| 26 7 98 97 96 73 2 70 1 2 2 7 3 6 4 6 11 15 15 16 33 2 6 7 42 42 41 40 40 11 1 1 1 1 1 34 34 33 32 2 1 1 23 22 3 1 4 4 2 2 2 3 2 1 1 2 2 7 63 63 57 59 57 36 22 14 7 5 4 8 8 14 14 12 71 45 26 18 7 25 47 18 18 3 2 1 2 1 2 1 3 30 30 32 23 10 4 13 2 11 6 13 3 10 28 2 29 30 30 30 30 29 30 30 30 30 29 29 94 75 12 11 1040 1009 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Extension Header handling for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Andi Kleen <ak@muc.de> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ /* Changes: * yoshfuji : ensure not to overrun while parsing * tlv options. * Mitsuru KANDA @USAGI and: Remove ipv6_parse_exthdrs(). * YOSHIFUJI Hideaki @USAGI Register inbound extension header * handlers as inet6_protocol{}. */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/icmpv6.h> #include <linux/slab.h> #include <linux/export.h> #include <net/dst.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/rawv6.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/calipso.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/xfrm.h> #endif #include <linux/seg6.h> #include <net/seg6.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif #include <net/rpl.h> #include <linux/ioam6.h> #include <linux/ioam6_genl.h> #include <net/ioam6.h> #include <net/dst_metadata.h> #include <linux/uaccess.h> /********************* Generic functions *********************/ /* An unknown option is detected, decide what to do */ static bool ip6_tlvopt_unknown(struct sk_buff *skb, int optoff, bool disallow_unknowns) { if (disallow_unknowns) { /* If unknown TLVs are disallowed by configuration * then always silently drop packet. Note this also * means no ICMP parameter problem is sent which * could be a good property to mitigate a reflection DOS * attack. */ goto drop; } switch ((skb_network_header(skb)[optoff] & 0xC0) >> 6) { case 0: /* ignore */ return true; case 1: /* drop packet */ break; case 3: /* Send ICMP if not a multicast address and drop packet */ /* Actually, it is redundant check. icmp_send will recheck in any case. */ if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) break; fallthrough; case 2: /* send ICMP PARM PROB regardless and drop packet */ icmpv6_param_prob_reason(skb, ICMPV6_UNK_OPTION, optoff, SKB_DROP_REASON_UNHANDLED_PROTO); return false; } drop: kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); return false; } static bool ipv6_hop_ra(struct sk_buff *skb, int optoff); static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff); static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff); static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff); #if IS_ENABLED(CONFIG_IPV6_MIP6) static bool ipv6_dest_hao(struct sk_buff *skb, int optoff); #endif /* Parse tlv encoded option header (hop-by-hop or destination) */ static bool ip6_parse_tlv(bool hopbyhop, struct sk_buff *skb, int max_count) { int len = (skb_transport_header(skb)[1] + 1) << 3; const unsigned char *nh = skb_network_header(skb); int off = skb_network_header_len(skb); bool disallow_unknowns = false; int tlv_count = 0; int padlen = 0; if (unlikely(max_count < 0)) { disallow_unknowns = true; max_count = -max_count; } off += 2; len -= 2; while (len > 0) { int optlen, i; if (nh[off] == IPV6_TLV_PAD1) { padlen++; if (padlen > 7) goto bad; off++; len--; continue; } if (len < 2) goto bad; optlen = nh[off + 1] + 2; if (optlen > len) goto bad; if (nh[off] == IPV6_TLV_PADN) { /* RFC 2460 states that the purpose of PadN is * to align the containing header to multiples * of 8. 7 is therefore the highest valid value. * See also RFC 4942, Section 2.1.9.5. */ padlen += optlen; if (padlen > 7) goto bad; /* RFC 4942 recommends receiving hosts to * actively check PadN payload to contain * only zeroes. */ for (i = 2; i < optlen; i++) { if (nh[off + i] != 0) goto bad; } } else { tlv_count++; if (tlv_count > max_count) goto bad; if (hopbyhop) { switch (nh[off]) { case IPV6_TLV_ROUTERALERT: if (!ipv6_hop_ra(skb, off)) return false; break; case IPV6_TLV_IOAM: if (!ipv6_hop_ioam(skb, off)) return false; nh = skb_network_header(skb); break; case IPV6_TLV_JUMBO: if (!ipv6_hop_jumbo(skb, off)) return false; break; case IPV6_TLV_CALIPSO: if (!ipv6_hop_calipso(skb, off)) return false; break; default: if (!ip6_tlvopt_unknown(skb, off, disallow_unknowns)) return false; break; } } else { switch (nh[off]) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_TLV_HAO: if (!ipv6_dest_hao(skb, off)) return false; break; #endif default: if (!ip6_tlvopt_unknown(skb, off, disallow_unknowns)) return false; break; } } padlen = 0; } off += optlen; len -= optlen; } if (len == 0) return true; bad: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /***************************** Destination options header. *****************************/ #if IS_ENABLED(CONFIG_IPV6_MIP6) static bool ipv6_dest_hao(struct sk_buff *skb, int optoff) { struct ipv6_destopt_hao *hao; struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6hdr *ipv6h = ipv6_hdr(skb); SKB_DR(reason); int ret; if (opt->dsthao) { net_dbg_ratelimited("hao duplicated\n"); goto discard; } opt->dsthao = opt->dst1; opt->dst1 = 0; hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff); if (hao->length != 16) { net_dbg_ratelimited("hao invalid option length = %d\n", hao->length); SKB_DR_SET(reason, IP_INHDR); goto discard; } if (!(ipv6_addr_type(&hao->addr) & IPV6_ADDR_UNICAST)) { net_dbg_ratelimited("hao is not an unicast addr: %pI6\n", &hao->addr); SKB_DR_SET(reason, INVALID_PROTO); goto discard; } ret = xfrm6_input_addr(skb, (xfrm_address_t *)&ipv6h->daddr, (xfrm_address_t *)&hao->addr, IPPROTO_DSTOPTS); if (unlikely(ret < 0)) { SKB_DR_SET(reason, XFRM_POLICY); goto discard; } if (skb_cloned(skb)) { if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) goto discard; /* update all variable using below by copied skbuff */ hao = (struct ipv6_destopt_hao *)(skb_network_header(skb) + optoff); ipv6h = ipv6_hdr(skb); } if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; swap(ipv6h->saddr, hao->addr); if (skb->tstamp == 0) __net_timestamp(skb); return true; discard: kfree_skb_reason(skb, reason); return false; } #endif static int ipv6_destopt_rcv(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) __u16 dstbuf; #endif struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(skb->dev); int extlen; if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { __IP6_INC_STATS(dev_net(dst->dev), idev, IPSTATS_MIB_INHDRERRORS); fail_and_free: kfree_skb(skb); return -1; } extlen = (skb_transport_header(skb)[1] + 1) << 3; if (extlen > net->ipv6.sysctl.max_dst_opts_len) goto fail_and_free; opt->lastopt = opt->dst1 = skb_network_header_len(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) dstbuf = opt->dst1; #endif if (ip6_parse_tlv(false, skb, net->ipv6.sysctl.max_dst_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) opt->nhoff = dstbuf; #else opt->nhoff = opt->dst1; #endif return 1; } __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return -1; } static void seg6_update_csum(struct sk_buff *skb) { struct ipv6_sr_hdr *hdr; struct in6_addr *addr; __be32 from, to; /* srh is at transport offset and seg_left is already decremented * but daddr is not yet updated with next segment */ hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); addr = hdr->segments + hdr->segments_left; hdr->segments_left++; from = *(__be32 *)hdr; hdr->segments_left--; to = *(__be32 *)hdr; /* update skb csum with diff resulting from seg_left decrement */ update_csum_diff4(skb, from, to); /* compute csum diff between current and next segment and update */ update_csum_diff16(skb, (__be32 *)(&ipv6_hdr(skb)->daddr), (__be32 *)addr); } static int ipv6_srh_rcv(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); struct ipv6_sr_hdr *hdr; struct inet6_dev *idev; struct in6_addr *addr; int accept_seg6; hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); idev = __in6_dev_get(skb->dev); accept_seg6 = min(READ_ONCE(net->ipv6.devconf_all->seg6_enabled), READ_ONCE(idev->cnf.seg6_enabled)); if (!accept_seg6) { kfree_skb(skb); return -1; } #ifdef CONFIG_IPV6_SEG6_HMAC if (!seg6_hmac_validate_skb(skb)) { kfree_skb(skb); return -1; } #endif looped_back: if (hdr->segments_left == 0) { if (hdr->nexthdr == NEXTHDR_IPV6 || hdr->nexthdr == NEXTHDR_IPV4) { int offset = (hdr->hdrlen + 1) << 3; skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); skb_pull(skb, offset); skb_postpull_rcsum(skb, skb_transport_header(skb), offset); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; if (hdr->nexthdr == NEXTHDR_IPV4) skb->protocol = htons(ETH_P_IP); __skb_tunnel_rx(skb, skb->dev, net); netif_rx(skb); return -1; } opt->srcrt = skb_network_header_len(skb); opt->lastopt = opt->srcrt; skb->transport_header += (hdr->hdrlen + 1) << 3; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } if (hdr->segments_left >= (hdr->hdrlen >> 1)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } if (skb_cloned(skb)) { if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -1; } hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb); } hdr->segments_left--; addr = hdr->segments + hdr->segments_left; skb_push(skb, sizeof(struct ipv6hdr)); if (skb->ip_summed == CHECKSUM_COMPLETE) seg6_update_csum(skb); ipv6_hdr(skb)->daddr = *addr; ip6_route_input(skb); if (skb_dst(skb)->error) { dst_input(skb); return -1; } if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; skb_pull(skb, sizeof(struct ipv6hdr)); goto looped_back; } dst_input(skb); return -1; } static int ipv6_rpl_srh_rcv(struct sk_buff *skb) { struct ipv6_rpl_sr_hdr *hdr, *ohdr, *chdr; struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); struct inet6_dev *idev; struct ipv6hdr *oldhdr; unsigned char *buf; int accept_rpl_seg; int i, err; u64 n = 0; u32 r; idev = __in6_dev_get(skb->dev); accept_rpl_seg = net->ipv6.devconf_all->rpl_seg_enabled; if (accept_rpl_seg > idev->cnf.rpl_seg_enabled) accept_rpl_seg = idev->cnf.rpl_seg_enabled; if (!accept_rpl_seg) { kfree_skb(skb); return -1; } looped_back: hdr = (struct ipv6_rpl_sr_hdr *)skb_transport_header(skb); if (hdr->segments_left == 0) { if (hdr->nexthdr == NEXTHDR_IPV6) { int offset = (hdr->hdrlen + 1) << 3; skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); skb_pull(skb, offset); skb_postpull_rcsum(skb, skb_transport_header(skb), offset); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; __skb_tunnel_rx(skb, skb->dev, net); netif_rx(skb); return -1; } opt->srcrt = skb_network_header_len(skb); opt->lastopt = opt->srcrt; skb->transport_header += (hdr->hdrlen + 1) << 3; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } n = (hdr->hdrlen << 3) - hdr->pad - (16 - hdr->cmpre); r = do_div(n, (16 - hdr->cmpri)); /* checks if calculation was without remainder and n fits into * unsigned char which is segments_left field. Should not be * higher than that. */ if (r || (n + 1) > 255) { kfree_skb(skb); return -1; } if (hdr->segments_left > n + 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } hdr->segments_left--; i = n - hdr->segments_left; buf = kcalloc(struct_size(hdr, segments.addr, n + 2), 2, GFP_ATOMIC); if (unlikely(!buf)) { kfree_skb(skb); return -1; } ohdr = (struct ipv6_rpl_sr_hdr *)buf; ipv6_rpl_srh_decompress(ohdr, hdr, &ipv6_hdr(skb)->daddr, n); chdr = (struct ipv6_rpl_sr_hdr *)(buf + ((ohdr->hdrlen + 1) << 3)); if (ipv6_addr_is_multicast(&ohdr->rpl_segaddr[i])) { kfree_skb(skb); kfree(buf); return -1; } err = ipv6_chk_rpl_srh_loop(net, ohdr->rpl_segaddr, n + 1); if (err) { icmpv6_send(skb, ICMPV6_PARAMPROB, 0, 0); kfree_skb(skb); kfree(buf); return -1; } swap(ipv6_hdr(skb)->daddr, ohdr->rpl_segaddr[i]); ipv6_rpl_srh_compress(chdr, ohdr, &ipv6_hdr(skb)->daddr, n); oldhdr = ipv6_hdr(skb); skb_pull(skb, ((hdr->hdrlen + 1) << 3)); skb_postpull_rcsum(skb, oldhdr, sizeof(struct ipv6hdr) + ((hdr->hdrlen + 1) << 3)); if (unlikely(!hdr->segments_left)) { if (pskb_expand_head(skb, sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3), 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); kfree(buf); return -1; } oldhdr = ipv6_hdr(skb); } skb_push(skb, ((chdr->hdrlen + 1) << 3) + sizeof(struct ipv6hdr)); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); memmove(ipv6_hdr(skb), oldhdr, sizeof(struct ipv6hdr)); memcpy(skb_transport_header(skb), chdr, (chdr->hdrlen + 1) << 3); ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, ipv6_hdr(skb), sizeof(struct ipv6hdr) + ((chdr->hdrlen + 1) << 3)); kfree(buf); ip6_route_input(skb); if (skb_dst(skb)->error) { dst_input(skb); return -1; } if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; skb_pull(skb, sizeof(struct ipv6hdr)); goto looped_back; } dst_input(skb); return -1; } /******************************** Routing header. ********************************/ /* called with rcu_read_lock() */ static int ipv6_rthdr_rcv(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); struct in6_addr *addr = NULL; int n, i; struct ipv6_rt_hdr *hdr; struct rt0_hdr *rthdr; struct net *net = dev_net(skb->dev); int accept_source_route; accept_source_route = READ_ONCE(net->ipv6.devconf_all->accept_source_route); if (idev) accept_source_route = min(accept_source_route, READ_ONCE(idev->cnf.accept_source_route)); if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb); if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) || skb->pkt_type != PACKET_HOST) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } switch (hdr->type) { case IPV6_SRCRT_TYPE_4: /* segment routing */ return ipv6_srh_rcv(skb); case IPV6_SRCRT_TYPE_3: /* rpl segment routing */ return ipv6_rpl_srh_rcv(skb); default: break; } looped_back: if (hdr->segments_left == 0) { switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: /* Silently discard type 2 header unless it was * processed by own */ if (!addr) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } break; #endif default: break; } opt->lastopt = opt->srcrt = skb_network_header_len(skb); skb->transport_header += (hdr->hdrlen + 1) << 3; opt->dst0 = opt->dst1; opt->dst1 = 0; opt->nhoff = (&hdr->nexthdr) - skb_network_header(skb); return 1; } switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (accept_source_route < 0) goto unknown_rh; /* Silently discard invalid RTH type 2 */ if (hdr->hdrlen != 2 || hdr->segments_left != 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } break; #endif default: goto unknown_rh; } /* * This is the routing header forwarding algorithm from * RFC 2460, page 16. */ n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); return -1; } /* We are about to mangle packet header. Be careful! Do not damage packets queued somewhere. */ if (skb_cloned(skb)) { /* the copy is a forwarded packet */ if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return -1; } hdr = (struct ipv6_rt_hdr *)skb_transport_header(skb); } if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; i = n - --hdr->segments_left; rthdr = (struct rt0_hdr *) hdr; addr = rthdr->addr; addr += i - 1; switch (hdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, IPPROTO_ROUTING) < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } if (!ipv6_chk_home_addr(dev_net(skb_dst(skb)->dev), addr)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } break; #endif default: break; } if (ipv6_addr_is_multicast(addr)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } swap(*addr, ipv6_hdr(skb)->daddr); ip6_route_input(skb); if (skb_dst(skb)->error) { skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; } if (skb_dst(skb)->dev->flags&IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); return -1; } ipv6_hdr(skb)->hop_limit--; goto looped_back; } skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; unknown_rh: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb_network_header(skb)); return -1; } static const struct inet6_protocol rthdr_protocol = { .handler = ipv6_rthdr_rcv, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol destopt_protocol = { .handler = ipv6_destopt_rcv, .flags = INET6_PROTO_NOPOLICY, }; static const struct inet6_protocol nodata_protocol = { .handler = dst_discard, .flags = INET6_PROTO_NOPOLICY, }; int __init ipv6_exthdrs_init(void) { int ret; ret = inet6_add_protocol(&rthdr_protocol, IPPROTO_ROUTING); if (ret) goto out; ret = inet6_add_protocol(&destopt_protocol, IPPROTO_DSTOPTS); if (ret) goto out_rthdr; ret = inet6_add_protocol(&nodata_protocol, IPPROTO_NONE); if (ret) goto out_destopt; out: return ret; out_destopt: inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); out_rthdr: inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); goto out; }; void ipv6_exthdrs_exit(void) { inet6_del_protocol(&nodata_protocol, IPPROTO_NONE); inet6_del_protocol(&destopt_protocol, IPPROTO_DSTOPTS); inet6_del_protocol(&rthdr_protocol, IPPROTO_ROUTING); } /********************************** Hop-by-hop options. **********************************/ /* Router Alert as of RFC 2711 */ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] == 2) { IP6CB(skb)->flags |= IP6SKB_ROUTERALERT; memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra)); return true; } net_dbg_ratelimited("ipv6_hop_ra: wrong RA length %d\n", nh[optoff + 1]); kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /* IOAM */ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) { struct ioam6_trace_hdr *trace; struct ioam6_namespace *ns; struct ioam6_hdr *hdr; /* Bad alignment (must be 4n-aligned) */ if (optoff & 3) goto drop; /* Ignore if IOAM is not enabled on ingress */ if (!READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_enabled)) goto ignore; /* Truncated Option header */ hdr = (struct ioam6_hdr *)(skb_network_header(skb) + optoff); if (hdr->opt_len < 2) goto drop; switch (hdr->type) { case IOAM6_TYPE_PREALLOC: /* Truncated Pre-allocated Trace header */ if (hdr->opt_len < 2 + sizeof(*trace)) goto drop; /* Malformed Pre-allocated Trace header */ trace = (struct ioam6_trace_hdr *)((u8 *)hdr + sizeof(*hdr)); if (hdr->opt_len < 2 + sizeof(*trace) + trace->remlen * 4) goto drop; /* Ignore if the IOAM namespace is unknown */ ns = ioam6_namespace(dev_net(skb->dev), trace->namespace_id); if (!ns) goto ignore; if (!skb_valid_dst(skb)) ip6_route_input(skb); /* About to mangle packet header */ if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) goto drop; /* Trace pointer may have changed */ trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + optoff + sizeof(*hdr)); ioam6_fill_trace_data(skb, ns, trace, true); ioam6_event(IOAM6_EVENT_TRACE, dev_net(skb->dev), GFP_ATOMIC, (void *)trace, hdr->opt_len - 2); break; default: break; } ignore: return true; drop: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } /* Jumbo payload */ static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); SKB_DR(reason); u32 pkt_len; if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", nh[optoff+1]); SKB_DR_SET(reason, IP_INHDR); goto drop; } pkt_len = ntohl(*(__be32 *)(nh + optoff + 2)); if (pkt_len <= IPV6_MAXPLEN) { icmpv6_param_prob_reason(skb, ICMPV6_HDR_FIELD, optoff + 2, SKB_DROP_REASON_IP_INHDR); return false; } if (ipv6_hdr(skb)->payload_len) { icmpv6_param_prob_reason(skb, ICMPV6_HDR_FIELD, optoff, SKB_DROP_REASON_IP_INHDR); return false; } if (pkt_len > skb->len - sizeof(struct ipv6hdr)) { SKB_DR_SET(reason, PKT_TOO_SMALL); goto drop; } if (pskb_trim_rcsum(skb, pkt_len + sizeof(struct ipv6hdr))) goto drop; IP6CB(skb)->flags |= IP6SKB_JUMBOGRAM; return true; drop: kfree_skb_reason(skb, reason); return false; } /* CALIPSO RFC 5570 */ static bool ipv6_hop_calipso(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] < 8) goto drop; if (nh[optoff + 6] * 4 + 8 > nh[optoff + 1]) goto drop; if (!calipso_validate(skb, nh + optoff)) goto drop; return true; drop: kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return false; } int ipv6_parse_hopopts(struct sk_buff *skb) { struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(skb->dev); int extlen; /* * skb_network_header(skb) is equal to skb->data, and * skb_network_header_len(skb) is always equal to * sizeof(struct ipv6hdr) by definition of * hop-by-hop options. */ if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + 8) || !pskb_may_pull(skb, (sizeof(struct ipv6hdr) + ((skb_transport_header(skb)[1] + 1) << 3)))) { fail_and_free: kfree_skb(skb); return -1; } extlen = (skb_transport_header(skb)[1] + 1) << 3; if (extlen > net->ipv6.sysctl.max_hbh_opts_len) goto fail_and_free; opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(true, skb, net->ipv6.sysctl.max_hbh_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); return 1; } return -1; } /* * Creating outbound headers. * * "build" functions work when skb is filled from head to tail (datagram) * "push" functions work when headers are added from tail to head (tcp) * * In both cases we assume, that caller reserved enough room * for headers. */ static void ipv6_push_rthdr0(struct sk_buff *skb, u8 *proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { struct rt0_hdr *phdr, *ihdr; int hops; ihdr = (struct rt0_hdr *) opt; phdr = skb_push(skb, (ihdr->rt_hdr.hdrlen + 1) << 3); memcpy(phdr, ihdr, sizeof(struct rt0_hdr)); hops = ihdr->rt_hdr.hdrlen >> 1; if (hops > 1) memcpy(phdr->addr, ihdr->addr + 1, (hops - 1) * sizeof(struct in6_addr)); phdr->addr[hops - 1] = **addr_p; *addr_p = ihdr->addr; phdr->rt_hdr.nexthdr = *proto; *proto = NEXTHDR_ROUTING; } static void ipv6_push_rthdr4(struct sk_buff *skb, u8 *proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { struct ipv6_sr_hdr *sr_phdr, *sr_ihdr; int plen, hops; sr_ihdr = (struct ipv6_sr_hdr *)opt; plen = (sr_ihdr->hdrlen + 1) << 3; sr_phdr = skb_push(skb, plen); memcpy(sr_phdr, sr_ihdr, sizeof(struct ipv6_sr_hdr)); hops = sr_ihdr->first_segment + 1; memcpy(sr_phdr->segments + 1, sr_ihdr->segments + 1, (hops - 1) * sizeof(struct in6_addr)); sr_phdr->segments[0] = **addr_p; *addr_p = &sr_ihdr->segments[sr_ihdr->segments_left]; if (sr_ihdr->hdrlen > hops * 2) { int tlvs_offset, tlvs_length; tlvs_offset = (1 + hops * 2) << 3; tlvs_length = (sr_ihdr->hdrlen - hops * 2) << 3; memcpy((char *)sr_phdr + tlvs_offset, (char *)sr_ihdr + tlvs_offset, tlvs_length); } #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(sr_phdr)) { struct net *net = NULL; if (skb->dev) net = dev_net(skb->dev); else if (skb->sk) net = sock_net(skb->sk); WARN_ON(!net); if (net) seg6_push_hmac(net, saddr, sr_phdr); } #endif sr_phdr->nexthdr = *proto; *proto = NEXTHDR_ROUTING; } static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto, struct ipv6_rt_hdr *opt, struct in6_addr **addr_p, struct in6_addr *saddr) { switch (opt->type) { case IPV6_SRCRT_TYPE_0: case IPV6_SRCRT_STRICT: case IPV6_SRCRT_TYPE_2: ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr); break; case IPV6_SRCRT_TYPE_4: ipv6_push_rthdr4(skb, proto, opt, addr_p, saddr); break; default: break; } } static void ipv6_push_exthdr(struct sk_buff *skb, u8 *proto, u8 type, struct ipv6_opt_hdr *opt) { struct ipv6_opt_hdr *h = skb_push(skb, ipv6_optlen(opt)); memcpy(h, opt, ipv6_optlen(opt)); h->nexthdr = *proto; *proto = type; } void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto, struct in6_addr **daddr, struct in6_addr *saddr) { if (opt->srcrt) { ipv6_push_rthdr(skb, proto, opt->srcrt, daddr, saddr); /* * IPV6_RTHDRDSTOPTS is ignored * unless IPV6_RTHDR is set (RFC3542). */ if (opt->dst0opt) ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst0opt); } if (opt->hopopt) ipv6_push_exthdr(skb, proto, NEXTHDR_HOP, opt->hopopt); } void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto) { if (opt->dst1opt) ipv6_push_exthdr(skb, proto, NEXTHDR_DEST, opt->dst1opt); } EXPORT_SYMBOL(ipv6_push_frag_opts); struct ipv6_txoptions * ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) { struct ipv6_txoptions *opt2; opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC); if (opt2) { long dif = (char *)opt2 - (char *)opt; memcpy(opt2, opt, opt->tot_len); if (opt2->hopopt) *((char **)&opt2->hopopt) += dif; if (opt2->dst0opt) *((char **)&opt2->dst0opt) += dif; if (opt2->dst1opt) *((char **)&opt2->dst1opt) += dif; if (opt2->srcrt) *((char **)&opt2->srcrt) += dif; refcount_set(&opt2->refcnt, 1); } return opt2; } EXPORT_SYMBOL_GPL(ipv6_dup_options); static void ipv6_renew_option(int renewtype, struct ipv6_opt_hdr **dest, struct ipv6_opt_hdr *old, struct ipv6_opt_hdr *new, int newtype, char **p) { struct ipv6_opt_hdr *src; src = (renewtype == newtype ? new : old); if (!src) return; memcpy(*p, src, ipv6_optlen(src)); *dest = (struct ipv6_opt_hdr *)*p; *p += CMSG_ALIGN(ipv6_optlen(*dest)); } /** * ipv6_renew_options - replace a specific ext hdr with a new one. * * @sk: sock from which to allocate memory * @opt: original options * @newtype: option type to replace in @opt * @newopt: new option of type @newtype to replace (user-mem) * * Returns a new set of options which is a copy of @opt with the * option type @newtype replaced with @newopt. * * @opt may be NULL, in which case a new set of options is returned * containing just @newopt. * * @newopt may be NULL, in which case the specified option type is * not copied into the new set of options. * * The new set of options is allocated from the socket option memory * buffer of @sk. */ struct ipv6_txoptions * ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt) { int tot_len = 0; char *p; struct ipv6_txoptions *opt2; if (opt) { if (newtype != IPV6_HOPOPTS && opt->hopopt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->hopopt)); if (newtype != IPV6_RTHDRDSTOPTS && opt->dst0opt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst0opt)); if (newtype != IPV6_RTHDR && opt->srcrt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->srcrt)); if (newtype != IPV6_DSTOPTS && opt->dst1opt) tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt)); } if (newopt) tot_len += CMSG_ALIGN(ipv6_optlen(newopt)); if (!tot_len) return NULL; tot_len += sizeof(*opt2); opt2 = sock_kmalloc(sk, tot_len, GFP_ATOMIC); if (!opt2) return ERR_PTR(-ENOBUFS); memset(opt2, 0, tot_len); refcount_set(&opt2->refcnt, 1); opt2->tot_len = tot_len; p = (char *)(opt2 + 1); ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt, (opt ? opt->hopopt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt, (opt ? opt->dst0opt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_RTHDR, (struct ipv6_opt_hdr **)&opt2->srcrt, (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL), newopt, newtype, &p); ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt, (opt ? opt->dst1opt : NULL), newopt, newtype, &p); opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) + (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) + (opt2->srcrt ? ipv6_optlen(opt2->srcrt) : 0); opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0); return opt2; } struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) { /* * ignore the dest before srcrt unless srcrt is being included. * --yoshfuji */ if (opt->dst0opt && !opt->srcrt) { if (opt_space != opt) { memcpy(opt_space, opt, sizeof(*opt_space)); opt = opt_space; } opt->opt_nflen -= ipv6_optlen(opt->dst0opt); opt->dst0opt = NULL; } return opt; } EXPORT_SYMBOL_GPL(__ipv6_fixup_options); /** * fl6_update_dst - update flowi destination address with info given * by srcrt option, if any. * * @fl6: flowi6 for which daddr is to be updated * @opt: struct ipv6_txoptions in which to look for srcrt opt * @orig: copy of original daddr address if modified * * Returns NULL if no txoptions or no srcrt, otherwise returns orig * and initial value of fl6->daddr set in orig */ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig) { if (!opt || !opt->srcrt) return NULL; *orig = fl6->daddr; switch (opt->srcrt->type) { case IPV6_SRCRT_TYPE_0: case IPV6_SRCRT_STRICT: case IPV6_SRCRT_TYPE_2: fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr; break; case IPV6_SRCRT_TYPE_4: { struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)opt->srcrt; fl6->daddr = srh->segments[srh->segments_left]; break; } default: return NULL; } return orig; } EXPORT_SYMBOL_GPL(fl6_update_dst); |
| 170 16 228 147 125 105 85 124 171 170 34 21 31 42 42 38 13 4 10 40 39 1 1 20 20 10 20 20 9 31 31 8 8 5 5 13 8 7 41 16 36 37 133 29 111 53 52 126 134 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 | // SPDX-License-Identifier: GPL-2.0+ /* * NILFS block mapping. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * * Written by Koji Sato. */ #include <linux/fs.h> #include <linux/string.h> #include <linux/errno.h> #include "nilfs.h" #include "bmap.h" #include "btree.h" #include "direct.h" #include "btnode.h" #include "mdt.h" #include "dat.h" #include "alloc.h" struct inode *nilfs_bmap_get_dat(const struct nilfs_bmap *bmap) { struct the_nilfs *nilfs = bmap->b_inode->i_sb->s_fs_info; return nilfs->ns_dat; } static int nilfs_bmap_convert_error(struct nilfs_bmap *bmap, const char *fname, int err) { struct inode *inode = bmap->b_inode; if (err == -EINVAL) { __nilfs_error(inode->i_sb, fname, "broken bmap (inode number=%lu)", inode->i_ino); err = -EIO; } return err; } /** * nilfs_bmap_lookup_at_level - find a data block or node block * @bmap: bmap * @key: key * @level: level * @ptrp: place to store the value associated to @key * * Description: nilfs_bmap_lookup_at_level() finds a record whose key * matches @key in the block at @level of the bmap. * * Return Value: On success, 0 is returned and the record associated with @key * is stored in the place pointed by @ptrp. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-ENOENT - A record associated with @key does not exist. */ int nilfs_bmap_lookup_at_level(struct nilfs_bmap *bmap, __u64 key, int level, __u64 *ptrp) { sector_t blocknr; int ret; down_read(&bmap->b_sem); ret = bmap->b_ops->bop_lookup(bmap, key, level, ptrp); if (ret < 0) goto out; if (NILFS_BMAP_USE_VBN(bmap)) { ret = nilfs_dat_translate(nilfs_bmap_get_dat(bmap), *ptrp, &blocknr); if (!ret) *ptrp = blocknr; else if (ret == -ENOENT) { /* * If there was no valid entry in DAT for the block * address obtained by b_ops->bop_lookup, then pass * internal code -EINVAL to nilfs_bmap_convert_error * to treat it as metadata corruption. */ ret = -EINVAL; } } out: up_read(&bmap->b_sem); return nilfs_bmap_convert_error(bmap, __func__, ret); } int nilfs_bmap_lookup_contig(struct nilfs_bmap *bmap, __u64 key, __u64 *ptrp, unsigned int maxblocks) { int ret; down_read(&bmap->b_sem); ret = bmap->b_ops->bop_lookup_contig(bmap, key, ptrp, maxblocks); up_read(&bmap->b_sem); return nilfs_bmap_convert_error(bmap, __func__, ret); } static int nilfs_bmap_do_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr) { __u64 keys[NILFS_BMAP_SMALL_HIGH + 1]; __u64 ptrs[NILFS_BMAP_SMALL_HIGH + 1]; int ret, n; if (bmap->b_ops->bop_check_insert != NULL) { ret = bmap->b_ops->bop_check_insert(bmap, key); if (ret > 0) { n = bmap->b_ops->bop_gather_data( bmap, keys, ptrs, NILFS_BMAP_SMALL_HIGH + 1); if (n < 0) return n; ret = nilfs_btree_convert_and_insert( bmap, key, ptr, keys, ptrs, n); if (ret == 0) bmap->b_u.u_flags |= NILFS_BMAP_LARGE; return ret; } else if (ret < 0) return ret; } return bmap->b_ops->bop_insert(bmap, key, ptr); } /** * nilfs_bmap_insert - insert a new key-record pair into a bmap * @bmap: bmap * @key: key * @rec: record * * Description: nilfs_bmap_insert() inserts the new key-record pair specified * by @key and @rec into @bmap. * * Return Value: On success, 0 is returned. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-EEXIST - A record associated with @key already exist. */ int nilfs_bmap_insert(struct nilfs_bmap *bmap, __u64 key, unsigned long rec) { int ret; down_write(&bmap->b_sem); ret = nilfs_bmap_do_insert(bmap, key, rec); up_write(&bmap->b_sem); return nilfs_bmap_convert_error(bmap, __func__, ret); } static int nilfs_bmap_do_delete(struct nilfs_bmap *bmap, __u64 key) { __u64 keys[NILFS_BMAP_LARGE_LOW + 1]; __u64 ptrs[NILFS_BMAP_LARGE_LOW + 1]; int ret, n; if (bmap->b_ops->bop_check_delete != NULL) { ret = bmap->b_ops->bop_check_delete(bmap, key); if (ret > 0) { n = bmap->b_ops->bop_gather_data( bmap, keys, ptrs, NILFS_BMAP_LARGE_LOW + 1); if (n < 0) return n; ret = nilfs_direct_delete_and_convert( bmap, key, keys, ptrs, n); if (ret == 0) bmap->b_u.u_flags &= ~NILFS_BMAP_LARGE; return ret; } else if (ret < 0) return ret; } return bmap->b_ops->bop_delete(bmap, key); } /** * nilfs_bmap_seek_key - seek a valid entry and return its key * @bmap: bmap struct * @start: start key number * @keyp: place to store valid key * * Description: nilfs_bmap_seek_key() seeks a valid key on @bmap * starting from @start, and stores it to @keyp if found. * * Return Value: On success, 0 is returned. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-ENOENT - No valid entry was found */ int nilfs_bmap_seek_key(struct nilfs_bmap *bmap, __u64 start, __u64 *keyp) { int ret; down_read(&bmap->b_sem); ret = bmap->b_ops->bop_seek_key(bmap, start, keyp); up_read(&bmap->b_sem); if (ret < 0) ret = nilfs_bmap_convert_error(bmap, __func__, ret); return ret; } int nilfs_bmap_last_key(struct nilfs_bmap *bmap, __u64 *keyp) { int ret; down_read(&bmap->b_sem); ret = bmap->b_ops->bop_last_key(bmap, keyp); up_read(&bmap->b_sem); if (ret < 0) ret = nilfs_bmap_convert_error(bmap, __func__, ret); return ret; } /** * nilfs_bmap_delete - delete a key-record pair from a bmap * @bmap: bmap * @key: key * * Description: nilfs_bmap_delete() deletes the key-record pair specified by * @key from @bmap. * * Return Value: On success, 0 is returned. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. * * %-ENOENT - A record associated with @key does not exist. */ int nilfs_bmap_delete(struct nilfs_bmap *bmap, __u64 key) { int ret; down_write(&bmap->b_sem); ret = nilfs_bmap_do_delete(bmap, key); up_write(&bmap->b_sem); return nilfs_bmap_convert_error(bmap, __func__, ret); } static int nilfs_bmap_do_truncate(struct nilfs_bmap *bmap, __u64 key) { __u64 lastkey; int ret; ret = bmap->b_ops->bop_last_key(bmap, &lastkey); if (ret < 0) { if (ret == -ENOENT) ret = 0; return ret; } while (key <= lastkey) { ret = nilfs_bmap_do_delete(bmap, lastkey); if (ret < 0) return ret; ret = bmap->b_ops->bop_last_key(bmap, &lastkey); if (ret < 0) { if (ret == -ENOENT) ret = 0; return ret; } } return 0; } /** * nilfs_bmap_truncate - truncate a bmap to a specified key * @bmap: bmap * @key: key * * Description: nilfs_bmap_truncate() removes key-record pairs whose keys are * greater than or equal to @key from @bmap. * * Return Value: On success, 0 is returned. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. */ int nilfs_bmap_truncate(struct nilfs_bmap *bmap, __u64 key) { int ret; down_write(&bmap->b_sem); ret = nilfs_bmap_do_truncate(bmap, key); up_write(&bmap->b_sem); return nilfs_bmap_convert_error(bmap, __func__, ret); } /** * nilfs_bmap_clear - free resources a bmap holds * @bmap: bmap * * Description: nilfs_bmap_clear() frees resources associated with @bmap. */ void nilfs_bmap_clear(struct nilfs_bmap *bmap) { down_write(&bmap->b_sem); if (bmap->b_ops->bop_clear != NULL) bmap->b_ops->bop_clear(bmap); up_write(&bmap->b_sem); } /** * nilfs_bmap_propagate - propagate dirty state * @bmap: bmap * @bh: buffer head * * Description: nilfs_bmap_propagate() marks the buffers that directly or * indirectly refer to the block specified by @bh dirty. * * Return Value: On success, 0 is returned. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. */ int nilfs_bmap_propagate(struct nilfs_bmap *bmap, struct buffer_head *bh) { int ret; down_write(&bmap->b_sem); ret = bmap->b_ops->bop_propagate(bmap, bh); up_write(&bmap->b_sem); return nilfs_bmap_convert_error(bmap, __func__, ret); } /** * nilfs_bmap_lookup_dirty_buffers - collect dirty block buffers * @bmap: bmap * @listp: pointer to buffer head list */ void nilfs_bmap_lookup_dirty_buffers(struct nilfs_bmap *bmap, struct list_head *listp) { if (bmap->b_ops->bop_lookup_dirty_buffers != NULL) bmap->b_ops->bop_lookup_dirty_buffers(bmap, listp); } /** * nilfs_bmap_assign - assign a new block number to a block * @bmap: bmap * @bh: pointer to buffer head * @blocknr: block number * @binfo: block information * * Description: nilfs_bmap_assign() assigns the block number @blocknr to the * buffer specified by @bh. * * Return Value: On success, 0 is returned and the buffer head of a newly * create buffer and the block information associated with the buffer are * stored in the place pointed by @bh and @binfo, respectively. On error, one * of the following negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. */ int nilfs_bmap_assign(struct nilfs_bmap *bmap, struct buffer_head **bh, unsigned long blocknr, union nilfs_binfo *binfo) { int ret; down_write(&bmap->b_sem); ret = bmap->b_ops->bop_assign(bmap, bh, blocknr, binfo); up_write(&bmap->b_sem); return nilfs_bmap_convert_error(bmap, __func__, ret); } /** * nilfs_bmap_mark - mark block dirty * @bmap: bmap * @key: key * @level: level * * Description: nilfs_bmap_mark() marks the block specified by @key and @level * as dirty. * * Return Value: On success, 0 is returned. On error, one of the following * negative error codes is returned. * * %-EIO - I/O error. * * %-ENOMEM - Insufficient amount of memory available. */ int nilfs_bmap_mark(struct nilfs_bmap *bmap, __u64 key, int level) { int ret; if (bmap->b_ops->bop_mark == NULL) return 0; down_write(&bmap->b_sem); ret = bmap->b_ops->bop_mark(bmap, key, level); up_write(&bmap->b_sem); return nilfs_bmap_convert_error(bmap, __func__, ret); } /** * nilfs_bmap_test_and_clear_dirty - test and clear a bmap dirty state * @bmap: bmap * * Description: nilfs_test_and_clear() is the atomic operation to test and * clear the dirty state of @bmap. * * Return Value: 1 is returned if @bmap is dirty, or 0 if clear. */ int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *bmap) { int ret; down_write(&bmap->b_sem); ret = nilfs_bmap_dirty(bmap); nilfs_bmap_clear_dirty(bmap); up_write(&bmap->b_sem); return ret; } /* * Internal use only */ __u64 nilfs_bmap_data_get_key(const struct nilfs_bmap *bmap, const struct buffer_head *bh) { loff_t pos = folio_pos(bh->b_folio) + bh_offset(bh); return pos >> bmap->b_inode->i_blkbits; } __u64 nilfs_bmap_find_target_seq(const struct nilfs_bmap *bmap, __u64 key) { __s64 diff; diff = key - bmap->b_last_allocated_key; if ((nilfs_bmap_keydiff_abs(diff) < NILFS_INODE_BMAP_SIZE) && (bmap->b_last_allocated_ptr != NILFS_BMAP_INVALID_PTR) && (bmap->b_last_allocated_ptr + diff > 0)) return bmap->b_last_allocated_ptr + diff; else return NILFS_BMAP_INVALID_PTR; } #define NILFS_BMAP_GROUP_DIV 8 __u64 nilfs_bmap_find_target_in_group(const struct nilfs_bmap *bmap) { struct inode *dat = nilfs_bmap_get_dat(bmap); unsigned long entries_per_group = nilfs_palloc_entries_per_group(dat); unsigned long group = bmap->b_inode->i_ino / entries_per_group; return group * entries_per_group + (bmap->b_inode->i_ino % NILFS_BMAP_GROUP_DIV) * (entries_per_group / NILFS_BMAP_GROUP_DIV); } static struct lock_class_key nilfs_bmap_dat_lock_key; static struct lock_class_key nilfs_bmap_mdt_lock_key; /** * nilfs_bmap_read - read a bmap from an inode * @bmap: bmap * @raw_inode: on-disk inode * * Description: nilfs_bmap_read() initializes the bmap @bmap. * * Return Value: On success, 0 is returned. On error, the following negative * error code is returned. * * %-ENOMEM - Insufficient amount of memory available. */ int nilfs_bmap_read(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode) { if (raw_inode == NULL) memset(bmap->b_u.u_data, 0, NILFS_BMAP_SIZE); else memcpy(bmap->b_u.u_data, raw_inode->i_bmap, NILFS_BMAP_SIZE); init_rwsem(&bmap->b_sem); bmap->b_state = 0; bmap->b_inode = &NILFS_BMAP_I(bmap)->vfs_inode; switch (bmap->b_inode->i_ino) { case NILFS_DAT_INO: bmap->b_ptr_type = NILFS_BMAP_PTR_P; bmap->b_last_allocated_key = 0; bmap->b_last_allocated_ptr = NILFS_BMAP_NEW_PTR_INIT; lockdep_set_class(&bmap->b_sem, &nilfs_bmap_dat_lock_key); break; case NILFS_CPFILE_INO: case NILFS_SUFILE_INO: bmap->b_ptr_type = NILFS_BMAP_PTR_VS; bmap->b_last_allocated_key = 0; bmap->b_last_allocated_ptr = NILFS_BMAP_INVALID_PTR; lockdep_set_class(&bmap->b_sem, &nilfs_bmap_mdt_lock_key); break; case NILFS_IFILE_INO: lockdep_set_class(&bmap->b_sem, &nilfs_bmap_mdt_lock_key); fallthrough; default: bmap->b_ptr_type = NILFS_BMAP_PTR_VM; bmap->b_last_allocated_key = 0; bmap->b_last_allocated_ptr = NILFS_BMAP_INVALID_PTR; break; } return (bmap->b_u.u_flags & NILFS_BMAP_LARGE) ? nilfs_btree_init(bmap) : nilfs_direct_init(bmap); } /** * nilfs_bmap_write - write back a bmap to an inode * @bmap: bmap * @raw_inode: on-disk inode * * Description: nilfs_bmap_write() stores @bmap in @raw_inode. */ void nilfs_bmap_write(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode) { memcpy(raw_inode->i_bmap, bmap->b_u.u_data, NILFS_INODE_BMAP_SIZE * sizeof(__le64)); if (bmap->b_inode->i_ino == NILFS_DAT_INO) bmap->b_last_allocated_ptr = NILFS_BMAP_NEW_PTR_INIT; } void nilfs_bmap_init_gc(struct nilfs_bmap *bmap) { memset(&bmap->b_u, 0, NILFS_BMAP_SIZE); init_rwsem(&bmap->b_sem); bmap->b_inode = &NILFS_BMAP_I(bmap)->vfs_inode; bmap->b_ptr_type = NILFS_BMAP_PTR_U; bmap->b_last_allocated_key = 0; bmap->b_last_allocated_ptr = NILFS_BMAP_INVALID_PTR; bmap->b_state = 0; nilfs_btree_init_gc(bmap); } void nilfs_bmap_save(const struct nilfs_bmap *bmap, struct nilfs_bmap_store *store) { memcpy(store->data, bmap->b_u.u_data, sizeof(store->data)); store->last_allocated_key = bmap->b_last_allocated_key; store->last_allocated_ptr = bmap->b_last_allocated_ptr; store->state = bmap->b_state; } void nilfs_bmap_restore(struct nilfs_bmap *bmap, const struct nilfs_bmap_store *store) { memcpy(bmap->b_u.u_data, store->data, sizeof(store->data)); bmap->b_last_allocated_key = store->last_allocated_key; bmap->b_last_allocated_ptr = store->last_allocated_ptr; bmap->b_state = store->state; } |
| 2938 1973 970 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __LICENSE_H #define __LICENSE_H static inline int license_is_gpl_compatible(const char *license) { return (strcmp(license, "GPL") == 0 || strcmp(license, "GPL v2") == 0 || strcmp(license, "GPL and additional rights") == 0 || strcmp(license, "Dual BSD/GPL") == 0 || strcmp(license, "Dual MIT/GPL") == 0 || strcmp(license, "Dual MPL/GPL") == 0); } #endif |
