df->lsm_rule); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", df->lsm_str); ret = 0; } return ret; } /* Duplicate an audit rule. This will be a deep copy with the exception * of the watch - that pointer is carried over. The LSM specific fields * will be updated in the copy. The point is to be able to replace the old * rule with the new rule in the filterlist, then free the old rule. * The rlist element is undefined; list manipulations are handled apart from * the initial copy. */ struct audit_entry *audit_dupe_rule(struct audit_krule *old) { u32 fcount = old->field_count; struct audit_entry *entry; struct audit_krule *new; char *fk; int i, err = 0; entry = audit_init_entry(fcount); if (unlikely(!entry)) return ERR_PTR(-ENOMEM); new = &entry->rule; new->flags = old->flags; new->pflags = old->pflags; new->listnr = old->listnr; new->action = old->action; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) new->mask[i] = old->mask[i]; new->prio = old->prio; new->buflen = old->buflen; new->inode_f = old->inode_f; new->field_count = old->field_count; /* * note that we are OK with not refcounting here; audit_match_tree() * never dereferences tree and we can't get false positives there * since we'd have to have rule gone from the list *and* removed * before the chunks found by lookup had been allocated, i.e. before * the beginning of list scan. */ new->tree = old->tree; memcpy(new->fields, old->fields, sizeof(struct audit_field) * fcount); /* deep copy this information, updating the lsm_rule fields, because * the originals will all be freed when the old rule is freed. */ for (i = 0; i < fcount; i++) { switch (new->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: err = audit_dupe_lsm_field(&new->fields[i], &old->fields[i]); break; case AUDIT_FILTERKEY: fk = kstrdup(old->filterkey, GFP_KERNEL); if (unlikely(!fk)) err = -ENOMEM; else new->filterkey = fk; break; case AUDIT_EXE: err = audit_dupe_exe(new, old); break; } if (err) { if (new->exe) audit_remove_mark(new->exe); audit_free_rule(entry); return ERR_PTR(err); } } if (old->watch) { audit_get_watch(old->watch); new->watch = old->watch; } return entry; } /* Find an existing audit rule. * Caller must hold audit_filter_mutex to prevent stale rule data. */ static struct audit_entry *audit_find_rule(struct audit_entry *entry, struct list_head **p) { struct audit_entry *e, *found = NULL; struct list_head *list; int h; if (entry->rule.inode_f) { h = audit_hash_ino(entry->rule.inode_f->val); *p = list = &audit_inode_hash[h]; } else if (entry->rule.watch) { /* we don't know the inode number, so must walk entire hash */ for (h = 0; h < AUDIT_INODE_BUCKETS; h++) { list = &audit_inode_hash[h]; list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } } goto out; } else { *p = list = &audit_filter_list[entry->rule.listnr]; } list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } out: return found; } static u64 prio_low = ~0ULL/2; static u64 prio_high = ~0ULL/2 - 1; /* Add rule to given filterlist if not a duplicate. */ static inline int audit_add_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int err = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch (entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (e) { mutex_unlock(&audit_filter_mutex); err = -EEXIST; /* normally audit_add_tree_rule() will free it on failure */ if (tree) audit_put_tree(tree); return err; } if (watch) { /* audit_filter_mutex is dropped and re-taken during this call */ err = audit_add_watch(&entry->rule, &list); if (err) { mutex_unlock(&audit_filter_mutex); /* * normally audit_add_tree_rule() will free it * on failure */ if (tree) audit_put_tree(tree); return err; } } if (tree) { err = audit_add_tree_rule(&entry->rule); if (err) { mutex_unlock(&audit_filter_mutex); return err; } } entry->rule.prio = ~0ULL; if (entry->rule.listnr == AUDIT_FILTER_EXIT || entry->rule.listnr == AUDIT_FILTER_URING_EXIT) { if (entry->rule.flags & AUDIT_FILTER_PREPEND) entry->rule.prio = ++prio_high; else entry->rule.prio = --prio_low; } if (entry->rule.flags & AUDIT_FILTER_PREPEND) { list_add(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_rcu(&entry->list, list); entry->rule.flags &= ~AUDIT_FILTER_PREPEND; } else { list_add_tail(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_tail_rcu(&entry->list, list); } #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules++; if (!audit_match_signal(entry)) audit_signals++; #endif mutex_unlock(&audit_filter_mutex); return err; } /* Remove an existing rule from filterlist. */ int audit_del_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int ret = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch (entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (!e) { ret = -ENOENT; goto out; } if (e->rule.watch) audit_remove_watch_rule(&e->rule); if (e->rule.tree) audit_remove_tree_rule(&e->rule); if (e->rule.exe) audit_remove_mark_rule(&e->rule); #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules--; if (!audit_match_signal(entry)) audit_signals--; #endif list_del_rcu(&e->list); list_del(&e->rule.list); call_rcu(&e->rcu, audit_free_rule_rcu); out: mutex_unlock(&audit_filter_mutex); if (tree) audit_put_tree(tree); /* that's the temporary one */ return ret; } /* List rules using struct audit_rule_data. */ static void audit_list_rules(int seq, struct sk_buff_head *q) { struct sk_buff *skb; struct audit_krule *r; int i; /* This is a blocking read, so use audit_filter_mutex instead of rcu * iterator to sync with list writers. */ for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry(r, &audit_rules_list[i], list) { struct audit_rule_data *data; data = audit_krule_to_data(r); if (unlikely(!data)) break; skb = audit_make_reply(seq, AUDIT_LIST_RULES, 0, 1, data, struct_size(data, buf, data->buflen)); if (skb) skb_queue_tail(q, skb); kfree(data); } } skb = audit_make_reply(seq, AUDIT_LIST_RULES, 1, 1, NULL, 0); if (skb) skb_queue_tail(q, skb); } /* Log rule additions and removals */ static void audit_log_rule_change(char *action, struct audit_krule *rule, int res) { struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; audit_log_session_info(ab); audit_log_task_context(ab); audit_log_format(ab, " op=%s", action); audit_log_key(ab, rule->filterkey); audit_log_format(ab, " list=%d res=%d", rule->listnr, res); audit_log_end(ab); } /** * audit_rule_change - apply all rules to the specified message type * @type: audit message type * @seq: netlink audit message sequence (serial) number * @data: payload data * @datasz: size of payload data */ int audit_rule_change(int type, int seq, void *data, size_t datasz) { int err = 0; struct audit_entry *entry; switch (type) { case AUDIT_ADD_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_add_rule(entry); audit_log_rule_change("add_rule", &entry->rule, !err); break; case AUDIT_DEL_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_del_rule(entry); audit_log_rule_change("remove_rule", &entry->rule, !err); break; default: WARN_ON(1); return -EINVAL; } if (err || type == AUDIT_DEL_RULE) { if (entry->rule.exe) audit_remove_mark(entry->rule.exe); audit_free_rule(entry); } return err; } /** * audit_list_rules_send - list the audit rules * @request_skb: skb of request we are replying to (used to target the reply) * @seq: netlink audit message sequence (serial) number */ int audit_list_rules_send(struct sk_buff *request_skb, int seq) { struct task_struct *tsk; struct audit_netlink_list *dest; /* We can't just spew out the rules here because we might fill * the available socket buffer space and deadlock waiting for * auditctl to read from it... which isn't ever going to * happen if we're actually running in the context of auditctl * trying to _send_ the stuff */ dest = kmalloc(sizeof(*dest), GFP_KERNEL); if (!dest) return -ENOMEM; dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); dest->portid = NETLINK_CB(request_skb).portid; skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); audit_list_rules(seq, &dest->q); mutex_unlock(&audit_filter_mutex); tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list"); if (IS_ERR(tsk)) { skb_queue_purge(&dest->q); put_net(dest->net); kfree(dest); return PTR_ERR(tsk); } return 0; } int audit_comparator(u32 left, u32 op, u32 right) { switch (op) { case Audit_equal: return (left == right); case Audit_not_equal: return (left != right); case Audit_lt: return (left < right); case Audit_le: return (left <= right); case Audit_gt: return (left > right); case Audit_ge: return (left >= right); case Audit_bitmask: return (left & right); case Audit_bittest: return ((left & right) == right); default: return 0; } } int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) { switch (op) { case Audit_equal: return uid_eq(left, right); case Audit_not_equal: return !uid_eq(left, right); case Audit_lt: return uid_lt(left, right); case Audit_le: return uid_lte(left, right); case Audit_gt: return uid_gt(left, right); case Audit_ge: return uid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } int audit_gid_comparator(kgid_t left, u32 op, kgid_t right) { switch (op) { case Audit_equal: return gid_eq(left, right); case Audit_not_equal: return !gid_eq(left, right); case Audit_lt: return gid_lt(left, right); case Audit_le: return gid_lte(left, right); case Audit_gt: return gid_gt(left, right); case Audit_ge: return gid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } /** * parent_len - find the length of the parent portion of a pathname * @path: pathname of which to determine length */ int parent_len(const char *path) { int plen; const char *p; plen = strlen(path); if (plen == 0) return plen; /* disregard trailing slashes */ p = path + plen - 1; while ((*p == '/') && (p > path)) p--; /* walk backward until we find the next slash or hit beginning */ while ((*p != '/') && (p > path)) p--; /* did we find a slash? Then increment to include it in path */ if (*p == '/') p++; return p - path; } /** * audit_compare_dname_path - compare given dentry name with last component in * given path. Return of 0 indicates a match. * @dname: dentry name that we're comparing * @path: full pathname that we're comparing * @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL * here indicates that we must compute this value. */ int audit_compare_dname_path(const struct qstr *dname, const char *path, int parentlen) { int dlen, pathlen; const char *p; dlen = dname->len; pathlen = strlen(path); if (pathlen < dlen) return 1; parentlen = parentlen == AUDIT_NAME_FULL ? parent_len(path) : parentlen; if (pathlen - parentlen != dlen) return 1; p = path + parentlen; return strncmp(p, dname->name, dlen); } int audit_filter(int msgtype, unsigned int listtype) { struct audit_entry *e; int ret = 1; /* Audit by default */ rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) { int i, result = 0; for (i = 0; i < e->rule.field_count; i++) { struct audit_field *f = &e->rule.fields[i]; pid_t pid; u32 sid; switch (f->type) { case AUDIT_PID: pid = task_pid_nr(current); result = audit_comparator(pid, f->op, f->val); break; case AUDIT_UID: result = audit_uid_comparator(current_uid(), f->op, f->uid); break; case AUDIT_GID: result = audit_gid_comparator(current_gid(), f->op, f->gid); break; case AUDIT_LOGINUID: result = audit_uid_comparator(audit_get_loginuid(current), f->op, f->uid); break; case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(current), f->op, f->val); break; case AUDIT_MSGTYPE: result = audit_comparator(msgtype, f->op, f->val); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: if (f->lsm_rule) { security_current_getsecid_subj(&sid); result = security_audit_rule_match(sid, f->type, f->op, f->lsm_rule); } break; case AUDIT_EXE: result = audit_exe_compare(current, e->rule.exe); if (f->op == Audit_not_equal) result = !result; break; default: goto unlock_and_return; } if (result < 0) /* error */ goto unlock_and_return; if (!result) break; } if (result > 0) { if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE) ret = 0; break; } } unlock_and_return: rcu_read_unlock(); return ret; } static int update_lsm_rule(struct audit_krule *r) { struct audit_entry *entry = container_of(r, struct audit_entry, rule); struct audit_entry *nentry; int err = 0; if (!security_audit_rule_known(r)) return 0; nentry = audit_dupe_rule(r); if (entry->rule.exe) audit_remove_mark(entry->rule.exe); if (IS_ERR(nentry)) { /* save the first error encountered for the * return value */ err = PTR_ERR(nentry); audit_panic("error updating LSM filters"); if (r->watch) list_del(&r->rlist); list_del_rcu(&entry->list); list_del(&r->list); } else { if (r->watch || r->tree) list_replace_init(&r->rlist, &nentry->rule.rlist); list_replace_rcu(&entry->list, &nentry->list); list_replace(&r->list, &nentry->rule.list); } call_rcu(&entry->rcu, audit_free_rule_rcu); return err; } /* This function will re-initialize the lsm_rule field of all applicable rules. * It will traverse the filter lists serarching for rules that contain LSM * specific filter fields. When such a rule is found, it is copied, the * LSM field is re-initialized, and the old rule is replaced with the * updated rule. */ int audit_update_lsm_rules(void) { struct audit_krule *r, *n; int i, err = 0; /* audit_filter_mutex synchronizes the writers */ mutex_lock(&audit_filter_mutex); for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry_safe(r, n, &audit_rules_list[i], list) { int res = update_lsm_rule(r); if (!err) err = res; } } mutex_unlock(&audit_filter_mutex); return err; } |
| 12 12 9 2 2 2 3 3 3 1 1 1 1 1 3 3 3 3 3 36 2 17 16 9 12 3 3 2 1 1 3 1 1 1 2 36 11 27 3 1 2 21 1 1 11 4 4 14 1 1 1 1 4 1 2 1 1 4 1 3 8 7 1 2 2 38 38 5 5 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 | // SPDX-License-Identifier: GPL-2.0 /* * cfg80211 - wext compat code * * This is temporary code until all wireless functionality is migrated * into cfg80211, when that happens all the exports here go away and * we directly assign the wireless handlers of wireless interfaces. * * Copyright 2008-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2019-2023 Intel Corporation */ #include <linux/export.h> #include <linux/wireless.h> #include <linux/nl80211.h> #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <net/iw_handler.h> #include <net/cfg80211.h> #include <net/cfg80211-wext.h> #include "wext-compat.h" #include "core.h" #include "rdev-ops.h" int cfg80211_wext_giwname(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { strcpy(wrqu->name, "IEEE 802.11"); return 0; } EXPORT_WEXT_HANDLER(cfg80211_wext_giwname); int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; struct vif_params vifparams; enum nl80211_iftype type; int ret; rdev = wiphy_to_rdev(wdev->wiphy); switch (*mode) { case IW_MODE_INFRA: type = NL80211_IFTYPE_STATION; break; case IW_MODE_ADHOC: type = NL80211_IFTYPE_ADHOC; break; case IW_MODE_MONITOR: type = NL80211_IFTYPE_MONITOR; break; default: return -EINVAL; } if (type == wdev->iftype) return 0; memset(&vifparams, 0, sizeof(vifparams)); wiphy_lock(wdev->wiphy); ret = cfg80211_change_iface(rdev, dev, type, &vifparams); wiphy_unlock(wdev->wiphy); return ret; } EXPORT_WEXT_HANDLER(cfg80211_wext_siwmode); int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; if (!wdev) return -EOPNOTSUPP; switch (wdev->iftype) { case NL80211_IFTYPE_AP: *mode = IW_MODE_MASTER; break; case NL80211_IFTYPE_STATION: *mode = IW_MODE_INFRA; break; case NL80211_IFTYPE_ADHOC: *mode = IW_MODE_ADHOC; break; case NL80211_IFTYPE_MONITOR: *mode = IW_MODE_MONITOR; break; case NL80211_IFTYPE_WDS: *mode = IW_MODE_REPEAT; break; case NL80211_IFTYPE_AP_VLAN: *mode = IW_MODE_SECOND; /* FIXME */ break; default: *mode = IW_MODE_AUTO; break; } return 0; } EXPORT_WEXT_HANDLER(cfg80211_wext_giwmode); int cfg80211_wext_giwrange(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_range *range = (struct iw_range *) extra; enum nl80211_band band; int i, c = 0; if (!wdev) return -EOPNOTSUPP; data->length = sizeof(struct iw_range); memset(range, 0, sizeof(struct iw_range)); range->we_version_compiled = WIRELESS_EXT; range->we_version_source = 21; range->retry_capa = IW_RETRY_LIMIT; range->retry_flags = IW_RETRY_LIMIT; range->min_retry = 0; range->max_retry = 255; range->min_rts = 0; range->max_rts = 2347; range->min_frag = 256; range->max_frag = 2346; range->max_encoding_tokens = 4; range->max_qual.updated = IW_QUAL_NOISE_INVALID; switch (wdev->wiphy->signal_type) { case CFG80211_SIGNAL_TYPE_NONE: break; case CFG80211_SIGNAL_TYPE_MBM: range->max_qual.level = (u8)-110; range->max_qual.qual = 70; range->avg_qual.qual = 35; range->max_qual.updated |= IW_QUAL_DBM; range->max_qual.updated |= IW_QUAL_QUAL_UPDATED; range->max_qual.updated |= IW_QUAL_LEVEL_UPDATED; break; case CFG80211_SIGNAL_TYPE_UNSPEC: range->max_qual.level = 100; range->max_qual.qual = 100; range->avg_qual.qual = 50; range->max_qual.updated |= IW_QUAL_QUAL_UPDATED; range->max_qual.updated |= IW_QUAL_LEVEL_UPDATED; break; } range->avg_qual.level = range->max_qual.level / 2; range->avg_qual.noise = range->max_qual.noise / 2; range->avg_qual.updated = range->max_qual.updated; for (i = 0; i < wdev->wiphy->n_cipher_suites; i++) { switch (wdev->wiphy->cipher_suites[i]) { case WLAN_CIPHER_SUITE_TKIP: range->enc_capa |= (IW_ENC_CAPA_CIPHER_TKIP | IW_ENC_CAPA_WPA); break; case WLAN_CIPHER_SUITE_CCMP: range->enc_capa |= (IW_ENC_CAPA_CIPHER_CCMP | IW_ENC_CAPA_WPA2); break; case WLAN_CIPHER_SUITE_WEP40: range->encoding_size[range->num_encoding_sizes++] = WLAN_KEY_LEN_WEP40; break; case WLAN_CIPHER_SUITE_WEP104: range->encoding_size[range->num_encoding_sizes++] = WLAN_KEY_LEN_WEP104; break; } } for (band = 0; band < NUM_NL80211_BANDS; band ++) { struct ieee80211_supported_band *sband; sband = wdev->wiphy->bands[band]; if (!sband) continue; for (i = 0; i < sband->n_channels && c < IW_MAX_FREQUENCIES; i++) { struct ieee80211_channel *chan = &sband->channels[i]; if (!(chan->flags & IEEE80211_CHAN_DISABLED)) { range->freq[c].i = ieee80211_frequency_to_channel( chan->center_freq); range->freq[c].m = chan->center_freq; range->freq[c].e = 6; c++; } } } range->num_channels = c; range->num_frequency = c; IW_EVENT_CAPA_SET_KERNEL(range->event_capa); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWAP); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWSCAN); if (wdev->wiphy->max_scan_ssids > 0) range->scan_capa |= IW_SCAN_CAPA_ESSID; return 0; } EXPORT_WEXT_HANDLER(cfg80211_wext_giwrange); /** * cfg80211_wext_freq - get wext frequency for non-"auto" * @freq: the wext freq encoding * * Returns: a frequency, or a negative error code, or 0 for auto. */ int cfg80211_wext_freq(struct iw_freq *freq) { /* * Parse frequency - return 0 for auto and * -EINVAL for impossible things. */ if (freq->e == 0) { enum nl80211_band band = NL80211_BAND_2GHZ; if (freq->m < 0) return 0; if (freq->m > 14) band = NL80211_BAND_5GHZ; return ieee80211_channel_to_frequency(freq->m, band); } else { int i, div = 1000000; for (i = 0; i < freq->e; i++) div /= 10; if (div <= 0) return -EINVAL; return freq->m / div; } } int cfg80211_wext_siwrts(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 orts = wdev->wiphy->rts_threshold; int err; wiphy_lock(&rdev->wiphy); if (rts->disabled || !rts->fixed) { wdev->wiphy->rts_threshold = (u32) -1; } else if (rts->value < 0) { err = -EINVAL; goto out; } else { wdev->wiphy->rts_threshold = rts->value; } err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_RTS_THRESHOLD); if (err) wdev->wiphy->rts_threshold = orts; out: wiphy_unlock(&rdev->wiphy); return err; } EXPORT_WEXT_HANDLER(cfg80211_wext_siwrts); int cfg80211_wext_giwrts(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; rts->value = wdev->wiphy->rts_threshold; rts->disabled = rts->value == (u32) -1; rts->fixed = 1; return 0; } EXPORT_WEXT_HANDLER(cfg80211_wext_giwrts); int cfg80211_wext_siwfrag(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 ofrag = wdev->wiphy->frag_threshold; int err; wiphy_lock(&rdev->wiphy); if (frag->disabled || !frag->fixed) { wdev->wiphy->frag_threshold = (u32) -1; } else if (frag->value < 256) { err = -EINVAL; goto out; } else { /* Fragment length must be even, so strip LSB. */ wdev->wiphy->frag_threshold = frag->value & ~0x1; } err = rdev_set_wiphy_params(rdev, WIPHY_PARAM_FRAG_THRESHOLD); if (err) wdev->wiphy->frag_threshold = ofrag; out: wiphy_unlock(&rdev->wiphy); return err; } EXPORT_WEXT_HANDLER(cfg80211_wext_siwfrag); int cfg80211_wext_giwfrag(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; frag->value = wdev->wiphy->frag_threshold; frag->disabled = frag->value == (u32) -1; frag->fixed = 1; return 0; } EXPORT_WEXT_HANDLER(cfg80211_wext_giwfrag); static int cfg80211_wext_siwretry(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 changed = 0; u8 olong = wdev->wiphy->retry_long; u8 oshort = wdev->wiphy->retry_short; int err; if (retry->disabled || retry->value < 1 || retry->value > 255 || (retry->flags & IW_RETRY_TYPE) != IW_RETRY_LIMIT) return -EINVAL; wiphy_lock(&rdev->wiphy); if (retry->flags & IW_RETRY_LONG) { wdev->wiphy->retry_long = retry->value; changed |= WIPHY_PARAM_RETRY_LONG; } else if (retry->flags & IW_RETRY_SHORT) { wdev->wiphy->retry_short = retry->value; changed |= WIPHY_PARAM_RETRY_SHORT; } else { wdev->wiphy->retry_short = retry->value; wdev->wiphy->retry_long = retry->value; changed |= WIPHY_PARAM_RETRY_LONG; changed |= WIPHY_PARAM_RETRY_SHORT; } err = rdev_set_wiphy_params(rdev, changed); if (err) { wdev->wiphy->retry_short = oshort; wdev->wiphy->retry_long = olong; } wiphy_unlock(&rdev->wiphy); return err; } int cfg80211_wext_giwretry(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; retry->disabled = 0; if (retry->flags == 0 || (retry->flags & IW_RETRY_SHORT)) { /* * First return short value, iwconfig will ask long value * later if needed */ retry->flags |= IW_RETRY_LIMIT | IW_RETRY_SHORT; retry->value = wdev->wiphy->retry_short; if (wdev->wiphy->retry_long == wdev->wiphy->retry_short) retry->flags |= IW_RETRY_LONG; return 0; } if (retry->flags & IW_RETRY_LONG) { retry->flags = IW_RETRY_LIMIT | IW_RETRY_LONG; retry->value = wdev->wiphy->retry_long; } return 0; } EXPORT_WEXT_HANDLER(cfg80211_wext_giwretry); static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, struct net_device *dev, bool pairwise, const u8 *addr, bool remove, bool tx_key, int idx, struct key_params *params) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err, i; bool rejoin = false; if (wdev->valid_links) return -EINVAL; if (pairwise && !addr) return -EINVAL; /* * In many cases we won't actually need this, but it's better * to do it first in case the allocation fails. Don't use wext. */ if (!wdev->wext.keys) { wdev->wext.keys = kzalloc(sizeof(*wdev->wext.keys), GFP_KERNEL); if (!wdev->wext.keys) return -ENOMEM; for (i = 0; i < 4; i++) wdev->wext.keys->params[i].key = wdev->wext.keys->data[i]; } if (wdev->iftype != NL80211_IFTYPE_ADHOC && wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC) { if (!wdev->connected) return -ENOLINK; if (!rdev->ops->set_default_mgmt_key) return -EOPNOTSUPP; if (idx < 4 || idx > 5) return -EINVAL; } else if (idx < 0 || idx > 3) return -EINVAL; if (remove) { err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) { /* * If removing the current TX key, we will need to * join a new IBSS without the privacy bit clear. */ if (idx == wdev->wext.default_key && wdev->iftype == NL80211_IFTYPE_ADHOC) { cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } if (!pairwise && addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) err = -ENOENT; else err = rdev_del_key(rdev, dev, -1, idx, pairwise, addr); } wdev->wext.connect.privacy = false; /* * Applications using wireless extensions expect to be * able to delete keys that don't exist, so allow that. */ if (err == -ENOENT) err = 0; if (!err) { if (!addr && idx < 4) { memset(wdev->wext.keys->data[idx], 0, sizeof(wdev->wext.keys->data[idx])); wdev->wext.keys->params[idx].key_len = 0; wdev->wext.keys->params[idx].cipher = 0; } if (idx == wdev->wext.default_key) wdev->wext.default_key = -1; else if (idx == wdev->wext.default_mgmt_key) wdev->wext.default_mgmt_key = -1; } if (!err && rejoin) err = cfg80211_ibss_wext_join(rdev, wdev); return err; } if (addr) tx_key = false; if (cfg80211_validate_key_settings(rdev, params, idx, pairwise, addr)) return -EINVAL; err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_add_key(rdev, dev, -1, idx, pairwise, addr, params); else if (params->cipher != WLAN_CIPHER_SUITE_WEP40 && params->cipher != WLAN_CIPHER_SUITE_WEP104) return -EINVAL; if (err) return err; /* * We only need to store WEP keys, since they're the only keys that * can be set before a connection is established and persist after * disconnecting. */ if (!addr && (params->cipher == WLAN_CIPHER_SUITE_WEP40 || params->cipher == WLAN_CIPHER_SUITE_WEP104)) { wdev->wext.keys->params[idx] = *params; memcpy(wdev->wext.keys->data[idx], params->key, params->key_len); wdev->wext.keys->params[idx].key = wdev->wext.keys->data[idx]; } if ((params->cipher == WLAN_CIPHER_SUITE_WEP40 || params->cipher == WLAN_CIPHER_SUITE_WEP104) && (tx_key || (!addr && wdev->wext.default_key == -1))) { if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) { /* * If we are getting a new TX key from not having * had one before we need to join a new IBSS with * the privacy bit set. */ if (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->wext.default_key == -1) { cfg80211_leave_ibss(rdev, wdev->netdev, true); rejoin = true; } err = rdev_set_default_key(rdev, dev, -1, idx, true, true); } if (!err) { wdev->wext.default_key = idx; if (rejoin) err = cfg80211_ibss_wext_join(rdev, wdev); } return err; } if (params->cipher == WLAN_CIPHER_SUITE_AES_CMAC && (tx_key || (!addr && wdev->wext.default_mgmt_key == -1))) { if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_set_default_mgmt_key(rdev, dev, -1, idx); if (!err) wdev->wext.default_mgmt_key = idx; return err; } return 0; } static int cfg80211_wext_siwencode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *keybuf) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int idx, err; bool remove = false; struct key_params params; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; /* no use -- only MFP (set_default_mgmt_key) is optional */ if (!rdev->ops->del_key || !rdev->ops->add_key || !rdev->ops->set_default_key) return -EOPNOTSUPP; wiphy_lock(&rdev->wiphy); if (wdev->valid_links) { err = -EOPNOTSUPP; goto out; } idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { idx = wdev->wext.default_key; if (idx < 0) idx = 0; } else if (idx < 1 || idx > 4) { err = -EINVAL; goto out; } else { idx--; } if (erq->flags & IW_ENCODE_DISABLED) remove = true; else if (erq->length == 0) { /* No key data - just set the default TX key index */ err = 0; if (wdev->connected || (wdev->iftype == NL80211_IFTYPE_ADHOC && wdev->u.ibss.current_bss)) err = rdev_set_default_key(rdev, dev, -1, idx, true, true); if (!err) wdev->wext.default_key = idx; goto out; } memset(¶ms, 0, sizeof(params)); params.key = keybuf; params.key_len = erq->length; if (erq->length == 5) { params.cipher = WLAN_CIPHER_SUITE_WEP40; } else if (erq->length == 13) { params.cipher = WLAN_CIPHER_SUITE_WEP104; } else if (!remove) { err = -EINVAL; goto out; } err = cfg80211_set_encryption(rdev, dev, false, NULL, remove, wdev->wext.default_key == -1, idx, ¶ms); out: wiphy_unlock(&rdev->wiphy); return err; } static int cfg80211_wext_siwencodeext(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct iw_encode_ext *ext = (struct iw_encode_ext *) extra; const u8 *addr; int idx; bool remove = false; struct key_params params; u32 cipher; int ret; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; /* no use -- only MFP (set_default_mgmt_key) is optional */ if (!rdev->ops->del_key || !rdev->ops->add_key || !rdev->ops->set_default_key) return -EOPNOTSUPP; if (wdev->valid_links) return -EOPNOTSUPP; switch (ext->alg) { case IW_ENCODE_ALG_NONE: remove = true; cipher = 0; break; case IW_ENCODE_ALG_WEP: if (ext->key_len == 5) cipher = WLAN_CIPHER_SUITE_WEP40; else if (ext->key_len == 13) cipher = WLAN_CIPHER_SUITE_WEP104; else return -EINVAL; break; case IW_ENCODE_ALG_TKIP: cipher = WLAN_CIPHER_SUITE_TKIP; break; case IW_ENCODE_ALG_CCMP: cipher = WLAN_CIPHER_SUITE_CCMP; break; case IW_ENCODE_ALG_AES_CMAC: cipher = WLAN_CIPHER_SUITE_AES_CMAC; break; default: return -EOPNOTSUPP; } if (erq->flags & IW_ENCODE_DISABLED) remove = true; idx = erq->flags & IW_ENCODE_INDEX; if (cipher == WLAN_CIPHER_SUITE_AES_CMAC) { if (idx < 4 || idx > 5) { idx = wdev->wext.default_mgmt_key; if (idx < 0) return -EINVAL; } else idx--; } else { if (idx < 1 || idx > 4) { idx = wdev->wext.default_key; if (idx < 0) return -EINVAL; } else idx--; } addr = ext->addr.sa_data; if (is_broadcast_ether_addr(addr)) addr = NULL; memset(¶ms, 0, sizeof(params)); params.key = ext->key; params.key_len = ext->key_len; params.cipher = cipher; if (ext->ext_flags & IW_ENCODE_EXT_RX_SEQ_VALID) { params.seq = ext->rx_seq; params.seq_len = 6; } wiphy_lock(wdev->wiphy); ret = cfg80211_set_encryption( rdev, dev, !(ext->ext_flags & IW_ENCODE_EXT_GROUP_KEY), addr, remove, ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, idx, ¶ms); wiphy_unlock(wdev->wiphy); return ret; } static int cfg80211_wext_giwencode(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *keybuf) { struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; int idx; if (wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_ADHOC) return -EOPNOTSUPP; idx = erq->flags & IW_ENCODE_INDEX; if (idx == 0) { idx = wdev->wext.default_key; if (idx < 0) idx = 0; } else if (idx < 1 || idx > 4) return -EINVAL; else idx--; erq->flags = idx + 1; if (!wdev->wext.keys || !wdev->wext.keys->params[idx].cipher) { erq->flags |= IW_ENCODE_DISABLED; erq->length = 0; return 0; } erq->length = min_t(size_t, erq->length, wdev->wext.keys->params[idx].key_len); memcpy(keybuf, wdev->wext.keys->params[idx].key, erq->length); erq->flags |= IW_ENCODE_ENABLED; return 0; } static int cfg80211_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_freq *wextfreq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = { .width = NL80211_CHAN_WIDTH_20_NOHT, }; int freq, ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); break; case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); break; case NL80211_IFTYPE_MONITOR: freq = cfg80211_wext_freq(wextfreq); if (freq < 0) { ret = freq; break; } if (freq == 0) { ret = -EINVAL; break; } chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); if (!chandef.chan) { ret = -EINVAL; break; } ret = cfg80211_set_monitor_channel(rdev, &chandef); break; case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wextfreq); if (freq < 0) { ret = freq; break; } if (freq == 0) { ret = -EINVAL; break; } chandef.center_freq1 = freq; chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); if (!chandef.chan) { ret = -EINVAL; break; } ret = cfg80211_set_mesh_channel(rdev, wdev, &chandef); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_freq *freq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = {}; int ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_giwfreq(dev, info, freq, extra); break; case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); break; case NL80211_IFTYPE_MONITOR: if (!rdev->ops->get_channel) { ret = -EINVAL; break; } ret = rdev_get_channel(rdev, wdev, 0, &chandef); if (ret) break; freq->m = chandef.chan->center_freq; freq->e = 6; ret = 0; break; default: ret = -EINVAL; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_siwtxpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); enum nl80211_tx_power_setting type; int dbm = 0; int ret; if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) return -EINVAL; if (data->txpower.flags & IW_TXPOW_RANGE) return -EINVAL; if (!rdev->ops->set_tx_power) return -EOPNOTSUPP; /* only change when not disabling */ if (!data->txpower.disabled) { rfkill_set_sw_state(rdev->wiphy.rfkill, false); if (data->txpower.fixed) { /* * wext doesn't support negative values, see * below where it's for automatic */ if (data->txpower.value < 0) return -EINVAL; dbm = data->txpower.value; type = NL80211_TX_POWER_FIXED; /* TODO: do regulatory check! */ } else { /* * Automatic power level setting, max being the value * passed in from userland. */ if (data->txpower.value < 0) { type = NL80211_TX_POWER_AUTOMATIC; } else { dbm = data->txpower.value; type = NL80211_TX_POWER_LIMITED; } } } else { if (rfkill_set_sw_state(rdev->wiphy.rfkill, true)) schedule_work(&rdev->rfkill_block); return 0; } wiphy_lock(&rdev->wiphy); ret = rdev_set_tx_power(rdev, wdev, type, DBM_TO_MBM(dbm)); wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwtxpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int err, val; if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM) return -EINVAL; if (data->txpower.flags & IW_TXPOW_RANGE) return -EINVAL; if (!rdev->ops->get_tx_power) return -EOPNOTSUPP; wiphy_lock(&rdev->wiphy); err = rdev_get_tx_power(rdev, wdev, &val); wiphy_unlock(&rdev->wiphy); if (err) return err; /* well... oh well */ data->txpower.fixed = 1; data->txpower.disabled = rfkill_blocked(rdev->wiphy.rfkill); data->txpower.value = val; data->txpower.flags = IW_TXPOW_DBM; return 0; } static int cfg80211_set_auth_alg(struct wireless_dev *wdev, s32 auth_alg) { int nr_alg = 0; if (!auth_alg) return -EINVAL; if (auth_alg & ~(IW_AUTH_ALG_OPEN_SYSTEM | IW_AUTH_ALG_SHARED_KEY | IW_AUTH_ALG_LEAP)) return -EINVAL; if (auth_alg & IW_AUTH_ALG_OPEN_SYSTEM) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; } if (auth_alg & IW_AUTH_ALG_SHARED_KEY) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_SHARED_KEY; } if (auth_alg & IW_AUTH_ALG_LEAP) { nr_alg++; wdev->wext.connect.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; } if (nr_alg > 1) wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC; return 0; } static int cfg80211_set_wpa_version(struct wireless_dev *wdev, u32 wpa_versions) { if (wpa_versions & ~(IW_AUTH_WPA_VERSION_WPA | IW_AUTH_WPA_VERSION_WPA2| IW_AUTH_WPA_VERSION_DISABLED)) return -EINVAL; if ((wpa_versions & IW_AUTH_WPA_VERSION_DISABLED) && (wpa_versions & (IW_AUTH_WPA_VERSION_WPA| IW_AUTH_WPA_VERSION_WPA2))) return -EINVAL; if (wpa_versions & IW_AUTH_WPA_VERSION_DISABLED) wdev->wext.connect.crypto.wpa_versions &= ~(NL80211_WPA_VERSION_1|NL80211_WPA_VERSION_2); if (wpa_versions & IW_AUTH_WPA_VERSION_WPA) wdev->wext.connect.crypto.wpa_versions |= NL80211_WPA_VERSION_1; if (wpa_versions & IW_AUTH_WPA_VERSION_WPA2) wdev->wext.connect.crypto.wpa_versions |= NL80211_WPA_VERSION_2; return 0; } static int cfg80211_set_cipher_group(struct wireless_dev *wdev, u32 cipher) { if (cipher & IW_AUTH_CIPHER_WEP40) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_WEP40; else if (cipher & IW_AUTH_CIPHER_WEP104) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_WEP104; else if (cipher & IW_AUTH_CIPHER_TKIP) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_TKIP; else if (cipher & IW_AUTH_CIPHER_CCMP) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_CCMP; else if (cipher & IW_AUTH_CIPHER_AES_CMAC) wdev->wext.connect.crypto.cipher_group = WLAN_CIPHER_SUITE_AES_CMAC; else if (cipher & IW_AUTH_CIPHER_NONE) wdev->wext.connect.crypto.cipher_group = 0; else return -EINVAL; return 0; } static int cfg80211_set_cipher_pairwise(struct wireless_dev *wdev, u32 cipher) { int nr_ciphers = 0; u32 *ciphers_pairwise = wdev->wext.connect.crypto.ciphers_pairwise; if (cipher & IW_AUTH_CIPHER_WEP40) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_WEP40; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_WEP104) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_WEP104; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_TKIP) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_TKIP; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_CCMP) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_CCMP; nr_ciphers++; } if (cipher & IW_AUTH_CIPHER_AES_CMAC) { ciphers_pairwise[nr_ciphers] = WLAN_CIPHER_SUITE_AES_CMAC; nr_ciphers++; } BUILD_BUG_ON(NL80211_MAX_NR_CIPHER_SUITES < 5); wdev->wext.connect.crypto.n_ciphers_pairwise = nr_ciphers; return 0; } static int cfg80211_set_key_mgt(struct wireless_dev *wdev, u32 key_mgt) { int nr_akm_suites = 0; if (key_mgt & ~(IW_AUTH_KEY_MGMT_802_1X | IW_AUTH_KEY_MGMT_PSK)) return -EINVAL; if (key_mgt & IW_AUTH_KEY_MGMT_802_1X) { wdev->wext.connect.crypto.akm_suites[nr_akm_suites] = WLAN_AKM_SUITE_8021X; nr_akm_suites++; } if (key_mgt & IW_AUTH_KEY_MGMT_PSK) { wdev->wext.connect.crypto.akm_suites[nr_akm_suites] = WLAN_AKM_SUITE_PSK; nr_akm_suites++; } wdev->wext.connect.crypto.n_akm_suites = nr_akm_suites; return 0; } static int cfg80211_wext_siwauth(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *data = &wrqu->param; struct wireless_dev *wdev = dev->ieee80211_ptr; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; switch (data->flags & IW_AUTH_INDEX) { case IW_AUTH_PRIVACY_INVOKED: wdev->wext.connect.privacy = data->value; return 0; case IW_AUTH_WPA_VERSION: return cfg80211_set_wpa_version(wdev, data->value); case IW_AUTH_CIPHER_GROUP: return cfg80211_set_cipher_group(wdev, data->value); case IW_AUTH_KEY_MGMT: return cfg80211_set_key_mgt(wdev, data->value); case IW_AUTH_CIPHER_PAIRWISE: return cfg80211_set_cipher_pairwise(wdev, data->value); case IW_AUTH_80211_AUTH_ALG: return cfg80211_set_auth_alg(wdev, data->value); case IW_AUTH_WPA_ENABLED: case IW_AUTH_RX_UNENCRYPTED_EAPOL: case IW_AUTH_DROP_UNENCRYPTED: case IW_AUTH_MFP: return 0; default: return -EOPNOTSUPP; } } static int cfg80211_wext_giwauth(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { /* XXX: what do we need? */ return -EOPNOTSUPP; } static int cfg80211_wext_siwpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); bool ps; int timeout = wdev->ps_timeout; int err; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; if (!rdev->ops->set_power_mgmt) return -EOPNOTSUPP; if (wrq->disabled) { ps = false; } else { switch (wrq->flags & IW_POWER_MODE) { case IW_POWER_ON: /* If not specified */ case IW_POWER_MODE: /* If set all mask */ case IW_POWER_ALL_R: /* If explicitely state all */ ps = true; break; default: /* Otherwise we ignore */ return -EINVAL; } if (wrq->flags & ~(IW_POWER_MODE | IW_POWER_TIMEOUT)) return -EINVAL; if (wrq->flags & IW_POWER_TIMEOUT) timeout = wrq->value / 1000; } wiphy_lock(&rdev->wiphy); err = rdev_set_power_mgmt(rdev, dev, ps, timeout); wiphy_unlock(&rdev->wiphy); if (err) return err; wdev->ps = ps; wdev->ps_timeout = timeout; return 0; } static int cfg80211_wext_giwpower(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; wrq->disabled = !wdev->ps; return 0; } static int cfg80211_wext_siwrate(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bitrate_mask mask; u32 fixed, maxrate; struct ieee80211_supported_band *sband; int band, ridx, ret; bool match = false; if (!rdev->ops->set_bitrate_mask) return -EOPNOTSUPP; memset(&mask, 0, sizeof(mask)); fixed = 0; maxrate = (u32)-1; if (rate->value < 0) { /* nothing */ } else if (rate->fixed) { fixed = rate->value / 100000; } else { maxrate = rate->value / 100000; } for (band = 0; band < NUM_NL80211_BANDS; band++) { sband = wdev->wiphy->bands[band]; if (sband == NULL) continue; for (ridx = 0; ridx < sband->n_bitrates; ridx++) { struct ieee80211_rate *srate = &sband->bitrates[ridx]; if (fixed == srate->bitrate) { mask.control[band].legacy = 1 << ridx; match = true; break; } if (srate->bitrate <= maxrate) { mask.control[band].legacy |= 1 << ridx; match = true; } } } if (!match) return -EINVAL; wiphy_lock(&rdev->wiphy); if (dev->ieee80211_ptr->valid_links) ret = -EOPNOTSUPP; else ret = rdev_set_bitrate_mask(rdev, dev, 0, NULL, &mask); wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwrate(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct station_info sinfo = {}; u8 addr[ETH_ALEN]; int err; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!rdev->ops->get_station) return -EOPNOTSUPP; err = 0; if (!wdev->valid_links && wdev->links[0].client.current_bss) memcpy(addr, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); else err = -EOPNOTSUPP; if (err) return err; wiphy_lock(&rdev->wiphy); err = rdev_get_station(rdev, dev, addr, &sinfo); wiphy_unlock(&rdev->wiphy); if (err) return err; if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) { err = -EOPNOTSUPP; goto free; } rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); free: cfg80211_sinfo_release_content(&sinfo); return err; } /* Get wireless statistics. Called by /proc/net/wireless and by SIOCGIWSTATS */ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); /* we are under RTNL - globally locked - so can use static structs */ static struct iw_statistics wstats; static struct station_info sinfo = {}; u8 bssid[ETH_ALEN]; int ret; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION) return NULL; if (!rdev->ops->get_station) return NULL; /* Grab BSSID of current BSS, if any */ wiphy_lock(&rdev->wiphy); if (wdev->valid_links || !wdev->links[0].client.current_bss) { wiphy_unlock(&rdev->wiphy); return NULL; } memcpy(bssid, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); memset(&sinfo, 0, sizeof(sinfo)); ret = rdev_get_station(rdev, dev, bssid, &sinfo); wiphy_unlock(&rdev->wiphy); if (ret) return NULL; memset(&wstats, 0, sizeof(wstats)); switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { int sig = sinfo.signal; wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; wstats.qual.updated |= IW_QUAL_DBM; wstats.qual.level = sig; if (sig < -110) sig = -110; else if (sig > -40) sig = -40; wstats.qual.qual = sig + 110; break; } fallthrough; case CFG80211_SIGNAL_TYPE_UNSPEC: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; wstats.qual.updated |= IW_QUAL_QUAL_UPDATED; wstats.qual.level = sinfo.signal; wstats.qual.qual = sinfo.signal; break; } fallthrough; default: wstats.qual.updated |= IW_QUAL_LEVEL_INVALID; wstats.qual.updated |= IW_QUAL_QUAL_INVALID; } wstats.qual.updated |= IW_QUAL_NOISE_INVALID; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC)) wstats.discard.misc = sinfo.rx_dropped_misc; if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED)) wstats.discard.retries = sinfo.tx_failed; cfg80211_sinfo_release_content(&sinfo); return &wstats; } static int cfg80211_wext_siwap(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra); break; case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwap(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra); break; case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_siwessid(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *ssid) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_siwessid(dev, info, data, ssid); break; case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_siwessid(dev, info, data, ssid); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_giwessid(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *ssid) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; data->flags = 0; data->length = 0; wiphy_lock(&rdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: ret = cfg80211_ibss_wext_giwessid(dev, info, data, ssid); break; case NL80211_IFTYPE_STATION: ret = cfg80211_mgd_wext_giwessid(dev, info, data, ssid); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static int cfg80211_wext_siwpmksa(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmksa cfg_pmksa; struct iw_pmksa *pmksa = (struct iw_pmksa *)extra; int ret; memset(&cfg_pmksa, 0, sizeof(struct cfg80211_pmksa)); if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; cfg_pmksa.bssid = pmksa->bssid.sa_data; cfg_pmksa.pmkid = pmksa->pmkid; wiphy_lock(&rdev->wiphy); switch (pmksa->cmd) { case IW_PMKSA_ADD: if (!rdev->ops->set_pmksa) { ret = -EOPNOTSUPP; break; } ret = rdev_set_pmksa(rdev, dev, &cfg_pmksa); break; case IW_PMKSA_REMOVE: if (!rdev->ops->del_pmksa) { ret = -EOPNOTSUPP; break; } ret = rdev_del_pmksa(rdev, dev, &cfg_pmksa); break; case IW_PMKSA_FLUSH: if (!rdev->ops->flush_pmksa) { ret = -EOPNOTSUPP; break; } ret = rdev_flush_pmksa(rdev, dev); break; default: ret = -EOPNOTSUPP; break; } wiphy_unlock(&rdev->wiphy); return ret; } static const iw_handler cfg80211_handlers[] = { IW_HANDLER(SIOCGIWNAME, cfg80211_wext_giwname), IW_HANDLER(SIOCSIWFREQ, cfg80211_wext_siwfreq), IW_HANDLER(SIOCGIWFREQ, cfg80211_wext_giwfreq), IW_HANDLER(SIOCSIWMODE, cfg80211_wext_siwmode), IW_HANDLER(SIOCGIWMODE, cfg80211_wext_giwmode), IW_HANDLER(SIOCGIWRANGE, cfg80211_wext_giwrange), IW_HANDLER(SIOCSIWAP, cfg80211_wext_siwap), IW_HANDLER(SIOCGIWAP, cfg80211_wext_giwap), IW_HANDLER(SIOCSIWMLME, cfg80211_wext_siwmlme), IW_HANDLER(SIOCSIWSCAN, cfg80211_wext_siwscan), IW_HANDLER(SIOCGIWSCAN, cfg80211_wext_giwscan), IW_HANDLER(SIOCSIWESSID, cfg80211_wext_siwessid), IW_HANDLER(SIOCGIWESSID, cfg80211_wext_giwessid), IW_HANDLER(SIOCSIWRATE, cfg80211_wext_siwrate), IW_HANDLER(SIOCGIWRATE, cfg80211_wext_giwrate), IW_HANDLER(SIOCSIWRTS, cfg80211_wext_siwrts), IW_HANDLER(SIOCGIWRTS, cfg80211_wext_giwrts), IW_HANDLER(SIOCSIWFRAG, cfg80211_wext_siwfrag), IW_HANDLER(SIOCGIWFRAG, cfg80211_wext_giwfrag), IW_HANDLER(SIOCSIWTXPOW, cfg80211_wext_siwtxpower), IW_HANDLER(SIOCGIWTXPOW, cfg80211_wext_giwtxpower), IW_HANDLER(SIOCSIWRETRY, cfg80211_wext_siwretry), IW_HANDLER(SIOCGIWRETRY, cfg80211_wext_giwretry), IW_HANDLER(SIOCSIWENCODE, cfg80211_wext_siwencode), IW_HANDLER(SIOCGIWENCODE, cfg80211_wext_giwencode), IW_HANDLER(SIOCSIWPOWER, cfg80211_wext_siwpower), IW_HANDLER(SIOCGIWPOWER, cfg80211_wext_giwpower), IW_HANDLER(SIOCSIWGENIE, cfg80211_wext_siwgenie), IW_HANDLER(SIOCSIWAUTH, cfg80211_wext_siwauth), IW_HANDLER(SIOCGIWAUTH, cfg80211_wext_giwauth), IW_HANDLER(SIOCSIWENCODEEXT, cfg80211_wext_siwencodeext), IW_HANDLER(SIOCSIWPMKSA, cfg80211_wext_siwpmksa), }; const struct iw_handler_def cfg80211_wext_handler = { .num_standard = ARRAY_SIZE(cfg80211_handlers), .standard = cfg80211_handlers, .get_wireless_stats = cfg80211_wireless_stats, }; |
| 135 93 86 11 11 11 11 105 104 66 10 10 10 10 1 10 2 2 125 2 128 2 107 18 283 285 150 150 132 288 4 4 611 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | /* License: GPL */ #include <linux/filter.h> #include <linux/mutex.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <linux/module.h> #include <net/sock.h> #include <linux/kernel.h> #include <linux/tcp.h> #include <linux/workqueue.h> #include <linux/nospec.h> #include <linux/cookie.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; DEFINE_COOKIE(sock_cookie); u64 __sock_gen_cookie(struct sock *sk) { u64 res = atomic64_read(&sk->sk_cookie); if (!res) { u64 new = gen_cookie_next(&sock_cookie); atomic64_cmpxchg(&sk->sk_cookie, res, new); /* Another thread might have changed sk_cookie before us. */ res = atomic64_read(&sk->sk_cookie); } return res; } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie) { u64 res; if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE) return 0; res = sock_gen_cookie(sk); if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1]) return -ESTALE; return 0; } EXPORT_SYMBOL_GPL(sock_diag_check_cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie) { u64 res = sock_gen_cookie(sk); cookie[0] = (u32)res; cookie[1] = (u32)(res >> 32); } EXPORT_SYMBOL_GPL(sock_diag_save_cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) { u32 mem[SK_MEMINFO_VARS]; sk_get_meminfo(sk, mem); return nla_put(skb, attrtype, sizeof(mem), &mem); } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; struct sk_filter *filter; struct nlattr *attr; unsigned int flen; int err = 0; if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (!filter) goto out; fprog = filter->prog->orig_prog; if (!fprog) goto out; flen = bpf_classic_proglen(fprog); attr = nla_reserve(skb, attrtype, flen); if (attr == NULL) { err = -EMSGSIZE; goto out; } memcpy(nla_data(attr), fprog->filter, flen); out: rcu_read_unlock(); return err; } EXPORT_SYMBOL(sock_diag_put_filterinfo); struct broadcast_sk { struct sock *sk; struct work_struct work; }; static size_t sock_diag_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct inet_diag_msg) + nla_total_size(sizeof(u8)) /* INET_DIAG_PROTOCOL */ + nla_total_size_64bit(sizeof(struct tcp_info))); /* INET_DIAG_INFO */ } static void sock_diag_broadcast_destroy_work(struct work_struct *work) { struct broadcast_sk *bsk = container_of(work, struct broadcast_sk, work); struct sock *sk = bsk->sk; const struct sock_diag_handler *hndl; struct sk_buff *skb; const enum sknetlink_groups group = sock_diag_destroy_group(sk); int err = -1; WARN_ON(group == SKNLGRP_NONE); skb = nlmsg_new(sock_diag_nlmsg_size(), GFP_KERNEL); if (!skb) goto out; mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[sk->sk_family]; if (hndl && hndl->get_info) err = hndl->get_info(skb, sk); mutex_unlock(&sock_diag_table_mutex); if (!err) nlmsg_multicast(sock_net(sk)->diag_nlsk, skb, 0, group, GFP_KERNEL); else kfree_skb(skb); out: sk_destruct(sk); kfree(bsk); } void sock_diag_broadcast_destroy(struct sock *sk) { /* Note, this function is often called from an interrupt context. */ struct broadcast_sk *bsk = kmalloc(sizeof(struct broadcast_sk), GFP_ATOMIC); if (!bsk) return sk_destruct(sk); bsk->sk = sk; INIT_WORK(&bsk->work, sock_diag_broadcast_destroy_work); queue_work(broadcast_wq, &bsk->work); } void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) { mutex_lock(&sock_diag_table_mutex); inet_rcv_compat = fn; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) { mutex_lock(&sock_diag_table_mutex); inet_rcv_compat = NULL; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); int sock_diag_register(const struct sock_diag_handler *hndl) { int err = 0; if (hndl->family >= AF_MAX) return -EINVAL; mutex_lock(&sock_diag_table_mutex); if (sock_diag_handlers[hndl->family]) err = -EBUSY; else sock_diag_handlers[hndl->family] = hndl; mutex_unlock(&sock_diag_table_mutex); return err; } EXPORT_SYMBOL_GPL(sock_diag_register); void sock_diag_unregister(const struct sock_diag_handler *hnld) { int family = hnld->family; if (family >= AF_MAX) return; mutex_lock(&sock_diag_table_mutex); BUG_ON(sock_diag_handlers[family] != hnld); sock_diag_handlers[family] = NULL; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister); static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) { int err; struct sock_diag_req *req = nlmsg_data(nlh); const struct sock_diag_handler *hndl; if (nlmsg_len(nlh) < sizeof(*req)) return -EINVAL; if (req->sdiag_family >= AF_MAX) return -EINVAL; req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX); if (sock_diag_handlers[req->sdiag_family] == NULL) sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; if (hndl == NULL) err = -ENOENT; else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY) err = hndl->dump(skb, nlh); else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy) err = hndl->destroy(skb, nlh); else err = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return err; } static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int ret; switch (nlh->nlmsg_type) { case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) ret = inet_rcv_compat(skb, nlh); else ret = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return ret; case SOCK_DIAG_BY_FAMILY: case SOCK_DESTROY: return __sock_diag_cmd(skb, nlh); default: return -EINVAL; } } static DEFINE_MUTEX(sock_diag_mutex); static void sock_diag_rcv(struct sk_buff *skb) { mutex_lock(&sock_diag_mutex); netlink_rcv_skb(skb, &sock_diag_rcv_msg); mutex_unlock(&sock_diag_mutex); } static int sock_diag_bind(struct net *net, int group) { switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) sock_load_diag_module(AF_INET6, 0); break; } return 0; } int sock_diag_destroy(struct sock *sk, int err) { if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!sk->sk_prot->diag_destroy) return -EOPNOTSUPP; return sk->sk_prot->diag_destroy(sk, err); } EXPORT_SYMBOL_GPL(sock_diag_destroy); static int __net_init diag_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .groups = SKNLGRP_MAX, .input = sock_diag_rcv, .bind = sock_diag_bind, .flags = NL_CFG_F_NONROOT_RECV, }; net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg); return net->diag_nlsk == NULL ? -ENOMEM : 0; } static void __net_exit diag_net_exit(struct net *net) { netlink_kernel_release(net->diag_nlsk); net->diag_nlsk = NULL; } static struct pernet_operations diag_net_ops = { .init = diag_net_init, .exit = diag_net_exit, }; static int __init sock_diag_init(void) { broadcast_wq = alloc_workqueue("sock_diag_events", 0, 0); BUG_ON(!broadcast_wq); return register_pernet_subsys(&diag_net_ops); } device_initcall(sock_diag_init); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* XDP user-space ring structure * Copyright(c) 2018 Intel Corporation. */ #ifndef _LINUX_XSK_QUEUE_H #define _LINUX_XSK_QUEUE_H #include <linux/types.h> #include <linux/if_xdp.h> #include <net/xdp_sock.h> #include <net/xsk_buff_pool.h> #include "xsk.h" struct xdp_ring { u32 producer ____cacheline_aligned_in_smp; /* Hinder the adjacent cache prefetcher to prefetch the consumer * pointer if the producer pointer is touched and vice versa. */ u32 pad1 ____cacheline_aligned_in_smp; u32 consumer ____cacheline_aligned_in_smp; u32 pad2 ____cacheline_aligned_in_smp; u32 flags; u32 pad3 ____cacheline_aligned_in_smp; }; /* Used for the RX and TX queues for packets */ struct xdp_rxtx_ring { struct xdp_ring ptrs; struct xdp_desc desc[] ____cacheline_aligned_in_smp; }; /* Used for the fill and completion queues for buffers */ struct xdp_umem_ring { struct xdp_ring ptrs; u64 desc[] ____cacheline_aligned_in_smp; }; struct xsk_queue { u32 ring_mask; u32 nentries; u32 cached_prod; u32 cached_cons; struct xdp_ring *ring; u64 invalid_descs; u64 queue_empty_descs; size_t ring_vmalloc_size; }; struct parsed_desc { u32 mb; u32 valid; }; /* The structure of the shared state of the rings are a simple * circular buffer, as outlined in * Documentation/core-api/circular-buffers.rst. For the Rx and * completion ring, the kernel is the producer and user space is the * consumer. For the Tx and fill rings, the kernel is the consumer and * user space is the producer. * * producer consumer * * if (LOAD ->consumer) { (A) LOAD.acq ->producer (C) * STORE $data LOAD $data * STORE.rel ->producer (B) STORE.rel ->consumer (D) * } * * (A) pairs with (D), and (B) pairs with (C). * * Starting with (B), it protects the data from being written after * the producer pointer. If this barrier was missing, the consumer * could observe the producer pointer being set and thus load the data * before the producer has written the new data. The consumer would in * this case load the old data. * * (C) protects the consumer from speculatively loading the data before * the producer pointer actually has been read. If we do not have this * barrier, some architectures could load old data as speculative loads * are not discarded as the CPU does not know there is a dependency * between ->producer and data. * * (A) is a control dependency that separates the load of ->consumer * from the stores of $data. In case ->consumer indicates there is no * room in the buffer to store $data we do not. The dependency will * order both of the stores after the loads. So no barrier is needed. * * (D) protects the load of the data to be observed to happen after the * store of the consumer pointer. If we did not have this memory * barrier, the producer could observe the consumer pointer being set * and overwrite the data with a new value before the consumer got the * chance to read the old value. The consumer would thus miss reading * the old entry and very likely read the new entry twice, once right * now and again after circling through the ring. */ /* The operations on the rings are the following: * * producer consumer * * RESERVE entries PEEK in the ring for entries * WRITE data into the ring READ data from the ring * SUBMIT entries RELEASE entries * * The producer reserves one or more entries in the ring. It can then * fill in these entries and finally submit them so that they can be * seen and read by the consumer. * * The consumer peeks into the ring to see if the producer has written * any new entries. If so, the consumer can then read these entries * and when it is done reading them release them back to the producer * so that the producer can use these slots to fill in new entries. * * The function names below reflect these operations. */ /* Functions that read and validate content from consumer rings. */ static inline void __xskq_cons_read_addr_unchecked(struct xsk_queue *q, u32 cached_cons, u64 *addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; u32 idx = cached_cons & q->ring_mask; *addr = ring->desc[idx]; } static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) { if (q->cached_cons != q->cached_prod) { __xskq_cons_read_addr_unchecked(q, q->cached_cons, addr); return true; } return false; } static inline bool xp_unused_options_set(u32 options) { return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA); } static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { u64 addr = desc->addr - pool->tx_metadata_len; u64 len = desc->len + pool->tx_metadata_len; u64 offset = addr & (pool->chunk_size - 1); if (!desc->len) return false; if (offset + len > pool->chunk_size) return false; if (addr >= pool->addrs_cnt) return false; if (xp_unused_options_set(desc->options)) return false; return true; } static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len; u64 len = desc->len + pool->tx_metadata_len; if (!desc->len) return false; if (len > pool->chunk_size) return false; if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt || xp_desc_crosses_non_contig_pg(pool, addr, len)) return false; if (xp_unused_options_set(desc->options)) return false; return true; } static inline bool xp_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { return pool->unaligned ? xp_unaligned_validate_desc(pool, desc) : xp_aligned_validate_desc(pool, desc); } static inline bool xskq_has_descs(struct xsk_queue *q) { return q->cached_cons != q->cached_prod; } static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, struct xsk_buff_pool *pool) { if (!xp_validate_desc(pool, d)) { q->invalid_descs++; return false; } return true; } static inline bool xskq_cons_read_desc(struct xsk_queue *q, struct xdp_desc *desc, struct xsk_buff_pool *pool) { if (q->cached_cons != q->cached_prod) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = q->cached_cons & q->ring_mask; *desc = ring->desc[idx]; return xskq_cons_is_valid_desc(q, desc, pool); } q->queue_empty_descs++; return false; } static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt) { q->cached_cons += cnt; } static inline void parse_desc(struct xsk_queue *q, struct xsk_buff_pool *pool, struct xdp_desc *desc, struct parsed_desc *parsed) { parsed->valid = xskq_cons_is_valid_desc(q, desc, pool); parsed->mb = xp_mb_desc(desc); } static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool, u32 max) { u32 cached_cons = q->cached_cons, nb_entries = 0; struct xdp_desc *descs = pool->tx_descs; u32 total_descs = 0, nr_frags = 0; /* track first entry, if stumble upon *any* invalid descriptor, rewind * current packet that consists of frags and stop the processing */ while (cached_cons != q->cached_prod && nb_entries < max) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = cached_cons & q->ring_mask; struct parsed_desc parsed; descs[nb_entries] = ring->desc[idx]; cached_cons++; parse_desc(q, pool, &descs[nb_entries], &parsed); if (unlikely(!parsed.valid)) break; if (likely(!parsed.mb)) { total_descs += (nr_frags + 1); nr_frags = 0; } else { nr_frags++; if (nr_frags == pool->netdev->xdp_zc_max_segs) { nr_frags = 0; break; } } nb_entries++; } cached_cons -= nr_frags; /* Release valid plus any invalid entries */ xskq_cons_release_n(q, cached_cons - q->cached_cons); return total_descs; } /* Functions for consumers */ static inline void __xskq_cons_release(struct xsk_queue *q) { smp_store_release(&q->ring->consumer, q->cached_cons); /* D, matchees A */ } static inline void __xskq_cons_peek(struct xsk_queue *q) { /* Refresh the local pointer */ q->cached_prod = smp_load_acquire(&q->ring->producer); /* C, matches B */ } static inline void xskq_cons_get_entries(struct xsk_queue *q) { __xskq_cons_release(q); __xskq_cons_peek(q); } static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max) { u32 entries = q->cached_prod - q->cached_cons; if (entries >= max) return max; __xskq_cons_peek(q); entries = q->cached_prod - q->cached_cons; return entries >= max ? max : entries; } static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt) { return xskq_cons_nb_entries(q, cnt) >= cnt; } static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); return xskq_cons_read_addr_unchecked(q, addr); } static inline bool xskq_cons_peek_desc(struct xsk_queue *q, struct xdp_desc *desc, struct xsk_buff_pool *pool) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); return xskq_cons_read_desc(q, desc, pool); } /* To improve performance in the xskq_cons_release functions, only update local state here. * Reflect this to global state when we get new entries from the ring in * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop. */ static inline void xskq_cons_release(struct xsk_queue *q) { q->cached_cons++; } static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt) { q->cached_cons -= cnt; } static inline u32 xskq_cons_present_entries(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer); } /* Functions for producers */ static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max) { u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons); if (free_entries >= max) return max; /* Refresh the local tail pointer */ q->cached_cons = READ_ONCE(q->ring->consumer); free_entries = q->nentries - (q->cached_prod - q->cached_cons); return free_entries >= max ? max : free_entries; } static inline bool xskq_prod_is_full(struct xsk_queue *q) { return xskq_prod_nb_free(q, 1) ? false : true; } static inline void xskq_prod_cancel_n(struct xsk_queue *q, u32 cnt) { q->cached_prod -= cnt; } static inline int xskq_prod_reserve(struct xsk_queue *q) { if (xskq_prod_is_full(q)) return -ENOSPC; /* A, matches D */ q->cached_prod++; return 0; } static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; if (xskq_prod_is_full(q)) return -ENOSPC; /* A, matches D */ ring->desc[q->cached_prod++ & q->ring_mask] = addr; return 0; } static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs, u32 nb_entries) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; u32 i, cached_prod; /* A, matches D */ cached_prod = q->cached_prod; for (i = 0; i < nb_entries; i++) ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr; q->cached_prod = cached_prod; } static inline int xskq_prod_reserve_desc(struct xsk_queue *q, u64 addr, u32 len, u32 flags) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx; if (xskq_prod_is_full(q)) return -ENOBUFS; /* A, matches D */ idx = q->cached_prod++ & q->ring_mask; ring->desc[idx].addr = addr; ring->desc[idx].len = len; ring->desc[idx].options = flags; return 0; } static inline void __xskq_prod_submit(struct xsk_queue *q, u32 idx) { smp_store_release(&q->ring->producer, idx); /* B, matches C */ } static inline void xskq_prod_submit(struct xsk_queue *q) { __xskq_prod_submit(q, q->cached_prod); } static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries) { __xskq_prod_submit(q, q->ring->producer + nb_entries); } static inline bool xskq_prod_is_empty(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ return READ_ONCE(q->ring->consumer) == READ_ONCE(q->ring->producer); } /* For both producers and consumers */ static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q) { return q ? q->invalid_descs : 0; } static inline u64 xskq_nb_queue_empty_descs(struct xsk_queue *q) { return q ? q->queue_empty_descs : 0; } struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); void xskq_destroy(struct xsk_queue *q_ops); #endif /* _LINUX_XSK_QUEUE_H */ |