| 2748 2715 11 482 189 1474 1476 1475 1477 483 1507 68 4 79 40 1342 209 1478 11 1470 3 1 604 913 837 833 694 912 1470 7 4 682 926 17 1335 1364 222 1327 251 392 1474 127 2512 7 154 1 2709 11 2706 54 2667 1578 2701 174 1512 2220 547 22 2721 23 2739 9 504 1752 7 4 2124 621 2708 85 151 2 10 266 2453 25 189 151 2122 646 2704 2709 2748 2741 2716 2746 2705 84 2374 2557 15 29 2554 2552 2554 2512 2747 28 2724 2 2751 2 2749 1 2676 72 2752 2559 2541 19 135 115 1 1 16 2 2 1 2 3 4 2 2 4 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * Released under the GPLv2 only. */ #include <linux/usb.h> #include <linux/usb/ch9.h> #include <linux/usb/hcd.h> #include <linux/usb/quirks.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/device.h> #include <asm/byteorder.h> #include "usb.h" #define USB_MAXALTSETTING 128 /* Hard limit */ #define USB_MAXCONFIG 8 /* Arbitrary limit */ static inline const char *plural(int n) { return (n == 1 ? "" : "s"); } static int find_next_descriptor(unsigned char *buffer, int size, int dt1, int dt2, int *num_skipped) { struct usb_descriptor_header *h; int n = 0; unsigned char *buffer0 = buffer; /* Find the next descriptor of type dt1 or dt2 */ while (size > 0) { h = (struct usb_descriptor_header *) buffer; if (h->bDescriptorType == dt1 || h->bDescriptorType == dt2) break; buffer += h->bLength; size -= h->bLength; ++n; } /* Store the number of descriptors skipped and return the * number of bytes skipped */ if (num_skipped) *num_skipped = n; return buffer - buffer0; } static void usb_parse_ssp_isoc_endpoint_companion(struct device *ddev, int cfgno, int inum, int asnum, struct usb_host_endpoint *ep, unsigned char *buffer, int size) { struct usb_ssp_isoc_ep_comp_descriptor *desc; /* * The SuperSpeedPlus Isoc endpoint companion descriptor immediately * follows the SuperSpeed Endpoint Companion descriptor */ desc = (struct usb_ssp_isoc_ep_comp_descriptor *) buffer; if (desc->bDescriptorType != USB_DT_SSP_ISOC_ENDPOINT_COMP || size < USB_DT_SSP_ISOC_EP_COMP_SIZE) { dev_notice(ddev, "Invalid SuperSpeedPlus isoc endpoint companion" "for config %d interface %d altsetting %d ep %d.\n", cfgno, inum, asnum, ep->desc.bEndpointAddress); return; } memcpy(&ep->ssp_isoc_ep_comp, desc, USB_DT_SSP_ISOC_EP_COMP_SIZE); } static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno, int inum, int asnum, struct usb_host_endpoint *ep, unsigned char *buffer, int size) { struct usb_ss_ep_comp_descriptor *desc; int max_tx; /* The SuperSpeed endpoint companion descriptor is supposed to * be the first thing immediately following the endpoint descriptor. */ desc = (struct usb_ss_ep_comp_descriptor *) buffer; if (desc->bDescriptorType != USB_DT_SS_ENDPOINT_COMP || size < USB_DT_SS_EP_COMP_SIZE) { dev_notice(ddev, "No SuperSpeed endpoint companion for config %d " " interface %d altsetting %d ep %d: " "using minimum values\n", cfgno, inum, asnum, ep->desc.bEndpointAddress); /* Fill in some default values. * Leave bmAttributes as zero, which will mean no streams for * bulk, and isoc won't support multiple bursts of packets. * With bursts of only one packet, and a Mult of 1, the max * amount of data moved per endpoint service interval is one * packet. */ ep->ss_ep_comp.bLength = USB_DT_SS_EP_COMP_SIZE; ep->ss_ep_comp.bDescriptorType = USB_DT_SS_ENDPOINT_COMP; if (usb_endpoint_xfer_isoc(&ep->desc) || usb_endpoint_xfer_int(&ep->desc)) ep->ss_ep_comp.wBytesPerInterval = ep->desc.wMaxPacketSize; return; } buffer += desc->bLength; size -= desc->bLength; memcpy(&ep->ss_ep_comp, desc, USB_DT_SS_EP_COMP_SIZE); /* Check the various values */ if (usb_endpoint_xfer_control(&ep->desc) && desc->bMaxBurst != 0) { dev_notice(ddev, "Control endpoint with bMaxBurst = %d in " "config %d interface %d altsetting %d ep %d: " "setting to zero\n", desc->bMaxBurst, cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bMaxBurst = 0; } else if (desc->bMaxBurst > 15) { dev_notice(ddev, "Endpoint with bMaxBurst = %d in " "config %d interface %d altsetting %d ep %d: " "setting to 15\n", desc->bMaxBurst, cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bMaxBurst = 15; } if ((usb_endpoint_xfer_control(&ep->desc) || usb_endpoint_xfer_int(&ep->desc)) && desc->bmAttributes != 0) { dev_notice(ddev, "%s endpoint with bmAttributes = %d in " "config %d interface %d altsetting %d ep %d: " "setting to zero\n", usb_endpoint_xfer_control(&ep->desc) ? "Control" : "Bulk", desc->bmAttributes, cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bmAttributes = 0; } else if (usb_endpoint_xfer_bulk(&ep->desc) && desc->bmAttributes > 16) { dev_notice(ddev, "Bulk endpoint with more than 65536 streams in " "config %d interface %d altsetting %d ep %d: " "setting to max\n", cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bmAttributes = 16; } else if (usb_endpoint_xfer_isoc(&ep->desc) && !USB_SS_SSP_ISOC_COMP(desc->bmAttributes) && USB_SS_MULT(desc->bmAttributes) > 3) { dev_notice(ddev, "Isoc endpoint has Mult of %d in " "config %d interface %d altsetting %d ep %d: " "setting to 3\n", USB_SS_MULT(desc->bmAttributes), cfgno, inum, asnum, ep->desc.bEndpointAddress); ep->ss_ep_comp.bmAttributes = 2; } if (usb_endpoint_xfer_isoc(&ep->desc)) max_tx = (desc->bMaxBurst + 1) * (USB_SS_MULT(desc->bmAttributes)) * usb_endpoint_maxp(&ep->desc); else if (usb_endpoint_xfer_int(&ep->desc)) max_tx = usb_endpoint_maxp(&ep->desc) * (desc->bMaxBurst + 1); else max_tx = 999999; if (le16_to_cpu(desc->wBytesPerInterval) > max_tx) { dev_notice(ddev, "%s endpoint with wBytesPerInterval of %d in " "config %d interface %d altsetting %d ep %d: " "setting to %d\n", usb_endpoint_xfer_isoc(&ep->desc) ? "Isoc" : "Int", le16_to_cpu(desc->wBytesPerInterval), cfgno, inum, asnum, ep->desc.bEndpointAddress, max_tx); ep->ss_ep_comp.wBytesPerInterval = cpu_to_le16(max_tx); } /* Parse a possible SuperSpeedPlus isoc ep companion descriptor */ if (usb_endpoint_xfer_isoc(&ep->desc) && USB_SS_SSP_ISOC_COMP(desc->bmAttributes)) usb_parse_ssp_isoc_endpoint_companion(ddev, cfgno, inum, asnum, ep, buffer, size); } static const unsigned short low_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 8, [USB_ENDPOINT_XFER_ISOC] = 0, [USB_ENDPOINT_XFER_BULK] = 0, [USB_ENDPOINT_XFER_INT] = 8, }; static const unsigned short full_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 64, [USB_ENDPOINT_XFER_ISOC] = 1023, [USB_ENDPOINT_XFER_BULK] = 64, [USB_ENDPOINT_XFER_INT] = 64, }; static const unsigned short high_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 64, [USB_ENDPOINT_XFER_ISOC] = 1024, /* Bulk should be 512, but some devices use 1024: we will warn below */ [USB_ENDPOINT_XFER_BULK] = 1024, [USB_ENDPOINT_XFER_INT] = 1024, }; static const unsigned short super_speed_maxpacket_maxes[4] = { [USB_ENDPOINT_XFER_CONTROL] = 512, [USB_ENDPOINT_XFER_ISOC] = 1024, [USB_ENDPOINT_XFER_BULK] = 1024, [USB_ENDPOINT_XFER_INT] = 1024, }; static bool endpoint_is_duplicate(struct usb_endpoint_descriptor *e1, struct usb_endpoint_descriptor *e2) { if (e1->bEndpointAddress == e2->bEndpointAddress) return true; if (usb_endpoint_xfer_control(e1) || usb_endpoint_xfer_control(e2)) { if (usb_endpoint_num(e1) == usb_endpoint_num(e2)) return true; } return false; } /* * Check for duplicate endpoint addresses in other interfaces and in the * altsetting currently being parsed. */ static bool config_endpoint_is_duplicate(struct usb_host_config *config, int inum, int asnum, struct usb_endpoint_descriptor *d) { struct usb_endpoint_descriptor *epd; struct usb_interface_cache *intfc; struct usb_host_interface *alt; int i, j, k; for (i = 0; i < config->desc.bNumInterfaces; ++i) { intfc = config->intf_cache[i]; for (j = 0; j < intfc->num_altsetting; ++j) { alt = &intfc->altsetting[j]; if (alt->desc.bInterfaceNumber == inum && alt->desc.bAlternateSetting != asnum) continue; for (k = 0; k < alt->desc.bNumEndpoints; ++k) { epd = &alt->endpoint[k].desc; if (endpoint_is_duplicate(epd, d)) return true; } } } return false; } static int usb_parse_endpoint(struct device *ddev, int cfgno, struct usb_host_config *config, int inum, int asnum, struct usb_host_interface *ifp, int num_ep, unsigned char *buffer, int size) { struct usb_device *udev = to_usb_device(ddev); unsigned char *buffer0 = buffer; struct usb_endpoint_descriptor *d; struct usb_host_endpoint *endpoint; int n, i, j, retval; unsigned int maxp; const unsigned short *maxpacket_maxes; d = (struct usb_endpoint_descriptor *) buffer; buffer += d->bLength; size -= d->bLength; if (d->bLength >= USB_DT_ENDPOINT_AUDIO_SIZE) n = USB_DT_ENDPOINT_AUDIO_SIZE; else if (d->bLength >= USB_DT_ENDPOINT_SIZE) n = USB_DT_ENDPOINT_SIZE; else { dev_notice(ddev, "config %d interface %d altsetting %d has an " "invalid endpoint descriptor of length %d, skipping\n", cfgno, inum, asnum, d->bLength); goto skip_to_next_endpoint_or_interface_descriptor; } i = d->bEndpointAddress & USB_ENDPOINT_NUMBER_MASK; if (i == 0) { dev_notice(ddev, "config %d interface %d altsetting %d has an " "invalid descriptor for endpoint zero, skipping\n", cfgno, inum, asnum); goto skip_to_next_endpoint_or_interface_descriptor; } /* Only store as many endpoints as we have room for */ if (ifp->desc.bNumEndpoints >= num_ep) goto skip_to_next_endpoint_or_interface_descriptor; /* Save a copy of the descriptor and use it instead of the original */ endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints]; memcpy(&endpoint->desc, d, n); d = &endpoint->desc; /* Clear the reserved bits in bEndpointAddress */ i = d->bEndpointAddress & (USB_ENDPOINT_DIR_MASK | USB_ENDPOINT_NUMBER_MASK); if (i != d->bEndpointAddress) { dev_notice(ddev, "config %d interface %d altsetting %d has an endpoint descriptor with address 0x%X, changing to 0x%X\n", cfgno, inum, asnum, d->bEndpointAddress, i); endpoint->desc.bEndpointAddress = i; } /* Check for duplicate endpoint addresses */ if (config_endpoint_is_duplicate(config, inum, asnum, d)) { dev_notice(ddev, "config %d interface %d altsetting %d has a duplicate endpoint with address 0x%X, skipping\n", cfgno, inum, asnum, d->bEndpointAddress); goto skip_to_next_endpoint_or_interface_descriptor; } /* Ignore some endpoints */ if (udev->quirks & USB_QUIRK_ENDPOINT_IGNORE) { if (usb_endpoint_is_ignored(udev, ifp, d)) { dev_notice(ddev, "config %d interface %d altsetting %d has an ignored endpoint with address 0x%X, skipping\n", cfgno, inum, asnum, d->bEndpointAddress); goto skip_to_next_endpoint_or_interface_descriptor; } } /* Accept this endpoint */ ++ifp->desc.bNumEndpoints; INIT_LIST_HEAD(&endpoint->urb_list); /* * Fix up bInterval values outside the legal range. * Use 10 or 8 ms if no proper value can be guessed. */ i = 0; /* i = min, j = max, n = default */ j = 255; if (usb_endpoint_xfer_int(d)) { i = 1; switch (udev->speed) { case USB_SPEED_SUPER_PLUS: case USB_SPEED_SUPER: case USB_SPEED_HIGH: /* * Many device manufacturers are using full-speed * bInterval values in high-speed interrupt endpoint * descriptors. Try to fix those and fall back to an * 8-ms default value otherwise. */ n = fls(d->bInterval*8); if (n == 0) n = 7; /* 8 ms = 2^(7-1) uframes */ j = 16; /* * Adjust bInterval for quirked devices. */ /* * This quirk fixes bIntervals reported in ms. */ if (udev->quirks & USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL) { n = clamp(fls(d->bInterval) + 3, i, j); i = j = n; } /* * This quirk fixes bIntervals reported in * linear microframes. */ if (udev->quirks & USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL) { n = clamp(fls(d->bInterval), i, j); i = j = n; } break; default: /* USB_SPEED_FULL or _LOW */ /* * For low-speed, 10 ms is the official minimum. * But some "overclocked" devices might want faster * polling so we'll allow it. */ n = 10; break; } } else if (usb_endpoint_xfer_isoc(d)) { i = 1; j = 16; switch (udev->speed) { case USB_SPEED_HIGH: n = 7; /* 8 ms = 2^(7-1) uframes */ break; default: /* USB_SPEED_FULL */ n = 4; /* 8 ms = 2^(4-1) frames */ break; } } if (d->bInterval < i || d->bInterval > j) { dev_notice(ddev, "config %d interface %d altsetting %d " "endpoint 0x%X has an invalid bInterval %d, " "changing to %d\n", cfgno, inum, asnum, d->bEndpointAddress, d->bInterval, n); endpoint->desc.bInterval = n; } /* Some buggy low-speed devices have Bulk endpoints, which is * explicitly forbidden by the USB spec. In an attempt to make * them usable, we will try treating them as Interrupt endpoints. */ if (udev->speed == USB_SPEED_LOW && usb_endpoint_xfer_bulk(d)) { dev_notice(ddev, "config %d interface %d altsetting %d " "endpoint 0x%X is Bulk; changing to Interrupt\n", cfgno, inum, asnum, d->bEndpointAddress); endpoint->desc.bmAttributes = USB_ENDPOINT_XFER_INT; endpoint->desc.bInterval = 1; if (usb_endpoint_maxp(&endpoint->desc) > 8) endpoint->desc.wMaxPacketSize = cpu_to_le16(8); } /* * Validate the wMaxPacketSize field. * Some devices have isochronous endpoints in altsetting 0; * the USB-2 spec requires such endpoints to have wMaxPacketSize = 0 * (see the end of section 5.6.3), so don't warn about them. */ maxp = le16_to_cpu(endpoint->desc.wMaxPacketSize); if (maxp == 0 && !(usb_endpoint_xfer_isoc(d) && asnum == 0)) { dev_notice(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid wMaxPacketSize 0\n", cfgno, inum, asnum, d->bEndpointAddress); } /* Find the highest legal maxpacket size for this endpoint */ i = 0; /* additional transactions per microframe */ switch (udev->speed) { case USB_SPEED_LOW: maxpacket_maxes = low_speed_maxpacket_maxes; break; case USB_SPEED_FULL: maxpacket_maxes = full_speed_maxpacket_maxes; break; case USB_SPEED_HIGH: /* Multiple-transactions bits are allowed only for HS periodic endpoints */ if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) { i = maxp & USB_EP_MAXP_MULT_MASK; maxp &= ~i; } fallthrough; default: maxpacket_maxes = high_speed_maxpacket_maxes; break; case USB_SPEED_SUPER: case USB_SPEED_SUPER_PLUS: maxpacket_maxes = super_speed_maxpacket_maxes; break; } j = maxpacket_maxes[usb_endpoint_type(&endpoint->desc)]; if (maxp > j) { dev_notice(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid maxpacket %d, setting to %d\n", cfgno, inum, asnum, d->bEndpointAddress, maxp, j); maxp = j; endpoint->desc.wMaxPacketSize = cpu_to_le16(i | maxp); } /* * Some buggy high speed devices have bulk endpoints using * maxpacket sizes other than 512. High speed HCDs may not * be able to handle that particular bug, so let's warn... */ if (udev->speed == USB_SPEED_HIGH && usb_endpoint_xfer_bulk(d)) { if (maxp != 512) dev_notice(ddev, "config %d interface %d altsetting %d " "bulk endpoint 0x%X has invalid maxpacket %d\n", cfgno, inum, asnum, d->bEndpointAddress, maxp); } /* Parse a possible SuperSpeed endpoint companion descriptor */ if (udev->speed >= USB_SPEED_SUPER) usb_parse_ss_endpoint_companion(ddev, cfgno, inum, asnum, endpoint, buffer, size); /* Skip over any Class Specific or Vendor Specific descriptors; * find the next endpoint or interface descriptor */ endpoint->extra = buffer; i = find_next_descriptor(buffer, size, USB_DT_ENDPOINT, USB_DT_INTERFACE, &n); endpoint->extralen = i; retval = buffer - buffer0 + i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", n, plural(n), "endpoint"); return retval; skip_to_next_endpoint_or_interface_descriptor: i = find_next_descriptor(buffer, size, USB_DT_ENDPOINT, USB_DT_INTERFACE, NULL); return buffer - buffer0 + i; } void usb_release_interface_cache(struct kref *ref) { struct usb_interface_cache *intfc = ref_to_usb_interface_cache(ref); int j; for (j = 0; j < intfc->num_altsetting; j++) { struct usb_host_interface *alt = &intfc->altsetting[j]; kfree(alt->endpoint); kfree(alt->string); } kfree(intfc); } static int usb_parse_interface(struct device *ddev, int cfgno, struct usb_host_config *config, unsigned char *buffer, int size, u8 inums[], u8 nalts[]) { unsigned char *buffer0 = buffer; struct usb_interface_descriptor *d; int inum, asnum; struct usb_interface_cache *intfc; struct usb_host_interface *alt; int i, n; int len, retval; int num_ep, num_ep_orig; d = (struct usb_interface_descriptor *) buffer; buffer += d->bLength; size -= d->bLength; if (d->bLength < USB_DT_INTERFACE_SIZE) goto skip_to_next_interface_descriptor; /* Which interface entry is this? */ intfc = NULL; inum = d->bInterfaceNumber; for (i = 0; i < config->desc.bNumInterfaces; ++i) { if (inums[i] == inum) { intfc = config->intf_cache[i]; break; } } if (!intfc || intfc->num_altsetting >= nalts[i]) goto skip_to_next_interface_descriptor; /* Check for duplicate altsetting entries */ asnum = d->bAlternateSetting; for ((i = 0, alt = &intfc->altsetting[0]); i < intfc->num_altsetting; (++i, ++alt)) { if (alt->desc.bAlternateSetting == asnum) { dev_notice(ddev, "Duplicate descriptor for config %d " "interface %d altsetting %d, skipping\n", cfgno, inum, asnum); goto skip_to_next_interface_descriptor; } } ++intfc->num_altsetting; memcpy(&alt->desc, d, USB_DT_INTERFACE_SIZE); /* Skip over any Class Specific or Vendor Specific descriptors; * find the first endpoint or interface descriptor */ alt->extra = buffer; i = find_next_descriptor(buffer, size, USB_DT_ENDPOINT, USB_DT_INTERFACE, &n); alt->extralen = i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", n, plural(n), "interface"); buffer += i; size -= i; /* Allocate space for the right(?) number of endpoints */ num_ep = num_ep_orig = alt->desc.bNumEndpoints; alt->desc.bNumEndpoints = 0; /* Use as a counter */ if (num_ep > USB_MAXENDPOINTS) { dev_notice(ddev, "too many endpoints for config %d interface %d " "altsetting %d: %d, using maximum allowed: %d\n", cfgno, inum, asnum, num_ep, USB_MAXENDPOINTS); num_ep = USB_MAXENDPOINTS; } if (num_ep > 0) { /* Can't allocate 0 bytes */ len = sizeof(struct usb_host_endpoint) * num_ep; alt->endpoint = kzalloc(len, GFP_KERNEL); if (!alt->endpoint) return -ENOMEM; } /* Parse all the endpoint descriptors */ n = 0; while (size > 0) { if (((struct usb_descriptor_header *) buffer)->bDescriptorType == USB_DT_INTERFACE) break; retval = usb_parse_endpoint(ddev, cfgno, config, inum, asnum, alt, num_ep, buffer, size); if (retval < 0) return retval; ++n; buffer += retval; size -= retval; } if (n != num_ep_orig) dev_notice(ddev, "config %d interface %d altsetting %d has %d " "endpoint descriptor%s, different from the interface " "descriptor's value: %d\n", cfgno, inum, asnum, n, plural(n), num_ep_orig); return buffer - buffer0; skip_to_next_interface_descriptor: i = find_next_descriptor(buffer, size, USB_DT_INTERFACE, USB_DT_INTERFACE, NULL); return buffer - buffer0 + i; } static int usb_parse_configuration(struct usb_device *dev, int cfgidx, struct usb_host_config *config, unsigned char *buffer, int size) { struct device *ddev = &dev->dev; unsigned char *buffer0 = buffer; int cfgno; int nintf, nintf_orig; int i, j, n; struct usb_interface_cache *intfc; unsigned char *buffer2; int size2; struct usb_descriptor_header *header; int retval; u8 inums[USB_MAXINTERFACES], nalts[USB_MAXINTERFACES]; unsigned iad_num = 0; memcpy(&config->desc, buffer, USB_DT_CONFIG_SIZE); nintf = nintf_orig = config->desc.bNumInterfaces; config->desc.bNumInterfaces = 0; // Adjusted later if (config->desc.bDescriptorType != USB_DT_CONFIG || config->desc.bLength < USB_DT_CONFIG_SIZE || config->desc.bLength > size) { dev_notice(ddev, "invalid descriptor for config index %d: " "type = 0x%X, length = %d\n", cfgidx, config->desc.bDescriptorType, config->desc.bLength); return -EINVAL; } cfgno = config->desc.bConfigurationValue; buffer += config->desc.bLength; size -= config->desc.bLength; if (nintf > USB_MAXINTERFACES) { dev_notice(ddev, "config %d has too many interfaces: %d, " "using maximum allowed: %d\n", cfgno, nintf, USB_MAXINTERFACES); nintf = USB_MAXINTERFACES; } /* Go through the descriptors, checking their length and counting the * number of altsettings for each interface */ n = 0; for ((buffer2 = buffer, size2 = size); size2 > 0; (buffer2 += header->bLength, size2 -= header->bLength)) { if (size2 < sizeof(struct usb_descriptor_header)) { dev_notice(ddev, "config %d descriptor has %d excess " "byte%s, ignoring\n", cfgno, size2, plural(size2)); break; } header = (struct usb_descriptor_header *) buffer2; if ((header->bLength > size2) || (header->bLength < 2)) { dev_notice(ddev, "config %d has an invalid descriptor " "of length %d, skipping remainder of the config\n", cfgno, header->bLength); break; } if (header->bDescriptorType == USB_DT_INTERFACE) { struct usb_interface_descriptor *d; int inum; d = (struct usb_interface_descriptor *) header; if (d->bLength < USB_DT_INTERFACE_SIZE) { dev_notice(ddev, "config %d has an invalid " "interface descriptor of length %d, " "skipping\n", cfgno, d->bLength); continue; } inum = d->bInterfaceNumber; if ((dev->quirks & USB_QUIRK_HONOR_BNUMINTERFACES) && n >= nintf_orig) { dev_notice(ddev, "config %d has more interface " "descriptors, than it declares in " "bNumInterfaces, ignoring interface " "number: %d\n", cfgno, inum); continue; } if (inum >= nintf_orig) dev_notice(ddev, "config %d has an invalid " "interface number: %d but max is %d\n", cfgno, inum, nintf_orig - 1); /* Have we already encountered this interface? * Count its altsettings */ for (i = 0; i < n; ++i) { if (inums[i] == inum) break; } if (i < n) { if (nalts[i] < 255) ++nalts[i]; } else if (n < USB_MAXINTERFACES) { inums[n] = inum; nalts[n] = 1; ++n; } } else if (header->bDescriptorType == USB_DT_INTERFACE_ASSOCIATION) { struct usb_interface_assoc_descriptor *d; d = (struct usb_interface_assoc_descriptor *)header; if (d->bLength < USB_DT_INTERFACE_ASSOCIATION_SIZE) { dev_notice(ddev, "config %d has an invalid interface association descriptor of length %d, skipping\n", cfgno, d->bLength); continue; } if (iad_num == USB_MAXIADS) { dev_notice(ddev, "found more Interface " "Association Descriptors " "than allocated for in " "configuration %d\n", cfgno); } else { config->intf_assoc[iad_num] = d; iad_num++; } } else if (header->bDescriptorType == USB_DT_DEVICE || header->bDescriptorType == USB_DT_CONFIG) dev_notice(ddev, "config %d contains an unexpected " "descriptor of type 0x%X, skipping\n", cfgno, header->bDescriptorType); } /* for ((buffer2 = buffer, size2 = size); ...) */ size = buffer2 - buffer; config->desc.wTotalLength = cpu_to_le16(buffer2 - buffer0); if (n != nintf) dev_notice(ddev, "config %d has %d interface%s, different from " "the descriptor's value: %d\n", cfgno, n, plural(n), nintf_orig); else if (n == 0) dev_notice(ddev, "config %d has no interfaces?\n", cfgno); config->desc.bNumInterfaces = nintf = n; /* Check for missing interface numbers */ for (i = 0; i < nintf; ++i) { for (j = 0; j < nintf; ++j) { if (inums[j] == i) break; } if (j >= nintf) dev_notice(ddev, "config %d has no interface number " "%d\n", cfgno, i); } /* Allocate the usb_interface_caches and altsetting arrays */ for (i = 0; i < nintf; ++i) { j = nalts[i]; if (j > USB_MAXALTSETTING) { dev_notice(ddev, "too many alternate settings for " "config %d interface %d: %d, " "using maximum allowed: %d\n", cfgno, inums[i], j, USB_MAXALTSETTING); nalts[i] = j = USB_MAXALTSETTING; } intfc = kzalloc(struct_size(intfc, altsetting, j), GFP_KERNEL); config->intf_cache[i] = intfc; if (!intfc) return -ENOMEM; kref_init(&intfc->ref); } /* FIXME: parse the BOS descriptor */ /* Skip over any Class Specific or Vendor Specific descriptors; * find the first interface descriptor */ config->extra = buffer; i = find_next_descriptor(buffer, size, USB_DT_INTERFACE, USB_DT_INTERFACE, &n); config->extralen = i; if (n > 0) dev_dbg(ddev, "skipped %d descriptor%s after %s\n", n, plural(n), "configuration"); buffer += i; size -= i; /* Parse all the interface/altsetting descriptors */ while (size > 0) { retval = usb_parse_interface(ddev, cfgno, config, buffer, size, inums, nalts); if (retval < 0) return retval; buffer += retval; size -= retval; } /* Check for missing altsettings */ for (i = 0; i < nintf; ++i) { intfc = config->intf_cache[i]; for (j = 0; j < intfc->num_altsetting; ++j) { for (n = 0; n < intfc->num_altsetting; ++n) { if (intfc->altsetting[n].desc. bAlternateSetting == j) break; } if (n >= intfc->num_altsetting) dev_notice(ddev, "config %d interface %d has no " "altsetting %d\n", cfgno, inums[i], j); } } return 0; } /* hub-only!! ... and only exported for reset/reinit path. * otherwise used internally on disconnect/destroy path */ void usb_destroy_configuration(struct usb_device *dev) { int c, i; if (!dev->config) return; if (dev->rawdescriptors) { for (i = 0; i < dev->descriptor.bNumConfigurations; i++) kfree(dev->rawdescriptors[i]); kfree(dev->rawdescriptors); dev->rawdescriptors = NULL; } for (c = 0; c < dev->descriptor.bNumConfigurations; c++) { struct usb_host_config *cf = &dev->config[c]; kfree(cf->string); for (i = 0; i < cf->desc.bNumInterfaces; i++) { if (cf->intf_cache[i]) kref_put(&cf->intf_cache[i]->ref, usb_release_interface_cache); } } kfree(dev->config); dev->config = NULL; } /* * Get the USB config descriptors, cache and parse'em * * hub-only!! ... and only in reset path, or usb_new_device() * (used by real hubs and virtual root hubs) */ int usb_get_configuration(struct usb_device *dev) { struct device *ddev = &dev->dev; int ncfg = dev->descriptor.bNumConfigurations; unsigned int cfgno, length; unsigned char *bigbuffer; struct usb_config_descriptor *desc; int result; if (ncfg > USB_MAXCONFIG) { dev_notice(ddev, "too many configurations: %d, " "using maximum allowed: %d\n", ncfg, USB_MAXCONFIG); dev->descriptor.bNumConfigurations = ncfg = USB_MAXCONFIG; } if (ncfg < 1) { dev_err(ddev, "no configurations\n"); return -EINVAL; } length = ncfg * sizeof(struct usb_host_config); dev->config = kzalloc(length, GFP_KERNEL); if (!dev->config) return -ENOMEM; length = ncfg * sizeof(char *); dev->rawdescriptors = kzalloc(length, GFP_KERNEL); if (!dev->rawdescriptors) return -ENOMEM; desc = kmalloc(USB_DT_CONFIG_SIZE, GFP_KERNEL); if (!desc) return -ENOMEM; for (cfgno = 0; cfgno < ncfg; cfgno++) { /* We grab just the first descriptor so we know how long * the whole configuration is */ result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, desc, USB_DT_CONFIG_SIZE); if (result < 0) { dev_err(ddev, "unable to read config index %d " "descriptor/%s: %d\n", cfgno, "start", result); if (result != -EPIPE) goto err; dev_notice(ddev, "chopping to %d config(s)\n", cfgno); dev->descriptor.bNumConfigurations = cfgno; break; } else if (result < 4) { dev_err(ddev, "config index %d descriptor too short " "(expected %i, got %i)\n", cfgno, USB_DT_CONFIG_SIZE, result); result = -EINVAL; goto err; } length = max((int) le16_to_cpu(desc->wTotalLength), USB_DT_CONFIG_SIZE); /* Now that we know the length, get the whole thing */ bigbuffer = kmalloc(length, GFP_KERNEL); if (!bigbuffer) { result = -ENOMEM; goto err; } if (dev->quirks & USB_QUIRK_DELAY_INIT) msleep(200); result = usb_get_descriptor(dev, USB_DT_CONFIG, cfgno, bigbuffer, length); if (result < 0) { dev_err(ddev, "unable to read config index %d " "descriptor/%s\n", cfgno, "all"); kfree(bigbuffer); goto err; } if (result < length) { dev_notice(ddev, "config index %d descriptor too short " "(expected %i, got %i)\n", cfgno, length, result); length = result; } dev->rawdescriptors[cfgno] = bigbuffer; result = usb_parse_configuration(dev, cfgno, &dev->config[cfgno], bigbuffer, length); if (result < 0) { ++cfgno; goto err; } } err: kfree(desc); dev->descriptor.bNumConfigurations = cfgno; return result; } void usb_release_bos_descriptor(struct usb_device *dev) { if (dev->bos) { kfree(dev->bos->desc); kfree(dev->bos); dev->bos = NULL; } } static const __u8 bos_desc_len[256] = { [USB_CAP_TYPE_WIRELESS_USB] = USB_DT_USB_WIRELESS_CAP_SIZE, [USB_CAP_TYPE_EXT] = USB_DT_USB_EXT_CAP_SIZE, [USB_SS_CAP_TYPE] = USB_DT_USB_SS_CAP_SIZE, [USB_SSP_CAP_TYPE] = USB_DT_USB_SSP_CAP_SIZE(1), [CONTAINER_ID_TYPE] = USB_DT_USB_SS_CONTN_ID_SIZE, [USB_PTM_CAP_TYPE] = USB_DT_USB_PTM_ID_SIZE, }; /* Get BOS descriptor set */ int usb_get_bos_descriptor(struct usb_device *dev) { struct device *ddev = &dev->dev; struct usb_bos_descriptor *bos; struct usb_dev_cap_header *cap; struct usb_ssp_cap_descriptor *ssp_cap; unsigned char *buffer, *buffer0; int length, total_len, num, i, ssac; __u8 cap_type; int ret; bos = kzalloc(sizeof(*bos), GFP_KERNEL); if (!bos) return -ENOMEM; /* Get BOS descriptor */ ret = usb_get_descriptor(dev, USB_DT_BOS, 0, bos, USB_DT_BOS_SIZE); if (ret < USB_DT_BOS_SIZE || bos->bLength < USB_DT_BOS_SIZE) { dev_notice(ddev, "unable to get BOS descriptor or descriptor too short\n"); if (ret >= 0) ret = -ENOMSG; kfree(bos); return ret; } length = bos->bLength; total_len = le16_to_cpu(bos->wTotalLength); num = bos->bNumDeviceCaps; kfree(bos); if (total_len < length) return -EINVAL; dev->bos = kzalloc(sizeof(*dev->bos), GFP_KERNEL); if (!dev->bos) return -ENOMEM; /* Now let's get the whole BOS descriptor set */ buffer = kzalloc(total_len, GFP_KERNEL); if (!buffer) { ret = -ENOMEM; goto err; } dev->bos->desc = (struct usb_bos_descriptor *)buffer; ret = usb_get_descriptor(dev, USB_DT_BOS, 0, buffer, total_len); if (ret < total_len) { dev_notice(ddev, "unable to get BOS descriptor set\n"); if (ret >= 0) ret = -ENOMSG; goto err; } buffer0 = buffer; total_len -= length; buffer += length; for (i = 0; i < num; i++) { cap = (struct usb_dev_cap_header *)buffer; if (total_len < sizeof(*cap) || total_len < cap->bLength) { dev->bos->desc->bNumDeviceCaps = i; break; } cap_type = cap->bDevCapabilityType; length = cap->bLength; if (bos_desc_len[cap_type] && length < bos_desc_len[cap_type]) { dev->bos->desc->bNumDeviceCaps = i; break; } if (cap->bDescriptorType != USB_DT_DEVICE_CAPABILITY) { dev_notice(ddev, "descriptor type invalid, skip\n"); goto skip_to_next_descriptor; } switch (cap_type) { case USB_CAP_TYPE_EXT: dev->bos->ext_cap = (struct usb_ext_cap_descriptor *)buffer; break; case USB_SS_CAP_TYPE: dev->bos->ss_cap = (struct usb_ss_cap_descriptor *)buffer; break; case USB_SSP_CAP_TYPE: ssp_cap = (struct usb_ssp_cap_descriptor *)buffer; ssac = (le32_to_cpu(ssp_cap->bmAttributes) & USB_SSP_SUBLINK_SPEED_ATTRIBS); if (length >= USB_DT_USB_SSP_CAP_SIZE(ssac)) dev->bos->ssp_cap = ssp_cap; break; case CONTAINER_ID_TYPE: dev->bos->ss_id = (struct usb_ss_container_id_descriptor *)buffer; break; case USB_PTM_CAP_TYPE: dev->bos->ptm_cap = (struct usb_ptm_cap_descriptor *)buffer; break; default: break; } skip_to_next_descriptor: total_len -= length; buffer += length; } dev->bos->desc->wTotalLength = cpu_to_le16(buffer - buffer0); return 0; err: usb_release_bos_descriptor(dev); return ret; } |
| 7 7 7 7 1 10 1 8 3 10 8 2 2 2 1 1 1 1 1 2 1 1 1 1 1 1 1 1 2 2 2 1 2 2 11 6 5 5 1 2 4 3 4 4 3 1 1 1 1 5 5 2 5 1 3 1 5 5 2 3 3 3 3 2 2 2 2 2 16 4 12 32 9 25 32 5 25 2 20 7 8 8 8 8 1 1 1 42 3 2 3 34 3 2 1 2 12 22 1 19 3 3 1 3 29 25 1 2 7 1 2 18 16 16 3 1 2 4 1 3 7 7 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 | // SPDX-License-Identifier: GPL-2.0-only /* * cec-adap.c - HDMI Consumer Electronics Control framework - CEC adapter * * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #include <linux/errno.h> #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/ktime.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/types.h> #include <drm/drm_connector.h> #include <drm/drm_device.h> #include <drm/drm_edid.h> #include <drm/drm_file.h> #include "cec-priv.h" static void cec_fill_msg_report_features(struct cec_adapter *adap, struct cec_msg *msg, unsigned int la_idx); static int cec_log_addr2idx(const struct cec_adapter *adap, u8 log_addr) { int i; for (i = 0; i < adap->log_addrs.num_log_addrs; i++) if (adap->log_addrs.log_addr[i] == log_addr) return i; return -1; } static unsigned int cec_log_addr2dev(const struct cec_adapter *adap, u8 log_addr) { int i = cec_log_addr2idx(adap, log_addr); return adap->log_addrs.primary_device_type[i < 0 ? 0 : i]; } u16 cec_get_edid_phys_addr(const u8 *edid, unsigned int size, unsigned int *offset) { unsigned int loc = cec_get_edid_spa_location(edid, size); if (offset) *offset = loc; if (loc == 0) return CEC_PHYS_ADDR_INVALID; return (edid[loc] << 8) | edid[loc + 1]; } EXPORT_SYMBOL_GPL(cec_get_edid_phys_addr); void cec_fill_conn_info_from_drm(struct cec_connector_info *conn_info, const struct drm_connector *connector) { memset(conn_info, 0, sizeof(*conn_info)); conn_info->type = CEC_CONNECTOR_TYPE_DRM; conn_info->drm.card_no = connector->dev->primary->index; conn_info->drm.connector_id = connector->base.id; } EXPORT_SYMBOL_GPL(cec_fill_conn_info_from_drm); /* * Queue a new event for this filehandle. If ts == 0, then set it * to the current time. * * We keep a queue of at most max_event events where max_event differs * per event. If the queue becomes full, then drop the oldest event and * keep track of how many events we've dropped. */ void cec_queue_event_fh(struct cec_fh *fh, const struct cec_event *new_ev, u64 ts) { static const u16 max_events[CEC_NUM_EVENTS] = { 1, 1, 800, 800, 8, 8, 8, 8 }; struct cec_event_entry *entry; unsigned int ev_idx = new_ev->event - 1; if (WARN_ON(ev_idx >= ARRAY_SIZE(fh->events))) return; if (ts == 0) ts = ktime_get_ns(); mutex_lock(&fh->lock); if (ev_idx < CEC_NUM_CORE_EVENTS) entry = &fh->core_events[ev_idx]; else entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (entry) { if (new_ev->event == CEC_EVENT_LOST_MSGS && fh->queued_events[ev_idx]) { entry->ev.lost_msgs.lost_msgs += new_ev->lost_msgs.lost_msgs; goto unlock; } entry->ev = *new_ev; entry->ev.ts = ts; if (fh->queued_events[ev_idx] < max_events[ev_idx]) { /* Add new msg at the end of the queue */ list_add_tail(&entry->list, &fh->events[ev_idx]); fh->queued_events[ev_idx]++; fh->total_queued_events++; goto unlock; } if (ev_idx >= CEC_NUM_CORE_EVENTS) { list_add_tail(&entry->list, &fh->events[ev_idx]); /* drop the oldest event */ entry = list_first_entry(&fh->events[ev_idx], struct cec_event_entry, list); list_del(&entry->list); kfree(entry); } } /* Mark that events were lost */ entry = list_first_entry_or_null(&fh->events[ev_idx], struct cec_event_entry, list); if (entry) entry->ev.flags |= CEC_EVENT_FL_DROPPED_EVENTS; unlock: mutex_unlock(&fh->lock); wake_up_interruptible(&fh->wait); } /* Queue a new event for all open filehandles. */ static void cec_queue_event(struct cec_adapter *adap, const struct cec_event *ev) { u64 ts = ktime_get_ns(); struct cec_fh *fh; mutex_lock(&adap->devnode.lock_fhs); list_for_each_entry(fh, &adap->devnode.fhs, list) cec_queue_event_fh(fh, ev, ts); mutex_unlock(&adap->devnode.lock_fhs); } /* Notify userspace that the CEC pin changed state at the given time. */ void cec_queue_pin_cec_event(struct cec_adapter *adap, bool is_high, bool dropped_events, ktime_t ts) { struct cec_event ev = { .event = is_high ? CEC_EVENT_PIN_CEC_HIGH : CEC_EVENT_PIN_CEC_LOW, .flags = dropped_events ? CEC_EVENT_FL_DROPPED_EVENTS : 0, }; struct cec_fh *fh; mutex_lock(&adap->devnode.lock_fhs); list_for_each_entry(fh, &adap->devnode.fhs, list) { if (fh->mode_follower == CEC_MODE_MONITOR_PIN) cec_queue_event_fh(fh, &ev, ktime_to_ns(ts)); } mutex_unlock(&adap->devnode.lock_fhs); } EXPORT_SYMBOL_GPL(cec_queue_pin_cec_event); /* Notify userspace that the HPD pin changed state at the given time. */ void cec_queue_pin_hpd_event(struct cec_adapter *adap, bool is_high, ktime_t ts) { struct cec_event ev = { .event = is_high ? CEC_EVENT_PIN_HPD_HIGH : CEC_EVENT_PIN_HPD_LOW, }; struct cec_fh *fh; mutex_lock(&adap->devnode.lock_fhs); list_for_each_entry(fh, &adap->devnode.fhs, list) cec_queue_event_fh(fh, &ev, ktime_to_ns(ts)); mutex_unlock(&adap->devnode.lock_fhs); } EXPORT_SYMBOL_GPL(cec_queue_pin_hpd_event); /* Notify userspace that the 5V pin changed state at the given time. */ void cec_queue_pin_5v_event(struct cec_adapter *adap, bool is_high, ktime_t ts) { struct cec_event ev = { .event = is_high ? CEC_EVENT_PIN_5V_HIGH : CEC_EVENT_PIN_5V_LOW, }; struct cec_fh *fh; mutex_lock(&adap->devnode.lock_fhs); list_for_each_entry(fh, &adap->devnode.fhs, list) cec_queue_event_fh(fh, &ev, ktime_to_ns(ts)); mutex_unlock(&adap->devnode.lock_fhs); } EXPORT_SYMBOL_GPL(cec_queue_pin_5v_event); /* * Queue a new message for this filehandle. * * We keep a queue of at most CEC_MAX_MSG_RX_QUEUE_SZ messages. If the * queue becomes full, then drop the oldest message and keep track * of how many messages we've dropped. */ static void cec_queue_msg_fh(struct cec_fh *fh, const struct cec_msg *msg) { static const struct cec_event ev_lost_msgs = { .event = CEC_EVENT_LOST_MSGS, .flags = 0, { .lost_msgs = { 1 }, }, }; struct cec_msg_entry *entry; mutex_lock(&fh->lock); entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (entry) { entry->msg = *msg; /* Add new msg at the end of the queue */ list_add_tail(&entry->list, &fh->msgs); if (fh->queued_msgs < CEC_MAX_MSG_RX_QUEUE_SZ) { /* All is fine if there is enough room */ fh->queued_msgs++; mutex_unlock(&fh->lock); wake_up_interruptible(&fh->wait); return; } /* * if the message queue is full, then drop the oldest one and * send a lost message event. */ entry = list_first_entry(&fh->msgs, struct cec_msg_entry, list); list_del(&entry->list); kfree(entry); } mutex_unlock(&fh->lock); /* * We lost a message, either because kmalloc failed or the queue * was full. */ cec_queue_event_fh(fh, &ev_lost_msgs, ktime_get_ns()); } /* * Queue the message for those filehandles that are in monitor mode. * If valid_la is true (this message is for us or was sent by us), * then pass it on to any monitoring filehandle. If this message * isn't for us or from us, then only give it to filehandles that * are in MONITOR_ALL mode. * * This can only happen if the CEC_CAP_MONITOR_ALL capability is * set and the CEC adapter was placed in 'monitor all' mode. */ static void cec_queue_msg_monitor(struct cec_adapter *adap, const struct cec_msg *msg, bool valid_la) { struct cec_fh *fh; u32 monitor_mode = valid_la ? CEC_MODE_MONITOR : CEC_MODE_MONITOR_ALL; mutex_lock(&adap->devnode.lock_fhs); list_for_each_entry(fh, &adap->devnode.fhs, list) { if (fh->mode_follower >= monitor_mode) cec_queue_msg_fh(fh, msg); } mutex_unlock(&adap->devnode.lock_fhs); } /* * Queue the message for follower filehandles. */ static void cec_queue_msg_followers(struct cec_adapter *adap, const struct cec_msg *msg) { struct cec_fh *fh; mutex_lock(&adap->devnode.lock_fhs); list_for_each_entry(fh, &adap->devnode.fhs, list) { if (fh->mode_follower == CEC_MODE_FOLLOWER) cec_queue_msg_fh(fh, msg); } mutex_unlock(&adap->devnode.lock_fhs); } /* Notify userspace of an adapter state change. */ static void cec_post_state_event(struct cec_adapter *adap) { struct cec_event ev = { .event = CEC_EVENT_STATE_CHANGE, }; ev.state_change.phys_addr = adap->phys_addr; ev.state_change.log_addr_mask = adap->log_addrs.log_addr_mask; ev.state_change.have_conn_info = adap->conn_info.type != CEC_CONNECTOR_TYPE_NO_CONNECTOR; cec_queue_event(adap, &ev); } /* * A CEC transmit (and a possible wait for reply) completed. * If this was in blocking mode, then complete it, otherwise * queue the message for userspace to dequeue later. * * This function is called with adap->lock held. */ static void cec_data_completed(struct cec_data *data) { /* * Delete this transmit from the filehandle's xfer_list since * we're done with it. * * Note that if the filehandle is closed before this transmit * finished, then the release() function will set data->fh to NULL. * Without that we would be referring to a closed filehandle. */ if (data->fh) list_del_init(&data->xfer_list); if (data->blocking) { /* * Someone is blocking so mark the message as completed * and call complete. */ data->completed = true; complete(&data->c); } else { /* * No blocking, so just queue the message if needed and * free the memory. */ if (data->fh) cec_queue_msg_fh(data->fh, &data->msg); kfree(data); } } /* * A pending CEC transmit needs to be cancelled, either because the CEC * adapter is disabled or the transmit takes an impossibly long time to * finish, or the reply timed out. * * This function is called with adap->lock held. */ static void cec_data_cancel(struct cec_data *data, u8 tx_status, u8 rx_status) { struct cec_adapter *adap = data->adap; /* * It's either the current transmit, or it is a pending * transmit. Take the appropriate action to clear it. */ if (adap->transmitting == data) { adap->transmitting = NULL; } else { list_del_init(&data->list); if (!(data->msg.tx_status & CEC_TX_STATUS_OK)) if (!WARN_ON(!adap->transmit_queue_sz)) adap->transmit_queue_sz--; } if (data->msg.tx_status & CEC_TX_STATUS_OK) { data->msg.rx_ts = ktime_get_ns(); data->msg.rx_status = rx_status; if (!data->blocking) data->msg.tx_status = 0; } else { data->msg.tx_ts = ktime_get_ns(); data->msg.tx_status |= tx_status | CEC_TX_STATUS_MAX_RETRIES; data->msg.tx_error_cnt++; data->attempts = 0; if (!data->blocking) data->msg.rx_status = 0; } /* Queue transmitted message for monitoring purposes */ cec_queue_msg_monitor(adap, &data->msg, 1); if (!data->blocking && data->msg.sequence) /* Allow drivers to react to a canceled transmit */ call_void_op(adap, adap_nb_transmit_canceled, &data->msg); cec_data_completed(data); } /* * Flush all pending transmits and cancel any pending timeout work. * * This function is called with adap->lock held. */ static void cec_flush(struct cec_adapter *adap) { struct cec_data *data, *n; /* * If the adapter is disabled, or we're asked to stop, * then cancel any pending transmits. */ while (!list_empty(&adap->transmit_queue)) { data = list_first_entry(&adap->transmit_queue, struct cec_data, list); cec_data_cancel(data, CEC_TX_STATUS_ABORTED, 0); } if (adap->transmitting) adap->transmit_in_progress_aborted = true; /* Cancel the pending timeout work. */ list_for_each_entry_safe(data, n, &adap->wait_queue, list) { if (cancel_delayed_work(&data->work)) cec_data_cancel(data, CEC_TX_STATUS_OK, CEC_RX_STATUS_ABORTED); /* * If cancel_delayed_work returned false, then * the cec_wait_timeout function is running, * which will call cec_data_completed. So no * need to do anything special in that case. */ } /* * If something went wrong and this counter isn't what it should * be, then this will reset it back to 0. Warn if it is not 0, * since it indicates a bug, either in this framework or in a * CEC driver. */ if (WARN_ON(adap->transmit_queue_sz)) adap->transmit_queue_sz = 0; } /* * Main CEC state machine * * Wait until the thread should be stopped, or we are not transmitting and * a new transmit message is queued up, in which case we start transmitting * that message. When the adapter finished transmitting the message it will * call cec_transmit_done(). * * If the adapter is disabled, then remove all queued messages instead. * * If the current transmit times out, then cancel that transmit. */ int cec_thread_func(void *_adap) { struct cec_adapter *adap = _adap; for (;;) { unsigned int signal_free_time; struct cec_data *data; bool timeout = false; u8 attempts; if (adap->transmit_in_progress) { int err; /* * We are transmitting a message, so add a timeout * to prevent the state machine to get stuck waiting * for this message to finalize and add a check to * see if the adapter is disabled in which case the * transmit should be canceled. */ err = wait_event_interruptible_timeout(adap->kthread_waitq, (adap->needs_hpd && (!adap->is_configured && !adap->is_configuring)) || kthread_should_stop() || (!adap->transmit_in_progress && !list_empty(&adap->transmit_queue)), msecs_to_jiffies(adap->xfer_timeout_ms)); timeout = err == 0; } else { /* Otherwise we just wait for something to happen. */ wait_event_interruptible(adap->kthread_waitq, kthread_should_stop() || (!adap->transmit_in_progress && !list_empty(&adap->transmit_queue))); } mutex_lock(&adap->lock); if ((adap->needs_hpd && (!adap->is_configured && !adap->is_configuring)) || kthread_should_stop()) { cec_flush(adap); goto unlock; } if (adap->transmit_in_progress && adap->transmit_in_progress_aborted) { if (adap->transmitting) cec_data_cancel(adap->transmitting, CEC_TX_STATUS_ABORTED, 0); adap->transmit_in_progress = false; adap->transmit_in_progress_aborted = false; goto unlock; } if (adap->transmit_in_progress && timeout) { /* * If we timeout, then log that. Normally this does * not happen and it is an indication of a faulty CEC * adapter driver, or the CEC bus is in some weird * state. On rare occasions it can happen if there is * so much traffic on the bus that the adapter was * unable to transmit for xfer_timeout_ms (2.1s by * default). */ if (adap->transmitting) { pr_warn("cec-%s: message %*ph timed out\n", adap->name, adap->transmitting->msg.len, adap->transmitting->msg.msg); /* Just give up on this. */ cec_data_cancel(adap->transmitting, CEC_TX_STATUS_TIMEOUT, 0); } else { pr_warn("cec-%s: transmit timed out\n", adap->name); } adap->transmit_in_progress = false; adap->tx_timeout_cnt++; goto unlock; } /* * If we are still transmitting, or there is nothing new to * transmit, then just continue waiting. */ if (adap->transmit_in_progress || list_empty(&adap->transmit_queue)) goto unlock; /* Get a new message to transmit */ data = list_first_entry(&adap->transmit_queue, struct cec_data, list); list_del_init(&data->list); if (!WARN_ON(!data->adap->transmit_queue_sz)) adap->transmit_queue_sz--; /* Make this the current transmitting message */ adap->transmitting = data; /* * Suggested number of attempts as per the CEC 2.0 spec: * 4 attempts is the default, except for 'secondary poll * messages', i.e. poll messages not sent during the adapter * configuration phase when it allocates logical addresses. */ if (data->msg.len == 1 && adap->is_configured) attempts = 2; else attempts = 4; /* Set the suggested signal free time */ if (data->attempts) { /* should be >= 3 data bit periods for a retry */ signal_free_time = CEC_SIGNAL_FREE_TIME_RETRY; } else if (adap->last_initiator != cec_msg_initiator(&data->msg)) { /* should be >= 5 data bit periods for new initiator */ signal_free_time = CEC_SIGNAL_FREE_TIME_NEW_INITIATOR; adap->last_initiator = cec_msg_initiator(&data->msg); } else { /* * should be >= 7 data bit periods for sending another * frame immediately after another. */ signal_free_time = CEC_SIGNAL_FREE_TIME_NEXT_XFER; } if (data->attempts == 0) data->attempts = attempts; adap->transmit_in_progress_aborted = false; /* Tell the adapter to transmit, cancel on error */ if (call_op(adap, adap_transmit, data->attempts, signal_free_time, &data->msg)) cec_data_cancel(data, CEC_TX_STATUS_ABORTED, 0); else adap->transmit_in_progress = true; unlock: mutex_unlock(&adap->lock); if (kthread_should_stop()) break; } return 0; } /* * Called by the CEC adapter if a transmit finished. */ void cec_transmit_done_ts(struct cec_adapter *adap, u8 status, u8 arb_lost_cnt, u8 nack_cnt, u8 low_drive_cnt, u8 error_cnt, ktime_t ts) { struct cec_data *data; struct cec_msg *msg; unsigned int attempts_made = arb_lost_cnt + nack_cnt + low_drive_cnt + error_cnt; bool done = status & (CEC_TX_STATUS_MAX_RETRIES | CEC_TX_STATUS_OK); bool aborted = adap->transmit_in_progress_aborted; dprintk(2, "%s: status 0x%02x\n", __func__, status); if (attempts_made < 1) attempts_made = 1; mutex_lock(&adap->lock); data = adap->transmitting; if (!data) { /* * This might happen if a transmit was issued and the cable is * unplugged while the transmit is ongoing. Ignore this * transmit in that case. */ if (!adap->transmit_in_progress) dprintk(1, "%s was called without an ongoing transmit!\n", __func__); adap->transmit_in_progress = false; goto wake_thread; } adap->transmit_in_progress = false; adap->transmit_in_progress_aborted = false; msg = &data->msg; /* Drivers must fill in the status! */ WARN_ON(status == 0); msg->tx_ts = ktime_to_ns(ts); msg->tx_status |= status; msg->tx_arb_lost_cnt += arb_lost_cnt; msg->tx_nack_cnt += nack_cnt; msg->tx_low_drive_cnt += low_drive_cnt; msg->tx_error_cnt += error_cnt; adap->tx_arb_lost_cnt += arb_lost_cnt; adap->tx_low_drive_cnt += low_drive_cnt; adap->tx_error_cnt += error_cnt; /* * Low Drive transmission errors should really not happen for * well-behaved CEC devices and proper HDMI cables. * * Ditto for the 'Error' status. * * For the first few times that this happens, log this. * Stop logging after that, since that will not add any more * useful information and instead it will just flood the kernel log. */ if (done && adap->tx_low_drive_log_cnt < 8 && msg->tx_low_drive_cnt) { adap->tx_low_drive_log_cnt++; dprintk(0, "low drive counter: %u (seq %u: %*ph)\n", msg->tx_low_drive_cnt, msg->sequence, msg->len, msg->msg); } if (done && adap->tx_error_log_cnt < 8 && msg->tx_error_cnt) { adap->tx_error_log_cnt++; dprintk(0, "error counter: %u (seq %u: %*ph)\n", msg->tx_error_cnt, msg->sequence, msg->len, msg->msg); } /* Mark that we're done with this transmit */ adap->transmitting = NULL; /* * If there are still retry attempts left and there was an error and * the hardware didn't signal that it retried itself (by setting * CEC_TX_STATUS_MAX_RETRIES), then we will retry ourselves. */ if (!aborted && data->attempts > attempts_made && !done) { /* Retry this message */ data->attempts -= attempts_made; if (msg->timeout) dprintk(2, "retransmit: %*ph (attempts: %d, wait for %*ph)\n", msg->len, msg->msg, data->attempts, data->match_len, data->match_reply); else dprintk(2, "retransmit: %*ph (attempts: %d)\n", msg->len, msg->msg, data->attempts); /* Add the message in front of the transmit queue */ list_add(&data->list, &adap->transmit_queue); adap->transmit_queue_sz++; goto wake_thread; } if (aborted && !done) status |= CEC_TX_STATUS_ABORTED; data->attempts = 0; /* Always set CEC_TX_STATUS_MAX_RETRIES on error */ if (!(status & CEC_TX_STATUS_OK)) msg->tx_status |= CEC_TX_STATUS_MAX_RETRIES; /* Queue transmitted message for monitoring purposes */ cec_queue_msg_monitor(adap, msg, 1); if ((status & CEC_TX_STATUS_OK) && adap->is_configured && msg->timeout) { /* * Queue the message into the wait queue if we want to wait * for a reply. */ list_add_tail(&data->list, &adap->wait_queue); schedule_delayed_work(&data->work, msecs_to_jiffies(msg->timeout)); } else { /* Otherwise we're done */ cec_data_completed(data); } wake_thread: /* * Wake up the main thread to see if another message is ready * for transmitting or to retry the current message. */ wake_up_interruptible(&adap->kthread_waitq); mutex_unlock(&adap->lock); } EXPORT_SYMBOL_GPL(cec_transmit_done_ts); void cec_transmit_attempt_done_ts(struct cec_adapter *adap, u8 status, ktime_t ts) { switch (status & ~CEC_TX_STATUS_MAX_RETRIES) { case CEC_TX_STATUS_OK: cec_transmit_done_ts(adap, status, 0, 0, 0, 0, ts); return; case CEC_TX_STATUS_ARB_LOST: cec_transmit_done_ts(adap, status, 1, 0, 0, 0, ts); return; case CEC_TX_STATUS_NACK: cec_transmit_done_ts(adap, status, 0, 1, 0, 0, ts); return; case CEC_TX_STATUS_LOW_DRIVE: cec_transmit_done_ts(adap, status, 0, 0, 1, 0, ts); return; case CEC_TX_STATUS_ERROR: cec_transmit_done_ts(adap, status, 0, 0, 0, 1, ts); return; default: /* Should never happen */ WARN(1, "cec-%s: invalid status 0x%02x\n", adap->name, status); return; } } EXPORT_SYMBOL_GPL(cec_transmit_attempt_done_ts); /* * Called when waiting for a reply times out. */ static void cec_wait_timeout(struct work_struct *work) { struct cec_data *data = container_of(work, struct cec_data, work.work); struct cec_adapter *adap = data->adap; mutex_lock(&adap->lock); /* * Sanity check in case the timeout and the arrival of the message * happened at the same time. */ if (list_empty(&data->list)) goto unlock; /* Mark the message as timed out */ list_del_init(&data->list); cec_data_cancel(data, CEC_TX_STATUS_OK, CEC_RX_STATUS_TIMEOUT); unlock: mutex_unlock(&adap->lock); } /* * Transmit a message. The fh argument may be NULL if the transmit is not * associated with a specific filehandle. * * This function is called with adap->lock held. */ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg, struct cec_fh *fh, bool block) { struct cec_data *data; bool is_raw = msg_is_raw(msg); bool reply_vendor_id = (msg->flags & CEC_MSG_FL_REPLY_VENDOR_ID) && msg->len > 1 && msg->msg[1] == CEC_MSG_VENDOR_COMMAND_WITH_ID; int err; if (adap->devnode.unregistered) return -ENODEV; msg->rx_ts = 0; msg->tx_ts = 0; msg->rx_status = 0; msg->tx_status = 0; msg->tx_arb_lost_cnt = 0; msg->tx_nack_cnt = 0; msg->tx_low_drive_cnt = 0; msg->tx_error_cnt = 0; msg->sequence = 0; msg->flags &= CEC_MSG_FL_REPLY_TO_FOLLOWERS | CEC_MSG_FL_RAW | (reply_vendor_id ? CEC_MSG_FL_REPLY_VENDOR_ID : 0); if ((reply_vendor_id || msg->reply) && msg->timeout == 0) { /* Make sure the timeout isn't 0. */ msg->timeout = 1000; } if (!msg->timeout) msg->flags &= ~CEC_MSG_FL_REPLY_TO_FOLLOWERS; /* Sanity checks */ if (msg->len == 0 || msg->len > CEC_MAX_MSG_SIZE) { dprintk(1, "%s: invalid length %d\n", __func__, msg->len); return -EINVAL; } if (reply_vendor_id && msg->len < 6) { dprintk(1, "%s: <Vendor Command With ID> message too short\n", __func__); return -EINVAL; } memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len); if (msg->timeout) dprintk(2, "%s: %*ph (wait for 0x%02x%s)\n", __func__, msg->len, msg->msg, msg->reply, !block ? ", nb" : ""); else dprintk(2, "%s: %*ph%s\n", __func__, msg->len, msg->msg, !block ? " (nb)" : ""); if (msg->timeout && msg->len == 1) { dprintk(1, "%s: can't reply to poll msg\n", __func__); return -EINVAL; } if (is_raw) { if (!capable(CAP_SYS_RAWIO)) return -EPERM; } else { /* A CDC-Only device can only send CDC messages */ if ((adap->log_addrs.flags & CEC_LOG_ADDRS_FL_CDC_ONLY) && (msg->len == 1 || msg->msg[1] != CEC_MSG_CDC_MESSAGE)) { dprintk(1, "%s: not a CDC message\n", __func__); return -EINVAL; } if (msg->len >= 4 && msg->msg[1] == CEC_MSG_CDC_MESSAGE) { msg->msg[2] = adap->phys_addr >> 8; msg->msg[3] = adap->phys_addr & 0xff; } if (msg->len == 1) { if (cec_msg_destination(msg) == 0xf) { dprintk(1, "%s: invalid poll message\n", __func__); return -EINVAL; } if (cec_has_log_addr(adap, cec_msg_destination(msg))) { /* * If the destination is a logical address our * adapter has already claimed, then just NACK * this. It depends on the hardware what it will * do with a POLL to itself (some OK this), so * it is just as easy to handle it here so the * behavior will be consistent. */ msg->tx_ts = ktime_get_ns(); msg->tx_status = CEC_TX_STATUS_NACK | CEC_TX_STATUS_MAX_RETRIES; msg->tx_nack_cnt = 1; msg->sequence = ++adap->sequence; if (!msg->sequence) msg->sequence = ++adap->sequence; return 0; } } if (msg->len > 1 && !cec_msg_is_broadcast(msg) && cec_has_log_addr(adap, cec_msg_destination(msg))) { dprintk(1, "%s: destination is the adapter itself\n", __func__); return -EINVAL; } if (msg->len > 1 && adap->is_configured && !cec_has_log_addr(adap, cec_msg_initiator(msg))) { dprintk(1, "%s: initiator has unknown logical address %d\n", __func__, cec_msg_initiator(msg)); return -EINVAL; } /* * Special case: allow Ping and IMAGE/TEXT_VIEW_ON to be * transmitted to a TV, even if the adapter is unconfigured. * This makes it possible to detect or wake up displays that * pull down the HPD when in standby. */ if (!adap->is_configured && !adap->is_configuring && (msg->len > 2 || cec_msg_destination(msg) != CEC_LOG_ADDR_TV || (msg->len == 2 && msg->msg[1] != CEC_MSG_IMAGE_VIEW_ON && msg->msg[1] != CEC_MSG_TEXT_VIEW_ON))) { dprintk(1, "%s: adapter is unconfigured\n", __func__); return -ENONET; } } if (!adap->is_configured && !adap->is_configuring) { if (adap->needs_hpd) { dprintk(1, "%s: adapter is unconfigured and needs HPD\n", __func__); return -ENONET; } if (reply_vendor_id || msg->reply) { dprintk(1, "%s: adapter is unconfigured so reply is not supported\n", __func__); return -EINVAL; } } if (adap->transmit_queue_sz >= CEC_MAX_MSG_TX_QUEUE_SZ) { dprintk(2, "%s: transmit queue full\n", __func__); return -EBUSY; } data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; msg->sequence = ++adap->sequence; if (!msg->sequence) msg->sequence = ++adap->sequence; data->msg = *msg; data->fh = fh; data->adap = adap; data->blocking = block; if (reply_vendor_id) { memcpy(data->match_reply, msg->msg + 1, 4); data->match_reply[4] = msg->reply; data->match_len = 5; } else if (msg->timeout) { data->match_reply[0] = msg->reply; data->match_len = 1; } init_completion(&data->c); INIT_DELAYED_WORK(&data->work, cec_wait_timeout); if (fh) list_add_tail(&data->xfer_list, &fh->xfer_list); else INIT_LIST_HEAD(&data->xfer_list); list_add_tail(&data->list, &adap->transmit_queue); adap->transmit_queue_sz++; if (!adap->transmitting) wake_up_interruptible(&adap->kthread_waitq); /* All done if we don't need to block waiting for completion */ if (!block) return 0; /* * Release the lock and wait, retake the lock afterwards. */ mutex_unlock(&adap->lock); err = wait_for_completion_killable(&data->c); cancel_delayed_work_sync(&data->work); mutex_lock(&adap->lock); if (err) adap->transmit_in_progress_aborted = true; /* Cancel the transmit if it was interrupted */ if (!data->completed) { if (data->msg.tx_status & CEC_TX_STATUS_OK) cec_data_cancel(data, CEC_TX_STATUS_OK, CEC_RX_STATUS_ABORTED); else cec_data_cancel(data, CEC_TX_STATUS_ABORTED, 0); } /* The transmit completed (possibly with an error) */ *msg = data->msg; if (WARN_ON(!list_empty(&data->list))) list_del(&data->list); if (WARN_ON(!list_empty(&data->xfer_list))) list_del(&data->xfer_list); kfree(data); return 0; } /* Helper function to be used by drivers and this framework. */ int cec_transmit_msg(struct cec_adapter *adap, struct cec_msg *msg, bool block) { int ret; mutex_lock(&adap->lock); ret = cec_transmit_msg_fh(adap, msg, NULL, block); mutex_unlock(&adap->lock); return ret; } EXPORT_SYMBOL_GPL(cec_transmit_msg); /* * I don't like forward references but without this the low-level * cec_received_msg() function would come after a bunch of high-level * CEC protocol handling functions. That was very confusing. */ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, bool is_reply); #define DIRECTED 0x80 #define BCAST1_4 0x40 #define BCAST2_0 0x20 /* broadcast only allowed for >= 2.0 */ #define BCAST (BCAST1_4 | BCAST2_0) #define BOTH (BCAST | DIRECTED) /* * Specify minimum length and whether the message is directed, broadcast * or both. Messages that do not match the criteria are ignored as per * the CEC specification. */ static const u8 cec_msg_size[256] = { [CEC_MSG_ACTIVE_SOURCE] = 4 | BCAST, [CEC_MSG_IMAGE_VIEW_ON] = 2 | DIRECTED, [CEC_MSG_TEXT_VIEW_ON] = 2 | DIRECTED, [CEC_MSG_INACTIVE_SOURCE] = 4 | DIRECTED, [CEC_MSG_REQUEST_ACTIVE_SOURCE] = 2 | BCAST, [CEC_MSG_ROUTING_CHANGE] = 6 | BCAST, [CEC_MSG_ROUTING_INFORMATION] = 4 | BCAST, [CEC_MSG_SET_STREAM_PATH] = 4 | BCAST, [CEC_MSG_STANDBY] = 2 | BOTH, [CEC_MSG_RECORD_OFF] = 2 | DIRECTED, [CEC_MSG_RECORD_ON] = 3 | DIRECTED, [CEC_MSG_RECORD_STATUS] = 3 | DIRECTED, [CEC_MSG_RECORD_TV_SCREEN] = 2 | DIRECTED, [CEC_MSG_CLEAR_ANALOGUE_TIMER] = 13 | DIRECTED, [CEC_MSG_CLEAR_DIGITAL_TIMER] = 16 | DIRECTED, [CEC_MSG_CLEAR_EXT_TIMER] = 13 | DIRECTED, [CEC_MSG_SET_ANALOGUE_TIMER] = 13 | DIRECTED, [CEC_MSG_SET_DIGITAL_TIMER] = 16 | DIRECTED, [CEC_MSG_SET_EXT_TIMER] = 13 | DIRECTED, [CEC_MSG_SET_TIMER_PROGRAM_TITLE] = 2 | DIRECTED, [CEC_MSG_TIMER_CLEARED_STATUS] = 3 | DIRECTED, [CEC_MSG_TIMER_STATUS] = 3 | DIRECTED, [CEC_MSG_CEC_VERSION] = 3 | DIRECTED, [CEC_MSG_GET_CEC_VERSION] = 2 | DIRECTED, [CEC_MSG_GIVE_PHYSICAL_ADDR] = 2 | DIRECTED, [CEC_MSG_GET_MENU_LANGUAGE] = 2 | DIRECTED, [CEC_MSG_REPORT_PHYSICAL_ADDR] = 5 | BCAST, [CEC_MSG_SET_MENU_LANGUAGE] = 5 | BCAST, [CEC_MSG_REPORT_FEATURES] = 6 | BCAST, [CEC_MSG_GIVE_FEATURES] = 2 | DIRECTED, [CEC_MSG_DECK_CONTROL] = 3 | DIRECTED, [CEC_MSG_DECK_STATUS] = 3 | DIRECTED, [CEC_MSG_GIVE_DECK_STATUS] = 3 | DIRECTED, [CEC_MSG_PLAY] = 3 | DIRECTED, [CEC_MSG_GIVE_TUNER_DEVICE_STATUS] = 3 | DIRECTED, [CEC_MSG_SELECT_ANALOGUE_SERVICE] = 6 | DIRECTED, [CEC_MSG_SELECT_DIGITAL_SERVICE] = 9 | DIRECTED, [CEC_MSG_TUNER_DEVICE_STATUS] = 7 | DIRECTED, [CEC_MSG_TUNER_STEP_DECREMENT] = 2 | DIRECTED, [CEC_MSG_TUNER_STEP_INCREMENT] = 2 | DIRECTED, [CEC_MSG_DEVICE_VENDOR_ID] = 5 | BCAST, [CEC_MSG_GIVE_DEVICE_VENDOR_ID] = 2 | DIRECTED, [CEC_MSG_VENDOR_COMMAND] = 2 | DIRECTED, [CEC_MSG_VENDOR_COMMAND_WITH_ID] = 5 | BOTH, [CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN] = 2 | BOTH, [CEC_MSG_VENDOR_REMOTE_BUTTON_UP] = 2 | BOTH, [CEC_MSG_SET_OSD_STRING] = 3 | DIRECTED, [CEC_MSG_GIVE_OSD_NAME] = 2 | DIRECTED, [CEC_MSG_SET_OSD_NAME] = 2 | DIRECTED, [CEC_MSG_MENU_REQUEST] = 3 | DIRECTED, [CEC_MSG_MENU_STATUS] = 3 | DIRECTED, [CEC_MSG_USER_CONTROL_PRESSED] = 3 | DIRECTED, [CEC_MSG_USER_CONTROL_RELEASED] = 2 | DIRECTED, [CEC_MSG_GIVE_DEVICE_POWER_STATUS] = 2 | DIRECTED, [CEC_MSG_REPORT_POWER_STATUS] = 3 | DIRECTED | BCAST2_0, [CEC_MSG_FEATURE_ABORT] = 4 | DIRECTED, [CEC_MSG_ABORT] = 2 | DIRECTED, [CEC_MSG_GIVE_AUDIO_STATUS] = 2 | DIRECTED, [CEC_MSG_GIVE_SYSTEM_AUDIO_MODE_STATUS] = 2 | DIRECTED, [CEC_MSG_REPORT_AUDIO_STATUS] = 3 | DIRECTED, [CEC_MSG_REPORT_SHORT_AUDIO_DESCRIPTOR] = 2 | DIRECTED, [CEC_MSG_REQUEST_SHORT_AUDIO_DESCRIPTOR] = 2 | DIRECTED, [CEC_MSG_SET_SYSTEM_AUDIO_MODE] = 3 | BOTH, [CEC_MSG_SET_AUDIO_VOLUME_LEVEL] = 3 | DIRECTED, [CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST] = 2 | DIRECTED, [CEC_MSG_SYSTEM_AUDIO_MODE_STATUS] = 3 | DIRECTED, [CEC_MSG_SET_AUDIO_RATE] = 3 | DIRECTED, [CEC_MSG_INITIATE_ARC] = 2 | DIRECTED, [CEC_MSG_REPORT_ARC_INITIATED] = 2 | DIRECTED, [CEC_MSG_REPORT_ARC_TERMINATED] = 2 | DIRECTED, [CEC_MSG_REQUEST_ARC_INITIATION] = 2 | DIRECTED, [CEC_MSG_REQUEST_ARC_TERMINATION] = 2 | DIRECTED, [CEC_MSG_TERMINATE_ARC] = 2 | DIRECTED, [CEC_MSG_REQUEST_CURRENT_LATENCY] = 4 | BCAST, [CEC_MSG_REPORT_CURRENT_LATENCY] = 6 | BCAST, [CEC_MSG_CDC_MESSAGE] = 2 | BCAST, }; /* Called by the CEC adapter if a message is received */ void cec_received_msg_ts(struct cec_adapter *adap, struct cec_msg *msg, ktime_t ts) { struct cec_data *data; u8 msg_init = cec_msg_initiator(msg); u8 msg_dest = cec_msg_destination(msg); u8 cmd = msg->msg[1]; bool is_reply = false; bool valid_la = true; bool monitor_valid_la = true; u8 min_len = 0; if (WARN_ON(!msg->len || msg->len > CEC_MAX_MSG_SIZE)) return; if (adap->devnode.unregistered) return; /* * Some CEC adapters will receive the messages that they transmitted. * This test filters out those messages by checking if we are the * initiator, and just returning in that case. * * Note that this won't work if this is an Unregistered device. * * It is bad practice if the hardware receives the message that it * transmitted and luckily most CEC adapters behave correctly in this * respect. */ if (msg_init != CEC_LOG_ADDR_UNREGISTERED && cec_has_log_addr(adap, msg_init)) return; msg->rx_ts = ktime_to_ns(ts); msg->rx_status = CEC_RX_STATUS_OK; msg->sequence = msg->reply = msg->timeout = 0; msg->tx_status = 0; msg->tx_ts = 0; msg->tx_arb_lost_cnt = 0; msg->tx_nack_cnt = 0; msg->tx_low_drive_cnt = 0; msg->tx_error_cnt = 0; msg->flags = 0; memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len); mutex_lock(&adap->lock); dprintk(2, "%s: %*ph\n", __func__, msg->len, msg->msg); if (!adap->transmit_in_progress) adap->last_initiator = 0xff; /* Check if this message was for us (directed or broadcast). */ if (!cec_msg_is_broadcast(msg)) { valid_la = cec_has_log_addr(adap, msg_dest); monitor_valid_la = valid_la; } /* * Check if the length is not too short or if the message is a * broadcast message where a directed message was expected or * vice versa. If so, then the message has to be ignored (according * to section CEC 7.3 and CEC 12.2). */ if (valid_la && msg->len > 1 && cec_msg_size[cmd]) { u8 dir_fl = cec_msg_size[cmd] & BOTH; min_len = cec_msg_size[cmd] & 0x1f; if (msg->len < min_len) valid_la = false; else if (!cec_msg_is_broadcast(msg) && !