| 148 137 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/filter.h> #include <linux/bpf.h> #include <net/netlink.h> #include <net/sock.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_bpf.h> #include <net/tc_act/tc_bpf.h> #include <net/tc_wrapper.h> #define ACT_BPF_NAME_LEN 256 struct tcf_bpf_cfg { struct bpf_prog *filter; struct sock_filter *bpf_ops; const char *bpf_name; u16 bpf_num_ops; bool is_ebpf; }; static struct tc_action_ops act_bpf_ops; TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { bool at_ingress = skb_at_tc_ingress(skb); struct tcf_bpf *prog = to_bpf(act); struct bpf_prog *filter; int action, filter_res; tcf_lastuse_update(&prog->tcf_tm); bstats_update(this_cpu_ptr(prog->common.cpu_bstats), skb); filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); bpf_compute_data_pointers(skb); filter_res = bpf_prog_run(filter, skb); __skb_pull(skb, skb->mac_len); } else { bpf_compute_data_pointers(skb); filter_res = bpf_prog_run(filter, skb); } if (unlikely(!skb->tstamp && skb->mono_delivery_time)) skb->mono_delivery_time = 0; if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); /* A BPF program may overwrite the default action opcode. * Similarly as in cls_bpf, if filter_res == -1 we use the * default action specified from tc. * * In case a different well-known TC_ACT opcode has been * returned, it will overwrite the default one. * * For everything else that is unknown, TC_ACT_UNSPEC is * returned. */ switch (filter_res) { case TC_ACT_PIPE: case TC_ACT_RECLASSIFY: case TC_ACT_OK: case TC_ACT_REDIRECT: action = filter_res; break; case TC_ACT_SHOT: action = filter_res; qstats_drop_inc(this_cpu_ptr(prog->common.cpu_qstats)); break; case TC_ACT_UNSPEC: action = prog->tcf_action; break; default: action = TC_ACT_UNSPEC; break; } return action; } static bool tcf_bpf_is_ebpf(const struct tcf_bpf *prog) { return !prog->bpf_ops; } static int tcf_bpf_dump_bpf_info(const struct tcf_bpf *prog, struct sk_buff *skb) { struct nlattr *nla; if (nla_put_u16(skb, TCA_ACT_BPF_OPS_LEN, prog->bpf_num_ops)) return -EMSGSIZE; nla = nla_reserve(skb, TCA_ACT_BPF_OPS, prog->bpf_num_ops * sizeof(struct sock_filter)); if (nla == NULL) return -EMSGSIZE; memcpy(nla_data(nla), prog->bpf_ops, nla_len(nla)); return 0; } static int tcf_bpf_dump_ebpf_info(const struct tcf_bpf *prog, struct sk_buff *skb) { struct nlattr *nla; if (prog->bpf_name && nla_put_string(skb, TCA_ACT_BPF_NAME, prog->bpf_name)) return -EMSGSIZE; if (nla_put_u32(skb, TCA_ACT_BPF_ID, prog->filter->aux->id)) return -EMSGSIZE; nla = nla_reserve(skb, TCA_ACT_BPF_TAG, sizeof(prog->filter->tag)); if (nla == NULL) return -EMSGSIZE; memcpy(nla_data(nla), prog->filter->tag, nla_len(nla)); return 0; } static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, int bind, int ref) { unsigned char *tp = skb_tail_pointer(skb); struct tcf_bpf *prog = to_bpf(act); struct tc_act_bpf opt = { .index = prog->tcf_index, .refcnt = refcount_read(&prog->tcf_refcnt) - ref, .bindcnt = atomic_read(&prog->tcf_bindcnt) - bind, }; struct tcf_t tm; int ret; spin_lock_bh(&prog->tcf_lock); opt.action = prog->tcf_action; if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if (tcf_bpf_is_ebpf(prog)) ret = tcf_bpf_dump_ebpf_info(prog, skb); else ret = tcf_bpf_dump_bpf_info(prog, skb); if (ret) goto nla_put_failure; tcf_tm_dump(&tm, &prog->tcf_tm); if (nla_put_64bit(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm, TCA_ACT_BPF_PAD)) goto nla_put_failure; spin_unlock_bh(&prog->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&prog->tcf_lock); nlmsg_trim(skb, tp); return -1; } static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = { [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) }, [TCA_ACT_BPF_FD] = { .type = NLA_U32 }, [TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN }, [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, }; static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg) { struct sock_filter *bpf_ops; struct sock_fprog_kern fprog_tmp; struct bpf_prog *fp; u16 bpf_size, bpf_num_ops; int ret; bpf_num_ops = nla_get_u16(tb[TCA_ACT_BPF_OPS_LEN]); if (bpf_num_ops > BPF_MAXINSNS || bpf_num_ops == 0) return -EINVAL; bpf_size = bpf_num_ops * sizeof(*bpf_ops); if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS])) return -EINVAL; bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL); if (bpf_ops == NULL) return -ENOMEM; fprog_tmp.len = bpf_num_ops; fprog_tmp.filter = bpf_ops; ret = bpf_prog_create(&fp, &fprog_tmp); if (ret < 0) { kfree(bpf_ops); return ret; } cfg->bpf_ops = bpf_ops; cfg->bpf_num_ops = bpf_num_ops; cfg->filter = fp; cfg->is_ebpf = false; return 0; } static int tcf_bpf_init_from_efd(struct nlattr **tb, struct tcf_bpf_cfg *cfg) { struct bpf_prog *fp; char *name = NULL; u32 bpf_fd; bpf_fd = nla_get_u32(tb[TCA_ACT_BPF_FD]); fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_ACT); if (IS_ERR(fp)) return PTR_ERR(fp); if (tb[TCA_ACT_BPF_NAME]) { name = nla_memdup(tb[TCA_ACT_BPF_NAME], GFP_KERNEL); if (!name) { bpf_prog_put(fp); return -ENOMEM; } } cfg->bpf_name = name; cfg->filter = fp; cfg->is_ebpf = true; return 0; } static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg) { struct bpf_prog *filter = cfg->filter; if (filter) { if (cfg->is_ebpf) bpf_prog_put(filter); else bpf_prog_destroy(filter); } kfree(cfg->bpf_ops); kfree(cfg->bpf_name); } static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog, struct tcf_bpf_cfg *cfg) { cfg->is_ebpf = tcf_bpf_is_ebpf(prog); /* updates to prog->filter are prevented, since it's called either * with tcf lock or during final cleanup in rcu callback */ cfg->filter = rcu_dereference_protected(prog->filter, 1); cfg->bpf_ops = prog->bpf_ops; cfg->bpf_name = prog->bpf_name; } static int tcf_bpf_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tcf_bpf_cfg cfg, old; struct tc_act_bpf *parm; struct tcf_bpf *prog; bool is_bpf, is_ebpf; int ret, res = 0; u32 index; if (!nla) return -EINVAL; ret = nla_parse_nested_deprecated(tb, TCA_ACT_BPF_MAX, nla, act_bpf_policy, NULL); if (ret < 0) return ret; if (!tb[TCA_ACT_BPF_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_ACT_BPF_PARMS]); index = parm->index; ret = tcf_idr_check_alloc(tn, &index, act, bind); if (!ret) { ret = tcf_idr_create(tn, index, est, act, &act_bpf_ops, bind, true, flags); if (ret < 0) { tcf_idr_cleanup(tn, index); return ret; } res = ACT_P_CREATED; } else if (ret > 0) { /* Don't override defaults. */ if (bind) return ACT_P_BOUND; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*act, bind); return -EEXIST; } } else { return ret; } ret = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (ret < 0) goto release_idr; is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS]; is_ebpf = tb[TCA_ACT_BPF_FD]; if (is_bpf == is_ebpf) { ret = -EINVAL; goto put_chain; } memset(&cfg, 0, sizeof(cfg)); ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) : tcf_bpf_init_from_efd(tb, &cfg); if (ret < 0) goto put_chain; prog = to_bpf(*act); spin_lock_bh(&prog->tcf_lock); if (res != ACT_P_CREATED) tcf_bpf_prog_fill_cfg(prog, &old); prog->bpf_ops = cfg.bpf_ops; prog->bpf_name = cfg.bpf_name; if (cfg.bpf_num_ops) prog->bpf_num_ops = cfg.bpf_num_ops; goto_ch = tcf_action_set_ctrlact(*act, parm->action, goto_ch); rcu_assign_pointer(prog->filter, cfg.filter); spin_unlock_bh(&prog->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (res != ACT_P_CREATED) { /* make sure the program being replaced is no longer executing */ synchronize_rcu(); tcf_bpf_cfg_cleanup(&old); } return res; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*act, bind); return ret; } static void tcf_bpf_cleanup(struct tc_action *act) { struct tcf_bpf_cfg tmp; tcf_bpf_prog_fill_cfg(to_bpf(act), &tmp); tcf_bpf_cfg_cleanup(&tmp); } static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", .id = TCA_ID_BPF, .owner = THIS_MODULE, .act = tcf_bpf_act, .dump = tcf_bpf_dump, .cleanup = tcf_bpf_cleanup, .init = tcf_bpf_init, .size = sizeof(struct tcf_bpf), }; static __net_init int bpf_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_bpf_ops.net_id); return tc_action_net_init(net, tn, &act_bpf_ops); } static void __net_exit bpf_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_bpf_ops.net_id); } static struct pernet_operations bpf_net_ops = { .init = bpf_init_net, .exit_batch = bpf_exit_net, .id = &act_bpf_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init bpf_init_module(void) { return tcf_register_action(&act_bpf_ops, &bpf_net_ops); } static void __exit bpf_cleanup_module(void) { tcf_unregister_action(&act_bpf_ops, &bpf_net_ops); } module_init(bpf_init_module); module_exit(bpf_cleanup_module); MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>"); MODULE_DESCRIPTION("TC BPF based action"); MODULE_LICENSE("GPL v2"); |
| 864 903 1379 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This header is used to share core functionality between the * standalone connection tracking module, and the compatibility layer's use * of connection tracking. * * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> * - generalize L3 protocol dependent part. * * Derived from include/linux/netfiter_ipv4/ip_conntrack_core.h */ #ifndef _NF_CONNTRACK_CORE_H #define _NF_CONNTRACK_CORE_H #include <linux/netfilter.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_l4proto.h> /* This header is used to share core functionality between the standalone connection tracking module, and the compatibility layer's use of connection tracking. */ unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state); int nf_conntrack_init_net(struct net *net); void nf_conntrack_cleanup_net(struct net *net); void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list); void nf_conntrack_proto_pernet_init(struct net *net); int nf_conntrack_proto_init(void); void nf_conntrack_proto_fini(void); int nf_conntrack_init_start(void); void nf_conntrack_cleanup_start(void); void nf_conntrack_init_end(void); void nf_conntrack_cleanup_end(void); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig); /* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple); int __nf_conntrack_confirm(struct sk_buff *skb); /* Confirm a connection: returns NF_DROP if packet must be dropped. */ static inline int nf_conntrack_confirm(struct sk_buff *skb) { struct nf_conn *ct = (struct nf_conn *)skb_nfct(skb); int ret = NF_ACCEPT; if (ct) { if (!nf_ct_is_confirmed(ct)) { ret = __nf_conntrack_confirm(skb); if (ret == NF_ACCEPT) ct = (struct nf_conn *)skb_nfct(skb); } if (ret == NF_ACCEPT && nf_ct_ecache_exist(ct)) nf_ct_deliver_cached_events(ct); } return ret; } unsigned int nf_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *proto); #define CONNTRACK_LOCKS 1024 extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; void nf_conntrack_lock(spinlock_t *lock); extern spinlock_t nf_conntrack_expect_lock; /* ctnetlink code shared by both ctnetlink and nf_conntrack_bpf */ static inline void __nf_ct_set_timeout(struct nf_conn *ct, u64 timeout) { if (timeout > INT_MAX) timeout = INT_MAX; if (nf_ct_is_confirmed(ct)) WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout); else ct->timeout = (u32)timeout; } int __nf_ct_change_timeout(struct nf_conn *ct, u64 cta_timeout); void __nf_ct_change_status(struct nf_conn *ct, unsigned long on, unsigned long off); int nf_ct_change_status_common(struct nf_conn *ct, unsigned int status); #endif /* _NF_CONNTRACK_CORE_H */ |
| 53 64 64 64 64 64 64 44 44 44 44 44 123 86 85 13 13 96 66 66 2 47 3 44 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 | /* * net/tipc/bcast.c: TIPC broadcast code * * Copyright (c) 2004-2006, 2014-2017, Ericsson AB * Copyright (c) 2004, Intel Corporation. * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include <linux/tipc_config.h> #include "socket.h" #include "msg.h" #include "bcast.h" #include "link.h" #include "name_table.h" #define BCLINK_WIN_DEFAULT 50 /* bcast link window size (default) */ #define BCLINK_WIN_MIN 32 /* bcast minimum link window size */ const char tipc_bclink_name[] = "broadcast-link"; unsigned long sysctl_tipc_bc_retruni __read_mostly; /** * struct tipc_bc_base - base structure for keeping broadcast send state * @link: broadcast send link structure * @inputq: data input queue; will only carry SOCK_WAKEUP messages * @dests: array keeping number of reachable destinations per bearer * @primary_bearer: a bearer having links to all broadcast destinations, if any * @bcast_support: indicates if primary bearer, if any, supports broadcast * @force_bcast: forces broadcast for multicast traffic * @rcast_support: indicates if all peer nodes support replicast * @force_rcast: forces replicast for multicast traffic * @rc_ratio: dest count as percentage of cluster size where send method changes * @bc_threshold: calculated from rc_ratio; if dests > threshold use broadcast */ struct tipc_bc_base { struct tipc_link *link; struct sk_buff_head inputq; int dests[MAX_BEARERS]; int primary_bearer; bool bcast_support; bool force_bcast; bool rcast_support; bool force_rcast; int rc_ratio; int bc_threshold; }; static struct tipc_bc_base *tipc_bc_base(struct net *net) { return tipc_net(net)->bcbase; } /* tipc_bcast_get_mtu(): -get the MTU currently used by broadcast link * Note: the MTU is decremented to give room for a tunnel header, in * case the message needs to be sent as replicast */ int tipc_bcast_get_mtu(struct net *net) { return tipc_link_mss(tipc_bc_sndlink(net)); } void tipc_bcast_toggle_rcast(struct net *net, bool supp) { tipc_bc_base(net)->rcast_support = supp; } static void tipc_bcbase_calc_bc_threshold(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); int cluster_size = tipc_link_bc_peers(tipc_bc_sndlink(net)); bb->bc_threshold = 1 + (cluster_size * bb->rc_ratio / 100); } /* tipc_bcbase_select_primary(): find a bearer with links to all destinations, * if any, and make it primary bearer */ static void tipc_bcbase_select_primary(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); int all_dests = tipc_link_bc_peers(bb->link); int max_win = tipc_link_max_win(bb->link); int min_win = tipc_link_min_win(bb->link); int i, mtu, prim; bb->primary_bearer = INVALID_BEARER_ID; bb->bcast_support = true; if (!all_dests) return; for (i = 0; i < MAX_BEARERS; i++) { if (!bb->dests[i]) continue; mtu = tipc_bearer_mtu(net, i); if (mtu < tipc_link_mtu(bb->link)) { tipc_link_set_mtu(bb->link, mtu); tipc_link_set_queue_limits(bb->link, min_win, max_win); } bb->bcast_support &= tipc_bearer_bcast_support(net, i); if (bb->dests[i] < all_dests) continue; bb->primary_bearer = i; /* Reduce risk that all nodes select same primary */ if ((i ^ tipc_own_addr(net)) & 1) break; } prim = bb->primary_bearer; if (prim != INVALID_BEARER_ID) bb->bcast_support = tipc_bearer_bcast_support(net, prim); } void tipc_bcast_inc_bearer_dst_cnt(struct net *net, int bearer_id) { struct tipc_bc_base *bb = tipc_bc_base(net); tipc_bcast_lock(net); bb->dests[bearer_id]++; tipc_bcbase_select_primary(net); tipc_bcast_unlock(net); } void tipc_bcast_dec_bearer_dst_cnt(struct net *net, int bearer_id) { struct tipc_bc_base *bb = tipc_bc_base(net); tipc_bcast_lock(net); bb->dests[bearer_id]--; tipc_bcbase_select_primary(net); tipc_bcast_unlock(net); } /* tipc_bcbase_xmit - broadcast a packet queue across one or more bearers * * Note that number of reachable destinations, as indicated in the dests[] * array, may transitionally differ from the number of destinations indicated * in each sent buffer. We can sustain this. Excess destination nodes will * drop and never acknowledge the unexpected packets, and missing destinations * will either require retransmission (if they are just about to be added to * the bearer), or be removed from the buffer's 'ackers' counter (if they * just went down) */ static void tipc_bcbase_xmit(struct net *net, struct sk_buff_head *xmitq) { int bearer_id; struct tipc_bc_base *bb = tipc_bc_base(net); struct sk_buff *skb, *_skb; struct sk_buff_head _xmitq; if (skb_queue_empty(xmitq)) return; /* The typical case: at least one bearer has links to all nodes */ bearer_id = bb->primary_bearer; if (bearer_id >= 0) { tipc_bearer_bc_xmit(net, bearer_id, xmitq); return; } /* We have to transmit across all bearers */ __skb_queue_head_init(&_xmitq); for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { if (!bb->dests[bearer_id]) continue; skb_queue_walk(xmitq, skb) { _skb = pskb_copy_for_clone(skb, GFP_ATOMIC); if (!_skb) break; __skb_queue_tail(&_xmitq, _skb); } tipc_bearer_bc_xmit(net, bearer_id, &_xmitq); } __skb_queue_purge(xmitq); __skb_queue_purge(&_xmitq); } static void tipc_bcast_select_xmit_method(struct net *net, int dests, struct tipc_mc_method *method) { struct tipc_bc_base *bb = tipc_bc_base(net); unsigned long exp = method->expires; /* Broadcast supported by used bearer/bearers? */ if (!bb->bcast_support) { method->rcast = true; return; } /* Any destinations which don't support replicast ? */ if (!bb->rcast_support) { method->rcast = false; return; } /* Can current method be changed ? */ method->expires = jiffies + TIPC_METHOD_EXPIRE; if (method->mandatory) return; if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL) && time_before(jiffies, exp)) return; /* Configuration as force 'broadcast' method */ if (bb->force_bcast) { method->rcast = false; return; } /* Configuration as force 'replicast' method */ if (bb->force_rcast) { method->rcast = true; return; } /* Configuration as 'autoselect' or default method */ /* Determine method to use now */ method->rcast = dests <= bb->bc_threshold; } /* tipc_bcast_xmit - broadcast the buffer chain to all external nodes * @net: the applicable net namespace * @pkts: chain of buffers containing message * @cong_link_cnt: set to 1 if broadcast link is congested, otherwise 0 * Consumes the buffer chain. * Returns 0 if success, otherwise errno: -EHOSTUNREACH,-EMSGSIZE */ int tipc_bcast_xmit(struct net *net, struct sk_buff_head *pkts, u16 *cong_link_cnt) { struct tipc_link *l = tipc_bc_sndlink(net); struct sk_buff_head xmitq; int rc = 0; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (tipc_link_bc_peers(l)) rc = tipc_link_xmit(l, pkts, &xmitq); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); __skb_queue_purge(pkts); if (rc == -ELINKCONG) { *cong_link_cnt = 1; rc = 0; } return rc; } /* tipc_rcast_xmit - replicate and send a message to given destination nodes * @net: the applicable net namespace * @pkts: chain of buffers containing message * @dests: list of destination nodes * @cong_link_cnt: returns number of congested links * @cong_links: returns identities of congested links * Returns 0 if success, otherwise errno */ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, struct tipc_nlist *dests, u16 *cong_link_cnt) { struct tipc_dest *dst, *tmp; struct sk_buff_head _pkts; u32 dnode, selector; selector = msg_link_selector(buf_msg(skb_peek(pkts))); __skb_queue_head_init(&_pkts); list_for_each_entry_safe(dst, tmp, &dests->list, list) { dnode = dst->node; if (!tipc_msg_pskb_copy(dnode, pkts, &_pkts)) return -ENOMEM; /* Any other return value than -ELINKCONG is ignored */ if (tipc_node_xmit(net, &_pkts, dnode, selector) == -ELINKCONG) (*cong_link_cnt)++; } return 0; } /* tipc_mcast_send_sync - deliver a dummy message with SYN bit * @net: the applicable net namespace * @skb: socket buffer to copy * @method: send method to be used * @dests: destination nodes for message. * Returns 0 if success, otherwise errno */ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, struct tipc_mc_method *method, struct tipc_nlist *dests) { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; struct sk_buff *_skb; u16 cong_link_cnt; int rc = 0; /* Is a cluster supporting with new capabilities ? */ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) return 0; hdr = buf_msg(skb); if (msg_user(hdr) == MSG_FRAGMENTER) hdr = msg_inner_hdr(hdr); if (msg_type(hdr) != TIPC_MCAST_MSG) return 0; /* Allocate dummy message */ _skb = tipc_buf_acquire(MCAST_H_SIZE, GFP_KERNEL); if (!_skb) return -ENOMEM; /* Preparing for 'synching' header */ msg_set_syn(hdr, 1); /* Copy skb's header into a dummy header */ skb_copy_to_linear_data(_skb, hdr, MCAST_H_SIZE); skb_orphan(_skb); /* Reverse method for dummy message */ _hdr = buf_msg(_skb); msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); msg_set_errcode(_hdr, TIPC_ERR_NO_PORT); __skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt); else rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt); /* This queue should normally be empty by now */ __skb_queue_purge(&tmpq); return rc; } /* tipc_mcast_xmit - deliver message to indicated destination nodes * and to identified node local sockets * @net: the applicable net namespace * @pkts: chain of buffers containing message * @method: send method to be used * @dests: destination nodes for message. * @cong_link_cnt: returns number of encountered congested destination links * Consumes buffer chain. * Returns 0 if success, otherwise errno */ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, struct tipc_mc_method *method, struct tipc_nlist *dests, u16 *cong_link_cnt) { struct sk_buff_head inputq, localq; bool rcast = method->rcast; struct tipc_msg *hdr; struct sk_buff *skb; int rc = 0; skb_queue_head_init(&inputq); __skb_queue_head_init(&localq); /* Clone packets before they are consumed by next call */ if (dests->local && !tipc_msg_reassemble(pkts, &localq)) { rc = -ENOMEM; goto exit; } /* Send according to determined transmit method */ if (dests->remote) { tipc_bcast_select_xmit_method(net, dests->remote, method); skb = skb_peek(pkts); hdr = buf_msg(skb); if (msg_user(hdr) == MSG_FRAGMENTER) hdr = msg_inner_hdr(hdr); msg_set_is_rcast(hdr, method->rcast); /* Switch method ? */ if (rcast != method->rcast) { rc = tipc_mcast_send_sync(net, skb, method, dests); if (unlikely(rc)) { pr_err("Unable to send SYN: method %d, rc %d\n", rcast, rc); goto exit; } } if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); else rc = tipc_bcast_xmit(net, pkts, cong_link_cnt); } if (dests->local) { tipc_loopback_trace(net, &localq); tipc_sk_mcast_rcv(net, &localq, &inputq); } exit: /* This queue should normally be empty by now */ __skb_queue_purge(pkts); return rc; } /* tipc_bcast_rcv - receive a broadcast packet, and deliver to rcv link * * RCU is locked, no other locks set */ int tipc_bcast_rcv(struct net *net, struct tipc_link *l, struct sk_buff *skb) { struct tipc_msg *hdr = buf_msg(skb); struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; struct sk_buff_head xmitq; int rc; __skb_queue_head_init(&xmitq); if (msg_mc_netid(hdr) != tipc_netid(net) || !tipc_link_is_up(l)) { kfree_skb(skb); return 0; } tipc_bcast_lock(net); if (msg_user(hdr) == BCAST_PROTOCOL) rc = tipc_link_bc_nack_rcv(l, skb, &xmitq); else rc = tipc_link_rcv(l, skb, NULL); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); return rc; } /* tipc_bcast_ack_rcv - receive and handle a broadcast acknowledge * * RCU is locked, no other locks set */ void tipc_bcast_ack_rcv(struct net *net, struct tipc_link *l, struct tipc_msg *hdr) { struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; u16 acked = msg_bcast_ack(hdr); struct sk_buff_head xmitq; /* Ignore bc acks sent by peer before bcast synch point was received */ if (msg_bc_ack_invalid(hdr)) return; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); tipc_link_bc_ack_rcv(l, acked, 0, NULL, &xmitq, NULL); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); } /* tipc_bcast_synch_rcv - check and update rcv link with peer's send state * * RCU is locked, no other locks set */ int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l, struct tipc_msg *hdr, struct sk_buff_head *retrq) { struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; struct tipc_gap_ack_blks *ga; struct sk_buff_head xmitq; int rc = 0; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); if (msg_type(hdr) != STATE_MSG) { tipc_link_bc_init_rcv(l, hdr); } else if (!msg_bc_ack_invalid(hdr)) { tipc_get_gap_ack_blks(&ga, l, hdr, false); if (!sysctl_tipc_bc_retruni) retrq = &xmitq; rc = tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr), msg_bc_gap(hdr), ga, &xmitq, retrq); rc |= tipc_link_bc_sync_rcv(l, hdr, &xmitq); } tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); return rc; } /* tipc_bcast_add_peer - add a peer node to broadcast link and bearer * * RCU is locked, node lock is set */ void tipc_bcast_add_peer(struct net *net, struct tipc_link *uc_l, struct sk_buff_head *xmitq) { struct tipc_link *snd_l = tipc_bc_sndlink(net); tipc_bcast_lock(net); tipc_link_add_bc_peer(snd_l, uc_l, xmitq); tipc_bcbase_select_primary(net); tipc_bcbase_calc_bc_threshold(net); tipc_bcast_unlock(net); } /* tipc_bcast_remove_peer - remove a peer node from broadcast link and bearer * * RCU is locked, node lock is set */ void tipc_bcast_remove_peer(struct net *net, struct tipc_link *rcv_l) { struct tipc_link *snd_l = tipc_bc_sndlink(net); struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq; struct sk_buff_head xmitq; __skb_queue_head_init(&xmitq); tipc_bcast_lock(net); tipc_link_remove_bc_peer(snd_l, rcv_l, &xmitq); tipc_bcbase_select_primary(net); tipc_bcbase_calc_bc_threshold(net); tipc_bcast_unlock(net); tipc_bcbase_xmit(net, &xmitq); /* Any socket wakeup messages ? */ if (!skb_queue_empty(inputq)) tipc_sk_rcv(net, inputq); } int tipc_bclink_reset_stats(struct net *net, struct tipc_link *l) { if (!l) return -ENOPROTOOPT; tipc_bcast_lock(net); tipc_link_reset_stats(l); tipc_bcast_unlock(net); return 0; } static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win) { struct tipc_link *l = tipc_bc_sndlink(net); if (!l) return -ENOPROTOOPT; if (max_win < BCLINK_WIN_MIN) max_win = BCLINK_WIN_MIN; if (max_win > TIPC_MAX_LINK_WIN) return -EINVAL; tipc_bcast_lock(net); tipc_link_set_queue_limits(l, tipc_link_min_win(l), max_win); tipc_bcast_unlock(net); return 0; } static int tipc_bc_link_set_broadcast_mode(struct net *net, u32 bc_mode) { struct tipc_bc_base *bb = tipc_bc_base(net); switch (bc_mode) { case BCLINK_MODE_BCAST: if (!bb->bcast_support) return -ENOPROTOOPT; bb->force_bcast = true; bb->force_rcast = false; break; case BCLINK_MODE_RCAST: if (!bb->rcast_support) return -ENOPROTOOPT; bb->force_bcast = false; bb->force_rcast = true; break; case BCLINK_MODE_SEL: if (!bb->bcast_support || !bb->rcast_support) return -ENOPROTOOPT; bb->force_bcast = false; bb->force_rcast = false; break; default: return -EINVAL; } return 0; } static int tipc_bc_link_set_broadcast_ratio(struct net *net, u32 bc_ratio) { struct tipc_bc_base *bb = tipc_bc_base(net); if (!bb->bcast_support || !bb->rcast_support) return -ENOPROTOOPT; if (bc_ratio > 100 || bc_ratio <= 0) return -EINVAL; bb->rc_ratio = bc_ratio; tipc_bcast_lock(net); tipc_bcbase_calc_bc_threshold(net); tipc_bcast_unlock(net); return 0; } int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]) { int err; u32 win; u32 bc_mode; u32 bc_ratio; struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; if (!attrs[TIPC_NLA_LINK_PROP]) return -EINVAL; err = tipc_nl_parse_link_prop(attrs[TIPC_NLA_LINK_PROP], props); if (err) return err; if (!props[TIPC_NLA_PROP_WIN] && !props[TIPC_NLA_PROP_BROADCAST] && !props[TIPC_NLA_PROP_BROADCAST_RATIO]) { return -EOPNOTSUPP; } if (props[TIPC_NLA_PROP_BROADCAST]) { bc_mode = nla_get_u32(props[TIPC_NLA_PROP_BROADCAST]); err = tipc_bc_link_set_broadcast_mode(net, bc_mode); } if (!err && props[TIPC_NLA_PROP_BROADCAST_RATIO]) { bc_ratio = nla_get_u32(props[TIPC_NLA_PROP_BROADCAST_RATIO]); err = tipc_bc_link_set_broadcast_ratio(net, bc_ratio); } if (!err && props[TIPC_NLA_PROP_WIN]) { win = nla_get_u32(props[TIPC_NLA_PROP_WIN]); err = tipc_bc_link_set_queue_limits(net, win); } return err; } int tipc_bcast_init(struct net *net) { struct tipc_net *tn = tipc_net(net); struct tipc_bc_base *bb = NULL; struct tipc_link *l = NULL; bb = kzalloc(sizeof(*bb), GFP_KERNEL); if (!bb) goto enomem; tn->bcbase = bb; spin_lock_init(&tipc_net(net)->bclock); if (!tipc_link_bc_create(net, 0, 0, NULL, one_page_mtu, BCLINK_WIN_DEFAULT, BCLINK_WIN_DEFAULT, 0, &bb->inputq, NULL, NULL, &l)) goto enomem; bb->link = l; tn->bcl = l; bb->rc_ratio = 10; bb->rcast_support = true; return 0; enomem: kfree(bb); kfree(l); return -ENOMEM; } void tipc_bcast_stop(struct net *net) { struct tipc_net *tn = net_generic(net, tipc_net_id); synchronize_net(); kfree(tn->bcbase); kfree(tn->bcl); } void tipc_nlist_init(struct tipc_nlist *nl, u32 self) { memset(nl, 0, sizeof(*nl)); INIT_LIST_HEAD(&nl->list); nl->self = self; } void tipc_nlist_add(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = true; else if (tipc_dest_push(&nl->list, node, 0)) nl->remote++; } void tipc_nlist_del(struct tipc_nlist *nl, u32 node) { if (node == nl->self) nl->local = false; else if (tipc_dest_del(&nl->list, node, 0)) nl->remote--; } void tipc_nlist_purge(struct tipc_nlist *nl) { tipc_dest_list_purge(&nl->list); nl->remote = 0; nl->local = false; } u32 tipc_bcast_get_mode(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); if (bb->force_bcast) return BCLINK_MODE_BCAST; if (bb->force_rcast) return BCLINK_MODE_RCAST; if (bb->bcast_support && bb->rcast_support) return BCLINK_MODE_SEL; return 0; } u32 tipc_bcast_get_broadcast_ratio(struct net *net) { struct tipc_bc_base *bb = tipc_bc_base(net); return bb->rc_ratio; } void tipc_mcast_filter_msg(struct net *net, struct sk_buff_head *defq, struct sk_buff_head *inputq) { struct sk_buff *skb, *_skb, *tmp; struct tipc_msg *hdr, *_hdr; bool match = false; u32 node, port; skb = skb_peek(inputq); if (!skb) return; hdr = buf_msg(skb); if (likely(!msg_is_syn(hdr) && skb_queue_empty(defq))) return; node = msg_orignode(hdr); if (node == tipc_own_addr(net)) return; port = msg_origport(hdr); /* Has the twin SYN message already arrived ? */ skb_queue_walk(defq, _skb) { _hdr = buf_msg(_skb); if (msg_orignode(_hdr) != node) continue; if (msg_origport(_hdr) != port) continue; match = true; break; } if (!match) { if (!msg_is_syn(hdr)) return; __skb_dequeue(inputq); __skb_queue_tail(defq, skb); return; } /* Deliver non-SYN message from other link, otherwise queue it */ if (!msg_is_syn(hdr)) { if (msg_is_rcast(hdr) != msg_is_rcast(_hdr)) return; __skb_dequeue(inputq); __skb_queue_tail(defq, skb); return; } /* Queue non-SYN/SYN message from same link */ if (msg_is_rcast(hdr) == msg_is_rcast(_hdr)) { __skb_dequeue(inputq); __skb_queue_tail(defq, skb); return; } /* Matching SYN messages => return the one with data, if any */ __skb_unlink(_skb, defq); if (msg_data_sz(hdr)) { kfree_skb(_skb); } else { __skb_dequeue(inputq); kfree_skb(skb); __skb_queue_tail(inputq, _skb); } /* Deliver subsequent non-SYN messages from same peer */ skb_queue_walk_safe(defq, _skb, tmp) { _hdr = buf_msg(_skb); if (msg_orignode(_hdr) != node) continue; if (msg_origport(_hdr) != port) continue; if (msg_is_syn(_hdr)) break; __skb_unlink(_skb, defq); __skb_queue_tail(inputq, _skb); } } |
| 4 27 13 77 77 77 77 77 77 77 40 77 77 77 77 17 2 17 17 40 25 77 77 77 77 77 77 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 17 37 27 17 17 37 43 43 4 43 21 43 43 51 50 51 51 10 51 43 43 51 51 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ #include <linux/mm.h> #include <linux/llist.h> #include <linux/bpf.h> #include <linux/irq_work.h> #include <linux/bpf_mem_alloc.h> #include <linux/memcontrol.h> #include <asm/local.h> /* Any context (including NMI) BPF specific memory allocator. * * Tracing BPF programs can attach to kprobe and fentry. Hence they * run in unknown context where calling plain kmalloc() might not be safe. * * Front-end kmalloc() with per-cpu per-bucket cache of free elements. * Refill this cache asynchronously from irq_work. * * CPU_0 buckets * 16 32 64 96 128 196 256 512 1024 2048 4096 * ... * CPU_N buckets * 16 32 64 96 128 196 256 512 1024 2048 4096 * * The buckets are prefilled at the start. * BPF programs always run with migration disabled. * It's safe to allocate from cache of the current cpu with irqs disabled. * Free-ing is always done into bucket of the current cpu as well. * irq_work trims extra free elements from buckets with kfree * and refills them with kmalloc, so global kmalloc logic takes care * of freeing objects allocated by one cpu and freed on another. * * Every allocated objected is padded with extra 8 bytes that contains * struct llist_node. */ #define LLIST_NODE_SZ sizeof(struct llist_node) /* similar to kmalloc, but sizeof == 8 bucket is gone */ static u8 size_index[24] __ro_after_init = { 3, /* 8 */ 3, /* 16 */ 4, /* 24 */ 4, /* 32 */ 5, /* 40 */ 5, /* 48 */ 5, /* 56 */ 5, /* 64 */ 1, /* 72 */ 1, /* 80 */ 1, /* 88 */ 1, /* 96 */ 6, /* 104 */ 6, /* 112 */ 6, /* 120 */ 6, /* 128 */ 2, /* 136 */ 2, /* 144 */ 2, /* 152 */ 2, /* 160 */ 2, /* 168 */ 2, /* 176 */ 2, /* 184 */ 2 /* 192 */ }; static int bpf_mem_cache_idx(size_t size) { if (!size || size > 4096) return -1; if (size <= 192) return size_index[(size - 1) / 8] - 1; return fls(size - 1) - 2; } #define NUM_CACHES 11 struct bpf_mem_cache { /* per-cpu list of free objects of size 'unit_size'. * All accesses are done with interrupts disabled and 'active' counter * protection with __llist_add() and __llist_del_first(). */ struct llist_head free_llist; local_t active; /* Operations on the free_list from unit_alloc/unit_free/bpf_mem_refill * are sequenced by per-cpu 'active' counter. But unit_free() cannot * fail. When 'active' is busy the unit_free() will add an object to * free_llist_extra. */ struct llist_head free_llist_extra; struct irq_work refill_work; struct obj_cgroup *objcg; int unit_size; /* count of objects in free_llist */ int free_cnt; int low_watermark, high_watermark, batch; int percpu_size; bool draining; struct bpf_mem_cache *tgt; /* list of objects to be freed after RCU GP */ struct llist_head free_by_rcu; struct llist_node *free_by_rcu_tail; struct llist_head waiting_for_gp; struct llist_node *waiting_for_gp_tail; struct rcu_head rcu; atomic_t call_rcu_in_progress; struct llist_head free_llist_extra_rcu; /* list of objects to be freed after RCU tasks trace GP */ struct llist_head free_by_rcu_ttrace; struct llist_head waiting_for_gp_ttrace; struct rcu_head rcu_ttrace; atomic_t call_rcu_ttrace_in_progress; }; struct bpf_mem_caches { struct bpf_mem_cache cache[NUM_CACHES]; }; static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096}; static struct llist_node notrace *__llist_del_first(struct llist_head *head) { struct llist_node *entry, *next; entry = head->first; if (!entry) return NULL; next = entry->next; head->first = next; return entry; } static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags) { if (c->percpu_size) { void **obj = kmalloc_node(c->percpu_size, flags, node); void *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags); if (!obj || !pptr) { free_percpu(pptr); kfree(obj); return NULL; } obj[1] = pptr; return obj; } return kmalloc_node(c->unit_size, flags | __GFP_ZERO, node); } static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c) { #ifdef CONFIG_MEMCG_KMEM if (c->objcg) return get_mem_cgroup_from_objcg(c->objcg); #endif #ifdef CONFIG_MEMCG return root_mem_cgroup; #else return NULL; #endif } static void inc_active(struct bpf_mem_cache *c, unsigned long *flags) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) /* In RT irq_work runs in per-cpu kthread, so disable * interrupts to avoid preemption and interrupts and * reduce the chance of bpf prog executing on this cpu * when active counter is busy. */ local_irq_save(*flags); /* alloc_bulk runs from irq_work which will not preempt a bpf * program that does unit_alloc/unit_free since IRQs are * disabled there. There is no race to increment 'active' * counter. It protects free_llist from corruption in case NMI * bpf prog preempted this loop. */ WARN_ON_ONCE(local_inc_return(&c->active) != 1); } static void dec_active(struct bpf_mem_cache *c, unsigned long *flags) { local_dec(&c->active); if (IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_restore(*flags); } static void add_obj_to_free_list(struct bpf_mem_cache *c, void *obj) { unsigned long flags; inc_active(c, &flags); __llist_add(obj, &c->free_llist); c->free_cnt++; dec_active(c, &flags); } /* Mostly runs from irq_work except __init phase. */ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic) { struct mem_cgroup *memcg = NULL, *old_memcg; gfp_t gfp; void *obj; int i; gfp = __GFP_NOWARN | __GFP_ACCOUNT; gfp |= atomic ? GFP_NOWAIT : GFP_KERNEL; for (i = 0; i < cnt; i++) { /* * For every 'c' llist_del_first(&c->free_by_rcu_ttrace); is * done only by one CPU == current CPU. Other CPUs might * llist_add() and llist_del_all() in parallel. */ obj = llist_del_first(&c->free_by_rcu_ttrace); if (!obj) break; add_obj_to_free_list(c, obj); } if (i >= cnt) return; for (; i < cnt; i++) { obj = llist_del_first(&c->waiting_for_gp_ttrace); if (!obj) break; add_obj_to_free_list(c, obj); } if (i >= cnt) return; memcg = get_memcg(c); old_memcg = set_active_memcg(memcg); for (; i < cnt; i++) { /* Allocate, but don't deplete atomic reserves that typical * GFP_ATOMIC would do. irq_work runs on this cpu and kmalloc * will allocate from the current numa node which is what we * want here. */ obj = __alloc(c, node, gfp); if (!obj) break; add_obj_to_free_list(c, obj); } set_active_memcg(old_memcg); mem_cgroup_put(memcg); } static void free_one(void *obj, bool percpu) { if (percpu) { free_percpu(((void **)obj)[1]); kfree(obj); return; } kfree(obj); } static int free_all(struct llist_node *llnode, bool percpu) { struct llist_node *pos, *t; int cnt = 0; llist_for_each_safe(pos, t, llnode) { free_one(pos, percpu); cnt++; } return cnt; } static void __free_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace); free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); atomic_set(&c->call_rcu_ttrace_in_progress, 0); } static void __free_rcu_tasks_trace(struct rcu_head *head) { /* If RCU Tasks Trace grace period implies RCU grace period, * there is no need to invoke call_rcu(). */ if (rcu_trace_implies_rcu_gp()) __free_rcu(head); else call_rcu(head, __free_rcu); } static void enque_to_free(struct bpf_mem_cache *c, void *obj) { struct llist_node *llnode = obj; /* bpf_mem_cache is a per-cpu object. Freeing happens in irq_work. * Nothing races to add to free_by_rcu_ttrace list. */ llist_add(llnode, &c->free_by_rcu_ttrace); } static void do_call_rcu_ttrace(struct bpf_mem_cache *c) { struct llist_node *llnode, *t; if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) { if (unlikely(READ_ONCE(c->draining))) { llnode = llist_del_all(&c->free_by_rcu_ttrace); free_all(llnode, !!c->percpu_size); } return; } WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); llist_for_each_safe(llnode, t, llist_del_all(&c->free_by_rcu_ttrace)) llist_add(llnode, &c->waiting_for_gp_ttrace); if (unlikely(READ_ONCE(c->draining))) { __free_rcu(&c->rcu_ttrace); return; } /* Use call_rcu_tasks_trace() to wait for sleepable progs to finish. * If RCU Tasks Trace grace period implies RCU grace period, free * these elements directly, else use call_rcu() to wait for normal * progs to finish and finally do free_one() on each element. */ call_rcu_tasks_trace(&c->rcu_ttrace, __free_rcu_tasks_trace); } static void free_bulk(struct bpf_mem_cache *c) { struct bpf_mem_cache *tgt = c->tgt; struct llist_node *llnode, *t; unsigned long flags; int cnt; WARN_ON_ONCE(tgt->unit_size != c->unit_size); WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); do { inc_active(c, &flags); llnode = __llist_del_first(&c->free_llist); if (llnode) cnt = --c->free_cnt; else cnt = 0; dec_active(c, &flags); if (llnode) enque_to_free(tgt, llnode); } while (cnt > (c->high_watermark + c->low_watermark) / 2); /* and drain free_llist_extra */ llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra)) enque_to_free(tgt, llnode); do_call_rcu_ttrace(tgt); } static void __free_by_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu); struct bpf_mem_cache *tgt = c->tgt; struct llist_node *llnode; WARN_ON_ONCE(tgt->unit_size != c->unit_size); WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); llnode = llist_del_all(&c->waiting_for_gp); if (!llnode) goto out; llist_add_batch(llnode, c->waiting_for_gp_tail, &tgt->free_by_rcu_ttrace); /* Objects went through regular RCU GP. Send them to RCU tasks trace */ do_call_rcu_ttrace(tgt); out: atomic_set(&c->call_rcu_in_progress, 0); } static void check_free_by_rcu(struct bpf_mem_cache *c) { struct llist_node *llnode, *t; unsigned long flags; /* drain free_llist_extra_rcu */ if (unlikely(!llist_empty(&c->free_llist_extra_rcu))) { inc_active(c, &flags); llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra_rcu)) if (__llist_add(llnode, &c->free_by_rcu)) c->free_by_rcu_tail = llnode; dec_active(c, &flags); } if (llist_empty(&c->free_by_rcu)) return; if (atomic_xchg(&c->call_rcu_in_progress, 1)) { /* * Instead of kmalloc-ing new rcu_head and triggering 10k * call_rcu() to hit rcutree.qhimark and force RCU to notice * the overload just ask RCU to hurry up. There could be many * objects in free_by_rcu list. * This hint reduces memory consumption for an artificial * benchmark from 2 Gbyte to 150 Mbyte. */ rcu_request_urgent_qs_task(current); return; } WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); inc_active(c, &flags); WRITE_ONCE(c->waiting_for_gp.first, __llist_del_all(&c->free_by_rcu)); c->waiting_for_gp_tail = c->free_by_rcu_tail; dec_active(c, &flags); if (unlikely(READ_ONCE(c->draining))) { free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size); atomic_set(&c->call_rcu_in_progress, 0); } else { call_rcu_hurry(&c->rcu, __free_by_rcu); } } static void bpf_mem_refill(struct irq_work *work) { struct bpf_mem_cache *c = container_of(work, struct bpf_mem_cache, refill_work); int cnt; /* Racy access to free_cnt. It doesn't need to be 100% accurate */ cnt = c->free_cnt; if (cnt < c->low_watermark) /* irq_work runs on this cpu and kmalloc will allocate * from the current numa node which is what we want here. */ alloc_bulk(c, c->batch, NUMA_NO_NODE, true); else if (cnt > c->high_watermark) free_bulk(c); check_free_by_rcu(c); } static void notrace irq_work_raise(struct bpf_mem_cache *c) { irq_work_queue(&c->refill_work); } /* For typical bpf map case that uses bpf_mem_cache_alloc and single bucket * the freelist cache will be elem_size * 64 (or less) on each cpu. * * For bpf programs that don't have statically known allocation sizes and * assuming (low_mark + high_mark) / 2 as an average number of elements per * bucket and all buckets are used the total amount of memory in freelists * on each cpu will be: * 64*16 + 64*32 + 64*64 + 64*96 + 64*128 + 64*196 + 64*256 + 32*512 + 16*1024 + 8*2048 + 4*4096 * == ~ 116 Kbyte using below heuristic. * Initialized, but unused bpf allocator (not bpf map specific one) will * consume ~ 11 Kbyte per cpu. * Typical case will be between 11K and 116K closer to 11K. * bpf progs can and should share bpf_mem_cache when possible. * * Percpu allocation is typically rare. To avoid potential unnecessary large * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1. */ static void init_refill_work(struct bpf_mem_cache *c) { init_irq_work(&c->refill_work, bpf_mem_refill); if (c->percpu_size) { c->low_watermark = 1; c->high_watermark = 3; } else if (c->unit_size <= 256) { c->low_watermark = 32; c->high_watermark = 96; } else { /* When page_size == 4k, order-0 cache will have low_mark == 2 * and high_mark == 6 with batch alloc of 3 individual pages at * a time. * 8k allocs and above low == 1, high == 3, batch == 1. */ c->low_watermark = max(32 * 256 / c->unit_size, 1); c->high_watermark = max(96 * 256 / c->unit_size, 3); } c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1); } static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu) { int cnt = 1; /* To avoid consuming memory, for non-percpu allocation, assume that * 1st run of bpf prog won't be doing more than 4 map_update_elem from * irq disabled region if unit size is less than or equal to 256. * For all other cases, let us just do one allocation. */ if (!c->percpu_size && c->unit_size <= 256) cnt = 4; alloc_bulk(c, cnt, cpu_to_node(cpu), false); } /* When size != 0 bpf_mem_cache for each cpu. * This is typical bpf hash map use case when all elements have equal size. * * When size == 0 allocate 11 bpf_mem_cache-s for each cpu, then rely on * kmalloc/kfree. Max allocation size is 4096 in this case. * This is bpf_dynptr and bpf_kptr use case. */ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) { struct bpf_mem_caches *cc, __percpu *pcc; struct bpf_mem_cache *c, __percpu *pc; struct obj_cgroup *objcg = NULL; int cpu, i, unit_size, percpu_size = 0; if (percpu && size == 0) return -EINVAL; /* room for llist_node and per-cpu pointer */ if (percpu) percpu_size = LLIST_NODE_SZ + sizeof(void *); ma->percpu = percpu; if (size) { pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL); if (!pc) return -ENOMEM; if (!percpu) size += LLIST_NODE_SZ; /* room for llist_node */ unit_size = size; #ifdef CONFIG_MEMCG_KMEM if (memcg_bpf_enabled()) objcg = get_obj_cgroup_from_current(); #endif ma->objcg = objcg; for_each_possible_cpu(cpu) { c = per_cpu_ptr(pc, cpu); c->unit_size = unit_size; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } ma->cache = pc; return 0; } pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; #ifdef CONFIG_MEMCG_KMEM objcg = get_obj_cgroup_from_current(); #endif ma->objcg = objcg; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; c->unit_size = sizes[i]; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } } ma->caches = pcc; return 0; } int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg) { struct bpf_mem_caches __percpu *pcc; pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL); if (!pcc) return -ENOMEM; ma->caches = pcc; ma->objcg = objcg; ma->percpu = true; return 0; } int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size) { struct bpf_mem_caches *cc, __percpu *pcc; int cpu, i, unit_size, percpu_size; struct obj_cgroup *objcg; struct bpf_mem_cache *c; i = bpf_mem_cache_idx(size); if (i < 0) return -EINVAL; /* room for llist_node and per-cpu pointer */ percpu_size = LLIST_NODE_SZ + sizeof(void *); unit_size = sizes[i]; objcg = ma->objcg; pcc = ma->caches; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(pcc, cpu); c = &cc->cache[i]; if (c->unit_size) break; c->unit_size = unit_size; c->objcg = objcg; c->percpu_size = percpu_size; c->tgt = c; init_refill_work(c); prefill_mem_cache(c, cpu); } return 0; } static void drain_mem_cache(struct bpf_mem_cache *c) { bool percpu = !!c->percpu_size; /* No progs are using this bpf_mem_cache, but htab_map_free() called * bpf_mem_cache_free() for all remaining elements and they can be in * free_by_rcu_ttrace or in waiting_for_gp_ttrace lists, so drain those lists now. * * Except for waiting_for_gp_ttrace list, there are no concurrent operations * on these lists, so it is safe to use __llist_del_all(). */ free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu); free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu); free_all(__llist_del_all(&c->free_llist), percpu); free_all(__llist_del_all(&c->free_llist_extra), percpu); free_all(__llist_del_all(&c->free_by_rcu), percpu); free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu); free_all(llist_del_all(&c->waiting_for_gp), percpu); } static void check_mem_cache(struct bpf_mem_cache *c) { WARN_ON_ONCE(!llist_empty(&c->free_by_rcu_ttrace)); WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp_ttrace)); WARN_ON_ONCE(!llist_empty(&c->free_llist)); WARN_ON_ONCE(!llist_empty(&c->free_llist_extra)); WARN_ON_ONCE(!llist_empty(&c->free_by_rcu)); WARN_ON_ONCE(!llist_empty(&c->free_llist_extra_rcu)); WARN_ON_ONCE(!llist_empty(&c->waiting_for_gp)); } static void check_leaked_objs(struct bpf_mem_alloc *ma) { struct bpf_mem_caches *cc; struct bpf_mem_cache *c; int cpu, i; if (ma->cache) { for_each_possible_cpu(cpu) { c = per_cpu_ptr(ma->cache, cpu); check_mem_cache(c); } } if (ma->caches) { for_each_possible_cpu(cpu) { cc = per_cpu_ptr(ma->caches, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; check_mem_cache(c); } } } } static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) { check_leaked_objs(ma); free_percpu(ma->cache); free_percpu(ma->caches); ma->cache = NULL; ma->caches = NULL; } static void free_mem_alloc(struct bpf_mem_alloc *ma) { /* waiting_for_gp[_ttrace] lists were drained, but RCU callbacks * might still execute. Wait for them. * * rcu_barrier_tasks_trace() doesn't imply synchronize_rcu_tasks_trace(), * but rcu_barrier_tasks_trace() and rcu_barrier() below are only used * to wait for the pending __free_rcu_tasks_trace() and __free_rcu(), * so if call_rcu(head, __free_rcu) is skipped due to * rcu_trace_implies_rcu_gp(), it will be OK to skip rcu_barrier() by * using rcu_trace_implies_rcu_gp() as well. */ rcu_barrier(); /* wait for __free_by_rcu */ rcu_barrier_tasks_trace(); /* wait for __free_rcu */ if (!rcu_trace_implies_rcu_gp()) rcu_barrier(); free_mem_alloc_no_barrier(ma); } static void free_mem_alloc_deferred(struct work_struct *work) { struct bpf_mem_alloc *ma = container_of(work, struct bpf_mem_alloc, work); free_mem_alloc(ma); kfree(ma); } static void destroy_mem_alloc(struct bpf_mem_alloc *ma, int rcu_in_progress) { struct bpf_mem_alloc *copy; if (!rcu_in_progress) { /* Fast path. No callbacks are pending, hence no need to do * rcu_barrier-s. */ free_mem_alloc_no_barrier(ma); return; } copy = kmemdup(ma, sizeof(*ma), GFP_KERNEL); if (!copy) { /* Slow path with inline barrier-s */ free_mem_alloc(ma); return; } /* Defer barriers into worker to let the rest of map memory to be freed */ memset(ma, 0, sizeof(*ma)); INIT_WORK(©->work, free_mem_alloc_deferred); queue_work(system_unbound_wq, ©->work); } void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma) { struct bpf_mem_caches *cc; struct bpf_mem_cache *c; int cpu, i, rcu_in_progress; if (ma->cache) { rcu_in_progress = 0; for_each_possible_cpu(cpu) { c = per_cpu_ptr(ma->cache, cpu); WRITE_ONCE(c->draining, true); irq_work_sync(&c->refill_work); drain_mem_cache(c); rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } if (ma->objcg) obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } if (ma->caches) { rcu_in_progress = 0; for_each_possible_cpu(cpu) { cc = per_cpu_ptr(ma->caches, cpu); for (i = 0; i < NUM_CACHES; i++) { c = &cc->cache[i]; WRITE_ONCE(c->draining, true); irq_work_sync(&c->refill_work); drain_mem_cache(c); rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress); rcu_in_progress += atomic_read(&c->call_rcu_in_progress); } } if (ma->objcg) obj_cgroup_put(ma->objcg); destroy_mem_alloc(ma, rcu_in_progress); } } /* notrace is necessary here and in other functions to make sure * bpf programs cannot attach to them and cause llist corruptions. */ static void notrace *unit_alloc(struct bpf_mem_cache *c) { struct llist_node *llnode = NULL; unsigned long flags; int cnt = 0; /* Disable irqs to prevent the following race for majority of prog types: * prog_A * bpf_mem_alloc * preemption or irq -> prog_B * bpf_mem_alloc * * but prog_B could be a perf_event NMI prog. * Use per-cpu 'active' counter to order free_list access between * unit_alloc/unit_free/bpf_mem_refill. */ local_irq_save(flags); if (local_inc_return(&c->active) == 1) { llnode = __llist_del_first(&c->free_llist); if (llnode) { cnt = --c->free_cnt; *(struct bpf_mem_cache **)llnode = c; } } local_dec(&c->active); WARN_ON(cnt < 0); if (cnt < c->low_watermark) irq_work_raise(c); /* Enable IRQ after the enqueue of irq work completes, so irq work * will run after IRQ is enabled and free_llist may be refilled by * irq work before other task preempts current task. */ local_irq_restore(flags); return llnode; } /* Though 'ptr' object could have been allocated on a different cpu * add it to the free_llist of the current cpu. * Let kfree() logic deal with it when it's later called from irq_work. */ static void notrace unit_free(struct bpf_mem_cache *c, void *ptr) { struct llist_node *llnode = ptr - LLIST_NODE_SZ; unsigned long flags; int cnt = 0; BUILD_BUG_ON(LLIST_NODE_SZ > 8); /* * Remember bpf_mem_cache that allocated this object. * The hint is not accurate. */ c->tgt = *(struct bpf_mem_cache **)llnode; local_irq_save(flags); if (local_inc_return(&c->active) == 1) { __llist_add(llnode, &c->free_llist); cnt = ++c->free_cnt; } else { /* unit_free() cannot fail. Therefore add an object to atomic * llist. free_bulk() will drain it. Though free_llist_extra is * a per-cpu list we have to use atomic llist_add here, since * it also can be interrupted by bpf nmi prog that does another * unit_free() into the same free_llist_extra. */ llist_add(llnode, &c->free_llist_extra); } local_dec(&c->active); if (cnt > c->high_watermark) /* free few objects from current cpu into global kmalloc pool */ irq_work_raise(c); /* Enable IRQ after irq_work_raise() completes, otherwise when current * task is preempted by task which does unit_alloc(), unit_alloc() may * return NULL unexpectedly because irq work is already pending but can * not been triggered and free_llist can not be refilled timely. */ local_irq_restore(flags); } static void notrace unit_free_rcu(struct bpf_mem_cache *c, void *ptr) { struct llist_node *llnode = ptr - LLIST_NODE_SZ; unsigned long flags; c->tgt = *(struct bpf_mem_cache **)llnode; local_irq_save(flags); if (local_inc_return(&c->active) == 1) { if (__llist_add(llnode, &c->free_by_rcu)) c->free_by_rcu_tail = llnode; } else { llist_add(llnode, &c->free_llist_extra_rcu); } local_dec(&c->active); if (!atomic_read(&c->call_rcu_in_progress)) irq_work_raise(c); local_irq_restore(flags); } /* Called from BPF program or from sys_bpf syscall. * In both cases migration is disabled. */ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) { int idx; void *ret; if (!size) return NULL; if (!ma->percpu) size += LLIST_NODE_SZ; idx = bpf_mem_cache_idx(size); if (idx < 0) return NULL; ret = unit_alloc(this_cpu_ptr(ma->caches)->cache + idx); return !ret ? NULL : ret + LLIST_NODE_SZ; } void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) { struct bpf_mem_cache *c; int idx; if (!ptr) return; c = *(void **)(ptr - LLIST_NODE_SZ); idx = bpf_mem_cache_idx(c->unit_size); if (WARN_ON_ONCE(idx < 0)) return; unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr); } void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr) { struct bpf_mem_cache *c; int idx; if (!ptr) return; c = *(void **)(ptr - LLIST_NODE_SZ); idx = bpf_mem_cache_idx(c->unit_size); if (WARN_ON_ONCE(idx < 0)) return; unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr); } void notrace *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma) { void *ret; ret = unit_alloc(this_cpu_ptr(ma->cache)); return !ret ? NULL : ret + LLIST_NODE_SZ; } void notrace bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr) { if (!ptr) return; unit_free(this_cpu_ptr(ma->cache), ptr); } void notrace bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr) { if (!ptr) return; unit_free_rcu(this_cpu_ptr(ma->cache), ptr); } /* Directly does a kfree() without putting 'ptr' back to the free_llist * for reuse and without waiting for a rcu_tasks_trace gp. * The caller must first go through the rcu_tasks_trace gp for 'ptr' * before calling bpf_mem_cache_raw_free(). * It could be used when the rcu_tasks_trace callback does not have * a hold on the original bpf_mem_alloc object that allocated the * 'ptr'. This should only be used in the uncommon code path. * Otherwise, the bpf_mem_alloc's free_llist cannot be refilled * and may affect performance. */ void bpf_mem_cache_raw_free(void *ptr) { if (!ptr) return; kfree(ptr - LLIST_NODE_SZ); } /* When flags == GFP_KERNEL, it signals that the caller will not cause * deadlock when using kmalloc. bpf_mem_cache_alloc_flags() will use * kmalloc if the free_llist is empty. */ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) { struct bpf_mem_cache *c; void *ret; c = this_cpu_ptr(ma->cache); ret = unit_alloc(c); if (!ret && flags == GFP_KERNEL) { struct mem_cgroup *memcg, *old_memcg; memcg = get_memcg(c); old_memcg = set_active_memcg(memcg); ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT); if (ret) *(struct bpf_mem_cache **)ret = c; set_active_memcg(old_memcg); mem_cgroup_put(memcg); } return !ret ? NULL : ret + LLIST_NODE_SZ; } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* net/atm/svc.c - ATM SVC sockets */ /* Written 1995-2000 by Werner Almesberger, EPFL LRC/ICA */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ #include <linux/string.h> #include <linux/net.h> /* struct socket, struct proto_ops */ #include <linux/errno.h> /* error codes */ #include <linux/kernel.h> /* printk */ #include <linux/skbuff.h> #include <linux/wait.h> #include <linux/sched/signal.h> #include <linux/fcntl.h> /* O_NONBLOCK */ #include <linux/init.h> #include <linux/atm.h> /* ATM stuff */ #include <linux/atmsap.h> #include <linux/atmsvc.h> #include <linux/atmdev.h> #include <linux/bitops.h> #include <net/sock.h> /* for sock_no_* */ #include <linux/uaccess.h> #include <linux/export.h> #include "resources.h" #include "common.h" /* common for PVCs and SVCs */ #include "signaling.h" #include "addr.h" #ifdef CONFIG_COMPAT /* It actually takes struct sockaddr_atmsvc, not struct atm_iobuf */ #define COMPAT_ATM_ADDPARTY _IOW('a', ATMIOC_SPECIAL + 4, struct compat_atm_iobuf) #endif static int svc_create(struct net *net, struct socket *sock, int protocol, int kern); /* * Note: since all this is still nicely synchronized with the signaling demon, * there's no need to protect sleep loops with clis. If signaling is * moved into the kernel, that would change. */ static int svc_shutdown(struct socket *sock, int how) { return 0; } static void svc_disconnect(struct atm_vcc *vcc) { DEFINE_WAIT(wait); struct sk_buff *skb; struct sock *sk = sk_atm(vcc); pr_debug("%p\n", vcc); if (test_bit(ATM_VF_REGIS, &vcc->flags)) { sigd_enq(vcc, as_close, NULL, NULL, NULL); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (test_bit(ATM_VF_RELEASED, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); } /* beware - socket is still in use by atmsigd until the last as_indicate has been answered */ while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { atm_return(vcc, skb->truesize); pr_debug("LISTEN REL\n"); sigd_enq2(NULL, as_reject, vcc, NULL, NULL, &vcc->qos, 0); dev_kfree_skb(skb); } clear_bit(ATM_VF_REGIS, &vcc->flags); /* ... may retry later */ } static int svc_release(struct socket *sock) { struct sock *sk = sock->sk; struct atm_vcc *vcc; if (sk) { vcc = ATM_SD(sock); pr_debug("%p\n", vcc); clear_bit(ATM_VF_READY, &vcc->flags); /* * VCC pointer is used as a reference, * so we must not free it (thereby subjecting it to re-use) * before all pending connections are closed */ svc_disconnect(vcc); vcc_release(sock); } return 0; } static int svc_bind(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct sockaddr_atmsvc *addr; struct atm_vcc *vcc; int error; if (sockaddr_len != sizeof(struct sockaddr_atmsvc)) return -EINVAL; lock_sock(sk); if (sock->state == SS_CONNECTED) { error = -EISCONN; goto out; } if (sock->state != SS_UNCONNECTED) { error = -EINVAL; goto out; } vcc = ATM_SD(sock); addr = (struct sockaddr_atmsvc *) sockaddr; if (addr->sas_family != AF_ATMSVC) { error = -EAFNOSUPPORT; goto out; } clear_bit(ATM_VF_BOUND, &vcc->flags); /* failing rebind will kill old binding */ /* @@@ check memory (de)allocation on rebind */ if (!test_bit(ATM_VF_HASQOS, &vcc->flags)) { error = -EBADFD; goto out; } vcc->local = *addr; set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_bind, NULL, NULL, &vcc->local); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); clear_bit(ATM_VF_REGIS, &vcc->flags); /* doesn't count */ if (!sigd) { error = -EUNATCH; goto out; } if (!sk->sk_err) set_bit(ATM_VF_BOUND, &vcc->flags); error = -sk->sk_err; out: release_sock(sk); return error; } static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len, int flags) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct sockaddr_atmsvc *addr; struct atm_vcc *vcc = ATM_SD(sock); int error; pr_debug("%p\n", vcc); lock_sock(sk); if (sockaddr_len != sizeof(struct sockaddr_atmsvc)) { error = -EINVAL; goto out; } switch (sock->state) { default: error = -EINVAL; goto out; case SS_CONNECTED: error = -EISCONN; goto out; case SS_CONNECTING: if (test_bit(ATM_VF_WAITING, &vcc->flags)) { error = -EALREADY; goto out; } sock->state = SS_UNCONNECTED; if (sk->sk_err) { error = -sk->sk_err; goto out; } break; case SS_UNCONNECTED: addr = (struct sockaddr_atmsvc *) sockaddr; if (addr->sas_family != AF_ATMSVC) { error = -EAFNOSUPPORT; goto out; } if (!test_bit(ATM_VF_HASQOS, &vcc->flags)) { error = -EBADFD; goto out; } if (vcc->qos.txtp.traffic_class == ATM_ANYCLASS || vcc->qos.rxtp.traffic_class == ATM_ANYCLASS) { error = -EINVAL; goto out; } if (!vcc->qos.txtp.traffic_class && !vcc->qos.rxtp.traffic_class) { error = -EINVAL; goto out; } vcc->remote = *addr; set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_connect, NULL, NULL, &vcc->remote); if (flags & O_NONBLOCK) { sock->state = SS_CONNECTING; error = -EINPROGRESS; goto out; } error = 0; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { schedule(); if (!signal_pending(current)) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); continue; } pr_debug("*ABORT*\n"); /* * This is tricky: * Kernel ---close--> Demon * Kernel <--close--- Demon * or * Kernel ---close--> Demon * Kernel <--error--- Demon * or * Kernel ---close--> Demon * Kernel <--okay---- Demon * Kernel <--close--- Demon */ sigd_enq(vcc, as_close, NULL, NULL, NULL); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); schedule(); } if (!sk->sk_err) while (!test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); schedule(); } clear_bit(ATM_VF_REGIS, &vcc->flags); clear_bit(ATM_VF_RELEASED, &vcc->flags); clear_bit(ATM_VF_CLOSE, &vcc->flags); /* we're gone now but may connect later */ error = -EINTR; break; } finish_wait(sk_sleep(sk), &wait); if (error) goto out; if (!sigd) { error = -EUNATCH; goto out; } if (sk->sk_err) { error = -sk->sk_err; goto out; } } vcc->qos.txtp.max_pcr = SELECT_TOP_PCR(vcc->qos.txtp); vcc->qos.txtp.pcr = 0; vcc->qos.txtp.min_pcr = 0; error = vcc_connect(sock, vcc->itf, vcc->vpi, vcc->vci); if (!error) sock->state = SS_CONNECTED; else (void)svc_disconnect(vcc); out: release_sock(sk); return error; } static int svc_listen(struct socket *sock, int backlog) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; pr_debug("%p\n", vcc); lock_sock(sk); /* let server handle listen on unbound sockets */ if (test_bit(ATM_VF_SESSION, &vcc->flags)) { error = -EINVAL; goto out; } if (test_bit(ATM_VF_LISTEN, &vcc->flags)) { error = -EADDRINUSE; goto out; } set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_listen, NULL, NULL, &vcc->local); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) { error = -EUNATCH; goto out; } set_bit(ATM_VF_LISTEN, &vcc->flags); vcc_insert_socket(sk); sk->sk_max_ack_backlog = backlog > 0 ? backlog : ATM_BACKLOG_DEFAULT; error = -sk->sk_err; out: release_sock(sk); return error; } static int svc_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk = sock->sk; struct sk_buff *skb; struct atmsvc_msg *msg; struct atm_vcc *old_vcc = ATM_SD(sock); struct atm_vcc *new_vcc; int error; lock_sock(sk); error = svc_create(sock_net(sk), newsock, 0, kern); if (error) goto out; new_vcc = ATM_SD(newsock); pr_debug("%p -> %p\n", old_vcc, new_vcc); while (1) { DEFINE_WAIT(wait); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (!(skb = skb_dequeue(&sk->sk_receive_queue)) && sigd) { if (test_bit(ATM_VF_RELEASED, &old_vcc->flags)) break; if (test_bit(ATM_VF_CLOSE, &old_vcc->flags)) { error = -sk->sk_err; break; } if (flags & O_NONBLOCK) { error = -EAGAIN; break; } release_sock(sk); schedule(); lock_sock(sk); if (signal_pending(current)) { error = -ERESTARTSYS; break; } prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } finish_wait(sk_sleep(sk), &wait); if (error) goto out; if (!skb) { error = -EUNATCH; goto out; } msg = (struct atmsvc_msg *)skb->data; new_vcc->qos = msg->qos; set_bit(ATM_VF_HASQOS, &new_vcc->flags); new_vcc->remote = msg->svc; new_vcc->local = msg->local; new_vcc->sap = msg->sap; error = vcc_connect(newsock, msg->pvc.sap_addr.itf, msg->pvc.sap_addr.vpi, msg->pvc.sap_addr.vci); dev_kfree_skb(skb); sk_acceptq_removed(sk); if (error) { sigd_enq2(NULL, as_reject, old_vcc, NULL, NULL, &old_vcc->qos, error); error = error == -EAGAIN ? -EBUSY : error; goto out; } /* wait should be short, so we ignore the non-blocking flag */ set_bit(ATM_VF_WAITING, &new_vcc->flags); sigd_enq(new_vcc, as_accept, old_vcc, NULL, NULL); for (;;) { prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &new_vcc->flags) || !sigd) break; release_sock(sk); schedule(); lock_sock(sk); } finish_wait(sk_sleep(sk_atm(new_vcc)), &wait); if (!sigd) { error = -EUNATCH; goto out; } if (!sk_atm(new_vcc)->sk_err) break; if (sk_atm(new_vcc)->sk_err != ERESTARTSYS) { error = -sk_atm(new_vcc)->sk_err; goto out; } } newsock->state = SS_CONNECTED; out: release_sock(sk); return error; } static int svc_getname(struct socket *sock, struct sockaddr *sockaddr, int peer) { struct sockaddr_atmsvc *addr; addr = (struct sockaddr_atmsvc *) sockaddr; memcpy(addr, peer ? &ATM_SD(sock)->remote : &ATM_SD(sock)->local, sizeof(struct sockaddr_atmsvc)); return sizeof(struct sockaddr_atmsvc); } int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos) { struct sock *sk = sk_atm(vcc); DEFINE_WAIT(wait); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq2(vcc, as_modify, NULL, NULL, &vcc->local, qos, 0); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || test_bit(ATM_VF_RELEASED, &vcc->flags) || !sigd) { break; } schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) return -EUNATCH; return -sk->sk_err; } static int svc_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int value, error = 0; lock_sock(sk); switch (optname) { case SO_ATMSAP: if (level != SOL_ATM || optlen != sizeof(struct atm_sap)) { error = -EINVAL; goto out; } if (copy_from_sockptr(&vcc->sap, optval, optlen)) { error = -EFAULT; goto out; } set_bit(ATM_VF_HASSAP, &vcc->flags); break; case SO_MULTIPOINT: if (level != SOL_ATM || optlen != sizeof(int)) { error = -EINVAL; goto out; } if (copy_from_sockptr(&value, optval, sizeof(int))) { error = -EFAULT; goto out; } if (value == 1) set_bit(ATM_VF_SESSION, &vcc->flags); else if (value == 0) clear_bit(ATM_VF_SESSION, &vcc->flags); else error = -EINVAL; break; default: error = vcc_setsockopt(sock, level, optname, optval, optlen); } out: release_sock(sk); return error; } static int svc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int error = 0, len; lock_sock(sk); if (!__SO_LEVEL_MATCH(optname, level) || optname != SO_ATMSAP) { error = vcc_getsockopt(sock, level, optname, optval, optlen); goto out; } if (get_user(len, optlen)) { error = -EFAULT; goto out; } if (len != sizeof(struct atm_sap)) { error = -EINVAL; goto out; } if (copy_to_user(optval, &ATM_SD(sock)->sap, sizeof(struct atm_sap))) { error = -EFAULT; goto out; } out: release_sock(sk); return error; } static int svc_addparty(struct socket *sock, struct sockaddr *sockaddr, int sockaddr_len, int flags) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; lock_sock(sk); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq(vcc, as_addparty, NULL, NULL, (struct sockaddr_atmsvc *) sockaddr); if (flags & O_NONBLOCK) { error = -EINPROGRESS; goto out; } pr_debug("added wait queue\n"); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); error = -xchg(&sk->sk_err_soft, 0); out: release_sock(sk); return error; } static int svc_dropparty(struct socket *sock, int ep_ref) { DEFINE_WAIT(wait); struct sock *sk = sock->sk; struct atm_vcc *vcc = ATM_SD(sock); int error; lock_sock(sk); set_bit(ATM_VF_WAITING, &vcc->flags); sigd_enq2(vcc, as_dropparty, NULL, NULL, NULL, NULL, ep_ref); for (;;) { prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (!test_bit(ATM_VF_WAITING, &vcc->flags) || !sigd) break; schedule(); } finish_wait(sk_sleep(sk), &wait); if (!sigd) { error = -EUNATCH; goto out; } error = -xchg(&sk->sk_err_soft, 0); out: release_sock(sk); return error; } static int svc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { int error, ep_ref; struct sockaddr_atmsvc sa; struct atm_vcc *vcc = ATM_SD(sock); switch (cmd) { case ATM_ADDPARTY: if (!test_bit(ATM_VF_SESSION, &vcc->flags)) return -EINVAL; if (copy_from_user(&sa, (void __user *) arg, sizeof(sa))) return -EFAULT; error = svc_addparty(sock, (struct sockaddr *)&sa, sizeof(sa), 0); break; case ATM_DROPPARTY: if (!test_bit(ATM_VF_SESSION, &vcc->flags)) return -EINVAL; if (copy_from_user(&ep_ref, (void __user *) arg, sizeof(int))) return -EFAULT; error = svc_dropparty(sock, ep_ref); break; default: error = vcc_ioctl(sock, cmd, arg); } return error; } #ifdef CONFIG_COMPAT static int svc_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { /* The definition of ATM_ADDPARTY uses the size of struct atm_iobuf. But actually it takes a struct sockaddr_atmsvc, which doesn't need compat handling. So all we have to do is fix up cmd... */ if (cmd == COMPAT_ATM_ADDPARTY) cmd = ATM_ADDPARTY; if (cmd == ATM_ADDPARTY || cmd == ATM_DROPPARTY) return svc_ioctl(sock, cmd, arg); else return vcc_compat_ioctl(sock, cmd, arg); } #endif /* CONFIG_COMPAT */ static const struct proto_ops svc_proto_ops = { .family = PF_ATMSVC, .owner = THIS_MODULE, .release = svc_release, .bind = svc_bind, .connect = svc_connect, .socketpair = sock_no_socketpair, .accept = svc_accept, .getname = svc_getname, .poll = vcc_poll, .ioctl = svc_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = svc_compat_ioctl, #endif .gettstamp = sock_gettstamp, .listen = svc_listen, .shutdown = svc_shutdown, .setsockopt = svc_setsockopt, .getsockopt = svc_getsockopt, .sendmsg = vcc_sendmsg, .recvmsg = vcc_recvmsg, .mmap = sock_no_mmap, }; static int svc_create(struct net *net, struct socket *sock, int protocol, int kern) { int error; if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; sock->ops = &svc_proto_ops; error = vcc_create(net, sock, protocol, AF_ATMSVC, kern); if (error) return error; ATM_SD(sock)->local.sas_family = AF_ATMSVC; ATM_SD(sock)->remote.sas_family = AF_ATMSVC; return 0; } static const struct net_proto_family svc_family_ops = { .family = PF_ATMSVC, .create = svc_create, .owner = THIS_MODULE, }; /* * Initialize the ATM SVC protocol family */ int __init atmsvc_init(void) { return sock_register(&svc_family_ops); } void atmsvc_exit(void) { sock_unregister(PF_ATMSVC); } |
| 11521 1070 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(unsigned long call_site, bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Module kallsyms support * * Copyright (C) 2010 Rusty Russell */ #include <linux/module.h> #include <linux/module_symbol.h> #include <linux/kallsyms.h> #include <linux/buildid.h> #include <linux/bsearch.h> #include "internal.h" /* Lookup exported symbol in given range of kernel_symbols */ static const struct kernel_symbol *lookup_exported_symbol(const char *name, const struct kernel_symbol *start, const struct kernel_symbol *stop) { return bsearch(name, start, stop - start, sizeof(struct kernel_symbol), cmp_name); } static int is_exported(const char *name, unsigned long value, const struct module *mod) { const struct kernel_symbol *ks; if (!mod) ks = lookup_exported_symbol(name, __start___ksymtab, __stop___ksymtab); else ks = lookup_exported_symbol(name, mod->syms, mod->syms + mod->num_syms); return ks && kernel_symbol_value(ks) == value; } /* As per nm */ static char elf_type(const Elf_Sym *sym, const struct load_info *info) { const Elf_Shdr *sechdrs = info->sechdrs; if (ELF_ST_BIND(sym->st_info) == STB_WEAK) { if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT) return 'v'; else return 'w'; } if (sym->st_shndx == SHN_UNDEF) return 'U'; if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu) return 'a'; if (sym->st_shndx >= SHN_LORESERVE) return '?'; if (sechdrs[sym->st_shndx].sh_flags & SHF_EXECINSTR) return 't'; if (sechdrs[sym->st_shndx].sh_flags & SHF_ALLOC && sechdrs[sym->st_shndx].sh_type != SHT_NOBITS) { if (!(sechdrs[sym->st_shndx].sh_flags & SHF_WRITE)) return 'r'; else if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) return 'g'; else return 'd'; } if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) { if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) return 's'; else return 'b'; } if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name, ".debug")) { return 'n'; } return '?'; } static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, unsigned int shnum, unsigned int pcpundx) { const Elf_Shdr *sec; enum mod_mem_type type; if (src->st_shndx == SHN_UNDEF || src->st_shndx >= shnum || !src->st_name) return false; #ifdef CONFIG_KALLSYMS_ALL if (src->st_shndx == pcpundx) return true; #endif sec = sechdrs + src->st_shndx; type = sec->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT; if (!(sec->sh_flags & SHF_ALLOC) #ifndef CONFIG_KALLSYMS_ALL || !(sec->sh_flags & SHF_EXECINSTR) #endif || mod_mem_type_is_init(type)) return false; return true; } /* * We only allocate and copy the strings needed by the parts of symtab * we keep. This is simple, but has the effect of making multiple * copies of duplicates. We could be more sophisticated, see * linux-kernel thread starting with * <73defb5e4bca04a6431392cc341112b1@localhost>. */ void layout_symtab(struct module *mod, struct load_info *info) { Elf_Shdr *symsect = info->sechdrs + info->index.sym; Elf_Shdr *strsect = info->sechdrs + info->index.str; const Elf_Sym *src; unsigned int i, nsrc, ndst, strtab_size = 0; struct module_memory *mod_mem_data = &mod->mem[MOD_DATA]; struct module_memory *mod_mem_init_data = &mod->mem[MOD_INIT_DATA]; /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; symsect->sh_entsize = module_get_offset_and_type(mod, MOD_INIT_DATA, symsect, info->index.sym); pr_debug("\t%s\n", info->secstrings + symsect->sh_name); src = (void *)info->hdr + symsect->sh_offset; nsrc = symsect->sh_size / sizeof(*src); /* Compute total space required for the core symbols' strtab. */ for (ndst = i = 0; i < nsrc; i++) { if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { strtab_size += strlen(&info->strtab[src[i].st_name]) + 1; ndst++; } } /* Append room for core symbols at end of core part. */ info->symoffs = ALIGN(mod_mem_data->size, symsect->sh_addralign ?: 1); info->stroffs = mod_mem_data->size = info->symoffs + ndst * sizeof(Elf_Sym); mod_mem_data->size += strtab_size; /* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */ info->core_typeoffs = mod_mem_data->size; mod_mem_data->size += ndst * sizeof(char); /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; strsect->sh_entsize = module_get_offset_and_type(mod, MOD_INIT_DATA, strsect, info->index.str); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); /* We'll tack temporary mod_kallsyms on the end. */ mod_mem_init_data->size = ALIGN(mod_mem_init_data->size, __alignof__(struct mod_kallsyms)); info->mod_kallsyms_init_off = mod_mem_init_data->size; mod_mem_init_data->size += sizeof(struct mod_kallsyms); info->init_typeoffs = mod_mem_init_data->size; mod_mem_init_data->size += nsrc * sizeof(char); } /* * We use the full symtab and strtab which layout_symtab arranged to * be appended to the init section. Later we switch to the cut-down * core-only ones. */ void add_kallsyms(struct module *mod, const struct load_info *info) { unsigned int i, ndst; const Elf_Sym *src; Elf_Sym *dst; char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; unsigned long strtab_size; void *data_base = mod->mem[MOD_DATA].base; void *init_data_base = mod->mem[MOD_INIT_DATA].base; /* Set up to point into init section. */ mod->kallsyms = (void __rcu *)init_data_base + info->mod_kallsyms_init_off; rcu_read_lock(); /* The following is safe since this pointer cannot change */ rcu_dereference(mod->kallsyms)->symtab = (void *)symsec->sh_addr; rcu_dereference(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ rcu_dereference(mod->kallsyms)->strtab = (void *)info->sechdrs[info->index.str].sh_addr; rcu_dereference(mod->kallsyms)->typetab = init_data_base + info->init_typeoffs; /* * Now populate the cut down core kallsyms for after init * and set types up while we still have access to sections. */ mod->core_kallsyms.symtab = dst = data_base + info->symoffs; mod->core_kallsyms.strtab = s = data_base + info->stroffs; mod->core_kallsyms.typetab = data_base + info->core_typeoffs; strtab_size = info->core_typeoffs - info->stroffs; src = rcu_dereference(mod->kallsyms)->symtab; for (ndst = i = 0; i < rcu_dereference(mod->kallsyms)->num_symtab; i++) { rcu_dereference(mod->kallsyms)->typetab[i] = elf_type(src + i, info); if (i == 0 || is_livepatch_module(mod) || is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { ssize_t ret; mod->core_kallsyms.typetab[ndst] = rcu_dereference(mod->kallsyms)->typetab[i]; dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_kallsyms.strtab; ret = strscpy(s, &rcu_dereference(mod->kallsyms)->strtab[src[i].st_name], strtab_size); if (ret < 0) break; s += ret + 1; strtab_size -= ret + 1; } } rcu_read_unlock(); mod->core_kallsyms.num_symtab = ndst; } #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) void init_build_id(struct module *mod, const struct load_info *info) { const Elf_Shdr *sechdr; unsigned int i; for (i = 0; i < info->hdr->e_shnum; i++) { sechdr = &info->sechdrs[i]; if (!sect_empty(sechdr) && sechdr->sh_type == SHT_NOTE && !build_id_parse_buf((void *)sechdr->sh_addr, mod->build_id, sechdr->sh_size)) break; } } #else void init_build_id(struct module *mod, const struct load_info *info) { } #endif static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum) { return kallsyms->strtab + kallsyms->symtab[symnum].st_name; } /* * Given a module and address, find the corresponding symbol and return its name * while providing its size and offset if needed. */ static const char *find_kallsyms_symbol(struct module *mod, unsigned long addr, unsigned long *size, unsigned long *offset) { unsigned int i, best = 0; unsigned long nextval, bestval; struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); struct module_memory *mod_mem; /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) mod_mem = &mod->mem[MOD_INIT_TEXT]; else mod_mem = &mod->mem[MOD_TEXT]; nextval = (unsigned long)mod_mem->base + mod_mem->size; bestval = kallsyms_symbol_value(&kallsyms->symtab[best]); /* * Scan for closest preceding symbol, and next symbol. (ELF * starts real symbols at 1). */ for (i = 1; i < kallsyms->num_symtab; i++) { const Elf_Sym *sym = &kallsyms->symtab[i]; unsigned long thisval = kallsyms_symbol_value(sym); if (sym->st_shndx == SHN_UNDEF) continue; /* * We ignore unnamed symbols: they're uninformative * and inserted at a whim. */ if (*kallsyms_symbol_name(kallsyms, i) == '\0' || is_mapping_symbol(kallsyms_symbol_name(kallsyms, i))) continue; if (thisval <= addr && thisval > bestval) { best = i; bestval = thisval; } if (thisval > addr && thisval < nextval) nextval = thisval; } if (!best) return NULL; if (size) *size = nextval - bestval; if (offset) *offset = addr - bestval; return kallsyms_symbol_name(kallsyms, best); } void * __weak dereference_module_function_descriptor(struct module *mod, void *ptr) { return ptr; } /* * For kallsyms to ask for address resolution. NULL means not found. Careful * not to lock to avoid deadlock on oopses, simply disable preemption. */ const char *module_address_lookup(unsigned long addr, unsigned long *size, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { const char *ret = NULL; struct module *mod; preempt_disable(); mod = __module_address(addr); if (mod) { if (modname) *modname = mod->name; if (modbuildid) { #if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) *modbuildid = mod->build_id; #else *modbuildid = NULL; #endif } ret = find_kallsyms_symbol(mod, addr, size, offset); } /* Make a copy in here where it's safe */ if (ret) { strncpy(namebuf, ret, KSYM_NAME_LEN - 1); ret = namebuf; } preempt_enable(); return ret; } int lookup_module_symbol_name(unsigned long addr, char *symname) { struct module *mod; preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; if (within_module(addr, mod)) { const char *sym; sym = find_kallsyms_symbol(mod, addr, NULL, NULL); if (!sym) goto out; strscpy(symname, sym, KSYM_NAME_LEN); preempt_enable(); return 0; } } out: preempt_enable(); return -ERANGE; } int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) { struct module *mod; preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { struct mod_kallsyms *kallsyms; if (mod->state == MODULE_STATE_UNFORMED) continue; kallsyms = rcu_dereference_sched(mod->kallsyms); if (symnum < kallsyms->num_symtab) { const Elf_Sym *sym = &kallsyms->symtab[symnum]; *value = kallsyms_symbol_value(sym); *type = kallsyms->typetab[symnum]; strscpy(name, kallsyms_symbol_name(kallsyms, symnum), KSYM_NAME_LEN); strscpy(module_name, mod->name, MODULE_NAME_LEN); *exported = is_exported(name, *value, mod); preempt_enable(); return 0; } symnum -= kallsyms->num_symtab; } preempt_enable(); return -ERANGE; } /* Given a module and name of symbol, find and return the symbol's value */ static unsigned long __find_kallsyms_symbol_value(struct module *mod, const char *name) { unsigned int i; struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); for (i = 0; i < kallsyms->num_symtab; i++) { const Elf_Sym *sym = &kallsyms->symtab[i]; if (strcmp(name, kallsyms_symbol_name(kallsyms, i)) == 0 && sym->st_shndx != SHN_UNDEF) return kallsyms_symbol_value(sym); } return 0; } static unsigned long __module_kallsyms_lookup_name(const char *name) { struct module *mod; char *colon; colon = strnchr(name, MODULE_NAME_LEN, ':'); if (colon) { mod = find_module_all(name, colon - name, false); if (mod) return __find_kallsyms_symbol_value(mod, colon + 1); return 0; } list_for_each_entry_rcu(mod, &modules, list) { unsigned long ret; if (mod->state == MODULE_STATE_UNFORMED) continue; ret = __find_kallsyms_symbol_value(mod, name); if (ret) return ret; } return 0; } /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name) { unsigned long ret; /* Don't lock: we're in enough trouble already. */ preempt_disable(); ret = __module_kallsyms_lookup_name(name); preempt_enable(); return ret; } unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name) { unsigned long ret; preempt_disable(); ret = __find_kallsyms_symbol_value(mod, name); preempt_enable(); return ret; } int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, unsigned long), void *data) { struct module *mod; unsigned int i; int ret = 0; mutex_lock(&module_mutex); list_for_each_entry(mod, &modules, list) { struct mod_kallsyms *kallsyms; if (mod->state == MODULE_STATE_UNFORMED) continue; if (modname && strcmp(modname, mod->name)) continue; /* Use rcu_dereference_sched() to remain compliant with the sparse tool */ preempt_disable(); kallsyms = rcu_dereference_sched(mod->kallsyms); preempt_enable(); for (i = 0; i < kallsyms->num_symtab; i++) { const Elf_Sym *sym = &kallsyms->symtab[i]; if (sym->st_shndx == SHN_UNDEF) continue; ret = fn(data, kallsyms_symbol_name(kallsyms, i), kallsyms_symbol_value(sym)); if (ret != 0) goto out; } /* * The given module is found, the subsequent modules do not * need to be compared. */ if (modname) break; } out: mutex_unlock(&module_mutex); return ret; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Header for use in defining a given L4 protocol for connection tracking. * * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp> * - generalized L3 protocol dependent part. * * Derived from include/linux/netfiter_ipv4/ip_conntrack_protcol.h */ #ifndef _NF_CONNTRACK_L4PROTO_H #define _NF_CONNTRACK_L4PROTO_H #include <linux/netlink.h> #include <net/netlink.h> #include <net/netfilter/nf_conntrack.h> #include <net/netns/generic.h> struct seq_file; struct nf_conntrack_l4proto { /* L4 Protocol number. */ u_int8_t l4proto; /* Resolve clashes on insertion races. */ bool allow_clash; /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; /* called by gc worker if table is full */ bool (*can_early_drop)(const struct nf_conn *ct); /* convert protoinfo to nfnetink attributes */ int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct, bool destroy); /* convert nfnetlink attributes to protoinfo */ int (*from_nlattr)(struct nlattr *tb[], struct nf_conn *ct); int (*tuple_to_nlattr)(struct sk_buff *skb, const struct nf_conntrack_tuple *t); /* Calculate tuple nlattr size */ unsigned int (*nlattr_tuple_size)(void); int (*nlattr_to_tuple)(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags); const struct nla_policy *nla_policy; struct { int (*nlattr_to_obj)(struct nlattr *tb[], struct net *net, void *data); int (*obj_to_nlattr)(struct sk_buff *skb, const void *data); u16 obj_size; u16 nlattr_max; const struct nla_policy *nla_policy; } ctnl_timeout; #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ void (*print_conntrack)(struct seq_file *s, struct nf_conn *); #endif }; bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple); bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple); bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig); int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state, u8 l4proto, union nf_inet_addr *outer_daddr); int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state); int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state); int nf_conntrack_icmp_packet(struct nf_conn *ct, struct sk_buff *skb, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); int nf_conntrack_icmpv6_packet(struct nf_conn *ct, struct sk_buff *skb, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); int nf_conntrack_udplite_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); int nf_conntrack_tcp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); int nf_conntrack_sctp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); int nf_conntrack_gre_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); void nf_conntrack_generic_init_net(struct net *net); void nf_conntrack_tcp_init_net(struct net *net); void nf_conntrack_udp_init_net(struct net *net); void nf_conntrack_gre_init_net(struct net *net); void nf_conntrack_dccp_init_net(struct net *net); void nf_conntrack_sctp_init_net(struct net *net); void nf_conntrack_icmp_init_net(struct net *net); void nf_conntrack_icmpv6_init_net(struct net *net); /* Existing built-in generic protocol */ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; #define MAX_NF_CT_PROTO IPPROTO_UDPLITE const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto); /* Generic netlink helpers */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple); int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t, u_int32_t flags); unsigned int nf_ct_port_nlattr_tuple_size(void); extern const struct nla_policy nf_ct_port_nla_policy[]; #ifdef CONFIG_SYSCTL __printf(4, 5) __cold void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, const struct nf_hook_state *state, const char *fmt, ...); __printf(4, 5) __cold void nf_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_hook_state *state, u8 protonum, const char *fmt, ...); #else static inline __printf(4, 5) __cold void nf_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_hook_state *state, u8 protonum, const char *fmt, ...) {} static inline __printf(4, 5) __cold void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, const struct nf_hook_state *state, const char *fmt, ...) { } #endif /* CONFIG_SYSCTL */ #if IS_ENABLED(CONFIG_NF_CONNTRACK) static inline struct nf_generic_net *nf_generic_pernet(struct net *net) { return &net->ct.nf_ct_proto.generic; } static inline struct nf_tcp_net *nf_tcp_pernet(struct net *net) { return &net->ct.nf_ct_proto.tcp; } static inline struct nf_udp_net *nf_udp_pernet(struct net *net) { return &net->ct.nf_ct_proto.udp; } static inline struct nf_icmp_net *nf_icmp_pernet(struct net *net) { return &net->ct.nf_ct_proto.icmp; } static inline struct nf_icmp_net *nf_icmpv6_pernet(struct net *net) { return &net->ct.nf_ct_proto.icmpv6; } /* Caller must check nf_ct_protonum(ct) is IPPROTO_TCP before calling. */ static inline void nf_ct_set_tcp_be_liberal(struct nf_conn *ct) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } /* Caller must check nf_ct_protonum(ct) is IPPROTO_TCP before calling. */ static inline bool nf_conntrack_tcp_established(const struct nf_conn *ct) { return ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED && test_bit(IPS_ASSURED_BIT, &ct->status); } #endif #ifdef CONFIG_NF_CT_PROTO_DCCP static inline struct nf_dccp_net *nf_dccp_pernet(struct net *net) { return &net->ct.nf_ct_proto.dccp; } #endif #ifdef CONFIG_NF_CT_PROTO_SCTP static inline struct nf_sctp_net *nf_sctp_pernet(struct net *net) { return &net->ct.nf_ct_proto.sctp; } #endif #ifdef CONFIG_NF_CT_PROTO_GRE static inline struct nf_gre_net *nf_gre_pernet(struct net *net) { return &net->ct.nf_ct_proto.gre; } #endif #endif /*_NF_CONNTRACK_PROTOCOL_H*/ |
| 1965 1963 369 1965 1965 1964 1965 1964 1738 1739 1739 402 1705 1705 1683 477 1705 1705 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 | /* * Ext4 orphan inode handling */ #include <linux/fs.h> #include <linux/quotaops.h> #include <linux/buffer_head.h> #include "ext4.h" #include "ext4_jbd2.h" static int ext4_orphan_file_add(handle_t *handle, struct inode *inode) { int i, j, start; struct ext4_orphan_info *oi = &EXT4_SB(inode->i_sb)->s_orphan_info; int ret = 0; bool found = false; __le32 *bdata; int inodes_per_ob = ext4_inodes_per_orphan_block(inode->i_sb); int looped = 0; /* * Find block with free orphan entry. Use CPU number for a naive hash * for a search start in the orphan file */ start = raw_smp_processor_id()*13 % oi->of_blocks; i = start; do { if (atomic_dec_if_positive(&oi->of_binfo[i].ob_free_entries) >= 0) { found = true; break; } if (++i >= oi->of_blocks) i = 0; } while (i != start); if (!found) { /* * For now we don't grow or shrink orphan file. We just use * whatever was allocated at mke2fs time. The additional * credits we would have to reserve for each orphan inode * operation just don't seem worth it. */ return -ENOSPC; } ret = ext4_journal_get_write_access(handle, inode->i_sb, oi->of_binfo[i].ob_bh, EXT4_JTR_ORPHAN_FILE); if (ret) { atomic_inc(&oi->of_binfo[i].ob_free_entries); return ret; } bdata = (__le32 *)(oi->of_binfo[i].ob_bh->b_data); /* Find empty slot in a block */ j = 0; do { if (looped) { /* * Did we walk through the block several times without * finding free entry? It is theoretically possible * if entries get constantly allocated and freed or * if the block is corrupted. Avoid indefinite looping * and bail. We'll use orphan list instead. */ if (looped > 3) { atomic_inc(&oi->of_binfo[i].ob_free_entries); return -ENOSPC; } cond_resched(); } while (bdata[j]) { if (++j >= inodes_per_ob) { j = 0; looped++; } } } while (cmpxchg(&bdata[j], (__le32)0, cpu_to_le32(inode->i_ino)) != (__le32)0); EXT4_I(inode)->i_orphan_idx = i * inodes_per_ob + j; ext4_set_inode_state(inode, EXT4_STATE_ORPHAN_FILE); return ext4_handle_dirty_metadata(handle, NULL, oi->of_binfo[i].ob_bh); } /* * ext4_orphan_add() links an unlinked or truncated inode into a list of * such inodes, starting at the superblock, in case we crash before the * file is closed/deleted, or in case the inode truncate spans multiple * transactions and the last transaction is not recovered after a crash. * * At filesystem recovery time, we walk this list deleting unlinked * inodes and truncating linked inodes in ext4_orphan_cleanup(). * * Orphan list manipulation functions must be called under i_rwsem unless * we are just creating the inode or deleting it. */ int ext4_orphan_add(handle_t *handle, struct inode *inode) { struct super_block *sb = inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_iloc iloc; int err = 0, rc; bool dirty = false; if (!sbi->s_journal || is_bad_inode(inode)) return 0; WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) && !inode_is_locked(inode)); /* * Inode orphaned in orphan file or in orphan list? */ if (ext4_test_inode_state(inode, EXT4_STATE_ORPHAN_FILE) || !list_empty(&EXT4_I(inode)->i_orphan)) return 0; /* * Orphan handling is only valid for files with data blocks * being truncated, or files being unlinked. Note that we either * hold i_rwsem, or the inode can not be referenced from outside, * so i_nlink should not be bumped due to race */ ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) || inode->i_nlink == 0); if (sbi->s_orphan_info.of_blocks) { err = ext4_orphan_file_add(handle, inode); /* * Fallback to normal orphan list of orphan file is * out of space */ if (err != -ENOSPC) return err; } BUFFER_TRACE(sbi->s_sbh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, sbi->s_sbh, EXT4_JTR_NONE); if (err) goto out; err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto out; mutex_lock(&sbi->s_orphan_lock); /* * Due to previous errors inode may be already a part of on-disk * orphan list. If so skip on-disk list modification. */ if (!NEXT_ORPHAN(inode) || NEXT_ORPHAN(inode) > (le32_to_cpu(sbi->s_es->s_inodes_count))) { /* Insert this inode at the head of the on-disk orphan list */ NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan); lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); ext4_superblock_csum_set(sb); unlock_buffer(sbi->s_sbh); dirty = true; } list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan); mutex_unlock(&sbi->s_orphan_lock); if (dirty) { err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; if (err) { /* * We have to remove inode from in-memory list if * addition to on disk orphan list failed. Stray orphan * list entries can cause panics at unmount time. */ mutex_lock(&sbi->s_orphan_lock); list_del_init(&EXT4_I(inode)->i_orphan); mutex_unlock(&sbi->s_orphan_lock); } } else brelse(iloc.bh); ext4_debug("superblock will point to %lu\n", inode->i_ino); ext4_debug("orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); out: ext4_std_error(sb, err); return err; } static int ext4_orphan_file_del(handle_t *handle, struct inode *inode) { struct ext4_orphan_info *oi = &EXT4_SB(inode->i_sb)->s_orphan_info; __le32 *bdata; int blk, off; int inodes_per_ob = ext4_inodes_per_orphan_block(inode->i_sb); int ret = 0; if (!handle) goto out; blk = EXT4_I(inode)->i_orphan_idx / inodes_per_ob; off = EXT4_I(inode)->i_orphan_idx % inodes_per_ob; if (WARN_ON_ONCE(blk >= oi->of_blocks)) goto out; ret = ext4_journal_get_write_access(handle, inode->i_sb, oi->of_binfo[blk].ob_bh, EXT4_JTR_ORPHAN_FILE); if (ret) goto out; bdata = (__le32 *)(oi->of_binfo[blk].ob_bh->b_data); bdata[off] = 0; atomic_inc(&oi->of_binfo[blk].ob_free_entries); ret = ext4_handle_dirty_metadata(handle, NULL, oi->of_binfo[blk].ob_bh); out: ext4_clear_inode_state(inode, EXT4_STATE_ORPHAN_FILE); INIT_LIST_HEAD(&EXT4_I(inode)->i_orphan); return ret; } /* * ext4_orphan_del() removes an unlinked or truncated inode from the list * of such inodes stored on disk, because it is finally being cleaned up. */ int ext4_orphan_del(handle_t *handle, struct inode *inode) { struct list_head *prev; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 ino_next; struct ext4_iloc iloc; int err = 0; if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS)) return 0; WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) && !inode_is_locked(inode)); if (ext4_test_inode_state(inode, EXT4_STATE_ORPHAN_FILE)) return ext4_orphan_file_del(handle, inode); /* Do this quick check before taking global s_orphan_lock. */ if (list_empty(&ei->i_orphan)) return 0; if (handle) { /* Grab inode buffer early before taking global s_orphan_lock */ err = ext4_reserve_inode_write(handle, inode, &iloc); } mutex_lock(&sbi->s_orphan_lock); ext4_debug("remove inode %lu from orphan list\n", inode->i_ino); prev = ei->i_orphan.prev; list_del_init(&ei->i_orphan); /* If we're on an error path, we may not have a valid * transaction handle with which to update the orphan list on * disk, but we still need to remove the inode from the linked * list in memory. */ if (!handle || err) { mutex_unlock(&sbi->s_orphan_lock); goto out_err; } ino_next = NEXT_ORPHAN(inode); if (prev == &sbi->s_orphan) { ext4_debug("superblock will point to %u\n", ino_next); BUFFER_TRACE(sbi->s_sbh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, sbi->s_sbh, EXT4_JTR_NONE); if (err) { mutex_unlock(&sbi->s_orphan_lock); goto out_brelse; } lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); ext4_superblock_csum_set(inode->i_sb); unlock_buffer(sbi->s_sbh); mutex_unlock(&sbi->s_orphan_lock); err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); } else { struct ext4_iloc iloc2; struct inode *i_prev = &list_entry(prev, struct ext4_inode_info, i_orphan)->vfs_inode; ext4_debug("orphan inode %lu will point to %u\n", i_prev->i_ino, ino_next); err = ext4_reserve_inode_write(handle, i_prev, &iloc2); if (err) { mutex_unlock(&sbi->s_orphan_lock); goto out_brelse; } NEXT_ORPHAN(i_prev) = ino_next; err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2); mutex_unlock(&sbi->s_orphan_lock); } if (err) goto out_brelse; NEXT_ORPHAN(inode) = 0; err = ext4_mark_iloc_dirty(handle, inode, &iloc); out_err: ext4_std_error(inode->i_sb, err); return err; out_brelse: brelse(iloc.bh); goto out_err; } #ifdef CONFIG_QUOTA static int ext4_quota_on_mount(struct super_block *sb, int type) { return dquot_quota_on_mount(sb, rcu_dereference_protected(EXT4_SB(sb)->s_qf_names[type], lockdep_is_held(&sb->s_umount)), EXT4_SB(sb)->s_jquota_fmt, type); } #endif static void ext4_process_orphan(struct inode *inode, int *nr_truncates, int *nr_orphans) { struct super_block *sb = inode->i_sb; int ret; dquot_initialize(inode); if (inode->i_nlink) { if (test_opt(sb, DEBUG)) ext4_msg(sb, KERN_DEBUG, "%s: truncating inode %lu to %lld bytes", __func__, inode->i_ino, inode->i_size); ext4_debug("truncating inode %lu to %lld bytes\n", inode->i_ino, inode->i_size); inode_lock(inode); truncate_inode_pages(inode->i_mapping, inode->i_size); ret = ext4_truncate(inode); if (ret) { /* * We need to clean up the in-core orphan list * manually if ext4_truncate() failed to get a * transaction handle. */ ext4_orphan_del(NULL, inode); ext4_std_error(inode->i_sb, ret); } inode_unlock(inode); (*nr_truncates)++; } else { if (test_opt(sb, DEBUG)) ext4_msg(sb, KERN_DEBUG, "%s: deleting unreferenced inode %lu", __func__, inode->i_ino); ext4_debug("deleting unreferenced inode %lu\n", inode->i_ino); (*nr_orphans)++; } iput(inode); /* The delete magic happens here! */ } /* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at * the superblock) which were deleted from all directories, but held open by * a process at the time of a crash. We walk the list and try to delete these * inodes at recovery time (only with a read-write filesystem). * * In order to keep the orphan inode chain consistent during traversal (in * case of crash during recovery), we link each inode into the superblock * orphan list_head and handle it the same way as an inode deletion during * normal operation (which journals the operations for us). * * We only do an iget() and an iput() on each inode, which is very safe if we * accidentally point at an in-use or already deleted inode. The worst that * can happen in this case is that we get a "bit already cleared" message from * ext4_free_inode(). The only reason we would point at a wrong inode is if * e2fsck was run on this filesystem, and it must have already done the orphan * inode cleanup for us, so we can safely abort without any further action. */ void ext4_orphan_cleanup(struct super_block *sb, struct ext4_super_block *es) { unsigned int s_flags = sb->s_flags; int nr_orphans = 0, nr_truncates = 0; struct inode *inode; int i, j; #ifdef CONFIG_QUOTA int quota_update = 0; #endif __le32 *bdata; struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info; int inodes_per_ob = ext4_inodes_per_orphan_block(sb); if (!es->s_last_orphan && !oi->of_blocks) { ext4_debug("no orphan inodes to clean up\n"); return; } if (bdev_read_only(sb->s_bdev)) { ext4_msg(sb, KERN_ERR, "write access " "unavailable, skipping orphan cleanup"); return; } /* Check if feature set would not allow a r/w mount */ if (!ext4_feature_set_ok(sb, 0)) { ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to " "unknown ROCOMPAT features"); return; } if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { /* don't clear list on RO mount w/ errors */ if (es->s_last_orphan && !(s_flags & SB_RDONLY)) { ext4_msg(sb, KERN_INFO, "Errors on filesystem, " "clearing orphan list."); es->s_last_orphan = 0; } ext4_debug("Skipping orphan recovery on fs with errors.\n"); return; } if (s_flags & SB_RDONLY) { ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs"); sb->s_flags &= ~SB_RDONLY; } #ifdef CONFIG_QUOTA /* * Turn on quotas which were not enabled for read-only mounts if * filesystem has quota feature, so that they are updated correctly. */ if (ext4_has_feature_quota(sb) && (s_flags & SB_RDONLY)) { int ret = ext4_enable_quotas(sb); if (!ret) quota_update = 1; else ext4_msg(sb, KERN_ERR, "Cannot turn on quotas: error %d", ret); } /* Turn on journaled quotas used for old sytle */ for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (EXT4_SB(sb)->s_qf_names[i]) { int ret = ext4_quota_on_mount(sb, i); if (!ret) quota_update = 1; else ext4_msg(sb, KERN_ERR, "Cannot turn on journaled " "quota: type %d: error %d", i, ret); } } #endif while (es->s_last_orphan) { /* * We may have encountered an error during cleanup; if * so, skip the rest. */ if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { ext4_debug("Skipping orphan recovery on fs with errors.\n"); es->s_last_orphan = 0; break; } inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)); if (IS_ERR(inode)) { es->s_last_orphan = 0; break; } list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan); ext4_process_orphan(inode, &nr_truncates, &nr_orphans); } for (i = 0; i < oi->of_blocks; i++) { bdata = (__le32 *)(oi->of_binfo[i].ob_bh->b_data); for (j = 0; j < inodes_per_ob; j++) { if (!bdata[j]) continue; inode = ext4_orphan_get(sb, le32_to_cpu(bdata[j])); if (IS_ERR(inode)) continue; ext4_set_inode_state(inode, EXT4_STATE_ORPHAN_FILE); EXT4_I(inode)->i_orphan_idx = i * inodes_per_ob + j; ext4_process_orphan(inode, &nr_truncates, &nr_orphans); } } #define PLURAL(x) (x), ((x) == 1) ? "" : "s" if (nr_orphans) ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted", PLURAL(nr_orphans)); if (nr_truncates) ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up", PLURAL(nr_truncates)); #ifdef CONFIG_QUOTA /* Turn off quotas if they were enabled for orphan cleanup */ if (quota_update) { for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (sb_dqopt(sb)->files[i]) dquot_quota_off(sb, i); } } #endif sb->s_flags = s_flags; /* Restore SB_RDONLY status */ } void ext4_release_orphan_info(struct super_block *sb) { int i; struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info; if (!oi->of_blocks) return; for (i = 0; i < oi->of_blocks; i++) brelse(oi->of_binfo[i].ob_bh); kfree(oi->of_binfo); } static struct ext4_orphan_block_tail *ext4_orphan_block_tail( struct super_block *sb, struct buffer_head *bh) { return (struct ext4_orphan_block_tail *)(bh->b_data + sb->s_blocksize - sizeof(struct ext4_orphan_block_tail)); } static int ext4_orphan_file_block_csum_verify(struct super_block *sb, struct buffer_head *bh) { __u32 calculated; int inodes_per_ob = ext4_inodes_per_orphan_block(sb); struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info; struct ext4_orphan_block_tail *ot; __le64 dsk_block_nr = cpu_to_le64(bh->b_blocknr); if (!ext4_has_metadata_csum(sb)) return 1; ot = ext4_orphan_block_tail(sb, bh); calculated = ext4_chksum(EXT4_SB(sb), oi->of_csum_seed, (__u8 *)&dsk_block_nr, sizeof(dsk_block_nr)); calculated = ext4_chksum(EXT4_SB(sb), calculated, (__u8 *)bh->b_data, inodes_per_ob * sizeof(__u32)); return le32_to_cpu(ot->ob_checksum) == calculated; } /* This gets called only when checksumming is enabled */ void ext4_orphan_file_block_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh, void *data, size_t size) { struct super_block *sb = EXT4_TRIGGER(triggers)->sb; __u32 csum; int inodes_per_ob = ext4_inodes_per_orphan_block(sb); struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info; struct ext4_orphan_block_tail *ot; __le64 dsk_block_nr = cpu_to_le64(bh->b_blocknr); csum = ext4_chksum(EXT4_SB(sb), oi->of_csum_seed, (__u8 *)&dsk_block_nr, sizeof(dsk_block_nr)); csum = ext4_chksum(EXT4_SB(sb), csum, (__u8 *)data, inodes_per_ob * sizeof(__u32)); ot = ext4_orphan_block_tail(sb, bh); ot->ob_checksum = cpu_to_le32(csum); } int ext4_init_orphan_info(struct super_block *sb) { struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info; struct inode *inode; int i, j; int ret; int free; __le32 *bdata; int inodes_per_ob = ext4_inodes_per_orphan_block(sb); struct ext4_orphan_block_tail *ot; ino_t orphan_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_orphan_file_inum); if (!ext4_has_feature_orphan_file(sb)) return 0; inode = ext4_iget(sb, orphan_ino, EXT4_IGET_SPECIAL); if (IS_ERR(inode)) { ext4_msg(sb, KERN_ERR, "get orphan inode failed"); return PTR_ERR(inode); } oi->of_blocks = inode->i_size >> sb->s_blocksize_bits; oi->of_csum_seed = EXT4_I(inode)->i_csum_seed; oi->of_binfo = kmalloc(oi->of_blocks*sizeof(struct ext4_orphan_block), GFP_KERNEL); if (!oi->of_binfo) { ret = -ENOMEM; goto out_put; } for (i = 0; i < oi->of_blocks; i++) { oi->of_binfo[i].ob_bh = ext4_bread(NULL, inode, i, 0); if (IS_ERR(oi->of_binfo[i].ob_bh)) { ret = PTR_ERR(oi->of_binfo[i].ob_bh); goto out_free; } if (!oi->of_binfo[i].ob_bh) { ret = -EIO; goto out_free; } ot = ext4_orphan_block_tail(sb, oi->of_binfo[i].ob_bh); if (le32_to_cpu(ot->ob_magic) != EXT4_ORPHAN_BLOCK_MAGIC) { ext4_error(sb, "orphan file block %d: bad magic", i); ret = -EIO; goto out_free; } if (!ext4_orphan_file_block_csum_verify(sb, oi->of_binfo[i].ob_bh)) { ext4_error(sb, "orphan file block %d: bad checksum", i); ret = -EIO; goto out_free; } bdata = (__le32 *)(oi->of_binfo[i].ob_bh->b_data); free = 0; for (j = 0; j < inodes_per_ob; j++) if (bdata[j] == 0) free++; atomic_set(&oi->of_binfo[i].ob_free_entries, free); } iput(inode); return 0; out_free: for (i--; i >= 0; i--) brelse(oi->of_binfo[i].ob_bh); kfree(oi->of_binfo); out_put: iput(inode); return ret; } int ext4_orphan_file_empty(struct super_block *sb) { struct ext4_orphan_info *oi = &EXT4_SB(sb)->s_orphan_info; int i; int inodes_per_ob = ext4_inodes_per_orphan_block(sb); if (!ext4_has_feature_orphan_file(sb)) return 1; for (i = 0; i < oi->of_blocks; i++) if (atomic_read(&oi->of_binfo[i].ob_free_entries) != inodes_per_ob) return 0; return 1; } |