(dir_fl & DIRECTED)) valid_la = false; else if (cec_msg_is_broadcast(msg) && !(dir_fl & BCAST)) valid_la = false; else if (cec_msg_is_broadcast(msg) && adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0 && !(dir_fl & BCAST1_4)) valid_la = false; } if (valid_la && min_len) { /* These messages have special length requirements */ switch (cmd) { case CEC_MSG_RECORD_ON: switch (msg->msg[2]) { case CEC_OP_RECORD_SRC_OWN: break; case CEC_OP_RECORD_SRC_DIGITAL: if (msg->len < 10) valid_la = false; break; case CEC_OP_RECORD_SRC_ANALOG: if (msg->len < 7) valid_la = false; break; case CEC_OP_RECORD_SRC_EXT_PLUG: if (msg->len < 4) valid_la = false; break; case CEC_OP_RECORD_SRC_EXT_PHYS_ADDR: if (msg->len < 5) valid_la = false; break; } break; } } /* It's a valid message and not a poll or CDC message */ if (valid_la && msg->len > 1 && cmd != CEC_MSG_CDC_MESSAGE) { bool abort = cmd == CEC_MSG_FEATURE_ABORT; /* The aborted command is in msg[2] */ if (abort) cmd = msg->msg[2]; /* * Walk over all transmitted messages that are waiting for a * reply. */ list_for_each_entry(data, &adap->wait_queue, list) { struct cec_msg *dst = &data->msg; /* * The *only* CEC message that has two possible replies * is CEC_MSG_INITIATE_ARC. * In this case allow either of the two replies. */ if (!abort && dst->msg[1] == CEC_MSG_INITIATE_ARC && (cmd == CEC_MSG_REPORT_ARC_INITIATED || cmd == CEC_MSG_REPORT_ARC_TERMINATED) && (data->match_reply[0] == CEC_MSG_REPORT_ARC_INITIATED || data->match_reply[0] == CEC_MSG_REPORT_ARC_TERMINATED)) { dst->reply = cmd; data->match_reply[0] = cmd; } /* Does the command match? */ if ((abort && cmd != dst->msg[1]) || (!abort && memcmp(data->match_reply, msg->msg + 1, data->match_len))) continue; /* Does the addressing match? */ if (msg_init != cec_msg_destination(dst) && !cec_msg_is_broadcast(dst)) continue; /* We got a reply */ memcpy(dst->msg, msg->msg, msg->len); dst->len = msg->len; dst->rx_ts = msg->rx_ts; dst->rx_status = msg->rx_status; if (abort) dst->rx_status |= CEC_RX_STATUS_FEATURE_ABORT; msg->flags = dst->flags; msg->sequence = dst->sequence; /* Remove it from the wait_queue */ list_del_init(&data->list); /* Cancel the pending timeout work */ if (!cancel_delayed_work(&data->work)) { mutex_unlock(&adap->lock); cancel_delayed_work_sync(&data->work); mutex_lock(&adap->lock); } /* * Mark this as a reply, provided someone is still * waiting for the answer. */ if (data->fh) is_reply = true; cec_data_completed(data); break; } } mutex_unlock(&adap->lock); /* Pass the message on to any monitoring filehandles */ cec_queue_msg_monitor(adap, msg, monitor_valid_la); /* We're done if it is not for us or a poll message */ if (!valid_la || msg->len <= 1) return; if (adap->log_addrs.log_addr_mask == 0) return; /* * Process the message on the protocol level. If is_reply is true, * then cec_receive_notify() won't pass on the reply to the listener(s) * since that was already done by cec_data_completed() above. */ cec_receive_notify(adap, msg, is_reply); } EXPORT_SYMBOL_GPL(cec_received_msg_ts); /* Logical Address Handling */ /* * Attempt to claim a specific logical address. * * This function is called with adap->lock held. */ static int cec_config_log_addr(struct cec_adapter *adap, unsigned int idx, unsigned int log_addr) { struct cec_log_addrs *las = &adap->log_addrs; struct cec_msg msg = { }; const unsigned int max_retries = 2; unsigned int i; int err; if (cec_has_log_addr(adap, log_addr)) return 0; /* Send poll message */ msg.len = 1; msg.msg[0] = (log_addr << 4) | log_addr; for (i = 0; i < max_retries; i++) { err = cec_transmit_msg_fh(adap, &msg, NULL, true); /* * While trying to poll the physical address was reset * and the adapter was unconfigured, so bail out. */ if (adap->phys_addr == CEC_PHYS_ADDR_INVALID) return -EINTR; /* Also bail out if the PA changed while configuring. */ if (adap->must_reconfigure) return -EINTR; if (err) return err; /* * The message was aborted or timed out due to a disconnect or * unconfigure, just bail out. */ if (msg.tx_status & (CEC_TX_STATUS_ABORTED | CEC_TX_STATUS_TIMEOUT)) return -EINTR; if (msg.tx_status & CEC_TX_STATUS_OK) return 0; if (msg.tx_status & CEC_TX_STATUS_NACK) break; /* * Retry up to max_retries times if the message was neither * OKed or NACKed. This can happen due to e.g. a Lost * Arbitration condition. */ } /* * If we are unable to get an OK or a NACK after max_retries attempts * (and note that each attempt already consists of four polls), then * we assume that something is really weird and that it is not a * good idea to try and claim this logical address. */ if (i == max_retries) { dprintk(0, "polling for LA %u failed with tx_status=0x%04x\n", log_addr, msg.tx_status); return 0; } /* * Message not acknowledged, so this logical * address is free to use. */ err = call_op(adap, adap_log_addr, log_addr); if (err) return err; las->log_addr[idx] = log_addr; las->log_addr_mask |= 1 << log_addr; return 1; } /* * Unconfigure the adapter: clear all logical addresses and send * the state changed event. * * This function is called with adap->lock held. */ static void cec_adap_unconfigure(struct cec_adapter *adap) { if (!adap->needs_hpd || adap->phys_addr != CEC_PHYS_ADDR_INVALID) WARN_ON(call_op(adap, adap_log_addr, CEC_LOG_ADDR_INVALID)); adap->log_addrs.log_addr_mask = 0; adap->is_configured = false; cec_flush(adap); wake_up_interruptible(&adap->kthread_waitq); cec_post_state_event(adap); call_void_op(adap, adap_unconfigured); } /* * Attempt to claim the required logical addresses. */ static int cec_config_thread_func(void *arg) { /* The various LAs for each type of device */ static const u8 tv_log_addrs[] = { CEC_LOG_ADDR_TV, CEC_LOG_ADDR_SPECIFIC, CEC_LOG_ADDR_INVALID }; static const u8 record_log_addrs[] = { CEC_LOG_ADDR_RECORD_1, CEC_LOG_ADDR_RECORD_2, CEC_LOG_ADDR_RECORD_3, CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, CEC_LOG_ADDR_INVALID }; static const u8 tuner_log_addrs[] = { CEC_LOG_ADDR_TUNER_1, CEC_LOG_ADDR_TUNER_2, CEC_LOG_ADDR_TUNER_3, CEC_LOG_ADDR_TUNER_4, CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, CEC_LOG_ADDR_INVALID }; static const u8 playback_log_addrs[] = { CEC_LOG_ADDR_PLAYBACK_1, CEC_LOG_ADDR_PLAYBACK_2, CEC_LOG_ADDR_PLAYBACK_3, CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, CEC_LOG_ADDR_INVALID }; static const u8 audiosystem_log_addrs[] = { CEC_LOG_ADDR_AUDIOSYSTEM, CEC_LOG_ADDR_INVALID }; static const u8 specific_use_log_addrs[] = { CEC_LOG_ADDR_SPECIFIC, CEC_LOG_ADDR_BACKUP_1, CEC_LOG_ADDR_BACKUP_2, CEC_LOG_ADDR_INVALID }; static const u8 *type2addrs[6] = { [CEC_LOG_ADDR_TYPE_TV] = tv_log_addrs, [CEC_LOG_ADDR_TYPE_RECORD] = record_log_addrs, [CEC_LOG_ADDR_TYPE_TUNER] = tuner_log_addrs, [CEC_LOG_ADDR_TYPE_PLAYBACK] = playback_log_addrs, [CEC_LOG_ADDR_TYPE_AUDIOSYSTEM] = audiosystem_log_addrs, [CEC_LOG_ADDR_TYPE_SPECIFIC] = specific_use_log_addrs, }; static const u16 type2mask[] = { [CEC_LOG_ADDR_TYPE_TV] = CEC_LOG_ADDR_MASK_TV, [CEC_LOG_ADDR_TYPE_RECORD] = CEC_LOG_ADDR_MASK_RECORD, [CEC_LOG_ADDR_TYPE_TUNER] = CEC_LOG_ADDR_MASK_TUNER, [CEC_LOG_ADDR_TYPE_PLAYBACK] = CEC_LOG_ADDR_MASK_PLAYBACK, [CEC_LOG_ADDR_TYPE_AUDIOSYSTEM] = CEC_LOG_ADDR_MASK_AUDIOSYSTEM, [CEC_LOG_ADDR_TYPE_SPECIFIC] = CEC_LOG_ADDR_MASK_SPECIFIC, }; struct cec_adapter *adap = arg; struct cec_log_addrs *las = &adap->log_addrs; int err; int i, j; mutex_lock(&adap->lock); dprintk(1, "physical address: %x.%x.%x.%x, claim %d logical addresses\n", cec_phys_addr_exp(adap->phys_addr), las->num_log_addrs); las->log_addr_mask = 0; if (las->log_addr_type[0] == CEC_LOG_ADDR_TYPE_UNREGISTERED) goto configured; reconfigure: for (i = 0; i < las->num_log_addrs; i++) { unsigned int type = las->log_addr_type[i]; const u8 *la_list; u8 last_la; /* * The TV functionality can only map to physical address 0. * For any other address, try the Specific functionality * instead as per the spec. */ if (adap->phys_addr && type == CEC_LOG_ADDR_TYPE_TV) type = CEC_LOG_ADDR_TYPE_SPECIFIC; la_list = type2addrs[type]; last_la = las->log_addr[i]; las->log_addr[i] = CEC_LOG_ADDR_INVALID; if (last_la == CEC_LOG_ADDR_INVALID || last_la == CEC_LOG_ADDR_UNREGISTERED || !((1 << last_la) & type2mask[type])) last_la = la_list[0]; err = cec_config_log_addr(adap, i, last_la); if (adap->must_reconfigure) { adap->must_reconfigure = false; las->log_addr_mask = 0; goto reconfigure; } if (err > 0) /* Reused last LA */ continue; if (err < 0) goto unconfigure; for (j = 0; la_list[j] != CEC_LOG_ADDR_INVALID; j++) { /* Tried this one already, skip it */ if (la_list[j] == last_la) continue; /* The backup addresses are CEC 2.0 specific */ if ((la_list[j] == CEC_LOG_ADDR_BACKUP_1 || la_list[j] == CEC_LOG_ADDR_BACKUP_2) && las->cec_version < CEC_OP_CEC_VERSION_2_0) continue; err = cec_config_log_addr(adap, i, la_list[j]); if (err == 0) /* LA is in use */ continue; if (err < 0) goto unconfigure; /* Done, claimed an LA */ break; } if (la_list[j] == CEC_LOG_ADDR_INVALID) dprintk(1, "could not claim LA %d\n", i); } if (adap->log_addrs.log_addr_mask == 0 && !(las->flags & CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK)) goto unconfigure; configured: if (adap->log_addrs.log_addr_mask == 0) { /* Fall back to unregistered */ las->log_addr[0] = CEC_LOG_ADDR_UNREGISTERED; las->log_addr_mask = 1 << las->log_addr[0]; for (i = 1; i < las->num_log_addrs; i++) las->log_addr[i] = CEC_LOG_ADDR_INVALID; } for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) las->log_addr[i] = CEC_LOG_ADDR_INVALID; adap->is_configured = true; adap->is_configuring = false; adap->must_reconfigure = false; cec_post_state_event(adap); /* * Now post the Report Features and Report Physical Address broadcast * messages. Note that these are non-blocking transmits, meaning that * they are just queued up and once adap->lock is unlocked the main * thread will kick in and start transmitting these. * * If after this function is done (but before one or more of these * messages are actually transmitted) the CEC adapter is unconfigured, * then any remaining messages will be dropped by the main thread. */ for (i = 0; i < las->num_log_addrs; i++) { struct cec_msg msg = {}; if (las->log_addr[i] == CEC_LOG_ADDR_INVALID || (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY)) continue; msg.msg[0] = (las->log_addr[i] << 4) | 0x0f; /* Report Features must come first according to CEC 2.0 */ if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED && adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0) { cec_fill_msg_report_features(adap, &msg, i); cec_transmit_msg_fh(adap, &msg, NULL, false); } /* Report Physical Address */ cec_msg_report_physical_addr(&msg, adap->phys_addr, las->primary_device_type[i]); dprintk(1, "config: la %d pa %x.%x.%x.%x\n", las->log_addr[i], cec_phys_addr_exp(adap->phys_addr)); cec_transmit_msg_fh(adap, &msg, NULL, false); /* Report Vendor ID */ if (adap->log_addrs.vendor_id != CEC_VENDOR_ID_NONE) { cec_msg_device_vendor_id(&msg, adap->log_addrs.vendor_id); cec_transmit_msg_fh(adap, &msg, NULL, false); } } adap->kthread_config = NULL; complete(&adap->config_completion); mutex_unlock(&adap->lock); call_void_op(adap, configured); return 0; unconfigure: for (i = 0; i < las->num_log_addrs; i++) las->log_addr[i] = CEC_LOG_ADDR_INVALID; cec_adap_unconfigure(adap); adap->is_configuring = false; adap->must_reconfigure = false; adap->kthread_config = NULL; complete(&adap->config_completion); mutex_unlock(&adap->lock); return 0; } /* * Called from either __cec_s_phys_addr or __cec_s_log_addrs to claim the * logical addresses. * * This function is called with adap->lock held. */ static void cec_claim_log_addrs(struct cec_adapter *adap, bool block) { if (WARN_ON(adap->is_claiming_log_addrs || adap->is_configuring || adap->is_configured)) return; adap->is_claiming_log_addrs = true; init_completion(&adap->config_completion); /* Ready to kick off the thread */ adap->is_configuring = true; adap->kthread_config = kthread_run(cec_config_thread_func, adap, "ceccfg-%s", adap->name); if (IS_ERR(adap->kthread_config)) { adap->kthread_config = NULL; adap->is_configuring = false; } else if (block) { mutex_unlock(&adap->lock); wait_for_completion(&adap->config_completion); mutex_lock(&adap->lock); } adap->is_claiming_log_addrs = false; } /* * Helper function to enable/disable the CEC adapter. * * This function is called with adap->lock held. */ int cec_adap_enable(struct cec_adapter *adap) { bool enable; int ret = 0; enable = adap->monitor_all_cnt || adap->monitor_pin_cnt || adap->log_addrs.num_log_addrs; if (adap->needs_hpd) enable = enable && adap->phys_addr != CEC_PHYS_ADDR_INVALID; if (adap->devnode.unregistered) enable = false; if (enable == adap->is_enabled) return 0; /* serialize adap_enable */ mutex_lock(&adap->devnode.lock); if (enable) { adap->last_initiator = 0xff; adap->transmit_in_progress = false; adap->tx_low_drive_log_cnt = 0; adap->tx_error_log_cnt = 0; ret = adap->ops->adap_enable(adap, true); if (!ret) { /* * Enable monitor-all/pin modes if needed. We warn, but * continue if this fails as this is not a critical error. */ if (adap->monitor_all_cnt) WARN_ON(call_op(adap, adap_monitor_all_enable, true)); if (adap->monitor_pin_cnt) WARN_ON(call_op(adap, adap_monitor_pin_enable, true)); } } else { /* Disable monitor-all/pin modes if needed (needs_hpd == 1) */ if (adap->monitor_all_cnt) WARN_ON(call_op(adap, adap_monitor_all_enable, false)); if (adap->monitor_pin_cnt) WARN_ON(call_op(adap, adap_monitor_pin_enable, false)); WARN_ON(adap->ops->adap_enable(adap, false)); adap->last_initiator = 0xff; adap->transmit_in_progress = false; adap->transmit_in_progress_aborted = false; if (adap->transmitting) cec_data_cancel(adap->transmitting, CEC_TX_STATUS_ABORTED, 0); } if (!ret) adap->is_enabled = enable; wake_up_interruptible(&adap->kthread_waitq); mutex_unlock(&adap->devnode.lock); return ret; } /* Set a new physical address and send an event notifying userspace of this. * * This function is called with adap->lock held. */ void __cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block) { bool becomes_invalid = phys_addr == CEC_PHYS_ADDR_INVALID; bool is_invalid = adap->phys_addr == CEC_PHYS_ADDR_INVALID; if (phys_addr == adap->phys_addr) return; if (!becomes_invalid && adap->devnode.unregistered) return; dprintk(1, "new physical address %x.%x.%x.%x\n", cec_phys_addr_exp(phys_addr)); if (becomes_invalid || !is_invalid) { adap->phys_addr = CEC_PHYS_ADDR_INVALID; cec_post_state_event(adap); cec_adap_unconfigure(adap); if (becomes_invalid) { cec_adap_enable(adap); return; } } adap->phys_addr = phys_addr; if (is_invalid) cec_adap_enable(adap); cec_post_state_event(adap); if (!adap->log_addrs.num_log_addrs) return; if (adap->is_configuring) adap->must_reconfigure = true; else cec_claim_log_addrs(adap, block); } void cec_s_phys_addr(struct cec_adapter *adap, u16 phys_addr, bool block) { if (IS_ERR_OR_NULL(adap)) return; mutex_lock(&adap->lock); __cec_s_phys_addr(adap, phys_addr, block); mutex_unlock(&adap->lock); } EXPORT_SYMBOL_GPL(cec_s_phys_addr); /* * Note: In the drm subsystem, prefer calling (if possible): * * cec_s_phys_addr(adap, connector->display_info.source_physical_address, false); */ void cec_s_phys_addr_from_edid(struct cec_adapter *adap, const struct edid *edid) { u16 pa = CEC_PHYS_ADDR_INVALID; if (edid && edid->extensions) pa = cec_get_edid_phys_addr((const u8 *)edid, EDID_LENGTH * (edid->extensions + 1), NULL); cec_s_phys_addr(adap, pa, false); } EXPORT_SYMBOL_GPL(cec_s_phys_addr_from_edid); void cec_s_conn_info(struct cec_adapter *adap, const struct cec_connector_info *conn_info) { if (IS_ERR_OR_NULL(adap)) return; if (!(adap->capabilities & CEC_CAP_CONNECTOR_INFO)) return; mutex_lock(&adap->lock); if (conn_info) adap->conn_info = *conn_info; else memset(&adap->conn_info, 0, sizeof(adap->conn_info)); cec_post_state_event(adap); mutex_unlock(&adap->lock); } EXPORT_SYMBOL_GPL(cec_s_conn_info); /* * Called from either the ioctl or a driver to set the logical addresses. * * This function is called with adap->lock held. */ int __cec_s_log_addrs(struct cec_adapter *adap, struct cec_log_addrs *log_addrs, bool block) { u16 type_mask = 0; int err; int i; if (adap->devnode.unregistered) return -ENODEV; if (!log_addrs || log_addrs->num_log_addrs == 0) { if (!adap->log_addrs.num_log_addrs) return 0; if (adap->is_configuring || adap->is_configured) cec_adap_unconfigure(adap); adap->log_addrs.num_log_addrs = 0; for (i = 0; i < CEC_MAX_LOG_ADDRS; i++) adap->log_addrs.log_addr[i] = CEC_LOG_ADDR_INVALID; adap->log_addrs.osd_name[0] = '\0'; adap->log_addrs.vendor_id = CEC_VENDOR_ID_NONE; adap->log_addrs.cec_version = CEC_OP_CEC_VERSION_2_0; cec_adap_enable(adap); return 0; } if (log_addrs->flags & CEC_LOG_ADDRS_FL_CDC_ONLY) { /* * Sanitize log_addrs fields if a CDC-Only device is * requested. */ log_addrs->num_log_addrs = 1; log_addrs->osd_name[0] = '\0'; log_addrs->vendor_id = CEC_VENDOR_ID_NONE; log_addrs->log_addr_type[0] = CEC_LOG_ADDR_TYPE_UNREGISTERED; /* * This is just an internal convention since a CDC-Only device * doesn't have to be a switch. But switches already use * unregistered, so it makes some kind of sense to pick this * as the primary device. Since a CDC-Only device never sends * any 'normal' CEC messages this primary device type is never * sent over the CEC bus. */ log_addrs->primary_device_type[0] = CEC_OP_PRIM_DEVTYPE_SWITCH; log_addrs->all_device_types[0] = 0; log_addrs->features[0][0] = 0; log_addrs->features[0][1] = 0; } /* Ensure the osd name is 0-terminated */ log_addrs->osd_name[sizeof(log_addrs->osd_name) - 1] = '\0'; /* Sanity checks */ if (log_addrs->num_log_addrs > adap->available_log_addrs) { dprintk(1, "num_log_addrs > %d\n", adap->available_log_addrs); return -EINVAL; } /* * Vendor ID is a 24 bit number, so check if the value is * within the correct range. */ if (log_addrs->vendor_id != CEC_VENDOR_ID_NONE && (log_addrs->vendor_id & 0xff000000) != 0) { dprintk(1, "invalid vendor ID\n"); return -EINVAL; } if (log_addrs->cec_version != CEC_OP_CEC_VERSION_1_4 && log_addrs->cec_version != CEC_OP_CEC_VERSION_2_0) { dprintk(1, "invalid CEC version\n"); return -EINVAL; } if (log_addrs->num_log_addrs > 1) for (i = 0; i < log_addrs->num_log_addrs; i++) if (log_addrs->log_addr_type[i] == CEC_LOG_ADDR_TYPE_UNREGISTERED) { dprintk(1, "num_log_addrs > 1 can't be combined with unregistered LA\n"); return -EINVAL; } for (i = 0; i < log_addrs->num_log_addrs; i++) { const u8 feature_sz = ARRAY_SIZE(log_addrs->features[0]); u8 *features = log_addrs->features[i]; bool op_is_dev_features = false; unsigned int j; log_addrs->log_addr[i] = CEC_LOG_ADDR_INVALID; if (log_addrs->log_addr_type[i] > CEC_LOG_ADDR_TYPE_UNREGISTERED) { dprintk(1, "unknown logical address type\n"); return -EINVAL; } if (type_mask & (1 << log_addrs->log_addr_type[i])) { dprintk(1, "duplicate logical address type\n"); return -EINVAL; } type_mask |= 1 << log_addrs->log_addr_type[i]; if ((type_mask & (1 << CEC_LOG_ADDR_TYPE_RECORD)) && (type_mask & (1 << CEC_LOG_ADDR_TYPE_PLAYBACK))) { /* Record already contains the playback functionality */ dprintk(1, "invalid record + playback combination\n"); return -EINVAL; } if (log_addrs->primary_device_type[i] > CEC_OP_PRIM_DEVTYPE_PROCESSOR) { dprintk(1, "unknown primary device type\n"); return -EINVAL; } if (log_addrs->primary_device_type[i] == 2) { dprintk(1, "invalid primary device type\n"); return -EINVAL; } for (j = 0; j < feature_sz; j++) { if ((features[j] & 0x80) == 0) { if (op_is_dev_features) break; op_is_dev_features = true; } } if (!op_is_dev_features || j == feature_sz) { dprintk(1, "malformed features\n"); return -EINVAL; } /* Zero unused part of the feature array */ memset(features + j + 1, 0, feature_sz - j - 1); } if (log_addrs->cec_version >= CEC_OP_CEC_VERSION_2_0) { if (log_addrs->num_log_addrs > 2) { dprintk(1, "CEC 2.0 allows no more than 2 logical addresses\n"); return -EINVAL; } if (log_addrs->num_log_addrs == 2) { if (!(type_mask & ((1 << CEC_LOG_ADDR_TYPE_AUDIOSYSTEM) | (1 << CEC_LOG_ADDR_TYPE_TV)))) { dprintk(1, "two LAs is only allowed for audiosystem and TV\n"); return -EINVAL; } if (!(type_mask & ((1 << CEC_LOG_ADDR_TYPE_PLAYBACK) | (1 << CEC_LOG_ADDR_TYPE_RECORD)))) { dprintk(1, "an audiosystem/TV can only be combined with record or playback\n"); return -EINVAL; } } } /* Zero unused LAs */ for (i = log_addrs->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++) { log_addrs->primary_device_type[i] = 0; log_addrs->log_addr_type[i] = 0; log_addrs->all_device_types[i] = 0; memset(log_addrs->features[i], 0, sizeof(log_addrs->features[i])); } log_addrs->log_addr_mask = adap->log_addrs.log_addr_mask; adap->log_addrs = *log_addrs; err = cec_adap_enable(adap); if (!err && adap->phys_addr != CEC_PHYS_ADDR_INVALID) cec_claim_log_addrs(adap, block); return err; } int cec_s_log_addrs(struct cec_adapter *adap, struct cec_log_addrs *log_addrs, bool block) { int err; mutex_lock(&adap->lock); err = __cec_s_log_addrs(adap, log_addrs, block); mutex_unlock(&adap->lock); return err; } EXPORT_SYMBOL_GPL(cec_s_log_addrs); /* High-level core CEC message handling */ /* Fill in the Report Features message */ static void cec_fill_msg_report_features(struct cec_adapter *adap, struct cec_msg *msg, unsigned int la_idx) { const struct cec_log_addrs *las = &adap->log_addrs; const u8 *features = las->features[la_idx]; bool op_is_dev_features = false; unsigned int idx; /* Report Features */ msg->msg[0] = (las->log_addr[la_idx] << 4) | 0x0f; msg->len = 4; msg->msg[1] = CEC_MSG_REPORT_FEATURES; msg->msg[2] = adap->log_addrs.cec_version; msg->msg[3] = las->all_device_types[la_idx]; /* Write RC Profiles first, then Device Features */ for (idx = 0; idx < ARRAY_SIZE(las->features[0]); idx++) { msg->msg[msg->len++] = features[idx]; if ((features[idx] & CEC_OP_FEAT_EXT) == 0) { if (op_is_dev_features) break; op_is_dev_features = true; } } } /* Transmit the Feature Abort message */ static int cec_feature_abort_reason(struct cec_adapter *adap, struct cec_msg *msg, u8 reason) { struct cec_msg tx_msg = { }; /* * Don't reply with CEC_MSG_FEATURE_ABORT to a CEC_MSG_FEATURE_ABORT * message! */ if (msg->msg[1] == CEC_MSG_FEATURE_ABORT) return 0; /* Don't Feature Abort messages from 'Unregistered' */ if (cec_msg_initiator(msg) == CEC_LOG_ADDR_UNREGISTERED) return 0; cec_msg_set_reply_to(&tx_msg, msg); cec_msg_feature_abort(&tx_msg, msg->msg[1], reason); return cec_transmit_msg(adap, &tx_msg, false); } static int cec_feature_abort(struct cec_adapter *adap, struct cec_msg *msg) { return cec_feature_abort_reason(adap, msg, CEC_OP_ABORT_UNRECOGNIZED_OP); } static int cec_feature_refused(struct cec_adapter *adap, struct cec_msg *msg) { return cec_feature_abort_reason(adap, msg, CEC_OP_ABORT_REFUSED); } /* * Called when a CEC message is received. This function will do any * necessary core processing. The is_reply bool is true if this message * is a reply to an earlier transmit. * * The message is either a broadcast message or a valid directed message. */ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg, bool is_reply) { bool is_broadcast = cec_msg_is_broadcast(msg); u8 dest_laddr = cec_msg_destination(msg); u8 init_laddr = cec_msg_initiator(msg); u8 devtype = cec_log_addr2dev(adap, dest_laddr); int la_idx = cec_log_addr2idx(adap, dest_laddr); bool from_unregistered = init_laddr == 0xf; struct cec_msg tx_cec_msg = { }; dprintk(2, "%s: %*ph\n", __func__, msg->len, msg->msg); /* If this is a CDC-Only device, then ignore any non-CDC messages */ if (cec_is_cdc_only(&adap->log_addrs) && msg->msg[1] != CEC_MSG_CDC_MESSAGE) return 0; /* Allow drivers to process the message first */ if (adap->ops->received && !adap->devnode.unregistered && adap->ops->received(adap, msg) != -ENOMSG) return 0; /* * REPORT_PHYSICAL_ADDR, CEC_MSG_USER_CONTROL_PRESSED and * CEC_MSG_USER_CONTROL_RELEASED messages always have to be * handled by the CEC core, even if the passthrough mode is on. * The others are just ignored if passthrough mode is on. */ switch (msg->msg[1]) { case CEC_MSG_GET_CEC_VERSION: case CEC_MSG_ABORT: case CEC_MSG_GIVE_DEVICE_POWER_STATUS: case CEC_MSG_GIVE_OSD_NAME: /* * These messages reply with a directed message, so ignore if * the initiator is Unregistered. */ if (!adap->passthrough && from_unregistered) return 0; fallthrough; case CEC_MSG_GIVE_DEVICE_VENDOR_ID: case CEC_MSG_GIVE_FEATURES: case CEC_MSG_GIVE_PHYSICAL_ADDR: /* * Skip processing these messages if the passthrough mode * is on. */ if (adap->passthrough) goto skip_processing; /* Ignore if addressing is wrong */ if (is_broadcast) return 0; break; case CEC_MSG_USER_CONTROL_PRESSED: case CEC_MSG_USER_CONTROL_RELEASED: /* Wrong addressing mode: don't process */ if (is_broadcast || from_unregistered) goto skip_processing; break; case CEC_MSG_REPORT_PHYSICAL_ADDR: /* * This message is always processed, regardless of the * passthrough setting. * * Exception: don't process if wrong addressing mode. */ if (!is_broadcast) goto skip_processing; break; default: break; } cec_msg_set_reply_to(&tx_cec_msg, msg); switch (msg->msg[1]) { /* The following messages are processed but still passed through */ case CEC_MSG_REPORT_PHYSICAL_ADDR: { u16 pa = (msg->msg[2] << 8) | msg->msg[3]; dprintk(1, "reported physical address %x.%x.%x.%x for logical address %d\n", cec_phys_addr_exp(pa), init_laddr); break; } case CEC_MSG_USER_CONTROL_PRESSED: if (!(adap->capabilities & CEC_CAP_RC) || !(adap->log_addrs.flags & CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU)) break; #ifdef CONFIG_MEDIA_CEC_RC switch (msg->msg[2]) { /* * Play function, this message can have variable length * depending on the specific play function that is used. */ case CEC_OP_UI_CMD_PLAY_FUNCTION: if (msg->len == 2) rc_keydown(adap->rc, RC_PROTO_CEC, msg->msg[2], 0); else rc_keydown(adap->rc, RC_PROTO_CEC, msg->msg[2] << 8 | msg->msg[3], 0); break; /* * Other function messages that are not handled. * Currently the RC framework does not allow to supply an * additional parameter to a keypress. These "keys" contain * other information such as channel number, an input number * etc. * For the time being these messages are not processed by the * framework and are simply forwarded to the user space. */ case CEC_OP_UI_CMD_SELECT_BROADCAST_TYPE: case CEC_OP_UI_CMD_SELECT_SOUND_PRESENTATION: case CEC_OP_UI_CMD_TUNE_FUNCTION: case CEC_OP_UI_CMD_SELECT_MEDIA_FUNCTION: case CEC_OP_UI_CMD_SELECT_AV_INPUT_FUNCTION: case CEC_OP_UI_CMD_SELECT_AUDIO_INPUT_FUNCTION: break; default: rc_keydown(adap->rc, RC_PROTO_CEC, msg->msg[2], 0); break; } #endif break; case CEC_MSG_USER_CONTROL_RELEASED: if (!(adap->capabilities & CEC_CAP_RC) || !(adap->log_addrs.flags & CEC_LOG_ADDRS_FL_ALLOW_RC_PASSTHRU)) break; #ifdef CONFIG_MEDIA_CEC_RC rc_keyup(adap->rc); #endif break; /* * The remaining messages are only processed if the passthrough mode * is off. */ case CEC_MSG_GET_CEC_VERSION: cec_msg_cec_version(&tx_cec_msg, adap->log_addrs.cec_version); return cec_transmit_msg(adap, &tx_cec_msg, false); case CEC_MSG_GIVE_PHYSICAL_ADDR: /* Do nothing for CEC switches using addr 15 */ if (devtype == CEC_OP_PRIM_DEVTYPE_SWITCH && dest_laddr == 15) return 0; cec_msg_report_physical_addr(&tx_cec_msg, adap->phys_addr, devtype); return cec_transmit_msg(adap, &tx_cec_msg, false); case CEC_MSG_GIVE_DEVICE_VENDOR_ID: if (adap->log_addrs.vendor_id == CEC_VENDOR_ID_NONE) return cec_feature_abort(adap, msg); cec_msg_device_vendor_id(&tx_cec_msg, adap->log_addrs.vendor_id); return cec_transmit_msg(adap, &tx_cec_msg, false); case CEC_MSG_ABORT: /* Do nothing for CEC switches */ if (devtype == CEC_OP_PRIM_DEVTYPE_SWITCH) return 0; return cec_feature_refused(adap, msg); case CEC_MSG_GIVE_OSD_NAME: { if (adap->log_addrs.osd_name[0] == 0) return cec_feature_abort(adap, msg); cec_msg_set_osd_name(&tx_cec_msg, adap->log_addrs.osd_name); return cec_transmit_msg(adap, &tx_cec_msg, false); } case CEC_MSG_GIVE_FEATURES: if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0) return cec_feature_abort(adap, msg); cec_fill_msg_report_features(adap, &tx_cec_msg, la_idx); return cec_transmit_msg(adap, &tx_cec_msg, false); default: /* * Unprocessed messages are aborted if userspace isn't doing * any processing either. */ if (!is_broadcast && !is_reply && !adap->follower_cnt && !adap->cec_follower && msg->msg[1] != CEC_MSG_FEATURE_ABORT) return cec_feature_abort(adap, msg); break; } skip_processing: /* If this was a reply, then we're done, unless otherwise specified */ if (is_reply && !(msg->flags & CEC_MSG_FL_REPLY_TO_FOLLOWERS)) return 0; /* * Send to the exclusive follower if there is one, otherwise send * to all followers. */ if (adap->cec_follower) cec_queue_msg_fh(adap->cec_follower, msg); else cec_queue_msg_followers(adap, msg); return 0; } /* * Helper functions to keep track of the 'monitor all' use count. * * These functions are called with adap->lock held. */ int cec_monitor_all_cnt_inc(struct cec_adapter *adap) { int ret; if (adap->monitor_all_cnt++) return 0; ret = cec_adap_enable(adap); if (ret) adap->monitor_all_cnt--; return ret; } void cec_monitor_all_cnt_dec(struct cec_adapter *adap) { if (WARN_ON(!adap->monitor_all_cnt)) return; if (--adap->monitor_all_cnt) return; WARN_ON(call_op(adap, adap_monitor_all_enable, false)); cec_adap_enable(adap); } /* * Helper functions to keep track of the 'monitor pin' use count. * * These functions are called with adap->lock held. */ int cec_monitor_pin_cnt_inc(struct cec_adapter *adap) { int ret; if (adap->monitor_pin_cnt++) return 0; ret = cec_adap_enable(adap); if (ret) adap->monitor_pin_cnt--; return ret; } void cec_monitor_pin_cnt_dec(struct cec_adapter *adap) { if (WARN_ON(!adap->monitor_pin_cnt)) return; if (--adap->monitor_pin_cnt) return; WARN_ON(call_op(adap, adap_monitor_pin_enable, false)); cec_adap_enable(adap); } #ifdef CONFIG_DEBUG_FS /* * Log the current state of the CEC adapter. * Very useful for debugging. */ int cec_adap_status(struct seq_file *file, void *priv) { struct cec_adapter *adap = dev_get_drvdata(file->private); struct cec_data *data; mutex_lock(&adap->lock); seq_printf(file, "enabled: %d\n", adap->is_enabled); seq_printf(file, "configured: %d\n", adap->is_configured); seq_printf(file, "configuring: %d\n", adap->is_configuring); seq_printf(file, "phys_addr: %x.%x.%x.%x\n", cec_phys_addr_exp(adap->phys_addr)); seq_printf(file, "number of LAs: %d\n", adap->log_addrs.num_log_addrs); seq_printf(file, "LA mask: 0x%04x\n", adap->log_addrs.log_addr_mask); if (adap->cec_follower) seq_printf(file, "has CEC follower%s\n", adap->passthrough ? " (in passthrough mode)" : ""); if (adap->cec_initiator) seq_puts(file, "has CEC initiator\n"); if (adap->monitor_all_cnt) seq_printf(file, "file handles in Monitor All mode: %u\n", adap->monitor_all_cnt); if (adap->monitor_pin_cnt) seq_printf(file, "file handles in Monitor Pin mode: %u\n", adap->monitor_pin_cnt); if (adap->tx_timeout_cnt) { seq_printf(file, "transmit timeout count: %u\n", adap->tx_timeout_cnt); adap->tx_timeout_cnt = 0; } if (adap->tx_low_drive_cnt) { seq_printf(file, "transmit low drive count: %u\n", adap->tx_low_drive_cnt); adap->tx_low_drive_cnt = 0; } if (adap->tx_arb_lost_cnt) { seq_printf(file, "transmit arbitration lost count: %u\n", adap->tx_arb_lost_cnt); adap->tx_arb_lost_cnt = 0; } if (adap->tx_error_cnt) { seq_printf(file, "transmit error count: %u\n", adap->tx_error_cnt); adap->tx_error_cnt = 0; } data = adap->transmitting; if (data) seq_printf(file, "transmitting message: %*ph (reply: %*ph, timeout: %ums)\n", data->msg.len, data->msg.msg, data->match_len, data->match_reply, data->msg.timeout); seq_printf(file, "pending transmits: %u\n", adap->transmit_queue_sz); list_for_each_entry(data, &adap->transmit_queue, list) { seq_printf(file, "queued tx message: %*ph (reply: %*ph, timeout: %ums)\n", data->msg.len, data->msg.msg, data->match_len, data->match_reply, data->msg.timeout); } list_for_each_entry(data, &adap->wait_queue, list) { seq_printf(file, "message waiting for reply: %*ph (reply: %*ph, timeout: %ums)\n", data->msg.len, data->msg.msg, data->match_len, data->match_reply, data->msg.timeout); } call_void_op(adap, adap_status, file); mutex_unlock(&adap->lock); return 0; } #endif |
| 1 1 5 5 4 1 1 2 2 2 2 2 2 2 2 2 5 1 4 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, Intel Corporation. * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> struct multiq_sched_data { u16 bands; u16 max_bands; u16 curband; struct tcf_proto __rcu *filter_list; struct tcf_block *block; struct Qdisc **queues; }; static struct Qdisc * multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) { struct multiq_sched_data *q = qdisc_priv(sch); u32 band; struct tcf_result res; struct tcf_proto *fl = rcu_dereference_bh(q->filter_list); int err; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; err = tcf_classify(skb, NULL, fl, &res, false); #ifdef CONFIG_NET_CLS_ACT switch (err) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; case TC_ACT_SHOT: return NULL; } #endif band = skb_get_queue_mapping(skb); if (band >= q->bands) return q->queues[0]; return q->queues[band]; } static int multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct Qdisc *qdisc; int ret; qdisc = multiq_classify(skb, sch, &ret); #ifdef CONFIG_NET_CLS_ACT if (qdisc == NULL) { if (ret & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return ret; } #endif ret = qdisc_enqueue(skb, qdisc, to_free); if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; return NET_XMIT_SUCCESS; } if (net_xmit_drop_count(ret)) qdisc_qstats_drop(sch); return ret; } static struct sk_buff *multiq_dequeue(struct Qdisc *sch) { struct multiq_sched_data *q = qdisc_priv(sch); struct Qdisc *qdisc; struct sk_buff *skb; int band; for (band = 0; band < q->bands; band++) { /* cycle through bands to ensure fairness */ q->curband++; if (q->curband >= q->bands) q->curband = 0; /* Check that target subqueue is available before * pulling an skb to avoid head-of-line blocking. */ if (!netif_xmit_stopped( netdev_get_tx_queue(qdisc_dev(sch), q->curband))) { qdisc = q->queues[q->curband]; skb = qdisc->dequeue(qdisc); if (skb) { qdisc_bstats_update(sch, skb); sch->q.qlen--; return skb; } } } return NULL; } static struct sk_buff *multiq_peek(struct Qdisc *sch) { struct multiq_sched_data *q = qdisc_priv(sch); unsigned int curband = q->curband; struct Qdisc *qdisc; struct sk_buff *skb; int band; for (band = 0; band < q->bands; band++) { /* cycle through bands to ensure fairness */ curband++; if (curband >= q->bands) curband = 0; /* Check that target subqueue is available before * pulling an skb to avoid head-of-line blocking. */ if (!netif_xmit_stopped( netdev_get_tx_queue(qdisc_dev(sch), curband))) { qdisc = q->queues[curband]; skb = qdisc->ops->peek(qdisc); if (skb) return skb; } } return NULL; } static void multiq_reset(struct Qdisc *sch) { u16 band; struct multiq_sched_data *q = qdisc_priv(sch); for (band = 0; band < q->bands; band++) qdisc_reset(q->queues[band]); q->curband = 0; } static void multiq_destroy(struct Qdisc *sch) { int band; struct multiq_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); for (band = 0; band < q->bands; band++) qdisc_put(q->queues[band]); kfree(q->queues); } static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); struct tc_multiq_qopt *qopt; struct Qdisc **removed; int i, n_removed = 0; if (!netif_is_multiqueue(qdisc_dev(sch))) return -EOPNOTSUPP; if (nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); qopt->bands = qdisc_dev(sch)->real_num_tx_queues; removed = kmalloc(sizeof(*removed) * (q->max_bands - qopt->bands), GFP_KERNEL); if (!removed) return -ENOMEM; sch_tree_lock(sch); q->bands = qopt->bands; for (i = q->bands; i < q->max_bands; i++) { if (q->queues[i] != &noop_qdisc) { struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; qdisc_purge_queue(child); removed[n_removed++] = child; } } sch_tree_unlock(sch); for (i = 0; i < n_removed; i++) qdisc_put(removed[i]); kfree(removed); for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, i + 1), extack); if (child) { sch_tree_lock(sch); old = q->queues[i]; q->queues[i] = child; if (child != &noop_qdisc) qdisc_hash_add(child, true); if (old != &noop_qdisc) qdisc_purge_queue(old); sch_tree_unlock(sch); qdisc_put(old); } } } return 0; } static int multiq_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); int i, err; q->queues = NULL; if (!opt) return -EINVAL; err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; q->max_bands = qdisc_dev(sch)->num_tx_queues; q->queues = kcalloc(q->max_bands, sizeof(struct Qdisc *), GFP_KERNEL); if (!q->queues) return -ENOBUFS; for (i = 0; i < q->max_bands; i++) q->queues[i] = &noop_qdisc; return multiq_tune(sch, opt, extack); } static int multiq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct multiq_sched_data *q = qdisc_priv(sch); unsigned char *b = skb_tail_pointer(skb); struct tc_multiq_qopt opt; opt.bands = q->bands; opt.max_bands = q->max_bands; if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; return skb->len; nla_put_failure: nlmsg_trim(skb, b); return -1; } static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; if (new == NULL) new = &noop_qdisc; *old = qdisc_replace(sch, new, &q->queues[band]); return 0; } static struct Qdisc * multiq_leaf(struct Qdisc *sch, unsigned long arg) { struct multiq_sched_data *q = qdisc_priv(sch); unsigned long band = arg - 1; return q->queues[band]; } static unsigned long multiq_find(struct Qdisc *sch, u32 classid) { struct multiq_sched_data *q = qdisc_priv(sch); unsigned long band = TC_H_MIN(classid); if (band - 1 >= q->bands) return 0; return band; } static unsigned long multiq_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { return multiq_find(sch, classid); } static void multiq_unbind(struct Qdisc *q, unsigned long cl) { } static int multiq_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct multiq_sched_data *q = qdisc_priv(sch); tcm->tcm_handle |= TC_H_MIN(cl); tcm->tcm_info = q->queues[cl - 1]->handle; return 0; } static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct multiq_sched_data *q = qdisc_priv(sch); struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; return 0; } static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct multiq_sched_data *q = qdisc_priv(sch); int band; if (arg->stop) return; for (band = 0; band < q->bands; band++) { if (!tc_qdisc_stats_dump(sch, band + 1, arg)) break; } } static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl, struct netlink_ext_ack *extack) { struct multiq_sched_data *q = qdisc_priv(sch); if (cl) return NULL; return q->block; } static const struct Qdisc_class_ops multiq_class_ops = { .graft = multiq_graft, .leaf = multiq_leaf, .find = multiq_find, .walk = multiq_walk, .tcf_block = multiq_tcf_block, .bind_tcf = multiq_bind, .unbind_tcf = multiq_unbind, .dump = multiq_dump_class, .dump_stats = multiq_dump_class_stats, }; static struct Qdisc_ops multiq_qdisc_ops __read_mostly = { .next = NULL, .cl_ops = &multiq_class_ops, .id = "multiq", .priv_size = sizeof(struct multiq_sched_data), .enqueue = multiq_enqueue, .dequeue = multiq_dequeue, .peek = multiq_peek, .init = multiq_init, .reset = multiq_reset, .destroy = multiq_destroy, .change = multiq_tune, .dump = multiq_dump, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("multiq"); static int __init multiq_module_init(void) { return register_qdisc(&multiq_qdisc_ops); } static void __exit multiq_module_exit(void) { unregister_qdisc(&multiq_qdisc_ops); } module_init(multiq_module_init) module_exit(multiq_module_exit) MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Multi queue to hardware queue mapping qdisc"); |
| 309 38 489 4 440 976 977 1183 1167 28 1186 1187 1169 28 1055 447 1171 18 29 13 13 463 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/inotify_user.c - inotify support for userspace * * Authors: * John McCutchan <ttb@tentacle.dhs.org> * Robert Love <rml@novell.com> * * Copyright (C) 2005 John McCutchan * Copyright 2006 Hewlett-Packard Development Company, L.P. * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * inotify was largely rewriten to make use of the fsnotify infrastructure */ #include <linux/dcache.h> /* d_unlinked */ #include <linux/fs.h> /* struct inode */ #include <linux/fsnotify_backend.h> #include <linux/inotify.h> #include <linux/path.h> /* struct path */ #include <linux/slab.h> /* kmem_* */ #include <linux/types.h> #include <linux/sched.h> #include <linux/sched/user.h> #include <linux/sched/mm.h> #include "inotify.h" /* * Check if 2 events contain the same information. */ static bool event_compare(struct fsnotify_event *old_fsn, struct fsnotify_event *new_fsn) { struct inotify_event_info *old, *new; old = INOTIFY_E(old_fsn); new = INOTIFY_E(new_fsn); if (old->mask & FS_IN_IGNORED) return false; if ((old->mask == new->mask) && (old->wd == new->wd) && (old->name_len == new->name_len) && (!old->name_len || !strcmp(old->name, new->name))) return true; return false; } static int inotify_merge(struct fsnotify_group *group, struct fsnotify_event *event) { struct list_head *list = &group->notification_list; struct fsnotify_event *last_event; last_event = list_entry(list->prev, struct fsnotify_event, list); return event_compare(last_event, event); } int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct inotify_inode_mark *i_mark; struct inotify_event_info *event; struct fsnotify_event *fsn_event; struct fsnotify_group *group = inode_mark->group; int ret; int len = 0, wd; int alloc_len = sizeof(struct inotify_event_info); struct mem_cgroup *old_memcg; if (name) { len = name->len; alloc_len += len + 1; } pr_debug("%s: group=%p mark=%p mask=%x\n", __func__, group, inode_mark, mask); i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); /* * We can be racing with mark being detached. Don't report event with * invalid wd. */ wd = READ_ONCE(i_mark->wd); if (wd == -1) return 0; /* * Whoever is interested in the event, pays for the allocation. Do not * trigger OOM killer in the target monitoring memcg as it may have * security repercussion. */ old_memcg = set_active_memcg(group->memcg); event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); set_active_memcg(old_memcg); if (unlikely(!event)) { /* * Treat lost event due to ENOMEM the same way as queue * overflow to let userspace know event was lost. */ fsnotify_queue_overflow(group); return -ENOMEM; } /* * We now report FS_ISDIR flag with MOVE_SELF and DELETE_SELF events * for fanotify. inotify never reported IN_ISDIR with those events. * It looks like an oversight, but to avoid the risk of breaking * existing inotify programs, mask the flag out from those events. */ if (mask & (IN_MOVE_SELF | IN_DELETE_SELF)) mask &= ~IN_ISDIR; fsn_event = &event->fse; fsnotify_init_event(fsn_event); event->mask = mask; event->wd = wd; event->sync_cookie = cookie; event->name_len = len; if (len) strcpy(event->name, name->name); ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { /* Our event wasn't used in the end. Free it. */ fsnotify_destroy_event(group, fsn_event); } if (inode_mark->flags & FSNOTIFY_MARK_FLAG_IN_ONESHOT) fsnotify_destroy_mark(inode_mark, group); return 0; } static void inotify_freeing_mark(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group) { inotify_ignored_and_remove_idr(fsn_mark, group); } /* * This is NEVER supposed to be called. Inotify marks should either have been * removed from the idr when the watch was removed or in the * fsnotify_destroy_mark_by_group() call when the inotify instance was being * torn down. This is only called if the idr is about to be freed but there * are still marks in it. */ static int idr_callback(int id, void *p, void *data) { struct fsnotify_mark *fsn_mark; struct inotify_inode_mark *i_mark; static bool warned = false; if (warned) return 0; warned = true; fsn_mark = p; i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); WARN(1, "inotify closing but id=%d for fsn_mark=%p in group=%p still in " "idr. Probably leaking memory\n", id, p, data); /* * I'm taking the liberty of assuming that the mark in question is a * valid address and I'm dereferencing it. This might help to figure * out why we got here and the panic is no worse than the original * BUG() that was here. */ if (fsn_mark) printk(KERN_WARNING "fsn_mark->group=%p wd=%d\n", fsn_mark->group, i_mark->wd); return 0; } static void inotify_free_group_priv(struct fsnotify_group *group) { /* ideally the idr is empty and we won't hit the BUG in the callback */ idr_for_each(&group->inotify_data.idr, idr_callback, group); idr_destroy(&group->inotify_data.idr); if (group->inotify_data.ucounts) dec_inotify_instances(group->inotify_data.ucounts); } static void inotify_free_event(struct fsnotify_group *group, struct fsnotify_event *fsn_event) { kfree(INOTIFY_E(fsn_event)); } /* ding dong the mark is dead */ static void inotify_free_mark(struct fsnotify_mark *fsn_mark) { struct inotify_inode_mark *i_mark; i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); kmem_cache_free(inotify_inode_mark_cachep, i_mark); } const struct fsnotify_ops inotify_fsnotify_ops = { .handle_inode_event = inotify_handle_inode_event, .free_group_priv = inotify_free_group_priv, .free_event = inotify_free_event, .freeing_mark = inotify_freeing_mark, .free_mark = inotify_free_mark, }; |