| 2134 4 4 8 8 7 8 8 85 85 78 78 85 85 1 87 87 1 85 85 68 47 85 85 78 50 72 72 4 4 5 5 93 93 93 78 48 50 72 92 213 213 213 213 64 64 62 62 1 1 1 224 224 80 80 80 91 91 88 88 78 47 47 47 47 2 1 1 115 116 116 2 115 116 116 86 1 5 3 2 2 2 1 1 2 2 2 2 2 2 2134 2134 2130 2 2 8 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/net/team/team.c - Network team device driver * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com> */ #include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/errno.h> #include <linux/ctype.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netpoll.h> #include <linux/if_vlan.h> #include <linux/if_arp.h> #include <linux/socket.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/rtnetlink.h> #include <net/genetlink.h> #include <net/netlink.h> #include <net/sch_generic.h> #include <generated/utsrelease.h> #include <linux/if_team.h> #define DRV_NAME "team" /********** * Helpers **********/ static struct team_port *team_port_get_rtnl(const struct net_device *dev) { struct team_port *port = rtnl_dereference(dev->rx_handler_data); return netif_is_team_port(dev) ? port : NULL; } /* * Since the ability to change device address for open port device is tested in * team_port_add, this function can be called without control of return value */ static int __set_port_dev_addr(struct net_device *port_dev, const unsigned char *dev_addr) { struct sockaddr_storage addr; memcpy(addr.__data, dev_addr, port_dev->addr_len); addr.ss_family = port_dev->type; return dev_set_mac_address(port_dev, (struct sockaddr *)&addr, NULL); } static int team_port_set_orig_dev_addr(struct team_port *port) { return __set_port_dev_addr(port->dev, port->orig.dev_addr); } static int team_port_set_team_dev_addr(struct team *team, struct team_port *port) { return __set_port_dev_addr(port->dev, team->dev->dev_addr); } int team_modeop_port_enter(struct team *team, struct team_port *port) { return team_port_set_team_dev_addr(team, port); } EXPORT_SYMBOL(team_modeop_port_enter); void team_modeop_port_change_dev_addr(struct team *team, struct team_port *port) { team_port_set_team_dev_addr(team, port); } EXPORT_SYMBOL(team_modeop_port_change_dev_addr); static void team_lower_state_changed(struct team_port *port) { struct netdev_lag_lower_state_info info; info.link_up = port->linkup; info.tx_enabled = team_port_enabled(port); netdev_lower_state_changed(port->dev, &info); } static void team_refresh_port_linkup(struct team_port *port) { bool new_linkup = port->user.linkup_enabled ? port->user.linkup : port->state.linkup; if (port->linkup != new_linkup) { port->linkup = new_linkup; team_lower_state_changed(port); } } /******************* * Options handling *******************/ struct team_option_inst { /* One for each option instance */ struct list_head list; struct list_head tmp_list; struct team_option *option; struct team_option_inst_info info; bool changed; bool removed; }; static struct team_option *__team_find_option(struct team *team, const char *opt_name) { struct team_option *option; list_for_each_entry(option, &team->option_list, list) { if (strcmp(option->name, opt_name) == 0) return option; } return NULL; } static void __team_option_inst_del(struct team_option_inst *opt_inst) { list_del(&opt_inst->list); kfree(opt_inst); } static void __team_option_inst_del_option(struct team *team, struct team_option *option) { struct team_option_inst *opt_inst, *tmp; list_for_each_entry_safe(opt_inst, tmp, &team->option_inst_list, list) { if (opt_inst->option == option) __team_option_inst_del(opt_inst); } } static int __team_option_inst_add(struct team *team, struct team_option *option, struct team_port *port) { struct team_option_inst *opt_inst; unsigned int array_size; unsigned int i; array_size = option->array_size; if (!array_size) array_size = 1; /* No array but still need one instance */ for (i = 0; i < array_size; i++) { opt_inst = kmalloc(sizeof(*opt_inst), GFP_KERNEL); if (!opt_inst) return -ENOMEM; opt_inst->option = option; opt_inst->info.port = port; opt_inst->info.array_index = i; opt_inst->changed = true; opt_inst->removed = false; list_add_tail(&opt_inst->list, &team->option_inst_list); if (option->init) option->init(team, &opt_inst->info); } return 0; } static int __team_option_inst_add_option(struct team *team, struct team_option *option) { int err; if (!option->per_port) { err = __team_option_inst_add(team, option, NULL); if (err) goto inst_del_option; } return 0; inst_del_option: __team_option_inst_del_option(team, option); return err; } static void __team_option_inst_mark_removed_option(struct team *team, struct team_option *option) { struct team_option_inst *opt_inst; list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->option == option) { opt_inst->changed = true; opt_inst->removed = true; } } } static void __team_option_inst_del_port(struct team *team, struct team_port *port) { struct team_option_inst *opt_inst, *tmp; list_for_each_entry_safe(opt_inst, tmp, &team->option_inst_list, list) { if (opt_inst->option->per_port && opt_inst->info.port == port) __team_option_inst_del(opt_inst); } } static int __team_option_inst_add_port(struct team *team, struct team_port *port) { struct team_option *option; int err; list_for_each_entry(option, &team->option_list, list) { if (!option->per_port) continue; err = __team_option_inst_add(team, option, port); if (err) goto inst_del_port; } return 0; inst_del_port: __team_option_inst_del_port(team, port); return err; } static void __team_option_inst_mark_removed_port(struct team *team, struct team_port *port) { struct team_option_inst *opt_inst; list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->info.port == port) { opt_inst->changed = true; opt_inst->removed = true; } } } static int __team_options_register(struct team *team, const struct team_option *option, size_t option_count) { int i; struct team_option **dst_opts; int err; dst_opts = kcalloc(option_count, sizeof(struct team_option *), GFP_KERNEL); if (!dst_opts) return -ENOMEM; for (i = 0; i < option_count; i++, option++) { if (__team_find_option(team, option->name)) { err = -EEXIST; goto alloc_rollback; } dst_opts[i] = kmemdup(option, sizeof(*option), GFP_KERNEL); if (!dst_opts[i]) { err = -ENOMEM; goto alloc_rollback; } } for (i = 0; i < option_count; i++) { err = __team_option_inst_add_option(team, dst_opts[i]); if (err) goto inst_rollback; list_add_tail(&dst_opts[i]->list, &team->option_list); } kfree(dst_opts); return 0; inst_rollback: for (i--; i >= 0; i--) { __team_option_inst_del_option(team, dst_opts[i]); list_del(&dst_opts[i]->list); } i = option_count; alloc_rollback: for (i--; i >= 0; i--) kfree(dst_opts[i]); kfree(dst_opts); return err; } static void __team_options_mark_removed(struct team *team, const struct team_option *option, size_t option_count) { int i; for (i = 0; i < option_count; i++, option++) { struct team_option *del_opt; del_opt = __team_find_option(team, option->name); if (del_opt) __team_option_inst_mark_removed_option(team, del_opt); } } static void __team_options_unregister(struct team *team, const struct team_option *option, size_t option_count) { int i; for (i = 0; i < option_count; i++, option++) { struct team_option *del_opt; del_opt = __team_find_option(team, option->name); if (del_opt) { __team_option_inst_del_option(team, del_opt); list_del(&del_opt->list); kfree(del_opt); } } } static void __team_options_change_check(struct team *team); int team_options_register(struct team *team, const struct team_option *option, size_t option_count) { int err; err = __team_options_register(team, option, option_count); if (err) return err; __team_options_change_check(team); return 0; } EXPORT_SYMBOL(team_options_register); void team_options_unregister(struct team *team, const struct team_option *option, size_t option_count) { __team_options_mark_removed(team, option, option_count); __team_options_change_check(team); __team_options_unregister(team, option, option_count); } EXPORT_SYMBOL(team_options_unregister); static int team_option_get(struct team *team, struct team_option_inst *opt_inst, struct team_gsetter_ctx *ctx) { if (!opt_inst->option->getter) return -EOPNOTSUPP; opt_inst->option->getter(team, ctx); return 0; } static int team_option_set(struct team *team, struct team_option_inst *opt_inst, struct team_gsetter_ctx *ctx) { if (!opt_inst->option->setter) return -EOPNOTSUPP; return opt_inst->option->setter(team, ctx); } void team_option_inst_set_change(struct team_option_inst_info *opt_inst_info) { struct team_option_inst *opt_inst; opt_inst = container_of(opt_inst_info, struct team_option_inst, info); opt_inst->changed = true; } EXPORT_SYMBOL(team_option_inst_set_change); void team_options_change_check(struct team *team) { __team_options_change_check(team); } EXPORT_SYMBOL(team_options_change_check); /**************** * Mode handling ****************/ static LIST_HEAD(mode_list); static DEFINE_SPINLOCK(mode_list_lock); struct team_mode_item { struct list_head list; const struct team_mode *mode; }; static struct team_mode_item *__find_mode(const char *kind) { struct team_mode_item *mitem; list_for_each_entry(mitem, &mode_list, list) { if (strcmp(mitem->mode->kind, kind) == 0) return mitem; } return NULL; } static bool is_good_mode_name(const char *name) { while (*name != '\0') { if (!isalpha(*name) && !isdigit(*name) && *name != '_') return false; name++; } return true; } int team_mode_register(const struct team_mode *mode) { int err = 0; struct team_mode_item *mitem; if (!is_good_mode_name(mode->kind) || mode->priv_size > TEAM_MODE_PRIV_SIZE) return -EINVAL; mitem = kmalloc(sizeof(*mitem), GFP_KERNEL); if (!mitem) return -ENOMEM; spin_lock(&mode_list_lock); if (__find_mode(mode->kind)) { err = -EEXIST; kfree(mitem); goto unlock; } mitem->mode = mode; list_add_tail(&mitem->list, &mode_list); unlock: spin_unlock(&mode_list_lock); return err; } EXPORT_SYMBOL(team_mode_register); void team_mode_unregister(const struct team_mode *mode) { struct team_mode_item *mitem; spin_lock(&mode_list_lock); mitem = __find_mode(mode->kind); if (mitem) { list_del_init(&mitem->list); kfree(mitem); } spin_unlock(&mode_list_lock); } EXPORT_SYMBOL(team_mode_unregister); static const struct team_mode *team_mode_get(const char *kind) { struct team_mode_item *mitem; const struct team_mode *mode = NULL; if (!try_module_get(THIS_MODULE)) return NULL; spin_lock(&mode_list_lock); mitem = __find_mode(kind); if (!mitem) { spin_unlock(&mode_list_lock); request_module("team-mode-%s", kind); spin_lock(&mode_list_lock); mitem = __find_mode(kind); } if (mitem) { mode = mitem->mode; if (!try_module_get(mode->owner)) mode = NULL; } spin_unlock(&mode_list_lock); module_put(THIS_MODULE); return mode; } static void team_mode_put(const struct team_mode *mode) { module_put(mode->owner); } static bool team_dummy_transmit(struct team *team, struct sk_buff *skb) { dev_kfree_skb_any(skb); return false; } static rx_handler_result_t team_dummy_receive(struct team *team, struct team_port *port, struct sk_buff *skb) { return RX_HANDLER_ANOTHER; } static const struct team_mode __team_no_mode = { .kind = "*NOMODE*", }; static bool team_is_mode_set(struct team *team) { return team->mode != &__team_no_mode; } static void team_set_no_mode(struct team *team) { team->user_carrier_enabled = false; team->mode = &__team_no_mode; } static void team_adjust_ops(struct team *team) { /* * To avoid checks in rx/tx skb paths, ensure here that non-null and * correct ops are always set. */ if (!team->en_port_count || !team_is_mode_set(team) || !team->mode->ops->transmit) team->ops.transmit = team_dummy_transmit; else team->ops.transmit = team->mode->ops->transmit; if (!team->en_port_count || !team_is_mode_set(team) || !team->mode->ops->receive) team->ops.receive = team_dummy_receive; else team->ops.receive = team->mode->ops->receive; } /* * We can benefit from the fact that it's ensured no port is present * at the time of mode change. Therefore no packets are in fly so there's no * need to set mode operations in any special way. */ static int __team_change_mode(struct team *team, const struct team_mode *new_mode) { /* Check if mode was previously set and do cleanup if so */ if (team_is_mode_set(team)) { void (*exit_op)(struct team *team) = team->ops.exit; /* Clear ops area so no callback is called any longer */ memset(&team->ops, 0, sizeof(struct team_mode_ops)); team_adjust_ops(team); if (exit_op) exit_op(team); team_mode_put(team->mode); team_set_no_mode(team); /* zero private data area */ memset(&team->mode_priv, 0, sizeof(struct team) - offsetof(struct team, mode_priv)); } if (!new_mode) return 0; if (new_mode->ops->init) { int err; err = new_mode->ops->init(team); if (err) return err; } team->mode = new_mode; memcpy(&team->ops, new_mode->ops, sizeof(struct team_mode_ops)); team_adjust_ops(team); return 0; } static int team_change_mode(struct team *team, const char *kind) { const struct team_mode *new_mode; struct net_device *dev = team->dev; int err; if (!list_empty(&team->port_list)) { netdev_err(dev, "No ports can be present during mode change\n"); return -EBUSY; } if (team_is_mode_set(team) && strcmp(team->mode->kind, kind) == 0) { netdev_err(dev, "Unable to change to the same mode the team is in\n"); return -EINVAL; } new_mode = team_mode_get(kind); if (!new_mode) { netdev_err(dev, "Mode \"%s\" not found\n", kind); return -EINVAL; } err = __team_change_mode(team, new_mode); if (err) { netdev_err(dev, "Failed to change to mode \"%s\"\n", kind); team_mode_put(new_mode); return err; } netdev_info(dev, "Mode changed to \"%s\"\n", kind); return 0; } /********************* * Peers notification *********************/ static void team_notify_peers_work(struct work_struct *work) { struct team *team; int val; team = container_of(work, struct team, notify_peers.dw.work); if (!rtnl_trylock()) { schedule_delayed_work(&team->notify_peers.dw, 0); return; } val = atomic_dec_if_positive(&team->notify_peers.count_pending); if (val < 0) { rtnl_unlock(); return; } call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, team->dev); rtnl_unlock(); if (val) schedule_delayed_work(&team->notify_peers.dw, msecs_to_jiffies(team->notify_peers.interval)); } static void team_notify_peers(struct team *team) { if (!team->notify_peers.count || !netif_running(team->dev)) return; atomic_add(team->notify_peers.count, &team->notify_peers.count_pending); schedule_delayed_work(&team->notify_peers.dw, 0); } static void team_notify_peers_init(struct team *team) { INIT_DELAYED_WORK(&team->notify_peers.dw, team_notify_peers_work); } static void team_notify_peers_fini(struct team *team) { cancel_delayed_work_sync(&team->notify_peers.dw); } /******************************* * Send multicast group rejoins *******************************/ static void team_mcast_rejoin_work(struct work_struct *work) { struct team *team; int val; team = container_of(work, struct team, mcast_rejoin.dw.work); if (!rtnl_trylock()) { schedule_delayed_work(&team->mcast_rejoin.dw, 0); return; } val = atomic_dec_if_positive(&team->mcast_rejoin.count_pending); if (val < 0) { rtnl_unlock(); return; } call_netdevice_notifiers(NETDEV_RESEND_IGMP, team->dev); rtnl_unlock(); if (val) schedule_delayed_work(&team->mcast_rejoin.dw, msecs_to_jiffies(team->mcast_rejoin.interval)); } static void team_mcast_rejoin(struct team *team) { if (!team->mcast_rejoin.count || !netif_running(team->dev)) return; atomic_add(team->mcast_rejoin.count, &team->mcast_rejoin.count_pending); schedule_delayed_work(&team->mcast_rejoin.dw, 0); } static void team_mcast_rejoin_init(struct team *team) { INIT_DELAYED_WORK(&team->mcast_rejoin.dw, team_mcast_rejoin_work); } static void team_mcast_rejoin_fini(struct team *team) { cancel_delayed_work_sync(&team->mcast_rejoin.dw); } /************************ * Rx path frame handler ************************/ /* note: already called with rcu_read_lock */ static rx_handler_result_t team_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct team_port *port; struct team *team; rx_handler_result_t res; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return RX_HANDLER_CONSUMED; *pskb = skb; port = team_port_get_rcu(skb->dev); team = port->team; if (!team_port_enabled(port)) { if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) /* link-local packets are mostly useful when stack receives them * with the link they arrive on. */ return RX_HANDLER_PASS; /* allow exact match delivery for disabled ports */ res = RX_HANDLER_EXACT; } else { res = team->ops.receive(team, port, skb); } if (res == RX_HANDLER_ANOTHER) { struct team_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(team->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->rx_packets); u64_stats_add(&pcpu_stats->rx_bytes, skb->len); if (skb->pkt_type == PACKET_MULTICAST) u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); skb->dev = team->dev; } else if (res == RX_HANDLER_EXACT) { this_cpu_inc(team->pcpu_stats->rx_nohandler); } else { this_cpu_inc(team->pcpu_stats->rx_dropped); } return res; } /************************************* * Multiqueue Tx port select override *************************************/ static int team_queue_override_init(struct team *team) { struct list_head *listarr; unsigned int queue_cnt = team->dev->num_tx_queues - 1; unsigned int i; if (!queue_cnt) return 0; listarr = kmalloc_array(queue_cnt, sizeof(struct list_head), GFP_KERNEL); if (!listarr) return -ENOMEM; team->qom_lists = listarr; for (i = 0; i < queue_cnt; i++) INIT_LIST_HEAD(listarr++); return 0; } static void team_queue_override_fini(struct team *team) { kfree(team->qom_lists); } static struct list_head *__team_get_qom_list(struct team *team, u16 queue_id) { return &team->qom_lists[queue_id - 1]; } /* * note: already called with rcu_read_lock */ static bool team_queue_override_transmit(struct team *team, struct sk_buff *skb) { struct list_head *qom_list; struct team_port *port; if (!team->queue_override_enabled || !skb->queue_mapping) return false; qom_list = __team_get_qom_list(team, skb->queue_mapping); list_for_each_entry_rcu(port, qom_list, qom_list) { if (!team_dev_queue_xmit(team, port, skb)) return true; } return false; } static void __team_queue_override_port_del(struct team *team, struct team_port *port) { if (!port->queue_id) return; list_del_rcu(&port->qom_list); } static bool team_queue_override_port_has_gt_prio_than(struct team_port *port, struct team_port *cur) { if (port->priority < cur->priority) return true; if (port->priority > cur->priority) return false; if (port->index < cur->index) return true; return false; } static void __team_queue_override_port_add(struct team *team, struct team_port *port) { struct team_port *cur; struct list_head *qom_list; struct list_head *node; if (!port->queue_id) return; qom_list = __team_get_qom_list(team, port->queue_id); node = qom_list; list_for_each_entry(cur, qom_list, qom_list) { if (team_queue_override_port_has_gt_prio_than(port, cur)) break; node = &cur->qom_list; } list_add_tail_rcu(&port->qom_list, node); } static void __team_queue_override_enabled_check(struct team *team) { struct team_port *port; bool enabled = false; list_for_each_entry(port, &team->port_list, list) { if (port->queue_id) { enabled = true; break; } } if (enabled == team->queue_override_enabled) return; netdev_dbg(team->dev, "%s queue override\n", enabled ? "Enabling" : "Disabling"); team->queue_override_enabled = enabled; } static void team_queue_override_port_prio_changed(struct team *team, struct team_port *port) { if (!port->queue_id || team_port_enabled(port)) return; __team_queue_override_port_del(team, port); __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } static void team_queue_override_port_change_queue_id(struct team *team, struct team_port *port, u16 new_queue_id) { if (team_port_enabled(port)) { __team_queue_override_port_del(team, port); port->queue_id = new_queue_id; __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } else { port->queue_id = new_queue_id; } } static void team_queue_override_port_add(struct team *team, struct team_port *port) { __team_queue_override_port_add(team, port); __team_queue_override_enabled_check(team); } static void team_queue_override_port_del(struct team *team, struct team_port *port) { __team_queue_override_port_del(team, port); __team_queue_override_enabled_check(team); } /**************** * Port handling ****************/ static bool team_port_find(const struct team *team, const struct team_port *port) { struct team_port *cur; list_for_each_entry(cur, &team->port_list, list) if (cur == port) return true; return false; } /* * Enable/disable port by adding to enabled port hashlist and setting * port->index (Might be racy so reader could see incorrect ifindex when * processing a flying packet, but that is not a problem). Write guarded * by team->lock. */ static void team_port_enable(struct team *team, struct team_port *port) { if (team_port_enabled(port)) return; port->index = team->en_port_count++; hlist_add_head_rcu(&port->hlist, team_port_index_hash(team, port->index)); team_adjust_ops(team); team_queue_override_port_add(team, port); if (team->ops.port_enabled) team->ops.port_enabled(team, port); team_notify_peers(team); team_mcast_rejoin(team); team_lower_state_changed(port); } static void __reconstruct_port_hlist(struct team *team, int rm_index) { int i; struct team_port *port; for (i = rm_index + 1; i < team->en_port_count; i++) { port = team_get_port_by_index(team, i); hlist_del_rcu(&port->hlist); port->index--; hlist_add_head_rcu(&port->hlist, team_port_index_hash(team, port->index)); } } static void team_port_disable(struct team *team, struct team_port *port) { if (!team_port_enabled(port)) return; if (team->ops.port_disabled) team->ops.port_disabled(team, port); hlist_del_rcu(&port->hlist); __reconstruct_port_hlist(team, port->index); port->index = -1; team->en_port_count--; team_queue_override_port_del(team, port); team_adjust_ops(team); team_lower_state_changed(port); } #define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ NETIF_F_HIGHDMA | NETIF_F_LRO) #define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) static void __team_compute_features(struct team *team) { struct team_port *port; netdev_features_t vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL; netdev_features_t enc_features = TEAM_ENC_FEATURES; unsigned short max_hard_header_len = ETH_HLEN; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, TEAM_VLAN_FEATURES); enc_features = netdev_increment_features(enc_features, port->dev->hw_enc_features, TEAM_ENC_FEATURES); dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } rcu_read_unlock(); team->dev->vlan_features = vlan_features; team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; team->dev->hard_header_len = max_hard_header_len; team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) team->dev->priv_flags |= IFF_XMIT_DST_RELEASE; } static void team_compute_features(struct team *team) { __team_compute_features(team); netdev_change_features(team->dev); } static int team_port_enter(struct team *team, struct team_port *port) { int err = 0; dev_hold(team->dev); if (team->ops.port_enter) { err = team->ops.port_enter(team, port); if (err) { netdev_err(team->dev, "Device %s failed to enter team mode\n", port->dev->name); goto err_port_enter; } } return 0; err_port_enter: dev_put(team->dev); return err; } static void team_port_leave(struct team *team, struct team_port *port) { if (team->ops.port_leave) team->ops.port_leave(team, port); dev_put(team->dev); } #ifdef CONFIG_NET_POLL_CONTROLLER static int __team_port_enable_netpoll(struct team_port *port) { struct netpoll *np; int err; np = kzalloc(sizeof(*np), GFP_KERNEL); if (!np) return -ENOMEM; err = __netpoll_setup(np, port->dev); if (err) { kfree(np); return err; } port->np = np; return err; } static int team_port_enable_netpoll(struct team_port *port) { if (!port->team->dev->npinfo) return 0; return __team_port_enable_netpoll(port); } static void team_port_disable_netpoll(struct team_port *port) { struct netpoll *np = port->np; if (!np) return; port->np = NULL; __netpoll_free(np); } #else static int team_port_enable_netpoll(struct team_port *port) { return 0; } static void team_port_disable_netpoll(struct team_port *port) { } #endif static int team_upper_dev_link(struct team *team, struct team_port *port, struct netlink_ext_ack *extack) { struct netdev_lag_upper_info lag_upper_info; int err; lag_upper_info.tx_type = team->mode->lag_tx_type; lag_upper_info.hash_type = NETDEV_LAG_HASH_UNKNOWN; err = netdev_master_upper_dev_link(port->dev, team->dev, NULL, &lag_upper_info, extack); if (err) return err; port->dev->priv_flags |= IFF_TEAM_PORT; return 0; } static void team_upper_dev_unlink(struct team *team, struct team_port *port) { netdev_upper_dev_unlink(port->dev, team->dev); port->dev->priv_flags &= ~IFF_TEAM_PORT; } static void __team_port_change_port_added(struct team_port *port, bool linkup); static int team_dev_type_check_change(struct net_device *dev, struct net_device *port_dev); static int team_port_add(struct team *team, struct net_device *port_dev, struct netlink_ext_ack *extack) { struct net_device *dev = team->dev; struct team_port *port; char *portname = port_dev->name; int err; if (port_dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG(extack, "Loopback device can't be added as a team port"); netdev_err(dev, "Device %s is loopback device. Loopback devices can't be added as a team port\n", portname); return -EINVAL; } if (netif_is_team_port(port_dev)) { NL_SET_ERR_MSG(extack, "Device is already a port of a team device"); netdev_err(dev, "Device %s is already a port " "of a team device\n", portname); return -EBUSY; } if (dev == port_dev) { NL_SET_ERR_MSG(extack, "Cannot enslave team device to itself"); netdev_err(dev, "Cannot enslave team device to itself\n"); return -EINVAL; } if (netdev_has_upper_dev(dev, port_dev)) { NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface"); netdev_err(dev, "Device %s is already an upper device of the team interface\n", portname); return -EBUSY; } if (port_dev->features & NETIF_F_VLAN_CHALLENGED && vlan_uses_dev(dev)) { NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up"); netdev_err(dev, "Device %s is VLAN challenged and team device has VLAN set up\n", portname); return -EPERM; } err = team_dev_type_check_change(dev, port_dev); if (err) return err; if (port_dev->flags & IFF_UP) { NL_SET_ERR_MSG(extack, "Device is up. Set it down before adding it as a team port"); netdev_err(dev, "Device %s is up. Set it down before adding it as a team port\n", portname); return -EBUSY; } port = kzalloc(sizeof(struct team_port) + team->mode->port_priv_size, GFP_KERNEL); if (!port) return -ENOMEM; port->dev = port_dev; port->team = team; INIT_LIST_HEAD(&port->qom_list); port->orig.mtu = port_dev->mtu; err = dev_set_mtu(port_dev, dev->mtu); if (err) { netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err); goto err_set_mtu; } memcpy(port->orig.dev_addr, port_dev->dev_addr, port_dev->addr_len); err = team_port_enter(team, port); if (err) { netdev_err(dev, "Device %s failed to enter team mode\n", portname); goto err_port_enter; } err = dev_open(port_dev, extack); if (err) { netdev_dbg(dev, "Device %s opening failed\n", portname); goto err_dev_open; } err = vlan_vids_add_by_dev(port_dev, dev); if (err) { netdev_err(dev, "Failed to add vlan ids to device %s\n", portname); goto err_vids_add; } err = team_port_enable_netpoll(port); if (err) { netdev_err(dev, "Failed to enable netpoll on device %s\n", portname); goto err_enable_netpoll; } if (!(dev->features & NETIF_F_LRO)) dev_disable_lro(port_dev); err = netdev_rx_handler_register(port_dev, team_handle_frame, port); if (err) { netdev_err(dev, "Device %s failed to register rx_handler\n", portname); goto err_handler_register; } err = team_upper_dev_link(team, port, extack); if (err) { netdev_err(dev, "Device %s failed to set upper link\n", portname); goto err_set_upper_link; } err = __team_option_inst_add_port(team, port); if (err) { netdev_err(dev, "Device %s failed to add per-port options\n", portname); goto err_option_port_add; } /* set promiscuity level to new slave */ if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(port_dev, 1); if (err) goto err_set_slave_promisc; } /* set allmulti level to new slave */ if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(port_dev, 1); if (err) { if (dev->flags & IFF_PROMISC) dev_set_promiscuity(port_dev, -1); goto err_set_slave_promisc; } } if (dev->flags & IFF_UP) { netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); dev_mc_sync_multiple(port_dev, dev); netif_addr_unlock_bh(dev); } port->index = -1; list_add_tail_rcu(&port->list, &team->port_list); team_port_enable(team, port); __team_compute_features(team); __team_port_change_port_added(port, !!netif_oper_up(port_dev)); __team_options_change_check(team); netdev_info(dev, "Port device %s added\n", portname); return 0; err_set_slave_promisc: __team_option_inst_del_port(team, port); err_option_port_add: team_upper_dev_unlink(team, port); err_set_upper_link: netdev_rx_handler_unregister(port_dev); err_handler_register: team_port_disable_netpoll(port); err_enable_netpoll: vlan_vids_del_by_dev(port_dev, dev); err_vids_add: dev_close(port_dev); err_dev_open: team_port_leave(team, port); team_port_set_orig_dev_addr(port); err_port_enter: dev_set_mtu(port_dev, port->orig.mtu); err_set_mtu: kfree(port); return err; } static void __team_port_change_port_removed(struct team_port *port); static int team_port_del(struct team *team, struct net_device *port_dev) { struct net_device *dev = team->dev; struct team_port *port; char *portname = port_dev->name; port = team_port_get_rtnl(port_dev); if (!port || !team_port_find(team, port)) { netdev_err(dev, "Device %s does not act as a port of this team\n", portname); return -ENOENT; } team_port_disable(team, port); list_del_rcu(&port->list); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(port_dev, -1); if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(port_dev, -1); team_upper_dev_unlink(team, port); netdev_rx_handler_unregister(port_dev); team_port_disable_netpoll(port); vlan_vids_del_by_dev(port_dev, dev); if (dev->flags & IFF_UP) { dev_uc_unsync(port_dev, dev); dev_mc_unsync(port_dev, dev); } dev_close(port_dev); team_port_leave(team, port); __team_option_inst_mark_removed_port(team, port); __team_options_change_check(team); __team_option_inst_del_port(team, port); __team_port_change_port_removed(port); team_port_set_orig_dev_addr(port); dev_set_mtu(port_dev, port->orig.mtu); kfree_rcu(port, rcu); netdev_info(dev, "Port device %s removed\n", portname); __team_compute_features(team); return 0; } /***************** * Net device ops *****************/ static void team_mode_option_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.str_val = team->mode->kind; } static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx) { return team_change_mode(team, ctx->data.str_val); } static void team_notify_peers_count_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->notify_peers.count; } static int team_notify_peers_count_set(struct team *team, struct team_gsetter_ctx *ctx) { team->notify_peers.count = ctx->data.u32_val; return 0; } static void team_notify_peers_interval_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->notify_peers.interval; } static int team_notify_peers_interval_set(struct team *team, struct team_gsetter_ctx *ctx) { team->notify_peers.interval = ctx->data.u32_val; return 0; } static void team_mcast_rejoin_count_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->mcast_rejoin.count; } static int team_mcast_rejoin_count_set(struct team *team, struct team_gsetter_ctx *ctx) { team->mcast_rejoin.count = ctx->data.u32_val; return 0; } static void team_mcast_rejoin_interval_get(struct team *team, struct team_gsetter_ctx *ctx) { ctx->data.u32_val = team->mcast_rejoin.interval; } static int team_mcast_rejoin_interval_set(struct team *team, struct team_gsetter_ctx *ctx) { team->mcast_rejoin.interval = ctx->data.u32_val; return 0; } static void team_port_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = team_port_enabled(port); } static int team_port_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; if (ctx->data.bool_val) team_port_enable(team, port); else team_port_disable(team, port); return 0; } static void team_user_linkup_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup; } static void __team_carrier_check(struct team *team); static int team_user_linkup_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; port->user.linkup = ctx->data.bool_val; team_refresh_port_linkup(port); __team_carrier_check(port->team); return 0; } static void team_user_linkup_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.bool_val = port->user.linkup_enabled; } static int team_user_linkup_en_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; port->user.linkup_enabled = ctx->data.bool_val; team_refresh_port_linkup(port); __team_carrier_check(port->team); return 0; } static void team_priority_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.s32_val = port->priority; } static int team_priority_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; s32 priority = ctx->data.s32_val; if (port->priority == priority) return 0; port->priority = priority; team_queue_override_port_prio_changed(team, port); return 0; } static void team_queue_id_option_get(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; ctx->data.u32_val = port->queue_id; } static int team_queue_id_option_set(struct team *team, struct team_gsetter_ctx *ctx) { struct team_port *port = ctx->info->port; u16 new_queue_id = ctx->data.u32_val; if (port->queue_id == new_queue_id) return 0; if (new_queue_id >= team->dev->real_num_tx_queues) return -EINVAL; team_queue_override_port_change_queue_id(team, port, new_queue_id); return 0; } static const struct team_option team_options[] = { { .name = "mode", .type = TEAM_OPTION_TYPE_STRING, .getter = team_mode_option_get, .setter = team_mode_option_set, }, { .name = "notify_peers_count", .type = TEAM_OPTION_TYPE_U32, .getter = team_notify_peers_count_get, .setter = team_notify_peers_count_set, }, { .name = "notify_peers_interval", .type = TEAM_OPTION_TYPE_U32, .getter = team_notify_peers_interval_get, .setter = team_notify_peers_interval_set, }, { .name = "mcast_rejoin_count", .type = TEAM_OPTION_TYPE_U32, .getter = team_mcast_rejoin_count_get, .setter = team_mcast_rejoin_count_set, }, { .name = "mcast_rejoin_interval", .type = TEAM_OPTION_TYPE_U32, .getter = team_mcast_rejoin_interval_get, .setter = team_mcast_rejoin_interval_set, }, { .name = "enabled", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_port_en_option_get, .setter = team_port_en_option_set, }, { .name = "user_linkup", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_user_linkup_option_get, .setter = team_user_linkup_option_set, }, { .name = "user_linkup_enabled", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, .getter = team_user_linkup_en_option_get, .setter = team_user_linkup_en_option_set, }, { .name = "priority", .type = TEAM_OPTION_TYPE_S32, .per_port = true, .getter = team_priority_option_get, .setter = team_priority_option_set, }, { .name = "queue_id", .type = TEAM_OPTION_TYPE_U32, .per_port = true, .getter = team_queue_id_option_get, .setter = team_queue_id_option_set, }, }; static int team_init(struct net_device *dev) { struct team *team = netdev_priv(dev); int i; int err; team->dev = dev; team_set_no_mode(team); team->notifier_ctx = false; team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); if (!team->pcpu_stats) return -ENOMEM; for (i = 0; i < TEAM_PORT_HASHENTRIES; i++) INIT_HLIST_HEAD(&team->en_port_hlist[i]); INIT_LIST_HEAD(&team->port_list); err = team_queue_override_init(team); if (err) goto err_team_queue_override_init; team_adjust_ops(team); INIT_LIST_HEAD(&team->option_list); INIT_LIST_HEAD(&team->option_inst_list); team_notify_peers_init(team); team_mcast_rejoin_init(team); err = team_options_register(team, team_options, ARRAY_SIZE(team_options)); if (err) goto err_options_register; netif_carrier_off(dev); lockdep_register_key(&team->team_lock_key); __mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key); netdev_lockdep_set_classes(dev); return 0; err_options_register: team_mcast_rejoin_fini(team); team_notify_peers_fini(team); team_queue_override_fini(team); err_team_queue_override_init: free_percpu(team->pcpu_stats); return err; } static void team_uninit(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; struct team_port *tmp; mutex_lock(&team->lock); list_for_each_entry_safe(port, tmp, &team->port_list, list) team_port_del(team, port->dev); __team_change_mode(team, NULL); /* cleanup */ __team_options_unregister(team, team_options, ARRAY_SIZE(team_options)); team_mcast_rejoin_fini(team); team_notify_peers_fini(team); team_queue_override_fini(team); mutex_unlock(&team->lock); netdev_change_features(dev); lockdep_unregister_key(&team->team_lock_key); } static void team_destructor(struct net_device *dev) { struct team *team = netdev_priv(dev); free_percpu(team->pcpu_stats); } static int team_open(struct net_device *dev) { return 0; } static int team_close(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; list_for_each_entry(port, &team->port_list, list) { dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); } return 0; } /* * note: already called with rcu_read_lock */ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) { struct team *team = netdev_priv(dev); bool tx_success; unsigned int len = skb->len; tx_success = team_queue_override_transmit(team, skb); if (!tx_success) tx_success = team->ops.transmit(team, skb); if (tx_success) { struct team_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(team->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->tx_packets); u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(team->pcpu_stats->tx_dropped); } return NETDEV_TX_OK; } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* * This helper function exists to help dev_pick_tx get the correct * destination queue. Using a helper function skips a call to * skb_tx_hash and will put the skbs in the queue we expect on their * way down to the team driver. */ u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; /* * Save the original txq to restore before passing to the driver */ qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; if (unlikely(txq >= dev->real_num_tx_queues)) { do { txq -= dev->real_num_tx_queues; } while (txq >= dev->real_num_tx_queues); } return txq; } static void team_change_rx_flags(struct net_device *dev, int change) { struct team *team = netdev_priv(dev); struct team_port *port; int inc; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { if (change & IFF_PROMISC) { inc = dev->flags & IFF_PROMISC ? 1 : -1; dev_set_promiscuity(port->dev, inc); } if (change & IFF_ALLMULTI) { inc = dev->flags & IFF_ALLMULTI ? 1 : -1; dev_set_allmulti(port->dev, inc); } } rcu_read_unlock(); } static void team_set_rx_mode(struct net_device *dev) { struct team *team = netdev_priv(dev); struct team_port *port; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { dev_uc_sync_multiple(port->dev, dev); dev_mc_sync_multiple(port->dev, dev); } rcu_read_unlock(); } static int team_set_mac_address(struct net_device *dev, void *p) { struct sockaddr *addr = p; struct team *team = netdev_priv(dev); struct team_port *port; if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; dev_addr_set(dev, addr->sa_data); mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) if (team->ops.port_change_dev_addr) team->ops.port_change_dev_addr(team, port); mutex_unlock(&team->lock); return 0; } static int team_change_mtu(struct net_device *dev, int new_mtu) { struct team *team = netdev_priv(dev); struct team_port *port; int err; /* * Alhough this is reader, it's guarded by team lock. It's not possible * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); team->port_mtu_change_allowed = true; list_for_each_entry(port, &team->port_list, list) { err = dev_set_mtu(port->dev, new_mtu); if (err) { netdev_err(dev, "Device %s failed to change mtu", port->dev->name); goto unwind; } } team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); dev->mtu = new_mtu; return 0; unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) dev_set_mtu(port->dev, dev->mtu); team->port_mtu_change_allowed = false; mutex_unlock(&team->lock); return err; } static void team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct team *team = netdev_priv(dev); struct team_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_dropped = 0, tx_dropped = 0, rx_nohandler = 0; unsigned int start; int i; for_each_possible_cpu(i) { p = per_cpu_ptr(team->pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rx_packets = u64_stats_read(&p->rx_packets); rx_bytes = u64_stats_read(&p->rx_bytes); rx_multicast = u64_stats_read(&p->rx_multicast); tx_packets = u64_stats_read(&p->tx_packets); tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; stats->multicast += rx_multicast; stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; /* * rx_dropped, tx_dropped & rx_nohandler are u32, * updated without syncp protection. */ rx_dropped += READ_ONCE(p->rx_dropped); tx_dropped += READ_ONCE(p->tx_dropped); rx_nohandler += READ_ONCE(p->rx_nohandler); } stats->rx_dropped = rx_dropped; stats->tx_dropped = tx_dropped; stats->rx_nohandler = rx_nohandler; } static int team_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct team *team = netdev_priv(dev); struct team_port *port; int err; /* * Alhough this is reader, it's guarded by team lock. It's not possible * to traverse list in reverse under rcu_read_lock */ mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { err = vlan_vid_add(port->dev, proto, vid); if (err) goto unwind; } mutex_unlock(&team->lock); return 0; unwind: list_for_each_entry_continue_reverse(port, &team->port_list, list) vlan_vid_del(port->dev, proto, vid); mutex_unlock(&team->lock); return err; } static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct team *team = netdev_priv(dev); struct team_port *port; mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) vlan_vid_del(port->dev, proto, vid); mutex_unlock(&team->lock); return 0; } #ifdef CONFIG_NET_POLL_CONTROLLER static void team_poll_controller(struct net_device *dev) { } static void __team_netpoll_cleanup(struct team *team) { struct team_port *port; list_for_each_entry(port, &team->port_list, list) team_port_disable_netpoll(port); } static void team_netpoll_cleanup(struct net_device *dev) { struct team *team = netdev_priv(dev); mutex_lock(&team->lock); __team_netpoll_cleanup(team); mutex_unlock(&team->lock); } static int team_netpoll_setup(struct net_device *dev, struct netpoll_info *npifo) { struct team *team = netdev_priv(dev); struct team_port *port; int err = 0; mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { err = __team_port_enable_netpoll(port); if (err) { __team_netpoll_cleanup(team); break; } } mutex_unlock(&team->lock); return err; } #endif static int team_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { struct team *team = netdev_priv(dev); int err; mutex_lock(&team->lock); err = team_port_add(team, port_dev, extack); mutex_unlock(&team->lock); if (!err) netdev_change_features(dev); return err; } static int team_del_slave(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); int err; mutex_lock(&team->lock); err = team_port_del(team, port_dev); mutex_unlock(&team->lock); if (err) return err; if (netif_is_team_master(port_dev)) { lockdep_unregister_key(&team->team_lock_key); lockdep_register_key(&team->team_lock_key); lockdep_set_class(&team->lock, &team->team_lock_key); } netdev_change_features(dev); return err; } static netdev_features_t team_fix_features(struct net_device *dev, netdev_features_t features) { struct team_port *port; struct team *team = netdev_priv(dev); netdev_features_t mask; mask = features; features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { features = netdev_increment_features(features, port->dev->features, mask); } rcu_read_unlock(); features = netdev_add_tso_features(features, mask); return features; } static int team_change_carrier(struct net_device *dev, bool new_carrier) { struct team *team = netdev_priv(dev); team->user_carrier_enabled = true; if (new_carrier) netif_carrier_on(dev); else netif_carrier_off(dev); return 0; } static const struct net_device_ops team_netdev_ops = { .ndo_init = team_init, .ndo_uninit = team_uninit, .ndo_open = team_open, .ndo_stop = team_close, .ndo_start_xmit = team_xmit, .ndo_select_queue = team_select_queue, .ndo_change_rx_flags = team_change_rx_flags, .ndo_set_rx_mode = team_set_rx_mode, .ndo_set_mac_address = team_set_mac_address, .ndo_change_mtu = team_change_mtu, .ndo_get_stats64 = team_get_stats64, .ndo_vlan_rx_add_vid = team_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = team_vlan_rx_kill_vid, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = team_poll_controller, .ndo_netpoll_setup = team_netpoll_setup, .ndo_netpoll_cleanup = team_netpoll_cleanup, #endif .ndo_add_slave = team_add_slave, .ndo_del_slave = team_del_slave, .ndo_fix_features = team_fix_features, .ndo_change_carrier = team_change_carrier, .ndo_features_check = passthru_features_check, }; /*********************** * ethtool interface ***********************/ static void team_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); strscpy(drvinfo->version, UTS_RELEASE, sizeof(drvinfo->version)); } static int team_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct team *team= netdev_priv(dev); unsigned long speed = 0; struct team_port *port; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { if (team_port_txable(port)) { if (port->state.speed != SPEED_UNKNOWN) speed += port->state.speed; if (cmd->base.duplex == DUPLEX_UNKNOWN && port->state.duplex != DUPLEX_UNKNOWN) cmd->base.duplex = port->state.duplex; } } rcu_read_unlock(); cmd->base.speed = speed ? : SPEED_UNKNOWN; return 0; } static const struct ethtool_ops team_ethtool_ops = { .get_drvinfo = team_ethtool_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = team_ethtool_get_link_ksettings, }; /*********************** * rt netlink interface ***********************/ static void team_setup_by_port(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); if (port_dev->type == ARPHRD_ETHER) dev->header_ops = team->header_ops_cache; else dev->header_ops = port_dev->header_ops; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; dev->needed_headroom = port_dev->needed_headroom; dev->addr_len = port_dev->addr_len; dev->mtu = port_dev->mtu; memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len); eth_hw_addr_inherit(dev, port_dev); if (port_dev->flags & IFF_POINTOPOINT) { dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); dev->flags |= (IFF_POINTOPOINT | IFF_NOARP); } else if ((port_dev->flags & (IFF_BROADCAST | IFF_MULTICAST)) == (IFF_BROADCAST | IFF_MULTICAST)) { dev->flags |= (IFF_BROADCAST | IFF_MULTICAST); dev->flags &= ~(IFF_POINTOPOINT | IFF_NOARP); } } static int team_dev_type_check_change(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); char *portname = port_dev->name; int err; if (dev->type == port_dev->type) return 0; if (!list_empty(&team->port_list)) { netdev_err(dev, "Device %s is of different type\n", portname); return -EBUSY; } err = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, dev); err = notifier_to_errno(err); if (err) { netdev_err(dev, "Refused to change device type\n"); return err; } dev_uc_flush(dev); dev_mc_flush(dev); team_setup_by_port(dev, port_dev); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); return 0; } static void team_setup(struct net_device *dev) { struct team *team = netdev_priv(dev); ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; team->header_ops_cache = dev->header_ops; dev->netdev_ops = &team_netdev_ops; dev->ethtool_ops = &team_ethtool_ops; dev->needs_free_netdev = true; dev->priv_destructor = team_destructor; dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_TEAM; /* * Indicate we support unicast address filtering. That way core won't * bring us to promisc mode in case a unicast addr is added. * Let this up to underlay drivers. */ dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE; dev->features |= NETIF_F_LLTX; dev->features |= NETIF_F_GRO; /* Don't allow team devices to change network namespaces. */ dev->features |= NETIF_F_NETNS_LOCAL; dev->hw_features = TEAM_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_FILTER; dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; dev->features |= dev->hw_features; dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } static int team_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS] == NULL) eth_hw_addr_random(dev); return register_netdevice(dev); } static int team_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } return 0; } static unsigned int team_get_num_tx_queues(void) { return TEAM_DEFAULT_NUM_TX_QUEUES; } static unsigned int team_get_num_rx_queues(void) { return TEAM_DEFAULT_NUM_RX_QUEUES; } static struct rtnl_link_ops team_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct team), .setup = team_setup, .newlink = team_newlink, .validate = team_validate, .get_num_tx_queues = team_get_num_tx_queues, .get_num_rx_queues = team_get_num_rx_queues, }; /*********************************** * Generic netlink custom interface ***********************************/ static struct genl_family team_nl_family; static const struct nla_policy team_nl_policy[TEAM_ATTR_MAX + 1] = { [TEAM_ATTR_UNSPEC] = { .type = NLA_UNSPEC, }, [TEAM_ATTR_TEAM_IFINDEX] = { .type = NLA_U32 }, [TEAM_ATTR_LIST_OPTION] = { .type = NLA_NESTED }, [TEAM_ATTR_LIST_PORT] = { .type = NLA_NESTED }, }; static const struct nla_policy team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = { [TEAM_ATTR_OPTION_UNSPEC] = { .type = NLA_UNSPEC, }, [TEAM_ATTR_OPTION_NAME] = { .type = NLA_STRING, .len = TEAM_STRING_MAX_LEN, }, [TEAM_ATTR_OPTION_CHANGED] = { .type = NLA_FLAG }, [TEAM_ATTR_OPTION_TYPE] = { .type = NLA_U8 }, [TEAM_ATTR_OPTION_DATA] = { .type = NLA_BINARY }, [TEAM_ATTR_OPTION_PORT_IFINDEX] = { .type = NLA_U32 }, [TEAM_ATTR_OPTION_ARRAY_INDEX] = { .type = NLA_U32 }, }; static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; void *hdr; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &team_nl_family, 0, TEAM_CMD_NOOP); if (!hdr) { err = -EMSGSIZE; goto err_msg_put; } genlmsg_end(msg, hdr); return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); err_msg_put: nlmsg_free(msg); return err; } /* * Netlink cmd functions should be locked by following two functions. * Since dev gets held here, that ensures dev won't disappear in between. */ static struct team *team_nl_team_get(struct genl_info *info) { struct net *net = genl_info_net(info); int ifindex; struct net_device *dev; struct team *team; if (!info->attrs[TEAM_ATTR_TEAM_IFINDEX]) return NULL; ifindex = nla_get_u32(info->attrs[TEAM_ATTR_TEAM_IFINDEX]); dev = dev_get_by_index(net, ifindex); if (!dev || dev->netdev_ops != &team_netdev_ops) { dev_put(dev); return NULL; } team = netdev_priv(dev); mutex_lock(&team->lock); return team; } static void team_nl_team_put(struct team *team) { mutex_unlock(&team->lock); dev_put(team->dev); } typedef int team_nl_send_func_t(struct sk_buff *skb, struct team *team, u32 portid); static int team_nl_send_unicast(struct sk_buff *skb, struct team *team, u32 portid) { return genlmsg_unicast(dev_net(team->dev), skb, portid); } static int team_nl_fill_one_option_get(struct sk_buff *skb, struct team *team, struct team_option_inst *opt_inst) { struct nlattr *option_item; struct team_option *option = opt_inst->option; struct team_option_inst_info *opt_inst_info = &opt_inst->info; struct team_gsetter_ctx ctx; int err; ctx.info = opt_inst_info; err = team_option_get(team, opt_inst, &ctx); if (err) return err; option_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_OPTION); if (!option_item) return -EMSGSIZE; if (nla_put_string(skb, TEAM_ATTR_OPTION_NAME, option->name)) goto nest_cancel; if (opt_inst_info->port && nla_put_u32(skb, TEAM_ATTR_OPTION_PORT_IFINDEX, opt_inst_info->port->dev->ifindex)) goto nest_cancel; if (opt_inst->option->array_size && nla_put_u32(skb, TEAM_ATTR_OPTION_ARRAY_INDEX, opt_inst_info->array_index)) goto nest_cancel; switch (option->type) { case TEAM_OPTION_TYPE_U32: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32)) goto nest_cancel; if (nla_put_u32(skb, TEAM_ATTR_OPTION_DATA, ctx.data.u32_val)) goto nest_cancel; break; case TEAM_OPTION_TYPE_STRING: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_STRING)) goto nest_cancel; if (nla_put_string(skb, TEAM_ATTR_OPTION_DATA, ctx.data.str_val)) goto nest_cancel; break; case TEAM_OPTION_TYPE_BINARY: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_BINARY)) goto nest_cancel; if (nla_put(skb, TEAM_ATTR_OPTION_DATA, ctx.data.bin_val.len, ctx.data.bin_val.ptr)) goto nest_cancel; break; case TEAM_OPTION_TYPE_BOOL: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_FLAG)) goto nest_cancel; if (ctx.data.bool_val && nla_put_flag(skb, TEAM_ATTR_OPTION_DATA)) goto nest_cancel; break; case TEAM_OPTION_TYPE_S32: if (nla_put_u8(skb, TEAM_ATTR_OPTION_TYPE, NLA_S32)) goto nest_cancel; if (nla_put_s32(skb, TEAM_ATTR_OPTION_DATA, ctx.data.s32_val)) goto nest_cancel; break; default: BUG(); } if (opt_inst->removed && nla_put_flag(skb, TEAM_ATTR_OPTION_REMOVED)) goto nest_cancel; if (opt_inst->changed) { if (nla_put_flag(skb, TEAM_ATTR_OPTION_CHANGED)) goto nest_cancel; opt_inst->changed = false; } nla_nest_end(skb, option_item); return 0; nest_cancel: nla_nest_cancel(skb, option_item); return -EMSGSIZE; } static int __send_and_alloc_skb(struct sk_buff **pskb, struct team *team, u32 portid, team_nl_send_func_t *send_func) { int err; if (*pskb) { err = send_func(*pskb, team, portid); if (err) return err; } *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!*pskb) return -ENOMEM; return 0; } static int team_nl_send_options_get(struct team *team, u32 portid, u32 seq, int flags, team_nl_send_func_t *send_func, struct list_head *sel_opt_inst_list) { struct nlattr *option_list; struct nlmsghdr *nlh; void *hdr; struct team_option_inst *opt_inst; int err; struct sk_buff *skb = NULL; bool incomplete; int i; opt_inst = list_first_entry(sel_opt_inst_list, struct team_option_inst, tmp_list); start_again: err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_OPTIONS_GET); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; option_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_OPTION); if (!option_list) goto nla_put_failure; i = 0; incomplete = false; list_for_each_entry_from(opt_inst, sel_opt_inst_list, tmp_list) { err = team_nl_fill_one_option_get(skb, team, opt_inst); if (err) { if (err == -EMSGSIZE) { if (!i) goto errout; incomplete = true; break; } goto errout; } i++; } nla_nest_end(skb, option_list); genlmsg_end(skb, hdr); if (incomplete) goto start_again; send_done: nlh = nlmsg_put(skb, portid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; goto send_done; } return send_func(skb, team, portid); nla_put_failure: err = -EMSGSIZE; errout: nlmsg_free(skb); return err; } static int team_nl_cmd_options_get(struct sk_buff *skb, struct genl_info *info) { struct team *team; struct team_option_inst *opt_inst; int err; LIST_HEAD(sel_opt_inst_list); team = team_nl_team_get(info); if (!team) return -EINVAL; list_for_each_entry(opt_inst, &team->option_inst_list, list) list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); err = team_nl_send_options_get(team, info->snd_portid, info->snd_seq, NLM_F_ACK, team_nl_send_unicast, &sel_opt_inst_list); team_nl_team_put(team); return err; } static int team_nl_send_event_options_get(struct team *team, struct list_head *sel_opt_inst_list); static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) { struct team *team; int err = 0; int i; struct nlattr *nl_option; rtnl_lock(); team = team_nl_team_get(info); if (!team) { err = -EINVAL; goto rtnl_unlock; } err = -EINVAL; if (!info->attrs[TEAM_ATTR_LIST_OPTION]) { err = -EINVAL; goto team_put; } nla_for_each_nested(nl_option, info->attrs[TEAM_ATTR_LIST_OPTION], i) { struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; struct nlattr *attr; struct nlattr *attr_data; LIST_HEAD(opt_inst_list); enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ u32 opt_array_index = 0; bool opt_is_array = false; struct team_option_inst *opt_inst; char *opt_name; bool opt_found = false; if (nla_type(nl_option) != TEAM_ATTR_ITEM_OPTION) { err = -EINVAL; goto team_put; } err = nla_parse_nested_deprecated(opt_attrs, TEAM_ATTR_OPTION_MAX, nl_option, team_nl_option_policy, info->extack); if (err) goto team_put; if (!opt_attrs[TEAM_ATTR_OPTION_NAME] || !opt_attrs[TEAM_ATTR_OPTION_TYPE]) { err = -EINVAL; goto team_put; } switch (nla_get_u8(opt_attrs[TEAM_ATTR_OPTION_TYPE])) { case NLA_U32: opt_type = TEAM_OPTION_TYPE_U32; break; case NLA_STRING: opt_type = TEAM_OPTION_TYPE_STRING; break; case NLA_BINARY: opt_type = TEAM_OPTION_TYPE_BINARY; break; case NLA_FLAG: opt_type = TEAM_OPTION_TYPE_BOOL; break; case NLA_S32: opt_type = TEAM_OPTION_TYPE_S32; break; default: goto team_put; } attr_data = opt_attrs[TEAM_ATTR_OPTION_DATA]; if (opt_type != TEAM_OPTION_TYPE_BOOL && !attr_data) { err = -EINVAL; goto team_put; } opt_name = nla_data(opt_attrs[TEAM_ATTR_OPTION_NAME]); attr = opt_attrs[TEAM_ATTR_OPTION_PORT_IFINDEX]; if (attr) opt_port_ifindex = nla_get_u32(attr); attr = opt_attrs[TEAM_ATTR_OPTION_ARRAY_INDEX]; if (attr) { opt_is_array = true; opt_array_index = nla_get_u32(attr); } list_for_each_entry(opt_inst, &team->option_inst_list, list) { struct team_option *option = opt_inst->option; struct team_gsetter_ctx ctx; struct team_option_inst_info *opt_inst_info; int tmp_ifindex; opt_inst_info = &opt_inst->info; tmp_ifindex = opt_inst_info->port ? opt_inst_info->port->dev->ifindex : 0; if (option->type != opt_type || strcmp(option->name, opt_name) || tmp_ifindex != opt_port_ifindex || (option->array_size && !opt_is_array) || opt_inst_info->array_index != opt_array_index) continue; opt_found = true; ctx.info = opt_inst_info; switch (opt_type) { case TEAM_OPTION_TYPE_U32: ctx.data.u32_val = nla_get_u32(attr_data); break; case TEAM_OPTION_TYPE_STRING: if (nla_len(attr_data) > TEAM_STRING_MAX_LEN) { err = -EINVAL; goto team_put; } ctx.data.str_val = nla_data(attr_data); break; case TEAM_OPTION_TYPE_BINARY: ctx.data.bin_val.len = nla_len(attr_data); ctx.data.bin_val.ptr = nla_data(attr_data); break; case TEAM_OPTION_TYPE_BOOL: ctx.data.bool_val = attr_data ? true : false; break; case TEAM_OPTION_TYPE_S32: ctx.data.s32_val = nla_get_s32(attr_data); break; default: BUG(); } err = team_option_set(team, opt_inst, &ctx); if (err) goto team_put; opt_inst->changed = true; list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { err = -ENOENT; goto team_put; } err = team_nl_send_event_options_get(team, &opt_inst_list); if (err) break; } team_put: team_nl_team_put(team); rtnl_unlock: rtnl_unlock(); return err; } static int team_nl_fill_one_port_get(struct sk_buff *skb, struct team_port *port) { struct nlattr *port_item; port_item = nla_nest_start_noflag(skb, TEAM_ATTR_ITEM_PORT); if (!port_item) goto nest_cancel; if (nla_put_u32(skb, TEAM_ATTR_PORT_IFINDEX, port->dev->ifindex)) goto nest_cancel; if (port->changed) { if (nla_put_flag(skb, TEAM_ATTR_PORT_CHANGED)) goto nest_cancel; port->changed = false; } if ((port->removed && nla_put_flag(skb, TEAM_ATTR_PORT_REMOVED)) || (port->state.linkup && nla_put_flag(skb, TEAM_ATTR_PORT_LINKUP)) || nla_put_u32(skb, TEAM_ATTR_PORT_SPEED, port->state.speed) || nla_put_u8(skb, TEAM_ATTR_PORT_DUPLEX, port->state.duplex)) goto nest_cancel; nla_nest_end(skb, port_item); return 0; nest_cancel: nla_nest_cancel(skb, port_item); return -EMSGSIZE; } static int team_nl_send_port_list_get(struct team *team, u32 portid, u32 seq, int flags, team_nl_send_func_t *send_func, struct team_port *one_port) { struct nlattr *port_list; struct nlmsghdr *nlh; void *hdr; struct team_port *port; int err; struct sk_buff *skb = NULL; bool incomplete; int i; port = list_first_entry_or_null(&team->port_list, struct team_port, list); start_again: err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_PORT_LIST_GET); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex)) goto nla_put_failure; port_list = nla_nest_start_noflag(skb, TEAM_ATTR_LIST_PORT); if (!port_list) goto nla_put_failure; i = 0; incomplete = false; /* If one port is selected, called wants to send port list containing * only this port. Otherwise go through all listed ports and send all */ if (one_port) { err = team_nl_fill_one_port_get(skb, one_port); if (err) goto errout; } else if (port) { list_for_each_entry_from(port, &team->port_list, list) { err = team_nl_fill_one_port_get(skb, port); if (err) { if (err == -EMSGSIZE) { if (!i) goto errout; incomplete = true; break; } goto errout; } i++; } } nla_nest_end(skb, port_list); genlmsg_end(skb, hdr); if (incomplete) goto start_again; send_done: nlh = nlmsg_put(skb, portid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; goto send_done; } return send_func(skb, team, portid); nla_put_failure: err = -EMSGSIZE; errout: nlmsg_free(skb); return err; } static int team_nl_cmd_port_list_get(struct sk_buff *skb, struct genl_info *info) { struct team *team; int err; team = team_nl_team_get(info); if (!team) return -EINVAL; err = team_nl_send_port_list_get(team, info->snd_portid, info->snd_seq, NLM_F_ACK, team_nl_send_unicast, NULL); team_nl_team_put(team); return err; } static const struct genl_small_ops team_nl_ops[] = { { .cmd = TEAM_CMD_NOOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = team_nl_cmd_noop, }, { .cmd = TEAM_CMD_OPTIONS_SET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = team_nl_cmd_options_set, .flags = GENL_ADMIN_PERM, }, { .cmd = TEAM_CMD_OPTIONS_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = team_nl_cmd_options_get, .flags = GENL_ADMIN_PERM, }, { .cmd = TEAM_CMD_PORT_LIST_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = team_nl_cmd_port_list_get, .flags = GENL_ADMIN_PERM, }, }; static const struct genl_multicast_group team_nl_mcgrps[] = { { .name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME, }, }; static struct genl_family team_nl_family __ro_after_init = { .name = TEAM_GENL_NAME, .version = TEAM_GENL_VERSION, .maxattr = TEAM_ATTR_MAX, .policy = team_nl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = team_nl_ops, .n_small_ops = ARRAY_SIZE(team_nl_ops), .resv_start_op = TEAM_CMD_PORT_LIST_GET + 1, .mcgrps = team_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(team_nl_mcgrps), }; static int team_nl_send_multicast(struct sk_buff *skb, struct team *team, u32 portid) { return genlmsg_multicast_netns(&team_nl_family, dev_net(team->dev), skb, 0, 0, GFP_KERNEL); } static int team_nl_send_event_options_get(struct team *team, struct list_head *sel_opt_inst_list) { return team_nl_send_options_get(team, 0, 0, 0, team_nl_send_multicast, sel_opt_inst_list); } static int team_nl_send_event_port_get(struct team *team, struct team_port *port) { return team_nl_send_port_list_get(team, 0, 0, 0, team_nl_send_multicast, port); } static int __init team_nl_init(void) { return genl_register_family(&team_nl_family); } static void __exit team_nl_fini(void) { genl_unregister_family(&team_nl_family); } /****************** * Change checkers ******************/ static void __team_options_change_check(struct team *team) { int err; struct team_option_inst *opt_inst; LIST_HEAD(sel_opt_inst_list); list_for_each_entry(opt_inst, &team->option_inst_list, list) { if (opt_inst->changed) list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); } err = team_nl_send_event_options_get(team, &sel_opt_inst_list); if (err && err != -ESRCH) netdev_warn(team->dev, "Failed to send options change via netlink (err %d)\n", err); } /* rtnl lock is held */ static void __team_port_change_send(struct team_port *port, bool linkup) { int err; port->changed = true; port->state.linkup = linkup; team_refresh_port_linkup(port); if (linkup) { struct ethtool_link_ksettings ecmd; err = __ethtool_get_link_ksettings(port->dev, &ecmd); if (!err) { port->state.speed = ecmd.base.speed; port->state.duplex = ecmd.base.duplex; goto send_event; } } port->state.speed = 0; port->state.duplex = 0; send_event: err = team_nl_send_event_port_get(port->team, port); if (err && err != -ESRCH) netdev_warn(port->team->dev, "Failed to send port change of device %s via netlink (err %d)\n", port->dev->name, err); } static void __team_carrier_check(struct team *team) { struct team_port *port; bool team_linkup; if (team->user_carrier_enabled) return; team_linkup = false; list_for_each_entry(port, &team->port_list, list) { if (port->linkup) { team_linkup = true; break; } } if (team_linkup) netif_carrier_on(team->dev); else netif_carrier_off(team->dev); } static void __team_port_change_check(struct team_port *port, bool linkup) { if (port->state.linkup != linkup) __team_port_change_send(port, linkup); __team_carrier_check(port->team); } static void __team_port_change_port_added(struct team_port *port, bool linkup) { __team_port_change_send(port, linkup); __team_carrier_check(port->team); } static void __team_port_change_port_removed(struct team_port *port) { port->removed = true; __team_port_change_send(port, false); __team_carrier_check(port->team); } static void team_port_change_check(struct team_port *port, bool linkup) { struct team *team = port->team; mutex_lock(&team->lock); __team_port_change_check(port, linkup); mutex_unlock(&team->lock); } /************************************ * Net device notifier event handler ************************************/ static int team_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct team_port *port; port = team_port_get_rtnl(dev); if (!port) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (netif_oper_up(dev)) team_port_change_check(port, true); break; case NETDEV_DOWN: team_port_change_check(port, false); break; case NETDEV_CHANGE: if (netif_running(port->dev)) team_port_change_check(port, !!netif_oper_up(port->dev)); break; case NETDEV_UNREGISTER: team_del_slave(port->team->dev, dev); break; case NETDEV_FEAT_CHANGE: if (!port->team->notifier_ctx) { port->team->notifier_ctx = true; team_compute_features(port->team); port->team->notifier_ctx = false; } break; case NETDEV_PRECHANGEMTU: /* Forbid to change mtu of underlaying device */ if (!port->team->port_mtu_change_allowed) return NOTIFY_BAD; break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid to change type of underlaying device */ return NOTIFY_BAD; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, port->team->dev); break; } return NOTIFY_DONE; } static struct notifier_block team_notifier_block __read_mostly = { .notifier_call = team_device_event, }; /*********************** * Module init and exit ***********************/ static int __init team_module_init(void) { int err; register_netdevice_notifier(&team_notifier_block); err = rtnl_link_register(&team_link_ops); if (err) goto err_rtnl_reg; err = team_nl_init(); if (err) goto err_nl_init; return 0; err_nl_init: rtnl_link_unregister(&team_link_ops); err_rtnl_reg: unregister_netdevice_notifier(&team_notifier_block); return err; } static void __exit team_module_exit(void) { team_nl_fini(); rtnl_link_unregister(&team_link_ops); unregister_netdevice_notifier(&team_notifier_block); } module_init(team_module_init); module_exit(team_module_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>"); MODULE_DESCRIPTION("Ethernet team device driver"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); |
| 7 7 441 442 197 5 244 13 2 13 13 15 15 19 16 12 12 16 3 13 127 4 9 98 22 51 4 47 37 12 90 3 4 1 2 1 1 5 5 6 2 93 441 326 442 114 183 403 172 118 119 119 119 80 46 80 88 35 185 185 6 1220 55 1217 454 935 1220 1217 1219 1220 6 118 119 118 1135 1135 1137 410 13 326 13 286 295 253 44 34 17 546 348 250 25 500 59 528 137 2 8 132 133 133 2 16 123 3 9 7 1 3 1 9 1 8 12 9 12 16 10 2 4 4 7 3 908 140 478 139 6 21 245 2 11 92 62 62 93 29 12 16 19 94 722 599 125 252 869 42 67 468 534 689 232 541 541 541 337 337 79 78 79 337 337 336 17 1 11 1 1 1 1 1 511 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/export.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/if_vlan.h> #include <linux/filter.h> #include <net/dsa.h> #include <net/dst_metadata.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/gre.h> #include <net/pptp.h> #include <net/tipc.h> #include <linux/igmp.h> #include <linux/icmp.h> #include <linux/sctp.h> #include <linux/dccp.h> #include <linux/if_tunnel.h> #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/stddef.h> #include <linux/if_ether.h> #include <linux/if_hsr.h> #include <linux/mpls.h> #include <linux/tcp.h> #include <linux/ptp_classify.h> #include <net/flow_dissector.h> #include <net/pkt_cls.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> #include <linux/bpf.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_labels.h> #endif #include <linux/bpf-netns.h> static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { flow_dissector->used_keys |= (1ULL << key_id); } void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count) { unsigned int i; memset(flow_dissector, 0, sizeof(*flow_dissector)); for (i = 0; i < key_count; i++, key++) { /* User should make sure that every key target offset is within * boundaries of unsigned short. */ BUG_ON(key->offset > USHRT_MAX); BUG_ON(dissector_uses_key(flow_dissector, key->key_id)); dissector_set_key(flow_dissector, key->key_id); flow_dissector->offset[key->key_id] = key->offset; } /* Ensure that the dissector always includes control and basic key. * That way we are able to avoid handling lack of these in fast path. */ BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL)); BUG_ON(!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_BASIC)); } EXPORT_SYMBOL(skb_flow_dissector_init); #ifdef CONFIG_BPF_SYSCALL int flow_dissector_bpf_prog_attach_check(struct net *net, struct bpf_prog *prog) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; if (net == &init_net) { /* BPF flow dissector in the root namespace overrides * any per-net-namespace one. When attaching to root, * make sure we don't have any BPF program attached * to the non-root namespaces. */ struct net *ns; for_each_net(ns) { if (ns == &init_net) continue; if (rcu_access_pointer(ns->bpf.run_array[type])) return -EEXIST; } } else { /* Make sure root flow dissector is not attached * when attaching to the non-root namespace. */ if (rcu_access_pointer(init_net.bpf.run_array[type])) return -EEXIST; } return 0; } #endif /* CONFIG_BPF_SYSCALL */ /** * __skb_flow_get_ports - extract the upper layer ports and return them * @skb: sk_buff to extract the ports from * @thoff: transport header offset * @ip_proto: protocol for which to get port offset * @data: raw buffer pointer to the packet, if NULL use skb->data * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * * The function will try to retrieve the ports at offset thoff + poff where poff * is the protocol port offset returned from proto_ports_offset */ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen) { int poff = proto_ports_offset(ip_proto); if (!data) { data = skb->data; hlen = skb_headlen(skb); } if (poff >= 0) { __be32 *ports, _ports; ports = __skb_header_pointer(skb, thoff + poff, sizeof(_ports), data, hlen, &_ports); if (ports) return *ports; } return 0; } EXPORT_SYMBOL(__skb_flow_get_ports); static bool icmp_has_id(u8 type) { switch (type) { case ICMP_ECHO: case ICMP_ECHOREPLY: case ICMP_TIMESTAMP: case ICMP_TIMESTAMPREPLY: case ICMPV6_ECHO_REQUEST: case ICMPV6_ECHO_REPLY: return true; } return false; } /** * skb_flow_get_icmp_tci - extract ICMP(6) Type, Code and Identifier fields * @skb: sk_buff to extract from * @key_icmp: struct flow_dissector_key_icmp to fill * @data: raw buffer pointer to the packet * @thoff: offset to extract at * @hlen: packet header length */ void skb_flow_get_icmp_tci(const struct sk_buff *skb, struct flow_dissector_key_icmp *key_icmp, const void *data, int thoff, int hlen) { struct icmphdr *ih, _ih; ih = __skb_header_pointer(skb, thoff, sizeof(_ih), data, hlen, &_ih); if (!ih) return; key_icmp->type = ih->type; key_icmp->code = ih->code; /* As we use 0 to signal that the Id field is not present, * avoid confusion with packets without such field */ if (icmp_has_id(ih->type)) key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1; else key_icmp->id = 0; } EXPORT_SYMBOL(skb_flow_get_icmp_tci); /* If FLOW_DISSECTOR_KEY_ICMP is set, dissect an ICMP packet * using skb_flow_get_icmp_tci(). */ static void __skb_flow_dissect_icmp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_icmp *key_icmp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP)) return; key_icmp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ICMP, target_container); skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen); } static void __skb_flow_dissect_ah(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_ipsec *key_ah; struct ip_auth_hdr _hdr, *hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_ah = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC, target_container); key_ah->spi = hdr->spi; } static void __skb_flow_dissect_esp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_ipsec *key_esp; struct ip_esp_hdr _hdr, *hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_esp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPSEC, target_container); key_esp->spi = hdr->spi; } static void __skb_flow_dissect_l2tpv3(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_l2tpv3 *key_l2tpv3; struct { __be32 session_id; } *hdr, _hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3)) return; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return; key_l2tpv3 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_L2TPV3, target_container); key_l2tpv3->session_id = hdr->session_id; } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_meta *meta; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_META)) return; meta = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_META, target_container); meta->ingress_ifindex = skb->skb_iif; #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) if (tc_skb_ext_tc_enabled()) { struct tc_skb_ext *ext; ext = skb_ext_find(skb, TC_SKB_EXT); if (ext) meta->l2_miss = ext->l2_miss; } #endif } EXPORT_SYMBOL(skb_flow_dissect_meta); static void skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_control *ctrl; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) return; ctrl = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL, target_container); ctrl->addr_type = type; } void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; struct nf_conn *ct; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CT)) return; ct = nf_ct_get(skb, &ctinfo); if (!ct && !post_ct) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CT, target_container); if (!ct) { key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_INVALID; key->ct_zone = zone; return; } if (ctinfo < mapsize) key->ct_state = ctinfo_map[ctinfo]; #if IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); if (cl) memcpy(key->ct_labels, cl->bits, sizeof(key->ct_labels)); #endif /* CONFIG_NF_CONNTRACK */ } EXPORT_SYMBOL(skb_flow_dissect_ct); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct ip_tunnel_info *info; struct ip_tunnel_key *key; /* A quick check to see if there might be something to do. */ if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) return; info = skb_tunnel_info(skb); if (!info) return; key = &info->key; switch (ip_tunnel_info_af(info)) { case AF_INET: skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_dissector_key_ipv4_addrs *ipv4; ipv4 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, target_container); ipv4->src = key->u.ipv4.src; ipv4->dst = key->u.ipv4.dst; } break; case AF_INET6: skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS, flow_dissector, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { struct flow_dissector_key_ipv6_addrs *ipv6; ipv6 = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, target_container); ipv6->src = key->u.ipv6.src; ipv6->dst = key->u.ipv6.dst; } break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { struct flow_dissector_key_keyid *keyid; keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID, target_container); keyid->keyid = tunnel_id_to_key32(key->tun_id); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { struct flow_dissector_key_ports *tp; tp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_PORTS, target_container); tp->src = key->tp_src; tp->dst = key->tp_dst; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { struct flow_dissector_key_ip *ip; ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP, target_container); ip->tos = key->tos; ip->ttl = key->ttl; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) { struct flow_dissector_key_enc_opts *enc_opt; enc_opt = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS, target_container); if (info->options_len) { enc_opt->len = info->options_len; ip_tunnel_info_opts_get(enc_opt->data, info); enc_opt->dst_opt_type = info->key.tun_flags & TUNNEL_OPTIONS_PRESENT; } } } EXPORT_SYMBOL(skb_flow_dissect_tunnel_info); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_hash *key; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_HASH)) return; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_HASH, target_container); key->hash = skb_get_hash_raw(skb); } EXPORT_SYMBOL(skb_flow_dissect_hash); static enum flow_dissect_ret __skb_flow_dissect_mpls(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen, int lse_index, bool *entropy_label) { struct mpls_label *hdr, _hdr; u32 entry, label, bos; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY) && !dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) return FLOW_DISSECT_RET_OUT_GOOD; if (lse_index >= FLOW_DIS_MPLS_MAX) return FLOW_DISSECT_RET_OUT_GOOD; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; entry = ntohl(hdr->entry); label = (entry & MPLS_LS_LABEL_MASK) >> MPLS_LS_LABEL_SHIFT; bos = (entry & MPLS_LS_S_MASK) >> MPLS_LS_S_SHIFT; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS)) { struct flow_dissector_key_mpls *key_mpls; struct flow_dissector_mpls_lse *lse; key_mpls = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS, target_container); lse = &key_mpls->ls[lse_index]; lse->mpls_ttl = (entry & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT; lse->mpls_bos = bos; lse->mpls_tc = (entry & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; lse->mpls_label = label; dissector_set_mpls_lse(key_mpls, lse_index); } if (*entropy_label && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY)) { struct flow_dissector_key_keyid *key_keyid; key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_MPLS_ENTROPY, target_container); key_keyid->keyid = cpu_to_be32(label); } *entropy_label = label == MPLS_LABEL_ENTROPY; return bos ? FLOW_DISSECT_RET_OUT_GOOD : FLOW_DISSECT_RET_PROTO_AGAIN; } static enum flow_dissect_ret __skb_flow_dissect_arp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_arp *key_arp; struct { unsigned char ar_sha[ETH_ALEN]; unsigned char ar_sip[4]; unsigned char ar_tha[ETH_ALEN]; unsigned char ar_tip[4]; } *arp_eth, _arp_eth; const struct arphdr *arp; struct arphdr _arp; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ARP)) return FLOW_DISSECT_RET_OUT_GOOD; arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data, hlen, &_arp); if (!arp) return FLOW_DISSECT_RET_OUT_BAD; if (arp->ar_hrd != htons(ARPHRD_ETHER) || arp->ar_pro != htons(ETH_P_IP) || arp->ar_hln != ETH_ALEN || arp->ar_pln != 4 || (arp->ar_op != htons(ARPOP_REPLY) && arp->ar_op != htons(ARPOP_REQUEST))) return FLOW_DISSECT_RET_OUT_BAD; arp_eth = __skb_header_pointer(skb, nhoff + sizeof(_arp), sizeof(_arp_eth), data, hlen, &_arp_eth); if (!arp_eth) return FLOW_DISSECT_RET_OUT_BAD; key_arp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ARP, target_container); memcpy(&key_arp->sip, arp_eth->ar_sip, sizeof(key_arp->sip)); memcpy(&key_arp->tip, arp_eth->ar_tip, sizeof(key_arp->tip)); /* Only store the lower byte of the opcode; * this covers ARPOP_REPLY and ARPOP_REQUEST. */ key_arp->op = ntohs(arp->ar_op) & 0xff; ether_addr_copy(key_arp->sha, arp_eth->ar_sha); ether_addr_copy(key_arp->tha, arp_eth->ar_tha); return FLOW_DISSECT_RET_OUT_GOOD; } static enum flow_dissect_ret __skb_flow_dissect_cfm(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, int hlen) { struct flow_dissector_key_cfm *key, *hdr, _hdr; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_CFM)) return FLOW_DISSECT_RET_OUT_GOOD; hdr = __skb_header_pointer(skb, nhoff, sizeof(*key), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; key = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CFM, target_container); key->mdl_ver = hdr->mdl_ver; key->opcode = hdr->opcode; return FLOW_DISSECT_RET_OUT_GOOD; } static enum flow_dissect_ret __skb_flow_dissect_gre(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 *p_proto, int *p_nhoff, int *p_hlen, unsigned int flags) { struct flow_dissector_key_keyid *key_keyid; struct gre_base_hdr *hdr, _hdr; int offset = 0; u16 gre_ver; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, *p_hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; /* Only look inside GRE without routing */ if (hdr->flags & GRE_ROUTING) return FLOW_DISSECT_RET_OUT_GOOD; /* Only look inside GRE for version 0 and 1 */ gre_ver = ntohs(hdr->flags & GRE_VERSION); if (gre_ver > 1) return FLOW_DISSECT_RET_OUT_GOOD; *p_proto = hdr->protocol; if (gre_ver) { /* Version1 must be PPTP, and check the flags */ if (!(*p_proto == GRE_PROTO_PPP && (hdr->flags & GRE_KEY))) return FLOW_DISSECT_RET_OUT_GOOD; } offset += sizeof(struct gre_base_hdr); if (hdr->flags & GRE_CSUM) offset += sizeof_field(struct gre_full_hdr, csum) + sizeof_field(struct gre_full_hdr, reserved1); if (hdr->flags & GRE_KEY) { const __be32 *keyid; __be32 _keyid; keyid = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_keyid), data, *p_hlen, &_keyid); if (!keyid) return FLOW_DISSECT_RET_OUT_BAD; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID)) { key_keyid = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_GRE_KEYID, target_container); if (gre_ver == 0) key_keyid->keyid = *keyid; else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } offset += sizeof_field(struct gre_full_hdr, key); } if (hdr->flags & GRE_SEQ) offset += sizeof_field(struct pptp_gre_header, seq); if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { const struct ethhdr *eth; struct ethhdr _eth; eth = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_eth), data, *p_hlen, &_eth); if (!eth) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = eth->h_proto; offset += sizeof(*eth); /* Cap headers that we access via pointers at the * end of the Ethernet header as our maximum alignment * at that point is only 2 bytes. */ if (NET_IP_ALIGN) *p_hlen = *p_nhoff + offset; } } else { /* version 1, must be PPTP */ u8 _ppp_hdr[PPP_HDRLEN]; u8 *ppp_hdr; if (hdr->flags & GRE_ACK) offset += sizeof_field(struct pptp_gre_header, ack); ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), data, *p_hlen, _ppp_hdr); if (!ppp_hdr) return FLOW_DISSECT_RET_OUT_BAD; switch (PPP_PROTOCOL(ppp_hdr)) { case PPP_IP: *p_proto = htons(ETH_P_IP); break; case PPP_IPV6: *p_proto = htons(ETH_P_IPV6); break; default: /* Could probably catch some more like MPLS */ break; } offset += PPP_HDRLEN; } *p_nhoff += offset; key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } /** * __skb_flow_dissect_batadv() - dissect batman-adv header * @skb: sk_buff to with the batman-adv header * @key_control: flow dissectors control key * @data: raw buffer pointer to the packet, if NULL use skb->data * @p_proto: pointer used to update the protocol to process next * @p_nhoff: pointer used to update inner network header offset * @hlen: packet header length * @flags: any combination of FLOW_DISSECTOR_F_* * * ETH_P_BATMAN packets are tried to be dissected. Only * &struct batadv_unicast packets are actually processed because they contain an * inner ethernet header and are usually followed by actual network header. This * allows the flow dissector to continue processing the packet. * * Return: FLOW_DISSECT_RET_PROTO_AGAIN when &struct batadv_unicast was found, * FLOW_DISSECT_RET_OUT_GOOD when dissector should stop after encapsulation, * otherwise FLOW_DISSECT_RET_OUT_BAD */ static enum flow_dissect_ret __skb_flow_dissect_batadv(const struct sk_buff *skb, struct flow_dissector_key_control *key_control, const void *data, __be16 *p_proto, int *p_nhoff, int hlen, unsigned int flags) { struct { struct batadv_unicast_packet batadv_unicast; struct ethhdr eth; } *hdr, _hdr; hdr = __skb_header_pointer(skb, *p_nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.version != BATADV_COMPAT_VERSION) return FLOW_DISSECT_RET_OUT_BAD; if (hdr->batadv_unicast.packet_type != BATADV_UNICAST) return FLOW_DISSECT_RET_OUT_BAD; *p_proto = hdr->eth.h_proto; *p_nhoff += sizeof(*hdr); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) return FLOW_DISSECT_RET_OUT_GOOD; return FLOW_DISSECT_RET_PROTO_AGAIN; } static void __skb_flow_dissect_tcp(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int thoff, int hlen) { struct flow_dissector_key_tcp *key_tcp; struct tcphdr *th, _th; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TCP)) return; th = __skb_header_pointer(skb, thoff, sizeof(_th), data, hlen, &_th); if (!th) return; if (unlikely(__tcp_hdrlen(th) < sizeof(_th))) return; key_tcp = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TCP, target_container); key_tcp->flags = (*(__be16 *) &tcp_flag_word(th) & htons(0x0FFF)); } static void __skb_flow_dissect_ports(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; struct flow_dissector_key_ports *key_ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) dissector_ports = FLOW_DISSECTOR_KEY_PORTS; else if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) return; key_ports = skb_flow_dissector_target(flow_dissector, dissector_ports, target_container); key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); } static void __skb_flow_dissect_ipv4(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct iphdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = iph->tos; key_ip->ttl = iph->ttl; } static void __skb_flow_dissect_ipv6(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, const struct ipv6hdr *iph) { struct flow_dissector_key_ip *key_ip; if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IP)) return; key_ip = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IP, target_container); key_ip->tos = ipv6_get_dsfield(iph); key_ip->ttl = iph->hop_limit; } /* Maximum number of protocol headers that can be parsed in * __skb_flow_dissect */ #define MAX_FLOW_DISSECT_HDRS 15 static bool skb_flow_dissect_allowed(int *num_hdrs) { ++*num_hdrs; return (*num_hdrs <= MAX_FLOW_DISSECT_HDRS); } static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); key_control->thoff = flow_keys->thoff; if (flow_keys->is_frag) key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (flow_keys->is_first_frag) key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flow_keys->is_encap) key_control->flags |= FLOW_DIS_ENCAPSULATION; key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); key_basic->n_proto = flow_keys->n_proto; key_basic->ip_proto = flow_keys->ip_proto; if (flow_keys->addr_proto == ETH_P_IP && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); key_addrs->v4addrs.src = flow_keys->ipv4_src; key_addrs->v4addrs.dst = flow_keys->ipv4_dst; key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } else if (flow_keys->addr_proto == ETH_P_IPV6 && dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &flow_keys->ipv6_src, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &flow_keys->ipv6_dst, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); else if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_keys->flow_label); } } u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct bpf_flow_keys *flow_keys = ctx->flow_keys; u32 result; /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); flow_keys->n_proto = proto; flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG != (int)FLOW_DISSECTOR_F_PARSE_1ST_FRAG); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL != (int)FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); BUILD_BUG_ON((int)BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP != (int)FLOW_DISSECTOR_F_STOP_AT_ENCAP); flow_keys->flags = flags; result = bpf_prog_run_pin_on_cpu(prog, ctx); flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, flow_keys->nhoff, hlen); return result; } static bool is_pppoe_ses_hdr_valid(const struct pppoe_hdr *hdr) { return hdr->ver == 1 && hdr->type == 1 && hdr->code == 0; } /** * __skb_flow_dissect - extract the flow_keys struct and return it * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into * @data: raw buffer pointer to the packet, if NULL use skb->data * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb) * @hlen: packet header length, if @data is NULL use skb_headlen(skb) * @flags: flags that control the dissection process, e.g. * FLOW_DISSECTOR_F_STOP_AT_ENCAP. * * The function will try to retrieve individual keys into target specified * by flow_dissector from either the skbuff or a raw buffer specified by the * rest parameters. * * Caller must take care of zeroing target container memory. */ bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; bool mpls_el = false; int mpls_lse = 0; int num_hdrs = 0; u8 ip_proto = 0; bool ret; if (!data) { data = skb->data; proto = skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); #if IS_ENABLED(CONFIG_NET_DSA) if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && proto == htons(ETH_P_XDSA))) { struct metadata_dst *md_dst = skb_metadata_dst(skb); const struct dsa_device_ops *ops; int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; /* Only DSA header taggers break flow dissection */ if (ops->needed_headroom && (!md_dst || md_dst->type != METADATA_HW_PORT_MUX)) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else dsa_tag_generic_flow_dissect(skb, &proto, &offset); hlen -= offset; nhoff += offset; } } #endif } /* It is ensured by skb_flow_dissector_init() that control key will * be always present. */ key_control = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_CONTROL, target_container); /* It is ensured by skb_flow_dissector_init() that basic key will * be always present. */ key_basic = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_BASIC, target_container); if (skb) { if (!net) { if (skb->dev) net = dev_net(skb->dev); else if (skb->sk) net = sock_net(skb->sk); } } WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; rcu_read_lock(); run_array = rcu_dereference(init_net.bpf.run_array[type]); if (!run_array) run_array = rcu_dereference(net->bpf.run_array[type]); if (run_array) { struct bpf_flow_keys flow_keys; struct bpf_flow_dissector ctx = { .flow_keys = &flow_keys, .data = data, .data_end = data + hlen, }; __be16 n_proto = proto; struct bpf_prog *prog; u32 result; if (skb) { ctx.skb = skb; /* we can't use 'proto' in the skb case * because it might be set to skb->vlan_proto * which has been pulled from the data */ n_proto = skb->protocol; } prog = READ_ONCE(run_array->items[0].prog); result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); if (result == BPF_FLOW_DISSECTOR_CONTINUE) goto dissect_continue; __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); return result == BPF_OK; } dissect_continue: rcu_read_unlock(); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); struct flow_dissector_key_eth_addrs *key_eth_addrs; key_eth_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS, target_container); memcpy(key_eth_addrs, eth, sizeof(*key_eth_addrs)); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS)) { struct flow_dissector_key_num_of_vlans *key_num_of_vlans; key_num_of_vlans = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_num_of_vlans->num_of_vlans = 0; } proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (proto) { case htons(ETH_P_IP): { const struct iphdr *iph; struct iphdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph || iph->ihl < 5) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += iph->ihl * 4; ip_proto = iph->protocol; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); memcpy(&key_addrs->v4addrs.src, &iph->saddr, sizeof(key_addrs->v4addrs.src)); memcpy(&key_addrs->v4addrs.dst, &iph->daddr, sizeof(key_addrs->v4addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } __skb_flow_dissect_ipv4(skb, flow_dissector, target_container, data, iph); if (ip_is_fragment(iph)) { key_control->flags |= FLOW_DIS_IS_FRAGMENT; if (iph->frag_off & htons(IP_OFFSET)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } else { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (!(flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } } break; } case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); if (!iph) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = iph->nexthdr; nhoff += sizeof(struct ipv6hdr); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); memcpy(&key_addrs->v6addrs.src, &iph->saddr, sizeof(key_addrs->v6addrs.src)); memcpy(&key_addrs->v6addrs.dst, &iph->daddr, sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } if ((dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL) || (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)) && ip6_flowlabel(iph)) { __be32 flow_label = ip6_flowlabel(iph); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { key_tags = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL, target_container); key_tags->flow_label = ntohl(flow_label); } if (flags & FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } } __skb_flow_dissect_ipv6(skb, flow_dissector, target_container, data, iph); break; } case htons(ETH_P_8021AD): case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan = NULL; struct vlan_hdr _vlan; __be16 saved_vlan_tpid = proto; if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX && skb && skb_vlan_tag_present(skb)) { proto = skb->protocol; } else { vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan); if (!vlan) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = vlan->h_vlan_encapsulated_proto; nhoff += sizeof(*vlan); } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS) && !(key_control->flags & FLOW_DIS_ENCAPSULATION)) { struct flow_dissector_key_num_of_vlans *key_nvs; key_nvs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_NUM_OF_VLANS, target_container); key_nvs->num_of_vlans++; } if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) { dissector_vlan = FLOW_DISSECTOR_KEY_VLAN; } else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) { dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN; } else { fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } if (dissector_uses_key(flow_dissector, dissector_vlan)) { key_vlan = skb_flow_dissector_target(flow_dissector, dissector_vlan, target_container); if (!vlan) { key_vlan->vlan_id = skb_vlan_tag_get_id(skb); key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb); } else { key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) & VLAN_VID_MASK; key_vlan->vlan_priority = (ntohs(vlan->h_vlan_TCI) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } case htons(ETH_P_PPP_SES): { struct { struct pppoe_hdr hdr; __be16 proto; } *hdr, _hdr; u16 ppp_proto; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (!is_pppoe_ses_hdr_valid(&hdr->hdr)) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* least significant bit of the most significant octet * indicates if protocol field was compressed */ ppp_proto = ntohs(hdr->proto); if (ppp_proto & 0x0100) { ppp_proto = ppp_proto >> 8; nhoff += PPPOE_SES_HLEN - 1; } else { nhoff += PPPOE_SES_HLEN; } if (ppp_proto == PPP_IP) { proto = htons(ETH_P_IP); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_IPV6) { proto = htons(ETH_P_IPV6); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_UC) { proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto == PPP_MPLS_MC) { proto = htons(ETH_P_MPLS_MC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; } else if (ppp_proto_is_valid(ppp_proto)) { fdret = FLOW_DISSECT_RET_OUT_GOOD; } else { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE)) { struct flow_dissector_key_pppoe *key_pppoe; key_pppoe = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PPPOE, target_container); key_pppoe->session_id = hdr->hdr.sid; key_pppoe->ppp_proto = htons(ppp_proto); key_pppoe->type = htons(ETH_P_PPP_SES); } break; } case htons(ETH_P_TIPC): { struct tipc_basic_hdr *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_TIPC)) { key_addrs = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_TIPC, target_container); key_addrs->tipckey.key = tipc_hdr_rps_key(hdr); key_control->addr_type = FLOW_DISSECTOR_KEY_TIPC; } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_MPLS_UC): case htons(ETH_P_MPLS_MC): fdret = __skb_flow_dissect_mpls(skb, flow_dissector, target_container, data, nhoff, hlen, mpls_lse, &mpls_el); nhoff += sizeof(struct mpls_label); mpls_lse++; break; case htons(ETH_P_FCOE): if ((hlen - nhoff) < FCOE_HEADER_LEN) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += FCOE_HEADER_LEN; fdret = FLOW_DISSECT_RET_OUT_GOOD; break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): fdret = __skb_flow_dissect_arp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case htons(ETH_P_BATMAN): fdret = __skb_flow_dissect_batadv(skb, key_control, data, &proto, &nhoff, hlen, flags); break; case htons(ETH_P_1588): { struct ptp_header *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } nhoff += sizeof(struct ptp_header); fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case htons(ETH_P_PRP): case htons(ETH_P_HSR): { struct hsr_tag *hdr, _hdr; hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr); if (!hdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } proto = hdr->encap_proto; nhoff += HSR_HLEN; fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; } case htons(ETH_P_CFM): fdret = __skb_flow_dissect_cfm(skb, flow_dissector, target_container, data, nhoff, hlen); break; default: fdret = FLOW_DISSECT_RET_OUT_BAD; break; } /* Process result of proto processing */ switch (fdret) { case FLOW_DISSECT_RET_OUT_GOOD: goto out_good; case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; goto out_good; case FLOW_DISSECT_RET_CONTINUE: case FLOW_DISSECT_RET_IPPROTO_AGAIN: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } ip_proto_again: fdret = FLOW_DISSECT_RET_CONTINUE; switch (ip_proto) { case IPPROTO_GRE: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = __skb_flow_dissect_gre(skb, key_control, flow_dissector, target_container, data, &proto, &nhoff, &hlen, flags); break; case NEXTHDR_HOP: case NEXTHDR_ROUTING: case NEXTHDR_DEST: { u8 _opthdr[2], *opthdr; if (proto != htons(ETH_P_IPV6)) break; opthdr = __skb_header_pointer(skb, nhoff, sizeof(_opthdr), data, hlen, &_opthdr); if (!opthdr) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } ip_proto = opthdr[0]; nhoff += (opthdr[1] + 1) << 3; fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } case NEXTHDR_FRAGMENT: { struct frag_hdr _fh, *fh; if (proto != htons(ETH_P_IPV6)) break; fh = __skb_header_pointer(skb, nhoff, sizeof(_fh), data, hlen, &_fh); if (!fh) { fdret = FLOW_DISSECT_RET_OUT_BAD; break; } key_control->flags |= FLOW_DIS_IS_FRAGMENT; nhoff += sizeof(_fh); ip_proto = fh->nexthdr; if (!(fh->frag_off & htons(IP6_OFFSET))) { key_control->flags |= FLOW_DIS_FIRST_FRAG; if (flags & FLOW_DISSECTOR_F_PARSE_1ST_FRAG) { fdret = FLOW_DISSECT_RET_IPPROTO_AGAIN; break; } } fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } case IPPROTO_IPIP: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IP); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_IPV6: if (flags & FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } proto = htons(ETH_P_IPV6); key_control->flags |= FLOW_DIS_ENCAPSULATION; if (flags & FLOW_DISSECTOR_F_STOP_AT_ENCAP) { fdret = FLOW_DISSECT_RET_OUT_GOOD; break; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_MPLS: proto = htons(ETH_P_MPLS_UC); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; break; case IPPROTO_TCP: __skb_flow_dissect_tcp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: __skb_flow_dissect_icmp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_L2TP: __skb_flow_dissect_l2tpv3(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_ESP: __skb_flow_dissect_esp(skb, flow_dissector, target_container, data, nhoff, hlen); break; case IPPROTO_AH: __skb_flow_dissect_ah(skb, flow_dissector, target_container, data, nhoff, hlen); break; default: break; } if (!(key_control->flags & FLOW_DIS_IS_FRAGMENT)) __skb_flow_dissect_ports(skb, flow_dissector, target_container, data, nhoff, ip_proto, hlen); /* Process result of IP proto processing */ switch (fdret) { case FLOW_DISSECT_RET_PROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto proto_again; break; case FLOW_DISSECT_RET_IPPROTO_AGAIN: if (skb_flow_dissect_allowed(&num_hdrs)) goto ip_proto_again; break; case FLOW_DISSECT_RET_OUT_GOOD: case FLOW_DISSECT_RET_CONTINUE: break; case FLOW_DISSECT_RET_OUT_BAD: default: goto out_bad; } out_good: ret = true; out: key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); key_basic->n_proto = proto; key_basic->ip_proto = ip_proto; return ret; out_bad: ret = false; goto out; } EXPORT_SYMBOL(__skb_flow_dissect); static siphash_aligned_key_t hashrnd; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } static const void *flow_keys_hash_start(const struct flow_keys *flow) { BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); return &flow->FLOW_KEYS_HASH_START_FIELD; } static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: diff -= sizeof(flow->addrs.v4addrs); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: diff -= sizeof(flow->addrs.v6addrs); break; case FLOW_DISSECTOR_KEY_TIPC: diff -= sizeof(flow->addrs.tipckey); break; } return sizeof(*flow) - diff; } __be32 flow_get_u32_src(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.src; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.src); case FLOW_DISSECTOR_KEY_TIPC: return flow->addrs.tipckey.key; default: return 0; } } EXPORT_SYMBOL(flow_get_u32_src); __be32 flow_get_u32_dst(const struct flow_keys *flow) { switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: return flow->addrs.v4addrs.dst; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: return (__force __be32)ipv6_addr_hash( &flow->addrs.v6addrs.dst); default: return 0; } } EXPORT_SYMBOL(flow_get_u32_dst); /* Sort the source and destination IP and the ports, * to have consistent hash within the two directions */ static inline void __flow_hash_consistentify(struct flow_keys *keys) { int addr_diff, i; switch (keys->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: if ((__force u32)keys->addrs.v4addrs.dst < (__force u32)keys->addrs.v4addrs.src) swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst); if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: addr_diff = memcmp(&keys->addrs.v6addrs.dst, &keys->addrs.v6addrs.src, sizeof(keys->addrs.v6addrs.dst)); if (addr_diff < 0) { for (i = 0; i < 4; i++) swap(keys->addrs.v6addrs.src.s6_addr32[i], keys->addrs.v6addrs.dst.s6_addr32[i]); } if ((__force u16)keys->ports.dst < (__force u16)keys->ports.src) { swap(keys->ports.src, keys->ports.dst); } break; } } static inline u32 __flow_hash_from_keys(struct flow_keys *keys, const siphash_key_t *keyval) { u32 hash; __flow_hash_consistentify(keys); hash = siphash(flow_keys_hash_start(keys), flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; return hash; } u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); static inline u32 ___skb_get_hash(const struct sk_buff *skb, struct flow_keys *keys, const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(keys, keyval); } struct _flow_keys_digest_data { __be16 n_proto; u8 ip_proto; u8 padding; __be32 ports; __be32 src; __be32 dst; }; void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow) { struct _flow_keys_digest_data *data = (struct _flow_keys_digest_data *)digest; BUILD_BUG_ON(sizeof(*data) > sizeof(*digest)); memset(digest, 0, sizeof(*digest)); data->n_proto = flow->basic.n_proto; data->ip_proto = flow->basic.ip_proto; data->ports = flow->ports.ports; data->src = flow->addrs.v4addrs.src; data->dst = flow->addrs.v4addrs.dst; } EXPORT_SYMBOL(make_flow_keys_digest); static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { struct flow_keys keys; __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, &keys, NULL, 0, 0, 0, 0); return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from * * This function calculates a flow hash based on src/dst addresses * and src/dst port numbers. Sets hash in skb to non-zero hash value * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. */ void __skb_get_hash(struct sk_buff *skb) { struct flow_keys keys; u32 hash; __flow_hash_secret_init(); hash = ___skb_get_hash(skb, &keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb) { struct flow_keys keys; return ___skb_get_hash(skb, &keys, perturb); } EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen) { u32 poff = keys->control.thoff; /* skip L4 headers for fragments after the first */ if ((keys->control.flags & FLOW_DIS_IS_FRAGMENT) && !(keys->control.flags & FLOW_DIS_FIRST_FRAG)) return poff; switch (keys->basic.ip_proto) { case IPPROTO_TCP: { /* access doff as u8 to avoid unaligned access */ const u8 *doff; u8 _doff; doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff), data, hlen, &_doff); if (!doff) return poff; poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2); break; } case IPPROTO_UDP: case IPPROTO_UDPLITE: poff += sizeof(struct udphdr); break; /* For the rest, we do not really care about header * extensions at this point for now. */ case IPPROTO_ICMP: poff += sizeof(struct icmphdr); break; case IPPROTO_ICMPV6: poff += sizeof(struct icmp6hdr); break; case IPPROTO_IGMP: poff += sizeof(struct igmphdr); break; case IPPROTO_DCCP: poff += sizeof(struct dccp_hdr); break; case IPPROTO_SCTP: poff += sizeof(struct sctphdr); break; } return poff; } /** * skb_get_poff - get the offset to the payload * @skb: sk_buff to get the payload offset from * * The function will get the offset to the payload as far as it could * be dissected. The main user is currently BPF, so that we can dynamically * truncate packets without needing to push actual payload to the user * space and can analyze headers only, instead. */ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys_basic keys; if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); } __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) { memset(keys, 0, sizeof(*keys)); memcpy(&keys->addrs.v6addrs.src, &fl6->saddr, sizeof(keys->addrs.v6addrs.src)); memcpy(&keys->addrs.v6addrs.dst, &fl6->daddr, sizeof(keys->addrs.v6addrs.dst)); keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; keys->ports.src = fl6->fl6_sport; keys->ports.dst = fl6->fl6_dport; keys->keyid.keyid = fl6->fl6_gre_key; keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); keys->basic.ip_proto = fl6->flowi6_proto; return flow_hash_from_keys(keys); } EXPORT_SYMBOL(__get_hash_from_flowi6); static const struct flow_dissector_key flow_keys_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_TIPC, .offset = offsetof(struct flow_keys, addrs.tipckey), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_VLAN, .offset = offsetof(struct flow_keys, vlan), }, { .key_id = FLOW_DISSECTOR_KEY_FLOW_LABEL, .offset = offsetof(struct flow_keys, tags), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct flow_keys, keyid), }, }; static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct flow_keys, addrs.v4addrs), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct flow_keys, addrs.v6addrs), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct flow_keys, ports), }, }; static const struct flow_dissector_key flow_keys_basic_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct flow_keys, basic), }, }; struct flow_dissector flow_keys_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_dissector); struct flow_dissector flow_keys_basic_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_basic_dissector); static int __init init_default_flow_dissectors(void) { skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); skb_flow_dissector_init(&flow_keys_dissector_symmetric, flow_keys_dissector_symmetric_keys, ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_basic_dissector, flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); return 0; } core_initcall(init_default_flow_dissectors); |