| 23 3 21 43 8 1 1 6 1 6 1 9 2 7 5 4 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* user_defined.c: user defined key type * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/err.h> #include <keys/user-type.h> #include <linux/uaccess.h> #include "internal.h" static int logon_vet_description(const char *desc); /* * user defined keys take an arbitrary string as the description and an * arbitrary blob of data as the payload */ struct key_type key_type_user = { .name = "user", .preparse = user_preparse, .free_preparse = user_free_preparse, .instantiate = generic_key_instantiate, .update = user_update, .revoke = user_revoke, .destroy = user_destroy, .describe = user_describe, .read = user_read, }; EXPORT_SYMBOL_GPL(key_type_user); /* * This key type is essentially the same as key_type_user, but it does * not define a .read op. This is suitable for storing username and * password pairs in the keyring that you do not want to be readable * from userspace. */ struct key_type key_type_logon = { .name = "logon", .preparse = user_preparse, .free_preparse = user_free_preparse, .instantiate = generic_key_instantiate, .update = user_update, .revoke = user_revoke, .destroy = user_destroy, .describe = user_describe, .vet_description = logon_vet_description, }; EXPORT_SYMBOL_GPL(key_type_logon); /* * Preparse a user defined key payload */ int user_preparse(struct key_preparsed_payload *prep) { struct user_key_payload *upayload; size_t datalen = prep->datalen; if (datalen <= 0 || datalen > 32767 || !prep->data) return -EINVAL; upayload = kmalloc(sizeof(*upayload) + datalen, GFP_KERNEL); if (!upayload) return -ENOMEM; /* attach the data */ prep->quotalen = datalen; prep->payload.data[0] = upayload; upayload->datalen = datalen; memcpy(upayload->data, prep->data, datalen); return 0; } EXPORT_SYMBOL_GPL(user_preparse); /* * Free a preparse of a user defined key payload */ void user_free_preparse(struct key_preparsed_payload *prep) { kfree_sensitive(prep->payload.data[0]); } EXPORT_SYMBOL_GPL(user_free_preparse); static void user_free_payload_rcu(struct rcu_head *head) { struct user_key_payload *payload; payload = container_of(head, struct user_key_payload, rcu); kfree_sensitive(payload); } /* * update a user defined key * - the key's semaphore is write-locked */ int user_update(struct key *key, struct key_preparsed_payload *prep) { struct user_key_payload *zap = NULL; int ret; /* check the quota and attach the new data */ ret = key_payload_reserve(key, prep->datalen); if (ret < 0) return ret; /* attach the new data, displacing the old */ key->expiry = prep->expiry; if (key_is_positive(key)) zap = dereference_key_locked(key); rcu_assign_keypointer(key, prep->payload.data[0]); prep->payload.data[0] = NULL; if (zap) call_rcu(&zap->rcu, user_free_payload_rcu); return ret; } EXPORT_SYMBOL_GPL(user_update); /* * dispose of the links from a revoked keyring * - called with the key sem write-locked */ void user_revoke(struct key *key) { struct user_key_payload *upayload = user_key_payload_locked(key); /* clear the quota */ key_payload_reserve(key, 0); if (upayload) { rcu_assign_keypointer(key, NULL); call_rcu(&upayload->rcu, user_free_payload_rcu); } } EXPORT_SYMBOL(user_revoke); /* * dispose of the data dangling from the corpse of a user key */ void user_destroy(struct key *key) { struct user_key_payload *upayload = key->payload.data[0]; kfree_sensitive(upayload); } EXPORT_SYMBOL_GPL(user_destroy); /* * describe the user key */ void user_describe(const struct key *key, struct seq_file *m) { seq_puts(m, key->description); if (key_is_positive(key)) seq_printf(m, ": %u", key->datalen); } EXPORT_SYMBOL_GPL(user_describe); /* * read the key data * - the key's semaphore is read-locked */ long user_read(const struct key *key, char *buffer, size_t buflen) { const struct user_key_payload *upayload; long ret; upayload = user_key_payload_locked(key); ret = upayload->datalen; /* we can return the data as is */ if (buffer && buflen > 0) { if (buflen > upayload->datalen) buflen = upayload->datalen; memcpy(buffer, upayload->data, buflen); } return ret; } EXPORT_SYMBOL_GPL(user_read); /* Vet the description for a "logon" key */ static int logon_vet_description(const char *desc) { char *p; /* require a "qualified" description string */ p = strchr(desc, ':'); if (!p) return -EINVAL; /* also reject description with ':' as first char */ if (p == desc) return -EINVAL; return 0; } |
| 195 838 118 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RANDOM_H #define _LINUX_RANDOM_H #include <linux/bug.h> #include <linux/kernel.h> #include <linux/list.h> #include <uapi/linux/random.h> struct notifier_block; void add_device_randomness(const void *buf, size_t len); void __init add_bootloader_randomness(const void *buf, size_t len); void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; void add_interrupt_randomness(int irq) __latent_entropy; void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after); static inline void add_latent_entropy(void) { #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); #else add_device_randomness(NULL, 0); #endif } #if IS_ENABLED(CONFIG_VMGENID) void add_vmfork_randomness(const void *unique_vm_id, size_t len); int register_random_vmfork_notifier(struct notifier_block *nb); int unregister_random_vmfork_notifier(struct notifier_block *nb); #else static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; } static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } #endif void get_random_bytes(void *buf, size_t len); u8 get_random_u8(void); u16 get_random_u16(void); u32 get_random_u32(void); u64 get_random_u64(void); static inline unsigned long get_random_long(void) { #if BITS_PER_LONG == 64 return get_random_u64(); #else return get_random_u32(); #endif } u32 __get_random_u32_below(u32 ceil); /* * Returns a random integer in the interval [0, ceil), with uniform * distribution, suitable for all uses. Fastest when ceil is a constant, but * still fast for variable ceil as well. */ static inline u32 get_random_u32_below(u32 ceil) { if (!__builtin_constant_p(ceil)) return __get_random_u32_below(ceil); /* * For the fast path, below, all operations on ceil are precomputed by * the compiler, so this incurs no overhead for checking pow2, doing * divisions, or branching based on integer size. The resultant * algorithm does traditional reciprocal multiplication (typically * optimized by the compiler into shifts and adds), rejecting samples * whose lower half would indicate a range indivisible by ceil. */ BUILD_BUG_ON_MSG(!ceil, "get_random_u32_below() must take ceil > 0"); if (ceil <= 1) return 0; for (;;) { if (ceil <= 1U << 8) { u32 mult = ceil * get_random_u8(); if (likely(is_power_of_2(ceil) || (u8)mult >= (1U << 8) % ceil)) return mult >> 8; } else if (ceil <= 1U << 16) { u32 mult = ceil * get_random_u16(); if (likely(is_power_of_2(ceil) || (u16)mult >= (1U << 16) % ceil)) return mult >> 16; } else { u64 mult = (u64)ceil * get_random_u32(); if (likely(is_power_of_2(ceil) || (u32)mult >= -ceil % ceil)) return mult >> 32; } } } /* * Returns a random integer in the interval (floor, U32_MAX], with uniform * distribution, suitable for all uses. Fastest when floor is a constant, but * still fast for variable floor as well. */ static inline u32 get_random_u32_above(u32 floor) { BUILD_BUG_ON_MSG(__builtin_constant_p(floor) && floor == U32_MAX, "get_random_u32_above() must take floor < U32_MAX"); return floor + 1 + get_random_u32_below(U32_MAX - floor); } /* * Returns a random integer in the interval [floor, ceil], with uniform * distribution, suitable for all uses. Fastest when floor and ceil are * constant, but still fast for variable floor and ceil as well. */ static inline u32 get_random_u32_inclusive(u32 floor, u32 ceil) { BUILD_BUG_ON_MSG(__builtin_constant_p(floor) && __builtin_constant_p(ceil) && (floor > ceil || ceil - floor == U32_MAX), "get_random_u32_inclusive() must take floor <= ceil"); return floor + get_random_u32_below(ceil - floor + 1); } void __init random_init_early(const char *command_line); void __init random_init(void); bool rng_is_initialized(void); int wait_for_random_bytes(void); int execute_with_initialized_rng(struct notifier_block *nb); /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ static inline int get_random_bytes_wait(void *buf, size_t nbytes) { int ret = wait_for_random_bytes(); get_random_bytes(buf, nbytes); return ret; } #define declare_get_random_var_wait(name, ret_type) \ static inline int get_random_ ## name ## _wait(ret_type *out) { \ int ret = wait_for_random_bytes(); \ if (unlikely(ret)) \ return ret; \ *out = get_random_ ## name(); \ return 0; \ } declare_get_random_var_wait(u8, u8) declare_get_random_var_wait(u16, u16) declare_get_random_var_wait(u32, u32) declare_get_random_var_wait(u64, u32) declare_get_random_var_wait(long, unsigned long) #undef declare_get_random_var /* * This is designed to be standalone for just prandom * users, but for now we include it from <linux/random.h> * for legacy reasons. */ #include <linux/prandom.h> #ifdef CONFIG_SMP int random_prepare_cpu(unsigned int cpu); int random_online_cpu(unsigned int cpu); #endif #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; #endif #endif /* _LINUX_RANDOM_H */ |
| 192 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM scsi #if !defined(_TRACE_SCSI_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SCSI_H #include <scsi/scsi_cmnd.h> #include <scsi/scsi_host.h> #include <linux/tracepoint.h> #include <linux/trace_seq.h> #define scsi_opcode_name(opcode) { opcode, #opcode } #define show_opcode_name(val) \ __print_symbolic(val, \ scsi_opcode_name(TEST_UNIT_READY), \ scsi_opcode_name(REZERO_UNIT), \ scsi_opcode_name(REQUEST_SENSE), \ scsi_opcode_name(FORMAT_UNIT), \ scsi_opcode_name(READ_BLOCK_LIMITS), \ scsi_opcode_name(REASSIGN_BLOCKS), \ scsi_opcode_name(INITIALIZE_ELEMENT_STATUS), \ scsi_opcode_name(READ_6), \ scsi_opcode_name(WRITE_6), \ scsi_opcode_name(SEEK_6), \ scsi_opcode_name(READ_REVERSE), \ scsi_opcode_name(WRITE_FILEMARKS), \ scsi_opcode_name(SPACE), \ scsi_opcode_name(INQUIRY), \ scsi_opcode_name(RECOVER_BUFFERED_DATA), \ scsi_opcode_name(MODE_SELECT), \ scsi_opcode_name(RESERVE), \ scsi_opcode_name(RELEASE), \ scsi_opcode_name(COPY), \ scsi_opcode_name(ERASE), \ scsi_opcode_name(MODE_SENSE), \ scsi_opcode_name(START_STOP), \ scsi_opcode_name(RECEIVE_DIAGNOSTIC), \ scsi_opcode_name(SEND_DIAGNOSTIC), \ scsi_opcode_name(ALLOW_MEDIUM_REMOVAL), \ scsi_opcode_name(SET_WINDOW), \ scsi_opcode_name(READ_CAPACITY), \ scsi_opcode_name(READ_10), \ scsi_opcode_name(WRITE_10), \ scsi_opcode_name(SEEK_10), \ scsi_opcode_name(POSITION_TO_ELEMENT), \ scsi_opcode_name(WRITE_VERIFY), \ scsi_opcode_name(VERIFY), \ scsi_opcode_name(SEARCH_HIGH), \ scsi_opcode_name(SEARCH_EQUAL), \ scsi_opcode_name(SEARCH_LOW), \ scsi_opcode_name(SET_LIMITS), \ scsi_opcode_name(PRE_FETCH), \ scsi_opcode_name(READ_POSITION), \ scsi_opcode_name(SYNCHRONIZE_CACHE), \ scsi_opcode_name(LOCK_UNLOCK_CACHE), \ scsi_opcode_name(READ_DEFECT_DATA), \ scsi_opcode_name(MEDIUM_SCAN), \ scsi_opcode_name(COMPARE), \ scsi_opcode_name(COPY_VERIFY), \ scsi_opcode_name(WRITE_BUFFER), \ scsi_opcode_name(READ_BUFFER), \ scsi_opcode_name(UPDATE_BLOCK), \ scsi_opcode_name(READ_LONG), \ scsi_opcode_name(WRITE_LONG), \ scsi_opcode_name(CHANGE_DEFINITION), \ scsi_opcode_name(WRITE_SAME), \ scsi_opcode_name(UNMAP), \ scsi_opcode_name(READ_TOC), \ scsi_opcode_name(LOG_SELECT), \ scsi_opcode_name(LOG_SENSE), \ scsi_opcode_name(XDWRITEREAD_10), \ scsi_opcode_name(MODE_SELECT_10), \ scsi_opcode_name(RESERVE_10), \ scsi_opcode_name(RELEASE_10), \ scsi_opcode_name(MODE_SENSE_10), \ scsi_opcode_name(PERSISTENT_RESERVE_IN), \ scsi_opcode_name(PERSISTENT_RESERVE_OUT), \ scsi_opcode_name(VARIABLE_LENGTH_CMD), \ scsi_opcode_name(REPORT_LUNS), \ scsi_opcode_name(MAINTENANCE_IN), \ scsi_opcode_name(MAINTENANCE_OUT), \ scsi_opcode_name(MOVE_MEDIUM), \ scsi_opcode_name(EXCHANGE_MEDIUM), \ scsi_opcode_name(READ_12), \ scsi_opcode_name(WRITE_12), \ scsi_opcode_name(WRITE_VERIFY_12), \ scsi_opcode_name(SEARCH_HIGH_12), \ scsi_opcode_name(SEARCH_EQUAL_12), \ scsi_opcode_name(SEARCH_LOW_12), \ scsi_opcode_name(READ_ELEMENT_STATUS), \ scsi_opcode_name(SEND_VOLUME_TAG), \ scsi_opcode_name(WRITE_LONG_2), \ scsi_opcode_name(READ_16), \ scsi_opcode_name(WRITE_16), \ scsi_opcode_name(VERIFY_16), \ scsi_opcode_name(WRITE_SAME_16), \ scsi_opcode_name(ZBC_OUT), \ scsi_opcode_name(ZBC_IN), \ scsi_opcode_name(SERVICE_ACTION_IN_16), \ scsi_opcode_name(READ_32), \ scsi_opcode_name(WRITE_32), \ scsi_opcode_name(WRITE_SAME_32), \ scsi_opcode_name(ATA_16), \ scsi_opcode_name(WRITE_ATOMIC_16), \ scsi_opcode_name(ATA_12)) #define scsi_hostbyte_name(result) { result, #result } #define show_hostbyte_name(val) \ __print_symbolic(val, \ scsi_hostbyte_name(DID_OK), \ scsi_hostbyte_name(DID_NO_CONNECT), \ scsi_hostbyte_name(DID_BUS_BUSY), \ scsi_hostbyte_name(DID_TIME_OUT), \ scsi_hostbyte_name(DID_BAD_TARGET), \ scsi_hostbyte_name(DID_ABORT), \ scsi_hostbyte_name(DID_PARITY), \ scsi_hostbyte_name(DID_ERROR), \ scsi_hostbyte_name(DID_RESET), \ scsi_hostbyte_name(DID_BAD_INTR), \ scsi_hostbyte_name(DID_PASSTHROUGH), \ scsi_hostbyte_name(DID_SOFT_ERROR), \ scsi_hostbyte_name(DID_IMM_RETRY), \ scsi_hostbyte_name(DID_REQUEUE), \ scsi_hostbyte_name(DID_TRANSPORT_DISRUPTED), \ scsi_hostbyte_name(DID_TRANSPORT_FAILFAST)) #define scsi_statusbyte_name(result) { result, #result } #define show_statusbyte_name(val) \ __print_symbolic(val, \ scsi_statusbyte_name(SAM_STAT_GOOD), \ scsi_statusbyte_name(SAM_STAT_CHECK_CONDITION), \ scsi_statusbyte_name(SAM_STAT_CONDITION_MET), \ scsi_statusbyte_name(SAM_STAT_BUSY), \ scsi_statusbyte_name(SAM_STAT_INTERMEDIATE), \ scsi_statusbyte_name(SAM_STAT_INTERMEDIATE_CONDITION_MET), \ scsi_statusbyte_name(SAM_STAT_RESERVATION_CONFLICT), \ scsi_statusbyte_name(SAM_STAT_COMMAND_TERMINATED), \ scsi_statusbyte_name(SAM_STAT_TASK_SET_FULL), \ scsi_statusbyte_name(SAM_STAT_ACA_ACTIVE), \ scsi_statusbyte_name(SAM_STAT_TASK_ABORTED)) #define scsi_prot_op_name(result) { result, #result } #define show_prot_op_name(val) \ __print_symbolic(val, \ scsi_prot_op_name(SCSI_PROT_NORMAL), \ scsi_prot_op_name(SCSI_PROT_READ_INSERT), \ scsi_prot_op_name(SCSI_PROT_WRITE_STRIP), \ scsi_prot_op_name(SCSI_PROT_READ_STRIP), \ scsi_prot_op_name(SCSI_PROT_WRITE_INSERT), \ scsi_prot_op_name(SCSI_PROT_READ_PASS), \ scsi_prot_op_name(SCSI_PROT_WRITE_PASS)) const char *scsi_trace_parse_cdb(struct trace_seq*, unsigned char*, int); #define __parse_cdb(cdb, len) scsi_trace_parse_cdb(p, cdb, len) TRACE_EVENT(scsi_dispatch_cmd_start, TP_PROTO(struct scsi_cmnd *cmd), TP_ARGS(cmd), TP_STRUCT__entry( __field( unsigned int, host_no ) __field( unsigned int, channel ) __field( unsigned int, id ) __field( unsigned int, lun ) __field( unsigned int, opcode ) __field( unsigned int, cmd_len ) __field( int, driver_tag) __field( int, scheduler_tag) __field( unsigned int, data_sglen ) __field( unsigned int, prot_sglen ) __field( unsigned char, prot_op ) __dynamic_array(unsigned char, cmnd, cmd->cmd_len) ), TP_fast_assign( __entry->host_no = cmd->device->host->host_no; __entry->channel = cmd->device->channel; __entry->id = cmd->device->id; __entry->lun = cmd->device->lun; __entry->opcode = cmd->cmnd[0]; __entry->cmd_len = cmd->cmd_len; __entry->driver_tag = scsi_cmd_to_rq(cmd)->tag; __entry->scheduler_tag = scsi_cmd_to_rq(cmd)->internal_tag; __entry->data_sglen = scsi_sg_count(cmd); __entry->prot_sglen = scsi_prot_sg_count(cmd); __entry->prot_op = scsi_get_prot_op(cmd); memcpy(__get_dynamic_array(cmnd), cmd->cmnd, cmd->cmd_len); ), TP_printk("host_no=%u channel=%u id=%u lun=%u data_sgl=%u prot_sgl=%u" \ " prot_op=%s driver_tag=%d scheduler_tag=%d cmnd=(%s %s raw=%s)", __entry->host_no, __entry->channel, __entry->id, __entry->lun, __entry->data_sglen, __entry->prot_sglen, show_prot_op_name(__entry->prot_op), __entry->driver_tag, __entry->scheduler_tag, show_opcode_name(__entry->opcode), __parse_cdb(__get_dynamic_array(cmnd), __entry->cmd_len), __print_hex(__get_dynamic_array(cmnd), __entry->cmd_len)) ); TRACE_EVENT(scsi_dispatch_cmd_error, TP_PROTO(struct scsi_cmnd *cmd, int rtn), TP_ARGS(cmd, rtn), TP_STRUCT__entry( __field( unsigned int, host_no ) __field( unsigned int, channel ) __field( unsigned int, id ) __field( unsigned int, lun ) __field( int, rtn ) __field( unsigned int, opcode ) __field( unsigned int, cmd_len ) __field( int, driver_tag) __field( int, scheduler_tag) __field( unsigned int, data_sglen ) __field( unsigned int, prot_sglen ) __field( unsigned char, prot_op ) __dynamic_array(unsigned char, cmnd, cmd->cmd_len) ), TP_fast_assign( __entry->host_no = cmd->device->host->host_no; __entry->channel = cmd->device->channel; __entry->id = cmd->device->id; __entry->lun = cmd->device->lun; __entry->rtn = rtn; __entry->opcode = cmd->cmnd[0]; __entry->cmd_len = cmd->cmd_len; __entry->driver_tag = scsi_cmd_to_rq(cmd)->tag; __entry->scheduler_tag = scsi_cmd_to_rq(cmd)->internal_tag; __entry->data_sglen = scsi_sg_count(cmd); __entry->prot_sglen = scsi_prot_sg_count(cmd); __entry->prot_op = scsi_get_prot_op(cmd); memcpy(__get_dynamic_array(cmnd), cmd->cmnd, cmd->cmd_len); ), TP_printk("host_no=%u channel=%u id=%u lun=%u data_sgl=%u prot_sgl=%u" \ " prot_op=%s driver_tag=%d scheduler_tag=%d cmnd=(%s %s raw=%s)" \ " rtn=%d", __entry->host_no, __entry->channel, __entry->id, __entry->lun, __entry->data_sglen, __entry->prot_sglen, show_prot_op_name(__entry->prot_op), __entry->driver_tag, __entry->scheduler_tag, show_opcode_name(__entry->opcode), __parse_cdb(__get_dynamic_array(cmnd), __entry->cmd_len), __print_hex(__get_dynamic_array(cmnd), __entry->cmd_len), __entry->rtn) ); DECLARE_EVENT_CLASS(scsi_cmd_done_timeout_template, TP_PROTO(struct scsi_cmnd *cmd), TP_ARGS(cmd), TP_STRUCT__entry( __field( unsigned int, host_no ) __field( unsigned int, channel ) __field( unsigned int, id ) __field( unsigned int, lun ) __field( int, result ) __field( unsigned int, opcode ) __field( unsigned int, cmd_len ) __field( int, driver_tag) __field( int, scheduler_tag) __field( unsigned int, data_sglen ) __field( unsigned int, prot_sglen ) __field( unsigned char, prot_op ) __dynamic_array(unsigned char, cmnd, cmd->cmd_len) __field( u8, sense_key ) __field( u8, asc ) __field( u8, ascq ) ), TP_fast_assign( struct scsi_sense_hdr sshdr; __entry->host_no = cmd->device->host->host_no; __entry->channel = cmd->device->channel; __entry->id = cmd->device->id; __entry->lun = cmd->device->lun; __entry->result = cmd->result; __entry->opcode = cmd->cmnd[0]; __entry->cmd_len = cmd->cmd_len; __entry->driver_tag = scsi_cmd_to_rq(cmd)->tag; __entry->scheduler_tag = scsi_cmd_to_rq(cmd)->internal_tag; __entry->data_sglen = scsi_sg_count(cmd); __entry->prot_sglen = scsi_prot_sg_count(cmd); __entry->prot_op = scsi_get_prot_op(cmd); memcpy(__get_dynamic_array(cmnd), cmd->cmnd, cmd->cmd_len); if (cmd->sense_buffer && SCSI_SENSE_VALID(cmd) && scsi_command_normalize_sense(cmd, &sshdr)) { __entry->sense_key = sshdr.sense_key; __entry->asc = sshdr.asc; __entry->ascq = sshdr.ascq; } else { __entry->sense_key = 0; __entry->asc = 0; __entry->ascq = 0; } ), TP_printk("host_no=%u channel=%u id=%u lun=%u data_sgl=%u prot_sgl=%u " \ "prot_op=%s driver_tag=%d scheduler_tag=%d cmnd=(%s %s raw=%s) " \ "result=(driver=%s host=%s message=%s status=%s) " "sense=(key=%#x asc=%#x ascq=%#x)", __entry->host_no, __entry->channel, __entry->id, __entry->lun, __entry->data_sglen, __entry->prot_sglen, show_prot_op_name(__entry->prot_op), __entry->driver_tag, __entry->scheduler_tag, show_opcode_name(__entry->opcode), __parse_cdb(__get_dynamic_array(cmnd), __entry->cmd_len), __print_hex(__get_dynamic_array(cmnd), __entry->cmd_len), "DRIVER_OK", show_hostbyte_name(((__entry->result) >> 16) & 0xff), "COMMAND_COMPLETE", show_statusbyte_name(__entry->result & 0xff), __entry->sense_key, __entry->asc, __entry->ascq) ); DEFINE_EVENT(scsi_cmd_done_timeout_template, scsi_dispatch_cmd_done, TP_PROTO(struct scsi_cmnd *cmd), TP_ARGS(cmd)); DEFINE_EVENT(scsi_cmd_done_timeout_template, scsi_dispatch_cmd_timeout, TP_PROTO(struct scsi_cmnd *cmd), TP_ARGS(cmd)); TRACE_EVENT(scsi_eh_wakeup, TP_PROTO(struct Scsi_Host *shost), TP_ARGS(shost), TP_STRUCT__entry( __field( unsigned int, host_no ) ), TP_fast_assign( __entry->host_no = shost->host_no; ), TP_printk("host_no=%u", __entry->host_no) ); #endif /* _TRACE_SCSI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 15 12 14 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | /* * linux/fs/nls/nls_koi8-r.c * * Charset koi8-r translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x2500, 0x2502, 0x250c, 0x2510, 0x2514, 0x2518, 0x251c, 0x2524, 0x252c, 0x2534, 0x253c, 0x2580, 0x2584, 0x2588, 0x258c, 0x2590, /* 0x90*/ 0x2591, 0x2592, 0x2593, 0x2320, 0x25a0, 0x2219, 0x221a, 0x2248, 0x2264, 0x2265, 0x00a0, 0x2321, 0x00b0, 0x00b2, 0x00b7, 0x00f7, /* 0xa0*/ 0x2550, 0x2551, 0x2552, 0x0451, 0x2553, 0x2554, 0x2555, 0x2556, 0x2557, 0x2558, 0x2559, 0x255a, 0x255b, 0x255c, 0x255d, 0x255e, /* 0xb0*/ 0x255f, 0x2560, 0x2561, 0x0401, 0x2562, 0x2563, 0x2564, 0x2565, 0x2566, 0x2567, 0x2568, 0x2569, 0x256a, 0x256b, 0x256c, 0x00a9, /* 0xc0*/ 0x044e, 0x0430, 0x0431, 0x0446, 0x0434, 0x0435, 0x0444, 0x0433, 0x0445, 0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e, /* 0xd0*/ 0x043f, 0x044f, 0x0440, 0x0441, 0x0442, 0x0443, 0x0436, 0x0432, 0x044c, 0x044b, 0x0437, 0x0448, 0x044d, 0x0449, 0x0447, 0x044a, /* 0xe0*/ 0x042e, 0x0410, 0x0411, 0x0426, 0x0414, 0x0415, 0x0424, 0x0413, 0x0425, 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, /* 0xf0*/ 0x041f, 0x042f, 0x0420, 0x0421, 0x0422, 0x0423, 0x0416, 0x0412, 0x042c, 0x042b, 0x0417, 0x0428, 0x042d, 0x0429, 0x0427, 0x042a, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x9a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0xbf, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x9c, 0x00, 0x9d, 0x00, 0x00, 0x00, 0x00, 0x9e, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x9f, /* 0xf0-0xf7 */ }; static const unsigned char page04[256] = { 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xe1, 0xe2, 0xf7, 0xe7, 0xe4, 0xe5, 0xf6, 0xfa, /* 0x10-0x17 */ 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, /* 0x18-0x1f */ 0xf2, 0xf3, 0xf4, 0xf5, 0xe6, 0xe8, 0xe3, 0xfe, /* 0x20-0x27 */ 0xfb, 0xfd, 0xff, 0xf9, 0xf8, 0xfc, 0xe0, 0xf1, /* 0x28-0x2f */ 0xc1, 0xc2, 0xd7, 0xc7, 0xc4, 0xc5, 0xd6, 0xda, /* 0x30-0x37 */ 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, 0xd0, /* 0x38-0x3f */ 0xd2, 0xd3, 0xd4, 0xd5, 0xc6, 0xc8, 0xc3, 0xde, /* 0x40-0x47 */ 0xdb, 0xdd, 0xdf, 0xd9, 0xd8, 0xdc, 0xc0, 0xd1, /* 0x48-0x4f */ 0x00, 0xa3, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x95, 0x96, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x97, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x98, 0x99, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page23[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x93, 0x9b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char page25[256] = { 0x80, 0x00, 0x81, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x82, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x83, 0x00, 0x00, 0x00, 0x84, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x85, 0x00, 0x00, 0x00, 0x86, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x87, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x88, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x89, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x8a, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xa0, 0xa1, 0xa2, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, /* 0x50-0x57 */ 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, 0xb0, /* 0x58-0x5f */ 0xb1, 0xb2, 0xb4, 0xb5, 0xb6, 0xb7, 0xb8, 0xb9, /* 0x60-0x67 */ 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x8b, 0x00, 0x00, 0x00, 0x8c, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x8d, 0x00, 0x00, 0x00, 0x8e, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x8f, 0x90, 0x91, 0x92, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x94, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, page04, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page22, page23, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xa3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xe0-0xe7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xe8-0xef */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xf0-0xf7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xb3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xc0-0xc7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xc8-0xcf */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xd0-0xd7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "koi8-r", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_koi8_r(void) { return register_nls(&table); } static void __exit exit_nls_koi8_r(void) { unregister_nls(&table); } module_init(init_nls_koi8_r) module_exit(exit_nls_koi8_r) MODULE_DESCRIPTION("NLS KOI8-R (Russian)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 11 11 12 13 13 10 11 11 11 11 11 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 | // SPDX-License-Identifier: LGPL-2.1-or-later /* * dvb_demux.c - DVB kernel demux API * * Copyright (C) 2000-2001 Ralph Metzler <ralph@convergence.de> * & Marcus Metzler <marcus@convergence.de> * for convergence integrated media GmbH */ #define pr_fmt(fmt) "dvb_demux: " fmt #include <linux/sched/signal.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/module.h> #include <linux/poll.h> #include <linux/string.h> #include <linux/crc32.h> #include <linux/uaccess.h> #include <asm/div64.h> #include <media/dvb_demux.h> static int dvb_demux_tscheck; module_param(dvb_demux_tscheck, int, 0644); MODULE_PARM_DESC(dvb_demux_tscheck, "enable transport stream continuity and TEI check"); static int dvb_demux_speedcheck; module_param(dvb_demux_speedcheck, int, 0644); MODULE_PARM_DESC(dvb_demux_speedcheck, "enable transport stream speed check"); static int dvb_demux_feed_err_pkts = 1; module_param(dvb_demux_feed_err_pkts, int, 0644); MODULE_PARM_DESC(dvb_demux_feed_err_pkts, "when set to 0, drop packets with the TEI bit set (1 by default)"); #define dprintk(fmt, arg...) \ printk(KERN_DEBUG pr_fmt("%s: " fmt), __func__, ##arg) #define dprintk_tscheck(x...) do { \ if (dvb_demux_tscheck && printk_ratelimit()) \ dprintk(x); \ } while (0) #ifdef CONFIG_DVB_DEMUX_SECTION_LOSS_LOG # define dprintk_sect_loss(x...) dprintk(x) #else # define dprintk_sect_loss(x...) #endif #define set_buf_flags(__feed, __flag) \ do { \ (__feed)->buffer_flags |= (__flag); \ } while (0) /****************************************************************************** * static inlined helper functions ******************************************************************************/ static inline u16 section_length(const u8 *buf) { return 3 + ((buf[1] & 0x0f) << 8) + buf[2]; } static inline u16 ts_pid(const u8 *buf) { return ((buf[1] & 0x1f) << 8) + buf[2]; } static inline u8 payload(const u8 *tsp) { if (!(tsp[3] & 0x10)) // no payload? return 0; if (tsp[3] & 0x20) { // adaptation field? if (tsp[4] > 183) // corrupted data? return 0; else return 184 - 1 - tsp[4]; } return 184; } static u32 dvb_dmx_crc32(struct dvb_demux_feed *f, const u8 *src, size_t len) { return (f->feed.sec.crc_val = crc32_be(f->feed.sec.crc_val, src, len)); } static void dvb_dmx_memcopy(struct dvb_demux_feed *f, u8 *d, const u8 *s, size_t len) { memcpy(d, s, len); } /****************************************************************************** * Software filter functions ******************************************************************************/ static inline int dvb_dmx_swfilter_payload(struct dvb_demux_feed *feed, const u8 *buf) { int count = payload(buf); int p; int ccok; u8 cc; if (count == 0) return -1; p = 188 - count; cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; if (!ccok) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("missed packet: %d instead of %d!\n", cc, (feed->cc + 1) & 0x0f); } feed->cc = cc; if (buf[1] & 0x40) // PUSI ? feed->peslen = 0xfffa; feed->peslen += count; return feed->cb.ts(&buf[p], count, NULL, 0, &feed->feed.ts, &feed->buffer_flags); } static int dvb_dmx_swfilter_sectionfilter(struct dvb_demux_feed *feed, struct dvb_demux_filter *f) { u8 neq = 0; int i; for (i = 0; i < DVB_DEMUX_MASK_MAX; i++) { u8 xor = f->filter.filter_value[i] ^ feed->feed.sec.secbuf[i]; if (f->maskandmode[i] & xor) return 0; neq |= f->maskandnotmode[i] & xor; } if (f->doneq && !neq) return 0; return feed->cb.sec(feed->feed.sec.secbuf, feed->feed.sec.seclen, NULL, 0, &f->filter, &feed->buffer_flags); } static inline int dvb_dmx_swfilter_section_feed(struct dvb_demux_feed *feed) { struct dvb_demux *demux = feed->demux; struct dvb_demux_filter *f = feed->filter; struct dmx_section_feed *sec = &feed->feed.sec; int section_syntax_indicator; if (!sec->is_filtering) return 0; if (!f) return 0; if (sec->check_crc) { section_syntax_indicator = ((sec->secbuf[1] & 0x80) != 0); if (section_syntax_indicator && demux->check_crc32(feed, sec->secbuf, sec->seclen)) { set_buf_flags(feed, DMX_BUFFER_FLAG_HAD_CRC32_DISCARD); return -1; } } do { if (dvb_dmx_swfilter_sectionfilter(feed, f) < 0) return -1; } while ((f = f->next) && sec->is_filtering); sec->seclen = 0; return 0; } static void dvb_dmx_swfilter_section_new(struct dvb_demux_feed *feed) { struct dmx_section_feed *sec = &feed->feed.sec; if (sec->secbufp < sec->tsfeedp) { int n = sec->tsfeedp - sec->secbufp; /* * Section padding is done with 0xff bytes entirely. * Due to speed reasons, we won't check all of them * but just first and last. */ if (sec->secbuf[0] != 0xff || sec->secbuf[n - 1] != 0xff) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("section ts padding loss: %d/%d\n", n, sec->tsfeedp); dprintk_sect_loss("pad data: %*ph\n", n, sec->secbuf); } } sec->tsfeedp = sec->secbufp = sec->seclen = 0; sec->secbuf = sec->secbuf_base; } /* * Losless Section Demux 1.4.1 by Emard * Valsecchi Patrick: * - middle of section A (no PUSI) * - end of section A and start of section B * (with PUSI pointing to the start of the second section) * * In this case, without feed->pusi_seen you'll receive a garbage section * consisting of the end of section A. Basically because tsfeedp * is incemented and the use=0 condition is not raised * when the second packet arrives. * * Fix: * when demux is started, let feed->pusi_seen = false to * prevent initial feeding of garbage from the end of * previous section. When you for the first time see PUSI=1 * then set feed->pusi_seen = true */ static int dvb_dmx_swfilter_section_copy_dump(struct dvb_demux_feed *feed, const u8 *buf, u8 len) { struct dvb_demux *demux = feed->demux; struct dmx_section_feed *sec = &feed->feed.sec; u16 limit, seclen; if (sec->tsfeedp >= DMX_MAX_SECFEED_SIZE) return 0; if (sec->tsfeedp + len > DMX_MAX_SECFEED_SIZE) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("section buffer full loss: %d/%d\n", sec->tsfeedp + len - DMX_MAX_SECFEED_SIZE, DMX_MAX_SECFEED_SIZE); len = DMX_MAX_SECFEED_SIZE - sec->tsfeedp; } if (len <= 0) return 0; demux->memcopy(feed, sec->secbuf_base + sec->tsfeedp, buf, len); sec->tsfeedp += len; /* * Dump all the sections we can find in the data (Emard) */ limit = sec->tsfeedp; if (limit > DMX_MAX_SECFEED_SIZE) return -1; /* internal error should never happen */ /* to be sure always set secbuf */ sec->secbuf = sec->secbuf_base + sec->secbufp; while (sec->secbufp + 2 < limit) { seclen = section_length(sec->secbuf); if (seclen <= 0 || seclen > DMX_MAX_SECTION_SIZE || seclen + sec->secbufp > limit) return 0; sec->seclen = seclen; sec->crc_val = ~0; /* dump [secbuf .. secbuf+seclen) */ if (feed->pusi_seen) { dvb_dmx_swfilter_section_feed(feed); } else { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("pusi not seen, discarding section data\n"); } sec->secbufp += seclen; /* secbufp and secbuf moving together is */ sec->secbuf += seclen; /* redundant but saves pointer arithmetic */ } return 0; } static int dvb_dmx_swfilter_section_packet(struct dvb_demux_feed *feed, const u8 *buf) { u8 p, count; int ccok, dc_i = 0; u8 cc; count = payload(buf); if (count == 0) /* count == 0 if no payload or out of range */ return -1; p = 188 - count; /* payload start */ cc = buf[3] & 0x0f; ccok = ((feed->cc + 1) & 0x0f) == cc; if (buf[3] & 0x20) { /* adaption field present, check for discontinuity_indicator */ if ((buf[4] > 0) && (buf[5] & 0x80)) dc_i = 1; } if (!ccok || dc_i) { if (dc_i) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_INDICATOR); dprintk_sect_loss("%d frame with disconnect indicator\n", cc); } else { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("discontinuity: %d instead of %d. %d bytes lost\n", cc, (feed->cc + 1) & 0x0f, count + 4); } /* * those bytes under some circumstances will again be reported * in the following dvb_dmx_swfilter_section_new */ /* * Discontinuity detected. Reset pusi_seen to * stop feeding of suspicious data until next PUSI=1 arrives * * FIXME: does it make sense if the MPEG-TS is the one * reporting discontinuity? */ feed->pusi_seen = false; dvb_dmx_swfilter_section_new(feed); } feed->cc = cc; if (buf[1] & 0x40) { /* PUSI=1 (is set), section boundary is here */ if (count > 1 && buf[p] < count) { const u8 *before = &buf[p + 1]; u8 before_len = buf[p]; const u8 *after = &before[before_len]; u8 after_len = count - 1 - before_len; dvb_dmx_swfilter_section_copy_dump(feed, before, before_len); /* before start of new section, set pusi_seen */ feed->pusi_seen = true; dvb_dmx_swfilter_section_new(feed); dvb_dmx_swfilter_section_copy_dump(feed, after, after_len); } else if (count > 0) { set_buf_flags(feed, DMX_BUFFER_FLAG_DISCONTINUITY_DETECTED); dprintk_sect_loss("PUSI=1 but %d bytes lost\n", count); } } else { /* PUSI=0 (is not set), no section boundary */ dvb_dmx_swfilter_section_copy_dump(feed, &buf[p], count); } return 0; } static inline void dvb_dmx_swfilter_packet_type(struct dvb_demux_feed *feed, const u8 *buf) { switch (feed->type) { case DMX_TYPE_TS: if (!feed->feed.ts.is_filtering) break; if (feed->ts_type & TS_PACKET) { if (feed->ts_type & TS_PAYLOAD_ONLY) dvb_dmx_swfilter_payload(feed, buf); else feed->cb.ts(buf, 188, NULL, 0, &feed->feed.ts, &feed->buffer_flags); } /* Used only on full-featured devices */ if (feed->ts_type & TS_DECODER) if (feed->demux->write_to_decoder) feed->demux->write_to_decoder(feed, buf, 188); break; case DMX_TYPE_SEC: if (!feed->feed.sec.is_filtering) break; if (dvb_dmx_swfilter_section_packet(feed, buf) < 0) feed->feed.sec.seclen = feed->feed.sec.secbufp = 0; break; default: break; } } #define DVR_FEED(f) \ (((f)->type == DMX_TYPE_TS) && \ ((f)->feed.ts.is_filtering) && \ (((f)->ts_type & (TS_PACKET | TS_DEMUX)) == TS_PACKET)) static void dvb_dmx_swfilter_packet(struct dvb_demux *demux, const u8 *buf) { struct dvb_demux_feed *feed; u16 pid = ts_pid(buf); int dvr_done = 0; if (dvb_demux_speedcheck) { ktime_t cur_time; u64 speed_bytes, speed_timedelta; demux->speed_pkts_cnt++; /* show speed every SPEED_PKTS_INTERVAL packets */ if (!(demux->speed_pkts_cnt % SPEED_PKTS_INTERVAL)) { cur_time = ktime_get(); if (ktime_to_ns(demux->speed_last_time) != 0) { speed_bytes = (u64)demux->speed_pkts_cnt * 188 * 8; /* convert to 1024 basis */ speed_bytes = 1000 * div64_u64(speed_bytes, 1024); speed_timedelta = ktime_ms_delta(cur_time, demux->speed_last_time); if (speed_timedelta) dprintk("TS speed %llu Kbits/sec \n", div64_u64(speed_bytes, speed_timedelta)); } demux->speed_last_time = cur_time; demux->speed_pkts_cnt = 0; } } if (buf[1] & 0x80) { list_for_each_entry(feed, &demux->feed_list, list_head) { if ((feed->pid != pid) && (feed->pid != 0x2000)) continue; set_buf_flags(feed, DMX_BUFFER_FLAG_TEI); } dprintk_tscheck("TEI detected. PID=0x%x data1=0x%x\n", pid, buf[1]); /* data in this packet can't be trusted - drop it unless * module option dvb_demux_feed_err_pkts is set */ if (!dvb_demux_feed_err_pkts) return; } else /* if TEI bit is set, pid may be wrong- skip pkt counter */ if (demux->cnt_storage && dvb_demux_tscheck) { /* check pkt counter */ if (pid < MAX_PID) { if (buf[3] & 0x10) demux->cnt_storage[pid] = (demux->cnt_storage[pid] + 1) & 0xf; if ((buf[3] & 0xf) != demux->cnt_storage[pid]) { list_for_each_entry(feed, &demux->feed_list, list_head) { if ((feed->pid != pid) && (feed->pid != 0x2000)) continue; set_buf_flags(feed, DMX_BUFFER_PKT_COUNTER_MISMATCH); } dprintk_tscheck("TS packet counter mismatch. PID=0x%x expected 0x%x got 0x%x\n", pid, demux->cnt_storage[pid], buf[3] & 0xf); demux->cnt_storage[pid] = buf[3] & 0xf; } } /* end check */ } list_for_each_entry(feed, &demux->feed_list, list_head) { if ((feed->pid != pid) && (feed->pid != 0x2000)) continue; /* copy each packet only once to the dvr device, even * if a PID is in multiple filters (e.g. video + PCR) */ if ((DVR_FEED(feed)) && (dvr_done++)) continue; if (feed->pid == pid) dvb_dmx_swfilter_packet_type(feed, buf); else if (feed->pid == 0x2000) feed->cb.ts(buf, 188, NULL, 0, &feed->feed.ts, &feed->buffer_flags); } } void dvb_dmx_swfilter_packets(struct dvb_demux *demux, const u8 *buf, size_t count) { unsigned long flags; spin_lock_irqsave(&demux->lock, flags); while (count--) { if (buf[0] == 0x47) dvb_dmx_swfilter_packet(demux, buf); buf += 188; } spin_unlock_irqrestore(&demux->lock, flags); } EXPORT_SYMBOL(dvb_dmx_swfilter_packets); static inline int find_next_packet(const u8 *buf, int pos, size_t count, const int pktsize) { int start = pos, lost; while (pos < count) { if (buf[pos] == 0x47 || (pktsize == 204 && buf[pos] == 0xB8)) break; pos++; } lost = pos - start; if (lost) { /* This garbage is part of a valid packet? */ int backtrack = pos - pktsize; if (backtrack >= 0 && (buf[backtrack] == 0x47 || (pktsize == 204 && buf[backtrack] == 0xB8))) return backtrack; } return pos; } /* Filter all pktsize= 188 or 204 sized packets and skip garbage. */ static inline void _dvb_dmx_swfilter(struct dvb_demux *demux, const u8 *buf, size_t count, const int pktsize) { int p = 0, i, j; const u8 *q; unsigned long flags; spin_lock_irqsave(&demux->lock, flags); if (demux->tsbufp) { /* tsbuf[0] is now 0x47. */ i = demux->tsbufp; j = pktsize - i; if (count < j) { memcpy(&demux->tsbuf[i], buf, count); demux->tsbufp += count; goto bailout; } memcpy(&demux->tsbuf[i], buf, j); if (demux->tsbuf[0] == 0x47) /* double check */ dvb_dmx_swfilter_packet(demux, demux->tsbuf); demux->tsbufp = 0; p += j; } while (1) { p = find_next_packet(buf, p, count, pktsize); if (p >= count) break; if (count - p < pktsize) break; q = &buf[p]; if (pktsize == 204 && (*q == 0xB8)) { memcpy(demux->tsbuf, q, 188); demux->tsbuf[0] = 0x47; q = demux->tsbuf; } dvb_dmx_swfilter_packet(demux, q); p += pktsize; } i = count - p; if (i) { memcpy(demux->tsbuf, &buf[p], i); demux->tsbufp = i; if (pktsize == 204 && demux->tsbuf[0] == 0xB8) demux->tsbuf[0] = 0x47; } bailout: spin_unlock_irqrestore(&demux->lock, flags); } void dvb_dmx_swfilter(struct dvb_demux *demux, const u8 *buf, size_t count) { _dvb_dmx_swfilter(demux, buf, count, 188); } EXPORT_SYMBOL(dvb_dmx_swfilter); void dvb_dmx_swfilter_204(struct dvb_demux *demux, const u8 *buf, size_t count) { _dvb_dmx_swfilter(demux, buf, count, 204); } EXPORT_SYMBOL(dvb_dmx_swfilter_204); void dvb_dmx_swfilter_raw(struct dvb_demux *demux, const u8 *buf, size_t count) { unsigned long flags; spin_lock_irqsave(&demux->lock, flags); demux->feed->cb.ts(buf, count, NULL, 0, &demux->feed->feed.ts, &demux->feed->buffer_flags); spin_unlock_irqrestore(&demux->lock, flags); } EXPORT_SYMBOL(dvb_dmx_swfilter_raw); static struct dvb_demux_filter *dvb_dmx_filter_alloc(struct dvb_demux *demux) { int i; for (i = 0; i < demux->filternum; i++) if (demux->filter[i].state == DMX_STATE_FREE) break; if (i == demux->filternum) return NULL; demux->filter[i].state = DMX_STATE_ALLOCATED; return &demux->filter[i]; } static struct dvb_demux_feed *dvb_dmx_feed_alloc(struct dvb_demux *demux) { int i; for (i = 0; i < demux->feednum; i++) if (demux->feed[i].state == DMX_STATE_FREE) break; if (i == demux->feednum) return NULL; demux->feed[i].state = DMX_STATE_ALLOCATED; return &demux->feed[i]; } static int dvb_demux_feed_find(struct dvb_demux_feed *feed) { struct dvb_demux_feed *entry; list_for_each_entry(entry, &feed->demux->feed_list, list_head) if (entry == feed) return 1; return 0; } static void dvb_demux_feed_add(struct dvb_demux_feed *feed) { spin_lock_irq(&feed->demux->lock); if (dvb_demux_feed_find(feed)) { pr_err("%s: feed already in list (type=%x state=%x pid=%x)\n", __func__, feed->type, feed->state, feed->pid); goto out; } list_add(&feed->list_head, &feed->demux->feed_list); out: spin_unlock_irq(&feed->demux->lock); } static void dvb_demux_feed_del(struct dvb_demux_feed *feed) { spin_lock_irq(&feed->demux->lock); if (!(dvb_demux_feed_find(feed))) { pr_err("%s: feed not in list (type=%x state=%x pid=%x)\n", __func__, feed->type, feed->state, feed->pid); goto out; } list_del(&feed->list_head); out: spin_unlock_irq(&feed->demux->lock); } static int dmx_ts_feed_set(struct dmx_ts_feed *ts_feed, u16 pid, int ts_type, enum dmx_ts_pes pes_type, ktime_t timeout) { struct dvb_demux_feed *feed = (struct dvb_demux_feed *)ts_feed; struct dvb_demux *demux = feed->demux; if (pid > DMX_MAX_PID) return -EINVAL; if (mutex_lock_interruptible(&demux->mutex)) return -ERESTARTSYS; if (ts_type & TS_DECODER) { if (pes_type >= DMX_PES_OTHER) { mutex_unlock(&demux->mutex); return -EINVAL; } if (demux->pesfilter[pes_type] && demux->pesfilter[pes_type] != feed) { mutex_unlock(&demux->mutex); return -EINVAL; } demux->pesfilter[pes_type] = feed; demux->pids[pes_type] = pid; } dvb_demux_feed_add(feed); feed->pid = pid; feed->timeout = timeout; feed->ts_type = ts_type; feed->pes_type = pes_type; feed->state = DMX_STATE_READY; mutex_unlock(&demux->mutex); return 0; } static int dmx_ts_feed_start_filtering(struct dmx_ts_feed *ts_feed) { struct dvb_demux_feed *feed = (struct dvb_demux_feed *)ts_feed; struct dvb_demux *demux = feed->demux; int ret; if (mutex_lock_interruptible(&demux->mutex)) return -ERESTARTSYS; if (feed->state != DMX_STATE_READY || feed->type != DMX_TYPE_TS) { mutex_unlock(&demux->mutex); return -EINVAL; } if (!demux->start_feed) { mutex_unlock(&demux->mutex); return -ENODEV; } if ((ret = demux->start_feed(feed)) < 0) { mutex_unlock(&demux->mutex); return ret; } spin_lock_irq(&demux->lock); ts_feed->is_filtering = 1; feed->state = DMX_STATE_GO; spin_unlock_irq(&demux->lock); mutex_unlock(&demux->mutex); return 0; } static int dmx_ts_feed_stop_filtering(struct dmx_ts_feed *ts_feed) { struct dvb_demux_feed *feed = (struct dvb_demux_feed *)ts_feed; struct dvb_demux *demux = feed->demux; int ret; mutex_lock(&demux->mutex); if (feed->state < DMX_STATE_GO) { mutex_unlock(&demux->mutex); return -EINVAL; } if (!demux->stop_feed) { mutex_unlock(&demux->mutex); return -ENODEV; } ret = demux->stop_feed(feed); spin_lock_irq(&demux->lock); ts_feed->is_filtering = 0; feed->state = DMX_STATE_ALLOCATED; spin_unlock_irq(&demux->lock); mutex_unlock(&demux->mutex); return ret; } static int dvbdmx_allocate_ts_feed(struct dmx_demux *dmx, struct dmx_ts_feed **ts_feed, dmx_ts_cb callback) { struct dvb_demux *demux = (struct dvb_demux *)dmx; struct dvb_demux_feed *feed; if (mutex_lock_interruptible(&demux->mutex)) return -ERESTARTSYS; if (!(feed = dvb_dmx_feed_alloc(demux))) { mutex_unlock(&demux->mutex); return -EBUSY; } feed->type = DMX_TYPE_TS; feed->cb.ts = callback; feed->demux = demux; feed->pid = 0xffff; feed->peslen = 0xfffa; feed->buffer_flags = 0; (*ts_feed) = &feed->feed.ts; (*ts_feed)->parent = dmx; (*ts_feed)->priv = NULL; (*ts_feed)->is_filtering = 0; (*ts_feed)->start_filtering = dmx_ts_feed_start_filtering; (*ts_feed)->stop_filtering = dmx_ts_feed_stop_filtering; (*ts_feed)->set = dmx_ts_feed_set; if (!(feed->filter = dvb_dmx_filter_alloc(demux))) { feed->state = DMX_STATE_FREE; mutex_unlock(&demux->mutex); return -EBUSY; } feed->filter->type = DMX_TYPE_TS; feed->filter->feed = feed; feed->filter->state = DMX_STATE_READY; mutex_unlock(&demux->mutex); return 0; } static int dvbdmx_release_ts_feed(struct dmx_demux *dmx, struct dmx_ts_feed *ts_feed) { struct dvb_demux *demux = (struct dvb_demux *)dmx; struct dvb_demux_feed *feed = (struct dvb_demux_feed *)ts_feed; mutex_lock(&demux->mutex); if (feed->state == DMX_STATE_FREE) { mutex_unlock(&demux->mutex); return -EINVAL; } feed->state = DMX_STATE_FREE; feed->filter->state = DMX_STATE_FREE; dvb_demux_feed_del(feed); feed->pid = 0xffff; if (feed->ts_type & TS_DECODER && feed->pes_type < DMX_PES_OTHER) demux->pesfilter[feed->pes_type] = NULL; mutex_unlock(&demux->mutex); return 0; } /****************************************************************************** * dmx_section_feed API calls ******************************************************************************/ static int dmx_section_feed_allocate_filter(struct dmx_section_feed *feed, struct dmx_section_filter **filter) { struct dvb_demux_feed *dvbdmxfeed = (struct dvb_demux_feed *)feed; struct dvb_demux *dvbdemux = dvbdmxfeed->demux; struct dvb_demux_filter *dvbdmxfilter; if (mutex_lock_interruptible(&dvbdemux->mutex)) return -ERESTARTSYS; dvbdmxfilter = dvb_dmx_filter_alloc(dvbdemux); if (!dvbdmxfilter) { mutex_unlock(&dvbdemux->mutex); return -EBUSY; } spin_lock_irq(&dvbdemux->lock); *filter = &dvbdmxfilter->filter; (*filter)->parent = feed; (*filter)->priv = NULL; dvbdmxfilter->feed = dvbdmxfeed; dvbdmxfilter->type = DMX_TYPE_SEC; dvbdmxfilter->state = DMX_STATE_READY; dvbdmxfilter->next = dvbdmxfeed->filter; dvbdmxfeed->filter = dvbdmxfilter; spin_unlock_irq(&dvbdemux->lock); mutex_unlock(&dvbdemux->mutex); return 0; } static int dmx_section_feed_set(struct dmx_section_feed *feed, u16 pid, int check_crc) { struct dvb_demux_feed *dvbdmxfeed = (struct dvb_demux_feed *)feed; struct dvb_demux *dvbdmx = dvbdmxfeed->demux; if (pid > 0x1fff) return -EINVAL; if (mutex_lock_interruptible(&dvbdmx->mutex)) return -ERESTARTSYS; dvb_demux_feed_add(dvbdmxfeed); dvbdmxfeed->pid = pid; dvbdmxfeed->feed.sec.check_crc = check_crc; dvbdmxfeed->state = DMX_STATE_READY; mutex_unlock(&dvbdmx->mutex); return 0; } static void prepare_secfilters(struct dvb_demux_feed *dvbdmxfeed) { int i; struct dvb_demux_filter *f; struct dmx_section_filter *sf; u8 mask, mode, doneq; if (!(f = dvbdmxfeed->filter)) return; do { sf = &f->filter; doneq = false; for (i = 0; i < DVB_DEMUX_MASK_MAX; i++) { mode = sf->filter_mode[i]; mask = sf->filter_mask[i]; f->maskandmode[i] = mask & mode; doneq |= f->maskandnotmode[i] = mask & ~mode; } f->doneq = doneq ? true : false; } while ((f = f->next)); } static int dmx_section_feed_start_filtering(struct dmx_section_feed *feed) { struct dvb_demux_feed *dvbdmxfeed = (struct dvb_demux_feed *)feed; struct dvb_demux *dvbdmx = dvbdmxfeed->demux; int ret; if (mutex_lock_interruptible(&dvbdmx->mutex)) return -ERESTARTSYS; if (feed->is_filtering) { mutex_unlock(&dvbdmx->mutex); return -EBUSY; } if (!dvbdmxfeed->filter) { mutex_unlock(&dvbdmx->mutex); return -EINVAL; } dvbdmxfeed->feed.sec.tsfeedp = 0; dvbdmxfeed->feed.sec.secbuf = dvbdmxfeed->feed.sec.secbuf_base; dvbdmxfeed->feed.sec.secbufp = 0; dvbdmxfeed->feed.sec.seclen = 0; dvbdmxfeed->pusi_seen = false; if (!dvbdmx->start_feed) { mutex_unlock(&dvbdmx->mutex); return -ENODEV; } prepare_secfilters(dvbdmxfeed); if ((ret = dvbdmx->start_feed(dvbdmxfeed)) < 0) { mutex_unlock(&dvbdmx->mutex); return ret; } spin_lock_irq(&dvbdmx->lock); feed->is_filtering = 1; dvbdmxfeed->state = DMX_STATE_GO; spin_unlock_irq(&dvbdmx->lock); mutex_unlock(&dvbdmx->mutex); return 0; } static int dmx_section_feed_stop_filtering(struct dmx_section_feed *feed) { struct dvb_demux_feed *dvbdmxfeed = (struct dvb_demux_feed *)feed; struct dvb_demux *dvbdmx = dvbdmxfeed->demux; int ret; mutex_lock(&dvbdmx->mutex); if (!dvbdmx->stop_feed) { mutex_unlock(&dvbdmx->mutex); return -ENODEV; } ret = dvbdmx->stop_feed(dvbdmxfeed); spin_lock_irq(&dvbdmx->lock); dvbdmxfeed->state = DMX_STATE_READY; feed->is_filtering = 0; spin_unlock_irq(&dvbdmx->lock); mutex_unlock(&dvbdmx->mutex); return ret; } static int dmx_section_feed_release_filter(struct dmx_section_feed *feed, struct dmx_section_filter *filter) { struct dvb_demux_filter *dvbdmxfilter = (struct dvb_demux_filter *)filter, *f; struct dvb_demux_feed *dvbdmxfeed = (struct dvb_demux_feed *)feed; struct dvb_demux *dvbdmx = dvbdmxfeed->demux; mutex_lock(&dvbdmx->mutex); if (dvbdmxfilter->feed != dvbdmxfeed) { mutex_unlock(&dvbdmx->mutex); return -EINVAL; } if (feed->is_filtering) { /* release dvbdmx->mutex as far as it is acquired by stop_filtering() itself */ mutex_unlock(&dvbdmx->mutex); feed->stop_filtering(feed); mutex_lock(&dvbdmx->mutex); } spin_lock_irq(&dvbdmx->lock); f = dvbdmxfeed->filter; if (f == dvbdmxfilter) { dvbdmxfeed->filter = dvbdmxfilter->next; } else { while (f->next != dvbdmxfilter) f = f->next; f->next = f->next->next; } dvbdmxfilter->state = DMX_STATE_FREE; spin_unlock_irq(&dvbdmx->lock); mutex_unlock(&dvbdmx->mutex); return 0; } static int dvbdmx_allocate_section_feed(struct dmx_demux *demux, struct dmx_section_feed **feed, dmx_section_cb callback) { struct dvb_demux *dvbdmx = (struct dvb_demux *)demux; struct dvb_demux_feed *dvbdmxfeed; if (mutex_lock_interruptible(&dvbdmx->mutex)) return -ERESTARTSYS; if (!(dvbdmxfeed = dvb_dmx_feed_alloc(dvbdmx))) { mutex_unlock(&dvbdmx->mutex); return -EBUSY; } dvbdmxfeed->type = DMX_TYPE_SEC; dvbdmxfeed->cb.sec = callback; dvbdmxfeed->demux = dvbdmx; dvbdmxfeed->pid = 0xffff; dvbdmxfeed->buffer_flags = 0; dvbdmxfeed->feed.sec.secbuf = dvbdmxfeed->feed.sec.secbuf_base; dvbdmxfeed->feed.sec.secbufp = dvbdmxfeed->feed.sec.seclen = 0; dvbdmxfeed->feed.sec.tsfeedp = 0; dvbdmxfeed->filter = NULL; (*feed) = &dvbdmxfeed->feed.sec; (*feed)->is_filtering = 0; (*feed)->parent = demux; (*feed)->priv = NULL; (*feed)->set = dmx_section_feed_set; (*feed)->allocate_filter = dmx_section_feed_allocate_filter; (*feed)->start_filtering = dmx_section_feed_start_filtering; (*feed)->stop_filtering = dmx_section_feed_stop_filtering; (*feed)->release_filter = dmx_section_feed_release_filter; mutex_unlock(&dvbdmx->mutex); return 0; } static int dvbdmx_release_section_feed(struct dmx_demux *demux, struct dmx_section_feed *feed) { struct dvb_demux_feed *dvbdmxfeed = (struct dvb_demux_feed *)feed; struct dvb_demux *dvbdmx = (struct dvb_demux *)demux; mutex_lock(&dvbdmx->mutex); if (dvbdmxfeed->state == DMX_STATE_FREE) { mutex_unlock(&dvbdmx->mutex); return -EINVAL; } dvbdmxfeed->state = DMX_STATE_FREE; dvb_demux_feed_del(dvbdmxfeed); dvbdmxfeed->pid = 0xffff; mutex_unlock(&dvbdmx->mutex); return 0; } /****************************************************************************** * dvb_demux kernel data API calls ******************************************************************************/ static int dvbdmx_open(struct dmx_demux *demux) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; if (dvbdemux->users >= MAX_DVB_DEMUX_USERS) return -EUSERS; dvbdemux->users++; return 0; } static int dvbdmx_close(struct dmx_demux *demux) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; if (dvbdemux->users == 0) return -ENODEV; dvbdemux->users--; //FIXME: release any unneeded resources if users==0 return 0; } static int dvbdmx_write(struct dmx_demux *demux, const char __user *buf, size_t count) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; void *p; if ((!demux->frontend) || (demux->frontend->source != DMX_MEMORY_FE)) return -EINVAL; p = memdup_user(buf, count); if (IS_ERR(p)) return PTR_ERR(p); if (mutex_lock_interruptible(&dvbdemux->mutex)) { kfree(p); return -ERESTARTSYS; } dvb_dmx_swfilter(dvbdemux, p, count); kfree(p); mutex_unlock(&dvbdemux->mutex); if (signal_pending(current)) return -EINTR; return count; } static int dvbdmx_add_frontend(struct dmx_demux *demux, struct dmx_frontend *frontend) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; struct list_head *head = &dvbdemux->frontend_list; list_add(&(frontend->connectivity_list), head); return 0; } static int dvbdmx_remove_frontend(struct dmx_demux *demux, struct dmx_frontend *frontend) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; struct list_head *pos, *n, *head = &dvbdemux->frontend_list; list_for_each_safe(pos, n, head) { if (DMX_FE_ENTRY(pos) == frontend) { list_del(pos); return 0; } } return -ENODEV; } static struct list_head *dvbdmx_get_frontends(struct dmx_demux *demux) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; if (list_empty(&dvbdemux->frontend_list)) return NULL; return &dvbdemux->frontend_list; } static int dvbdmx_connect_frontend(struct dmx_demux *demux, struct dmx_frontend *frontend) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; if (demux->frontend) return -EINVAL; mutex_lock(&dvbdemux->mutex); demux->frontend = frontend; mutex_unlock(&dvbdemux->mutex); return 0; } static int dvbdmx_disconnect_frontend(struct dmx_demux *demux) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; mutex_lock(&dvbdemux->mutex); demux->frontend = NULL; mutex_unlock(&dvbdemux->mutex); return 0; } static int dvbdmx_get_pes_pids(struct dmx_demux *demux, u16 * pids) { struct dvb_demux *dvbdemux = (struct dvb_demux *)demux; memcpy(pids, dvbdemux->pids, 5 * sizeof(u16)); return 0; } int dvb_dmx_init(struct dvb_demux *dvbdemux) { int i; struct dmx_demux *dmx = &dvbdemux->dmx; dvbdemux->cnt_storage = NULL; dvbdemux->users = 0; dvbdemux->filter = vmalloc(array_size(sizeof(struct dvb_demux_filter), dvbdemux->filternum)); if (!dvbdemux->filter) return -ENOMEM; dvbdemux->feed = vmalloc(array_size(sizeof(struct dvb_demux_feed), dvbdemux->feednum)); if (!dvbdemux->feed) { vfree(dvbdemux->filter); dvbdemux->filter = NULL; return -ENOMEM; } for (i = 0; i < dvbdemux->filternum; i++) { dvbdemux->filter[i].state = DMX_STATE_FREE; dvbdemux->filter[i].index = i; } for (i = 0; i < dvbdemux->feednum; i++) { dvbdemux->feed[i].state = DMX_STATE_FREE; dvbdemux->feed[i].index = i; } dvbdemux->cnt_storage = vmalloc(MAX_PID + 1); if (!dvbdemux->cnt_storage) pr_warn("Couldn't allocate memory for TS/TEI check. Disabling it\n"); INIT_LIST_HEAD(&dvbdemux->frontend_list); for (i = 0; i < DMX_PES_OTHER; i++) { dvbdemux->pesfilter[i] = NULL; dvbdemux->pids[i] = 0xffff; } INIT_LIST_HEAD(&dvbdemux->feed_list); dvbdemux->playing = 0; dvbdemux->recording = 0; dvbdemux->tsbufp = 0; if (!dvbdemux->check_crc32) dvbdemux->check_crc32 = dvb_dmx_crc32; if (!dvbdemux->memcopy) dvbdemux->memcopy = dvb_dmx_memcopy; dmx->frontend = NULL; dmx->priv = dvbdemux; dmx->open = dvbdmx_open; dmx->close = dvbdmx_close; dmx->write = dvbdmx_write; dmx->allocate_ts_feed = dvbdmx_allocate_ts_feed; dmx->release_ts_feed = dvbdmx_release_ts_feed; dmx->allocate_section_feed = dvbdmx_allocate_section_feed; dmx->release_section_feed = dvbdmx_release_section_feed; dmx->add_frontend = dvbdmx_add_frontend; dmx->remove_frontend = dvbdmx_remove_frontend; dmx->get_frontends = dvbdmx_get_frontends; dmx->connect_frontend = dvbdmx_connect_frontend; dmx->disconnect_frontend = dvbdmx_disconnect_frontend; dmx->get_pes_pids = dvbdmx_get_pes_pids; mutex_init(&dvbdemux->mutex); spin_lock_init(&dvbdemux->lock); return 0; } EXPORT_SYMBOL(dvb_dmx_init); void dvb_dmx_release(struct dvb_demux *dvbdemux) { vfree(dvbdemux->cnt_storage); vfree(dvbdemux->filter); vfree(dvbdemux->feed); } EXPORT_SYMBOL(dvb_dmx_release); |
| 10 625 621 751 682 130 130 93 39 621 549 119 120 634 7 627 15 615 12 16 1 8 7 4 5 2 6 24 2 620 24 14 12 38 16 1 17 28 10 2 7 23 40 24 9 26 45 1 3 35 2 5 1 1 37 19 7 2 2 33 3 620 795 5 33 34 33 1 1 33 39 171 133 78 177 102 20 20 102 102 73 20 20 150 131 19 5 5 20 20 5 356 80 79 353 1 352 259 2 2 253 5 256 2 260 1 257 258 2 258 255 21 3 6 258 8 1 1 1 366 368 366 25 234 249 250 7 2 349 1 358 355 1 7 44 342 355 337 329 329 331 50 6 17 328 346 330 16 43 343 5 1 6 6 609 1 1 9 611 3 1 6 651 644 1 1 26 1 68 15 1 541 175 437 622 1 625 577 6 1 608 357 3 1 12 4 249 253 267 6 34 23 3 26 25 1 14 2 1 4 2 1 1 3 2 2 1 1 2 1 1 690 1 1 75 3 7 17 654 560 4 563 36 2 75 126 301 1 1 90 40 40 3 650 1 17 6 1 629 356 293 358 8 1 8 8 8 1 2 11 11 2 1 8 6 8 8 1 1 1 1 2 1 2 1 1 1 2 2 3 18 2 1 2 2 2 4 1 5 7 4 5 5 6 3 1 1 2 2 2 1 6 6 1 1 1 7 7 2 3 3 9 1 2 5 3 7 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_api.c Packet scheduler API. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * * Rani Assaf <rani@magic.metawire.com> :980802: JIFFIES and CPU clock sources are repaired. * Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support * Jamal Hadi Salim <hadi@nortelnetworks.com>: 990601: ingress support */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> #include <linux/slab.h> #include <linux/hashtable.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <trace/events/qdisc.h> /* Short review. ------------- This file consists of two interrelated parts: 1. queueing disciplines manager frontend. 2. traffic classes manager frontend. Generally, queueing discipline ("qdisc") is a black box, which is able to enqueue packets and to dequeue them (when device is ready to send something) in order and at times determined by algorithm hidden in it. qdisc's are divided to two categories: - "queues", which have no internal structure visible from outside. - "schedulers", which split all the packets to "traffic classes", using "packet classifiers" (look at cls_api.c) In turn, classes may have child qdiscs (as rule, queues) attached to them etc. etc. etc. The goal of the routines in this file is to translate information supplied by user in the form of handles to more intelligible for kernel form, to make some sanity checks and part of work, which is common to all qdiscs and to provide rtnetlink notifications. All real intelligent work is done inside qdisc modules. Every discipline has two major routines: enqueue and dequeue. ---dequeue dequeue usually returns a skb to send. It is allowed to return NULL, but it does not mean that queue is empty, it just means that discipline does not want to send anything this time. Queue is really empty if q->q.qlen == 0. For complicated disciplines with multiple queues q->q is not real packet queue, but however q->q.qlen must be valid. ---enqueue enqueue returns 0, if packet was enqueued successfully. If packet (this one or another one) was dropped, it returns not zero error code. NET_XMIT_DROP - this packet dropped Expected action: do not backoff, but wait until queue will clear. NET_XMIT_CN - probably this packet enqueued, but another one dropped. Expected action: backoff or ignore Auxiliary routines: ---peek like dequeue but without removing a packet from the queue ---reset returns qdisc to initial state: purge all buffers, clear all timers, counters (except for statistics) etc. ---init initializes newly created qdisc. ---destroy destroys resources allocated by init and during lifetime of qdisc. ---change changes qdisc parameters. */ /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(qdisc_mod_lock); /************************************************ * Queueing disciplines manipulation. * ************************************************/ /* The list of all installed queueing disciplines. */ static struct Qdisc_ops *qdisc_base; /* Register/unregister queueing discipline */ int register_qdisc(struct Qdisc_ops *qops) { struct Qdisc_ops *q, **qp; int rc = -EEXIST; write_lock(&qdisc_mod_lock); for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (!strcmp(qops->id, q->id)) goto out; if (qops->enqueue == NULL) qops->enqueue = noop_qdisc_ops.enqueue; if (qops->peek == NULL) { if (qops->dequeue == NULL) qops->peek = noop_qdisc_ops.peek; else goto out_einval; } if (qops->dequeue == NULL) qops->dequeue = noop_qdisc_ops.dequeue; if (qops->cl_ops) { const struct Qdisc_class_ops *cops = qops->cl_ops; if (!(cops->find && cops->walk && cops->leaf)) goto out_einval; if (cops->tcf_block && !(cops->bind_tcf && cops->unbind_tcf)) goto out_einval; } qops->next = NULL; *qp = qops; rc = 0; out: write_unlock(&qdisc_mod_lock); return rc; out_einval: rc = -EINVAL; goto out; } EXPORT_SYMBOL(register_qdisc); void unregister_qdisc(struct Qdisc_ops *qops) { struct Qdisc_ops *q, **qp; int err = -ENOENT; write_lock(&qdisc_mod_lock); for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (q == qops) break; if (q) { *qp = q->next; q->next = NULL; err = 0; } write_unlock(&qdisc_mod_lock); WARN(err, "unregister qdisc(%s) failed\n", qops->id); } EXPORT_SYMBOL(unregister_qdisc); /* Get default qdisc if not otherwise specified */ void qdisc_get_default(char *name, size_t len) { read_lock(&qdisc_mod_lock); strscpy(name, default_qdisc_ops->id, len); read_unlock(&qdisc_mod_lock); } static struct Qdisc_ops *qdisc_lookup_default(const char *name) { struct Qdisc_ops *q = NULL; for (q = qdisc_base; q; q = q->next) { if (!strcmp(name, q->id)) { if (!try_module_get(q->owner)) q = NULL; break; } } return q; } /* Set new default qdisc to use */ int qdisc_set_default(const char *name) { const struct Qdisc_ops *ops; if (!capable(CAP_NET_ADMIN)) return -EPERM; write_lock(&qdisc_mod_lock); ops = qdisc_lookup_default(name); if (!ops) { /* Not found, drop lock and try to load module */ write_unlock(&qdisc_mod_lock); request_module(NET_SCH_ALIAS_PREFIX "%s", name); write_lock(&qdisc_mod_lock); ops = qdisc_lookup_default(name); } if (ops) { /* Set new default */ module_put(default_qdisc_ops->owner); default_qdisc_ops = ops; } write_unlock(&qdisc_mod_lock); return ops ? 0 : -ENOENT; } #ifdef CONFIG_NET_SCH_DEFAULT /* Set default value from kernel config */ static int __init sch_default_qdisc(void) { return qdisc_set_default(CONFIG_DEFAULT_NET_SCH); } late_initcall(sch_default_qdisc); #endif /* We know handle. Find qdisc among all qdisc's attached to device * (root qdisc, all its children, children of children etc.) * Note: caller either uses rtnl or rcu_read_lock() */ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) { struct Qdisc *q; if (!qdisc_dev(root)) return (root->handle == handle ? root : NULL); if (!(root->flags & TCQ_F_BUILTIN) && root->handle == handle) return root; hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle, lockdep_rtnl_is_held()) { if (q->handle == handle) return q; } return NULL; } void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); if (invisible) q->flags |= TCQ_F_INVISIBLE; } } EXPORT_SYMBOL(qdisc_hash_add); void qdisc_hash_del(struct Qdisc *q) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { ASSERT_RTNL(); hash_del_rcu(&q->hash); } } EXPORT_SYMBOL(qdisc_hash_del); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { struct Qdisc *q; if (!handle) return NULL; q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle); if (q) goto out; if (dev_ingress_queue(dev)) q = qdisc_match_from_root( rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping), handle); out: return q; } struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) { struct netdev_queue *nq; struct Qdisc *q; if (!handle) return NULL; q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle); if (q) goto out; nq = dev_ingress_queue_rcu(dev); if (nq) q = qdisc_match_from_root(rcu_dereference(nq->qdisc_sleeping), handle); out: return q; } static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) { unsigned long cl; const struct Qdisc_class_ops *cops = p->ops->cl_ops; if (cops == NULL) return NULL; cl = cops->find(p, classid); if (cl == 0) return NULL; return cops->leaf(p, cl); } /* Find queueing discipline by name */ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind) { struct Qdisc_ops *q = NULL; if (kind) { read_lock(&qdisc_mod_lock); for (q = qdisc_base; q; q = q->next) { if (nla_strcmp(kind, q->id) == 0) { if (!try_module_get(q->owner)) q = NULL; break; } } read_unlock(&qdisc_mod_lock); } return q; } /* The linklayer setting were not transferred from iproute2, in older * versions, and the rate tables lookup systems have been dropped in * the kernel. To keep backward compatible with older iproute2 tc * utils, we detect the linklayer setting by detecting if the rate * table were modified. * * For linklayer ATM table entries, the rate table will be aligned to * 48 bytes, thus some table entries will contain the same value. The * mpu (min packet unit) is also encoded into the old rate table, thus * starting from the mpu, we find low and high table entries for * mapping this cell. If these entries contain the same value, when * the rate tables have been modified for linklayer ATM. * * This is done by rounding mpu to the nearest 48 bytes cell/entry, * and then roundup to the next cell, calc the table entry one below, * and compare. */ static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) { int low = roundup(r->mpu, 48); int high = roundup(low+1, 48); int cell_low = low >> r->cell_log; int cell_high = (high >> r->cell_log) - 1; /* rtab is too inaccurate at rates > 100Mbit/s */ if ((r->rate > (100000000/8)) || (rtab[0] == 0)) { pr_debug("TC linklayer: Giving up ATM detection\n"); return TC_LINKLAYER_ETHERNET; } if ((cell_high > cell_low) && (cell_high < 256) && (rtab[cell_low] == rtab[cell_high])) { pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n", cell_low, cell_high, rtab[cell_high]); return TC_LINKLAYER_ATM; } return TC_LINKLAYER_ETHERNET; } static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack) { struct qdisc_rate_table *rtab; if (tab == NULL || r->rate == 0 || r->cell_log == 0 || r->cell_log >= 32 || nla_len(tab) != TC_RTAB_SIZE) { NL_SET_ERR_MSG(extack, "Invalid rate table parameters for searching"); return NULL; } for (rtab = qdisc_rtab_list; rtab; rtab = rtab->next) { if (!memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) && !memcmp(&rtab->data, nla_data(tab), 1024)) { rtab->refcnt++; return rtab; } } rtab = kmalloc(sizeof(*rtab), GFP_KERNEL); if (rtab) { rtab->rate = *r; rtab->refcnt = 1; memcpy(rtab->data, nla_data(tab), 1024); if (r->linklayer == TC_LINKLAYER_UNAWARE) r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; } else { NL_SET_ERR_MSG(extack, "Failed to allocate new qdisc rate table"); } return rtab; } EXPORT_SYMBOL(qdisc_get_rtab); void qdisc_put_rtab(struct qdisc_rate_table *tab) { struct qdisc_rate_table *rtab, **rtabp; if (!tab || --tab->refcnt) return; for (rtabp = &qdisc_rtab_list; (rtab = *rtabp) != NULL; rtabp = &rtab->next) { if (rtab == tab) { *rtabp = rtab->next; kfree(rtab); return; } } } EXPORT_SYMBOL(qdisc_put_rtab); static LIST_HEAD(qdisc_stab_list); static const struct nla_policy stab_policy[TCA_STAB_MAX + 1] = { [TCA_STAB_BASE] = { .len = sizeof(struct tc_sizespec) }, [TCA_STAB_DATA] = { .type = NLA_BINARY }, }; static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_STAB_MAX + 1]; struct qdisc_size_table *stab; struct tc_sizespec *s; unsigned int tsize = 0; u16 *tab = NULL; int err; err = nla_parse_nested_deprecated(tb, TCA_STAB_MAX, opt, stab_policy, extack); if (err < 0) return ERR_PTR(err); if (!tb[TCA_STAB_BASE]) { NL_SET_ERR_MSG(extack, "Size table base attribute is missing"); return ERR_PTR(-EINVAL); } s = nla_data(tb[TCA_STAB_BASE]); if (s->tsize > 0) { if (!tb[TCA_STAB_DATA]) { NL_SET_ERR_MSG(extack, "Size table data attribute is missing"); return ERR_PTR(-EINVAL); } tab = nla_data(tb[TCA_STAB_DATA]); tsize = nla_len(tb[TCA_STAB_DATA]) / sizeof(u16); } if (tsize != s->tsize || (!tab && tsize > 0)) { NL_SET_ERR_MSG(extack, "Invalid size of size table"); return ERR_PTR(-EINVAL); } list_for_each_entry(stab, &qdisc_stab_list, list) { if (memcmp(&stab->szopts, s, sizeof(*s))) continue; if (tsize > 0 && memcmp(stab->data, tab, flex_array_size(stab, data, tsize))) continue; stab->refcnt++; return stab; } if (s->size_log > STAB_SIZE_LOG_MAX || s->cell_log > STAB_SIZE_LOG_MAX) { NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); return ERR_PTR(-EINVAL); } stab = kmalloc(struct_size(stab, data, tsize), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); stab->refcnt = 1; stab->szopts = *s; if (tsize > 0) memcpy(stab->data, tab, flex_array_size(stab, data, tsize)); list_add_tail(&stab->list, &qdisc_stab_list); return stab; } void qdisc_put_stab(struct qdisc_size_table *tab) { if (!tab) return; if (--tab->refcnt == 0) { list_del(&tab->list); kfree_rcu(tab, rcu); } } EXPORT_SYMBOL(qdisc_put_stab); static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, TCA_STAB); if (nest == NULL) goto nla_put_failure; if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts)) goto nla_put_failure; nla_nest_end(skb, nest); return skb->len; nla_put_failure: return -1; } void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab) { int pkt_len, slot; pkt_len = skb->len + stab->szopts.overhead; if (unlikely(!stab->szopts.tsize)) goto out; slot = pkt_len + stab->szopts.cell_align; if (unlikely(slot < 0)) slot = 0; slot >>= stab->szopts.cell_log; if (likely(slot < stab->szopts.tsize)) pkt_len = stab->data[slot]; else pkt_len = stab->data[stab->szopts.tsize - 1] * (slot / stab->szopts.tsize) + stab->data[slot % stab->szopts.tsize]; pkt_len <<= stab->szopts.size_log; out: if (unlikely(pkt_len < 1)) pkt_len = 1; qdisc_skb_cb(skb)->pkt_len = pkt_len; } void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc) { if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", txt, qdisc->ops->id, qdisc->handle >> 16); qdisc->flags |= TCQ_F_WARN_NONWC; } } EXPORT_SYMBOL(qdisc_warn_nonwc); static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) { struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, timer); rcu_read_lock(); __netif_schedule(qdisc_root(wd->qdisc)); rcu_read_unlock(); return HRTIMER_NORESTART; } void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc, clockid_t clockid) { hrtimer_init(&wd->timer, clockid, HRTIMER_MODE_ABS_PINNED); wd->timer.function = qdisc_watchdog; wd->qdisc = qdisc; } EXPORT_SYMBOL(qdisc_watchdog_init_clockid); void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) { qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC); } EXPORT_SYMBOL(qdisc_watchdog_init); void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, u64 delta_ns) { bool deactivated; rcu_read_lock(); deactivated = test_bit(__QDISC_STATE_DEACTIVATED, &qdisc_root_sleeping(wd->qdisc)->state); rcu_read_unlock(); if (deactivated) return; if (hrtimer_is_queued(&wd->timer)) { u64 softexpires; softexpires = ktime_to_ns(hrtimer_get_softexpires(&wd->timer)); /* If timer is already set in [expires, expires + delta_ns], * do not reprogram it. */ if (softexpires - expires <= delta_ns) return; } hrtimer_start_range_ns(&wd->timer, ns_to_ktime(expires), delta_ns, HRTIMER_MODE_ABS_PINNED); } EXPORT_SYMBOL(qdisc_watchdog_schedule_range_ns); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { hrtimer_cancel(&wd->timer); } EXPORT_SYMBOL(qdisc_watchdog_cancel); static struct hlist_head *qdisc_class_hash_alloc(unsigned int n) { struct hlist_head *h; unsigned int i; h = kvmalloc_array(n, sizeof(struct hlist_head), GFP_KERNEL); if (h != NULL) { for (i = 0; i < n; i++) INIT_HLIST_HEAD(&h[i]); } return h; } void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) { struct Qdisc_class_common *cl; struct hlist_node *next; struct hlist_head *nhash, *ohash; unsigned int nsize, nmask, osize; unsigned int i, h; /* Rehash when load factor exceeds 0.75 */ if (clhash->hashelems * 4 <= clhash->hashsize * 3) return; nsize = clhash->hashsize * 2; nmask = nsize - 1; nhash = qdisc_class_hash_alloc(nsize); if (nhash == NULL) return; ohash = clhash->hash; osize = clhash->hashsize; sch_tree_lock(sch); for (i = 0; i < osize; i++) { hlist_for_each_entry_safe(cl, next, &ohash[i], hnode) { h = qdisc_class_hash(cl->classid, nmask); hlist_add_head(&cl->hnode, &nhash[h]); } } clhash->hash = nhash; clhash->hashsize = nsize; clhash->hashmask = nmask; sch_tree_unlock(sch); kvfree(ohash); } EXPORT_SYMBOL(qdisc_class_hash_grow); int qdisc_class_hash_init(struct Qdisc_class_hash *clhash) { unsigned int size = 4; clhash->hash = qdisc_class_hash_alloc(size); if (!clhash->hash) return -ENOMEM; clhash->hashsize = size; clhash->hashmask = size - 1; clhash->hashelems = 0; return 0; } EXPORT_SYMBOL(qdisc_class_hash_init); void qdisc_class_hash_destroy(struct Qdisc_class_hash *clhash) { kvfree(clhash->hash); } EXPORT_SYMBOL(qdisc_class_hash_destroy); void qdisc_class_hash_insert(struct Qdisc_class_hash *clhash, struct Qdisc_class_common *cl) { unsigned int h; INIT_HLIST_NODE(&cl->hnode); h = qdisc_class_hash(cl->classid, clhash->hashmask); hlist_add_head(&cl->hnode, &clhash->hash[h]); clhash->hashelems++; } EXPORT_SYMBOL(qdisc_class_hash_insert); void qdisc_class_hash_remove(struct Qdisc_class_hash *clhash, struct Qdisc_class_common *cl) { hlist_del(&cl->hnode); clhash->hashelems--; } EXPORT_SYMBOL(qdisc_class_hash_remove); /* Allocate an unique handle from space managed by kernel * Possible range is [8000-FFFF]:0000 (0x8000 values) */ static u32 qdisc_alloc_handle(struct net_device *dev) { int i = 0x8000; static u32 autohandle = TC_H_MAKE(0x80000000U, 0); do { autohandle += TC_H_MAKE(0x10000U, 0); if (autohandle == TC_H_MAKE(TC_H_ROOT, 0)) autohandle = TC_H_MAKE(0x80000000U, 0); if (!qdisc_lookup(dev, autohandle)) return autohandle; cond_resched(); } while (--i > 0); return 0; } void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; bool notify; int drops; if (n == 0 && len == 0) return; drops = max_t(int, n, 0); rcu_read_lock(); while ((parentid = sch->parent)) { if (parentid == TC_H_ROOT) break; if (sch->flags & TCQ_F_NOPARENT) break; /* Notify parent qdisc only if child qdisc becomes empty. * * If child was empty even before update then backlog * counter is screwed and we skip notification because * parent class is already passive. * * If the original child was offloaded then it is allowed * to be seem as empty, so the parent is notified anyway. */ notify = !sch->q.qlen && !WARN_ON_ONCE(!n && !qdisc_is_offloaded); /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { WARN_ON_ONCE(parentid != TC_H_ROOT); break; } cops = sch->ops->cl_ops; if (notify && cops->qlen_notify) { cl = cops->find(sch, parentid); cops->qlen_notify(sch, cl); } sch->q.qlen -= n; sch->qstats.backlog -= len; __qdisc_qstats_drop(sch, drops); } rcu_read_unlock(); } EXPORT_SYMBOL(qdisc_tree_reduce_backlog); int qdisc_offload_dump_helper(struct Qdisc *sch, enum tc_setup_type type, void *type_data) { struct net_device *dev = qdisc_dev(sch); int err; sch->flags &= ~TCQ_F_OFFLOADED; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return 0; err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); if (err == -EOPNOTSUPP) return 0; if (!err) sch->flags |= TCQ_F_OFFLOADED; return err; } EXPORT_SYMBOL(qdisc_offload_dump_helper); void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, struct Qdisc *new, struct Qdisc *old, enum tc_setup_type type, void *type_data, struct netlink_ext_ack *extack) { bool any_qdisc_is_offloaded; int err; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); /* Don't report error if the graft is part of destroy operation. */ if (!err || !new || new == &noop_qdisc) return; /* Don't report error if the parent, the old child and the new * one are not offloaded. */ any_qdisc_is_offloaded = new->flags & TCQ_F_OFFLOADED; any_qdisc_is_offloaded |= sch && sch->flags & TCQ_F_OFFLOADED; any_qdisc_is_offloaded |= old && old->flags & TCQ_F_OFFLOADED; if (any_qdisc_is_offloaded) NL_SET_ERR_MSG(extack, "Offloading graft operation failed."); } EXPORT_SYMBOL(qdisc_offload_graft_helper); void qdisc_offload_query_caps(struct net_device *dev, enum tc_setup_type type, void *caps, size_t caps_len) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_query_caps_base base = { .type = type, .caps = caps, }; memset(caps, 0, caps_len); if (ops->ndo_setup_tc) ops->ndo_setup_tc(dev, TC_QUERY_CAPS, &base); } EXPORT_SYMBOL(qdisc_offload_query_caps); static void qdisc_offload_graft_root(struct net_device *dev, struct Qdisc *new, struct Qdisc *old, struct netlink_ext_ack *extack) { struct tc_root_qopt_offload graft_offload = { .command = TC_ROOT_GRAFT, .handle = new ? new->handle : 0, .ingress = (new && new->flags & TCQ_F_INGRESS) || (old && old->flags & TCQ_F_INGRESS), }; qdisc_offload_graft_helper(dev, NULL, new, old, TC_SETUP_ROOT_QDISC, &graft_offload, extack); } static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, u32 portid, u32 seq, u16 flags, int event, struct netlink_ext_ack *extack) { struct gnet_stats_basic_sync __percpu *cpu_bstats = NULL; struct gnet_stats_queue __percpu *cpu_qstats = NULL; struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; struct qdisc_size_table *stab; u32 block_index; __u32 qlen; cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = clid; tcm->tcm_handle = q->handle; tcm->tcm_info = refcount_read(&q->refcnt); if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; if (q->ops->ingress_block_get) { block_index = q->ops->ingress_block_get(q); if (block_index && nla_put_u32(skb, TCA_INGRESS_BLOCK, block_index)) goto nla_put_failure; } if (q->ops->egress_block_get) { block_index = q->ops->egress_block_get(q); if (block_index && nla_put_u32(skb, TCA_EGRESS_BLOCK, block_index)) goto nla_put_failure; } if (q->ops->dump && q->ops->dump(q, skb) < 0) goto nla_put_failure; if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) goto nla_put_failure; qlen = qdisc_qlen_sum(q); stab = rtnl_dereference(q->stab); if (stab && qdisc_dump_stab(skb, stab) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, NULL, &d, TCA_PAD) < 0) goto nla_put_failure; if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0) goto nla_put_failure; if (qdisc_is_percpu_stats(q)) { cpu_bstats = q->cpu_bstats; cpu_qstats = q->cpu_qstats; } if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats, true) < 0 || gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) goto nla_put_failure; if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; if (extack && extack->_msg && nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) goto out_nlmsg_trim; nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; } static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) { if (q->flags & TCQ_F_BUILTIN) return true; if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible) return true; return false; } static int qdisc_get_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, u32 clid, struct Qdisc *q, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (!tc_qdisc_dump_ignore(q, false)) { if (tc_fill_qdisc(skb, q, clid, portid, n->nlmsg_seq, 0, RTM_NEWQDISC, extack) < 0) goto err_out; } if (skb->len) return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); err_out: kfree_skb(skb); return -EINVAL; } static int qdisc_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, u32 clid, struct Qdisc *old, struct Qdisc *new, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) return 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (old && !tc_qdisc_dump_ignore(old, false)) { if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, 0, RTM_DELQDISC, extack) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new, false)) { if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC, extack) < 0) goto err_out; } if (skb->len) return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); err_out: kfree_skb(skb); return -EINVAL; } static void notify_and_destroy(struct net *net, struct sk_buff *skb, struct nlmsghdr *n, u32 clid, struct Qdisc *old, struct Qdisc *new, struct netlink_ext_ack *extack) { if (new || old) qdisc_notify(net, skb, n, clid, old, new, extack); if (old) qdisc_put(old); } static void qdisc_clear_nolock(struct Qdisc *sch) { sch->flags &= ~TCQ_F_NOLOCK; if (!(sch->flags & TCQ_F_CPUSTATS)) return; free_percpu(sch->cpu_bstats); free_percpu(sch->cpu_qstats); sch->cpu_bstats = NULL; sch->cpu_qstats = NULL; sch->flags &= ~TCQ_F_CPUSTATS; } /* Graft qdisc "new" to class "classid" of qdisc "parent" or * to device "dev". * * When appropriate send a netlink notification using 'skb' * and "n". * * On success, destroy old qdisc. */ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, struct sk_buff *skb, struct nlmsghdr *n, u32 classid, struct Qdisc *new, struct Qdisc *old, struct netlink_ext_ack *extack) { struct Qdisc *q = old; struct net *net = dev_net(dev); if (parent == NULL) { unsigned int i, num_q, ingress; struct netdev_queue *dev_queue; ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || (new && new->flags & TCQ_F_INGRESS)) { ingress = 1; dev_queue = dev_ingress_queue(dev); if (!dev_queue) { NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); return -ENOENT; } q = rtnl_dereference(dev_queue->qdisc_sleeping); /* This is the counterpart of that qdisc_refcount_inc_nz() call in * __tcf_qdisc_find() for filter requests. */ if (!qdisc_refcount_dec_if_one(q)) { NL_SET_ERR_MSG(extack, "Current ingress or clsact Qdisc has ongoing filter requests"); return -EBUSY; } } if (dev->flags & IFF_UP) dev_deactivate(dev); qdisc_offload_graft_root(dev, new, old, extack); if (new && new->ops->attach && !ingress) goto skip; if (!ingress) { for (i = 0; i < num_q; i++) { dev_queue = netdev_get_tx_queue(dev, i); old = dev_graft_qdisc(dev_queue, new); if (new && i > 0) qdisc_refcount_inc(new); qdisc_put(old); } } else { old = dev_graft_qdisc(dev_queue, NULL); /* {ingress,clsact}_destroy() @old before grafting @new to avoid * unprotected concurrent accesses to net_device::miniq_{in,e}gress * pointer(s) in mini_qdisc_pair_swap(). */ qdisc_notify(net, skb, n, classid, old, new, extack); qdisc_destroy(old); dev_graft_qdisc(dev_queue, new); } skip: if (!ingress) { old = rtnl_dereference(dev->qdisc); if (new && !new->ops->attach) qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); notify_and_destroy(net, skb, n, classid, old, new, extack); if (new && new->ops->attach) new->ops->attach(new); } if (dev->flags & IFF_UP) dev_activate(dev); } else { const struct Qdisc_class_ops *cops = parent->ops->cl_ops; unsigned long cl; int err; /* Only support running class lockless if parent is lockless */ if (new && (new->flags & TCQ_F_NOLOCK) && !(parent->flags & TCQ_F_NOLOCK)) qdisc_clear_nolock(new); if (!cops || !cops->graft) return -EOPNOTSUPP; cl = cops->find(parent, classid); if (!cl) { NL_SET_ERR_MSG(extack, "Specified class not found"); return -ENOENT; } if (new && new->ops == &noqueue_qdisc_ops) { NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); return -EINVAL; } if (new && !(parent->flags & TCQ_F_MQROOT) && rcu_access_pointer(new->stab)) { NL_SET_ERR_MSG(extack, "STAB not supported on a non root"); return -EINVAL; } err = cops->graft(parent, cl, new, &old, extack); if (err) return err; notify_and_destroy(net, skb, n, classid, old, new, extack); } return 0; } static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, struct netlink_ext_ack *extack) { u32 block_index; if (tca[TCA_INGRESS_BLOCK]) { block_index = nla_get_u32(tca[TCA_INGRESS_BLOCK]); if (!block_index) { NL_SET_ERR_MSG(extack, "Ingress block index cannot be 0"); return -EINVAL; } if (!sch->ops->ingress_block_set) { NL_SET_ERR_MSG(extack, "Ingress block sharing is not supported"); return -EOPNOTSUPP; } sch->ops->ingress_block_set(sch, block_index); } if (tca[TCA_EGRESS_BLOCK]) { block_index = nla_get_u32(tca[TCA_EGRESS_BLOCK]); if (!block_index) { NL_SET_ERR_MSG(extack, "Egress block index cannot be 0"); return -EINVAL; } if (!sch->ops->egress_block_set) { NL_SET_ERR_MSG(extack, "Egress block sharing is not supported"); return -EOPNOTSUPP; } sch->ops->egress_block_set(sch, block_index); } return 0; } /* Allocate and initialize new qdisc. Parameters are passed via opt. */ static struct Qdisc *qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, u32 parent, u32 handle, struct nlattr **tca, int *errp, struct netlink_ext_ack *extack) { int err; struct nlattr *kind = tca[TCA_KIND]; struct Qdisc *sch; struct Qdisc_ops *ops; struct qdisc_size_table *stab; ops = qdisc_lookup_ops(kind); #ifdef CONFIG_MODULES if (ops == NULL && kind != NULL) { char name[IFNAMSIZ]; if (nla_strscpy(name, kind, IFNAMSIZ) >= 0) { /* We dropped the RTNL semaphore in order to * perform the module load. So, even if we * succeeded in loading the module we have to * tell the caller to replay the request. We * indicate this using -EAGAIN. * We replay the request because the device may * go away in the mean time. */ rtnl_unlock(); request_module(NET_SCH_ALIAS_PREFIX "%s", name); rtnl_lock(); ops = qdisc_lookup_ops(kind); if (ops != NULL) { /* We will try again qdisc_lookup_ops, * so don't keep a reference. */ module_put(ops->owner); err = -EAGAIN; goto err_out; } } } #endif err = -ENOENT; if (!ops) { NL_SET_ERR_MSG(extack, "Specified qdisc kind is unknown"); goto err_out; } sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { err = PTR_ERR(sch); goto err_out2; } sch->parent = parent; if (handle == TC_H_INGRESS) { if (!(sch->flags & TCQ_F_INGRESS)) { NL_SET_ERR_MSG(extack, "Specified parent ID is reserved for ingress and clsact Qdiscs"); err = -EINVAL; goto err_out3; } handle = TC_H_MAKE(TC_H_INGRESS, 0); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); if (handle == 0) { NL_SET_ERR_MSG(extack, "Maximum number of qdisc handles was exceeded"); err = -ENOSPC; goto err_out3; } } if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } sch->handle = handle; /* This exist to keep backward compatible with a userspace * loophole, what allowed userspace to get IFF_NO_QUEUE * facility on older kernels by setting tx_queue_len=0 (prior * to qdisc init), and then forgot to reinit tx_queue_len * before again attaching a qdisc. */ if ((dev->priv_flags & IFF_NO_QUEUE) && (dev->tx_queue_len == 0)) { WRITE_ONCE(dev->tx_queue_len, DEFAULT_TX_QUEUE_LEN); netdev_info(dev, "Caught tx_queue_len zero misconfig\n"); } err = qdisc_block_indexes_set(sch, tca, extack); if (err) goto err_out3; if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) { err = PTR_ERR(stab); goto err_out3; } rcu_assign_pointer(sch->stab, stab); } if (ops->init) { err = ops->init(sch, tca[TCA_OPTIONS], extack); if (err != 0) goto err_out4; } if (tca[TCA_RATE]) { err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); goto err_out4; } err = gen_new_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); goto err_out4; } } qdisc_hash_add(sch, false); trace_qdisc_create(ops, dev, parent); return sch; err_out4: /* Even if ops->init() failed, we call ops->destroy() * like qdisc_create_dflt(). */ if (ops->destroy) ops->destroy(sch); qdisc_put_stab(rtnl_dereference(sch->stab)); err_out3: lockdep_unregister_key(&sch->root_lock_key); netdev_put(dev, &sch->dev_tracker); qdisc_free(sch); err_out2: module_put(ops->owner); err_out: *errp = err; return NULL; } static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, struct netlink_ext_ack *extack) { struct qdisc_size_table *ostab, *stab = NULL; int err = 0; if (tca[TCA_OPTIONS]) { if (!sch->ops->change) { NL_SET_ERR_MSG(extack, "Change operation not supported by specified qdisc"); return -EINVAL; } if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { NL_SET_ERR_MSG(extack, "Change of blocks is not supported"); return -EOPNOTSUPP; } err = sch->ops->change(sch, tca[TCA_OPTIONS], extack); if (err) return err; } if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) return PTR_ERR(stab); } ostab = rtnl_dereference(sch->stab); rcu_assign_pointer(sch->stab, stab); qdisc_put_stab(ostab); if (tca[TCA_RATE]) { /* NB: ignores errors from replace_estimator because change can't be undone. */ if (sch->flags & TCQ_F_MQROOT) goto out; gen_replace_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, true, tca[TCA_RATE]); } out: return 0; } struct check_loop_arg { struct qdisc_walker w; struct Qdisc *p; int depth; }; static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w); static int check_loop(struct Qdisc *q, struct Qdisc *p, int depth) { struct check_loop_arg arg; if (q->ops->cl_ops == NULL) return 0; arg.w.stop = arg.w.skip = arg.w.count = 0; arg.w.fn = check_loop_fn; arg.depth = depth; arg.p = p; q->ops->cl_ops->walk(q, &arg.w); return arg.w.stop ? -ELOOP : 0; } static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) { struct Qdisc *leaf; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct check_loop_arg *arg = (struct check_loop_arg *)w; leaf = cops->leaf(q, cl); if (leaf) { if (leaf == arg->p || arg->depth > 7) return -ELOOP; return check_loop(leaf, arg->p, arg->depth + 1); } return 0; } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { [TCA_KIND] = { .type = NLA_STRING }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, [TCA_DUMP_INVISIBLE] = { .type = NLA_FLAG }, [TCA_CHAIN] = { .type = NLA_U32 }, [TCA_INGRESS_BLOCK] = { .type = NLA_U32 }, [TCA_EGRESS_BLOCK] = { .type = NLA_U32 }, }; /* * Delete/get qdisc. */ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; u32 clid; struct Qdisc *q = NULL; struct Qdisc *p = NULL; int err; err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; clid = tcm->tcm_parent; if (clid) { if (clid != TC_H_ROOT) { if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); if (!p) { NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue(dev)) { q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); } if (!q) { NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; } if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Invalid handle"); return -EINVAL; } } else { q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) { NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified handle"); return -ENOENT; } } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } if (n->nlmsg_type == RTM_DELQDISC) { if (!clid) { NL_SET_ERR_MSG(extack, "Classid cannot be zero"); return -EINVAL; } if (q->handle == 0) { NL_SET_ERR_MSG(extack, "Cannot delete qdisc with handle of zero"); return -ENOENT; } err = qdisc_graft(dev, p, skb, n, clid, NULL, q, extack); if (err != 0) return err; } else { qdisc_get_notify(net, skb, n, clid, q, NULL); } return 0; } static bool req_create_or_replace(struct nlmsghdr *n) { return (n->nlmsg_flags & NLM_F_CREATE && n->nlmsg_flags & NLM_F_REPLACE); } static bool req_create_exclusive(struct nlmsghdr *n) { return (n->nlmsg_flags & NLM_F_CREATE && n->nlmsg_flags & NLM_F_EXCL); } static bool req_change(struct nlmsghdr *n) { return (!(n->nlmsg_flags & NLM_F_CREATE) && !(n->nlmsg_flags & NLM_F_REPLACE) && !(n->nlmsg_flags & NLM_F_EXCL)); } /* * Create/change qdisc. */ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tcmsg *tcm; struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; u32 clid; struct Qdisc *q, *p; int err; replay: /* Reinit, just in case something touches this. */ err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; tcm = nlmsg_data(n); clid = tcm->tcm_parent; q = p = NULL; dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; if (clid) { if (clid != TC_H_ROOT) { if (clid != TC_H_INGRESS) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); if (!p) { NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } q = qdisc_leaf(p, clid); } else if (dev_ingress_queue_create(dev)) { q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); } /* It may be default qdisc, ignore it */ if (q && q->handle == 0) q = NULL; if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) { if (tcm->tcm_handle) { if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG(extack, "NLM_F_REPLACE needed to override"); return -EEXIST; } if (TC_H_MIN(tcm->tcm_handle)) { NL_SET_ERR_MSG(extack, "Invalid minor handle"); return -EINVAL; } q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) goto create_n_graft; if (n->nlmsg_flags & NLM_F_EXCL) { NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot override"); return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } if (q->flags & TCQ_F_INGRESS) { NL_SET_ERR_MSG(extack, "Cannot regraft ingress or clsact Qdiscs"); return -EINVAL; } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } if (clid == TC_H_INGRESS) { NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); return -EINVAL; } qdisc_refcount_inc(q); goto graft; } else { if (!q) goto create_n_graft; /* This magic test requires explanation. * * We know, that some child q is already * attached to this parent and have choice: * 1) change it or 2) create/graft new one. * If the requested qdisc kind is different * than the existing one, then we choose graft. * If they are the same then this is "change" * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only * if the request is explicitly stating * "please create if it doesn't exist". * * 2. If the request is to exclusive create * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. * This will happen when for example tc * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. * For now we select create/graft. */ if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { if (req_create_or_replace(n) || req_create_exclusive(n)) goto create_n_graft; else if (req_change(n)) goto create_n_graft2; } } } } else { if (!tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Handle cannot be zero"); return -EINVAL; } q = qdisc_lookup(dev, tcm->tcm_handle); } /* Change qdisc parameters */ if (!q) { NL_SET_ERR_MSG(extack, "Specified qdisc not found"); return -ENOENT; } if (n->nlmsg_flags & NLM_F_EXCL) { NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot modify"); return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } err = qdisc_change(q, tca, extack); if (err == 0) qdisc_notify(net, skb, n, clid, NULL, q, extack); return err; create_n_graft: if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } create_n_graft2: if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), tcm->tcm_parent, tcm->tcm_parent, tca, &err, extack); } else { NL_SET_ERR_MSG(extack, "Cannot find ingress queue for specified device"); err = -ENOENT; } } else { struct netdev_queue *dev_queue; if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue) dev_queue = p->ops->cl_ops->select_queue(p, tcm); else if (p) dev_queue = p->dev_queue; else dev_queue = netdev_get_tx_queue(dev, 0); q = qdisc_create(dev, dev_queue, tcm->tcm_parent, tcm->tcm_handle, tca, &err, extack); } if (q == NULL) { if (err == -EAGAIN) goto replay; return err; } graft: err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack); if (err) { if (q) qdisc_put(q); return err; } return 0; } static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, struct netlink_callback *cb, int *q_idx_p, int s_q_idx, bool recur, bool dump_invisible) { int ret = 0, q_idx = *q_idx_p; struct Qdisc *q; int b; if (!root) return 0; q = root; if (q_idx < s_q_idx) { q_idx++; } else { if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } /* If dumping singletons, there is no qdisc_dev(root) and the singleton * itself has already been dumped. * * If we've already dumped the top-level (ingress) qdisc above and the global * qdisc hashtable, we don't want to hit it again */ if (!qdisc_dev(root) || !recur) goto out; hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (q_idx < s_q_idx) { q_idx++; continue; } if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } out: *q_idx_p = q_idx; return ret; done: ret = -1; goto out; } static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx, q_idx; int s_idx, s_q_idx; struct net_device *dev; const struct nlmsghdr *nlh = cb->nlh; struct nlattr *tca[TCA_MAX + 1]; int err; s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; idx = 0; ASSERT_RTNL(); err = nlmsg_parse_deprecated(nlh, sizeof(struct tcmsg), tca, TCA_MAX, rtm_tca_policy, cb->extack); if (err < 0) return err; for_each_netdev(net, dev) { struct netdev_queue *dev_queue; if (idx < s_idx) goto cont; if (idx > s_idx) s_q_idx = 0; q_idx = 0; if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc), skb, cb, &q_idx, s_q_idx, true, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_qdisc_root(rtnl_dereference(dev_queue->qdisc_sleeping), skb, cb, &q_idx, s_q_idx, false, tca[TCA_DUMP_INVISIBLE]) < 0) goto done; cont: idx++; } done: cb->args[0] = idx; cb->args[1] = q_idx; return skb->len; } /************************************************ * Traffic classes manipulation. * ************************************************/ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, unsigned long cl, u32 portid, u32 seq, u16 flags, int event, struct netlink_ext_ack *extack) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = q->handle; tcm->tcm_handle = q->handle; tcm->tcm_info = 0; if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; if (cl_ops->dump && cl_ops->dump(q, cl, skb, tcm) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, NULL, &d, TCA_PAD) < 0) goto nla_put_failure; if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0) goto nla_put_failure; if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; if (extack && extack->_msg && nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) goto out_nlmsg_trim; nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; } static int tclass_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, unsigned long cl, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) return 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event, extack) < 0) { kfree_skb(skb); return -EINVAL; } return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); } static int tclass_get_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, unsigned long cl, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, RTM_NEWTCLASS, extack) < 0) { kfree_skb(skb); return -EINVAL; } return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); } static int tclass_del_notify(struct net *net, const struct Qdisc_class_ops *cops, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, unsigned long cl, struct netlink_ext_ack *extack) { u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; struct sk_buff *skb; int err = 0; if (!cops->delete) return -EOPNOTSUPP; if (rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, RTM_DELTCLASS, extack) < 0) { kfree_skb(skb); return -EINVAL; } } else { skb = NULL; } err = cops->delete(q, cl, extack); if (err) { kfree_skb(skb); return err; } err = rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); return err; } #ifdef CONFIG_NET_CLS struct tcf_bind_args { struct tcf_walker w; unsigned long base; unsigned long cl; u32 classid; }; static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) { struct tcf_bind_args *a = (void *)arg; if (n && tp->ops->bind_class) { struct Qdisc *q = tcf_block_q(tp->chain->block); sch_tree_lock(q); tp->ops->bind_class(n, a->classid, a->cl, q, a->base); sch_tree_unlock(q); } return 0; } struct tc_bind_class_args { struct qdisc_walker w; unsigned long new_cl; u32 portid; u32 clid; }; static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) { struct tc_bind_class_args *a = (struct tc_bind_class_args *)w; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tcf_block *block; struct tcf_chain *chain; block = cops->tcf_block(q, cl, NULL); if (!block) return 0; for (chain = tcf_get_next_chain(block, NULL); chain; chain = tcf_get_next_chain(block, chain)) { struct tcf_proto *tp; for (tp = tcf_get_next_proto(chain, NULL); tp; tp = tcf_get_next_proto(chain, tp)) { struct tcf_bind_args arg = {}; arg.w.fn = tcf_node_bind; arg.classid = a->clid; arg.base = cl; arg.cl = a->new_cl; tp->ops->walk(tp, &arg.w, true); } } return 0; } static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, unsigned long new_cl) { const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tc_bind_class_args args = {}; if (!cops->tcf_block) return; args.portid = portid; args.clid = clid; args.new_cl = new_cl; args.w.fn = tc_bind_class_walker; q->ops->cl_ops->walk(q, &args.w); } #else static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, unsigned long new_cl) { } #endif static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; struct Qdisc *q = NULL; const struct Qdisc_class_ops *cops; unsigned long cl = 0; unsigned long new_cl; u32 portid; u32 clid; u32 qid; int err; err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; /* parent == TC_H_UNSPEC - unspecified parent. parent == TC_H_ROOT - class is root, which has no parent. parent == X:0 - parent is root class. parent == X:Y - parent is a node in hierarchy. parent == 0:Y - parent is X:Y, where X:0 is qdisc. handle == 0:0 - generate handle from kernel pool. handle == 0:Y - class is X:Y, where X:0 is qdisc. handle == X:Y - clear. handle == X:0 - root class. */ /* Step 1. Determine qdisc handle X:0 */ portid = tcm->tcm_parent; clid = tcm->tcm_handle; qid = TC_H_MAJ(clid); if (portid != TC_H_ROOT) { u32 qid1 = TC_H_MAJ(portid); if (qid && qid1) { /* If both majors are known, they must be identical. */ if (qid != qid1) return -EINVAL; } else if (qid1) { qid = qid1; } else if (qid == 0) qid = rtnl_dereference(dev->qdisc)->handle; /* Now qid is genuine qdisc handle consistent * both with parent and child. * * TC_H_MAJ(portid) still may be unspecified, complete it now. */ if (portid) portid = TC_H_MAKE(qid, portid); } else { if (qid == 0) qid = rtnl_dereference(dev->qdisc)->handle; } /* OK. Locate qdisc */ q = qdisc_lookup(dev, qid); if (!q) return -ENOENT; /* An check that it supports classes */ cops = q->ops->cl_ops; if (cops == NULL) return -EINVAL; /* Now try to get class */ if (clid == 0) { if (portid == TC_H_ROOT) clid = qid; } else clid = TC_H_MAKE(qid, clid); if (clid) cl = cops->find(q, clid); if (cl == 0) { err = -ENOENT; if (n->nlmsg_type != RTM_NEWTCLASS || !