| 3 3 7 6 1 7 15 2 6 7 7 10 3 1 7 4 5 5 4 2 3 8 1 2 5 3 1 2 990 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bpf.h> #include <linux/bpf-netns.h> #include <linux/filter.h> #include <net/net_namespace.h> /* * Functions to manage BPF programs attached to netns */ struct bpf_netns_link { struct bpf_link link; enum bpf_attach_type type; enum netns_bpf_attach_type netns_type; /* We don't hold a ref to net in order to auto-detach the link * when netns is going away. Instead we rely on pernet * pre_exit callback to clear this pointer. Must be accessed * with netns_bpf_mutex held. */ struct net *net; struct list_head node; /* node in list of links attached to net */ }; /* Protects updates to netns_bpf */ DEFINE_MUTEX(netns_bpf_mutex); static void netns_bpf_attach_type_unneed(enum netns_bpf_attach_type type) { switch (type) { #ifdef CONFIG_INET case NETNS_BPF_SK_LOOKUP: static_branch_dec(&bpf_sk_lookup_enabled); break; #endif default: break; } } static void netns_bpf_attach_type_need(enum netns_bpf_attach_type type) { switch (type) { #ifdef CONFIG_INET case NETNS_BPF_SK_LOOKUP: static_branch_inc(&bpf_sk_lookup_enabled); break; #endif default: break; } } /* Must be called with netns_bpf_mutex held. */ static void netns_bpf_run_array_detach(struct net *net, enum netns_bpf_attach_type type) { struct bpf_prog_array *run_array; run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL, lockdep_is_held(&netns_bpf_mutex)); bpf_prog_array_free(run_array); } static int link_index(struct net *net, enum netns_bpf_attach_type type, struct bpf_netns_link *link) { struct bpf_netns_link *pos; int i = 0; list_for_each_entry(pos, &net->bpf.links[type], node) { if (pos == link) return i; i++; } return -ENOENT; } static int link_count(struct net *net, enum netns_bpf_attach_type type) { struct list_head *pos; int i = 0; list_for_each(pos, &net->bpf.links[type]) i++; return i; } static void fill_prog_array(struct net *net, enum netns_bpf_attach_type type, struct bpf_prog_array *prog_array) { struct bpf_netns_link *pos; unsigned int i = 0; list_for_each_entry(pos, &net->bpf.links[type], node) { prog_array->items[i].prog = pos->link.prog; i++; } } static void bpf_netns_link_release(struct bpf_link *link) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; struct bpf_prog_array *old_array, *new_array; struct net *net; int cnt, idx; mutex_lock(&netns_bpf_mutex); /* We can race with cleanup_net, but if we see a non-NULL * struct net pointer, pre_exit has not run yet and wait for * netns_bpf_mutex. */ net = net_link->net; if (!net) goto out_unlock; /* Mark attach point as unused */ netns_bpf_attach_type_unneed(type); /* Remember link position in case of safe delete */ idx = link_index(net, type, net_link); list_del(&net_link->node); cnt = link_count(net, type); if (!cnt) { netns_bpf_run_array_detach(net, type); goto out_unlock; } old_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); new_array = bpf_prog_array_alloc(cnt, GFP_KERNEL); if (!new_array) { WARN_ON(bpf_prog_array_delete_safe_at(old_array, idx)); goto out_unlock; } fill_prog_array(net, type, new_array); rcu_assign_pointer(net->bpf.run_array[type], new_array); bpf_prog_array_free(old_array); out_unlock: net_link->net = NULL; mutex_unlock(&netns_bpf_mutex); } static int bpf_netns_link_detach(struct bpf_link *link) { bpf_netns_link_release(link); return 0; } static void bpf_netns_link_dealloc(struct bpf_link *link) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); kfree(net_link); } static int bpf_netns_link_update_prog(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); enum netns_bpf_attach_type type = net_link->netns_type; struct bpf_prog_array *run_array; struct net *net; int idx, ret; if (old_prog && old_prog != link->prog) return -EPERM; if (new_prog->type != link->prog->type) return -EINVAL; mutex_lock(&netns_bpf_mutex); net = net_link->net; if (!net || !check_net(net)) { /* Link auto-detached or netns dying */ ret = -ENOLINK; goto out_unlock; } run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); idx = link_index(net, type, net_link); ret = bpf_prog_array_update_at(run_array, idx, new_prog); if (ret) goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: mutex_unlock(&netns_bpf_mutex); return ret; } static int bpf_netns_link_fill_info(const struct bpf_link *link, struct bpf_link_info *info) { const struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); unsigned int inum = 0; struct net *net; mutex_lock(&netns_bpf_mutex); net = net_link->net; if (net && check_net(net)) inum = net->ns.inum; mutex_unlock(&netns_bpf_mutex); info->netns.netns_ino = inum; info->netns.attach_type = net_link->type; return 0; } static void bpf_netns_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_link_info info = {}; bpf_netns_link_fill_info(link, &info); seq_printf(seq, "netns_ino:\t%u\n" "attach_type:\t%u\n", info.netns.netns_ino, info.netns.attach_type); } static const struct bpf_link_ops bpf_netns_link_ops = { .release = bpf_netns_link_release, .dealloc = bpf_netns_link_dealloc, .detach = bpf_netns_link_detach, .update_prog = bpf_netns_link_update_prog, .fill_link_info = bpf_netns_link_fill_info, .show_fdinfo = bpf_netns_link_show_fdinfo, }; /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr, struct net *net, enum netns_bpf_attach_type type) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); struct bpf_prog_array *run_array; u32 prog_cnt = 0, flags = 0; run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); if (run_array) prog_cnt = bpf_prog_array_length(run_array); if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) return -EFAULT; if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) return 0; return bpf_prog_array_copy_to_user(run_array, prog_ids, attr->query.prog_cnt); } int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { enum netns_bpf_attach_type type; struct net *net; int ret; if (attr->query.query_flags) return -EINVAL; type = to_netns_bpf_attach_type(attr->query.attach_type); if (type < 0) return -EINVAL; net = get_net_ns_by_fd(attr->query.target_fd); if (IS_ERR(net)) return PTR_ERR(net); mutex_lock(&netns_bpf_mutex); ret = __netns_bpf_prog_query(attr, uattr, net, type); mutex_unlock(&netns_bpf_mutex); put_net(net); return ret; } int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_prog_array *run_array; enum netns_bpf_attach_type type; struct bpf_prog *attached; struct net *net; int ret; if (attr->target_fd || attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; net = current->nsproxy->net_ns; mutex_lock(&netns_bpf_mutex); /* Attaching prog directly is not compatible with links */ if (!list_empty(&net->bpf.links[type])) { ret = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: ret = flow_dissector_bpf_prog_attach_check(net, prog); break; default: ret = -EINVAL; break; } if (ret) goto out_unlock; attached = net->bpf.progs[type]; if (attached == prog) { /* The same program cannot be attached twice */ ret = -EINVAL; goto out_unlock; } run_array = rcu_dereference_protected(net->bpf.run_array[type], lockdep_is_held(&netns_bpf_mutex)); if (run_array) { WRITE_ONCE(run_array->items[0].prog, prog); } else { run_array = bpf_prog_array_alloc(1, GFP_KERNEL); if (!run_array) { ret = -ENOMEM; goto out_unlock; } run_array->items[0].prog = prog; rcu_assign_pointer(net->bpf.run_array[type], run_array); } net->bpf.progs[type] = prog; if (attached) bpf_prog_put(attached); out_unlock: mutex_unlock(&netns_bpf_mutex); return ret; } /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_detach(struct net *net, enum netns_bpf_attach_type type, struct bpf_prog *old) { struct bpf_prog *attached; /* Progs attached via links cannot be detached */ if (!list_empty(&net->bpf.links[type])) return -EINVAL; attached = net->bpf.progs[type]; if (!attached || attached != old) return -ENOENT; netns_bpf_run_array_detach(net, type); net->bpf.progs[type] = NULL; bpf_prog_put(attached); return 0; } int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { enum netns_bpf_attach_type type; struct bpf_prog *prog; int ret; if (attr->target_fd) return -EINVAL; type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); mutex_lock(&netns_bpf_mutex); ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog); mutex_unlock(&netns_bpf_mutex); bpf_prog_put(prog); return ret; } static int netns_bpf_max_progs(enum netns_bpf_attach_type type) { switch (type) { case NETNS_BPF_FLOW_DISSECTOR: return 1; case NETNS_BPF_SK_LOOKUP: return 64; default: return 0; } } static int netns_bpf_link_attach(struct net *net, struct bpf_link *link, enum netns_bpf_attach_type type) { struct bpf_netns_link *net_link = container_of(link, struct bpf_netns_link, link); struct bpf_prog_array *run_array; int cnt, err; mutex_lock(&netns_bpf_mutex); cnt = link_count(net, type); if (cnt >= netns_bpf_max_progs(type)) { err = -E2BIG; goto out_unlock; } /* Links are not compatible with attaching prog directly */ if (net->bpf.progs[type]) { err = -EEXIST; goto out_unlock; } switch (type) { case NETNS_BPF_FLOW_DISSECTOR: err = flow_dissector_bpf_prog_attach_check(net, link->prog); break; case NETNS_BPF_SK_LOOKUP: err = 0; /* nothing to check */ break; default: err = -EINVAL; break; } if (err) goto out_unlock; run_array = bpf_prog_array_alloc(cnt + 1, GFP_KERNEL); if (!run_array) { err = -ENOMEM; goto out_unlock; } list_add_tail(&net_link->node, &net->bpf.links[type]); fill_prog_array(net, type, run_array); run_array = rcu_replace_pointer(net->bpf.run_array[type], run_array, lockdep_is_held(&netns_bpf_mutex)); bpf_prog_array_free(run_array); /* Mark attach point as used */ netns_bpf_attach_type_need(type); out_unlock: mutex_unlock(&netns_bpf_mutex); return err; } int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog) { enum netns_bpf_attach_type netns_type; struct bpf_link_primer link_primer; struct bpf_netns_link *net_link; enum bpf_attach_type type; struct net *net; int err; if (attr->link_create.flags) return -EINVAL; type = attr->link_create.attach_type; netns_type = to_netns_bpf_attach_type(type); if (netns_type < 0) return -EINVAL; net = get_net_ns_by_fd(attr->link_create.target_fd); if (IS_ERR(net)) return PTR_ERR(net); net_link = kzalloc(sizeof(*net_link), GFP_USER); if (!net_link) { err = -ENOMEM; goto out_put_net; } bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS, &bpf_netns_link_ops, prog); net_link->net = net; net_link->type = type; net_link->netns_type = netns_type; err = bpf_link_prime(&net_link->link, &link_primer); if (err) { kfree(net_link); goto out_put_net; } err = netns_bpf_link_attach(net, &net_link->link, netns_type); if (err) { bpf_link_cleanup(&link_primer); goto out_put_net; } put_net(net); return bpf_link_settle(&link_primer); out_put_net: put_net(net); return err; } static int __net_init netns_bpf_pernet_init(struct net *net) { int type; for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) INIT_LIST_HEAD(&net->bpf.links[type]); return 0; } static void __net_exit netns_bpf_pernet_pre_exit(struct net *net) { enum netns_bpf_attach_type type; struct bpf_netns_link *net_link; mutex_lock(&netns_bpf_mutex); for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) { netns_bpf_run_array_detach(net, type); list_for_each_entry(net_link, &net->bpf.links[type], node) { net_link->net = NULL; /* auto-detach link */ netns_bpf_attach_type_unneed(type); } if (net->bpf.progs[type]) bpf_prog_put(net->bpf.progs[type]); } mutex_unlock(&netns_bpf_mutex); } static struct pernet_operations netns_bpf_pernet_ops __net_initdata = { .init = netns_bpf_pernet_init, .pre_exit = netns_bpf_pernet_pre_exit, }; static int __init netns_bpf_init(void) { return register_pernet_subsys(&netns_bpf_pernet_ops); } subsys_initcall(netns_bpf_init); |
| 3 3 3 3 3 3 3 3 2132 2120 11 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* isotp.c - ISO 15765-2 CAN transport protocol for protocol family CAN * * This implementation does not provide ISO-TP specific return values to the * userspace. * * - RX path timeout of data reception leads to -ETIMEDOUT * - RX path SN mismatch leads to -EILSEQ * - RX path data reception with wrong padding leads to -EBADMSG * - TX path flowcontrol reception timeout leads to -ECOMM * - TX path flowcontrol reception overflow leads to -EMSGSIZE * - TX path flowcontrol reception with wrong layout/padding leads to -EBADMSG * - when a transfer (tx) is on the run the next write() blocks until it's done * - use CAN_ISOTP_WAIT_TX_DONE flag to block the caller until the PDU is sent * - as we have static buffers the check whether the PDU fits into the buffer * is done at FF reception time (no support for sending 'wait frames') * * Copyright (c) 2020 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. */ #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/wait.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/isotp.h> #include <linux/slab.h> #include <net/sock.h> #include <net/net_namespace.h> MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>"); MODULE_ALIAS("can-proto-6"); #define ISOTP_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp) #define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) /* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can * take full 32 bit values (4 Gbyte). We would need some good concept to handle * this between user space and kernel space. For now set the static buffer to * something about 8 kbyte to be able to test this new functionality. */ #define DEFAULT_MAX_PDU_SIZE 8300 /* maximum PDU size before ISO 15765-2:2016 extension was 4095 */ #define MAX_12BIT_PDU_SIZE 4095 /* limit the isotp pdu size from the optional module parameter to 1MByte */ #define MAX_PDU_SIZE (1025 * 1024U) static unsigned int max_pdu_size __read_mostly = DEFAULT_MAX_PDU_SIZE; module_param(max_pdu_size, uint, 0444); MODULE_PARM_DESC(max_pdu_size, "maximum isotp pdu size (default " __stringify(DEFAULT_MAX_PDU_SIZE) ")"); /* N_PCI type values in bits 7-4 of N_PCI bytes */ #define N_PCI_SF 0x00 /* single frame */ #define N_PCI_FF 0x10 /* first frame */ #define N_PCI_CF 0x20 /* consecutive frame */ #define N_PCI_FC 0x30 /* flow control */ #define N_PCI_SZ 1 /* size of the PCI byte #1 */ #define SF_PCI_SZ4 1 /* size of SingleFrame PCI including 4 bit SF_DL */ #define SF_PCI_SZ8 2 /* size of SingleFrame PCI including 8 bit SF_DL */ #define FF_PCI_SZ12 2 /* size of FirstFrame PCI including 12 bit FF_DL */ #define FF_PCI_SZ32 6 /* size of FirstFrame PCI including 32 bit FF_DL */ #define FC_CONTENT_SZ 3 /* flow control content size in byte (FS/BS/STmin) */ #define ISOTP_CHECK_PADDING (CAN_ISOTP_CHK_PAD_LEN | CAN_ISOTP_CHK_PAD_DATA) #define ISOTP_ALL_BC_FLAGS (CAN_ISOTP_SF_BROADCAST | CAN_ISOTP_CF_BROADCAST) /* Flow Status given in FC frame */ #define ISOTP_FC_CTS 0 /* clear to send */ #define ISOTP_FC_WT 1 /* wait */ #define ISOTP_FC_OVFLW 2 /* overflow */ #define ISOTP_FC_TIMEOUT 1 /* 1 sec */ #define ISOTP_ECHO_TIMEOUT 2 /* 2 secs */ enum { ISOTP_IDLE = 0, ISOTP_WAIT_FIRST_FC, ISOTP_WAIT_FC, ISOTP_WAIT_DATA, ISOTP_SENDING, ISOTP_SHUTDOWN, }; struct tpcon { u8 *buf; unsigned int buflen; unsigned int len; unsigned int idx; u32 state; u8 bs; u8 sn; u8 ll_dl; u8 sbuf[DEFAULT_MAX_PDU_SIZE]; }; struct isotp_sock { struct sock sk; int bound; int ifindex; canid_t txid; canid_t rxid; ktime_t tx_gap; ktime_t lastrxcf_tstamp; struct hrtimer rxtimer, txtimer, txfrtimer; struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; u32 frame_txtime; u32 force_tx_stmin; u32 force_rx_stmin; u32 cfecho; /* consecutive frame echo tag */ struct tpcon rx, tx; struct list_head notifier; wait_queue_head_t wait; spinlock_t rx_lock; /* protect single thread state machine */ }; static LIST_HEAD(isotp_notifier_list); static DEFINE_SPINLOCK(isotp_notifier_lock); static struct isotp_sock *isotp_busy_notifier; static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; } static u32 isotp_bc_flags(struct isotp_sock *so) { return so->opt.flags & ISOTP_ALL_BC_FLAGS; } static bool isotp_register_rxid(struct isotp_sock *so) { /* no broadcast modes => register rx_id for FC frame reception */ return (isotp_bc_flags(so) == 0); } static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, rxtimer); struct sock *sk = &so->sk; if (so->rx.state == ISOTP_WAIT_DATA) { /* we did not get new data frames in time */ /* report 'connection timed out' */ sk->sk_err = ETIMEDOUT; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; } return HRTIMER_NORESTART; } static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) { struct net_device *dev; struct sk_buff *nskb; struct canfd_frame *ncf; struct isotp_sock *so = isotp_sk(sk); int can_send_ret; nskb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), gfp_any()); if (!nskb) return 1; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) { kfree_skb(nskb); return 1; } can_skb_reserve(nskb); can_skb_prv(nskb)->ifindex = dev->ifindex; can_skb_prv(nskb)->skbcnt = 0; nskb->dev = dev; can_skb_set_owner(nskb, sk); ncf = (struct canfd_frame *)nskb->data; skb_put_zero(nskb, so->ll.mtu); /* create & send flow control reply */ ncf->can_id = so->txid; if (so->opt.flags & CAN_ISOTP_TX_PADDING) { memset(ncf->data, so->opt.txpad_content, CAN_MAX_DLEN); ncf->len = CAN_MAX_DLEN; } else { ncf->len = ae + FC_CONTENT_SZ; } ncf->data[ae] = N_PCI_FC | flowstatus; ncf->data[ae + 1] = so->rxfc.bs; ncf->data[ae + 2] = so->rxfc.stmin; if (ae) ncf->data[0] = so->opt.ext_address; ncf->flags = so->ll.tx_flags; can_send_ret = can_send(nskb, 1); if (can_send_ret) pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(can_send_ret)); dev_put(dev); /* reset blocksize counter */ so->rx.bs = 0; /* reset last CF frame rx timestamp for rx stmin enforcement */ so->lastrxcf_tstamp = ktime_set(0, 0); /* start rx timeout watchdog */ hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return 0; } static void isotp_rcv_skb(struct sk_buff *skb, struct sock *sk) { struct sockaddr_can *addr = (struct sockaddr_can *)skb->cb; BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can)); memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; if (sock_queue_rcv_skb(sk, skb) < 0) kfree_skb(skb); } static u8 padlen(u8 datalen) { static const u8 plen[] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, /* 0 - 8 */ 12, 12, 12, 12, /* 9 - 12 */ 16, 16, 16, 16, /* 13 - 16 */ 20, 20, 20, 20, /* 17 - 20 */ 24, 24, 24, 24, /* 21 - 24 */ 32, 32, 32, 32, 32, 32, 32, 32, /* 25 - 32 */ 48, 48, 48, 48, 48, 48, 48, 48, /* 33 - 40 */ 48, 48, 48, 48, 48, 48, 48, 48 /* 41 - 48 */ }; if (datalen > 48) return 64; return plen[datalen]; } /* check for length optimization and return 1/true when the check fails */ static int check_optimized(struct canfd_frame *cf, int start_index) { /* for CAN_DL <= 8 the start_index is equal to the CAN_DL as the * padding would start at this point. E.g. if the padding would * start at cf.data[7] cf->len has to be 7 to be optimal. * Note: The data[] index starts with zero. */ if (cf->len <= CAN_MAX_DLEN) return (cf->len != start_index); /* This relation is also valid in the non-linear DLC range, where * we need to take care of the minimal next possible CAN_DL. * The correct check would be (padlen(cf->len) != padlen(start_index)). * But as cf->len can only take discrete values from 12, .., 64 at this * point the padlen(cf->len) is always equal to cf->len. */ return (cf->len != padlen(start_index)); } /* check padding and return 1/true when the check fails */ static int check_pad(struct isotp_sock *so, struct canfd_frame *cf, int start_index, u8 content) { int i; /* no RX_PADDING value => check length of optimized frame length */ if (!(so->opt.flags & CAN_ISOTP_RX_PADDING)) { if (so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) return check_optimized(cf, start_index); /* no valid test against empty value => ignore frame */ return 1; } /* check datalength of correctly padded CAN frame */ if ((so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) && cf->len != padlen(cf->len)) return 1; /* check padding content */ if (so->opt.flags & CAN_ISOTP_CHK_PAD_DATA) { for (i = start_index; i < cf->len; i++) if (cf->data[i] != content) return 1; } return 0; } static void isotp_send_cframe(struct isotp_sock *so); static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) { struct sock *sk = &so->sk; if (so->tx.state != ISOTP_WAIT_FC && so->tx.state != ISOTP_WAIT_FIRST_FC) return 0; hrtimer_cancel(&so->txtimer); if ((cf->len < ae + FC_CONTENT_SZ) || ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return 1; } /* get communication parameters only from the first FC frame */ if (so->tx.state == ISOTP_WAIT_FIRST_FC) { so->txfc.bs = cf->data[ae + 1]; so->txfc.stmin = cf->data[ae + 2]; /* fix wrong STmin values according spec */ if (so->txfc.stmin > 0x7F && (so->txfc.stmin < 0xF1 || so->txfc.stmin > 0xF9)) so->txfc.stmin = 0x7F; so->tx_gap = ktime_set(0, 0); /* add transmission time for CAN frame N_As */ so->tx_gap = ktime_add_ns(so->tx_gap, so->frame_txtime); /* add waiting time for consecutive frames N_Cs */ if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) so->tx_gap = ktime_add_ns(so->tx_gap, so->force_tx_stmin); else if (so->txfc.stmin < 0x80) so->tx_gap = ktime_add_ns(so->tx_gap, so->txfc.stmin * 1000000); else so->tx_gap = ktime_add_ns(so->tx_gap, (so->txfc.stmin - 0xF0) * 100000); so->tx.state = ISOTP_WAIT_FC; } switch (cf->data[ae] & 0x0F) { case ISOTP_FC_CTS: so->tx.bs = 0; so->tx.state = ISOTP_SENDING; /* send CF frame and enable echo timeout handling */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); break; case ISOTP_FC_WT: /* start timer to wait for next FC frame */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); break; case ISOTP_FC_OVFLW: /* overflow on receiver side - report 'message too long' */ sk->sk_err = EMSGSIZE; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); fallthrough; default: /* stop this tx job */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); } return 0; } static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, struct sk_buff *skb, int len) { struct isotp_sock *so = isotp_sk(sk); struct sk_buff *nskb; hrtimer_cancel(&so->rxtimer); so->rx.state = ISOTP_IDLE; if (!len || len > cf->len - pcilen) return 1; if ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, pcilen + len, so->opt.rxpad_content)) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 1; } nskb = alloc_skb(len, gfp_any()); if (!nskb) return 1; memcpy(skb_put(nskb, len), &cf->data[pcilen], len); nskb->tstamp = skb->tstamp; nskb->dev = skb->dev; isotp_rcv_skb(nskb, sk); return 0; } static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae) { struct isotp_sock *so = isotp_sk(sk); int i; int off; int ff_pci_sz; hrtimer_cancel(&so->rxtimer); so->rx.state = ISOTP_IDLE; /* get the used sender LL_DL from the (first) CAN frame data length */ so->rx.ll_dl = padlen(cf->len); /* the first frame has to use the entire frame up to LL_DL length */ if (cf->len != so->rx.ll_dl) return 1; /* get the FF_DL */ so->rx.len = (cf->data[ae] & 0x0F) << 8; so->rx.len += cf->data[ae + 1]; /* Check for FF_DL escape sequence supporting 32 bit PDU length */ if (so->rx.len) { ff_pci_sz = FF_PCI_SZ12; } else { /* FF_DL = 0 => get real length from next 4 bytes */ so->rx.len = cf->data[ae + 2] << 24; so->rx.len += cf->data[ae + 3] << 16; so->rx.len += cf->data[ae + 4] << 8; so->rx.len += cf->data[ae + 5]; ff_pci_sz = FF_PCI_SZ32; } /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ off = (so->rx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; if (so->rx.len + ae + off + ff_pci_sz < so->rx.ll_dl) return 1; /* PDU size > default => try max_pdu_size */ if (so->rx.len > so->rx.buflen && so->rx.buflen < max_pdu_size) { u8 *newbuf = kmalloc(max_pdu_size, GFP_ATOMIC); if (newbuf) { so->rx.buf = newbuf; so->rx.buflen = max_pdu_size; } } if (so->rx.len > so->rx.buflen) { /* send FC frame with overflow status */ isotp_send_fc(sk, ae, ISOTP_FC_OVFLW); return 1; } /* copy the first received data bytes */ so->rx.idx = 0; for (i = ae + ff_pci_sz; i < so->rx.ll_dl; i++) so->rx.buf[so->rx.idx++] = cf->data[i]; /* initial setup for this pdu reception */ so->rx.sn = 1; so->rx.state = ISOTP_WAIT_DATA; /* no creation of flow control frames */ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) return 0; /* send our first FC frame */ isotp_send_fc(sk, ae, ISOTP_FC_CTS); return 0; } static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, struct sk_buff *skb) { struct isotp_sock *so = isotp_sk(sk); struct sk_buff *nskb; int i; if (so->rx.state != ISOTP_WAIT_DATA) return 0; /* drop if timestamp gap is less than force_rx_stmin nano secs */ if (so->opt.flags & CAN_ISOTP_FORCE_RXSTMIN) { if (ktime_to_ns(ktime_sub(skb->tstamp, so->lastrxcf_tstamp)) < so->force_rx_stmin) return 0; so->lastrxcf_tstamp = skb->tstamp; } hrtimer_cancel(&so->rxtimer); /* CFs are never longer than the FF */ if (cf->len > so->rx.ll_dl) return 1; /* CFs have usually the LL_DL length */ if (cf->len < so->rx.ll_dl) { /* this is only allowed for the last CF */ if (so->rx.len - so->rx.idx > so->rx.ll_dl - ae - N_PCI_SZ) return 1; } if ((cf->data[ae] & 0x0F) != so->rx.sn) { /* wrong sn detected - report 'illegal byte sequence' */ sk->sk_err = EILSEQ; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; return 1; } so->rx.sn++; so->rx.sn %= 16; for (i = ae + N_PCI_SZ; i < cf->len; i++) { so->rx.buf[so->rx.idx++] = cf->data[i]; if (so->rx.idx >= so->rx.len) break; } if (so->rx.idx >= so->rx.len) { /* we are done */ so->rx.state = ISOTP_IDLE; if ((so->opt.flags & ISOTP_CHECK_PADDING) && check_pad(so, cf, i + 1, so->opt.rxpad_content)) { /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); return 1; } nskb = alloc_skb(so->rx.len, gfp_any()); if (!nskb) return 1; memcpy(skb_put(nskb, so->rx.len), so->rx.buf, so->rx.len); nskb->tstamp = skb->tstamp; nskb->dev = skb->dev; isotp_rcv_skb(nskb, sk); return 0; } /* perform blocksize handling, if enabled */ if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) { /* start rx timeout watchdog */ hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return 0; } /* no creation of flow control frames */ if (so->opt.flags & CAN_ISOTP_LISTEN_MODE) return 0; /* we reached the specified blocksize so->rxfc.bs */ isotp_send_fc(sk, ae, ISOTP_FC_CTS); return 0; } static void isotp_rcv(struct sk_buff *skb, void *data) { struct sock *sk = (struct sock *)data; struct isotp_sock *so = isotp_sk(sk); struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; u8 n_pci_type, sf_dl; /* Strictly receive only frames with the configured MTU size * => clear separation of CAN2.0 / CAN FD transport channels */ if (skb->len != so->ll.mtu) return; cf = (struct canfd_frame *)skb->data; /* if enabled: check reception of my configured extended address */ if (ae && cf->data[0] != so->opt.rx_ext_address) return; n_pci_type = cf->data[ae] & 0xF0; /* Make sure the state changes and data structures stay consistent at * CAN frame reception time. This locking is not needed in real world * use cases but the inconsistency can be triggered with syzkaller. */ spin_lock(&so->rx_lock); if (so->opt.flags & CAN_ISOTP_HALF_DUPLEX) { /* check rx/tx path half duplex expectations */ if ((so->tx.state != ISOTP_IDLE && n_pci_type != N_PCI_FC) || (so->rx.state != ISOTP_IDLE && n_pci_type == N_PCI_FC)) goto out_unlock; } switch (n_pci_type) { case N_PCI_FC: /* tx path: flow control frame containing the FC parameters */ isotp_rcv_fc(so, cf, ae); break; case N_PCI_SF: /* rx path: single frame * * As we do not have a rx.ll_dl configuration, we can only test * if the CAN frames payload length matches the LL_DL == 8 * requirements - no matter if it's CAN 2.0 or CAN FD */ /* get the SF_DL from the N_PCI byte */ sf_dl = cf->data[ae] & 0x0F; if (cf->len <= CAN_MAX_DLEN) { isotp_rcv_sf(sk, cf, SF_PCI_SZ4 + ae, skb, sf_dl); } else { if (can_is_canfd_skb(skb)) { /* We have a CAN FD frame and CAN_DL is greater than 8: * Only frames with the SF_DL == 0 ESC value are valid. * * If so take care of the increased SF PCI size * (SF_PCI_SZ8) to point to the message content behind * the extended SF PCI info and get the real SF_DL * length value from the formerly first data byte. */ if (sf_dl == 0) isotp_rcv_sf(sk, cf, SF_PCI_SZ8 + ae, skb, cf->data[SF_PCI_SZ4 + ae]); } } break; case N_PCI_FF: /* rx path: first frame */ isotp_rcv_ff(sk, cf, ae); break; case N_PCI_CF: /* rx path: consecutive frame */ isotp_rcv_cf(sk, cf, ae, skb); break; } out_unlock: spin_unlock(&so->rx_lock); } static void isotp_fill_dataframe(struct canfd_frame *cf, struct isotp_sock *so, int ae, int off) { int pcilen = N_PCI_SZ + ae + off; int space = so->tx.ll_dl - pcilen; int num = min_t(int, so->tx.len - so->tx.idx, space); int i; cf->can_id = so->txid; cf->len = num + pcilen; if (num < space) { if (so->opt.flags & CAN_ISOTP_TX_PADDING) { /* user requested padding */ cf->len = padlen(cf->len); memset(cf->data, so->opt.txpad_content, cf->len); } else if (cf->len > CAN_MAX_DLEN) { /* mandatory padding for CAN FD frames */ cf->len = padlen(cf->len); memset(cf->data, CAN_ISOTP_DEFAULT_PAD_CONTENT, cf->len); } } for (i = 0; i < num; i++) cf->data[pcilen + i] = so->tx.buf[so->tx.idx++]; if (ae) cf->data[0] = so->opt.ext_address; } static void isotp_send_cframe(struct isotp_sock *so) { struct sock *sk = &so->sk; struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; int can_send_ret; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) return; skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), GFP_ATOMIC); if (!skb) { dev_put(dev); return; } can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); /* create consecutive frame */ isotp_fill_dataframe(cf, so, ae, 0); /* place consecutive frame N_PCI in appropriate index */ cf->data[ae] = N_PCI_CF | so->tx.sn++; so->tx.sn %= 16; so->tx.bs++; cf->flags = so->ll.tx_flags; skb->dev = dev; can_skb_set_owner(skb, sk); /* cfecho should have been zero'ed by init/isotp_rcv_echo() */ if (so->cfecho) pr_notice_once("can-isotp: cfecho is %08X != 0\n", so->cfecho); /* set consecutive frame echo tag */ so->cfecho = *(u32 *)cf->data; /* send frame with local echo enabled */ can_send_ret = can_send(skb, 1); if (can_send_ret) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(can_send_ret)); if (can_send_ret == -ENOBUFS) pr_notice_once("can-isotp: tx queue is full\n"); } dev_put(dev); } static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so, int ae) { int i; int ff_pci_sz; cf->can_id = so->txid; cf->len = so->tx.ll_dl; if (ae) cf->data[0] = so->opt.ext_address; /* create N_PCI bytes with 12/32 bit FF_DL data length */ if (so->tx.len > MAX_12BIT_PDU_SIZE) { /* use 32 bit FF_DL notation */ cf->data[ae] = N_PCI_FF; cf->data[ae + 1] = 0; cf->data[ae + 2] = (u8)(so->tx.len >> 24) & 0xFFU; cf->data[ae + 3] = (u8)(so->tx.len >> 16) & 0xFFU; cf->data[ae + 4] = (u8)(so->tx.len >> 8) & 0xFFU; cf->data[ae + 5] = (u8)so->tx.len & 0xFFU; ff_pci_sz = FF_PCI_SZ32; } else { /* use 12 bit FF_DL notation */ cf->data[ae] = (u8)(so->tx.len >> 8) | N_PCI_FF; cf->data[ae + 1] = (u8)so->tx.len & 0xFFU; ff_pci_sz = FF_PCI_SZ12; } /* add first data bytes depending on ae */ for (i = ae + ff_pci_sz; i < so->tx.ll_dl; i++) cf->data[i] = so->tx.buf[so->tx.idx++]; so->tx.sn = 1; } static void isotp_rcv_echo(struct sk_buff *skb, void *data) { struct sock *sk = (struct sock *)data; struct isotp_sock *so = isotp_sk(sk); struct canfd_frame *cf = (struct canfd_frame *)skb->data; /* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk || so->cfecho != *(u32 *)cf->data) return; /* cancel local echo timeout */ hrtimer_cancel(&so->txtimer); /* local echo skb with consecutive frame has been consumed */ so->cfecho = 0; if (so->tx.idx >= so->tx.len) { /* we are done */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return; } if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { /* stop and wait for FC with timeout */ so->tx.state = ISOTP_WAIT_FC; hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return; } /* no gap between data frames needed => use burst mode */ if (!so->tx_gap) { /* enable echo timeout handling */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); return; } /* start timer to send next consecutive frame with correct delay */ hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); } static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txtimer); struct sock *sk = &so->sk; /* don't handle timeouts in IDLE or SHUTDOWN state */ if (so->tx.state == ISOTP_IDLE || so->tx.state == ISOTP_SHUTDOWN) return HRTIMER_NORESTART; /* we did not get any flow control or echo frame in time */ /* report 'communication error on send' */ sk->sk_err = ECOMM; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); /* reset tx state */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return HRTIMER_NORESTART; } static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txfrtimer); /* start echo timeout handling and cover below protocol error */ hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); /* cfecho should be consumed by isotp_rcv_echo() here */ if (so->tx.state == ISOTP_SENDING && !so->cfecho) isotp_send_cframe(so); return HRTIMER_NORESTART; } static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT; int off; int err; if (!so->bound || so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; while (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE) { /* we do not support multiple buffers - for now */ if (msg->msg_flags & MSG_DONTWAIT) return -EAGAIN; if (so->tx.state == ISOTP_SHUTDOWN) return -EADDRNOTAVAIL; /* wait for complete transmission of current pdu */ err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); if (err) goto err_event_drop; } /* PDU size > default => try max_pdu_size */ if (size > so->tx.buflen && so->tx.buflen < max_pdu_size) { u8 *newbuf = kmalloc(max_pdu_size, GFP_KERNEL); if (newbuf) { so->tx.buf = newbuf; so->tx.buflen = max_pdu_size; } } if (!size || size > so->tx.buflen) { err = -EINVAL; goto err_out_drop; } /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0; /* does the given data fit into a single frame for SF_BROADCAST? */ if ((isotp_bc_flags(so) == CAN_ISOTP_SF_BROADCAST) && (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) { err = -EINVAL; goto err_out_drop; } err = memcpy_from_msg(so->tx.buf, msg, size); if (err < 0) goto err_out_drop; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) { err = -ENXIO; goto err_out_drop; } skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) { dev_put(dev); goto err_out_drop; } can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; so->tx.len = size; so->tx.idx = 0; cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); /* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ if (so->cfecho) pr_notice_once("can-isotp: uninit cfecho %08X\n", so->cfecho); /* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { /* The message size generally fits into a SingleFrame - good. * * SF_DL ESC offset optimization: * * When TX_DL is greater 8 but the message would still fit * into a 8 byte CAN frame, we can omit the offset. * This prevents a protocol caused length extension from * CAN_DL = 8 to CAN_DL = 12 due to the SF_SL ESC handling. */ if (size <= CAN_MAX_DLEN - SF_PCI_SZ4 - ae) off = 0; isotp_fill_dataframe(cf, so, ae, off); /* place single frame N_PCI w/o length in appropriate index */ cf->data[ae] = N_PCI_SF; /* place SF_DL size value depending on the SF_DL ESC offset */ if (off) cf->data[SF_PCI_SZ4 + ae] = size; else cf->data[ae] |= size; /* set CF echo tag for isotp_rcv_echo() (SF-mode) */ so->cfecho = *(u32 *)cf->data; } else { /* send first frame */ isotp_create_fframe(cf, so, ae); if (isotp_bc_flags(so) == CAN_ISOTP_CF_BROADCAST) { /* set timer for FC-less operation (STmin = 0) */ if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) so->tx_gap = ktime_set(0, so->force_tx_stmin); else so->tx_gap = ktime_set(0, so->frame_txtime); /* disable wait for FCs due to activated block size */ so->txfc.bs = 0; /* set CF echo tag for isotp_rcv_echo() (CF-mode) */ so->cfecho = *(u32 *)cf->data; } else { /* standard flow control check */ so->tx.state = ISOTP_WAIT_FIRST_FC; /* start timeout for FC */ hrtimer_sec = ISOTP_FC_TIMEOUT; /* no CF echo tag for isotp_rcv_echo() (FF-mode) */ so->cfecho = 0; } } hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), HRTIMER_MODE_REL_SOFT); /* send the first or only CAN frame */ cf->flags = so->ll.tx_flags; skb->dev = dev; skb->sk = sk; err = can_send(skb, 1); dev_put(dev); if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); /* no transmission -> no timeout monitoring */ hrtimer_cancel(&so->txtimer); /* reset consecutive frame echo tag */ so->cfecho = 0; goto err_out_drop; } if (wait_tx_done) { /* wait for complete transmission of current pdu */ err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); if (err) goto err_event_drop; err = sock_error(sk); if (err) return err; } return size; err_event_drop: /* got signal: force tx state machine to be idle */ so->tx.state = ISOTP_IDLE; hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); err_out_drop: /* drop this PDU and unlock a potential wait queue */ so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); return err; } static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; struct isotp_sock *so = isotp_sk(sk); int ret = 0; if (flags & ~(MSG_DONTWAIT | MSG_TRUNC | MSG_PEEK | MSG_CMSG_COMPAT)) return -EINVAL; if (!so->bound) return -EADDRNOTAVAIL; skb = skb_recv_datagram(sk, flags, &ret); if (!skb) return ret; if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else size = skb->len; ret = memcpy_to_msg(msg, skb->data, size); if (ret < 0) goto out_err; sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(ISOTP_MIN_NAMELEN); msg->msg_namelen = ISOTP_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* set length of return value */ ret = (flags & MSG_TRUNC) ? skb->len : size; out_err: skb_free_datagram(sk, skb); return ret; } static int isotp_release(struct socket *sock) { struct sock *sk = sock->sk; struct isotp_sock *so; struct net *net; if (!sk) return 0; so = isotp_sk(sk); net = sock_net(sk); /* wait for complete transmission of current pdu */ while (wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE) == 0 && cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SHUTDOWN) != ISOTP_IDLE) ; /* force state machines to be idle also when a signal occurred */ so->tx.state = ISOTP_SHUTDOWN; so->rx.state = ISOTP_IDLE; spin_lock(&isotp_notifier_lock); while (isotp_busy_notifier == so) { spin_unlock(&isotp_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&isotp_notifier_lock); } list_del(&so->notifier); spin_unlock(&isotp_notifier_lock); lock_sock(sk); /* remove current filters & unregister */ if (so->bound) { if (so->ifindex) { struct net_device *dev; dev = dev_get_by_index(net, so->ifindex); if (dev) { if (isotp_register_rxid(so)) can_rx_unregister(net, dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); can_rx_unregister(net, dev, so->txid, SINGLE_MASK(so->txid), isotp_rcv_echo, sk); dev_put(dev); synchronize_rcu(); } } } hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); hrtimer_cancel(&so->rxtimer); so->ifindex = 0; so->bound = 0; if (so->rx.buf != so->rx.sbuf) kfree(so->rx.buf); if (so->tx.buf != so->tx.sbuf) kfree(so->tx.buf); sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); struct net *net = sock_net(sk); int ifindex; struct net_device *dev; canid_t tx_id = addr->can_addr.tp.tx_id; canid_t rx_id = addr->can_addr.tp.rx_id; int err = 0; int notify_enetdown = 0; if (len < ISOTP_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; /* sanitize tx CAN identifier */ if (tx_id & CAN_EFF_FLAG) tx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); else tx_id &= CAN_SFF_MASK; /* give feedback on wrong CAN-ID value */ if (tx_id != addr->can_addr.tp.tx_id) return -EINVAL; /* sanitize rx CAN identifier (if needed) */ if (isotp_register_rxid(so)) { if (rx_id & CAN_EFF_FLAG) rx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); else rx_id &= CAN_SFF_MASK; /* give feedback on wrong CAN-ID value */ if (rx_id != addr->can_addr.tp.rx_id) return -EINVAL; } if (!addr->can_ifindex) return -ENODEV; lock_sock(sk); if (so->bound) { err = -EINVAL; goto out; } /* ensure different CAN IDs when the rx_id is to be registered */ if (isotp_register_rxid(so) && rx_id == tx_id) { err = -EADDRNOTAVAIL; goto out; } dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { dev_put(dev); err = -ENODEV; goto out; } if (dev->mtu < so->ll.mtu) { dev_put(dev); err = -EINVAL; goto out; } if (!(dev->flags & IFF_UP)) notify_enetdown = 1; ifindex = dev->ifindex; if (isotp_register_rxid(so)) can_rx_register(net, dev, rx_id, SINGLE_MASK(rx_id), isotp_rcv, sk, "isotp", sk); /* no consecutive frame echo skb in flight */ so->cfecho = 0; /* register for echo skb's */ can_rx_register(net, dev, tx_id, SINGLE_MASK(tx_id), isotp_rcv_echo, sk, "isotpe", sk); dev_put(dev); /* switch to new settings */ so->ifindex = ifindex; so->rxid = rx_id; so->txid = tx_id; so->bound = 1; out: release_sock(sk); if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } return err; } static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); if (peer) return -EOPNOTSUPP; memset(addr, 0, ISOTP_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = so->ifindex; addr->can_addr.tp.rx_id = so->rxid; addr->can_addr.tp.tx_id = so->txid; return ISOTP_MIN_NAMELEN; } static int isotp_setsockopt_locked(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int ret = 0; if (so->bound) return -EISCONN; switch (optname) { case CAN_ISOTP_OPTS: if (optlen != sizeof(struct can_isotp_options)) return -EINVAL; if (copy_from_sockptr(&so->opt, optval, optlen)) return -EFAULT; /* no separate rx_ext_address is given => use ext_address */ if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR)) so->opt.rx_ext_address = so->opt.ext_address; /* these broadcast flags are not allowed together */ if (isotp_bc_flags(so) == ISOTP_ALL_BC_FLAGS) { /* CAN_ISOTP_SF_BROADCAST is prioritized */ so->opt.flags &= ~CAN_ISOTP_CF_BROADCAST; /* give user feedback on wrong config attempt */ ret = -EINVAL; } /* check for frame_txtime changes (0 => no changes) */ if (so->opt.frame_txtime) { if (so->opt.frame_txtime == CAN_ISOTP_FRAME_TXTIME_ZERO) so->frame_txtime = 0; else so->frame_txtime = so->opt.frame_txtime; } break; case CAN_ISOTP_RECV_FC: if (optlen != sizeof(struct can_isotp_fc_options)) return -EINVAL; if (copy_from_sockptr(&so->rxfc, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_TX_STMIN: if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&so->force_tx_stmin, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_RX_STMIN: if (optlen != sizeof(u32)) return -EINVAL; if (copy_from_sockptr(&so->force_rx_stmin, optval, optlen)) return -EFAULT; break; case CAN_ISOTP_LL_OPTS: if (optlen == sizeof(struct can_isotp_ll_options)) { struct can_isotp_ll_options ll; if (copy_from_sockptr(&ll, optval, optlen)) return -EFAULT; /* check for correct ISO 11898-1 DLC data length */ if (ll.tx_dl != padlen(ll.tx_dl)) return -EINVAL; if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU) return -EINVAL; if (ll.mtu == CAN_MTU && (ll.tx_dl > CAN_MAX_DLEN || ll.tx_flags != 0)) return -EINVAL; memcpy(&so->ll, &ll, sizeof(ll)); /* set ll_dl for tx path to similar place as for rx */ so->tx.ll_dl = ll.tx_dl; } else { return -EINVAL; } break; default: ret = -ENOPROTOOPT; } return ret; } static int isotp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int ret; if (level != SOL_CAN_ISOTP) return -EINVAL; lock_sock(sk); ret = isotp_setsockopt_locked(sock, level, optname, optval, optlen); release_sock(sk); return ret; } static int isotp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); int len; void *val; if (level != SOL_CAN_ISOTP) return -EINVAL; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case CAN_ISOTP_OPTS: len = min_t(int, len, sizeof(struct can_isotp_options)); val = &so->opt; break; case CAN_ISOTP_RECV_FC: len = min_t(int, len, sizeof(struct can_isotp_fc_options)); val = &so->rxfc; break; case CAN_ISOTP_TX_STMIN: len = min_t(int, len, sizeof(u32)); val = &so->force_tx_stmin; break; case CAN_ISOTP_RX_STMIN: len = min_t(int, len, sizeof(u32)); val = &so->force_rx_stmin; break; case CAN_ISOTP_LL_OPTS: len = min_t(int, len, sizeof(struct can_isotp_ll_options)); val = &so->ll; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, val, len)) return -EFAULT; return 0; } static void isotp_notify(struct isotp_sock *so, unsigned long msg, struct net_device *dev) { struct sock *sk = &so->sk; if (!net_eq(dev_net(dev), sock_net(sk))) return; if (so->ifindex != dev->ifindex) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ if (so->bound) { if (isotp_register_rxid(so)) can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); can_rx_unregister(dev_net(dev), dev, so->txid, SINGLE_MASK(so->txid), isotp_rcv_echo, sk); } so->ifindex = 0; so->bound = 0; release_sock(sk); sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; } } static int isotp_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&isotp_notifier_lock); list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) { spin_unlock(&isotp_notifier_lock); isotp_notify(isotp_busy_notifier, msg, dev); spin_lock(&isotp_notifier_lock); } isotp_busy_notifier = NULL; spin_unlock(&isotp_notifier_lock); return NOTIFY_DONE; } static int isotp_init(struct sock *sk) { struct isotp_sock *so = isotp_sk(sk); so->ifindex = 0; so->bound = 0; so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS; so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; so->opt.rx_ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS; so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; so->frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS; so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN; so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX; so->ll.mtu = CAN_ISOTP_DEFAULT_LL_MTU; so->ll.tx_dl = CAN_ISOTP_DEFAULT_LL_TX_DL; so->ll.tx_flags = CAN_ISOTP_DEFAULT_LL_TX_FLAGS; /* set ll_dl for tx path to similar place as for rx */ so->tx.ll_dl = so->ll.tx_dl; so->rx.state = ISOTP_IDLE; so->tx.state = ISOTP_IDLE; so->rx.buf = so->rx.sbuf; so->tx.buf = so->tx.sbuf; so->rx.buflen = ARRAY_SIZE(so->rx.sbuf); so->tx.buflen = ARRAY_SIZE(so->tx.sbuf); hrtimer_init(&so->rxtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->rxtimer.function = isotp_rx_timer_handler; hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txtimer.function = isotp_tx_timer_handler; hrtimer_init(&so->txfrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txfrtimer.function = isotp_txfr_timer_handler; init_waitqueue_head(&so->wait); spin_lock_init(&so->rx_lock); spin_lock(&isotp_notifier_lock); list_add_tail(&so->notifier, &isotp_notifier_list); spin_unlock(&isotp_notifier_lock); return 0; } static __poll_t isotp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct isotp_sock *so = isotp_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); poll_wait(file, &so->wait, wait); /* Check for false positives due to TX state */ if ((mask & EPOLLWRNORM) && (so->tx.state != ISOTP_IDLE)) mask &= ~(EPOLLOUT | EPOLLWRNORM); return mask; } static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops isotp_ops = { .family = PF_CAN, .release = isotp_release, .bind = isotp_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = isotp_getname, .poll = isotp_poll, .ioctl = isotp_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = isotp_setsockopt, .getsockopt = isotp_getsockopt, .sendmsg = isotp_sendmsg, .recvmsg = isotp_recvmsg, .mmap = sock_no_mmap, }; static struct proto isotp_proto __read_mostly = { .name = "CAN_ISOTP", .owner = THIS_MODULE, .obj_size = sizeof(struct isotp_sock), .init = isotp_init, }; static const struct can_proto isotp_can_proto = { .type = SOCK_DGRAM, .protocol = CAN_ISOTP, .ops = &isotp_ops, .prot = &isotp_proto, }; static struct notifier_block canisotp_notifier = { .notifier_call = isotp_notifier }; static __init int isotp_module_init(void) { int err; max_pdu_size = max_t(unsigned int, max_pdu_size, MAX_12BIT_PDU_SIZE); max_pdu_size = min_t(unsigned int, max_pdu_size, MAX_PDU_SIZE); pr_info("can: isotp protocol (max_pdu_size %d)\n", max_pdu_size); err = can_proto_register(&isotp_can_proto); if (err < 0) pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err)); else register_netdevice_notifier(&canisotp_notifier); return err; } static __exit void isotp_module_exit(void) { can_proto_unregister(&isotp_can_proto); unregister_netdevice_notifier(&canisotp_notifier); } module_init(isotp_module_init); module_exit(isotp_module_exit); |
| 96 83 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 | // SPDX-License-Identifier: GPL-2.0+ /* net/sched/act_ctinfo.c netfilter ctinfo connmark actions * * Copyright (c) 2019 Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk> */ #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 <net/netlink.h> #include <net/pkt_sched.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <uapi/linux/tc_act/tc_ctinfo.h> #include <net/tc_act/tc_ctinfo.h> #include <net/tc_wrapper.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_zones.h> static struct tc_action_ops act_ctinfo_ops; static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct tcf_ctinfo_params *cp, struct sk_buff *skb, int wlen, int proto) { u8 dscp, newdscp; newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & ~INET_ECN_MASK; switch (proto) { case NFPROTO_IPV4: dscp = ipv4_get_dsfield(ip_hdr(skb)) & ~INET_ECN_MASK; if (dscp != newdscp) { if (likely(!skb_try_make_writable(skb, wlen))) { ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, newdscp); ca->stats_dscp_set++; } else { ca->stats_dscp_error++; } } break; case NFPROTO_IPV6: dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK; if (dscp != newdscp) { if (likely(!skb_try_make_writable(skb, wlen))) { ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, newdscp); ca->stats_dscp_set++; } else { ca->stats_dscp_error++; } } break; default: break; } } static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct tcf_ctinfo_params *cp, struct sk_buff *skb) { ca->stats_cpmark_set++; skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; } TC_INDIRECT_SCOPE int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { const struct nf_conntrack_tuple_hash *thash = NULL; struct tcf_ctinfo *ca = to_ctinfo(a); struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; enum ip_conntrack_info ctinfo; struct tcf_ctinfo_params *cp; struct nf_conn *ct; int proto, wlen; int action; cp = rcu_dereference_bh(ca->params); tcf_lastuse_update(&ca->tcf_tm); tcf_action_update_bstats(&ca->common, skb); action = READ_ONCE(ca->tcf_action); wlen = skb_network_offset(skb); switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV4; break; case htons(ETH_P_IPV6): wlen += sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen)) goto out; proto = NFPROTO_IPV6; break; default: goto out; } ct = nf_ct_get(skb, &ctinfo); if (!ct) { /* look harder, usually ingress */ if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, cp->net, &tuple)) goto out; zone.id = cp->zone; zone.dir = NF_CT_DEFAULT_ZONE_DIR; thash = nf_conntrack_find_get(cp->net, &zone, &tuple); if (!thash) goto out; ct = nf_ct_tuplehash_to_ctrack(thash); } if (cp->mode & CTINFO_MODE_DSCP) if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); if (cp->mode & CTINFO_MODE_CPMARK) tcf_ctinfo_cpmark_set(ct, ca, cp, skb); if (thash) nf_ct_put(ct); out: return action; } static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = { [TCA_CTINFO_ACT] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ctinfo)), [TCA_CTINFO_ZONE] = { .type = NLA_U16 }, [TCA_CTINFO_PARMS_DSCP_MASK] = { .type = NLA_U32 }, [TCA_CTINFO_PARMS_DSCP_STATEMASK] = { .type = NLA_U32 }, [TCA_CTINFO_PARMS_CPMARK_MASK] = { .type = NLA_U32 }, }; static int tcf_ctinfo_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_ctinfo_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; u32 dscpmask = 0, dscpstatemask, index; struct nlattr *tb[TCA_CTINFO_MAX + 1]; struct tcf_ctinfo_params *cp_new; struct tcf_chain *goto_ch = NULL; struct tc_ctinfo *actparm; struct tcf_ctinfo *ci; u8 dscpmaskshift; int ret = 0, err; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "ctinfo requires attributes to be passed"); return -EINVAL; } err = nla_parse_nested(tb, TCA_CTINFO_MAX, nla, ctinfo_policy, extack); if (err < 0) return err; if (!tb[TCA_CTINFO_ACT]) { NL_SET_ERR_MSG_MOD(extack, "Missing required TCA_CTINFO_ACT attribute"); return -EINVAL; } actparm = nla_data(tb[TCA_CTINFO_ACT]); /* do some basic validation here before dynamically allocating things */ /* that we would otherwise have to clean up. */ if (tb[TCA_CTINFO_PARMS_DSCP_MASK]) { dscpmask = nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_MASK]); /* need contiguous 6 bit mask */ dscpmaskshift = dscpmask ? __ffs(dscpmask) : 0; if ((~0 & (dscpmask >> dscpmaskshift)) != 0x3f) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CTINFO_PARMS_DSCP_MASK], "dscp mask must be 6 contiguous bits"); return -EINVAL; } dscpstatemask = tb[TCA_CTINFO_PARMS_DSCP_STATEMASK] ? nla_get_u32(tb[TCA_CTINFO_PARMS_DSCP_STATEMASK]) : 0; /* mask & statemask must not overlap */ if (dscpmask & dscpstatemask) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CTINFO_PARMS_DSCP_STATEMASK], "dscp statemask must not overlap dscp mask"); return -EINVAL; } } /* done the validation:now to the actual action allocation */ index = actparm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_ctinfo_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (err > 0) { if (bind) /* don't override defaults */ return ACT_P_BOUND; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } else { return err; } err = tcf_action_check_ctrlact(actparm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; ci = to_ctinfo(*a); cp_new = kzalloc(sizeof(*cp_new), GFP_KERNEL); if (unlikely(!cp_new)) { err = -ENOMEM; goto put_chain; } cp_new->net = net; cp_new->zone = tb[TCA_CTINFO_ZONE] ? nla_get_u16(tb[TCA_CTINFO_ZONE]) : 0; if (dscpmask) { cp_new->dscpmask = dscpmask; cp_new->dscpmaskshift = dscpmaskshift; cp_new->dscpstatemask = dscpstatemask; cp_new->mode |= CTINFO_MODE_DSCP; } if (tb[TCA_CTINFO_PARMS_CPMARK_MASK]) { cp_new->cpmarkmask = nla_get_u32(tb[TCA_CTINFO_PARMS_CPMARK_MASK]); cp_new->mode |= CTINFO_MODE_CPMARK; } spin_lock_bh(&ci->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, actparm->action, goto_ch); cp_new = rcu_replace_pointer(ci->params, cp_new, lockdep_is_held(&ci->tcf_lock)); spin_unlock_bh(&ci->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (cp_new) kfree_rcu(cp_new, rcu); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_ctinfo_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { struct tcf_ctinfo *ci = to_ctinfo(a); struct tc_ctinfo opt = { .index = ci->tcf_index, .refcnt = refcount_read(&ci->tcf_refcnt) - ref, .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, }; unsigned char *b = skb_tail_pointer(skb); struct tcf_ctinfo_params *cp; struct tcf_t t; spin_lock_bh(&ci->tcf_lock); cp = rcu_dereference_protected(ci->params, lockdep_is_held(&ci->tcf_lock)); tcf_tm_dump(&t, &ci->tcf_tm); if (nla_put_64bit(skb, TCA_CTINFO_TM, sizeof(t), &t, TCA_CTINFO_PAD)) goto nla_put_failure; opt.action = ci->tcf_action; if (nla_put(skb, TCA_CTINFO_ACT, sizeof(opt), &opt)) goto nla_put_failure; if (nla_put_u16(skb, TCA_CTINFO_ZONE, cp->zone)) goto nla_put_failure; if (cp->mode & CTINFO_MODE_DSCP) { if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_MASK, cp->dscpmask)) goto nla_put_failure; if (nla_put_u32(skb, TCA_CTINFO_PARMS_DSCP_STATEMASK, cp->dscpstatemask)) goto nla_put_failure; } if (cp->mode & CTINFO_MODE_CPMARK) { if (nla_put_u32(skb, TCA_CTINFO_PARMS_CPMARK_MASK, cp->cpmarkmask)) goto nla_put_failure; } if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_SET, ci->stats_dscp_set, TCA_CTINFO_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_ERROR, ci->stats_dscp_error, TCA_CTINFO_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_CPMARK_SET, ci->stats_cpmark_set, TCA_CTINFO_PAD)) goto nla_put_failure; spin_unlock_bh(&ci->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&ci->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_ctinfo_cleanup(struct tc_action *a) { struct tcf_ctinfo *ci = to_ctinfo(a); struct tcf_ctinfo_params *cp; cp = rcu_dereference_protected(ci->params, 1); if (cp) kfree_rcu(cp, rcu); } static struct tc_action_ops act_ctinfo_ops = { .kind = "ctinfo", .id = TCA_ID_CTINFO, .owner = THIS_MODULE, .act = tcf_ctinfo_act, .dump = tcf_ctinfo_dump, .init = tcf_ctinfo_init, .cleanup= tcf_ctinfo_cleanup, .size = sizeof(struct tcf_ctinfo), }; static __net_init int ctinfo_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_ctinfo_ops.net_id); return tc_action_net_init(net, tn, &act_ctinfo_ops); } static void __net_exit ctinfo_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_ctinfo_ops.net_id); } static struct pernet_operations ctinfo_net_ops = { .init = ctinfo_init_net, .exit_batch = ctinfo_exit_net, .id = &act_ctinfo_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init ctinfo_init_module(void) { return tcf_register_action(&act_ctinfo_ops, &ctinfo_net_ops); } static void __exit ctinfo_cleanup_module(void) { tcf_unregister_action(&act_ctinfo_ops, &ctinfo_net_ops); } module_init(ctinfo_init_module); module_exit(ctinfo_cleanup_module); MODULE_AUTHOR("Kevin Darbyshire-Bryant <ldir@darbyshire-bryant.me.uk>"); MODULE_DESCRIPTION("Connection tracking mark actions"); MODULE_LICENSE("GPL"); |