(n->nlmsg_flags & NLM_F_CREATE)) goto out; } else { switch (n->nlmsg_type) { case RTM_NEWTCLASS: err = -EEXIST; if (n->nlmsg_flags & NLM_F_EXCL) goto out; break; case RTM_DELTCLASS: err = tclass_del_notify(net, cops, skb, n, q, cl, extack); /* Unbind the class with flilters with 0 */ tc_bind_tclass(q, portid, clid, 0); goto out; case RTM_GETTCLASS: err = tclass_get_notify(net, skb, n, q, cl, extack); goto out; default: err = -EINVAL; goto out; } } if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { NL_SET_ERR_MSG(extack, "Shared blocks are not supported for classes"); return -EOPNOTSUPP; } new_cl = cl; err = -EOPNOTSUPP; if (cops->change) err = cops->change(q, clid, portid, tca, &new_cl, extack); if (err == 0) { tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS, extack); /* We just create a new class, need to do reverse binding. */ if (cl != new_cl) tc_bind_tclass(q, portid, clid, new_cl); } out: return err; } struct qdisc_dump_args { struct qdisc_walker w; struct sk_buff *skb; struct netlink_callback *cb; }; static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg) { struct qdisc_dump_args *a = (struct qdisc_dump_args *)arg; return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTCLASS, NULL); } static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, int *t_p, int s_t) { struct qdisc_dump_args arg; if (tc_qdisc_dump_ignore(q, false) || *t_p < s_t || !q->ops->cl_ops || (tcm->tcm_parent && TC_H_MAJ(tcm->tcm_parent) != q->handle)) { (*t_p)++; return 0; } if (*t_p > s_t) memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); arg.w.fn = qdisc_class_dump; arg.skb = skb; arg.cb = cb; arg.w.stop = 0; arg.w.skip = cb->args[1]; arg.w.count = 0; q->ops->cl_ops->walk(q, &arg.w); cb->args[1] = arg.w.count; if (arg.w.stop) return -1; (*t_p)++; return 0; } static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, int *t_p, int s_t, bool recur) { struct Qdisc *q; int b; if (!root) return 0; if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0) return -1; if (!qdisc_dev(root) || !recur) return 0; if (tcm->tcm_parent) { q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent)); if (q && q != root && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; return 0; } hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; } return 0; } static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) { struct tcmsg *tcm = nlmsg_data(cb->nlh); struct net *net = sock_net(skb->sk); struct netdev_queue *dev_queue; struct net_device *dev; int t, s_t; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return 0; dev = dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return 0; s_t = cb->args[0]; t = 0; if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc), skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_tclass_root(rtnl_dereference(dev_queue->qdisc_sleeping), skb, tcm, cb, &t, s_t, false) < 0) goto done; done: cb->args[0] = t; dev_put(dev); return skb->len; } #ifdef CONFIG_PROC_FS static int psched_show(struct seq_file *seq, void *v) { seq_printf(seq, "%08x %08x %08x %08x\n", (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1), 1000000, (u32)NSEC_PER_SEC / hrtimer_resolution); return 0; } static int __net_init psched_net_init(struct net *net) { struct proc_dir_entry *e; e = proc_create_single("psched", 0, net->proc_net, psched_show); if (e == NULL) return -ENOMEM; return 0; } static void __net_exit psched_net_exit(struct net *net) { remove_proc_entry("psched", net->proc_net); } #else static int __net_init psched_net_init(struct net *net) { return 0; } static void __net_exit psched_net_exit(struct net *net) { } #endif static struct pernet_operations psched_net_ops = { .init = psched_net_init, .exit = psched_net_exit, }; #if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper); #endif static int __init pktsched_init(void) { int err; err = register_pernet_subsys(&psched_net_ops); if (err) { pr_err("pktsched_init: " "cannot initialize per netns operations\n"); return err; } register_qdisc(&pfifo_fast_ops); register_qdisc(&pfifo_qdisc_ops); register_qdisc(&bfifo_qdisc_ops); register_qdisc(&pfifo_head_drop_qdisc_ops); register_qdisc(&mq_qdisc_ops); register_qdisc(&noqueue_qdisc_ops); rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, 0); rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, 0); tc_wrapper_init(); return 0; } subsys_initcall(pktsched_init); |
| 3 3 20 2 18 9 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 | // SPDX-License-Identifier: GPL-2.0-only /* * test/set flag bits stored in conntrack extension area. * * (C) 2013 Astaro GmbH & Co KG */ #include <linux/export.h> #include <linux/types.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h> static int replace_u32(u32 *address, u32 mask, u32 new) { u32 old, tmp; do { old = *address; tmp = (old & mask) ^ new; if (old == tmp) return 0; } while (cmpxchg(address, old, tmp) != old); return 1; } int nf_connlabels_replace(struct nf_conn *ct, const u32 *data, const u32 *mask, unsigned int words32) { struct nf_conn_labels *labels; unsigned int size, i; int changed = 0; u32 *dst; labels = nf_ct_labels_find(ct); if (!labels) return -ENOSPC; size = sizeof(labels->bits); if (size < (words32 * sizeof(u32))) words32 = size / sizeof(u32); dst = (u32 *) labels->bits; for (i = 0; i < words32; i++) changed |= replace_u32(&dst[i], mask ? ~mask[i] : 0, data[i]); size /= sizeof(u32); for (i = words32; i < size; i++) /* pad */ replace_u32(&dst[i], 0, 0); if (changed) nf_conntrack_event_cache(IPCT_LABEL, ct); return 0; } EXPORT_SYMBOL_GPL(nf_connlabels_replace); int nf_connlabels_get(struct net *net, unsigned int bits) { int v; if (BIT_WORD(bits) >= NF_CT_LABELS_MAX_SIZE / sizeof(long)) return -ERANGE; BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX); v = atomic_inc_return_relaxed(&net->ct.labels_used); WARN_ON_ONCE(v <= 0); return 0; } EXPORT_SYMBOL_GPL(nf_connlabels_get); void nf_connlabels_put(struct net *net) { int v = atomic_dec_return_relaxed(&net->ct.labels_used); WARN_ON_ONCE(v < 0); } EXPORT_SYMBOL_GPL(nf_connlabels_put); |
| 19 255 237 19 1 16 10 10 1 1 1 1 2 2 16 16 3 3 76 60 16 16 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 | // SPDX-License-Identifier: GPL-2.0 /* * Author: Andrei Vagin <avagin@openvz.org> * Author: Dmitry Safonov <dima@arista.com> */ #include <linux/time_namespace.h> #include <linux/user_namespace.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/clocksource.h> #include <linux/seq_file.h> #include <linux/proc_ns.h> #include <linux/export.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/err.h> #include <linux/mm.h> #include <vdso/datapage.h> ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, struct timens_offsets *ns_offsets) { ktime_t offset; switch (clockid) { case CLOCK_MONOTONIC: offset = timespec64_to_ktime(ns_offsets->monotonic); break; case CLOCK_BOOTTIME: case CLOCK_BOOTTIME_ALARM: offset = timespec64_to_ktime(ns_offsets->boottime); break; default: return tim; } /* * Check that @tim value is in [offset, KTIME_MAX + offset] * and subtract offset. */ if (tim < offset) { /* * User can specify @tim *absolute* value - if it's lesser than * the time namespace's offset - it's already expired. */ tim = 0; } else { tim = ktime_sub(tim, offset); if (unlikely(tim > KTIME_MAX)) tim = KTIME_MAX; } return tim; } static struct ucounts *inc_time_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES); } static void dec_time_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES); } /** * clone_time_ns - Clone a time namespace * @user_ns: User namespace which owns a new namespace. * @old_ns: Namespace to clone * * Clone @old_ns and set the clone refcount to 1 * * Return: The new namespace or ERR_PTR. */ static struct time_namespace *clone_time_ns(struct user_namespace *user_ns, struct time_namespace *old_ns) { struct time_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; ucounts = inc_time_namespaces(user_ns); if (!ucounts) goto fail; err = -ENOMEM; ns = kmalloc(sizeof(*ns), GFP_KERNEL_ACCOUNT); if (!ns) goto fail_dec; refcount_set(&ns->ns.count, 1); ns->vvar_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!ns->vvar_page) goto fail_free; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free_page; ns->ucounts = ucounts; ns->ns.ops = &timens_operations; ns->user_ns = get_user_ns(user_ns); ns->offsets = old_ns->offsets; ns->frozen_offsets = false; return ns; fail_free_page: __free_page(ns->vvar_page); fail_free: kfree(ns); fail_dec: dec_time_namespaces(ucounts); fail: return ERR_PTR(err); } /** * copy_time_ns - Create timens_for_children from @old_ns * @flags: Cloning flags * @user_ns: User namespace which owns a new namespace. * @old_ns: Namespace to clone * * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children; * adds a refcounter to @old_ns otherwise. * * Return: timens_for_children namespace or ERR_PTR. */ struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { if (!(flags & CLONE_NEWTIME)) return get_time_ns(old_ns); return clone_time_ns(user_ns, old_ns); } static struct timens_offset offset_from_ts(struct timespec64 off) { struct timens_offset ret; ret.sec = off.tv_sec; ret.nsec = off.tv_nsec; return ret; } /* * A time namespace VVAR page has the same layout as the VVAR page which * contains the system wide VDSO data. * * For a normal task the VVAR pages are installed in the normal ordering: * VVAR * PVCLOCK * HVCLOCK * TIMENS <- Not really required * * Now for a timens task the pages are installed in the following order: * TIMENS * PVCLOCK * HVCLOCK * VVAR * * The check for vdso_data->clock_mode is in the unlikely path of * the seq begin magic. So for the non-timens case most of the time * 'seq' is even, so the branch is not taken. * * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the * update to finish and for 'seq' to become even anyway. * * Timens page has vdso_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which * enforces the time namespace handling path. */ static void timens_setup_vdso_data(struct vdso_data *vdata, struct time_namespace *ns) { struct timens_offset *offset = vdata->offset; struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic); struct timens_offset boottime = offset_from_ts(ns->offsets.boottime); vdata->seq = 1; vdata->clock_mode = VDSO_CLOCKMODE_TIMENS; offset[CLOCK_MONOTONIC] = monotonic; offset[CLOCK_MONOTONIC_RAW] = monotonic; offset[CLOCK_MONOTONIC_COARSE] = monotonic; offset[CLOCK_BOOTTIME] = boottime; offset[CLOCK_BOOTTIME_ALARM] = boottime; } struct page *find_timens_vvar_page(struct vm_area_struct *vma) { if (likely(vma->vm_mm == current->mm)) return current->nsproxy->time_ns->vvar_page; /* * VM_PFNMAP | VM_IO protect .fault() handler from being called * through interfaces like /proc/$pid/mem or * process_vm_{readv,writev}() as long as there's no .access() * in special_mapping_vmops(). * For more details check_vma_flags() and __access_remote_vm() */ WARN(1, "vvar_page accessed remotely"); return NULL; } /* * Protects possibly multiple offsets writers racing each other * and tasks entering the namespace. */ static DEFINE_MUTEX(offset_lock); static void timens_set_vvar_page(struct task_struct *task, struct time_namespace *ns) { struct vdso_data *vdata; unsigned int i; if (ns == &init_time_ns) return; /* Fast-path, taken by every task in namespace except the first. */ if (likely(ns->frozen_offsets)) return; mutex_lock(&offset_lock); /* Nothing to-do: vvar_page has been already initialized. */ if (ns->frozen_offsets) goto out; ns->frozen_offsets = true; vdata = arch_get_vdso_data(page_address(ns->vvar_page)); for (i = 0; i < CS_BASES; i++) timens_setup_vdso_data(&vdata[i], ns); out: mutex_unlock(&offset_lock); } void free_time_ns(struct time_namespace *ns) { dec_time_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); __free_page(ns->vvar_page); kfree(ns); } static struct time_namespace *to_time_ns(struct ns_common *ns) { return container_of(ns, struct time_namespace, ns); } static struct ns_common *timens_get(struct task_struct *task) { struct time_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->time_ns; get_time_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static struct ns_common *timens_for_children_get(struct task_struct *task) { struct time_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->time_ns_for_children; get_time_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void timens_put(struct ns_common *ns) { put_time_ns(to_time_ns(ns)); } void timens_commit(struct task_struct *tsk, struct time_namespace *ns) { timens_set_vvar_page(tsk, ns); vdso_join_timens(tsk, ns); } static int timens_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct time_namespace *ns = to_time_ns(new); if (!current_is_single_threaded()) return -EUSERS; if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; get_time_ns(ns); put_time_ns(nsproxy->time_ns); nsproxy->time_ns = ns; get_time_ns(ns); put_time_ns(nsproxy->time_ns_for_children); nsproxy->time_ns_for_children = ns; return 0; } void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { struct ns_common *nsc = &nsproxy->time_ns_for_children->ns; struct time_namespace *ns = to_time_ns(nsc); /* create_new_namespaces() already incremented the ref counter */ if (nsproxy->time_ns == nsproxy->time_ns_for_children) return; get_time_ns(ns); put_time_ns(nsproxy->time_ns); nsproxy->time_ns = ns; timens_commit(tsk, ns); } static struct user_namespace *timens_owner(struct ns_common *ns) { return to_time_ns(ns)->user_ns; } static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts) { char *clock; switch (clockid) { case CLOCK_BOOTTIME: clock = "boottime"; break; case CLOCK_MONOTONIC: clock = "monotonic"; break; default: clock = "unknown"; break; } seq_printf(m, "%-10s %10lld %9ld\n", clock, ts->tv_sec, ts->tv_nsec); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m) { struct ns_common *ns; struct time_namespace *time_ns; ns = timens_for_children_get(p); if (!ns) return; time_ns = to_time_ns(ns); show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic); show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime); put_time_ns(time_ns); } int proc_timens_set_offset(struct file *file, struct task_struct *p, struct proc_timens_offset *offsets, int noffsets) { struct ns_common *ns; struct time_namespace *time_ns; struct timespec64 tp; int i, err; ns = timens_for_children_get(p); if (!ns) return -ESRCH; time_ns = to_time_ns(ns); if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME)) { put_time_ns(time_ns); return -EPERM; } for (i = 0; i < noffsets; i++) { struct proc_timens_offset *off = &offsets[i]; switch (off->clockid) { case CLOCK_MONOTONIC: ktime_get_ts64(&tp); break; case CLOCK_BOOTTIME: ktime_get_boottime_ts64(&tp); break; default: err = -EINVAL; goto out; } err = -ERANGE; if (off->val.tv_sec > KTIME_SEC_MAX || off->val.tv_sec < -KTIME_SEC_MAX) goto out; tp = timespec64_add(tp, off->val); /* * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is * still unreachable. */ if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2) goto out; } mutex_lock(&offset_lock); if (time_ns->frozen_offsets) { err = -EACCES; goto out_unlock; } err = 0; /* Don't report errors after this line */ for (i = 0; i < noffsets; i++) { struct proc_timens_offset *off = &offsets[i]; struct timespec64 *offset = NULL; switch (off->clockid) { case CLOCK_MONOTONIC: offset = &time_ns->offsets.monotonic; break; case CLOCK_BOOTTIME: offset = &time_ns->offsets.boottime; break; } *offset = off->val; } out_unlock: mutex_unlock(&offset_lock); out: put_time_ns(time_ns); return err; } const struct proc_ns_operations timens_operations = { .name = "time", .type = CLONE_NEWTIME, .get = timens_get, .put = timens_put, .install = timens_install, .owner = timens_owner, }; const struct proc_ns_operations timens_for_children_operations = { .name = "time_for_children", .real_ns_name = "time", .type = CLONE_NEWTIME, .get = timens_for_children_get, .put = timens_put, .install = timens_install, .owner = timens_owner, }; struct time_namespace init_time_ns = { .ns.count = REFCOUNT_INIT(3), .user_ns = &init_user_ns, .ns.inum = PROC_TIME_INIT_INO, .ns.ops = &timens_operations, .frozen_offsets = true, }; |
| 22 14 18 12 5 10 12 10 9 10 9 23 13 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_inode_item.h" #include <linux/iversion.h> /* * Add a locked inode to the transaction. * * The inode must be locked, and it cannot be associated with any transaction. * If lock_flags is non-zero the inode will be unlocked on transaction commit. */ void xfs_trans_ijoin( struct xfs_trans *tp, struct xfs_inode *ip, uint lock_flags) { struct xfs_inode_log_item *iip; xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); if (ip->i_itemp == NULL) xfs_inode_item_init(ip, ip->i_mount); iip = ip->i_itemp; ASSERT(iip->ili_lock_flags == 0); iip->ili_lock_flags = lock_flags; ASSERT(!xfs_iflags_test(ip, XFS_ISTALE)); /* Reset the per-tx dirty context and add the item to the tx. */ iip->ili_dirty_flags = 0; xfs_trans_add_item(tp, &iip->ili_item); } /* * Transactional inode timestamp update. Requires the inode to be locked and * joined to the transaction supplied. Relies on the transaction subsystem to * track dirty state and update/writeback the inode accordingly. */ void xfs_trans_ichgtime( struct xfs_trans *tp, struct xfs_inode *ip, int flags) { struct inode *inode = VFS_I(ip); struct timespec64 tv; ASSERT(tp); xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); tv = current_time(inode); if (flags & XFS_ICHGTIME_MOD) inode_set_mtime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_CHG) inode_set_ctime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_ACCESS) inode_set_atime_to_ts(inode, tv); if (flags & XFS_ICHGTIME_CREATE) ip->i_crtime = tv; } /* * This is called to mark the fields indicated in fieldmask as needing to be * logged when the transaction is committed. The inode must already be * associated with the given transaction. All we do here is record where the * inode was dirtied and mark the transaction and inode log item dirty; * everything else is done in the ->precommit log item operation after the * changes in the transaction have been completed. */ void xfs_trans_log_inode( struct xfs_trans *tp, struct xfs_inode *ip, uint flags) { struct xfs_inode_log_item *iip = ip->i_itemp; struct inode *inode = VFS_I(ip); ASSERT(iip); xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); ASSERT(!xfs_iflags_test(ip, XFS_ISTALE)); tp->t_flags |= XFS_TRANS_DIRTY; /* * First time we log the inode in a transaction, bump the inode change * counter if it is configured for this to occur. While we have the * inode locked exclusively for metadata modification, we can usually * avoid setting XFS_ILOG_CORE if no one has queried the value since * the last time it was incremented. If we have XFS_ILOG_CORE already * set however, then go ahead and bump the i_version counter * unconditionally. */ if (!test_and_set_bit(XFS_LI_DIRTY, &iip->ili_item.li_flags)) { if (IS_I_VERSION(inode) && inode_maybe_inc_iversion(inode, flags & XFS_ILOG_CORE)) flags |= XFS_ILOG_IVERSION; } iip->ili_dirty_flags |= flags; } int xfs_trans_roll_inode( struct xfs_trans **tpp, struct xfs_inode *ip) { int error; xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE); error = xfs_trans_roll(tpp); if (!error) xfs_trans_ijoin(*tpp, ip, 0); return error; } |
| 35 33 12 32 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 | /* * net/tipc/discover.c * * Copyright (c) 2003-2006, 2014-2018, Ericsson AB * Copyright (c) 2005-2006, 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 "core.h" #include "node.h" #include "discover.h" /* min delay during bearer start up */ #define TIPC_DISC_INIT msecs_to_jiffies(125) /* max delay if bearer has no links */ #define TIPC_DISC_FAST msecs_to_jiffies(1000) /* max delay if bearer has links */ #define TIPC_DISC_SLOW msecs_to_jiffies(60000) /* indicates no timer in use */ #define TIPC_DISC_INACTIVE 0xffffffff /** * struct tipc_discoverer - information about an ongoing link setup request * @bearer_id: identity of bearer issuing requests * @net: network namespace instance * @dest: destination address for request messages * @domain: network domain to which links can be established * @num_nodes: number of nodes currently discovered (i.e. with an active link) * @lock: spinlock for controlling access to requests * @skb: request message to be (repeatedly) sent * @timer: timer governing period between requests * @timer_intv: current interval between requests (in ms) */ struct tipc_discoverer { u32 bearer_id; struct tipc_media_addr dest; struct net *net; u32 domain; int num_nodes; spinlock_t lock; struct sk_buff *skb; struct timer_list timer; unsigned long timer_intv; }; /** * tipc_disc_init_msg - initialize a link setup message * @net: the applicable net namespace * @skb: buffer containing message * @mtyp: message type (request or response) * @b: ptr to bearer issuing message */ static void tipc_disc_init_msg(struct net *net, struct sk_buff *skb, u32 mtyp, struct tipc_bearer *b) { struct tipc_net *tn = tipc_net(net); u32 dest_domain = b->domain; struct tipc_msg *hdr; hdr = buf_msg(skb); tipc_msg_init(tn->trial_addr, hdr, LINK_CONFIG, mtyp, MAX_H_SIZE, dest_domain); msg_set_size(hdr, MAX_H_SIZE + NODE_ID_LEN); msg_set_non_seq(hdr, 1); msg_set_node_sig(hdr, tn->random); msg_set_node_capabilities(hdr, TIPC_NODE_CAPABILITIES); msg_set_dest_domain(hdr, dest_domain); msg_set_bc_netid(hdr, tn->net_id); b->media->addr2msg(msg_media_addr(hdr), &b->addr); msg_set_peer_net_hash(hdr, tipc_net_hash_mixes(net, tn->random)); msg_set_node_id(hdr, tipc_own_id(net)); } static void tipc_disc_msg_xmit(struct net *net, u32 mtyp, u32 dst, u32 src, u32 sugg_addr, struct tipc_media_addr *maddr, struct tipc_bearer *b) { struct tipc_msg *hdr; struct sk_buff *skb; skb = tipc_buf_acquire(MAX_H_SIZE + NODE_ID_LEN, GFP_ATOMIC); if (!skb) return; hdr = buf_msg(skb); tipc_disc_init_msg(net, skb, mtyp, b); msg_set_sugg_node_addr(hdr, sugg_addr); msg_set_dest_domain(hdr, dst); tipc_bearer_xmit_skb(net, b->identity, skb, maddr); } /** * disc_dupl_alert - issue node address duplication alert * @b: pointer to bearer detecting duplication * @node_addr: duplicated node address * @media_addr: media address advertised by duplicated node */ static void disc_dupl_alert(struct tipc_bearer *b, u32 node_addr, struct tipc_media_addr *media_addr) { char media_addr_str[64]; tipc_media_addr_printf(media_addr_str, sizeof(media_addr_str), media_addr); pr_warn("Duplicate %x using %s seen on <%s>\n", node_addr, media_addr_str, b->name); } /* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer * Returns true if message should be dropped by caller, i.e., if it is a * trial message or we are inside trial period. Otherwise false. */ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, struct tipc_media_addr *maddr, struct tipc_bearer *b, u32 dst, u32 src, u32 sugg_addr, u8 *peer_id, int mtyp) { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); u32 self = tipc_own_addr(net); bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) return true; /* Ignore if somebody else already gave new suggestion */ if (dst != tn->trial_addr) return true; /* Otherwise update trial address and restart trial period */ tn->trial_addr = sugg_addr; msg_set_prevnode(buf_msg(d->skb), sugg_addr); tn->addr_trial_end = jiffies + msecs_to_jiffies(1000); return true; } /* Apply trial address if we just left trial period */ if (!trial && !self) { schedule_work(&tn->work); msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } /* Accept regular link requests/responses only after trial period */ if (mtyp != DSC_TRIAL_MSG) return trial; sugg_addr = tipc_node_try_addr(net, peer_id, src); if (sugg_addr) tipc_disc_msg_xmit(net, DSC_TRIAL_FAIL_MSG, src, self, sugg_addr, maddr, b); return true; } /** * tipc_disc_rcv - handle incoming discovery message (request or response) * @net: applicable net namespace * @skb: buffer containing message * @b: bearer that message arrived on */ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) { struct tipc_net *tn = tipc_net(net); struct tipc_msg *hdr = buf_msg(skb); u32 pnet_hash = msg_peer_net_hash(hdr); u16 caps = msg_node_capabilities(hdr); bool legacy = tn->legacy_addr_format; u32 sugg = msg_sugg_node_addr(hdr); u32 signature = msg_node_sig(hdr); u8 peer_id[NODE_ID_LEN] = {0,}; u32 dst = msg_dest_domain(hdr); u32 net_id = msg_bc_netid(hdr); struct tipc_media_addr maddr; u32 src = msg_prevnode(hdr); u32 mtyp = msg_type(hdr); bool dupl_addr = false; bool respond = false; u32 self; int err; if (skb_linearize(skb)) { kfree_skb(skb); return; } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) memcpy(peer_id, msg_node_id(hdr), NODE_ID_LEN); else sprintf(peer_id, "%x", src); err = b->media->msg2addr(b, &maddr, msg_media_addr(hdr)); kfree_skb(skb); if (err || maddr.broadcast) { pr_warn_ratelimited("Rcv corrupt discovery message\n"); return; } /* Ignore discovery messages from own node */ if (!memcmp(&maddr, &b->addr, sizeof(maddr))) return; if (net_id != tn->net_id) return; if (tipc_disc_addr_trial_msg(b->disc, &maddr, b, dst, src, sugg, peer_id, mtyp)) return; self = tipc_own_addr(net); /* Message from somebody using this node's address */ if (in_own_node(net, src)) { disc_dupl_alert(b, self, &maddr); return; } if (!tipc_in_scope(legacy, dst, self)) return; if (!tipc_in_scope(legacy, b->domain, src)) return; tipc_node_check_dest(net, src, peer_id, b, caps, signature, pnet_hash, &maddr, &respond, &dupl_addr); if (dupl_addr) disc_dupl_alert(b, src, &maddr); if (!respond) return; if (mtyp != DSC_REQ_MSG) return; tipc_disc_msg_xmit(net, DSC_RESP_MSG, src, self, 0, &maddr, b); } /* tipc_disc_add_dest - increment set of discovered nodes */ void tipc_disc_add_dest(struct tipc_discoverer *d) { spin_lock_bh(&d->lock); d->num_nodes++; spin_unlock_bh(&d->lock); } /* tipc_disc_remove_dest - decrement set of discovered nodes */ void tipc_disc_remove_dest(struct tipc_discoverer *d) { int intv, num; spin_lock_bh(&d->lock); d->num_nodes--; num = d->num_nodes; intv = d->timer_intv; if (!num && (intv == TIPC_DISC_INACTIVE || intv > TIPC_DISC_FAST)) { d->timer_intv = TIPC_DISC_INIT; mod_timer(&d->timer, jiffies + d->timer_intv); } spin_unlock_bh(&d->lock); } /* tipc_disc_timeout - send a periodic link setup request * Called whenever a link setup request timer associated with a bearer expires. * - Keep doubling time between sent request until limit is reached; * - Hold at fast polling rate if we don't have any associated nodes * - Otherwise hold at slow polling rate */ static void tipc_disc_timeout(struct timer_list *t) { struct tipc_discoverer *d = from_timer(d, t, timer); struct tipc_net *tn = tipc_net(d->net); struct tipc_media_addr maddr; struct sk_buff *skb = NULL; struct net *net = d->net; u32 bearer_id; spin_lock_bh(&d->lock); /* Stop searching if only desired node has been found */ if (tipc_node(d->domain) && d->num_nodes) { d->timer_intv = TIPC_DISC_INACTIVE; goto exit; } /* Did we just leave trial period ? */ if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) { mod_timer(&d->timer, jiffies + TIPC_DISC_INIT); spin_unlock_bh(&d->lock); schedule_work(&tn->work); return; } /* Adjust timeout interval according to discovery phase */ if (time_before(jiffies, tn->addr_trial_end)) { d->timer_intv = TIPC_DISC_INIT; } else { d->timer_intv *= 2; if (d->num_nodes && d->timer_intv > TIPC_DISC_SLOW) d->timer_intv = TIPC_DISC_SLOW; else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST) d->timer_intv = TIPC_DISC_FAST; msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); msg_set_prevnode(buf_msg(d->skb), tn->trial_addr); } mod_timer(&d->timer, jiffies + d->timer_intv); memcpy(&maddr, &d->dest, sizeof(maddr)); skb = skb_clone(d->skb, GFP_ATOMIC); bearer_id = d->bearer_id; exit: spin_unlock_bh(&d->lock); if (skb) tipc_bearer_xmit_skb(net, bearer_id, skb, &maddr); } /** * tipc_disc_create - create object to send periodic link setup requests * @net: the applicable net namespace * @b: ptr to bearer issuing requests * @dest: destination address for request messages * @skb: pointer to created frame * * Return: 0 if successful, otherwise -errno. */ int tipc_disc_create(struct net *net, struct tipc_bearer *b, struct tipc_media_addr *dest, struct sk_buff **skb) { struct tipc_net *tn = tipc_net(net); struct tipc_discoverer *d; d = kmalloc(sizeof(*d), GFP_ATOMIC); if (!d) return -ENOMEM; d->skb = tipc_buf_acquire(MAX_H_SIZE + NODE_ID_LEN, GFP_ATOMIC); if (!d->skb) { kfree(d); return -ENOMEM; } tipc_disc_init_msg(net, d->skb, DSC_REQ_MSG, b); /* Do we need an address trial period first ? */ if (!tipc_own_addr(net)) { tn->addr_trial_end = jiffies + msecs_to_jiffies(1000); msg_set_type(buf_msg(d->skb), DSC_TRIAL_MSG); } memcpy(&d->dest, dest, sizeof(*dest)); d->net = net; d->bearer_id = b->identity; d->domain = b->domain; d->num_nodes = 0; d->timer_intv = TIPC_DISC_INIT; spin_lock_init(&d->lock); timer_setup(&d->timer, tipc_disc_timeout, 0); mod_timer(&d->timer, jiffies + d->timer_intv); b->disc = d; *skb = skb_clone(d->skb, GFP_ATOMIC); return 0; } /** * tipc_disc_delete - destroy object sending periodic link setup requests * @d: ptr to link dest structure */ void tipc_disc_delete(struct tipc_discoverer *d) { timer_shutdown_sync(&d->timer); kfree_skb(d->skb); kfree(d); } /** * tipc_disc_reset - reset object to send periodic link setup requests * @net: the applicable net namespace * @b: ptr to bearer issuing requests */ void tipc_disc_reset(struct net *net, struct tipc_bearer *b) { struct tipc_discoverer *d = b->disc; struct tipc_media_addr maddr; struct sk_buff *skb; spin_lock_bh(&d->lock); tipc_disc_init_msg(net, d->skb, DSC_REQ_MSG, b); d->net = net; d->bearer_id = b->identity; d->domain = b->domain; d->num_nodes = 0; d->timer_intv = TIPC_DISC_INIT; memcpy(&maddr, &d->dest, sizeof(maddr)); mod_timer(&d->timer, jiffies + d->timer_intv); skb = skb_clone(d->skb, GFP_ATOMIC); spin_unlock_bh(&d->lock); if (skb) tipc_bearer_xmit_skb(net, b->identity, skb, &maddr); } |
| 151 204 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NLS_H #define _LINUX_NLS_H #include <linux/init.h> /* Unicode has changed over the years. Unicode code points no longer * fit into 16 bits; as of Unicode 5 valid code points range from 0 * to 0x10ffff (17 planes, where each plane holds 65536 code points). * * The original decision to represent Unicode characters as 16-bit * wchar_t values is now outdated. But plane 0 still includes the * most commonly used characters, so we will retain it. The newer * 32-bit unicode_t type can be used when it is necessary to * represent the full Unicode character set. */ /* Plane-0 Unicode character */ typedef u16 wchar_t; #define MAX_WCHAR_T 0xffff /* Arbitrary Unicode character */ typedef u32 unicode_t; struct nls_table { const char *charset; const char *alias; int (*uni2char) (wchar_t uni, unsigned char *out, int boundlen); int (*char2uni) (const unsigned char *rawstring, int boundlen, wchar_t *uni); const unsigned char *charset2lower; const unsigned char *charset2upper; struct module *owner; struct nls_table *next; }; /* this value hold the maximum octet of charset */ #define NLS_MAX_CHARSET_SIZE 6 /* for UTF-8 */ /* Byte order for UTF-16 strings */ enum utf16_endian { UTF16_HOST_ENDIAN, UTF16_LITTLE_ENDIAN, UTF16_BIG_ENDIAN }; /* nls_base.c */ extern int __register_nls(struct nls_table *, struct module *); extern int unregister_nls(struct nls_table *); extern struct nls_table *load_nls(const char *charset); extern void unload_nls(struct nls_table *); extern struct nls_table *load_nls_default(void); #define register_nls(nls) __register_nls((nls), THIS_MODULE) extern int utf8_to_utf32(const u8 *s, int len, unicode_t *pu); extern int utf32_to_utf8(unicode_t u, u8 *s, int maxlen); extern int utf8s_to_utf16s(const u8 *s, int len, enum utf16_endian endian, wchar_t *pwcs, int maxlen); extern int utf16s_to_utf8s(const wchar_t *pwcs, int len, enum utf16_endian endian, u8 *s, int maxlen); static inline unsigned char nls_tolower(struct nls_table *t, unsigned char c) { unsigned char nc = t->charset2lower[c]; return nc ? nc : c; } static inline unsigned char nls_toupper(struct nls_table *t, unsigned char c) { unsigned char nc = t->charset2upper[c]; return nc ? nc : c; } static inline int nls_strnicmp(struct nls_table *t, const unsigned char *s1, const unsigned char *s2, int len) { while (len--) { if (nls_tolower(t, *s1++) != nls_tolower(t, *s2++)) return 1; } return 0; } /* * nls_nullsize - return length of null character for codepage * @codepage - codepage for which to return length of NULL terminator * * Since we can't guarantee that the null terminator will be a particular * length, we have to check against the codepage. If there's a problem * determining it, assume a single-byte NULL terminator. */ static inline int nls_nullsize(const struct nls_table *codepage) { int charlen; char tmp[NLS_MAX_CHARSET_SIZE]; charlen = codepage->uni2char(0, tmp, NLS_MAX_CHARSET_SIZE); return charlen > 0 ? charlen : 1; } #define MODULE_ALIAS_NLS(name) MODULE_ALIAS("nls_" __stringify(name)) #endif /* _LINUX_NLS_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KDEV_T_H #define _LINUX_KDEV_T_H #include <uapi/linux/kdev_t.h> #define MINORBITS 20 #define MINORMASK ((1U << MINORBITS) - 1) #define MAJOR(dev) ((unsigned int) ((dev) >> MINORBITS)) #define MINOR(dev) ((unsigned int) ((dev) & MINORMASK)) #define MKDEV(ma,mi) (((ma) << MINORBITS) | (mi)) #define print_dev_t(buffer, dev) \ sprintf((buffer), "%u:%u\n", MAJOR(dev), MINOR(dev)) #define format_dev_t(buffer, dev) \ ({ \ sprintf(buffer, "%u:%u", MAJOR(dev), MINOR(dev)); \ buffer; \ }) /* acceptable for old filesystems */ static __always_inline bool old_valid_dev(dev_t dev) { return MAJOR(dev) < 256 && MINOR(dev) < 256; } static __always_inline u16 old_encode_dev(dev_t dev) { return (MAJOR(dev) << 8) | MINOR(dev); } static __always_inline dev_t old_decode_dev(u16 val) { return MKDEV((val >> 8) & 255, val & 255); } static __always_inline u32 new_encode_dev(dev_t dev) { unsigned major = MAJOR(dev); unsigned minor = MINOR(dev); return (minor & 0xff) | (major << 8) | ((minor & ~0xff) << 12); } static __always_inline dev_t new_decode_dev(u32 dev) { unsigned major = (dev & 0xfff00) >> 8; unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00); return MKDEV(major, minor); } static __always_inline u64 huge_encode_dev(dev_t dev) { return new_encode_dev(dev); } static __always_inline dev_t huge_decode_dev(u64 dev) { return new_decode_dev(dev); } static __always_inline int sysv_valid_dev(dev_t dev) { return MAJOR(dev) < (1<<14) && MINOR(dev) < (1<<18); } static __always_inline u32 sysv_encode_dev(dev_t dev) { return MINOR(dev) | (MAJOR(dev) << 18); } static __always_inline unsigned sysv_major(u32 dev) { return (dev >> 18) & 0x3fff; } static __always_inline unsigned sysv_minor(u32 dev) { return dev & 0x3ffff; } #endif |
| 9 1 2 11 77 78 11 77 35 30 5 30 22 7 14 2 17 9 10 101 95 1 6 72 3 69 63 9 89 77 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock LSM - Ptrace hooks * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2019-2020 ANSSI */ #include <asm/current.h> #include <linux/cred.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <net/af_unix.h> #include <net/sock.h> #include "common.h" #include "cred.h" #include "fs.h" #include "ruleset.h" #include "setup.h" #include "task.h" /** * domain_scope_le - Checks domain ordering for scoped ptrace * * @parent: Parent domain. * @child: Potential child of @parent. * * Checks if the @parent domain is less or equal to (i.e. an ancestor, which * means a subset of) the @child domain. */ static bool domain_scope_le(const struct landlock_ruleset *const parent, const struct landlock_ruleset *const child) { const struct landlock_hierarchy *walker; if (!parent) return true; if (!child) return false; for (walker = child->hierarchy; walker; walker = walker->parent) { if (walker == parent->hierarchy) /* @parent is in the scoped hierarchy of @child. */ return true; } /* There is no relationship between @parent and @child. */ return false; } static bool task_is_scoped(const struct task_struct *const parent, const struct task_struct *const child) { bool is_scoped; const struct landlock_ruleset *dom_parent, *dom_child; rcu_read_lock(); dom_parent = landlock_get_task_domain(parent); dom_child = landlock_get_task_domain(child); is_scoped = domain_scope_le(dom_parent, dom_child); rcu_read_unlock(); return is_scoped; } static int task_ptrace(const struct task_struct *const parent, const struct task_struct *const child) { /* Quick return for non-landlocked tasks. */ if (!landlocked(parent)) return 0; if (task_is_scoped(parent, child)) return 0; return -EPERM; } /** * hook_ptrace_access_check - Determines whether the current process may access * another * * @child: Process to be accessed. * @mode: Mode of attachment. * * If the current task has Landlock rules, then the child must have at least * the same rules. Else denied. * * Determines whether a process may access another, returning 0 if permission * granted, -errno if denied. */ static int hook_ptrace_access_check(struct task_struct *const child, const unsigned int mode) { return task_ptrace(current, child); } /** * hook_ptrace_traceme - Determines whether another process may trace the * current one * * @parent: Task proposed to be the tracer. * * If the parent has Landlock rules, then the current task must have the same * or more rules. Else denied. * * Determines whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -errno if denied. */ static int hook_ptrace_traceme(struct task_struct *const parent) { return task_ptrace(parent, current); } /** * domain_is_scoped - Checks if the client domain is scoped in the same * domain as the server. * * @client: IPC sender domain. * @server: IPC receiver domain. * @scope: The scope restriction criteria. * * Returns: True if the @client domain is scoped to access the @server, * unless the @server is also scoped in the same domain as @client. */ static bool domain_is_scoped(const struct landlock_ruleset *const client, const struct landlock_ruleset *const server, access_mask_t scope) { int client_layer, server_layer; struct landlock_hierarchy *client_walker, *server_walker; /* Quick return if client has no domain */ if (WARN_ON_ONCE(!client)) return false; client_layer = client->num_layers - 1; client_walker = client->hierarchy; /* * client_layer must be a signed integer with greater capacity * than client->num_layers to ensure the following loop stops. */ BUILD_BUG_ON(sizeof(client_layer) > sizeof(client->num_layers)); server_layer = server ? (server->num_layers - 1) : -1; server_walker = server ? server->hierarchy : NULL; /* * Walks client's parent domains down to the same hierarchy level * as the server's domain, and checks that none of these client's * parent domains are scoped. */ for (; client_layer > server_layer; client_layer--) { if (landlock_get_scope_mask(client, client_layer) & scope) return true; client_walker = client_walker->parent; } /* * Walks server's parent domains down to the same hierarchy level as * the client's domain. */ for (; server_layer > client_layer; server_layer--) server_walker = server_walker->parent; for (; client_layer >= 0; client_layer--) { if (landlock_get_scope_mask(client, client_layer) & scope) { /* * Client and server are at the same level in the * hierarchy. If the client is scoped, the request is * only allowed if this domain is also a server's * ancestor. */ return server_walker != client_walker; } client_walker = client_walker->parent; server_walker = server_walker->parent; } return false; } static bool sock_is_scoped(struct sock *const other, const struct landlock_ruleset *const domain) { const struct landlock_ruleset *dom_other; /* The credentials will not change. */ lockdep_assert_held(&unix_sk(other)->lock); dom_other = landlock_cred(other->sk_socket->file->f_cred)->domain; return domain_is_scoped(domain, dom_other, LANDLOCK_SCOPE_ABSTRACT_UNIX_SOCKET); } static bool is_abstract_socket(struct sock *const sock) { struct unix_address *addr = unix_sk(sock)->addr; if (!addr) return false; if (addr->len >= offsetof(struct sockaddr_un, sun_path) + 1 && addr->name->sun_path[0] == '\0') return true; return false; } static int hook_unix_stream_connect(struct sock *const sock, struct sock *const other, struct sock *const newsk) { const struct landlock_ruleset *const dom = landlock_get_current_domain(); /* Quick return for non-landlocked tasks. */ if (!dom) return 0; if (is_abstract_socket(other) && sock_is_scoped(other, dom)) return -EPERM; return 0; } static int hook_unix_may_send(struct socket *const sock, struct socket *const other) { const struct landlock_ruleset *const dom = landlock_get_current_domain(); if (!dom) return 0; /* * Checks if this datagram socket was already allowed to be connected * to other. */ if (unix_peer(sock->sk) == other->sk) return 0; if (is_abstract_socket(other->sk) && sock_is_scoped(other->sk, dom)) return -EPERM; return 0; } static int hook_task_kill(struct task_struct *const p, struct kernel_siginfo *const info, const int sig, const struct cred *const cred) { bool is_scoped; const struct landlock_ruleset *dom; if (cred) { /* Dealing with USB IO. */ dom = landlock_cred(cred)->domain; } else { dom = landlock_get_current_domain(); } /* Quick return for non-landlocked tasks. */ if (!dom) return 0; rcu_read_lock(); is_scoped = domain_is_scoped(dom, landlock_get_task_domain(p), LANDLOCK_SCOPE_SIGNAL); rcu_read_unlock(); if (is_scoped) return -EPERM; return 0; } static int hook_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int signum) { const struct landlock_ruleset *dom; bool is_scoped = false; /* Lock already held by send_sigio() and send_sigurg(). */ lockdep_assert_held(&fown->lock); dom = landlock_file(fown->file)->fown_domain; /* Quick return for unowned socket. */ if (!dom) return 0; rcu_read_lock(); is_scoped = domain_is_scoped(dom, landlock_get_task_domain(tsk), LANDLOCK_SCOPE_SIGNAL); rcu_read_unlock(); if (is_scoped) return -EPERM; return 0; } static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, hook_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, hook_ptrace_traceme), LSM_HOOK_INIT(unix_stream_connect, hook_unix_stream_connect), LSM_HOOK_INIT(unix_may_send, hook_unix_may_send), LSM_HOOK_INIT(task_kill, hook_task_kill), LSM_HOOK_INIT(file_send_sigiotask, hook_file_send_sigiotask), }; __init void landlock_add_task_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), &landlock_lsmid); } |
| 5 5 5 2 9 9 9 10 1 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <rdma/rdma_netlink.h> #include <net/addrconf.h> #include "rxe.h" #include "rxe_loc.h" MODULE_AUTHOR("Bob Pearson, Frank Zago, John Groves, Kamal Heib"); MODULE_DESCRIPTION("Soft RDMA transport"); MODULE_LICENSE("Dual BSD/GPL"); /* free resources for a rxe device all objects created for this device must * have been destroyed */ void rxe_dealloc(struct ib_device *ib_dev) { struct rxe_dev *rxe = container_of(ib_dev, struct rxe_dev, ib_dev); rxe_pool_cleanup(&rxe->uc_pool); rxe_pool_cleanup(&rxe->pd_pool); rxe_pool_cleanup(&rxe->ah_pool); rxe_pool_cleanup(&rxe->srq_pool); rxe_pool_cleanup(&rxe->qp_pool); rxe_pool_cleanup(&rxe->cq_pool); rxe_pool_cleanup(&rxe->mr_pool); rxe_pool_cleanup(&rxe->mw_pool); WARN_ON(!RB_EMPTY_ROOT(&rxe->mcg_tree)); if (rxe->tfm) crypto_free_shash(rxe->tfm); mutex_destroy(&rxe->usdev_lock); } /* initialize rxe device parameters */ static void rxe_init_device_param(struct rxe_dev *rxe) { rxe->max_inline_data = RXE_MAX_INLINE_DATA; rxe->attr.vendor_id = RXE_VENDOR_ID; rxe->attr.max_mr_size = RXE_MAX_MR_SIZE; rxe->attr.page_size_cap = RXE_PAGE_SIZE_CAP; rxe->attr.max_qp = RXE_MAX_QP; rxe->attr.max_qp_wr = RXE_MAX_QP_WR; rxe->attr.device_cap_flags = RXE_DEVICE_CAP_FLAGS; rxe->attr.kernel_cap_flags = IBK_ALLOW_USER_UNREG; rxe->attr.max_send_sge = RXE_MAX_SGE; rxe->attr.max_recv_sge = RXE_MAX_SGE; rxe->attr.max_sge_rd = RXE_MAX_SGE_RD; rxe->attr.max_cq = RXE_MAX_CQ; rxe->attr.max_cqe = (1 << RXE_MAX_LOG_CQE) - 1; rxe->attr.max_mr = RXE_MAX_MR; rxe->attr.max_mw = RXE_MAX_MW; rxe->attr.max_pd = RXE_MAX_PD; rxe->attr.max_qp_rd_atom = RXE_MAX_QP_RD_ATOM; rxe->attr.max_res_rd_atom = RXE_MAX_RES_RD_ATOM; rxe->attr.max_qp_init_rd_atom = RXE_MAX_QP_INIT_RD_ATOM; rxe->attr.atomic_cap = IB_ATOMIC_HCA; rxe->attr.max_mcast_grp = RXE_MAX_MCAST_GRP; rxe->attr.max_mcast_qp_attach = RXE_MAX_MCAST_QP_ATTACH; rxe->attr.max_total_mcast_qp_attach = RXE_MAX_TOT_MCAST_QP_ATTACH; rxe->attr.max_ah = RXE_MAX_AH; rxe->attr.max_srq = RXE_MAX_SRQ; rxe->attr.max_srq_wr = RXE_MAX_SRQ_WR; rxe->attr.max_srq_sge = RXE_MAX_SRQ_SGE; rxe->attr.max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN; rxe->attr.max_pkeys = RXE_MAX_PKEYS; rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY; addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid, rxe->ndev->dev_addr); rxe->max_ucontext = RXE_MAX_UCONTEXT; } /* initialize port attributes */ static void rxe_init_port_param(struct rxe_port *port) { port->attr.state = IB_PORT_DOWN; port->attr.max_mtu = IB_MTU_4096; port->attr.active_mtu = IB_MTU_256; port->attr.gid_tbl_len = RXE_PORT_GID_TBL_LEN; port->attr.port_cap_flags = RXE_PORT_PORT_CAP_FLAGS; port->attr.max_msg_sz = RXE_PORT_MAX_MSG_SZ; port->attr.bad_pkey_cntr = RXE_PORT_BAD_PKEY_CNTR; port->attr.qkey_viol_cntr = RXE_PORT_QKEY_VIOL_CNTR; port->attr.pkey_tbl_len = RXE_PORT_PKEY_TBL_LEN; port->attr.lid = RXE_PORT_LID; port->attr.sm_lid = RXE_PORT_SM_LID; port->attr.lmc = RXE_PORT_LMC; port->attr.max_vl_num = RXE_PORT_MAX_VL_NUM; port->attr.sm_sl = RXE_PORT_SM_SL; port->attr.subnet_timeout = RXE_PORT_SUBNET_TIMEOUT; port->attr.init_type_reply = RXE_PORT_INIT_TYPE_REPLY; port->attr.active_width = RXE_PORT_ACTIVE_WIDTH; port->attr.active_speed = RXE_PORT_ACTIVE_SPEED; port->attr.phys_state = RXE_PORT_PHYS_STATE; port->mtu_cap = ib_mtu_enum_to_int(IB_MTU_256); port->subnet_prefix = cpu_to_be64(RXE_PORT_SUBNET_PREFIX); } /* initialize port state, note IB convention that HCA ports are always * numbered from 1 */ static void rxe_init_ports(struct rxe_dev *rxe) { struct rxe_port *port = &rxe->port; rxe_init_port_param(port); addrconf_addr_eui48((unsigned char *)&port->port_guid, rxe->ndev->dev_addr); spin_lock_init(&port->port_lock); } /* init pools of managed objects */ static void rxe_init_pools(struct rxe_dev *rxe) { rxe_pool_init(rxe, &rxe->uc_pool, RXE_TYPE_UC); rxe_pool_init(rxe, &rxe->pd_pool, RXE_TYPE_PD); rxe_pool_init(rxe, &rxe->ah_pool, RXE_TYPE_AH); rxe_pool_init(rxe, &rxe->srq_pool, RXE_TYPE_SRQ); rxe_pool_init(rxe, &rxe->qp_pool, RXE_TYPE_QP); rxe_pool_init(rxe, &rxe->cq_pool, RXE_TYPE_CQ); rxe_pool_init(rxe, &rxe->mr_pool, RXE_TYPE_MR); rxe_pool_init(rxe, &rxe->mw_pool, RXE_TYPE_MW); } /* initialize rxe device state */ static void rxe_init(struct rxe_dev *rxe) { /* init default device parameters */ rxe_init_device_param(rxe); rxe_init_ports(rxe); rxe_init_pools(rxe); /* init pending mmap list */ spin_lock_init(&rxe->mmap_offset_lock); spin_lock_init(&rxe->pending_lock); INIT_LIST_HEAD(&rxe->pending_mmaps); /* init multicast support */ spin_lock_init(&rxe->mcg_lock); rxe->mcg_tree = RB_ROOT; mutex_init(&rxe->usdev_lock); } void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu) { struct rxe_port *port = &rxe->port; enum ib_mtu mtu; mtu = eth_mtu_int_to_enum(ndev_mtu); /* Make sure that new MTU in range */ mtu = mtu ? min_t(enum ib_mtu, mtu, IB_MTU_4096) : IB_MTU_256; port->attr.active_mtu = mtu; port->mtu_cap = ib_mtu_enum_to_int(mtu); } /* called by ifc layer to create new rxe device. * The caller should allocate memory for rxe by calling ib_alloc_device. */ int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name) { rxe_init(rxe); rxe_set_mtu(rxe, mtu); return rxe_register_device(rxe, ibdev_name); } static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) { struct rxe_dev *rxe; int err = 0; if (is_vlan_dev(ndev)) { rxe_err("rxe creation allowed on top of a real device only\n"); err = -EPERM; goto err; } rxe = rxe_get_dev_from_net(ndev); if (rxe) { ib_device_put(&rxe->ib_dev); rxe_err_dev(rxe, "already configured on %s\n", ndev->name); err = -EEXIST; goto err; } err = rxe_net_add(ibdev_name, ndev); if (err) { rxe_err("failed to add %s\n", ndev->name); goto err; } err: return err; } static struct rdma_link_ops rxe_link_ops = { .type = "rxe", .newlink = rxe_newlink, }; static int __init rxe_module_init(void) { int err; err = rxe_alloc_wq(); if (err) return err; err = rxe_net_init(); if (err) { rxe_destroy_wq(); return err; } rdma_link_register(&rxe_link_ops); pr_info("loaded\n"); return 0; } static void __exit rxe_module_exit(void) { rdma_link_unregister(&rxe_link_ops); ib_unregister_driver(RDMA_DRIVER_RXE); rxe_net_exit(); rxe_destroy_wq(); pr_info("unloaded\n"); } late_initcall(rxe_module_init); module_exit(rxe_module_exit); MODULE_ALIAS_RDMA_LINK("rxe"); |
| 2 3 3 3 3 3 3 3 1 2 1 1 2 2 2 2 2 14 14 12 12 199 198 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/list.h> #include <linux/rbtree.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> struct nft_rbtree { struct rb_root root; rwlock_t lock; seqcount_rwlock_t count; unsigned long last_gc; }; struct nft_rbtree_elem { struct nft_elem_priv priv; struct rb_node node; struct nft_set_ext ext; }; static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe) { return nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) && (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END); } static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) { return !nft_rbtree_interval_end(rbe); } static int nft_rbtree_cmp(const struct nft_set *set, const struct nft_rbtree_elem *e1, const struct nft_rbtree_elem *e2) { return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext), set->klen); } static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) { return nft_set_elem_expired(&rbe->ext); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) { struct nft_rbtree *priv = nft_set_priv(set); const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; int d; parent = rcu_dereference_raw(priv->root.rb_node); while (parent != NULL) { if (read_seqcount_retry(&priv->count, seq)) return false; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (interval && !nft_rbtree_cmp(set, rbe, interval) && nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; interval = rbe; } else if (d > 0) parent = rcu_dereference_raw(parent->rb_right); else { if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); continue; } if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { if (nft_set_is_anonymous(set)) return false; parent = rcu_dereference_raw(parent->rb_left); interval = NULL; continue; } *ext = &rbe->ext; return true; } } if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; } return false; } INDIRECT_CALLABLE_SCOPE bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); bool ret; ret = __nft_rbtree_lookup(net, set, key, ext, seq); if (ret || !read_seqcount_retry(&priv->count, seq)) return ret; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); ret = __nft_rbtree_lookup(net, set, key, ext, seq); read_unlock_bh(&priv->lock); return ret; } static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, const u32 *key, struct nft_rbtree_elem **elem, unsigned int seq, unsigned int flags, u8 genmask) { struct nft_rbtree_elem *rbe, *interval = NULL; struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent; const void *this; int d; parent = rcu_dereference_raw(priv->root.rb_node); while (parent != NULL) { if (read_seqcount_retry(&priv->count, seq)) return false; rbe = rb_entry(parent, struct nft_rbtree_elem, node); this = nft_set_ext_key(&rbe->ext); d = memcmp(this, key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (!(flags & NFT_SET_ELEM_INTERVAL_END)) interval = rbe; } else if (d > 0) { parent = rcu_dereference_raw(parent->rb_right); if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); continue; } if (nft_set_elem_expired(&rbe->ext)) return false; if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == (flags & NFT_SET_ELEM_INTERVAL_END)) { *elem = rbe; return true; } if (nft_rbtree_interval_end(rbe)) interval = NULL; parent = rcu_dereference_raw(parent->rb_left); } } if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && !nft_set_elem_expired(&interval->ext) && ((!nft_rbtree_interval_end(interval) && !(flags & NFT_SET_ELEM_INTERVAL_END)) || (nft_rbtree_interval_end(interval) && (flags & NFT_SET_ELEM_INTERVAL_END)))) { *elem = interval; return true; } return false; } static struct nft_elem_priv * nft_rbtree_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); struct nft_rbtree_elem *rbe = ERR_PTR(-ENOENT); const u32 *key = (const u32 *)&elem->key.val; u8 genmask = nft_genmask_cur(net); bool ret; ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); if (ret || !read_seqcount_retry(&priv->count, seq)) return &rbe->priv; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); read_unlock_bh(&priv->lock); if (!ret) return ERR_PTR(-ENOENT); return &rbe->priv; } static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { lockdep_assert_held_write(&priv->lock); nft_setelem_data_deactivate(net, set, &rbe->priv); rb_erase(&rbe->node, &priv->root); } static const struct nft_rbtree_elem * nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; struct nft_trans_gc *gc; gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); if (!gc) return ERR_PTR(-ENOMEM); /* search for end interval coming before this element. * end intervals don't carry a timeout extension, they * are coupled with the interval start element. */ while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev) && nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY)) break; prev = rb_prev(prev); } rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); nft_rbtree_gc_elem_remove(net, set, priv, rbe_prev); /* There is always room in this trans gc for this element, * memory allocation never actually happens, hence, the warning * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, * this is synchronous gc which never fails. */ gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe_prev); } nft_rbtree_gc_elem_remove(net, set, priv, rbe); gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) return ERR_PTR(-ENOMEM); nft_trans_gc_elem_add(gc, rbe); nft_trans_gc_queue_sync_done(gc); return rbe_prev; } static bool nft_rbtree_update_first(const struct nft_set *set, struct nft_rbtree_elem *rbe, struct rb_node *first) { struct nft_rbtree_elem *first_elem; first_elem = rb_entry(first, struct nft_rbtree_elem, node); /* this element is closest to where the new element is to be inserted: * update the first element for the node list path. */ if (nft_rbtree_cmp(set, rbe, first_elem) < 0) return true; return false; } static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; struct rb_node *node, *next, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 cur_genmask = nft_genmask_cur(net); u8 genmask = nft_genmask_next(net); u64 tstamp = nft_net_tstamp(net); int d; /* Descend the tree to search for an existing element greater than the * key value to insert that is greater than the new element. This is the * first element to walk the ordered elements to find possible overlap. */ parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = nft_rbtree_cmp(set, rbe, new); if (d < 0) { p = &parent->rb_left; } else if (d > 0) { if (!first || nft_rbtree_update_first(set, rbe, first)) first = &rbe->node; p = &parent->rb_right; } else { if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; else p = &parent->rb_right; } } if (!first) first = rb_first(&priv->root); /* Detect overlap by going through the list of valid tree nodes. * Values stored in the tree are in reversed order, starting from * highest to lowest value. */ for (node = first; node != NULL; node = next) { next = rb_next(node); rbe = rb_entry(node, struct nft_rbtree_elem, node); if (!nft_set_elem_active(&rbe->ext, genmask)) continue; /* perform garbage collection to avoid bogus overlap reports * but skip new elements in this transaction. */ if (__nft_set_elem_expired(&rbe->ext, tstamp) && nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; removed_end = nft_rbtree_gc_elem(set, priv, rbe); if (IS_ERR(removed_end)) return PTR_ERR(removed_end); if (removed_end == rbe_le || removed_end == rbe_ge) return -EAGAIN; continue; } d = nft_rbtree_cmp(set, rbe, new); if (d == 0) { /* Matching end element: no need to look for an * overlapping greater or equal element. */ if (nft_rbtree_interval_end(rbe)) { rbe_le = rbe; break; } /* first element that is greater or equal to key value. */ if (!rbe_ge) { rbe_ge = rbe; continue; } /* this is a closer more or equal element, update it. */ if (nft_rbtree_cmp(set, rbe_ge, new) != 0) { rbe_ge = rbe; continue; } /* element is equal to key value, make sure flags are * the same, an existing more or equal start element * must not be replaced by more or equal end element. */ if ((nft_rbtree_interval_start(new) && nft_rbtree_interval_start(rbe_ge)) || (nft_rbtree_interval_end(new) && nft_rbtree_interval_end(rbe_ge))) { rbe_ge = rbe; continue; } } else if (d > 0) { /* annotate element greater than the new element. */ rbe_ge = rbe; continue; } else if (d < 0) { /* annotate element less than the new element. */ rbe_le = rbe; break; } } /* - new start element matching existing start element: full overlap * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. */ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { *elem_priv = &rbe_ge->priv; return -EEXIST; } /* - new end element matching existing end element: full overlap * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. */ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { *elem_priv = &rbe_le->priv; return -EEXIST; } /* - new start element with existing closest, less or equal key value * being a start element: partial overlap, reported as -ENOTEMPTY. * Anonymous sets allow for two consecutive start element since they * are constant, skip them to avoid bogus overlap reports. */ if (!nft_set_is_anonymous(set) && rbe_le && nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) return -ENOTEMPTY; /* - new end element with existing closest, less or equal key value * being a end element: partial overlap, reported as -ENOTEMPTY. */ if (rbe_le && nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; /* - new end element with existing closest, greater or equal key value * being an end element: partial overlap, reported as -ENOTEMPTY */ if (rbe_ge && nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; /* Accepted element: pick insertion point depending on key value */ parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = nft_rbtree_cmp(set, rbe, new); if (d < 0) p = &parent->rb_left; else if (d > 0) p = &parent->rb_right; else if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; else p = &parent->rb_right; } rb_link_node_rcu(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); return 0; } static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem->priv); struct nft_rbtree *priv = nft_set_priv(set); int err; do { if (fatal_signal_pending(current)) return -EINTR; cond_resched(); write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); err = __nft_rbtree_insert(net, set, rbe, elem_priv); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } while (err == -EAGAIN); return err; } static void nft_rbtree_erase(struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); rb_erase(&rbe->node, &priv->root); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } static void nft_rbtree_remove(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); struct nft_rbtree *priv = nft_set_priv(set); nft_rbtree_erase(priv, rbe); } static void nft_rbtree_activate(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_clear(net, &rbe->ext); } static void nft_rbtree_flush(const struct net *net, const struct nft_set *set, struct nft_elem_priv *elem_priv) { struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &rbe->ext); } static struct nft_elem_priv * nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) { struct nft_rbtree_elem *rbe, *this = nft_elem_priv_cast(elem->priv); const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; u8 genmask = nft_genmask_next(net); u64 tstamp = nft_net_tstamp(net); int d; while (parent != NULL) { rbe = rb_entry(parent, struct nft_rbtree_elem, node); d = memcmp(nft_set_ext_key(&rbe->ext), &elem->key.val, set->klen); if (d < 0) parent = parent->rb_left; else if (d > 0) parent = parent->rb_right; else { if (nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(this)) { parent = parent->rb_left; continue; } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) { break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; } nft_rbtree_flush(net, set, &rbe->priv); return &rbe->priv; } } return NULL; } static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *node; read_lock_bh(&priv->lock); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); if (iter->count < iter->skip) goto cont; iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { read_unlock_bh(&priv->lock); return; } cont: iter->count++; } read_unlock_bh(&priv->lock); } static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { nft_setelem_data_deactivate(net, set, &rbe->priv); nft_rbtree_erase(priv, rbe); } static void nft_rbtree_gc(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe, *rbe_end = NULL; struct net *net = read_pnet(&set->net); u64 tstamp = nft_net_tstamp(net); struct rb_node *node, *next; struct nft_trans_gc *gc; set = nft_set_container_of(priv); net = read_pnet(&set->net); gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (!gc) return; for (node = rb_first(&priv->root); node ; node = next) { next = rb_next(node); rbe = rb_entry(node, struct nft_rbtree_elem, node); /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is * always visited before the start element. */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!__nft_set_elem_expired(&rbe->ext, tstamp)) continue; gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; /* end element needs to be removed first, it has * no timeout extension. */ if (rbe_end) { nft_rbtree_gc_remove(net, set, priv, rbe_end); nft_trans_gc_elem_add(gc, rbe_end); rbe_end = NULL; } gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; nft_rbtree_gc_remove(net, set, priv, rbe); nft_trans_gc_elem_add(gc, rbe); } try_later: if (gc) { gc = nft_trans_gc_catchall_sync(gc); nft_trans_gc_queue_sync_done(gc); priv->last_gc = jiffies; } } static u64 nft_rbtree_privsize(const struct nlattr * const nla[], const struct nft_set_desc *desc) { return sizeof(struct nft_rbtree); } static int nft_rbtree_init(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]) { struct nft_rbtree *priv = nft_set_priv(set); BUILD_BUG_ON(offsetof(struct nft_rbtree_elem, priv) != 0); rwlock_init(&priv->lock); seqcount_rwlock_init(&priv->count, &priv->lock); priv->root = RB_ROOT; return 0; } static void nft_rbtree_destroy(const struct nft_ctx *ctx, const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; struct rb_node *node; while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); nf_tables_set_elem_destroy(ctx, set, &rbe->priv); } } static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { if (desc->field_count > 1) return false; if (desc->size) est->size = sizeof(struct nft_rbtree) + desc->size * sizeof(struct nft_rbtree_elem); else est->size = ~0; est->lookup = NFT_SET_CLASS_O_LOG_N; est->space = NFT_SET_CLASS_O_N; return true; } static void nft_rbtree_commit(struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) nft_rbtree_gc(set); } static void nft_rbtree_gc_init(const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); priv->last_gc = jiffies; } const struct nft_set_type nft_set_rbtree_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { .privsize = nft_rbtree_privsize, .elemsize = offsetof(struct nft_rbtree_elem, ext), .estimate = nft_rbtree_estimate, .init = nft_rbtree_init, .destroy = nft_rbtree_destroy, .insert = nft_rbtree_insert, .remove = nft_rbtree_remove, .deactivate = nft_rbtree_deactivate, .flush = nft_rbtree_flush, .activate = nft_rbtree_activate, .commit = nft_rbtree_commit, .gc_init = nft_rbtree_gc_init, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .get = nft_rbtree_get, }, }; |
| 1 1 1 1 4 1 3 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Roccat Isku driver for Linux * * Copyright (c) 2011 Stefan Achatz <erazor_de@users.sourceforge.net> */ /* */ /* * Roccat Isku is a gamer keyboard with macro keys that can be configured in * 5 profiles. */ #include <linux/device.h> #include <linux/input.h> #include <linux/hid.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/hid-roccat.h> #include "hid-ids.h" #include "hid-roccat-common.h" #include "hid-roccat-isku.h" static void isku_profile_activated(struct isku_device *isku, uint new_profile) { isku->actual_profile = new_profile; } static int isku_receive(struct usb_device *usb_dev, uint command, void *buf, uint size) { return roccat_common2_receive(usb_dev, command, buf, size); } static int isku_get_actual_profile(struct usb_device *usb_dev) { struct isku_actual_profile buf; int retval; retval = isku_receive(usb_dev, ISKU_COMMAND_ACTUAL_PROFILE, &buf, sizeof(struct isku_actual_profile)); return retval ? retval : buf.actual_profile; } static int isku_set_actual_profile(struct usb_device *usb_dev, int new_profile) { struct isku_actual_profile buf; buf.command = ISKU_COMMAND_ACTUAL_PROFILE; buf.size = sizeof(struct isku_actual_profile); buf.actual_profile = new_profile; return roccat_common2_send_with_status(usb_dev, ISKU_COMMAND_ACTUAL_PROFILE, &buf, sizeof(struct isku_actual_profile)); } static ssize_t isku_sysfs_show_actual_profile(struct device *dev, struct device_attribute *attr, char *buf) { struct isku_device *isku = hid_get_drvdata(dev_get_drvdata(dev->parent->parent)); return sysfs_emit(buf, "%d\n", isku->actual_profile); } static ssize_t isku_sysfs_set_actual_profile(struct device *dev, struct device_attribute *attr, char const *buf, size_t size) { struct isku_device *isku; struct usb_device *usb_dev; unsigned long profile; int retval; struct isku_roccat_report roccat_report; dev = dev->parent->parent; isku = hid_get_drvdata(dev_get_drvdata(dev)); usb_dev = interface_to_usbdev(to_usb_interface(dev)); retval = kstrtoul(buf, 10, &profile); if (retval) return retval; if (profile > 4) return -EINVAL; mutex_lock(&isku->isku_lock); retval = isku_set_actual_profile(usb_dev, profile); if (retval) { mutex_unlock(&isku->isku_lock); return retval; } isku_profile_activated(isku, profile); roccat_report.event = ISKU_REPORT_BUTTON_EVENT_PROFILE; roccat_report.data1 = profile + 1; roccat_report.data2 = 0; roccat_report.profile = profile + 1; roccat_report_event(isku->chrdev_minor, (uint8_t const *)&roccat_report); mutex_unlock(&isku->isku_lock); return size; } static DEVICE_ATTR(actual_profile, 0660, isku_sysfs_show_actual_profile, isku_sysfs_set_actual_profile); static struct attribute *isku_attrs[] = { &dev_attr_actual_profile.attr, NULL, }; static ssize_t isku_sysfs_read(struct file *fp, struct kobject *kobj, char *buf, loff_t off, size_t count, size_t real_size, uint command) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct isku_device *isku = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; if (off >= real_size) return 0; if (off != 0 || count > real_size) return -EINVAL; mutex_lock(&isku->isku_lock); retval = isku_receive(usb_dev, command, buf, count); mutex_unlock(&isku->isku_lock); return retval ? retval : count; } static ssize_t isku_sysfs_write(struct file *fp, struct kobject *kobj, void const *buf, loff_t off, size_t count, size_t real_size, uint command) { struct device *dev = kobj_to_dev(kobj)->parent->parent; struct isku_device *isku = hid_get_drvdata(dev_get_drvdata(dev)); struct usb_device *usb_dev = interface_to_usbdev(to_usb_interface(dev)); int retval; if (off != 0 || count > real_size) return -EINVAL; mutex_lock(&isku->isku_lock); retval = roccat_common2_send_with_status(usb_dev, command, (void *)buf, count); mutex_unlock(&isku->isku_lock); return retval ? retval : count; } #define ISKU_SYSFS_W(thingy, THINGY) \ static ssize_t isku_sysfs_write_ ## thingy(struct file *fp, struct kobject *kobj, \ struct bin_attribute *attr, char *buf, \ loff_t off, size_t count) \ { \ return isku_sysfs_write(fp, kobj, buf, off, count, \ ISKU_SIZE_ ## THINGY, ISKU_COMMAND_ ## THINGY); \ } #define ISKU_SYSFS_R(thingy, THINGY) \ static ssize_t isku_sysfs_read_ ## thingy(struct file *fp, struct kobject *kobj, \ struct bin_attribute *attr, char *buf, \ loff_t off, size_t count) \ { \ return isku_sysfs_read(fp, kobj, buf, off, count, \ ISKU_SIZE_ ## THINGY, ISKU_COMMAND_ ## THINGY); \ } #define ISKU_SYSFS_RW(thingy, THINGY) \ ISKU_SYSFS_R(thingy, THINGY) \ ISKU_SYSFS_W(thingy, THINGY) #define ISKU_BIN_ATTR_RW(thingy, THINGY) \ ISKU_SYSFS_RW(thingy, THINGY); \ static struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0660 }, \ .size = ISKU_SIZE_ ## THINGY, \ .read = isku_sysfs_read_ ## thingy, \ .write = isku_sysfs_write_ ## thingy \ } #define ISKU_BIN_ATTR_R(thingy, THINGY) \ ISKU_SYSFS_R(thingy, THINGY); \ static struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0440 }, \ .size = ISKU_SIZE_ ## THINGY, \ .read = isku_sysfs_read_ ## thingy, \ } #define ISKU_BIN_ATTR_W(thingy, THINGY) \ ISKU_SYSFS_W(thingy, THINGY); \ static struct bin_attribute bin_attr_##thingy = { \ .attr = { .name = #thingy, .mode = 0220 }, \ .size = ISKU_SIZE_ ## THINGY, \ .write = isku_sysfs_write_ ## thingy \ } ISKU_BIN_ATTR_RW(macro, MACRO); ISKU_BIN_ATTR_RW(keys_function, KEYS_FUNCTION); ISKU_BIN_ATTR_RW(keys_easyzone, KEYS_EASYZONE); ISKU_BIN_ATTR_RW(keys_media, KEYS_MEDIA); ISKU_BIN_ATTR_RW(keys_thumbster, KEYS_THUMBSTER); ISKU_BIN_ATTR_RW(keys_macro, KEYS_MACRO); ISKU_BIN_ATTR_RW(keys_capslock, KEYS_CAPSLOCK); ISKU_BIN_ATTR_RW(light, LIGHT); ISKU_BIN_ATTR_RW(key_mask, KEY_MASK); ISKU_BIN_ATTR_RW(last_set, LAST_SET); ISKU_BIN_ATTR_W(talk, TALK); ISKU_BIN_ATTR_W(talkfx, TALKFX); ISKU_BIN_ATTR_W(control, CONTROL); ISKU_BIN_ATTR_W(reset, RESET); ISKU_BIN_ATTR_R(info, INFO); static struct bin_attribute *isku_bin_attributes[] = { &bin_attr_macro, &bin_attr_keys_function, &bin_attr_keys_easyzone, &bin_attr_keys_media, &bin_attr_keys_thumbster, &bin_attr_keys_macro, &bin_attr_keys_capslock, &bin_attr_light, &bin_attr_key_mask, &bin_attr_last_set, &bin_attr_talk, &bin_attr_talkfx, &bin_attr_control, &bin_attr_reset, &bin_attr_info, NULL, }; static const struct attribute_group isku_group = { .attrs = isku_attrs, .bin_attrs = isku_bin_attributes, }; static const struct attribute_group *isku_groups[] = { &isku_group, NULL, }; static const struct class isku_class = { .name = "isku", .dev_groups = isku_groups, }; static int isku_init_isku_device_struct(struct usb_device *usb_dev, struct isku_device *isku) { int retval; mutex_init(&isku->isku_lock); retval = isku_get_actual_profile(usb_dev); if (retval < 0) return retval; isku_profile_activated(isku, retval); return 0; } static int isku_init_specials(struct hid_device *hdev) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); struct usb_device *usb_dev = interface_to_usbdev(intf); struct isku_device *isku; int retval; if (intf->cur_altsetting->desc.bInterfaceProtocol != ISKU_USB_INTERFACE_PROTOCOL) { hid_set_drvdata(hdev, NULL); return 0; } isku = kzalloc(sizeof(*isku), GFP_KERNEL); if (!isku) { hid_err(hdev, "can't alloc device descriptor\n"); return -ENOMEM; } hid_set_drvdata(hdev, isku); retval = isku_init_isku_device_struct(usb_dev, isku); if (retval) { hid_err(hdev, "couldn't init struct isku_device\n"); goto exit_free; } retval = roccat_connect(&isku_class, hdev, sizeof(struct isku_roccat_report)); if (retval < 0) { hid_err(hdev, "couldn't init char dev\n"); } else { isku->chrdev_minor = retval; isku->roccat_claimed = 1; } return 0; exit_free: kfree(isku); return retval; } static void isku_remove_specials(struct hid_device *hdev) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); struct isku_device *isku; if (intf->cur_altsetting->desc.bInterfaceProtocol != ISKU_USB_INTERFACE_PROTOCOL) return; isku = hid_get_drvdata(hdev); if (isku->roccat_claimed) roccat_disconnect(isku->chrdev_minor); kfree(isku); } static int isku_probe(struct hid_device *hdev, const struct hid_device_id *id) { int retval; if (!hid_is_usb(hdev)) return -EINVAL; retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); goto exit; } retval = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (retval) { hid_err(hdev, "hw start failed\n"); goto exit; } retval = isku_init_specials(hdev); if (retval) { hid_err(hdev, "couldn't install keyboard\n"); goto exit_stop; } return 0; exit_stop: hid_hw_stop(hdev); exit: return retval; } static void isku_remove(struct hid_device *hdev) { isku_remove_specials(hdev); hid_hw_stop(hdev); } static void isku_keep_values_up_to_date(struct isku_device *isku, u8 const *data) { struct isku_report_button const *button_report; switch (data[0]) { case ISKU_REPORT_NUMBER_BUTTON: button_report = (struct isku_report_button const *)data; switch (button_report->event) { case ISKU_REPORT_BUTTON_EVENT_PROFILE: isku_profile_activated(isku, button_report->data1 - 1); break; } break; } } static void isku_report_to_chrdev(struct isku_device const *isku, u8 const *data) { struct isku_roccat_report roccat_report; struct isku_report_button const *button_report; if (data[0] != ISKU_REPORT_NUMBER_BUTTON) return; button_report = (struct isku_report_button const *)data; roccat_report.event = button_report->event; roccat_report.data1 = button_report->data1; roccat_report.data2 = button_report->data2; roccat_report.profile = isku->actual_profile + 1; roccat_report_event(isku->chrdev_minor, (uint8_t const *)&roccat_report); } static int isku_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); struct isku_device *isku = hid_get_drvdata(hdev); if (intf->cur_altsetting->desc.bInterfaceProtocol != ISKU_USB_INTERFACE_PROTOCOL) return 0; if (isku == NULL) return 0; isku_keep_values_up_to_date(isku, data); if (isku->roccat_claimed) isku_report_to_chrdev(isku, data); return 0; } static const struct hid_device_id isku_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKU) }, { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKUFX) }, { } }; MODULE_DEVICE_TABLE(hid, isku_devices); static struct hid_driver isku_driver = { .name = "isku", .id_table = isku_devices, .probe = isku_probe, .remove = isku_remove, .raw_event = isku_raw_event }; static int __init isku_init(void) { int retval; retval = class_register(&isku_class); if (retval) return retval; retval = hid_register_driver(&isku_driver); if (retval) class_unregister(&isku_class); return retval; } static void __exit isku_exit(void) { hid_unregister_driver(&isku_driver); class_unregister(&isku_class); } module_init(isku_init); module_exit(isku_exit); MODULE_AUTHOR("Stefan Achatz"); MODULE_DESCRIPTION("USB Roccat Isku/FX driver"); MODULE_LICENSE("GPL v2"); |
| 40 39 39 67 24 50 53 16 4 56 18 68 46 21 15 68 30 28 5 5 10 31 55 55 17 35 8 40 30 21 21 40 30 8 10 14 31 21 30 40 40 40 7 30 7 3 9 27 6 39 39 31 10 30 3 40 23 1 1 19 6 10 48 1 1 74 75 67 7 15 13 26 54 53 12 28 1 2 50 3 70 66 64 7 68 35 41 60 8 37 2 36 72 10 65 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Red Hat, Inc. * Copyright (c) 2016-2021 Christoph Hellwig. */ #include <linux/module.h> #include <linux/compiler.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/pagemap.h> #include <linux/iomap.h> #include <linux/backing-dev.h> #include <linux/uio.h> #include <linux/task_io_accounting_ops.h> #include "trace.h" #include "../internal.h" /* * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: */ #define IOMAP_DIO_CALLER_COMP (1U << 26) #define IOMAP_DIO_INLINE_COMP (1U << 27) #define IOMAP_DIO_WRITE_THROUGH (1U << 28) #define IOMAP_DIO_NEED_SYNC (1U << 29) #define IOMAP_DIO_WRITE (1U << 30) #define IOMAP_DIO_DIRTY (1U << 31) /* * Used for sub block zeroing in iomap_dio_zero() */ #define IOMAP_ZERO_PAGE_SIZE (SZ_64K) #define IOMAP_ZERO_PAGE_ORDER (get_order(IOMAP_ZERO_PAGE_SIZE)) static struct page *zero_page; struct iomap_dio { struct kiocb *iocb; const struct iomap_dio_ops *dops; loff_t i_size; loff_t size; atomic_t ref; unsigned flags; int error; size_t done_before; bool wait_for_completion; union { /* used during submission and for synchronous completion: */ struct { struct iov_iter *iter; struct task_struct *waiter; } submit; /* used for aio completion: */ struct { struct work_struct work; } aio; }; }; static struct bio *iomap_dio_alloc_bio(const struct iomap_iter *iter, struct iomap_dio *dio, unsigned short nr_vecs, blk_opf_t opf) { if (dio->dops && dio->dops->bio_set) return bio_alloc_bioset(iter->iomap.bdev, nr_vecs, opf, GFP_KERNEL, dio->dops->bio_set); return bio_alloc(iter->iomap.bdev, nr_vecs, opf, GFP_KERNEL); } static void iomap_dio_submit_bio(const struct iomap_iter *iter, struct iomap_dio *dio, struct bio *bio, loff_t pos) { struct kiocb *iocb = dio->iocb; atomic_inc(&dio->ref); /* Sync dio can't be polled reliably */ if ((iocb->ki_flags & IOCB_HIPRI) && !is_sync_kiocb(iocb)) { bio_set_polled(bio, iocb); WRITE_ONCE(iocb->private, bio); } if (dio->dops && dio->dops->submit_io) dio->dops->submit_io(iter, bio, pos); else submit_bio(bio); } ssize_t iomap_dio_complete(struct iomap_dio *dio) { const struct iomap_dio_ops *dops = dio->dops; struct kiocb *iocb = dio->iocb; loff_t offset = iocb->ki_pos; ssize_t ret = dio->error; if (dops && dops->end_io) ret = dops->end_io(iocb, dio->size, ret, dio->flags); if (likely(!ret)) { ret = dio->size; /* check for short read */ if (offset + ret > dio->i_size && !(dio->flags & IOMAP_DIO_WRITE)) ret = dio->i_size - offset; } /* * Try again to invalidate clean pages which might have been cached by * non-direct readahead, or faulted in by get_user_pages() if the source * of the write was an mmap'ed region of the file we're writing. Either * one is a pretty crazy thing to do, so we don't support it 100%. If * this invalidation fails, tough, the write still worked... * * And this page cache invalidation has to be after ->end_io(), as some * filesystems convert unwritten extents to real allocations in * ->end_io() when necessary, otherwise a racing buffer read would cache * zeros from unwritten extents. */ if (!dio->error && dio->size && (dio->flags & IOMAP_DIO_WRITE)) kiocb_invalidate_post_direct_write(iocb, dio->size); inode_dio_end(file_inode(iocb->ki_filp)); if (ret > 0) { iocb->ki_pos += ret; /* * If this is a DSYNC write, make sure we push it to stable * storage now that we've written data. */ if (dio->flags & IOMAP_DIO_NEED_SYNC) ret = generic_write_sync(iocb, ret); if (ret > 0) ret += dio->done_before; } trace_iomap_dio_complete(iocb, dio->error, ret); kfree(dio); return ret; } EXPORT_SYMBOL_GPL(iomap_dio_complete); static ssize_t iomap_dio_deferred_complete(void *data) { return iomap_dio_complete(data); } static void iomap_dio_complete_work(struct work_struct *work) { struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work); struct kiocb *iocb = dio->iocb; iocb->ki_complete(iocb, iomap_dio_complete(dio)); } /* * Set an error in the dio if none is set yet. We have to use cmpxchg * as the submission context and the completion context(s) can race to * update the error. */ static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret) { cmpxchg(&dio->error, 0, ret); } void iomap_dio_bio_end_io(struct bio *bio) { struct iomap_dio *dio = bio->bi_private; bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); struct kiocb *iocb = dio->iocb; if (bio->bi_status) iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status)); if (!atomic_dec_and_test(&dio->ref)) goto release_bio; /* * Synchronous dio, task itself will handle any completion work * that needs after IO. All we need to do is wake the task. */ if (dio->wait_for_completion) { struct task_struct *waiter = dio->submit.waiter; WRITE_ONCE(dio->submit.waiter, NULL); blk_wake_io_task(waiter); goto release_bio; } /* * Flagged with IOMAP_DIO_INLINE_COMP, we can complete it inline */ if (dio->flags & IOMAP_DIO_INLINE_COMP) { WRITE_ONCE(iocb->private, NULL); iomap_dio_complete_work(&dio->aio.work); goto release_bio; } /* * If this dio is flagged with IOMAP_DIO_CALLER_COMP, then schedule * our completion that way to avoid an async punt to a workqueue. */ if (dio->flags & IOMAP_DIO_CALLER_COMP) { /* only polled IO cares about private cleared */ iocb->private = dio; iocb->dio_complete = iomap_dio_deferred_complete; /* * Invoke ->ki_complete() directly. We've assigned our * dio_complete callback handler, and since the issuer set * IOCB_DIO_CALLER_COMP, we know their ki_complete handler will * notice ->dio_complete being set and will defer calling that * handler until it can be done from a safe task context. * * Note that the 'res' being passed in here is not important * for this case. The actual completion value of the request * will be gotten from dio_complete when that is run by the * issuer. */ iocb->ki_complete(iocb, 0); goto release_bio; } /* * Async DIO completion that requires filesystem level completion work * gets punted to a work queue to complete as the operation may require * more IO to be issued to finalise filesystem metadata changes or * guarantee data integrity. */ INIT_WORK(&dio->aio.work, iomap_dio_complete_work); queue_work(file_inode(iocb->ki_filp)->i_sb->s_dio_done_wq, &dio->aio.work); release_bio: if (should_dirty) { bio_check_pages_dirty(bio); } else { bio_release_pages(bio, false); bio_put(bio); } } EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io); static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio, loff_t pos, unsigned len) { struct inode *inode = file_inode(dio->iocb->ki_filp); struct bio *bio; if (!len) return 0; /* * Max block size supported is 64k */ if (WARN_ON_ONCE(len > IOMAP_ZERO_PAGE_SIZE)) return -EINVAL; bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE); fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); bio->bi_iter.bi_sector = iomap_sector(&iter->iomap, pos); bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; __bio_add_page(bio, zero_page, len, 0); iomap_dio_submit_bio(iter, dio, bio, pos); return 0; } /* * Figure out the bio's operation flags from the dio request, the * mapping, and whether or not we want FUA. Note that we can end up * clearing the WRITE_THROUGH flag in the dio request. */ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio, const struct iomap *iomap, bool use_fua) { blk_opf_t opflags = REQ_SYNC | REQ_IDLE; if (!(dio->flags & IOMAP_DIO_WRITE)) return REQ_OP_READ; opflags |= REQ_OP_WRITE; if (use_fua) opflags |= REQ_FUA; else dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; return opflags; } static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter, struct iomap_dio *dio) { const struct iomap *iomap = &iter->iomap; struct inode *inode = iter->inode; unsigned int fs_block_size = i_blocksize(inode), pad; loff_t length = iomap_length(iter); loff_t pos = iter->pos; blk_opf_t bio_opf; struct bio *bio; bool need_zeroout = false; bool use_fua = false; int nr_pages, ret = 0; size_t copied = 0; size_t orig_count; if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) || !bdev_iter_is_aligned(iomap->bdev, dio->submit.iter)) return -EINVAL; if (iomap->type == IOMAP_UNWRITTEN) { dio->flags |= IOMAP_DIO_UNWRITTEN; need_zeroout = true; } if (iomap->flags & IOMAP_F_SHARED) dio->flags |= IOMAP_DIO_COW; if (iomap->flags & IOMAP_F_NEW) { need_zeroout = true; } else if (iomap->type == IOMAP_MAPPED) { /* * Use a FUA write if we need datasync semantics, this is a pure * data IO that doesn't require any metadata updates (including * after IO completion such as unwritten extent conversion) and * the underlying device either supports FUA or doesn't have * a volatile write cache. This allows us to avoid cache flushes * on IO completion. If we can't use writethrough and need to * sync, disable in-task completions as dio completion will * need to call generic_write_sync() which will do a blocking * fsync / cache flush call. */ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && (dio->flags & IOMAP_DIO_WRITE_THROUGH) && (bdev_fua(iomap->bdev) || !bdev_write_cache(iomap->bdev))) use_fua = true; else if (dio->flags & IOMAP_DIO_NEED_SYNC) dio->flags &= ~IOMAP_DIO_CALLER_COMP; } /* * Save the original count and trim the iter to just the extent we * are operating on right now. The iter will be re-expanded once * we are done. */ orig_count = iov_iter_count(dio->submit.iter); iov_iter_truncate(dio->submit.iter, length); if (!iov_iter_count(dio->submit.iter)) goto out; /* * We can only do deferred completion for pure overwrites that * don't require additional IO at completion. This rules out * writes that need zeroing or extent conversion, extend * the file size, or issue journal IO or cache flushes * during completion processing. */ if (need_zeroout || ((dio->flags & IOMAP_DIO_NEED_SYNC) && !use_fua) || ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) dio->flags &= ~IOMAP_DIO_CALLER_COMP; /* * The rules for polled IO completions follow the guidelines as the * ones we set for inline and deferred completions. If none of those * are available for this IO, clear the polled flag. */ if (!(dio->flags & (IOMAP_DIO_INLINE_COMP|IOMAP_DIO_CALLER_COMP))) dio->iocb->ki_flags &= ~IOCB_HIPRI; if (need_zeroout) { /* zero out from the start of the block to the write offset */ pad = pos & (fs_block_size - 1); ret = iomap_dio_zero(iter, dio, pos - pad, pad); if (ret) goto out; } /* * Set the operation flags early so that bio_iov_iter_get_pages * can set up the page vector appropriately for a ZONE_APPEND * operation. */ bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua); nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS); do { size_t n; if (dio->error) { iov_iter_revert(dio->submit.iter, copied); copied = ret = 0; goto out; } bio = iomap_dio_alloc_bio(iter, dio, nr_pages, bio_opf); fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits, GFP_KERNEL); bio->bi_iter.bi_sector = iomap_sector(iomap, pos); bio->bi_write_hint = inode->i_write_hint; bio->bi_ioprio = dio->iocb->ki_ioprio; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; ret = bio_iov_iter_get_pages(bio, dio->submit.iter); if (unlikely(ret)) { /* * We have to stop part way through an IO. We must fall * through to the sub-block tail zeroing here, otherwise * this short IO may expose stale data in the tail of * the block we haven't written data to. */ bio_put(bio); goto zero_tail; } n = bio->bi_iter.bi_size; if (dio->flags & IOMAP_DIO_WRITE) { task_io_account_write(n); } else { if (dio->flags & IOMAP_DIO_DIRTY) bio_set_pages_dirty(bio); } dio->size += n; copied += n; nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS); /* * We can only poll for single bio I/Os. */ if (nr_pages) dio->iocb->ki_flags &= ~IOCB_HIPRI; iomap_dio_submit_bio(iter, dio, bio, pos); pos += n; } while (nr_pages); /* * We need to zeroout the tail of a sub-block write if the extent type * requires zeroing or the write extends beyond EOF. If we don't zero * the block tail in the latter case, we can expose stale data via mmap * reads of the EOF block. */ zero_tail: if (need_zeroout || ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) { /* zero out from the end of the write to the end of the block */ pad = pos & (fs_block_size - 1); if (pad) ret = iomap_dio_zero(iter, dio, pos, fs_block_size - pad); } out: /* Undo iter limitation to current extent */ iov_iter_reexpand(dio->submit.iter, orig_count - copied); if (copied) return copied; return ret; } static loff_t iomap_dio_hole_iter(const struct iomap_iter *iter, struct iomap_dio *dio) { loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter); dio->size += length; if (!length) return -EFAULT; return length; } static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi, struct iomap_dio *dio) { const struct iomap *iomap = &iomi->iomap; struct iov_iter *iter = dio->submit.iter; void *inline_data = iomap_inline_data(iomap, iomi->pos); loff_t length = iomap_length(iomi); loff_t pos = iomi->pos; size_t copied; if (WARN_ON_ONCE(!iomap_inline_data_valid(iomap))) return -EIO; if (dio->flags & IOMAP_DIO_WRITE) { loff_t size = iomi->inode->i_size; if (pos > size) memset(iomap_inline_data(iomap, size), 0, pos - size); copied = copy_from_iter(inline_data, length, iter); if (copied) { if (pos + copied > size) i_size_write(iomi->inode, pos + copied); mark_inode_dirty(iomi->inode); } } else { copied = copy_to_iter(inline_data, length, iter); } dio->size += copied; if (!copied) return -EFAULT; return copied; } static loff_t iomap_dio_iter(const struct iomap_iter *iter, struct iomap_dio *dio) { switch (iter->iomap.type) { case IOMAP_HOLE: if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE)) return -EIO; return iomap_dio_hole_iter(iter, dio); case IOMAP_UNWRITTEN: if (!(dio->flags & IOMAP_DIO_WRITE)) return iomap_dio_hole_iter(iter, dio); return iomap_dio_bio_iter(iter, dio); case IOMAP_MAPPED: return iomap_dio_bio_iter(iter, dio); case IOMAP_INLINE: return iomap_dio_inline_iter(iter, dio); case IOMAP_DELALLOC: /* * DIO is not serialised against mmap() access at all, and so * if the page_mkwrite occurs between the writeback and the * iomap_iter() call in the DIO path, then it will see the * DELALLOC block that the page-mkwrite allocated. */ pr_warn_ratelimited("Direct I/O collision with buffered writes! File: %pD4 Comm: %.20s\n", dio->iocb->ki_filp, current->comm); return -EIO; default: WARN_ON_ONCE(1); return -EIO; } } /* * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO * is being issued as AIO or not. This allows us to optimise pure data writes * to use REQ_FUA rather than requiring generic_write_sync() to issue a * REQ_FLUSH post write. This is slightly tricky because a single request here * can be mapped into multiple disjoint IOs and only a subset of the IOs issued * may be pure data writes. In that case, we still need to do a full data sync * completion. * * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL, * __iomap_dio_rw can return a partial result if it encounters a non-resident * page in @iter after preparing a transfer. In that case, the non-resident * pages can be faulted in and the request resumed with @done_before set to the * number of bytes previously transferred. The request will then complete with * the correct total number of bytes transferred; this is essential for * completing partial requests asynchronously. * * Returns -ENOTBLK In case of a page invalidation invalidation failure for * writes. The callers needs to fall back to buffered I/O in this case. */ struct iomap_dio * __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before) { struct inode *inode = file_inode(iocb->ki_filp); struct iomap_iter iomi = { .inode = inode, .pos = iocb->ki_pos, .len = iov_iter_count(iter), .flags = IOMAP_DIRECT, .private = private, }; bool wait_for_completion = is_sync_kiocb(iocb) || (dio_flags & IOMAP_DIO_FORCE_WAIT); struct blk_plug plug; struct iomap_dio *dio; loff_t ret = 0; trace_iomap_dio_rw_begin(iocb, iter, dio_flags, done_before); if (!iomi.len) return NULL; dio = kmalloc(sizeof(*dio), GFP_KERNEL); if (!dio) return ERR_PTR(-ENOMEM); dio->iocb = iocb; atomic_set(&dio->ref, 1); dio->size = 0; dio->i_size = i_size_read(inode); dio->dops = dops; dio->error = 0; dio->flags = 0; dio->done_before = done_before; dio->submit.iter = iter; dio->submit.waiter = current; if (iocb->ki_flags & IOCB_NOWAIT) iomi.flags |= IOMAP_NOWAIT; if (iov_iter_rw(iter) == READ) { /* reads can always complete inline */ dio->flags |= IOMAP_DIO_INLINE_COMP; if (iomi.pos >= dio->i_size) goto out_free_dio; if (user_backed_iter(iter)) dio->flags |= IOMAP_DIO_DIRTY; ret = kiocb_write_and_wait(iocb, iomi.len); if (ret) goto out_free_dio; } else { iomi.flags |= IOMAP_WRITE; dio->flags |= IOMAP_DIO_WRITE; /* * Flag as supporting deferred completions, if the issuer * groks it. This can avoid a workqueue punt for writes. * We may later clear this flag if we need to do other IO * as part of this IO completion. */ if (iocb->ki_flags & IOCB_DIO_CALLER_COMP) dio->flags |= IOMAP_DIO_CALLER_COMP; if (dio_flags & IOMAP_DIO_OVERWRITE_ONLY) { ret = -EAGAIN; if (iomi.pos >= dio->i_size || iomi.pos + iomi.len > dio->i_size) goto out_free_dio; iomi.flags |= IOMAP_OVERWRITE_ONLY; } /* for data sync or sync, we need sync completion processing */ if (iocb_is_dsync(iocb)) { dio->flags |= IOMAP_DIO_NEED_SYNC; /* * For datasync only writes, we optimistically try using * WRITE_THROUGH for this IO. This flag requires either * FUA writes through the device's write cache, or a * normal write to a device without a volatile write * cache. For the former, Any non-FUA write that occurs * will clear this flag, hence we know before completion * whether a cache flush is necessary. */ if (!(iocb->ki_flags & IOCB_SYNC)) dio->flags |= IOMAP_DIO_WRITE_THROUGH; } /* * Try to invalidate cache pages for the range we are writing. * If this invalidation fails, let the caller fall back to * buffered I/O. */ ret = kiocb_invalidate_pages(iocb, iomi.len); if (ret) { if (ret != -EAGAIN) { trace_iomap_dio_invalidate_fail(inode, iomi.pos, iomi.len); ret = -ENOTBLK; } goto out_free_dio; } if (!wait_for_completion && !inode->i_sb->s_dio_done_wq) { ret = sb_init_dio_done_wq(inode->i_sb); if (ret < 0) goto out_free_dio; } } inode_dio_begin(inode); blk_start_plug(&plug); while ((ret = iomap_iter(&iomi, ops)) > 0) { iomi.processed = iomap_dio_iter(&iomi, dio); /* * We can only poll for single bio I/Os. */ iocb->ki_flags &= ~IOCB_HIPRI; } blk_finish_plug(&plug); /* * We only report that we've read data up to i_size. * Revert iter to a state corresponding to that as some callers (such * as the splice code) rely on it. */ if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size) iov_iter_revert(iter, iomi.pos - dio->i_size); if (ret == -EFAULT && dio->size && (dio_flags & IOMAP_DIO_PARTIAL)) { if (!(iocb->ki_flags & IOCB_NOWAIT)) wait_for_completion = true; ret = 0; } /* magic error code to fall back to buffered I/O */ if (ret == -ENOTBLK) { wait_for_completion = true; ret = 0; } if (ret < 0) iomap_dio_set_error(dio, ret); /* * If all the writes we issued were already written through to the * media, we don't need to flush the cache on IO completion. Clear the * sync flag for this case. */ if (dio->flags & IOMAP_DIO_WRITE_THROUGH) dio->flags &= ~IOMAP_DIO_NEED_SYNC; /* * We are about to drop our additional submission reference, which * might be the last reference to the dio. There are three different * ways we can progress here: * * (a) If this is the last reference we will always complete and free * the dio ourselves. * (b) If this is not the last reference, and we serve an asynchronous * iocb, we must never touch the dio after the decrement, the * I/O completion handler will complete and free it. * (c) If this is not the last reference, but we serve a synchronous * iocb, the I/O completion handler will wake us up on the drop * of the final reference, and we will complete and free it here * after we got woken by the I/O completion handler. */ dio->wait_for_completion = wait_for_completion; if (!atomic_dec_and_test(&dio->ref)) { if (!wait_for_completion) { trace_iomap_dio_rw_queued(inode, iomi.pos, iomi.len); return ERR_PTR(-EIOCBQUEUED); } for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(dio->submit.waiter)) break; blk_io_schedule(); } __set_current_state(TASK_RUNNING); } return dio; out_free_dio: kfree(dio); if (ret) return ERR_PTR(ret); return NULL; } EXPORT_SYMBOL_GPL(__iomap_dio_rw); ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before) { struct iomap_dio *dio; dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, private, done_before); if (IS_ERR_OR_NULL(dio)) return PTR_ERR_OR_ZERO(dio); return iomap_dio_complete(dio); } EXPORT_SYMBOL_GPL(iomap_dio_rw); static int __init iomap_dio_init(void) { zero_page = alloc_pages(GFP_KERNEL | __GFP_ZERO, IOMAP_ZERO_PAGE_ORDER); if (!zero_page) return -ENOMEM; return 0; } fs_initcall(iomap_dio_init); |