| 7542 516 2471 2469 2471 215 276 465 471 1594 1595 34 422 388 387 4442 3101 1235 169 270 124 1014 1135 2 379 379 379 374 363 6954 4684 681 1372 379 150 2255 1271 26 1246 32 21 11 1302 9 3 1855 544 1311 5 9 9 1607 1605 37 1606 1262 1170 1261 143 1262 1170 1262 14 9 1 316 578 578 475 475 474 25 327 1262 1262 141 1166 1262 1262 1262 1262 1260 1262 1261 184 1262 1260 1262 1256 578 454 313 1262 1258 213 1262 1262 1243 368 1262 1262 225 225 82 173 178 119 1259 29 2 1262 1262 368 1243 1243 1243 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io */ #include <uapi/linux/btf.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/math64.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) static bool bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) { /* ubuf and len_total should both be specified (or not) together */ if (!!log->ubuf != !!log->len_total) return false; /* log buf without log_level is meaningless */ if (log->ubuf && log->level == 0) return false; if (log->level & ~BPF_LOG_MASK) return false; if (log->len_total > UINT_MAX >> 2) return false; return true; } int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level, char __user *log_buf, u32 log_size) { log->level = log_level; log->ubuf = log_buf; log->len_total = log_size; /* log attributes have to be sane */ if (!bpf_verifier_log_attr_valid(log)) return -EINVAL; return 0; } static void bpf_vlog_update_len_max(struct bpf_verifier_log *log, u32 add_len) { /* add_len includes terminal \0, so no need for +1. */ u64 len = log->end_pos + add_len; /* log->len_max could be larger than our current len due to * bpf_vlog_reset() calls, so we maintain the max of any length at any * previous point */ if (len > UINT_MAX) log->len_max = UINT_MAX; else if (len > log->len_max) log->len_max = len; } void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args) { u64 cur_pos; u32 new_n, n; n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); if (log->level == BPF_LOG_KERNEL) { bool newline = n > 0 && log->kbuf[n - 1] == '\n'; pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); return; } n += 1; /* include terminating zero */ bpf_vlog_update_len_max(log, n); if (log->level & BPF_LOG_FIXED) { /* check if we have at least something to put into user buf */ new_n = 0; if (log->end_pos < log->len_total) { new_n = min_t(u32, log->len_total - log->end_pos, n); log->kbuf[new_n - 1] = '\0'; } cur_pos = log->end_pos; log->end_pos += n - 1; /* don't count terminating '\0' */ if (log->ubuf && new_n && copy_to_user(log->ubuf + cur_pos, log->kbuf, new_n)) goto fail; } else { u64 new_end, new_start; u32 buf_start, buf_end, new_n; new_end = log->end_pos + n; if (new_end - log->start_pos >= log->len_total) new_start = new_end - log->len_total; else new_start = log->start_pos; log->start_pos = new_start; log->end_pos = new_end - 1; /* don't count terminating '\0' */ if (!log->ubuf) return; new_n = min(n, log->len_total); cur_pos = new_end - new_n; div_u64_rem(cur_pos, log->len_total, &buf_start); div_u64_rem(new_end, log->len_total, &buf_end); /* new_end and buf_end are exclusive indices, so if buf_end is * exactly zero, then it actually points right to the end of * ubuf and there is no wrap around */ if (buf_end == 0) buf_end = log->len_total; /* if buf_start > buf_end, we wrapped around; * if buf_start == buf_end, then we fill ubuf completely; we * can't have buf_start == buf_end to mean that there is * nothing to write, because we always write at least * something, even if terminal '\0' */ if (buf_start < buf_end) { /* message fits within contiguous chunk of ubuf */ if (copy_to_user(log->ubuf + buf_start, log->kbuf + n - new_n, buf_end - buf_start)) goto fail; } else { /* message wraps around the end of ubuf, copy in two chunks */ if (copy_to_user(log->ubuf + buf_start, log->kbuf + n - new_n, log->len_total - buf_start)) goto fail; if (copy_to_user(log->ubuf, log->kbuf + n - buf_end, buf_end)) goto fail; } } return; fail: log->ubuf = NULL; } void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos) { char zero = 0; u32 pos; if (WARN_ON_ONCE(new_pos > log->end_pos)) return; if (!bpf_verifier_log_needed(log) || log->level == BPF_LOG_KERNEL) return; /* if position to which we reset is beyond current log window, * then we didn't preserve any useful content and should adjust * start_pos to end up with an empty log (start_pos == end_pos) */ log->end_pos = new_pos; if (log->end_pos < log->start_pos) log->start_pos = log->end_pos; if (!log->ubuf) return; if (log->level & BPF_LOG_FIXED) pos = log->end_pos + 1; else div_u64_rem(new_pos, log->len_total, &pos); if (pos < log->len_total && put_user(zero, log->ubuf + pos)) log->ubuf = NULL; } static void bpf_vlog_reverse_kbuf(char *buf, int len) { int i, j; for (i = 0, j = len - 1; i < j; i++, j--) swap(buf[i], buf[j]); } static int bpf_vlog_reverse_ubuf(struct bpf_verifier_log *log, int start, int end) { /* we split log->kbuf into two equal parts for both ends of array */ int n = sizeof(log->kbuf) / 2, nn; char *lbuf = log->kbuf, *rbuf = log->kbuf + n; /* Read ubuf's section [start, end) two chunks at a time, from left * and right side; within each chunk, swap all the bytes; after that * reverse the order of lbuf and rbuf and write result back to ubuf. * This way we'll end up with swapped contents of specified * [start, end) ubuf segment. */ while (end - start > 1) { nn = min(n, (end - start ) / 2); if (copy_from_user(lbuf, log->ubuf + start, nn)) return -EFAULT; if (copy_from_user(rbuf, log->ubuf + end - nn, nn)) return -EFAULT; bpf_vlog_reverse_kbuf(lbuf, nn); bpf_vlog_reverse_kbuf(rbuf, nn); /* we write lbuf to the right end of ubuf, while rbuf to the * left one to end up with properly reversed overall ubuf */ if (copy_to_user(log->ubuf + start, rbuf, nn)) return -EFAULT; if (copy_to_user(log->ubuf + end - nn, lbuf, nn)) return -EFAULT; start += nn; end -= nn; } return 0; } int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual) { u32 sublen; int err; *log_size_actual = 0; if (!log || log->level == 0 || log->level == BPF_LOG_KERNEL) return 0; if (!log->ubuf) goto skip_log_rotate; /* If we never truncated log, there is nothing to move around. */ if (log->start_pos == 0) goto skip_log_rotate; /* Otherwise we need to rotate log contents to make it start from the * buffer beginning and be a continuous zero-terminated string. Note * that if log->start_pos != 0 then we definitely filled up entire log * buffer with no gaps, and we just need to shift buffer contents to * the left by (log->start_pos % log->len_total) bytes. * * Unfortunately, user buffer could be huge and we don't want to * allocate temporary kernel memory of the same size just to shift * contents in a straightforward fashion. Instead, we'll be clever and * do in-place array rotation. This is a leetcode-style problem, which * could be solved by three rotations. * * Let's say we have log buffer that has to be shifted left by 7 bytes * (spaces and vertical bar is just for demonstrative purposes): * E F G H I J K | A B C D * * First, we reverse entire array: * D C B A | K J I H G F E * * Then we rotate first 4 bytes (DCBA) and separately last 7 bytes * (KJIHGFE), resulting in a properly rotated array: * A B C D | E F G H I J K * * We'll utilize log->kbuf to read user memory chunk by chunk, swap * bytes, and write them back. Doing it byte-by-byte would be * unnecessarily inefficient. Altogether we are going to read and * write each byte twice, for total 4 memory copies between kernel and * user space. */ /* length of the chopped off part that will be the beginning; * len(ABCD) in the example above */ div_u64_rem(log->start_pos, log->len_total, &sublen); sublen = log->len_total - sublen; err = bpf_vlog_reverse_ubuf(log, 0, log->len_total); err = err ?: bpf_vlog_reverse_ubuf(log, 0, sublen); err = err ?: bpf_vlog_reverse_ubuf(log, sublen, log->len_total); if (err) log->ubuf = NULL; skip_log_rotate: *log_size_actual = log->len_max; /* properly initialized log has either both ubuf!=NULL and len_total>0 * or ubuf==NULL and len_total==0, so if this condition doesn't hold, * we got a fault somewhere along the way, so report it back */ if (!!log->ubuf != !!log->len_total) return -EFAULT; /* did truncation actually happen? */ if (log->ubuf && log->len_max > log->len_total) return -ENOSPC; return 0; } /* log_level controls verbosity level of eBPF verifier. * bpf_verifier_log_write() is used to dump the verification trace to the log, * so the user can figure out what's wrong with the program */ __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...) { va_list args; if (!bpf_verifier_log_needed(&env->log)) return; va_start(args, fmt); bpf_verifier_vlog(&env->log, fmt, args); va_end(args); } EXPORT_SYMBOL_GPL(bpf_verifier_log_write); __printf(2, 3) void bpf_log(struct bpf_verifier_log *log, const char *fmt, ...) { va_list args; if (!bpf_verifier_log_needed(log)) return; va_start(args, fmt); bpf_verifier_vlog(log, fmt, args); va_end(args); } EXPORT_SYMBOL_GPL(bpf_log); static const struct bpf_line_info * find_linfo(const struct bpf_verifier_env *env, u32 insn_off) { const struct bpf_line_info *linfo; const struct bpf_prog *prog; u32 i, nr_linfo; prog = env->prog; nr_linfo = prog->aux->nr_linfo; if (!nr_linfo || insn_off >= prog->len) return NULL; linfo = prog->aux->linfo; for (i = 1; i < nr_linfo; i++) if (insn_off < linfo[i].insn_off) break; return &linfo[i - 1]; } static const char *ltrim(const char *s) { while (isspace(*s)) s++; return s; } __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...) { const struct bpf_line_info *linfo; if (!bpf_verifier_log_needed(&env->log)) return; linfo = find_linfo(env, insn_off); if (!linfo || linfo == env->prev_linfo) return; if (prefix_fmt) { va_list args; va_start(args, prefix_fmt); bpf_verifier_vlog(&env->log, prefix_fmt, args); va_end(args); } verbose(env, "%s\n", ltrim(btf_name_by_offset(env->prog->aux->btf, linfo->line_off))); env->prev_linfo = linfo; } static const char *btf_type_name(const struct btf *btf, u32 id) { return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } /* string representation of 'enum bpf_reg_type' * * Note that reg_type_str() can not appear more than once in a single verbose() * statement. */ const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) { char postfix[16] = {0}, prefix[64] = {0}; static const char * const str[] = { [NOT_INIT] = "?", [SCALAR_VALUE] = "scalar", [PTR_TO_CTX] = "ctx", [CONST_PTR_TO_MAP] = "map_ptr", [PTR_TO_MAP_VALUE] = "map_value", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", [PTR_TO_FLOW_KEYS] = "flow_keys", [PTR_TO_SOCKET] = "sock", [PTR_TO_SOCK_COMMON] = "sock_common", [PTR_TO_TCP_SOCK] = "tcp_sock", [PTR_TO_TP_BUFFER] = "tp_buffer", [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_MEM] = "mem", [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_MAP_KEY] = "map_key", [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", }; if (type & PTR_MAYBE_NULL) { if (base_type(type) == PTR_TO_BTF_ID) strncpy(postfix, "or_null_", 16); else strncpy(postfix, "_or_null", 16); } snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", type & MEM_RDONLY ? "rdonly_" : "", type & MEM_RINGBUF ? "ringbuf_" : "", type & MEM_USER ? "user_" : "", type & MEM_PERCPU ? "percpu_" : "", type & MEM_RCU ? "rcu_" : "", type & PTR_UNTRUSTED ? "untrusted_" : "", type & PTR_TRUSTED ? "trusted_" : "" ); snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); return env->tmp_str_buf; } const char *dynptr_type_str(enum bpf_dynptr_type type) { switch (type) { case BPF_DYNPTR_TYPE_LOCAL: return "local"; case BPF_DYNPTR_TYPE_RINGBUF: return "ringbuf"; case BPF_DYNPTR_TYPE_SKB: return "skb"; case BPF_DYNPTR_TYPE_XDP: return "xdp"; case BPF_DYNPTR_TYPE_INVALID: return "<invalid>"; default: WARN_ONCE(1, "unknown dynptr type %d\n", type); return "<unknown>"; } } const char *iter_type_str(const struct btf *btf, u32 btf_id) { if (!btf || btf_id == 0) return "<invalid>"; /* we already validated that type is valid and has conforming name */ return btf_type_name(btf, btf_id) + sizeof(ITER_PREFIX) - 1; } const char *iter_state_str(enum bpf_iter_state state) { switch (state) { case BPF_ITER_STATE_ACTIVE: return "active"; case BPF_ITER_STATE_DRAINED: return "drained"; case BPF_ITER_STATE_INVALID: return "<invalid>"; default: WARN_ONCE(1, "unknown iter state %d\n", state); return "<unknown>"; } } static char slot_type_char[] = { [STACK_INVALID] = '?', [STACK_SPILL] = 'r', [STACK_MISC] = 'm', [STACK_ZERO] = '0', [STACK_DYNPTR] = 'd', [STACK_ITER] = 'i', }; static void print_liveness(struct bpf_verifier_env *env, enum bpf_reg_liveness live) { if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE)) verbose(env, "_"); if (live & REG_LIVE_READ) verbose(env, "r"); if (live & REG_LIVE_WRITTEN) verbose(env, "w"); if (live & REG_LIVE_DONE) verbose(env, "D"); } #define UNUM_MAX_DECIMAL U16_MAX #define SNUM_MAX_DECIMAL S16_MAX #define SNUM_MIN_DECIMAL S16_MIN static bool is_unum_decimal(u64 num) { return num <= UNUM_MAX_DECIMAL; } static bool is_snum_decimal(s64 num) { return num >= SNUM_MIN_DECIMAL && num <= SNUM_MAX_DECIMAL; } static void verbose_unum(struct bpf_verifier_env *env, u64 num) { if (is_unum_decimal(num)) verbose(env, "%llu", num); else verbose(env, "%#llx", num); } static void verbose_snum(struct bpf_verifier_env *env, s64 num) { if (is_snum_decimal(num)) verbose(env, "%lld", num); else verbose(env, "%#llx", num); } int tnum_strn(char *str, size_t size, struct tnum a) { /* print as a constant, if tnum is fully known */ if (a.mask == 0) { if (is_unum_decimal(a.value)) return snprintf(str, size, "%llu", a.value); else return snprintf(str, size, "%#llx", a.value); } return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); } EXPORT_SYMBOL_GPL(tnum_strn); static void print_scalar_ranges(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, const char **sep) { /* For signed ranges, we want to unify 64-bit and 32-bit values in the * output as much as possible, but there is a bit of a complication. * If we choose to print values as decimals, this is natural to do, * because negative 64-bit and 32-bit values >= -S32_MIN have the same * representation due to sign extension. But if we choose to print * them in hex format (see is_snum_decimal()), then sign extension is * misleading. * E.g., smin=-2 and smin32=-2 are exactly the same in decimal, but in * hex they will be smin=0xfffffffffffffffe and smin32=0xfffffffe, two * very different numbers. * So we avoid sign extension if we choose to print values in hex. */ struct { const char *name; u64 val; bool omit; } minmaxs[] = { {"smin", reg->smin_value, reg->smin_value == S64_MIN}, {"smax", reg->smax_value, reg->smax_value == S64_MAX}, {"umin", reg->umin_value, reg->umin_value == 0}, {"umax", reg->umax_value, reg->umax_value == U64_MAX}, {"smin32", is_snum_decimal((s64)reg->s32_min_value) ? (s64)reg->s32_min_value : (u32)reg->s32_min_value, reg->s32_min_value == S32_MIN}, {"smax32", is_snum_decimal((s64)reg->s32_max_value) ? (s64)reg->s32_max_value : (u32)reg->s32_max_value, reg->s32_max_value == S32_MAX}, {"umin32", reg->u32_min_value, reg->u32_min_value == 0}, {"umax32", reg->u32_max_value, reg->u32_max_value == U32_MAX}, }, *m1, *m2, *mend = &minmaxs[ARRAY_SIZE(minmaxs)]; bool neg1, neg2; for (m1 = &minmaxs[0]; m1 < mend; m1++) { if (m1->omit) continue; neg1 = m1->name[0] == 's' && (s64)m1->val < 0; verbose(env, "%s%s=", *sep, m1->name); *sep = ","; for (m2 = m1 + 2; m2 < mend; m2 += 2) { if (m2->omit || m2->val != m1->val) continue; /* don't mix negatives with positives */ neg2 = m2->name[0] == 's' && (s64)m2->val < 0; if (neg2 != neg1) continue; m2->omit = true; verbose(env, "%s=", m2->name); } if (m1->name[0] == 's') verbose_snum(env, m1->val); else verbose_unum(env, m1->val); } } static bool type_is_map_ptr(enum bpf_reg_type t) { switch (base_type(t)) { case CONST_PTR_TO_MAP: case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: return true; default: return false; } } /* * _a stands for append, was shortened to avoid multiline statements below. * This macro is used to output a comma separated list of attributes. */ #define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; }) static void print_reg_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, const struct bpf_reg_state *reg) { enum bpf_reg_type t; const char *sep = ""; t = reg->type; if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) { /* reg->off should be 0 for SCALAR_VALUE */ verbose_snum(env, reg->var_off.value + reg->off); return; } verbose(env, "%s", reg_type_str(env, t)); if (t == PTR_TO_STACK) { if (state->frameno != reg->frameno) verbose(env, "[%d]", reg->frameno); if (tnum_is_const(reg->var_off)) { verbose_snum(env, reg->var_off.value + reg->off); return; } } if (base_type(t) == PTR_TO_BTF_ID) verbose(env, "%s", btf_type_name(reg->btf, reg->btf_id)); verbose(env, "("); if (reg->id) verbose_a("id=%d", reg->id); if (reg->ref_obj_id) verbose_a("ref_obj_id=%d", reg->ref_obj_id); if (type_is_non_owning_ref(reg->type)) verbose_a("%s", "non_own_ref"); if (type_is_map_ptr(t)) { if (reg->map_ptr->name[0]) verbose_a("map=%s", reg->map_ptr->name); verbose_a("ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); } if (t != SCALAR_VALUE && reg->off) { verbose_a("off="); verbose_snum(env, reg->off); } if (type_is_pkt_pointer(t)) { verbose_a("r="); verbose_unum(env, reg->range); } if (base_type(t) == PTR_TO_MEM) { verbose_a("sz="); verbose_unum(env, reg->mem_size); } if (t == CONST_PTR_TO_DYNPTR) verbose_a("type=%s", dynptr_type_str(reg->dynptr.type)); if (tnum_is_const(reg->var_off)) { /* a pointer register with fixed offset */ if (reg->var_off.value) { verbose_a("imm="); verbose_snum(env, reg->var_off.value); } } else { print_scalar_ranges(env, reg, &sep); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose_a("var_off=%s", tn_buf); } } verbose(env, ")"); } void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, bool print_all) { const struct bpf_reg_state *reg; int i; if (state->frameno) verbose(env, " frame%d:", state->frameno); for (i = 0; i < MAX_BPF_REG; i++) { reg = &state->regs[i]; if (reg->type == NOT_INIT) continue; if (!print_all && !reg_scratched(env, i)) continue; verbose(env, " R%d", i); print_liveness(env, reg->live); verbose(env, "="); print_reg_state(env, state, reg); } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { char types_buf[BPF_REG_SIZE + 1]; const char *sep = ""; bool valid = false; u8 slot_type; int j; if (!print_all && !stack_slot_scratched(env, i)) continue; for (j = 0; j < BPF_REG_SIZE; j++) { slot_type = state->stack[i].slot_type[j]; if (slot_type != STACK_INVALID) valid = true; types_buf[j] = slot_type_char[slot_type]; } types_buf[BPF_REG_SIZE] = 0; if (!valid) continue; reg = &state->stack[i].spilled_ptr; switch (state->stack[i].slot_type[BPF_REG_SIZE - 1]) { case STACK_SPILL: /* print MISC/ZERO/INVALID slots above subreg spill */ for (j = 0; j < BPF_REG_SIZE; j++) if (state->stack[i].slot_type[j] == STACK_SPILL) break; types_buf[j] = '\0'; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, reg->live); verbose(env, "=%s", types_buf); print_reg_state(env, state, reg); break; case STACK_DYNPTR: /* skip to main dynptr slot */ i += BPF_DYNPTR_NR_SLOTS - 1; reg = &state->stack[i].spilled_ptr; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, reg->live); verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type)); if (reg->id) verbose_a("id=%d", reg->id); if (reg->ref_obj_id) verbose_a("ref_id=%d", reg->ref_obj_id); if (reg->dynptr_id) verbose_a("dynptr_id=%d", reg->dynptr_id); verbose(env, ")"); break; case STACK_ITER: /* only main slot has ref_obj_id set; skip others */ if (!reg->ref_obj_id) continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, reg->live); verbose(env, "=iter_%s(ref_id=%d,state=%s,depth=%u)", iter_type_str(reg->iter.btf, reg->iter.btf_id), reg->ref_obj_id, iter_state_str(reg->iter.state), reg->iter.depth); break; case STACK_MISC: case STACK_ZERO: default: verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, reg->live); verbose(env, "=%s", types_buf); break; } } if (state->acquired_refs && state->refs[0].id) { verbose(env, " refs=%d", state->refs[0].id); for (i = 1; i < state->acquired_refs; i++) if (state->refs[i].id) verbose(env, ",%d", state->refs[i].id); } if (state->in_callback_fn) verbose(env, " cb"); if (state->in_async_callback_fn) verbose(env, " async_cb"); verbose(env, "\n"); if (!print_all) mark_verifier_state_clean(env); } static inline u32 vlog_alignment(u32 pos) { return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), BPF_LOG_MIN_ALIGNMENT) - pos - 1; } void print_insn_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { if (env->prev_log_pos && env->prev_log_pos == env->log.end_pos) { /* remove new line character */ bpf_vlog_reset(&env->log, env->prev_log_pos - 1); verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_pos), ' '); } else { verbose(env, "%d:", env->insn_idx); } print_verifier_state(env, state, false); } |
| 1666 1666 1666 1666 1666 1666 1666 1666 1666 1630 1666 1666 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org> * * Fixes from William Schumacher incorporated on 15 March 2001. * (Reported by Charles Bertsch, <CBertsch@microtest.com>). */ /* * This file contains generic functions for manipulating * POSIX 1003.1e draft standard 17 ACLs. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/mnt_idmapping.h> #include <linux/iversion.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/fsnotify.h> #include <linux/filelock.h> #include "internal.h" static struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { case ACL_TYPE_ACCESS: return &inode->i_acl; case ACL_TYPE_DEFAULT: return &inode->i_default_acl; default: BUG(); } } struct posix_acl *get_cached_acl(struct inode *inode, int type) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *acl; for (;;) { rcu_read_lock(); acl = rcu_dereference(*p); if (!acl || is_uncached_acl(acl) || refcount_inc_not_zero(&acl->a_refcount)) break; rcu_read_unlock(); cpu_relax(); } rcu_read_unlock(); return acl; } EXPORT_SYMBOL(get_cached_acl); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type)); if (acl == ACL_DONT_CACHE) { struct posix_acl *ret; ret = inode->i_op->get_inode_acl(inode, type, LOOKUP_RCU); if (!IS_ERR(ret)) acl = ret; } return acl; } EXPORT_SYMBOL(get_cached_acl_rcu); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *old; old = xchg(p, posix_acl_dup(acl)); if (!is_uncached_acl(old)) posix_acl_release(old); } EXPORT_SYMBOL(set_cached_acl); static void __forget_cached_acl(struct posix_acl **p) { struct posix_acl *old; old = xchg(p, ACL_NOT_CACHED); if (!is_uncached_acl(old)) posix_acl_release(old); } void forget_cached_acl(struct inode *inode, int type) { __forget_cached_acl(acl_by_type(inode, type)); } EXPORT_SYMBOL(forget_cached_acl); void forget_all_cached_acls(struct inode *inode) { __forget_cached_acl(&inode->i_acl); __forget_cached_acl(&inode->i_default_acl); } EXPORT_SYMBOL(forget_all_cached_acls); static struct posix_acl *__get_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, int type) { struct posix_acl *sentinel; struct posix_acl **p; struct posix_acl *acl; /* * The sentinel is used to detect when another operation like * set_cached_acl() or forget_cached_acl() races with get_inode_acl(). * It is guaranteed that is_uncached_acl(sentinel) is true. */ acl = get_cached_acl(inode, type); if (!is_uncached_acl(acl)) return acl; if (!IS_POSIXACL(inode)) return NULL; sentinel = uncached_acl_sentinel(current); p = acl_by_type(inode, type); /* * If the ACL isn't being read yet, set our sentinel. Otherwise, the * current value of the ACL will not be ACL_NOT_CACHED and so our own * sentinel will not be set; another task will update the cache. We * could wait for that other task to complete its job, but it's easier * to just call ->get_inode_acl to fetch the ACL ourself. (This is * going to be an unlikely race.) */ cmpxchg(p, ACL_NOT_CACHED, sentinel); /* * Normally, the ACL returned by ->get{_inode}_acl will be cached. * A filesystem can prevent that by calling * forget_cached_acl(inode, type) in ->get{_inode}_acl. * * If the filesystem doesn't have a get{_inode}_ acl() function at all, * we'll just create the negative cache entry. */ if (dentry && inode->i_op->get_acl) { acl = inode->i_op->get_acl(idmap, dentry, type); } else if (inode->i_op->get_inode_acl) { acl = inode->i_op->get_inode_acl(inode, type, false); } else { set_cached_acl(inode, type, NULL); return NULL; } if (IS_ERR(acl)) { /* * Remove our sentinel so that we don't block future attempts * to cache the ACL. */ cmpxchg(p, sentinel, ACL_NOT_CACHED); return acl; } /* * Cache the result, but only if our sentinel is still in place. */ posix_acl_dup(acl); if (unlikely(!try_cmpxchg(p, &sentinel, acl))) posix_acl_release(acl); return acl; } struct posix_acl *get_inode_acl(struct inode *inode, int type) { return __get_acl(&nop_mnt_idmap, NULL, inode, type); } EXPORT_SYMBOL(get_inode_acl); /* * Init a fresh posix_acl */ void posix_acl_init(struct posix_acl *acl, int count) { refcount_set(&acl->a_refcount, 1); acl->a_count = count; } EXPORT_SYMBOL(posix_acl_init); /* * Allocate a new ACL with the specified number of entries. */ struct posix_acl * posix_acl_alloc(int count, gfp_t flags) { const size_t size = sizeof(struct posix_acl) + count * sizeof(struct posix_acl_entry); struct posix_acl *acl = kmalloc(size, flags); if (acl) posix_acl_init(acl, count); return acl; } EXPORT_SYMBOL(posix_acl_alloc); /* * Clone an ACL. */ struct posix_acl * posix_acl_clone(const struct posix_acl *acl, gfp_t flags) { struct posix_acl *clone = NULL; if (acl) { int size = sizeof(struct posix_acl) + acl->a_count * sizeof(struct posix_acl_entry); clone = kmemdup(acl, size, flags); if (clone) refcount_set(&clone->a_refcount, 1); } return clone; } EXPORT_SYMBOL_GPL(posix_acl_clone); /* * Check if an acl is valid. Returns 0 if it is, or -E... otherwise. */ int posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl) { const struct posix_acl_entry *pa, *pe; int state = ACL_USER_OBJ; int needs_mask = 0; FOREACH_ACL_ENTRY(pa, acl, pe) { if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE)) return -EINVAL; switch (pa->e_tag) { case ACL_USER_OBJ: if (state == ACL_USER_OBJ) { state = ACL_USER; break; } return -EINVAL; case ACL_USER: if (state != ACL_USER) return -EINVAL; if (!kuid_has_mapping(user_ns, pa->e_uid)) return -EINVAL; needs_mask = 1; break; case ACL_GROUP_OBJ: if (state == ACL_USER) { state = ACL_GROUP; break; } return -EINVAL; case ACL_GROUP: if (state != ACL_GROUP) return -EINVAL; if (!kgid_has_mapping(user_ns, pa->e_gid)) return -EINVAL; needs_mask = 1; break; case ACL_MASK: if (state != ACL_GROUP) return -EINVAL; state = ACL_OTHER; break; case ACL_OTHER: if (state == ACL_OTHER || (state == ACL_GROUP && !needs_mask)) { state = 0; break; } return -EINVAL; default: return -EINVAL; } } if (state == 0) return 0; return -EINVAL; } EXPORT_SYMBOL(posix_acl_valid); /* * Returns 0 if the acl can be exactly represented in the traditional * file mode permission bits, or else 1. Returns -E... on error. */ int posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) { const struct posix_acl_entry *pa, *pe; umode_t mode = 0; int not_equiv = 0; /* * A null ACL can always be presented as mode bits. */ if (!acl) return 0; FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: mode |= (pa->e_perm & S_IRWXO) << 6; break; case ACL_GROUP_OBJ: mode |= (pa->e_perm & S_IRWXO) << 3; break; case ACL_OTHER: mode |= pa->e_perm & S_IRWXO; break; case ACL_MASK: mode = (mode & ~S_IRWXG) | ((pa->e_perm & S_IRWXO) << 3); not_equiv = 1; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; default: return -EINVAL; } } if (mode_p) *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } EXPORT_SYMBOL(posix_acl_equiv_mode); /* * Create an ACL representing the file mode permission bits of an inode. */ struct posix_acl * posix_acl_from_mode(umode_t mode, gfp_t flags) { struct posix_acl *acl = posix_acl_alloc(3, flags); if (!acl) return ERR_PTR(-ENOMEM); acl->a_entries[0].e_tag = ACL_USER_OBJ; acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6; acl->a_entries[1].e_tag = ACL_GROUP_OBJ; acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3; acl->a_entries[2].e_tag = ACL_OTHER; acl->a_entries[2].e_perm = (mode & S_IRWXO); return acl; } EXPORT_SYMBOL(posix_acl_from_mode); /* * Return 0 if current is granted want access to the inode * by the acl. Returns -E... otherwise. */ int posix_acl_permission(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; want &= MAY_READ | MAY_WRITE | MAY_EXEC; FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto check_perm; break; case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; break; case ACL_GROUP_OBJ: vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_MASK: break; case ACL_OTHER: if (found) return -EACCES; else goto check_perm; default: return -EIO; } } return -EIO; mask: for (mask_obj = pa+1; mask_obj != pe; mask_obj++) { if (mask_obj->e_tag == ACL_MASK) { if ((pa->e_perm & mask_obj->e_perm & want) == want) return 0; return -EACCES; } } check_perm: if ((pa->e_perm & want) == want) return 0; return -EACCES; } /* * Modify acl when creating a new inode. The caller must ensure the acl is * only referenced once. * * mode_p initially must contain the mode parameter to the open() / creat() * system calls. All permissions that are not granted by the acl are removed. * The permissions in the acl are changed to reflect the mode_p parameter. */ static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_OTHER: pa->e_perm &= mode | ~S_IRWXO; mode &= pa->e_perm | ~S_IRWXO; break; case ACL_MASK: mask_obj = pa; not_equiv = 1; break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; } else { if (!group_obj) return -EIO; group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (group_obj->e_perm << 3) | ~S_IRWXG; } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } /* * Modify the ACL for the chmod syscall. */ static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode) { struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; struct posix_acl_entry *pa, *pe; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm = (mode & S_IRWXU) >> 6; break; case ACL_USER: case ACL_GROUP: break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_MASK: mask_obj = pa; break; case ACL_OTHER: pa->e_perm = (mode & S_IRWXO); break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm = (mode & S_IRWXG) >> 3; } else { if (!group_obj) return -EIO; group_obj->e_perm = (mode & S_IRWXG) >> 3; } return 0; } int __posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = posix_acl_create_masq(clone, mode_p); if (err < 0) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_create); int __posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = __posix_acl_chmod_masq(clone, mode); if (err) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_chmod); /** * posix_acl_chmod - chmod a posix acl * * @idmap: idmap of the mount @inode was found from * @dentry: dentry to check permissions on * @mode: the new mode of @inode * * If the dentry has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int ret = 0; if (!IS_POSIXACL(inode)) return 0; if (!inode->i_op->set_acl) return -EOPNOTSUPP; acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR_OR_NULL(acl)) { if (acl == ERR_PTR(-EOPNOTSUPP)) return 0; return PTR_ERR(acl); } ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) return ret; ret = inode->i_op->set_acl(idmap, dentry, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); return ret; } EXPORT_SYMBOL(posix_acl_chmod); int posix_acl_create(struct inode *dir, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { struct posix_acl *p; struct posix_acl *clone; int ret; *acl = NULL; *default_acl = NULL; if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) return 0; p = get_inode_acl(dir, ACL_TYPE_DEFAULT); if (!p || p == ERR_PTR(-EOPNOTSUPP)) { *mode &= ~current_umask(); return 0; } if (IS_ERR(p)) return PTR_ERR(p); ret = -ENOMEM; clone = posix_acl_clone(p, GFP_NOFS); if (!clone) goto err_release; ret = posix_acl_create_masq(clone, mode); if (ret < 0) goto err_release_clone; if (ret == 0) posix_acl_release(clone); else *acl = clone; if (!S_ISDIR(*mode)) posix_acl_release(p); else *default_acl = p; return 0; err_release_clone: posix_acl_release(clone); err_release: posix_acl_release(p); return ret; } EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl * @idmap: idmap of the mount @inode was found from * @inode: target inode * @mode_p: mode (pointer) for update * @acl: acl pointer * * Update the file mode when setting an ACL: compute the new file permission * bits based on the ACL. In addition, if the ACL is equivalent to the new * file mode, set *@acl to NULL to indicate that no ACL should be set. * * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Called from set_acl inode operations. */ int posix_acl_update_mode(struct mnt_idmap *idmap, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { umode_t mode = inode->i_mode; int error; error = posix_acl_equiv_mode(*acl, &mode); if (error < 0) return error; if (error == 0) *acl = NULL; if (!vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)) && !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID)) mode &= ~S_ISGID; *mode_p = mode; return 0; } EXPORT_SYMBOL(posix_acl_update_mode); /* * Fix up the uids and gids in posix acl extended attributes in place. */ static int posix_acl_fix_xattr_common(const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; int count; if (!header) return -EINVAL; if (size < sizeof(struct posix_acl_xattr_header)) return -EINVAL; if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION)) return -EOPNOTSUPP; count = posix_acl_xattr_count(size); if (count < 0) return -EINVAL; if (count == 0) return 0; return count; } /** * posix_acl_from_xattr - convert POSIX ACLs from backing store to VFS format * @userns: the filesystem's idmapping * @value: the uapi representation of POSIX ACLs * @size: the size of @void * * Filesystems that store POSIX ACLs in the unaltered uapi format should use * posix_acl_from_xattr() when reading them from the backing store and * converting them into the struct posix_acl VFS format. The helper is * specifically intended to be called from the acl inode operation. * * The posix_acl_from_xattr() function will map the raw {g,u}id values stored * in ACL_{GROUP,USER} entries into idmapping in @userns. * * Note that posix_acl_from_xattr() does not take idmapped mounts into account. * If it did it calling it from the get acl inode operation would return POSIX * ACLs mapped according to an idmapped mount which would mean that the value * couldn't be cached for the filesystem. Idmapped mounts are taken into * account on the fly during permission checking or right at the VFS - * userspace boundary before reporting them to the user. * * Return: Allocated struct posix_acl on success, NULL for a valid header but * without actual POSIX ACL entries, or ERR_PTR() encoded error code. */ struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns, const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end; int count; struct posix_acl *acl; struct posix_acl_entry *acl_e; count = posix_acl_fix_xattr_common(value, size); if (count < 0) return ERR_PTR(count); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); acl_e = acl->a_entries; for (end = entry + count; entry != end; acl_e++, entry++) { acl_e->e_tag = le16_to_cpu(entry->e_tag); acl_e->e_perm = le16_to_cpu(entry->e_perm); switch(acl_e->e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: break; case ACL_USER: acl_e->e_uid = make_kuid(userns, le32_to_cpu(entry->e_id)); if (!uid_valid(acl_e->e_uid)) goto fail; break; case ACL_GROUP: acl_e->e_gid = make_kgid(userns, le32_to_cpu(entry->e_id)); if (!gid_valid(acl_e->e_gid)) goto fail; break; default: goto fail; } } return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL (posix_acl_from_xattr); /* * Convert from in-memory to extended attribute representation. */ int posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; int real_size, n; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: ext_entry->e_id = cpu_to_le32(from_kuid(user_ns, acl_e->e_uid)); break; case ACL_GROUP: ext_entry->e_id = cpu_to_le32(from_kgid(user_ns, acl_e->e_gid)); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } EXPORT_SYMBOL (posix_acl_to_xattr); /** * vfs_posix_acl_to_xattr - convert from kernel to userspace representation * @idmap: idmap of the mount * @inode: inode the posix acls are set on * @acl: the posix acls as represented by the vfs * @buffer: the buffer into which to convert @acl * @size: size of @buffer * * This converts @acl from the VFS representation in the filesystem idmapping * to the uapi form reportable to userspace. And mount and caller idmappings * are handled appropriately. * * Return: On success, the size of the stored uapi posix acls, on error a * negative errno. */ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; struct user_namespace *fs_userns, *caller_userns; ssize_t real_size, n; vfsuid_t vfsuid; vfsgid_t vfsgid; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); fs_userns = i_user_ns(inode); caller_userns = current_user_ns(); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, acl_e->e_uid); ext_entry->e_id = cpu_to_le32(from_kuid( caller_userns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, acl_e->e_gid); ext_entry->e_id = cpu_to_le32(from_kgid( caller_userns, vfsgid_into_kgid(vfsgid))); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } int set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type, struct posix_acl *acl) { struct inode *inode = d_inode(dentry); if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) return -EOPNOTSUPP; if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (acl) { int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl); if (ret) return ret; } return inode->i_op->set_acl(idmap, dentry, acl, type); } EXPORT_SYMBOL(set_posix_acl); int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size) { int err; if (!IS_POSIXACL(inode)) return 0; if (inode->i_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_ACCESS); if (err) return err; } if (inode->i_default_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_DEFAULT); if (err) return err; } return 0; } static bool posix_acl_xattr_list(struct dentry *dentry) { return IS_POSIXACL(d_backing_inode(dentry)); } /* * nop_posix_acl_access - legacy xattr handler for access POSIX ACLs * * This is the legacy POSIX ACL access xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_access = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_access); /* * nop_posix_acl_default - legacy xattr handler for default POSIX ACLs * * This is the legacy POSIX ACL default xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_default = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_default); int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error; struct inode *inode = d_inode(dentry); if (type == ACL_TYPE_ACCESS) { error = posix_acl_update_mode(idmap, inode, &inode->i_mode, &acl); if (error) return error; } inode_set_ctime_current(inode); if (IS_I_VERSION(inode)) inode_inc_iversion(inode); set_cached_acl(inode, type, acl); return 0; } int simple_acl_create(struct inode *dir, struct inode *inode) { struct posix_acl *default_acl, *acl; int error; error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (error) return error; set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl); set_cached_acl(inode, ACL_TYPE_ACCESS, acl); if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); return 0; } static int vfs_set_acl_idmapped_mnt(struct mnt_idmap *idmap, struct user_namespace *fs_userns, struct posix_acl *acl) { for (int n = 0; n < acl->a_count; n++) { struct posix_acl_entry *acl_e = &acl->a_entries[n]; switch (acl_e->e_tag) { case ACL_USER: acl_e->e_uid = from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(acl_e->e_uid)); break; case ACL_GROUP: acl_e->e_gid = from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(acl_e->e_gid)); break; } } return 0; } /** * vfs_set_acl - set posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to set the posix acls * @acl_name: the name of the posix acl * @kacl: the posix acls in the appropriate VFS format * * This function sets @kacl. The caller must all posix_acl_release() on @kacl * afterwards. * * Return: On success 0, on error negative errno. */ int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct inode *delegated_inode = NULL; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; if (kacl) { /* * If we're on an idmapped mount translate from mount specific * vfs{g,u}id_t into global filesystem k{g,u}id_t. * Afterwards we can cache the POSIX ACLs filesystem wide and - * if this is a filesystem with a backing store - ultimately * translate them to backing store values. */ error = vfs_set_acl_idmapped_mnt(idmap, i_user_ns(inode), kacl); if (error) return error; } retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_set_acl(idmap, dentry, acl_name, kacl); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, kacl); else error = -EIO; if (!error) { fsnotify_xattr(dentry); evm_inode_post_set_acl(dentry, acl_name, kacl); } out_inode_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_set_acl); /** * vfs_get_acl - get posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function retrieves @kacl from the filesystem. The caller must all * posix_acl_release() on @kacl. * * Return: On success POSIX ACLs in VFS format, on error negative errno. */ struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int acl_type, error; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return ERR_PTR(-EINVAL); /* * The VFS has no restrictions on reading POSIX ACLs so calling * something like xattr_permission() isn't needed. Only LSMs get a say. */ error = security_inode_get_acl(idmap, dentry, acl_name); if (error) return ERR_PTR(error); if (!IS_POSIXACL(inode)) return ERR_PTR(-EOPNOTSUPP); if (S_ISLNK(inode->i_mode)) return ERR_PTR(-EOPNOTSUPP); acl = __get_acl(idmap, dentry, inode, acl_type); if (IS_ERR(acl)) return acl; if (!acl) return ERR_PTR(-ENODATA); return acl; } EXPORT_SYMBOL_GPL(vfs_get_acl); /** * vfs_remove_acl - remove posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function removes posix acls. * * Return: On success 0, on error negative errno. */ int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct inode *delegated_inode = NULL; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_remove_acl(idmap, dentry, acl_name); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, NULL); else error = -EIO; if (!error) { fsnotify_xattr(dentry); evm_inode_post_remove_acl(idmap, dentry, acl_name); } out_inode_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_remove_acl); int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { int error; struct posix_acl *acl = NULL; if (size) { /* * Note that posix_acl_from_xattr() uses GFP_NOFS when it * probably doesn't need to here. */ acl = posix_acl_from_xattr(current_user_ns(), kvalue, size); if (IS_ERR(acl)) return PTR_ERR(acl); } error = vfs_set_acl(idmap, dentry, acl_name, acl); posix_acl_release(acl); return error; } ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { ssize_t error; struct posix_acl *acl; acl = vfs_get_acl(idmap, dentry, acl_name); if (IS_ERR(acl)) return PTR_ERR(acl); error = vfs_posix_acl_to_xattr(idmap, d_inode(dentry), acl, kvalue, size); posix_acl_release(acl); return error; } |
| 2132 2131 1041 1041 536 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Monitoring code for network dropped packet alerts * * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/netlink.h> #include <linux/net_dropmon.h> #include <linux/bitfield.h> #include <linux/percpu.h> #include <linux/timer.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/module.h> #include <net/genetlink.h> #include <net/netevent.h> #include <net/flow_offload.h> #include <net/dropreason.h> #include <net/devlink.h> #include <trace/events/skb.h> #include <trace/events/napi.h> #include <trace/events/devlink.h> #include <asm/unaligned.h> #define TRACE_ON 1 #define TRACE_OFF 0 /* * Globals, our netlink socket pointer * and the work handle that will send up * netlink alerts */ static int trace_state = TRACE_OFF; static bool monitor_hw; /* net_dm_mutex * * An overall lock guarding every operation coming from userspace. */ static DEFINE_MUTEX(net_dm_mutex); struct net_dm_stats { u64_stats_t dropped; struct u64_stats_sync syncp; }; #define NET_DM_MAX_HW_TRAP_NAME_LEN 40 struct net_dm_hw_entry { char trap_name[NET_DM_MAX_HW_TRAP_NAME_LEN]; u32 count; }; struct net_dm_hw_entries { u32 num_entries; struct net_dm_hw_entry entries[]; }; struct per_cpu_dm_data { spinlock_t lock; /* Protects 'skb', 'hw_entries' and * 'send_timer' */ union { struct sk_buff *skb; struct net_dm_hw_entries *hw_entries; }; struct sk_buff_head drop_queue; struct work_struct dm_alert_work; struct timer_list send_timer; struct net_dm_stats stats; }; struct dm_hw_stat_delta { unsigned long last_rx; unsigned long last_drop_val; struct rcu_head rcu; }; static struct genl_family net_drop_monitor_family; static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_hw_cpu_data); static int dm_hit_limit = 64; static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static enum net_dm_alert_mode net_dm_alert_mode = NET_DM_ALERT_MODE_SUMMARY; static u32 net_dm_trunc_len; static u32 net_dm_queue_len = 1000; struct net_dm_alert_ops { void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason); void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, int work, int budget); void (*work_item_func)(struct work_struct *work); void (*hw_work_item_func)(struct work_struct *work); void (*hw_trap_probe)(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata); }; struct net_dm_skb_cb { union { struct devlink_trap_metadata *hw_metadata; void *pc; }; enum skb_drop_reason reason; }; #define NET_DM_SKB_CB(__skb) ((struct net_dm_skb_cb *)&((__skb)->cb[0])) static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; struct sk_buff *skb; unsigned long flags; void *msg_header; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); al += sizeof(struct nlattr); skb = genlmsg_new(al, GFP_KERNEL); if (!skb) goto err; msg_header = genlmsg_put(skb, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); if (!msg_header) { nlmsg_free(skb); skb = NULL; goto err; } nla = nla_reserve(skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg)); if (!nla) { nlmsg_free(skb); skb = NULL; goto err; } msg = nla_data(nla); memset(msg, 0, al); goto out; err: mod_timer(&data->send_timer, jiffies + HZ / 10); out: spin_lock_irqsave(&data->lock, flags); swap(data->skb, skb); spin_unlock_irqrestore(&data->lock, flags); if (skb) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb->data; struct genlmsghdr *gnlh = (struct genlmsghdr *)nlmsg_data(nlh); genlmsg_end(skb, genlmsg_data(gnlh)); } return skb; } static const struct genl_multicast_group dropmon_mcgrps[] = { { .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, }, }; static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; struct per_cpu_dm_data *data; data = container_of(work, struct per_cpu_dm_data, dm_alert_work); skb = reset_per_cpu_data(data); if (skb) genlmsg_multicast(&net_drop_monitor_family, skb, 0, 0, GFP_KERNEL); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the * hysteresis period. */ static void sched_send_work(struct timer_list *t) { struct per_cpu_dm_data *data = from_timer(data, t, send_timer); schedule_work(&data->dm_alert_work); } static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; struct net_dm_drop_point *point; struct nlmsghdr *nlh; struct nlattr *nla; int i; struct sk_buff *dskb; struct per_cpu_dm_data *data; unsigned long flags; local_irq_save(flags); data = this_cpu_ptr(&dm_cpu_data); spin_lock(&data->lock); dskb = data->skb; if (!dskb) goto out; nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); point = msg->points; for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, &point->pc, sizeof(void *))) { point->count++; goto out; } point++; } if (msg->entries == dm_hit_limit) goto out; /* * We need to create a new entry */ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); memcpy(point->pc, &location, sizeof(void *)); point->count = 1; msg->entries++; if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; add_timer(&data->send_timer); } out: spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason) { trace_drop_common(skb, location); } static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, int work, int budget) { struct net_device *dev = napi->dev; struct dm_hw_stat_delta *stat; /* * Don't check napi structures with no associated device */ if (!dev) return; rcu_read_lock(); stat = rcu_dereference(dev->dm_private); if (stat) { /* * only add a note to our monitor buffer if: * 1) its after the last_rx delta * 2) our rx_dropped count has gone up */ if (time_after(jiffies, stat->last_rx + dm_hw_check_delta) && (dev->stats.rx_dropped != stat->last_drop_val)) { trace_drop_common(NULL, NULL); stat->last_drop_val = dev->stats.rx_dropped; stat->last_rx = jiffies; } } rcu_read_unlock(); } static struct net_dm_hw_entries * net_dm_hw_reset_per_cpu_data(struct per_cpu_dm_data *hw_data) { struct net_dm_hw_entries *hw_entries; unsigned long flags; hw_entries = kzalloc(struct_size(hw_entries, entries, dm_hit_limit), GFP_KERNEL); if (!hw_entries) { /* If the memory allocation failed, we try to perform another * allocation in 1/10 second. Otherwise, the probe function * will constantly bail out. */ mod_timer(&hw_data->send_timer, jiffies + HZ / 10); } spin_lock_irqsave(&hw_data->lock, flags); swap(hw_data->hw_entries, hw_entries); spin_unlock_irqrestore(&hw_data->lock, flags); return hw_entries; } static int net_dm_hw_entry_put(struct sk_buff *msg, const struct net_dm_hw_entry *hw_entry) { struct nlattr *attr; attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRY); if (!attr) return -EMSGSIZE; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_entry->trap_name)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_HW_TRAP_COUNT, hw_entry->count)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_hw_entries_put(struct sk_buff *msg, const struct net_dm_hw_entries *hw_entries) { struct nlattr *attr; int i; attr = nla_nest_start(msg, NET_DM_ATTR_HW_ENTRIES); if (!attr) return -EMSGSIZE; for (i = 0; i < hw_entries->num_entries; i++) { int rc; rc = net_dm_hw_entry_put(msg, &hw_entries->entries[i]); if (rc) goto nla_put_failure; } nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_hw_summary_report_fill(struct sk_buff *msg, const struct net_dm_hw_entries *hw_entries) { struct net_dm_alert_msg anc_hdr = { 0 }; void *hdr; int rc; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_ALERT); if (!hdr) return -EMSGSIZE; /* We need to put the ancillary header in order not to break user * space. */ if (nla_put(msg, NLA_UNSPEC, sizeof(anc_hdr), &anc_hdr)) goto nla_put_failure; rc = net_dm_hw_entries_put(msg, hw_entries); if (rc) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void net_dm_hw_summary_work(struct work_struct *work) { struct net_dm_hw_entries *hw_entries; struct per_cpu_dm_data *hw_data; struct sk_buff *msg; int rc; hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); if (!hw_entries) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) goto out; rc = net_dm_hw_summary_report_fill(msg, hw_entries); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: kfree(hw_entries); } static void net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata) { struct net_dm_hw_entries *hw_entries; struct net_dm_hw_entry *hw_entry; struct per_cpu_dm_data *hw_data; unsigned long flags; int i; if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) return; hw_data = this_cpu_ptr(&dm_hw_cpu_data); spin_lock_irqsave(&hw_data->lock, flags); hw_entries = hw_data->hw_entries; if (!hw_entries) goto out; for (i = 0; i < hw_entries->num_entries; i++) { hw_entry = &hw_entries->entries[i]; if (!strncmp(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) { hw_entry->count++; goto out; } } if (WARN_ON_ONCE(hw_entries->num_entries == dm_hit_limit)) goto out; hw_entry = &hw_entries->entries[hw_entries->num_entries]; strscpy(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1); hw_entry->count = 1; hw_entries->num_entries++; if (!timer_pending(&hw_data->send_timer)) { hw_data->send_timer.expires = jiffies + dm_delay * HZ; add_timer(&hw_data->send_timer); } out: spin_unlock_irqrestore(&hw_data->lock, flags); } static const struct net_dm_alert_ops net_dm_alert_summary_ops = { .kfree_skb_probe = trace_kfree_skb_hit, .napi_poll_probe = trace_napi_poll_hit, .work_item_func = send_dm_alert, .hw_work_item_func = net_dm_hw_summary_work, .hw_trap_probe = net_dm_hw_trap_summary_probe, }; static void net_dm_packet_trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, enum skb_drop_reason reason) { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; struct net_dm_skb_cb *cb; struct sk_buff *nskb; unsigned long flags; if (!skb_mac_header_was_set(skb)) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; cb = NET_DM_SKB_CB(nskb); cb->reason = reason; cb->pc = location; /* Override the timestamp because we care about the time when the * packet was dropped. */ nskb->tstamp = tstamp; data = this_cpu_ptr(&dm_cpu_data); spin_lock_irqsave(&data->drop_queue.lock, flags); if (skb_queue_len(&data->drop_queue) < net_dm_queue_len) __skb_queue_tail(&data->drop_queue, nskb); else goto unlock_free; spin_unlock_irqrestore(&data->drop_queue.lock, flags); schedule_work(&data->dm_alert_work); return; unlock_free: spin_unlock_irqrestore(&data->drop_queue.lock, flags); u64_stats_update_begin(&data->stats.syncp); u64_stats_inc(&data->stats.dropped); u64_stats_update_end(&data->stats.syncp); consume_skb(nskb); } static void net_dm_packet_trace_napi_poll_hit(void *ignore, struct napi_struct *napi, int work, int budget) { } static size_t net_dm_in_port_size(void) { /* NET_DM_ATTR_IN_PORT nest */ return nla_total_size(0) + /* NET_DM_ATTR_PORT_NETDEV_IFINDEX */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PORT_NETDEV_NAME */ nla_total_size(IFNAMSIZ + 1); } #define NET_DM_MAX_SYMBOL_LEN 40 #define NET_DM_MAX_REASON_LEN 50 static size_t net_dm_packet_report_size(size_t payload_len) { size_t size; size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); return NLMSG_ALIGN(size) + /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PC */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_SYMBOL */ nla_total_size(NET_DM_MAX_SYMBOL_LEN + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_REASON */ nla_total_size(NET_DM_MAX_REASON_LEN + 1) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } static int net_dm_packet_report_in_port_put(struct sk_buff *msg, int ifindex, const char *name) { struct nlattr *attr; attr = nla_nest_start(msg, NET_DM_ATTR_IN_PORT); if (!attr) return -EMSGSIZE; if (ifindex && nla_put_u32(msg, NET_DM_ATTR_PORT_NETDEV_IFINDEX, ifindex)) goto nla_put_failure; if (name && nla_put_string(msg, NET_DM_ATTR_PORT_NETDEV_NAME, name)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { struct net_dm_skb_cb *cb = NET_DM_SKB_CB(skb); const struct drop_reason_list *list = NULL; unsigned int subsys, subsys_reason; char buf[NET_DM_MAX_SYMBOL_LEN]; struct nlattr *attr; void *hdr; int rc; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_PACKET_ALERT); if (!hdr) return -EMSGSIZE; if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_SW)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_PC, (u64)(uintptr_t)cb->pc, NET_DM_ATTR_PAD)) goto nla_put_failure; rcu_read_lock(); subsys = u32_get_bits(cb->reason, SKB_DROP_REASON_SUBSYS_MASK); if (subsys < SKB_DROP_REASON_SUBSYS_NUM) list = rcu_dereference(drop_reasons_by_subsys[subsys]); subsys_reason = cb->reason & ~SKB_DROP_REASON_SUBSYS_MASK; if (!list || subsys_reason >= list->n_reasons || !list->reasons[subsys_reason] || strlen(list->reasons[subsys_reason]) > NET_DM_MAX_REASON_LEN) { list = rcu_dereference(drop_reasons_by_subsys[SKB_DROP_REASON_SUBSYS_CORE]); subsys_reason = SKB_DROP_REASON_NOT_SPECIFIED; } if (nla_put_string(msg, NET_DM_ATTR_REASON, list->reasons[subsys_reason])) { rcu_read_unlock(); goto nla_put_failure; } rcu_read_unlock(); snprintf(buf, sizeof(buf), "%pS", cb->pc); if (nla_put_string(msg, NET_DM_ATTR_SYMBOL, buf)) goto nla_put_failure; rc = net_dm_packet_report_in_port_put(msg, skb->skb_iif, NULL); if (rc) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) goto nla_put_failure; if (!payload_len) goto out; if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; attr = skb_put(msg, nla_total_size(payload_len)); attr->nla_type = NET_DM_ATTR_PAYLOAD; attr->nla_len = nla_attr_size(payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } #define NET_DM_MAX_PACKET_SIZE (0xffff - NLA_HDRLEN - NLA_ALIGNTO) static void net_dm_packet_report(struct sk_buff *skb) { struct sk_buff *msg; size_t payload_len; int rc; /* Make sure we start copying the packet from the MAC header */ if (skb->data > skb_mac_header(skb)) skb_push(skb, skb->data - skb_mac_header(skb)); else skb_pull(skb, skb_mac_header(skb) - skb->data); /* Ensure packet fits inside a single netlink attribute */ payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); msg = nlmsg_new(net_dm_packet_report_size(payload_len), GFP_KERNEL); if (!msg) goto out; rc = net_dm_packet_report_fill(msg, skb, payload_len); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: consume_skb(skb); } static void net_dm_packet_work(struct work_struct *work) { struct per_cpu_dm_data *data; struct sk_buff_head list; struct sk_buff *skb; unsigned long flags; data = container_of(work, struct per_cpu_dm_data, dm_alert_work); __skb_queue_head_init(&list); spin_lock_irqsave(&data->drop_queue.lock, flags); skb_queue_splice_tail_init(&data->drop_queue, &list); spin_unlock_irqrestore(&data->drop_queue.lock, flags); while ((skb = __skb_dequeue(&list))) net_dm_packet_report(skb); } static size_t net_dm_flow_action_cookie_size(const struct devlink_trap_metadata *hw_metadata) { return hw_metadata->fa_cookie ? nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; } static size_t net_dm_hw_packet_report_size(size_t payload_len, const struct devlink_trap_metadata *hw_metadata) { size_t size; size = nlmsg_msg_size(GENL_HDRLEN + net_drop_monitor_family.hdrsize); return NLMSG_ALIGN(size) + /* NET_DM_ATTR_ORIGIN */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_HW_TRAP_GROUP_NAME */ nla_total_size(strlen(hw_metadata->trap_group_name) + 1) + /* NET_DM_ATTR_HW_TRAP_NAME */ nla_total_size(strlen(hw_metadata->trap_name) + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + /* NET_DM_ATTR_FLOW_ACTION_COOKIE */ net_dm_flow_action_cookie_size(hw_metadata) + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ nla_total_size(sizeof(u32)) + /* NET_DM_ATTR_PROTO */ nla_total_size(sizeof(u16)) + /* NET_DM_ATTR_PAYLOAD */ nla_total_size(payload_len); } static int net_dm_hw_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { struct devlink_trap_metadata *hw_metadata; struct nlattr *attr; void *hdr; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; hdr = genlmsg_put(msg, 0, 0, &net_drop_monitor_family, 0, NET_DM_CMD_PACKET_ALERT); if (!hdr) return -EMSGSIZE; if (nla_put_u16(msg, NET_DM_ATTR_ORIGIN, NET_DM_ORIGIN_HW)) goto nla_put_failure; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_GROUP_NAME, hw_metadata->trap_group_name)) goto nla_put_failure; if (nla_put_string(msg, NET_DM_ATTR_HW_TRAP_NAME, hw_metadata->trap_name)) goto nla_put_failure; if (hw_metadata->input_dev) { struct net_device *dev = hw_metadata->input_dev; int rc; rc = net_dm_packet_report_in_port_put(msg, dev->ifindex, dev->name); if (rc) goto nla_put_failure; } if (hw_metadata->fa_cookie && nla_put(msg, NET_DM_ATTR_FLOW_ACTION_COOKIE, hw_metadata->fa_cookie->cookie_len, hw_metadata->fa_cookie->cookie)) goto nla_put_failure; if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_ORIG_LEN, skb->len)) goto nla_put_failure; if (!payload_len) goto out; if (nla_put_u16(msg, NET_DM_ATTR_PROTO, be16_to_cpu(skb->protocol))) goto nla_put_failure; attr = skb_put(msg, nla_total_size(payload_len)); attr->nla_type = NET_DM_ATTR_PAYLOAD; attr->nla_len = nla_attr_size(payload_len); if (skb_copy_bits(skb, 0, nla_data(attr), payload_len)) goto nla_put_failure; out: genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static struct devlink_trap_metadata * net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata) { const struct flow_action_cookie *fa_cookie; struct devlink_trap_metadata *hw_metadata; const char *trap_group_name; const char *trap_name; hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); if (!hw_metadata) return NULL; trap_group_name = kstrdup(metadata->trap_group_name, GFP_ATOMIC); if (!trap_group_name) goto free_hw_metadata; hw_metadata->trap_group_name = trap_group_name; trap_name = kstrdup(metadata->trap_name, GFP_ATOMIC); if (!trap_name) goto free_trap_group; hw_metadata->trap_name = trap_name; if (metadata->fa_cookie) { size_t cookie_size = sizeof(*fa_cookie) + metadata->fa_cookie->cookie_len; fa_cookie = kmemdup(metadata->fa_cookie, cookie_size, GFP_ATOMIC); if (!fa_cookie) goto free_trap_name; hw_metadata->fa_cookie = fa_cookie; } hw_metadata->input_dev = metadata->input_dev; netdev_hold(hw_metadata->input_dev, &hw_metadata->dev_tracker, GFP_ATOMIC); return hw_metadata; free_trap_name: kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: kfree(hw_metadata); return NULL; } static void net_dm_hw_metadata_free(struct devlink_trap_metadata *hw_metadata) { netdev_put(hw_metadata->input_dev, &hw_metadata->dev_tracker); kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); kfree(hw_metadata); } static void net_dm_hw_packet_report(struct sk_buff *skb) { struct devlink_trap_metadata *hw_metadata; struct sk_buff *msg; size_t payload_len; int rc; if (skb->data > skb_mac_header(skb)) skb_push(skb, skb->data - skb_mac_header(skb)); else skb_pull(skb, skb_mac_header(skb) - skb->data); payload_len = min_t(size_t, skb->len, NET_DM_MAX_PACKET_SIZE); if (net_dm_trunc_len) payload_len = min_t(size_t, net_dm_trunc_len, payload_len); hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; msg = nlmsg_new(net_dm_hw_packet_report_size(payload_len, hw_metadata), GFP_KERNEL); if (!msg) goto out; rc = net_dm_hw_packet_report_fill(msg, skb, payload_len); if (rc) { nlmsg_free(msg); goto out; } genlmsg_multicast(&net_drop_monitor_family, msg, 0, 0, GFP_KERNEL); out: net_dm_hw_metadata_free(NET_DM_SKB_CB(skb)->hw_metadata); consume_skb(skb); } static void net_dm_hw_packet_work(struct work_struct *work) { struct per_cpu_dm_data *hw_data; struct sk_buff_head list; struct sk_buff *skb; unsigned long flags; hw_data = container_of(work, struct per_cpu_dm_data, dm_alert_work); __skb_queue_head_init(&list); spin_lock_irqsave(&hw_data->drop_queue.lock, flags); skb_queue_splice_tail_init(&hw_data->drop_queue, &list); spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); while ((skb = __skb_dequeue(&list))) net_dm_hw_packet_report(skb); } static void net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink, struct sk_buff *skb, const struct devlink_trap_metadata *metadata) { struct devlink_trap_metadata *n_hw_metadata; ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *hw_data; struct sk_buff *nskb; unsigned long flags; if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) return; if (!skb_mac_header_was_set(skb)) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; n_hw_metadata = net_dm_hw_metadata_copy(metadata); if (!n_hw_metadata) goto free; NET_DM_SKB_CB(nskb)->hw_metadata = n_hw_metadata; nskb->tstamp = tstamp; hw_data = this_cpu_ptr(&dm_hw_cpu_data); spin_lock_irqsave(&hw_data->drop_queue.lock, flags); if (skb_queue_len(&hw_data->drop_queue) < net_dm_queue_len) __skb_queue_tail(&hw_data->drop_queue, nskb); else goto unlock_free; spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); schedule_work(&hw_data->dm_alert_work); return; unlock_free: spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); u64_stats_update_begin(&hw_data->stats.syncp); u64_stats_inc(&hw_data->stats.dropped); u64_stats_update_end(&hw_data->stats.syncp); net_dm_hw_metadata_free(n_hw_metadata); free: consume_skb(nskb); } static const struct net_dm_alert_ops net_dm_alert_packet_ops = { .kfree_skb_probe = net_dm_packet_trace_kfree_skb_hit, .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, .work_item_func = net_dm_packet_work, .hw_work_item_func = net_dm_hw_packet_work, .hw_trap_probe = net_dm_hw_trap_packet_probe, }; static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { [NET_DM_ALERT_MODE_SUMMARY] = &net_dm_alert_summary_ops, [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, }; #if IS_ENABLED(CONFIG_NET_DEVLINK) static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL); } static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) { unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL); tracepoint_synchronize_unregister(); } #else static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { return -EOPNOTSUPP; } static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) { } #endif static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu, rc; if (monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled"); return -EAGAIN; } ops = net_dm_alert_ops_arr[net_dm_alert_mode]; if (!try_module_get(THIS_MODULE)) { NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); return -ENODEV; } for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct net_dm_hw_entries *hw_entries; INIT_WORK(&hw_data->dm_alert_work, ops->hw_work_item_func); timer_setup(&hw_data->send_timer, sched_send_work, 0); hw_entries = net_dm_hw_reset_per_cpu_data(hw_data); kfree(hw_entries); } rc = net_dm_hw_probe_register(ops); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint"); goto err_module_put; } monitor_hw = true; return 0; err_module_put: for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; del_timer_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); consume_skb(skb); } } module_put(THIS_MODULE); return rc; } static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu; if (!monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already disabled"); return; } ops = net_dm_alert_ops_arr[net_dm_alert_mode]; monitor_hw = false; net_dm_hw_probe_unregister(ops); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct sk_buff *skb; del_timer_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); consume_skb(skb); } } module_put(THIS_MODULE); } static int net_dm_trace_on_set(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; int cpu, rc; ops = net_dm_alert_ops_arr[net_dm_alert_mode]; if (!try_module_get(THIS_MODULE)) { NL_SET_ERR_MSG_MOD(extack, "Failed to take reference on module"); return -ENODEV; } for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; INIT_WORK(&data->dm_alert_work, ops->work_item_func); timer_setup(&data->send_timer, sched_send_work, 0); /* Allocate a new per-CPU skb for the summary alert message and * free the old one which might contain stale data from * previous tracing. */ skb = reset_per_cpu_data(data); consume_skb(skb); } rc = register_trace_kfree_skb(ops->kfree_skb_probe, NULL); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to kfree_skb() tracepoint"); goto err_module_put; } rc = register_trace_napi_poll(ops->napi_poll_probe, NULL); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to napi_poll() tracepoint"); goto err_unregister_trace; } return 0; err_unregister_trace: unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); err_module_put: for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; del_timer_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); } module_put(THIS_MODULE); return rc; } static void net_dm_trace_off_set(void) { const struct net_dm_alert_ops *ops; int cpu; ops = net_dm_alert_ops_arr[net_dm_alert_mode]; unregister_trace_napi_poll(ops->napi_poll_probe, NULL); unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); tracepoint_synchronize_unregister(); /* Make sure we do not send notifications to user space after request * to stop tracing returns. */ for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct sk_buff *skb; del_timer_sync(&data->send_timer); cancel_work_sync(&data->dm_alert_work); while ((skb = __skb_dequeue(&data->drop_queue))) consume_skb(skb); } module_put(THIS_MODULE); } static int set_all_monitor_traces(int state, struct netlink_ext_ack *extack) { int rc = 0; if (state == trace_state) { NL_SET_ERR_MSG_MOD(extack, "Trace state already set to requested state"); return -EAGAIN; } switch (state) { case TRACE_ON: rc = net_dm_trace_on_set(extack); break; case TRACE_OFF: net_dm_trace_off_set(); break; default: rc = 1; break; } if (!rc) trace_state = state; else rc = -EINPROGRESS; return rc; } static bool net_dm_is_monitoring(void) { return trace_state == TRACE_ON || monitor_hw; } static int net_dm_alert_mode_get_from_info(struct genl_info *info, enum net_dm_alert_mode *p_alert_mode) { u8 val; val = nla_get_u8(info->attrs[NET_DM_ATTR_ALERT_MODE]); switch (val) { case NET_DM_ALERT_MODE_SUMMARY: case NET_DM_ALERT_MODE_PACKET: *p_alert_mode = val; break; default: return -EINVAL; } return 0; } static int net_dm_alert_mode_set(struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; enum net_dm_alert_mode alert_mode; int rc; if (!info->attrs[NET_DM_ATTR_ALERT_MODE]) return 0; rc = net_dm_alert_mode_get_from_info(info, &alert_mode); if (rc) { NL_SET_ERR_MSG_MOD(extack, "Invalid alert mode"); return -EINVAL; } net_dm_alert_mode = alert_mode; return 0; } static void net_dm_trunc_len_set(struct genl_info *info) { if (!info->attrs[NET_DM_ATTR_TRUNC_LEN]) return; net_dm_trunc_len = nla_get_u32(info->attrs[NET_DM_ATTR_TRUNC_LEN]); } static void net_dm_queue_len_set(struct genl_info *info) { if (!info->attrs[NET_DM_ATTR_QUEUE_LEN]) return; net_dm_queue_len = nla_get_u32(info->attrs[NET_DM_ATTR_QUEUE_LEN]); } static int net_dm_cmd_config(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; int rc; if (net_dm_is_monitoring()) { NL_SET_ERR_MSG_MOD(extack, "Cannot configure drop monitor during monitoring"); return -EBUSY; } rc = net_dm_alert_mode_set(info); if (rc) return rc; net_dm_trunc_len_set(info); net_dm_queue_len_set(info); return 0; } static int net_dm_monitor_start(bool set_sw, bool set_hw, struct netlink_ext_ack *extack) { bool sw_set = false; int rc; if (set_sw) { rc = set_all_monitor_traces(TRACE_ON, extack); if (rc) return rc; sw_set = true; } if (set_hw) { rc = net_dm_hw_monitor_start(extack); if (rc) goto err_monitor_hw; } return 0; err_monitor_hw: if (sw_set) set_all_monitor_traces(TRACE_OFF, extack); return rc; } static void net_dm_monitor_stop(bool set_sw, bool set_hw, struct netlink_ext_ack *extack) { if (set_hw) net_dm_hw_monitor_stop(extack); if (set_sw) set_all_monitor_traces(TRACE_OFF, extack); } static int net_dm_cmd_trace(struct sk_buff *skb, struct genl_info *info) { bool set_sw = !!info->attrs[NET_DM_ATTR_SW_DROPS]; bool set_hw = !!info->attrs[NET_DM_ATTR_HW_DROPS]; struct netlink_ext_ack *extack = info->extack; /* To maintain backward compatibility, we start / stop monitoring of * software drops if no flag is specified. */ if (!set_sw && !set_hw) set_sw = true; switch (info->genlhdr->cmd) { case NET_DM_CMD_START: return net_dm_monitor_start(set_sw, set_hw, extack); case NET_DM_CMD_STOP: net_dm_monitor_stop(set_sw, set_hw, extack); return 0; } return -EOPNOTSUPP; } static int net_dm_config_fill(struct sk_buff *msg, struct genl_info *info) { void *hdr; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &net_drop_monitor_family, 0, NET_DM_CMD_CONFIG_NEW); if (!hdr) return -EMSGSIZE; if (nla_put_u8(msg, NET_DM_ATTR_ALERT_MODE, net_dm_alert_mode)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_TRUNC_LEN, net_dm_trunc_len)) goto nla_put_failure; if (nla_put_u32(msg, NET_DM_ATTR_QUEUE_LEN, net_dm_queue_len)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int net_dm_cmd_config_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; int rc; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rc = net_dm_config_fill(msg, info); if (rc) goto free_msg; return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); return rc; } static void net_dm_stats_read(struct net_dm_stats *stats) { int cpu; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); struct net_dm_stats *cpu_stats = &data->stats; unsigned int start; u64 dropped; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } } static int net_dm_stats_put(struct sk_buff *msg) { struct net_dm_stats stats; struct nlattr *attr; net_dm_stats_read(&stats); attr = nla_nest_start(msg, NET_DM_ATTR_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static void net_dm_hw_stats_read(struct net_dm_stats *stats) { int cpu; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); struct net_dm_stats *cpu_stats = &hw_data->stats; unsigned int start; u64 dropped; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->dropped, dropped); } } static int net_dm_hw_stats_put(struct sk_buff *msg) { struct net_dm_stats stats; struct nlattr *attr; net_dm_hw_stats_read(&stats); attr = nla_nest_start(msg, NET_DM_ATTR_HW_STATS); if (!attr) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); return 0; nla_put_failure: nla_nest_cancel(msg, attr); return -EMSGSIZE; } static int net_dm_stats_fill(struct sk_buff *msg, struct genl_info *info) { void *hdr; int rc; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &net_drop_monitor_family, 0, NET_DM_CMD_STATS_NEW); if (!hdr) return -EMSGSIZE; rc = net_dm_stats_put(msg); if (rc) goto nla_put_failure; rc = net_dm_hw_stats_put(msg); if (rc) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int net_dm_cmd_stats_get(struct sk_buff *skb, struct genl_info *info) { struct sk_buff *msg; int rc; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; rc = net_dm_stats_fill(msg, info); if (rc) goto free_msg; return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); return rc; } static int dropmon_net_event(struct notifier_block *ev_block, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct dm_hw_stat_delta *stat; switch (event) { case NETDEV_REGISTER: if (WARN_ON_ONCE(rtnl_dereference(dev->dm_private))) break; stat = kzalloc(sizeof(*stat), GFP_KERNEL); if (!stat) break; stat->last_rx = jiffies; rcu_assign_pointer(dev->dm_private, stat); break; case NETDEV_UNREGISTER: stat = rtnl_dereference(dev->dm_private); if (stat) { rcu_assign_pointer(dev->dm_private, NULL); kfree_rcu(stat, rcu); } break; } return NOTIFY_DONE; } static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { [NET_DM_ATTR_UNSPEC] = { .strict_start_type = NET_DM_ATTR_UNSPEC + 1 }, [NET_DM_ATTR_ALERT_MODE] = { .type = NLA_U8 }, [NET_DM_ATTR_TRUNC_LEN] = { .type = NLA_U32 }, [NET_DM_ATTR_QUEUE_LEN] = { .type = NLA_U32 }, [NET_DM_ATTR_SW_DROPS] = {. type = NLA_FLAG }, [NET_DM_ATTR_HW_DROPS] = {. type = NLA_FLAG }, }; static const struct genl_small_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_config, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_CONFIG_GET, .doit = net_dm_cmd_config_get, }, { .cmd = NET_DM_CMD_STATS_GET, .doit = net_dm_cmd_stats_get, }, }; static int net_dm_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_lock(&net_dm_mutex); return 0; } static void net_dm_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_unlock(&net_dm_mutex); } static struct genl_family net_drop_monitor_family __ro_after_init = { .hdrsize = 0, .name = "NET_DM", .version = 2, .maxattr = NET_DM_ATTR_MAX, .policy = net_dm_nl_policy, .pre_doit = net_dm_nl_pre_doit, .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, .small_ops = dropmon_ops, .n_small_ops = ARRAY_SIZE(dropmon_ops), .resv_start_op = NET_DM_CMD_STATS_GET + 1, .mcgrps = dropmon_mcgrps, .n_mcgrps = ARRAY_SIZE(dropmon_mcgrps), }; static struct notifier_block dropmon_net_notifier = { .notifier_call = dropmon_net_event }; static void __net_dm_cpu_data_init(struct per_cpu_dm_data *data) { spin_lock_init(&data->lock); skb_queue_head_init(&data->drop_queue); u64_stats_init(&data->stats.syncp); } static void __net_dm_cpu_data_fini(struct per_cpu_dm_data *data) { WARN_ON(!skb_queue_empty(&data->drop_queue)); } static void net_dm_cpu_data_init(int cpu) { struct per_cpu_dm_data *data; data = &per_cpu(dm_cpu_data, cpu); __net_dm_cpu_data_init(data); } static void net_dm_cpu_data_fini(int cpu) { struct per_cpu_dm_data *data; data = &per_cpu(dm_cpu_data, cpu); /* At this point, we should have exclusive access * to this struct and can free the skb inside it. */ consume_skb(data->skb); __net_dm_cpu_data_fini(data); } static void net_dm_hw_cpu_data_init(int cpu) { struct per_cpu_dm_data *hw_data; hw_data = &per_cpu(dm_hw_cpu_data, cpu); __net_dm_cpu_data_init(hw_data); } static void net_dm_hw_cpu_data_fini(int cpu) { struct per_cpu_dm_data *hw_data; hw_data = &per_cpu(dm_hw_cpu_data, cpu); kfree(hw_data->hw_entries); __net_dm_cpu_data_fini(hw_data); } static int __init init_net_drop_monitor(void) { int cpu, rc; pr_info("Initializing network drop monitor service\n"); if (sizeof(void *) > 8) { pr_err("Unable to store program counters on this arch, Drop monitor failed\n"); return -ENOSPC; } rc = genl_register_family(&net_drop_monitor_family); if (rc) { pr_err("Could not create drop monitor netlink family\n"); return rc; } WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); goto out_unreg; } rc = 0; for_each_possible_cpu(cpu) { net_dm_cpu_data_init(cpu); net_dm_hw_cpu_data_init(cpu); } goto out; out_unreg: genl_unregister_family(&net_drop_monitor_family); out: return rc; } static void exit_net_drop_monitor(void) { int cpu; BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } BUG_ON(genl_unregister_family(&net_drop_monitor_family)); } module_init(init_net_drop_monitor); module_exit(exit_net_drop_monitor); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>"); MODULE_ALIAS_GENL_FAMILY("NET_DM"); MODULE_DESCRIPTION("Monitoring code for network dropped packet alerts"); |
| 202 200 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/filesystems.c * * Copyright (C) 1991, 1992 Linus Torvalds * * table of configured filesystems */ #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs_parser.h> /* * Handling of filesystem drivers list. * Rules: * Inclusion to/removals from/scanning of list are protected by spinlock. * During the unload module must call unregister_filesystem(). * We can access the fields of list element if: * 1) spinlock is held or * 2) we hold the reference to the module. * The latter can be guaranteed by call of try_module_get(); if it * returned 0 we must skip the element, otherwise we got the reference. * Once the reference is obtained we can drop the spinlock. */ static struct file_system_type *file_systems; static DEFINE_RWLOCK(file_systems_lock); /* WARNING: This can be used only if we _already_ own a reference */ struct file_system_type *get_filesystem(struct file_system_type *fs) { __module_get(fs->owner); return fs; } void put_filesystem(struct file_system_type *fs) { module_put(fs->owner); } static struct file_system_type **find_filesystem(const char *name, unsigned len) { struct file_system_type **p; for (p = &file_systems; *p; p = &(*p)->next) if (strncmp((*p)->name, name, len) == 0 && !(*p)->name[len]) break; return p; } /** * register_filesystem - register a new filesystem * @fs: the file system structure * * Adds the file system passed to the list of file systems the kernel * is aware of for mount and other syscalls. Returns 0 on success, * or a negative errno code on an error. * * The &struct file_system_type that is passed is linked into the kernel * structures and must not be freed until the file system has been * unregistered. */ int register_filesystem(struct file_system_type * fs) { int res = 0; struct file_system_type ** p; if (fs->parameters && !fs_validate_description(fs->name, fs->parameters)) return -EINVAL; BUG_ON(strchr(fs->name, '.')); if (fs->next) return -EBUSY; write_lock(&file_systems_lock); p = find_filesystem(fs->name, strlen(fs->name)); if (*p) res = -EBUSY; else *p = fs; write_unlock(&file_systems_lock); return res; } EXPORT_SYMBOL(register_filesystem); /** * unregister_filesystem - unregister a file system * @fs: filesystem to unregister * * Remove a file system that was previously successfully registered * with the kernel. An error is returned if the file system is not found. * Zero is returned on a success. * * Once this function has returned the &struct file_system_type structure * may be freed or reused. */ int unregister_filesystem(struct file_system_type * fs) { struct file_system_type ** tmp; write_lock(&file_systems_lock); tmp = &file_systems; while (*tmp) { if (fs == *tmp) { *tmp = fs->next; fs->next = NULL; write_unlock(&file_systems_lock); synchronize_rcu(); return 0; } tmp = &(*tmp)->next; } write_unlock(&file_systems_lock); return -EINVAL; } EXPORT_SYMBOL(unregister_filesystem); #ifdef CONFIG_SYSFS_SYSCALL static int fs_index(const char __user * __name) { struct file_system_type * tmp; struct filename *name; int err, index; name = getname(__name); err = PTR_ERR(name); if (IS_ERR(name)) return err; err = -EINVAL; read_lock(&file_systems_lock); for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) { if (strcmp(tmp->name, name->name) == 0) { err = index; break; } } read_unlock(&file_systems_lock); putname(name); return err; } static int fs_name(unsigned int index, char __user * buf) { struct file_system_type * tmp; int len, res; read_lock(&file_systems_lock); for (tmp = file_systems; tmp; tmp = tmp->next, index--) if (index <= 0 && try_module_get(tmp->owner)) break; read_unlock(&file_systems_lock); if (!tmp) return -EINVAL; /* OK, we got the reference, so we can safely block */ len = strlen(tmp->name) + 1; res = copy_to_user(buf, tmp->name, len) ? -EFAULT : 0; put_filesystem(tmp); return res; } static int fs_maxindex(void) { struct file_system_type * tmp; int index; read_lock(&file_systems_lock); for (tmp = file_systems, index = 0 ; tmp ; tmp = tmp->next, index++) ; read_unlock(&file_systems_lock); return index; } /* * Whee.. Weird sysv syscall. */ SYSCALL_DEFINE3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2) { int retval = -EINVAL; switch (option) { case 1: retval = fs_index((const char __user *) arg1); break; case 2: retval = fs_name(arg1, (char __user *) arg2); break; case 3: retval = fs_maxindex(); break; } return retval; } #endif int __init list_bdev_fs_names(char *buf, size_t size) { struct file_system_type *p; size_t len; int count = 0; read_lock(&file_systems_lock); for (p = file_systems; p; p = p->next) { if (!(p->fs_flags & FS_REQUIRES_DEV)) continue; len = strlen(p->name) + 1; if (len > size) { pr_warn("%s: truncating file system list\n", __func__); break; } memcpy(buf, p->name, len); buf += len; size -= len; count++; } read_unlock(&file_systems_lock); return count; } #ifdef CONFIG_PROC_FS static int filesystems_proc_show(struct seq_file *m, void *v) { struct file_system_type * tmp; read_lock(&file_systems_lock); tmp = file_systems; while (tmp) { seq_printf(m, "%s\t%s\n", (tmp->fs_flags & FS_REQUIRES_DEV) ? "" : "nodev", tmp->name); tmp = tmp->next; } read_unlock(&file_systems_lock); return 0; } static int __init proc_filesystems_init(void) { proc_create_single("filesystems", 0, NULL, filesystems_proc_show); return 0; } module_init(proc_filesystems_init); #endif static struct file_system_type *__get_fs_type(const char *name, int len) { struct file_system_type *fs; read_lock(&file_systems_lock); fs = *(find_filesystem(name, len)); if (fs && !try_module_get(fs->owner)) fs = NULL; read_unlock(&file_systems_lock); return fs; } struct file_system_type *get_fs_type(const char *name) { struct file_system_type *fs; const char *dot = strchr(name, '.'); int len = dot ? dot - name : strlen(name); fs = __get_fs_type(name, len); if (!fs && (request_module("fs-%.*s", len, name) == 0)) { fs = __get_fs_type(name, len); if (!fs) pr_warn_once("request_module fs-%.*s succeeded, but still no fs?\n", len, name); } if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) { put_filesystem(fs); fs = NULL; } return fs; } EXPORT_SYMBOL(get_fs_type); |
| 1852 1852 1851 1852 1852 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/mlock.c * * (C) Copyright 1995 Linus Torvalds * (C) Copyright 2002 Christoph Hellwig */ #include <linux/capability.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/sched/user.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/pagewalk.h> #include <linux/mempolicy.h> #include <linux/syscalls.h> #include <linux/sched.h> #include <linux/export.h> #include <linux/rmap.h> #include <linux/mmzone.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/secretmem.h> #include "internal.h" struct mlock_fbatch { local_lock_t lock; struct folio_batch fbatch; }; static DEFINE_PER_CPU(struct mlock_fbatch, mlock_fbatch) = { .lock = INIT_LOCAL_LOCK(lock), }; bool can_do_mlock(void) { if (rlimit(RLIMIT_MEMLOCK) != 0) return true; if (capable(CAP_IPC_LOCK)) return true; return false; } EXPORT_SYMBOL(can_do_mlock); /* * Mlocked folios are marked with the PG_mlocked flag for efficient testing * in vmscan and, possibly, the fault path; and to support semi-accurate * statistics. * * An mlocked folio [folio_test_mlocked(folio)] is unevictable. As such, it * will be ostensibly placed on the LRU "unevictable" list (actually no such * list exists), rather than the [in]active lists. PG_unevictable is set to * indicate the unevictable state. */ static struct lruvec *__mlock_folio(struct folio *folio, struct lruvec *lruvec) { /* There is nothing more we can do while it's off LRU */ if (!folio_test_clear_lru(folio)) return lruvec; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (unlikely(folio_evictable(folio))) { /* * This is a little surprising, but quite possible: PG_mlocked * must have got cleared already by another CPU. Could this * folio be unevictable? I'm not sure, but move it now if so. */ if (folio_test_unevictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, folio_nr_pages(folio)); } goto out; } if (folio_test_unevictable(folio)) { if (folio_test_mlocked(folio)) folio->mlock_count++; goto out; } lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: folio_set_lru(folio); return lruvec; } static struct lruvec *__mlock_new_folio(struct folio *folio, struct lruvec *lruvec) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); lruvec = folio_lruvec_relock_irq(folio, lruvec); /* As above, this is a little surprising, but possible */ if (unlikely(folio_evictable(folio))) goto out; folio_set_unevictable(folio); folio->mlock_count = !!folio_test_mlocked(folio); __count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio)); out: lruvec_add_folio(lruvec, folio); folio_set_lru(folio); return lruvec; } static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec) { int nr_pages = folio_nr_pages(folio); bool isolated = false; if (!folio_test_clear_lru(folio)) goto munlock; isolated = true; lruvec = folio_lruvec_relock_irq(folio, lruvec); if (folio_test_unevictable(folio)) { /* Then mlock_count is maintained, but might undercount */ if (folio->mlock_count) folio->mlock_count--; if (folio->mlock_count) goto out; } /* else assume that was the last mlock: reclaim will fix it if not */ munlock: if (folio_test_clear_mlocked(folio)) { __zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages); if (isolated || !folio_test_unevictable(folio)) __count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages); else __count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages); } /* folio_evictable() has to be checked *after* clearing Mlocked */ if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) { lruvec_del_folio(lruvec, folio); folio_clear_unevictable(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } out: if (isolated) folio_set_lru(folio); return lruvec; } /* * Flags held in the low bits of a struct folio pointer on the mlock_fbatch. */ #define LRU_FOLIO 0x1 #define NEW_FOLIO 0x2 static inline struct folio *mlock_lru(struct folio *folio) { return (struct folio *)((unsigned long)folio + LRU_FOLIO); } static inline struct folio *mlock_new(struct folio *folio) { return (struct folio *)((unsigned long)folio + NEW_FOLIO); } /* * mlock_folio_batch() is derived from folio_batch_move_lru(): perhaps that can * make use of such folio pointer flags in future, but for now just keep it for * mlock. We could use three separate folio batches instead, but one feels * better (munlocking a full folio batch does not need to drain mlocking folio * batches first). */ static void mlock_folio_batch(struct folio_batch *fbatch) { struct lruvec *lruvec = NULL; unsigned long mlock; struct folio *folio; int i; for (i = 0; i < folio_batch_count(fbatch); i++) { folio = fbatch->folios[i]; mlock = (unsigned long)folio & (LRU_FOLIO | NEW_FOLIO); folio = (struct folio *)((unsigned long)folio - mlock); fbatch->folios[i] = folio; if (mlock & LRU_FOLIO) lruvec = __mlock_folio(folio, lruvec); else if (mlock & NEW_FOLIO) lruvec = __mlock_new_folio(folio, lruvec); else lruvec = __munlock_folio(folio, lruvec); } if (lruvec) unlock_page_lruvec_irq(lruvec); folios_put(fbatch->folios, folio_batch_count(fbatch)); folio_batch_reinit(fbatch); } void mlock_drain_local(void) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } void mlock_drain_remote(int cpu) { struct folio_batch *fbatch; WARN_ON_ONCE(cpu_online(cpu)); fbatch = &per_cpu(mlock_fbatch.fbatch, cpu); if (folio_batch_count(fbatch)) mlock_folio_batch(fbatch); } bool need_mlock_drain(int cpu) { return folio_batch_count(&per_cpu(mlock_fbatch.fbatch, cpu)); } /** * mlock_folio - mlock a folio already on (or temporarily off) LRU * @folio: folio to be mlocked. */ void mlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); if (!folio_test_set_mlocked(folio)) { int nr_pages = folio_nr_pages(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * mlock_new_folio - mlock a newly allocated folio not yet on LRU * @folio: folio to be mlocked, either normal or a THP head. */ void mlock_new_folio(struct folio *folio) { struct folio_batch *fbatch; int nr_pages = folio_nr_pages(folio); local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); folio_set_mlocked(folio); zone_stat_mod_folio(folio, NR_MLOCK, nr_pages); __count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } /** * munlock_folio - munlock a folio * @folio: folio to be munlocked, either normal or a THP head. */ void munlock_folio(struct folio *folio) { struct folio_batch *fbatch; local_lock(&mlock_fbatch.lock); fbatch = this_cpu_ptr(&mlock_fbatch.fbatch); /* * folio_test_clear_mlocked(folio) must be left to __munlock_folio(), * which will check whether the folio is multiply mlocked. */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || folio_test_large(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } static inline unsigned int folio_mlock_step(struct folio *folio, pte_t *pte, unsigned long addr, unsigned long end) { unsigned int count, i, nr = folio_nr_pages(folio); unsigned long pfn = folio_pfn(folio); pte_t ptent = ptep_get(pte); if (!folio_test_large(folio)) return 1; count = pfn + nr - pte_pfn(ptent); count = min_t(unsigned int, count, (end - addr) >> PAGE_SHIFT); for (i = 0; i < count; i++, pte++) { pte_t entry = ptep_get(pte); if (!pte_present(entry)) break; if (pte_pfn(entry) - pfn >= nr) break; } return i; } static inline bool allow_mlock_munlock(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned int step) { /* * For unlock, allow munlock large folio which is partially * mapped to VMA. As it's possible that large folio is * mlocked and VMA is split later. * * During memory pressure, such kind of large folio can * be split. And the pages are not in VM_LOCKed VMA * can be reclaimed. */ if (!(vma->vm_flags & VM_LOCKED)) return true; /* folio_within_range() cannot take KSM, but any small folio is OK */ if (!folio_test_large(folio)) return true; /* folio not in range [start, end), skip mlock */ if (!folio_within_range(folio, vma, start, end)) return false; /* folio is not fully mapped, skip mlock */ if (step != folio_nr_pages(folio)) return false; return true; } static int mlock_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte; pte_t ptent; struct folio *folio; unsigned int step = 1; unsigned long start = addr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (!pmd_present(*pmd)) goto out; if (is_huge_zero_pmd(*pmd)) goto out; folio = page_folio(pmd_page(*pmd)); if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); goto out; } start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) { walk->action = ACTION_AGAIN; return 0; } for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) { ptent = ptep_get(pte); if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; step = folio_mlock_step(folio, pte, addr, end); if (!allow_mlock_munlock(folio, vma, start, end, step)) goto next_entry; if (vma->vm_flags & VM_LOCKED) mlock_folio(folio); else munlock_folio(folio); next_entry: pte += step - 1; addr += (step - 1) << PAGE_SHIFT; } pte_unmap(start_pte); out: spin_unlock(ptl); cond_resched(); return 0; } /* * mlock_vma_pages_range() - mlock any pages already in the range, * or munlock all pages in the range. * @vma - vma containing range to be mlock()ed or munlock()ed * @start - start address in @vma of the range * @end - end of range in @vma * @newflags - the new set of flags for @vma. * * Called for mlock(), mlock2() and mlockall(), to set @vma VM_LOCKED; * called for munlock() and munlockall(), to clear VM_LOCKED from @vma. */ static void mlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, vm_flags_t newflags) { static const struct mm_walk_ops mlock_walk_ops = { .pmd_entry = mlock_pte_range, .walk_lock = PGWALK_WRLOCK_VERIFY, }; /* * There is a slight chance that concurrent page migration, * or page reclaim finding a page of this now-VM_LOCKED vma, * will call mlock_vma_folio() and raise page's mlock_count: * double counting, leaving the page unevictable indefinitely. * Communicate this danger to mlock_vma_folio() with VM_IO, * which is a VM_SPECIAL flag not allowed on VM_LOCKED vmas. * mmap_lock is held in write mode here, so this weird * combination should not be visible to other mmap_lock users; * but WRITE_ONCE so rmap walkers must see VM_IO if VM_LOCKED. */ if (newflags & VM_LOCKED) newflags |= VM_IO; vma_start_write(vma); vm_flags_reset_once(vma, newflags); lru_add_drain(); walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL); lru_add_drain(); if (newflags & VM_IO) { newflags &= ~VM_IO; vm_flags_reset_once(vma, newflags); } } /* * mlock_fixup - handle mlock[all]/munlock[all] requests. * * Filters out "special" vmas -- VM_LOCKED never gets set for these, and * munlock is a no-op. However, for some special vmas, we go ahead and * populate the ptes. * * For vmas that pass the filters, merge/split as appropriate. */ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, vm_flags_t newflags) { struct mm_struct *mm = vma->vm_mm; int nr_pages; int ret = 0; vm_flags_t oldflags = vma->vm_flags; if (newflags == oldflags || (oldflags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) || vma_is_dax(vma) || vma_is_secretmem(vma)) /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ goto out; vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; } /* * Keep track of amount of locked VM. */ nr_pages = (end - start) >> PAGE_SHIFT; if (!(newflags & VM_LOCKED)) nr_pages = -nr_pages; else if (oldflags & VM_LOCKED) nr_pages = 0; mm->locked_vm += nr_pages; /* * vm_flags is protected by the mmap_lock held in write mode. * It's okay if try_to_unmap_one unmaps a page just after we * set VM_LOCKED, populate_vma_page_range will bring it back. */ if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) { /* No work to do, and mlocking twice would be wrong */ vma_start_write(vma); vm_flags_reset(vma, newflags); } else { mlock_vma_pages_range(vma, start, end, newflags); } out: *prev = vma; return ret; } static int apply_vma_lock_flags(unsigned long start, size_t len, vm_flags_t flags) { unsigned long nstart, end, tmp; struct vm_area_struct *vma, *prev; VMA_ITERATOR(vmi, current->mm, start); VM_BUG_ON(offset_in_page(start)); VM_BUG_ON(len != PAGE_ALIGN(len)); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; vma = vma_iter_load(&vmi); if (!vma) return -ENOMEM; prev = vma_prev(&vmi); if (start > vma->vm_start) prev = vma; nstart = start; tmp = vma->vm_start; for_each_vma_range(vmi, vma, end) { int error; vm_flags_t newflags; if (vma->vm_start != tmp) return -ENOMEM; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= flags; /* Here we know that vma->vm_start <= nstart < vma->vm_end. */ tmp = vma->vm_end; if (tmp > end) tmp = end; error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags); if (error) return error; tmp = vma_iter_end(&vmi); nstart = tmp; } if (tmp < end) return -ENOMEM; return 0; } /* * Go through vma areas and sum size of mlocked * vma pages, as return value. * Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT) * is also counted. * Return value: previously mlocked page counts */ static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, unsigned long start, size_t len) { struct vm_area_struct *vma; unsigned long count = 0; unsigned long end; VMA_ITERATOR(vmi, mm, start); /* Don't overflow past ULONG_MAX */ if (unlikely(ULONG_MAX - len < start)) end = ULONG_MAX; else end = start + len; for_each_vma_range(vmi, vma, end) { if (vma->vm_flags & VM_LOCKED) { if (start > vma->vm_start) count -= (start - vma->vm_start); if (end < vma->vm_end) { count += end - vma->vm_start; break; } count += vma->vm_end - vma->vm_start; } } return count >> PAGE_SHIFT; } /* * convert get_user_pages() return value to posix mlock() error */ static int __mlock_posix_error_return(long retval) { if (retval == -EFAULT) retval = -ENOMEM; else if (retval == -ENOMEM) retval = -EAGAIN; return retval; } static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags) { unsigned long locked; unsigned long lock_limit; int error = -ENOMEM; start = untagged_addr(start); if (!can_do_mlock()) return -EPERM; len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; locked = len >> PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; locked += current->mm->locked_vm; if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) { /* * It is possible that the regions requested intersect with * previously mlocked areas, that part area in "mm->locked_vm" * should not be counted to new mlock increment count. So check * and adjust locked count if necessary. */ locked -= count_mm_mlocked_page_nr(current->mm, start, len); } /* check against resource limits */ if ((locked <= lock_limit) || capable(CAP_IPC_LOCK)) error = apply_vma_lock_flags(start, len, flags); mmap_write_unlock(current->mm); if (error) return error; error = __mm_populate(start, len, 0); if (error) return __mlock_posix_error_return(error); return 0; } SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) { return do_mlock(start, len, VM_LOCKED); } SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) { vm_flags_t vm_flags = VM_LOCKED; if (flags & ~MLOCK_ONFAULT) return -EINVAL; if (flags & MLOCK_ONFAULT) vm_flags |= VM_LOCKONFAULT; return do_mlock(start, len, vm_flags); } SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; start = untagged_addr(start); len = PAGE_ALIGN(len + (offset_in_page(start))); start &= PAGE_MASK; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_vma_lock_flags(start, len, 0); mmap_write_unlock(current->mm); return ret; } /* * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) * and translate into the appropriate modifications to mm->def_flags and/or the * flags for all current VMAs. * * There are a couple of subtleties with this. If mlockall() is called multiple * times with different flags, the values do not necessarily stack. If mlockall * is called once including the MCL_FUTURE flag and then a second time without * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags. */ static int apply_mlockall_flags(int flags) { VMA_ITERATOR(vmi, current->mm, 0); struct vm_area_struct *vma, *prev = NULL; vm_flags_t to_add = 0; current->mm->def_flags &= ~VM_LOCKED_MASK; if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; if (flags & MCL_ONFAULT) current->mm->def_flags |= VM_LOCKONFAULT; if (!(flags & MCL_CURRENT)) goto out; } if (flags & MCL_CURRENT) { to_add |= VM_LOCKED; if (flags & MCL_ONFAULT) to_add |= VM_LOCKONFAULT; } for_each_vma(vmi, vma) { vm_flags_t newflags; newflags = vma->vm_flags & ~VM_LOCKED_MASK; newflags |= to_add; /* Ignore errors */ mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end, newflags); cond_resched(); } out: return 0; } SYSCALL_DEFINE1(mlockall, int, flags) { unsigned long lock_limit; int ret; if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) || flags == MCL_ONFAULT) return -EINVAL; if (!can_do_mlock()) return -EPERM; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = -ENOMEM; if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) || capable(CAP_IPC_LOCK)) ret = apply_mlockall_flags(flags); mmap_write_unlock(current->mm); if (!ret && (flags & MCL_CURRENT)) mm_populate(0, TASK_SIZE); return ret; } SYSCALL_DEFINE0(munlockall) { int ret; if (mmap_write_lock_killable(current->mm)) return -EINTR; ret = apply_mlockall_flags(0); mmap_write_unlock(current->mm); return ret; } /* * Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB * shm segments) get accounted against the user_struct instead. */ static DEFINE_SPINLOCK(shmlock_user_lock); int user_shm_lock(size_t size, struct ucounts *ucounts) { unsigned long lock_limit, locked; long memlock; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; lock_limit = rlimit(RLIMIT_MEMLOCK); if (lock_limit != RLIM_INFINITY) lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); if ((memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); goto out; } if (!get_ucounts(ucounts)) { dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); allowed = 0; goto out; } allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; } void user_shm_unlock(size_t size, struct ucounts *ucounts) { spin_lock(&shmlock_user_lock); dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT); spin_unlock(&shmlock_user_lock); put_ucounts(ucounts); } |
| 275 250 275 275 268 234 174 268 268 268 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | // SPDX-License-Identifier: GPL-2.0 #include <linux/proc_fs.h> #include <linux/nsproxy.h> #include <linux/ptrace.h> #include <linux/namei.h> #include <linux/file.h> #include <linux/utsname.h> #include <net/net_namespace.h> #include <linux/ipc_namespace.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include "internal.h" static const struct proc_ns_operations *ns_entries[] = { #ifdef CONFIG_NET_NS &netns_operations, #endif #ifdef CONFIG_UTS_NS &utsns_operations, #endif #ifdef CONFIG_IPC_NS &ipcns_operations, #endif #ifdef CONFIG_PID_NS &pidns_operations, &pidns_for_children_operations, #endif #ifdef CONFIG_USER_NS &userns_operations, #endif &mntns_operations, #ifdef CONFIG_CGROUPS &cgroupns_operations, #endif #ifdef CONFIG_TIME_NS &timens_operations, &timens_for_children_operations, #endif }; static const char *proc_ns_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; struct path ns_path; int error = -EACCES; if (!dentry) return ERR_PTR(-ECHILD); task = get_proc_task(inode); if (!task) return ERR_PTR(-EACCES); if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out; error = ns_get_path(&ns_path, task, ns_ops); if (error) goto out; error = nd_jump_link(&ns_path); out: put_task_struct(task); return ERR_PTR(error); } static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; char name[50]; int res = -EACCES; task = get_proc_task(inode); if (!task) return res; if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { res = ns_get_name(name, sizeof(name), task, ns_ops); if (res >= 0) res = readlink_copy(buffer, buflen, name); } put_task_struct(task); return res; } static const struct inode_operations proc_ns_link_inode_operations = { .readlink = proc_ns_readlink, .get_link = proc_ns_get_link, .setattr = proc_setattr, }; static struct dentry *proc_ns_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { const struct proc_ns_operations *ns_ops = ptr; struct inode *inode; struct proc_inode *ei; inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO); if (!inode) return ERR_PTR(-ENOENT); ei = PROC_I(inode); inode->i_op = &proc_ns_link_inode_operations; ei->ns_ops = ns_ops; pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); return d_splice_alias(inode, dentry); } static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx) { struct task_struct *task = get_proc_task(file_inode(file)); const struct proc_ns_operations **entry, **last; if (!task) return -ENOENT; if (!dir_emit_dots(file, ctx)) goto out; if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries)) goto out; entry = ns_entries + (ctx->pos - 2); last = &ns_entries[ARRAY_SIZE(ns_entries) - 1]; while (entry <= last) { const struct proc_ns_operations *ops = *entry; if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name), proc_ns_instantiate, task, ops)) break; ctx->pos++; entry++; } out: put_task_struct(task); return 0; } const struct file_operations proc_ns_dir_operations = { .read = generic_read_dir, .iterate_shared = proc_ns_dir_readdir, .llseek = generic_file_llseek, }; static struct dentry *proc_ns_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct task_struct *task = get_proc_task(dir); const struct proc_ns_operations **entry, **last; unsigned int len = dentry->d_name.len; struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; last = &ns_entries[ARRAY_SIZE(ns_entries)]; for (entry = ns_entries; entry < last; entry++) { if (strlen((*entry)->name) != len) continue; if (!memcmp(dentry->d_name.name, (*entry)->name, len)) break; } if (entry == last) goto out; res = proc_ns_instantiate(dentry, task, *entry); out: put_task_struct(task); out_no_task: return res; } const struct inode_operations proc_ns_dir_inode_operations = { .lookup = proc_ns_dir_lookup, .getattr = pid_getattr, .setattr = proc_setattr, }; |
| 89 89 89 89 89 89 89 89 89 89 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * sha512_base.h - core logic for SHA-512 implementations * * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> */ #ifndef _CRYPTO_SHA512_BASE_H #define _CRYPTO_SHA512_BASE_H #include <crypto/internal/hash.h> #include <crypto/sha2.h> #include <linux/crypto.h> #include <linux/module.h> #include <linux/string.h> #include <asm/unaligned.h> typedef void (sha512_block_fn)(struct sha512_state *sst, u8 const *src, int blocks); static inline int sha384_base_init(struct shash_desc *desc) { struct sha512_state *sctx = shash_desc_ctx(desc); sctx->state[0] = SHA384_H0; sctx->state[1] = SHA384_H1; sctx->state[2] = SHA384_H2; sctx->state[3] = SHA384_H3; sctx->state[4] = SHA384_H4; sctx->state[5] = SHA384_H5; sctx->state[6] = SHA384_H6; sctx->state[7] = SHA384_H7; sctx->count[0] = sctx->count[1] = 0; return 0; } static inline int sha512_base_init(struct shash_desc *desc) { struct sha512_state *sctx = shash_desc_ctx(desc); sctx->state[0] = SHA512_H0; sctx->state[1] = SHA512_H1; sctx->state[2] = SHA512_H2; sctx->state[3] = SHA512_H3; sctx->state[4] = SHA512_H4; sctx->state[5] = SHA512_H5; sctx->state[6] = SHA512_H6; sctx->state[7] = SHA512_H7; sctx->count[0] = sctx->count[1] = 0; return 0; } static inline int sha512_base_do_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha512_block_fn *block_fn) { struct sha512_state *sctx = shash_desc_ctx(desc); unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE; sctx->count[0] += len; if (sctx->count[0] < len) sctx->count[1]++; if (unlikely((partial + len) >= SHA512_BLOCK_SIZE)) { int blocks; if (partial) { int p = SHA512_BLOCK_SIZE - partial; memcpy(sctx->buf + partial, data, p); data += p; len -= p; block_fn(sctx, sctx->buf, 1); } blocks = len / SHA512_BLOCK_SIZE; len %= SHA512_BLOCK_SIZE; if (blocks) { block_fn(sctx, data, blocks); data += blocks * SHA512_BLOCK_SIZE; } partial = 0; } if (len) memcpy(sctx->buf + partial, data, len); return 0; } static inline int sha512_base_do_finalize(struct shash_desc *desc, sha512_block_fn *block_fn) { const int bit_offset = SHA512_BLOCK_SIZE - sizeof(__be64[2]); struct sha512_state *sctx = shash_desc_ctx(desc); __be64 *bits = (__be64 *)(sctx->buf + bit_offset); unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE; sctx->buf[partial++] = 0x80; if (partial > bit_offset) { memset(sctx->buf + partial, 0x0, SHA512_BLOCK_SIZE - partial); partial = 0; block_fn(sctx, sctx->buf, 1); } memset(sctx->buf + partial, 0x0, bit_offset - partial); bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61); bits[1] = cpu_to_be64(sctx->count[0] << 3); block_fn(sctx, sctx->buf, 1); return 0; } static inline int sha512_base_finish(struct shash_desc *desc, u8 *out) { unsigned int digest_size = crypto_shash_digestsize(desc->tfm); struct sha512_state *sctx = shash_desc_ctx(desc); __be64 *digest = (__be64 *)out; int i; for (i = 0; digest_size > 0; i++, digest_size -= sizeof(__be64)) put_unaligned_be64(sctx->state[i], digest++); memzero_explicit(sctx, sizeof(*sctx)); return 0; } #endif /* _CRYPTO_SHA512_BASE_H */ |
| 811 843 811 811 811 844 844 811 811 811 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 | /* * Cryptographic API. * * Glue code for the SHA256 Secure Hash Algorithm assembler implementations * using SSSE3, AVX, AVX2, and SHA-NI instructions. * * This file is based on sha256_generic.c * * Copyright (C) 2013 Intel Corporation. * * Author: * Tim Chen <tim.c.chen@linux.intel.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version. * * 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. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <crypto/sha2.h> #include <crypto/sha256_base.h> #include <linux/string.h> #include <asm/cpu_device_id.h> #include <asm/simd.h> asmlinkage void sha256_transform_ssse3(struct sha256_state *state, const u8 *data, int blocks); static const struct x86_cpu_id module_cpu_ids[] = { #ifdef CONFIG_AS_SHA256_NI X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL), #endif X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); static int _sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha256_block_fn *sha256_xform) { struct sha256_state *sctx = shash_desc_ctx(desc); if (!crypto_simd_usable() || (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE) return crypto_sha256_update(desc, data, len); /* * Make sure struct sha256_state begins directly with the SHA256 * 256-bit internal state, as this is what the asm functions expect. */ BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); kernel_fpu_begin(); sha256_base_do_update(desc, data, len, sha256_xform); kernel_fpu_end(); return 0; } static int sha256_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out, sha256_block_fn *sha256_xform) { if (!crypto_simd_usable()) return crypto_sha256_finup(desc, data, len, out); kernel_fpu_begin(); if (len) sha256_base_do_update(desc, data, len, sha256_xform); sha256_base_do_finalize(desc, sha256_xform); kernel_fpu_end(); return sha256_base_finish(desc, out); } static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_ssse3); } static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_ssse3); } /* Add padding and return the message digest. */ static int sha256_ssse3_final(struct shash_desc *desc, u8 *out) { return sha256_ssse3_finup(desc, NULL, 0, out); } static int sha256_ssse3_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_ssse3_finup(desc, data, len, out); } static struct shash_alg sha256_ssse3_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ssse3_update, .final = sha256_ssse3_final, .finup = sha256_ssse3_finup, .digest = sha256_ssse3_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-ssse3", .cra_priority = 150, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_ssse3_update, .final = sha256_ssse3_final, .finup = sha256_ssse3_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-ssse3", .cra_priority = 150, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static int register_sha256_ssse3(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) return crypto_register_shashes(sha256_ssse3_algs, ARRAY_SIZE(sha256_ssse3_algs)); return 0; } static void unregister_sha256_ssse3(void) { if (boot_cpu_has(X86_FEATURE_SSSE3)) crypto_unregister_shashes(sha256_ssse3_algs, ARRAY_SIZE(sha256_ssse3_algs)); } asmlinkage void sha256_transform_avx(struct sha256_state *state, const u8 *data, int blocks); static int sha256_avx_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_avx); } static int sha256_avx_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_avx); } static int sha256_avx_final(struct shash_desc *desc, u8 *out) { return sha256_avx_finup(desc, NULL, 0, out); } static int sha256_avx_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_avx_finup(desc, data, len, out); } static struct shash_alg sha256_avx_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_avx_update, .final = sha256_avx_final, .finup = sha256_avx_finup, .digest = sha256_avx_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-avx", .cra_priority = 160, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_avx_update, .final = sha256_avx_final, .finup = sha256_avx_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-avx", .cra_priority = 160, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static bool avx_usable(void) { if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { if (boot_cpu_has(X86_FEATURE_AVX)) pr_info("AVX detected but unusable.\n"); return false; } return true; } static int register_sha256_avx(void) { if (avx_usable()) return crypto_register_shashes(sha256_avx_algs, ARRAY_SIZE(sha256_avx_algs)); return 0; } static void unregister_sha256_avx(void) { if (avx_usable()) crypto_unregister_shashes(sha256_avx_algs, ARRAY_SIZE(sha256_avx_algs)); } asmlinkage void sha256_transform_rorx(struct sha256_state *state, const u8 *data, int blocks); static int sha256_avx2_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_transform_rorx); } static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_transform_rorx); } static int sha256_avx2_final(struct shash_desc *desc, u8 *out) { return sha256_avx2_finup(desc, NULL, 0, out); } static int sha256_avx2_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_avx2_finup(desc, data, len, out); } static struct shash_alg sha256_avx2_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_avx2_update, .final = sha256_avx2_final, .finup = sha256_avx2_finup, .digest = sha256_avx2_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-avx2", .cra_priority = 170, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_avx2_update, .final = sha256_avx2_final, .finup = sha256_avx2_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-avx2", .cra_priority = 170, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static bool avx2_usable(void) { if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2)) return true; return false; } static int register_sha256_avx2(void) { if (avx2_usable()) return crypto_register_shashes(sha256_avx2_algs, ARRAY_SIZE(sha256_avx2_algs)); return 0; } static void unregister_sha256_avx2(void) { if (avx2_usable()) crypto_unregister_shashes(sha256_avx2_algs, ARRAY_SIZE(sha256_avx2_algs)); } #ifdef CONFIG_AS_SHA256_NI asmlinkage void sha256_ni_transform(struct sha256_state *digest, const u8 *data, int rounds); static int sha256_ni_update(struct shash_desc *desc, const u8 *data, unsigned int len) { return _sha256_update(desc, data, len, sha256_ni_transform); } static int sha256_ni_finup(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_finup(desc, data, len, out, sha256_ni_transform); } static int sha256_ni_final(struct shash_desc *desc, u8 *out) { return sha256_ni_finup(desc, NULL, 0, out); } static int sha256_ni_digest(struct shash_desc *desc, const u8 *data, unsigned int len, u8 *out) { return sha256_base_init(desc) ?: sha256_ni_finup(desc, data, len, out); } static struct shash_alg sha256_ni_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ni_update, .final = sha256_ni_final, .finup = sha256_ni_finup, .digest = sha256_ni_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-ni", .cra_priority = 250, .cra_blocksize = SHA256_BLOCK_SIZE, .cra_module = THIS_MODULE, } }, { .digestsize = SHA224_DIGEST_SIZE, .init = sha224_base_init, .update = sha256_ni_update, .final = sha256_ni_final, .finup = sha256_ni_finup, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-ni", .cra_priority = 250, .cra_blocksize = SHA224_BLOCK_SIZE, .cra_module = THIS_MODULE, } } }; static int register_sha256_ni(void) { if (boot_cpu_has(X86_FEATURE_SHA_NI)) return crypto_register_shashes(sha256_ni_algs, ARRAY_SIZE(sha256_ni_algs)); return 0; } static void unregister_sha256_ni(void) { if (boot_cpu_has(X86_FEATURE_SHA_NI)) crypto_unregister_shashes(sha256_ni_algs, ARRAY_SIZE(sha256_ni_algs)); } #else static inline int register_sha256_ni(void) { return 0; } static inline void unregister_sha256_ni(void) { } #endif static int __init sha256_ssse3_mod_init(void) { if (!x86_match_cpu(module_cpu_ids)) return -ENODEV; if (register_sha256_ssse3()) goto fail; if (register_sha256_avx()) { unregister_sha256_ssse3(); goto fail; } if (register_sha256_avx2()) { unregister_sha256_avx(); unregister_sha256_ssse3(); goto fail; } if (register_sha256_ni()) { unregister_sha256_avx2(); unregister_sha256_avx(); unregister_sha256_ssse3(); goto fail; } return 0; fail: return -ENODEV; } static void __exit sha256_ssse3_mod_fini(void) { unregister_sha256_ni(); unregister_sha256_avx2(); unregister_sha256_avx(); unregister_sha256_ssse3(); } module_init(sha256_ssse3_mod_init); module_exit(sha256_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated"); MODULE_ALIAS_CRYPTO("sha256"); MODULE_ALIAS_CRYPTO("sha256-ssse3"); MODULE_ALIAS_CRYPTO("sha256-avx"); MODULE_ALIAS_CRYPTO("sha256-avx2"); MODULE_ALIAS_CRYPTO("sha224"); MODULE_ALIAS_CRYPTO("sha224-ssse3"); MODULE_ALIAS_CRYPTO("sha224-avx"); MODULE_ALIAS_CRYPTO("sha224-avx2"); #ifdef CONFIG_AS_SHA256_NI MODULE_ALIAS_CRYPTO("sha256-ni"); MODULE_ALIAS_CRYPTO("sha224-ni"); #endif |
| 1 7 11 7 3 7 20 16 2 1 1 11 2 11 7 3 2 2 1 3 3 1 11 11 11 11 11 11 11 11 11 11 4 7 4 4 4 4 4 4 4 4 11 7 4 |