| 31 31 31 26 12 2 12 2 12 12 2 2 12 12 12 8 8 12 2 8 2 12 12 12 12 12 12 2 19 12 8 8 11 12 6 12 12 11 12 12 6 11 6 12 12 12 12 12 12 12 20 20 9 2 8 7 14 3 7 8 8 8 8 31 1 1 27 4 31 31 29 79 75 4 22 22 16 7 3 67 3 64 42 3 10 14 3 3 3 30 14 8 8 3 1 82 2 4 27 1 118 117 102 14 4 3 1 6 64 2 11 5 2 9 3 18 12 17 1 66 3 1 1 84 2 1 76 1 2 12 1 56 11 65 58 52 14 27 34 3 31 3 30 13 26 1 1 1 31 31 31 86 88 56 34 13 13 13 7 13 12 13 6 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 | /* * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/moduleparam.h> #include <linux/gfp.h> #include <net/sock.h> #include <linux/in.h> #include <linux/list.h> #include <linux/ratelimit.h> #include <linux/export.h> #include <linux/sizes.h> #include "rds.h" /* When transmitting messages in rds_send_xmit, we need to emerge from * time to time and briefly release the CPU. Otherwise the softlock watchdog * will kick our shin. * Also, it seems fairer to not let one busy connection stall all the * others. * * send_batch_count is the number of times we'll loop in send_xmit. Setting * it to 0 will restore the old behavior (where we looped until we had * drained the queue). */ static int send_batch_count = SZ_1K; module_param(send_batch_count, int, 0444); MODULE_PARM_DESC(send_batch_count, " batch factor when working the send queue"); static void rds_send_remove_from_sock(struct list_head *messages, int status); /* * Reset the send state. Callers must ensure that this doesn't race with * rds_send_xmit(). */ void rds_send_path_reset(struct rds_conn_path *cp) { struct rds_message *rm, *tmp; unsigned long flags; if (cp->cp_xmit_rm) { rm = cp->cp_xmit_rm; cp->cp_xmit_rm = NULL; /* Tell the user the RDMA op is no longer mapped by the * transport. This isn't entirely true (it's flushed out * independently) but as the connection is down, there's * no ongoing RDMA to/from that memory */ rds_message_unmapped(rm); rds_message_put(rm); } cp->cp_xmit_sg = 0; cp->cp_xmit_hdr_off = 0; cp->cp_xmit_data_off = 0; cp->cp_xmit_atomic_sent = 0; cp->cp_xmit_rdma_sent = 0; cp->cp_xmit_data_sent = 0; cp->cp_conn->c_map_queued = 0; cp->cp_unacked_packets = rds_sysctl_max_unacked_packets; cp->cp_unacked_bytes = rds_sysctl_max_unacked_bytes; /* Mark messages as retransmissions, and move them to the send q */ spin_lock_irqsave(&cp->cp_lock, flags); list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) { set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags); set_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags); } list_splice_init(&cp->cp_retrans, &cp->cp_send_queue); spin_unlock_irqrestore(&cp->cp_lock, flags); } EXPORT_SYMBOL_GPL(rds_send_path_reset); static int acquire_in_xmit(struct rds_conn_path *cp) { return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0; } static void release_in_xmit(struct rds_conn_path *cp) { clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); /* * We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. */ if (waitqueue_active(&cp->cp_waitq)) wake_up_all(&cp->cp_waitq); } /* * We're making the conscious trade-off here to only send one message * down the connection at a time. * Pro: * - tx queueing is a simple fifo list * - reassembly is optional and easily done by transports per conn * - no per flow rx lookup at all, straight to the socket * - less per-frag memory and wire overhead * Con: * - queued acks can be delayed behind large messages * Depends: * - small message latency is higher behind queued large messages * - large message latency isn't starved by intervening small sends */ int rds_send_xmit(struct rds_conn_path *cp) { struct rds_connection *conn = cp->cp_conn; struct rds_message *rm; unsigned long flags; unsigned int tmp; struct scatterlist *sg; int ret = 0; LIST_HEAD(to_be_dropped); int batch_count; unsigned long send_gen = 0; int same_rm = 0; restart: batch_count = 0; /* * sendmsg calls here after having queued its message on the send * queue. We only have one task feeding the connection at a time. If * another thread is already feeding the queue then we back off. This * avoids blocking the caller and trading per-connection data between * caches per message. */ if (!acquire_in_xmit(cp)) { rds_stats_inc(s_send_lock_contention); ret = -ENOMEM; goto out; } if (rds_destroy_pending(cp->cp_conn)) { release_in_xmit(cp); ret = -ENETUNREACH; /* dont requeue send work */ goto out; } /* * we record the send generation after doing the xmit acquire. * if someone else manages to jump in and do some work, we'll use * this to avoid a goto restart farther down. * * The acquire_in_xmit() check above ensures that only one * caller can increment c_send_gen at any time. */ send_gen = READ_ONCE(cp->cp_send_gen) + 1; WRITE_ONCE(cp->cp_send_gen, send_gen); /* * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, * we do the opposite to avoid races. */ if (!rds_conn_path_up(cp)) { release_in_xmit(cp); ret = 0; goto out; } if (conn->c_trans->xmit_path_prepare) conn->c_trans->xmit_path_prepare(cp); /* * spin trying to push headers and data down the connection until * the connection doesn't make forward progress. */ while (1) { rm = cp->cp_xmit_rm; if (!rm) { same_rm = 0; } else { same_rm++; if (same_rm >= 4096) { rds_stats_inc(s_send_stuck_rm); ret = -EAGAIN; break; } } /* * If between sending messages, we can send a pending congestion * map update. */ if (!rm && test_and_clear_bit(0, &conn->c_map_queued)) { rm = rds_cong_update_alloc(conn); if (IS_ERR(rm)) { ret = PTR_ERR(rm); break; } rm->data.op_active = 1; rm->m_inc.i_conn_path = cp; rm->m_inc.i_conn = cp->cp_conn; cp->cp_xmit_rm = rm; } /* * If not already working on one, grab the next message. * * cp_xmit_rm holds a ref while we're sending this message down * the connction. We can use this ref while holding the * send_sem.. rds_send_reset() is serialized with it. */ if (!rm) { unsigned int len; batch_count++; /* we want to process as big a batch as we can, but * we also want to avoid softlockups. If we've been * through a lot of messages, lets back off and see * if anyone else jumps in */ if (batch_count >= send_batch_count) goto over_batch; spin_lock_irqsave(&cp->cp_lock, flags); if (!list_empty(&cp->cp_send_queue)) { rm = list_entry(cp->cp_send_queue.next, struct rds_message, m_conn_item); rds_message_addref(rm); /* * Move the message from the send queue to the retransmit * list right away. */ list_move_tail(&rm->m_conn_item, &cp->cp_retrans); } spin_unlock_irqrestore(&cp->cp_lock, flags); if (!rm) break; /* Unfortunately, the way Infiniband deals with * RDMA to a bad MR key is by moving the entire * queue pair to error state. We could possibly * recover from that, but right now we drop the * connection. * Therefore, we never retransmit messages with RDMA ops. */ if (test_bit(RDS_MSG_FLUSH, &rm->m_flags) || (rm->rdma.op_active && test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags))) { spin_lock_irqsave(&cp->cp_lock, flags); if (test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) list_move(&rm->m_conn_item, &to_be_dropped); spin_unlock_irqrestore(&cp->cp_lock, flags); continue; } /* Require an ACK every once in a while */ len = ntohl(rm->m_inc.i_hdr.h_len); if (cp->cp_unacked_packets == 0 || cp->cp_unacked_bytes < len) { set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags); cp->cp_unacked_packets = rds_sysctl_max_unacked_packets; cp->cp_unacked_bytes = rds_sysctl_max_unacked_bytes; rds_stats_inc(s_send_ack_required); } else { cp->cp_unacked_bytes -= len; cp->cp_unacked_packets--; } cp->cp_xmit_rm = rm; } /* The transport either sends the whole rdma or none of it */ if (rm->rdma.op_active && !cp->cp_xmit_rdma_sent) { rm->m_final_op = &rm->rdma; /* The transport owns the mapped memory for now. * You can't unmap it while it's on the send queue */ set_bit(RDS_MSG_MAPPED, &rm->m_flags); ret = conn->c_trans->xmit_rdma(conn, &rm->rdma); if (ret) { clear_bit(RDS_MSG_MAPPED, &rm->m_flags); wake_up_interruptible(&rm->m_flush_wait); break; } cp->cp_xmit_rdma_sent = 1; } if (rm->atomic.op_active && !cp->cp_xmit_atomic_sent) { rm->m_final_op = &rm->atomic; /* The transport owns the mapped memory for now. * You can't unmap it while it's on the send queue */ set_bit(RDS_MSG_MAPPED, &rm->m_flags); ret = conn->c_trans->xmit_atomic(conn, &rm->atomic); if (ret) { clear_bit(RDS_MSG_MAPPED, &rm->m_flags); wake_up_interruptible(&rm->m_flush_wait); break; } cp->cp_xmit_atomic_sent = 1; } /* * A number of cases require an RDS header to be sent * even if there is no data. * We permit 0-byte sends; rds-ping depends on this. * However, if there are exclusively attached silent ops, * we skip the hdr/data send, to enable silent operation. */ if (rm->data.op_nents == 0) { int ops_present; int all_ops_are_silent = 1; ops_present = (rm->atomic.op_active || rm->rdma.op_active); if (rm->atomic.op_active && !rm->atomic.op_silent) all_ops_are_silent = 0; if (rm->rdma.op_active && !rm->rdma.op_silent) all_ops_are_silent = 0; if (ops_present && all_ops_are_silent && !rm->m_rdma_cookie) rm->data.op_active = 0; } if (rm->data.op_active && !cp->cp_xmit_data_sent) { rm->m_final_op = &rm->data; ret = conn->c_trans->xmit(conn, rm, cp->cp_xmit_hdr_off, cp->cp_xmit_sg, cp->cp_xmit_data_off); if (ret <= 0) break; if (cp->cp_xmit_hdr_off < sizeof(struct rds_header)) { tmp = min_t(int, ret, sizeof(struct rds_header) - cp->cp_xmit_hdr_off); cp->cp_xmit_hdr_off += tmp; ret -= tmp; } sg = &rm->data.op_sg[cp->cp_xmit_sg]; while (ret) { tmp = min_t(int, ret, sg->length - cp->cp_xmit_data_off); cp->cp_xmit_data_off += tmp; ret -= tmp; if (cp->cp_xmit_data_off == sg->length) { cp->cp_xmit_data_off = 0; sg++; cp->cp_xmit_sg++; BUG_ON(ret != 0 && cp->cp_xmit_sg == rm->data.op_nents); } } if (cp->cp_xmit_hdr_off == sizeof(struct rds_header) && (cp->cp_xmit_sg == rm->data.op_nents)) cp->cp_xmit_data_sent = 1; } /* * A rm will only take multiple times through this loop * if there is a data op. Thus, if the data is sent (or there was * none), then we're done with the rm. */ if (!rm->data.op_active || cp->cp_xmit_data_sent) { cp->cp_xmit_rm = NULL; cp->cp_xmit_sg = 0; cp->cp_xmit_hdr_off = 0; cp->cp_xmit_data_off = 0; cp->cp_xmit_rdma_sent = 0; cp->cp_xmit_atomic_sent = 0; cp->cp_xmit_data_sent = 0; rds_message_put(rm); } } over_batch: if (conn->c_trans->xmit_path_complete) conn->c_trans->xmit_path_complete(cp); release_in_xmit(cp); /* Nuke any messages we decided not to retransmit. */ if (!list_empty(&to_be_dropped)) { /* irqs on here, so we can put(), unlike above */ list_for_each_entry(rm, &to_be_dropped, m_conn_item) rds_message_put(rm); rds_send_remove_from_sock(&to_be_dropped, RDS_RDMA_DROPPED); } /* * Other senders can queue a message after we last test the send queue * but before we clear RDS_IN_XMIT. In that case they'd back off and * not try and send their newly queued message. We need to check the * send queue after having cleared RDS_IN_XMIT so that their message * doesn't get stuck on the send queue. * * If the transport cannot continue (i.e ret != 0), then it must * call us when more room is available, such as from the tx * completion handler. * * We have an extra generation check here so that if someone manages * to jump in after our release_in_xmit, we'll see that they have done * some work and we will skip our goto */ if (ret == 0) { bool raced; smp_mb(); raced = send_gen != READ_ONCE(cp->cp_send_gen); if ((test_bit(0, &conn->c_map_queued) || !list_empty(&cp->cp_send_queue)) && !raced) { if (batch_count < send_batch_count) goto restart; rcu_read_lock(); if (rds_destroy_pending(cp->cp_conn)) ret = -ENETUNREACH; else queue_delayed_work(rds_wq, &cp->cp_send_w, 1); rcu_read_unlock(); } else if (raced) { rds_stats_inc(s_send_lock_queue_raced); } } out: return ret; } EXPORT_SYMBOL_GPL(rds_send_xmit); static void rds_send_sndbuf_remove(struct rds_sock *rs, struct rds_message *rm) { u32 len = be32_to_cpu(rm->m_inc.i_hdr.h_len); assert_spin_locked(&rs->rs_lock); BUG_ON(rs->rs_snd_bytes < len); rs->rs_snd_bytes -= len; if (rs->rs_snd_bytes == 0) rds_stats_inc(s_send_queue_empty); } static inline int rds_send_is_acked(struct rds_message *rm, u64 ack, is_acked_func is_acked) { if (is_acked) return is_acked(rm, ack); return be64_to_cpu(rm->m_inc.i_hdr.h_sequence) <= ack; } /* * This is pretty similar to what happens below in the ACK * handling code - except that we call here as soon as we get * the IB send completion on the RDMA op and the accompanying * message. */ void rds_rdma_send_complete(struct rds_message *rm, int status) { struct rds_sock *rs = NULL; struct rm_rdma_op *ro; struct rds_notifier *notifier; unsigned long flags; spin_lock_irqsave(&rm->m_rs_lock, flags); ro = &rm->rdma; if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) && ro->op_active && ro->op_notify && ro->op_notifier) { notifier = ro->op_notifier; rs = rm->m_rs; sock_hold(rds_rs_to_sk(rs)); notifier->n_status = status; spin_lock(&rs->rs_lock); list_add_tail(¬ifier->n_list, &rs->rs_notify_queue); spin_unlock(&rs->rs_lock); ro->op_notifier = NULL; } spin_unlock_irqrestore(&rm->m_rs_lock, flags); if (rs) { rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } } EXPORT_SYMBOL_GPL(rds_rdma_send_complete); /* * Just like above, except looks at atomic op */ void rds_atomic_send_complete(struct rds_message *rm, int status) { struct rds_sock *rs = NULL; struct rm_atomic_op *ao; struct rds_notifier *notifier; unsigned long flags; spin_lock_irqsave(&rm->m_rs_lock, flags); ao = &rm->atomic; if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) && ao->op_active && ao->op_notify && ao->op_notifier) { notifier = ao->op_notifier; rs = rm->m_rs; sock_hold(rds_rs_to_sk(rs)); notifier->n_status = status; spin_lock(&rs->rs_lock); list_add_tail(¬ifier->n_list, &rs->rs_notify_queue); spin_unlock(&rs->rs_lock); ao->op_notifier = NULL; } spin_unlock_irqrestore(&rm->m_rs_lock, flags); if (rs) { rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } } EXPORT_SYMBOL_GPL(rds_atomic_send_complete); /* * This is the same as rds_rdma_send_complete except we * don't do any locking - we have all the ingredients (message, * socket, socket lock) and can just move the notifier. */ static inline void __rds_send_complete(struct rds_sock *rs, struct rds_message *rm, int status) { struct rm_rdma_op *ro; struct rm_atomic_op *ao; ro = &rm->rdma; if (ro->op_active && ro->op_notify && ro->op_notifier) { ro->op_notifier->n_status = status; list_add_tail(&ro->op_notifier->n_list, &rs->rs_notify_queue); ro->op_notifier = NULL; } ao = &rm->atomic; if (ao->op_active && ao->op_notify && ao->op_notifier) { ao->op_notifier->n_status = status; list_add_tail(&ao->op_notifier->n_list, &rs->rs_notify_queue); ao->op_notifier = NULL; } /* No need to wake the app - caller does this */ } /* * This removes messages from the socket's list if they're on it. The list * argument must be private to the caller, we must be able to modify it * without locks. The messages must have a reference held for their * position on the list. This function will drop that reference after * removing the messages from the 'messages' list regardless of if it found * the messages on the socket list or not. */ static void rds_send_remove_from_sock(struct list_head *messages, int status) { unsigned long flags; struct rds_sock *rs = NULL; struct rds_message *rm; while (!list_empty(messages)) { int was_on_sock = 0; rm = list_entry(messages->next, struct rds_message, m_conn_item); list_del_init(&rm->m_conn_item); /* * If we see this flag cleared then we're *sure* that someone * else beat us to removing it from the sock. If we race * with their flag update we'll get the lock and then really * see that the flag has been cleared. * * The message spinlock makes sure nobody clears rm->m_rs * while we're messing with it. It does not prevent the * message from being removed from the socket, though. */ spin_lock_irqsave(&rm->m_rs_lock, flags); if (!test_bit(RDS_MSG_ON_SOCK, &rm->m_flags)) goto unlock_and_drop; if (rs != rm->m_rs) { if (rs) { rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } rs = rm->m_rs; if (rs) sock_hold(rds_rs_to_sk(rs)); } if (!rs) goto unlock_and_drop; spin_lock(&rs->rs_lock); if (test_and_clear_bit(RDS_MSG_ON_SOCK, &rm->m_flags)) { struct rm_rdma_op *ro = &rm->rdma; struct rds_notifier *notifier; list_del_init(&rm->m_sock_item); rds_send_sndbuf_remove(rs, rm); if (ro->op_active && ro->op_notifier && (ro->op_notify || (ro->op_recverr && status))) { notifier = ro->op_notifier; list_add_tail(¬ifier->n_list, &rs->rs_notify_queue); if (!notifier->n_status) notifier->n_status = status; rm->rdma.op_notifier = NULL; } was_on_sock = 1; } spin_unlock(&rs->rs_lock); unlock_and_drop: spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); if (was_on_sock) rds_message_put(rm); } if (rs) { rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } } /* * Transports call here when they've determined that the receiver queued * messages up to, and including, the given sequence number. Messages are * moved to the retrans queue when rds_send_xmit picks them off the send * queue. This means that in the TCP case, the message may not have been * assigned the m_ack_seq yet - but that's fine as long as tcp_is_acked * checks the RDS_MSG_HAS_ACK_SEQ bit. */ void rds_send_path_drop_acked(struct rds_conn_path *cp, u64 ack, is_acked_func is_acked) { struct rds_message *rm, *tmp; unsigned long flags; LIST_HEAD(list); spin_lock_irqsave(&cp->cp_lock, flags); list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) { if (!rds_send_is_acked(rm, ack, is_acked)) break; list_move(&rm->m_conn_item, &list); clear_bit(RDS_MSG_ON_CONN, &rm->m_flags); } /* order flag updates with spin locks */ if (!list_empty(&list)) smp_mb__after_atomic(); spin_unlock_irqrestore(&cp->cp_lock, flags); /* now remove the messages from the sock list as needed */ rds_send_remove_from_sock(&list, RDS_RDMA_SUCCESS); } EXPORT_SYMBOL_GPL(rds_send_path_drop_acked); void rds_send_drop_acked(struct rds_connection *conn, u64 ack, is_acked_func is_acked) { WARN_ON(conn->c_trans->t_mp_capable); rds_send_path_drop_acked(&conn->c_path[0], ack, is_acked); } EXPORT_SYMBOL_GPL(rds_send_drop_acked); void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest) { struct rds_message *rm, *tmp; struct rds_connection *conn; struct rds_conn_path *cp; unsigned long flags; LIST_HEAD(list); /* get all the messages we're dropping under the rs lock */ spin_lock_irqsave(&rs->rs_lock, flags); list_for_each_entry_safe(rm, tmp, &rs->rs_send_queue, m_sock_item) { if (dest && (!ipv6_addr_equal(&dest->sin6_addr, &rm->m_daddr) || dest->sin6_port != rm->m_inc.i_hdr.h_dport)) continue; list_move(&rm->m_sock_item, &list); rds_send_sndbuf_remove(rs, rm); clear_bit(RDS_MSG_ON_SOCK, &rm->m_flags); } /* order flag updates with the rs lock */ smp_mb__after_atomic(); spin_unlock_irqrestore(&rs->rs_lock, flags); if (list_empty(&list)) return; /* Remove the messages from the conn */ list_for_each_entry(rm, &list, m_sock_item) { conn = rm->m_inc.i_conn; if (conn->c_trans->t_mp_capable) cp = rm->m_inc.i_conn_path; else cp = &conn->c_path[0]; spin_lock_irqsave(&cp->cp_lock, flags); /* * Maybe someone else beat us to removing rm from the conn. * If we race with their flag update we'll get the lock and * then really see that the flag has been cleared. */ if (!test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) { spin_unlock_irqrestore(&cp->cp_lock, flags); continue; } list_del_init(&rm->m_conn_item); spin_unlock_irqrestore(&cp->cp_lock, flags); /* * Couldn't grab m_rs_lock in top loop (lock ordering), * but we can now. */ spin_lock_irqsave(&rm->m_rs_lock, flags); spin_lock(&rs->rs_lock); __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); spin_unlock(&rs->rs_lock); spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); } rds_wake_sk_sleep(rs); while (!list_empty(&list)) { rm = list_entry(list.next, struct rds_message, m_sock_item); list_del_init(&rm->m_sock_item); rds_message_wait(rm); /* just in case the code above skipped this message * because RDS_MSG_ON_CONN wasn't set, run it again here * taking m_rs_lock is the only thing that keeps us * from racing with ack processing. */ spin_lock_irqsave(&rm->m_rs_lock, flags); spin_lock(&rs->rs_lock); __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); spin_unlock(&rs->rs_lock); spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); } } /* * we only want this to fire once so we use the callers 'queued'. It's * possible that another thread can race with us and remove the * message from the flow with RDS_CANCEL_SENT_TO. */ static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn, struct rds_conn_path *cp, struct rds_message *rm, __be16 sport, __be16 dport, int *queued) { unsigned long flags; u32 len; if (*queued) goto out; len = be32_to_cpu(rm->m_inc.i_hdr.h_len); /* this is the only place which holds both the socket's rs_lock * and the connection's c_lock */ spin_lock_irqsave(&rs->rs_lock, flags); /* * If there is a little space in sndbuf, we don't queue anything, * and userspace gets -EAGAIN. But poll() indicates there's send * room. This can lead to bad behavior (spinning) if snd_bytes isn't * freed up by incoming acks. So we check the *old* value of * rs_snd_bytes here to allow the last msg to exceed the buffer, * and poll() now knows no more data can be sent. */ if (rs->rs_snd_bytes < rds_sk_sndbuf(rs)) { rs->rs_snd_bytes += len; /* let recv side know we are close to send space exhaustion. * This is probably not the optimal way to do it, as this * means we set the flag on *all* messages as soon as our * throughput hits a certain threshold. */ if (rs->rs_snd_bytes >= rds_sk_sndbuf(rs) / 2) set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags); list_add_tail(&rm->m_sock_item, &rs->rs_send_queue); set_bit(RDS_MSG_ON_SOCK, &rm->m_flags); rds_message_addref(rm); sock_hold(rds_rs_to_sk(rs)); rm->m_rs = rs; /* The code ordering is a little weird, but we're trying to minimize the time we hold c_lock */ rds_message_populate_header(&rm->m_inc.i_hdr, sport, dport, 0); rm->m_inc.i_conn = conn; rm->m_inc.i_conn_path = cp; rds_message_addref(rm); spin_lock(&cp->cp_lock); rm->m_inc.i_hdr.h_sequence = cpu_to_be64(cp->cp_next_tx_seq++); list_add_tail(&rm->m_conn_item, &cp->cp_send_queue); set_bit(RDS_MSG_ON_CONN, &rm->m_flags); spin_unlock(&cp->cp_lock); rdsdebug("queued msg %p len %d, rs %p bytes %d seq %llu\n", rm, len, rs, rs->rs_snd_bytes, (unsigned long long)be64_to_cpu(rm->m_inc.i_hdr.h_sequence)); *queued = 1; } spin_unlock_irqrestore(&rs->rs_lock, flags); out: return *queued; } /* * rds_message is getting to be quite complicated, and we'd like to allocate * it all in one go. This figures out how big it needs to be up front. */ static int rds_rm_size(struct msghdr *msg, int num_sgs, struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; int size = 0; int cmsg_groups = 0; int retval; bool zcopy_cookie = false; struct rds_iov_vector *iov, *tmp_iov; if (num_sgs < 0) return -EINVAL; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_RDS) continue; switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: if (vct->indx >= vct->len) { vct->len += vct->incr; tmp_iov = krealloc(vct->vec, vct->len * sizeof(struct rds_iov_vector), GFP_KERNEL); if (!tmp_iov) { vct->len -= vct->incr; return -ENOMEM; } vct->vec = tmp_iov; } iov = &vct->vec[vct->indx]; memset(iov, 0, sizeof(struct rds_iov_vector)); vct->indx++; cmsg_groups |= 1; retval = rds_rdma_extra_size(CMSG_DATA(cmsg), iov); if (retval < 0) return retval; size += retval; break; case RDS_CMSG_ZCOPY_COOKIE: zcopy_cookie = true; fallthrough; case RDS_CMSG_RDMA_DEST: case RDS_CMSG_RDMA_MAP: cmsg_groups |= 2; /* these are valid but do no add any size */ break; case RDS_CMSG_ATOMIC_CSWP: case RDS_CMSG_ATOMIC_FADD: case RDS_CMSG_MASKED_ATOMIC_CSWP: case RDS_CMSG_MASKED_ATOMIC_FADD: cmsg_groups |= 1; size += sizeof(struct scatterlist); break; default: return -EINVAL; } } if ((msg->msg_flags & MSG_ZEROCOPY) && !zcopy_cookie) return -EINVAL; size += num_sgs * sizeof(struct scatterlist); /* Ensure (DEST, MAP) are never used with (ARGS, ATOMIC) */ if (cmsg_groups == 3) return -EINVAL; return size; } static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { u32 *cookie; if (cmsg->cmsg_len < CMSG_LEN(sizeof(*cookie)) || !rm->data.op_mmp_znotifier) return -EINVAL; cookie = CMSG_DATA(cmsg); rm->data.op_mmp_znotifier->z_cookie = *cookie; return 0; } static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, struct msghdr *msg, int *allocated_mr, struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; int ret = 0, ind = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_RDS) continue; /* As a side effect, RDMA_DEST and RDMA_MAP will set * rm->rdma.m_rdma_cookie and rm->rdma.m_rdma_mr. */ switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: if (ind >= vct->indx) return -ENOMEM; ret = rds_cmsg_rdma_args(rs, rm, cmsg, &vct->vec[ind]); ind++; break; case RDS_CMSG_RDMA_DEST: ret = rds_cmsg_rdma_dest(rs, rm, cmsg); break; case RDS_CMSG_RDMA_MAP: ret = rds_cmsg_rdma_map(rs, rm, cmsg); if (!ret) *allocated_mr = 1; else if (ret == -ENODEV) /* Accommodate the get_mr() case which can fail * if connection isn't established yet. */ ret = -EAGAIN; break; case RDS_CMSG_ATOMIC_CSWP: case RDS_CMSG_ATOMIC_FADD: case RDS_CMSG_MASKED_ATOMIC_CSWP: case RDS_CMSG_MASKED_ATOMIC_FADD: ret = rds_cmsg_atomic(rs, rm, cmsg); break; case RDS_CMSG_ZCOPY_COOKIE: ret = rds_cmsg_zcopy(rs, rm, cmsg); break; default: return -EINVAL; } if (ret) break; } return ret; } static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn, int nonblock) { int hash; if (conn->c_npaths == 0) hash = RDS_MPATH_HASH(rs, RDS_MPATH_WORKERS); else hash = RDS_MPATH_HASH(rs, conn->c_npaths); if (conn->c_npaths == 0 && hash != 0) { rds_send_ping(conn, 0); /* The underlying connection is not up yet. Need to wait * until it is up to be sure that the non-zero c_path can be * used. But if we are interrupted, we have to use the zero * c_path in case the connection ends up being non-MP capable. */ if (conn->c_npaths == 0) { /* Cannot wait for the connection be made, so just use * the base c_path. */ if (nonblock) return 0; if (wait_event_interruptible(conn->c_hs_waitq, conn->c_npaths != 0)) hash = 0; } if (conn->c_npaths == 1) hash = 0; } return hash; } static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes) { struct rds_rdma_args *args; struct cmsghdr *cmsg; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_RDS) continue; if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) { if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args))) return -EINVAL; args = CMSG_DATA(cmsg); *rdma_bytes += args->remote_vec.bytes; } } return 0; } int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); __be16 dport; struct rds_message *rm = NULL; struct rds_connection *conn; int ret = 0; int queued = 0, allocated_mr = 0; int nonblock = msg->msg_flags & MSG_DONTWAIT; long timeo = sock_sndtimeo(sk, nonblock); struct rds_conn_path *cpath; struct in6_addr daddr; __u32 scope_id = 0; size_t rdma_payload_len = 0; bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = DIV_ROUND_UP(payload_len, PAGE_SIZE); int namelen; struct rds_iov_vector_arr vct; int ind; memset(&vct, 0, sizeof(vct)); /* expect 1 RDMA CMSG per rds_sendmsg. can still grow if more needed. */ vct.incr = 1; /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT | MSG_ZEROCOPY)) { ret = -EOPNOTSUPP; goto out; } namelen = msg->msg_namelen; if (namelen != 0) { if (namelen < sizeof(*usin)) { ret = -EINVAL; goto out; } switch (usin->sin_family) { case AF_INET: if (usin->sin_addr.s_addr == htonl(INADDR_ANY) || usin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || ipv4_is_multicast(usin->sin_addr.s_addr)) { ret = -EINVAL; goto out; } ipv6_addr_set_v4mapped(usin->sin_addr.s_addr, &daddr); dport = usin->sin_port; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { int addr_type; if (namelen < sizeof(*sin6)) { ret = -EINVAL; goto out; } addr_type = ipv6_addr_type(&sin6->sin6_addr); if (!(addr_type & IPV6_ADDR_UNICAST)) { __be32 addr4; if (!(addr_type & IPV6_ADDR_MAPPED)) { ret = -EINVAL; goto out; } /* It is a mapped address. Need to do some * sanity checks. */ addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || ipv4_is_multicast(addr4)) { ret = -EINVAL; goto out; } } if (addr_type & IPV6_ADDR_LINKLOCAL) { if (sin6->sin6_scope_id == 0) { ret = -EINVAL; goto out; } scope_id = sin6->sin6_scope_id; } daddr = sin6->sin6_addr; dport = sin6->sin6_port; break; } #endif default: ret = -EINVAL; goto out; } } else { /* We only care about consistency with ->connect() */ lock_sock(sk); daddr = rs->rs_conn_addr; dport = rs->rs_conn_port; scope_id = rs->rs_bound_scope_id; release_sock(sk); } lock_sock(sk); if (ipv6_addr_any(&rs->rs_bound_addr) || ipv6_addr_any(&daddr)) { release_sock(sk); ret = -ENOTCONN; goto out; } else if (namelen != 0) { /* Cannot send to an IPv4 address using an IPv6 source * address and cannot send to an IPv6 address using an * IPv4 source address. */ if (ipv6_addr_v4mapped(&daddr) ^ ipv6_addr_v4mapped(&rs->rs_bound_addr)) { release_sock(sk); ret = -EOPNOTSUPP; goto out; } /* If the socket is already bound to a link local address, * it can only send to peers on the same link. But allow * communicating between link local and non-link local address. */ if (scope_id != rs->rs_bound_scope_id) { if (!scope_id) { scope_id = rs->rs_bound_scope_id; } else if (rs->rs_bound_scope_id) { release_sock(sk); ret = -EINVAL; goto out; } } } release_sock(sk); ret = rds_rdma_bytes(msg, &rdma_payload_len); if (ret) goto out; if (max_t(size_t, payload_len, rdma_payload_len) > RDS_MAX_MSG_SIZE) { ret = -EMSGSIZE; goto out; } if (payload_len > rds_sk_sndbuf(rs)) { ret = -EMSGSIZE; goto out; } if (zcopy) { if (rs->rs_transport->t_type != RDS_TRANS_TCP) { ret = -EOPNOTSUPP; goto out; } num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX); } /* size of rm including all sgs */ ret = rds_rm_size(msg, num_sgs, &vct); if (ret < 0) goto out; rm = rds_message_alloc(ret, GFP_KERNEL); if (!rm) { ret = -ENOMEM; goto out; } /* Attach data to the rm */ if (payload_len) { rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); if (IS_ERR(rm->data.op_sg)) { ret = PTR_ERR(rm->data.op_sg); goto out; } ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; } rm->data.op_active = 1; rm->m_daddr = daddr; /* rds_conn_create has a spinlock that runs with IRQ off. * Caching the conn in the socket helps a lot. */ if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr) && rs->rs_tos == rs->rs_conn->c_tos) { conn = rs->rs_conn; } else { conn = rds_conn_create_outgoing(sock_net(sock->sk), &rs->rs_bound_addr, &daddr, rs->rs_transport, rs->rs_tos, sock->sk->sk_allocation, scope_id); if (IS_ERR(conn)) { ret = PTR_ERR(conn); goto out; } rs->rs_conn = conn; } if (conn->c_trans->t_mp_capable) cpath = &conn->c_path[rds_send_mprds_hash(rs, conn, nonblock)]; else cpath = &conn->c_path[0]; rm->m_conn_path = cpath; /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); if (ret) goto out; if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", &rm->rdma, conn->c_trans->xmit_rdma); ret = -EOPNOTSUPP; goto out; } if (rm->atomic.op_active && !conn->c_trans->xmit_atomic) { printk_ratelimited(KERN_NOTICE "atomic_op %p conn xmit_atomic %p\n", &rm->atomic, conn->c_trans->xmit_atomic); ret = -EOPNOTSUPP; goto out; } if (rds_destroy_pending(conn)) { ret = -EAGAIN; goto out; } if (rds_conn_path_down(cpath)) rds_check_all_paths(conn); ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs); if (ret) { rs->rs_seen_congestion = 1; goto out; } while (!rds_send_queue_rm(rs, conn, cpath, rm, rs->rs_bound_port, dport, &queued)) { rds_stats_inc(s_send_queue_full); if (nonblock) { ret = -EAGAIN; goto out; } timeo = wait_event_interruptible_timeout(*sk_sleep(sk), rds_send_queue_rm(rs, conn, cpath, rm, rs->rs_bound_port, dport, &queued), timeo); rdsdebug("sendmsg woke queued %d timeo %ld\n", queued, timeo); if (timeo > 0 || timeo == MAX_SCHEDULE_TIMEOUT) continue; ret = timeo; if (ret == 0) ret = -ETIMEDOUT; goto out; } /* * By now we've committed to the send. We reuse rds_send_worker() * to retry sends in the rds thread if the transport asks us to. */ rds_stats_inc(s_send_queued); ret = rds_send_xmit(cpath); if (ret == -ENOMEM || ret == -EAGAIN) { ret = 0; rcu_read_lock(); if (rds_destroy_pending(cpath->cp_conn)) ret = -ENETUNREACH; else queue_delayed_work(rds_wq, &cpath->cp_send_w, 1); rcu_read_unlock(); } if (ret) goto out; rds_message_put(rm); for (ind = 0; ind < vct.indx; ind++) kfree(vct.vec[ind].iov); kfree(vct.vec); return payload_len; out: for (ind = 0; ind < vct.indx; ind++) kfree(vct.vec[ind].iov); kfree(vct.vec); /* If the user included a RDMA_MAP cmsg, we allocated a MR on the fly. * If the sendmsg goes through, we keep the MR. If it fails with EAGAIN * or in any other way, we need to destroy the MR again */ if (allocated_mr) rds_rdma_unuse(rs, rds_rdma_cookie_key(rm->m_rdma_cookie), 1); if (rm) rds_message_put(rm); return ret; } /* * send out a probe. Can be shared by rds_send_ping, * rds_send_pong, rds_send_hb. * rds_send_hb should use h_flags * RDS_FLAG_HB_PING|RDS_FLAG_ACK_REQUIRED * or * RDS_FLAG_HB_PONG|RDS_FLAG_ACK_REQUIRED */ static int rds_send_probe(struct rds_conn_path *cp, __be16 sport, __be16 dport, u8 h_flags) { struct rds_message *rm; unsigned long flags; int ret = 0; rm = rds_message_alloc(0, GFP_ATOMIC); if (!rm) { ret = -ENOMEM; goto out; } rm->m_daddr = cp->cp_conn->c_faddr; rm->data.op_active = 1; rds_conn_path_connect_if_down(cp); ret = rds_cong_wait(cp->cp_conn->c_fcong, dport, 1, NULL); if (ret) goto out; spin_lock_irqsave(&cp->cp_lock, flags); list_add_tail(&rm->m_conn_item, &cp->cp_send_queue); set_bit(RDS_MSG_ON_CONN, &rm->m_flags); rds_message_addref(rm); rm->m_inc.i_conn = cp->cp_conn; rm->m_inc.i_conn_path = cp; rds_message_populate_header(&rm->m_inc.i_hdr, sport, dport, cp->cp_next_tx_seq); rm->m_inc.i_hdr.h_flags |= h_flags; cp->cp_next_tx_seq++; if (RDS_HS_PROBE(be16_to_cpu(sport), be16_to_cpu(dport)) && cp->cp_conn->c_trans->t_mp_capable) { u16 npaths = cpu_to_be16(RDS_MPATH_WORKERS); u32 my_gen_num = cpu_to_be32(cp->cp_conn->c_my_gen_num); rds_message_add_extension(&rm->m_inc.i_hdr, RDS_EXTHDR_NPATHS, &npaths, sizeof(npaths)); rds_message_add_extension(&rm->m_inc.i_hdr, RDS_EXTHDR_GEN_NUM, &my_gen_num, sizeof(u32)); } spin_unlock_irqrestore(&cp->cp_lock, flags); rds_stats_inc(s_send_queued); rds_stats_inc(s_send_pong); /* schedule the send work on rds_wq */ rcu_read_lock(); if (!rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_send_w, 1); rcu_read_unlock(); rds_message_put(rm); return 0; out: if (rm) rds_message_put(rm); return ret; } int rds_send_pong(struct rds_conn_path *cp, __be16 dport) { return rds_send_probe(cp, 0, dport, 0); } void rds_send_ping(struct rds_connection *conn, int cp_index) { unsigned long flags; struct rds_conn_path *cp = &conn->c_path[cp_index]; spin_lock_irqsave(&cp->cp_lock, flags); if (conn->c_ping_triggered) { spin_unlock_irqrestore(&cp->cp_lock, flags); return; } conn->c_ping_triggered = 1; spin_unlock_irqrestore(&cp->cp_lock, flags); rds_send_probe(cp, cpu_to_be16(RDS_FLAG_PROBE_PORT), 0, 0); } EXPORT_SYMBOL_GPL(rds_send_ping); |
| 55 53 2 49 2 2 2 51 47 3 53 35 23 23 18 23 3 1 2 127 124 4 50 50 4 3 3 46 3 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfs/btree.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handle opening/closing btree */ #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/log2.h> #include "btree.h" /* Get a reference to a B*Tree and do some initial checks */ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp keycmp) { struct hfs_btree *tree; struct hfs_btree_header_rec *head; struct address_space *mapping; struct page *page; unsigned int size; tree = kzalloc(sizeof(*tree), GFP_KERNEL); if (!tree) return NULL; mutex_init(&tree->tree_lock); spin_lock_init(&tree->hash_lock); /* Set the correct compare function */ tree->sb = sb; tree->cnid = id; tree->keycmp = keycmp; tree->inode = iget_locked(sb, id); if (!tree->inode) goto free_tree; BUG_ON(!(tree->inode->i_state & I_NEW)); { struct hfs_mdb *mdb = HFS_SB(sb)->mdb; HFS_I(tree->inode)->flags = 0; mutex_init(&HFS_I(tree->inode)->extents_lock); switch (id) { case HFS_EXT_CNID: hfs_inode_read_fork(tree->inode, mdb->drXTExtRec, mdb->drXTFlSize, mdb->drXTFlSize, be32_to_cpu(mdb->drXTClpSiz)); if (HFS_I(tree->inode)->alloc_blocks > HFS_I(tree->inode)->first_blocks) { pr_err("invalid btree extent records\n"); unlock_new_inode(tree->inode); goto free_inode; } tree->inode->i_mapping->a_ops = &hfs_btree_aops; break; case HFS_CAT_CNID: hfs_inode_read_fork(tree->inode, mdb->drCTExtRec, mdb->drCTFlSize, mdb->drCTFlSize, be32_to_cpu(mdb->drCTClpSiz)); if (!HFS_I(tree->inode)->first_blocks) { pr_err("invalid btree extent records (0 size)\n"); unlock_new_inode(tree->inode); goto free_inode; } tree->inode->i_mapping->a_ops = &hfs_btree_aops; break; default: BUG(); } } unlock_new_inode(tree->inode); mapping = tree->inode->i_mapping; page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) goto free_inode; /* Load the header */ head = (struct hfs_btree_header_rec *)(kmap_local_page(page) + sizeof(struct hfs_bnode_desc)); tree->root = be32_to_cpu(head->root); tree->leaf_count = be32_to_cpu(head->leaf_count); tree->leaf_head = be32_to_cpu(head->leaf_head); tree->leaf_tail = be32_to_cpu(head->leaf_tail); tree->node_count = be32_to_cpu(head->node_count); tree->free_nodes = be32_to_cpu(head->free_nodes); tree->attributes = be32_to_cpu(head->attributes); tree->node_size = be16_to_cpu(head->node_size); tree->max_key_len = be16_to_cpu(head->max_key_len); tree->depth = be16_to_cpu(head->depth); size = tree->node_size; if (!is_power_of_2(size)) goto fail_page; if (!tree->node_count) goto fail_page; switch (id) { case HFS_EXT_CNID: if (tree->max_key_len != HFS_MAX_EXT_KEYLEN) { pr_err("invalid extent max_key_len %d\n", tree->max_key_len); goto fail_page; } break; case HFS_CAT_CNID: if (tree->max_key_len != HFS_MAX_CAT_KEYLEN) { pr_err("invalid catalog max_key_len %d\n", tree->max_key_len); goto fail_page; } break; default: BUG(); } tree->node_size_shift = ffs(size) - 1; tree->pages_per_bnode = (tree->node_size + PAGE_SIZE - 1) >> PAGE_SHIFT; kunmap_local(head); put_page(page); return tree; fail_page: kunmap_local(head); put_page(page); free_inode: tree->inode->i_mapping->a_ops = &hfs_aops; iput(tree->inode); free_tree: kfree(tree); return NULL; } /* Release resources used by a btree */ void hfs_btree_close(struct hfs_btree *tree) { struct hfs_bnode *node; int i; if (!tree) return; for (i = 0; i < NODE_HASH_SIZE; i++) { while ((node = tree->node_hash[i])) { tree->node_hash[i] = node->next_hash; if (atomic_read(&node->refcnt)) pr_err("node %d:%d still has %d user(s)!\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); hfs_bnode_free(node); tree->node_hash_cnt--; } } iput(tree->inode); kfree(tree); } void hfs_btree_write(struct hfs_btree *tree) { struct hfs_btree_header_rec *head; struct hfs_bnode *node; struct page *page; node = hfs_bnode_find(tree, 0); if (IS_ERR(node)) /* panic? */ return; /* Load the header */ page = node->page[0]; head = (struct hfs_btree_header_rec *)(kmap_local_page(page) + sizeof(struct hfs_bnode_desc)); head->root = cpu_to_be32(tree->root); head->leaf_count = cpu_to_be32(tree->leaf_count); head->leaf_head = cpu_to_be32(tree->leaf_head); head->leaf_tail = cpu_to_be32(tree->leaf_tail); head->node_count = cpu_to_be32(tree->node_count); head->free_nodes = cpu_to_be32(tree->free_nodes); head->attributes = cpu_to_be32(tree->attributes); head->depth = cpu_to_be16(tree->depth); kunmap_local(head); set_page_dirty(page); hfs_bnode_put(node); } static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx) { struct hfs_btree *tree = prev->tree; struct hfs_bnode *node; struct hfs_bnode_desc desc; __be32 cnid; node = hfs_bnode_create(tree, idx); if (IS_ERR(node)) return node; if (!tree->free_nodes) panic("FIXME!!!"); tree->free_nodes--; prev->next = idx; cnid = cpu_to_be32(idx); hfs_bnode_write(prev, &cnid, offsetof(struct hfs_bnode_desc, next), 4); node->type = HFS_NODE_MAP; node->num_recs = 1; hfs_bnode_clear(node, 0, tree->node_size); desc.next = 0; desc.prev = 0; desc.type = HFS_NODE_MAP; desc.height = 0; desc.num_recs = cpu_to_be16(1); desc.reserved = 0; hfs_bnode_write(node, &desc, 0, sizeof(desc)); hfs_bnode_write_u16(node, 14, 0x8000); hfs_bnode_write_u16(node, tree->node_size - 2, 14); hfs_bnode_write_u16(node, tree->node_size - 4, tree->node_size - 6); return node; } /* Make sure @tree has enough space for the @rsvd_nodes */ int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes) { struct inode *inode = tree->inode; u32 count; int res; while (tree->free_nodes < rsvd_nodes) { res = hfs_extend_file(inode); if (res) return res; HFS_I(inode)->phys_size = inode->i_size = (loff_t)HFS_I(inode)->alloc_blocks * HFS_SB(tree->sb)->alloc_blksz; HFS_I(inode)->fs_blocks = inode->i_size >> tree->sb->s_blocksize_bits; inode_set_bytes(inode, inode->i_size); count = inode->i_size >> tree->node_size_shift; tree->free_nodes += count - tree->node_count; tree->node_count = count; } return 0; } struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree) { struct hfs_bnode *node, *next_node; struct page **pagep; u32 nidx, idx; unsigned off; u16 off16; u16 len; u8 *data, byte, m; int i, res; res = hfs_bmap_reserve(tree, 1); if (res) return ERR_PTR(res); nidx = 0; node = hfs_bnode_find(tree, nidx); if (IS_ERR(node)) return node; len = hfs_brec_lenoff(node, 2, &off16); off = off16; off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); data = kmap_local_page(*pagep); off &= ~PAGE_MASK; idx = 0; for (;;) { while (len) { byte = data[off]; if (byte != 0xff) { for (m = 0x80, i = 0; i < 8; m >>= 1, i++) { if (!(byte & m)) { idx += i; data[off] |= m; set_page_dirty(*pagep); kunmap_local(data); tree->free_nodes--; mark_inode_dirty(tree->inode); hfs_bnode_put(node); return hfs_bnode_create(tree, idx); } } } if (++off >= PAGE_SIZE) { kunmap_local(data); data = kmap_local_page(*++pagep); off = 0; } idx += 8; len--; } kunmap_local(data); nidx = node->next; if (!nidx) { printk(KERN_DEBUG "create new bmap node...\n"); next_node = hfs_bmap_new_bmap(node, idx); } else next_node = hfs_bnode_find(tree, nidx); hfs_bnode_put(node); if (IS_ERR(next_node)) return next_node; node = next_node; len = hfs_brec_lenoff(node, 0, &off16); off = off16; off += node->page_offset; pagep = node->page + (off >> PAGE_SHIFT); data = kmap_local_page(*pagep); off &= ~PAGE_MASK; } } void hfs_bmap_free(struct hfs_bnode *node) { struct hfs_btree *tree; struct page *page; u16 off, len; u32 nidx; u8 *data, byte, m; hfs_dbg(BNODE_MOD, "btree_free_node: %u\n", node->this); tree = node->tree; nidx = node->this; node = hfs_bnode_find(tree, 0); if (IS_ERR(node)) return; len = hfs_brec_lenoff(node, 2, &off); while (nidx >= len * 8) { u32 i; nidx -= len * 8; i = node->next; if (!i) { /* panic */; pr_crit("unable to free bnode %u. bmap not found!\n", node->this); hfs_bnode_put(node); return; } hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return; if (node->type != HFS_NODE_MAP) { /* panic */; pr_crit("invalid bmap found! (%u,%d)\n", node->this, node->type); hfs_bnode_put(node); return; } len = hfs_brec_lenoff(node, 0, &off); } off += node->page_offset + nidx / 8; page = node->page[off >> PAGE_SHIFT]; data = kmap_local_page(page); off &= ~PAGE_MASK; m = 1 << (~nidx & 7); byte = data[off]; if (!(byte & m)) { pr_crit("trying to free free bnode %u(%d)\n", node->this, node->type); kunmap_local(data); hfs_bnode_put(node); return; } data[off] = byte & ~m; set_page_dirty(page); kunmap_local(data); hfs_bnode_put(node); tree->free_nodes++; mark_inode_dirty(tree->inode); } |
| 13 13 11 11 9 10 7 3 10 16 6 2 3 3 2 3 1 2 16 7 19 8 8 5 2 3 2 5 1 7 8 8 1 6 1 4 6 1 3 1 2 2 2 2 27 27 1 1 25 1 4 16 20 6 21 27 27 10 1 1 2 2 6 6 5 1 1 8 1 2 3 5 5 5 1 5 5 5 4 5 1 1 1 8 1 2 5 1 4 4 3 1 2 2 6 2 1 4 4 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware VMCI Driver * * Copyright (C) 2012 VMware, Inc. All rights reserved. */ #include <linux/vmw_vmci_defs.h> #include <linux/vmw_vmci_api.h> #include <linux/highmem.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/pagemap.h> #include <linux/pci.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/uio.h> #include <linux/wait.h> #include <linux/vmalloc.h> #include <linux/skbuff.h> #include "vmci_handle_array.h" #include "vmci_queue_pair.h" #include "vmci_datagram.h" #include "vmci_resource.h" #include "vmci_context.h" #include "vmci_driver.h" #include "vmci_event.h" #include "vmci_route.h" /* * In the following, we will distinguish between two kinds of VMX processes - * the ones with versions lower than VMCI_VERSION_NOVMVM that use specialized * VMCI page files in the VMX and supporting VM to VM communication and the * newer ones that use the guest memory directly. We will in the following * refer to the older VMX versions as old-style VMX'en, and the newer ones as * new-style VMX'en. * * The state transition datagram is as follows (the VMCIQPB_ prefix has been * removed for readability) - see below for more details on the transtions: * * -------------- NEW ------------- * | | * \_/ \_/ * CREATED_NO_MEM <-----------------> CREATED_MEM * | | | * | o-----------------------o | * | | | * \_/ \_/ \_/ * ATTACHED_NO_MEM <----------------> ATTACHED_MEM * | | | * | o----------------------o | * | | | * \_/ \_/ \_/ * SHUTDOWN_NO_MEM <----------------> SHUTDOWN_MEM * | | * | | * -------------> gone <------------- * * In more detail. When a VMCI queue pair is first created, it will be in the * VMCIQPB_NEW state. It will then move into one of the following states: * * - VMCIQPB_CREATED_NO_MEM: this state indicates that either: * * - the created was performed by a host endpoint, in which case there is * no backing memory yet. * * - the create was initiated by an old-style VMX, that uses * vmci_qp_broker_set_page_store to specify the UVAs of the queue pair at * a later point in time. This state can be distinguished from the one * above by the context ID of the creator. A host side is not allowed to * attach until the page store has been set. * * - VMCIQPB_CREATED_MEM: this state is the result when the queue pair * is created by a VMX using the queue pair device backend that * sets the UVAs of the queue pair immediately and stores the * information for later attachers. At this point, it is ready for * the host side to attach to it. * * Once the queue pair is in one of the created states (with the exception of * the case mentioned for older VMX'en above), it is possible to attach to the * queue pair. Again we have two new states possible: * * - VMCIQPB_ATTACHED_MEM: this state can be reached through the following * paths: * * - from VMCIQPB_CREATED_NO_MEM when a new-style VMX allocates a queue * pair, and attaches to a queue pair previously created by the host side. * * - from VMCIQPB_CREATED_MEM when the host side attaches to a queue pair * already created by a guest. * * - from VMCIQPB_ATTACHED_NO_MEM, when an old-style VMX calls * vmci_qp_broker_set_page_store (see below). * * - VMCIQPB_ATTACHED_NO_MEM: If the queue pair already was in the * VMCIQPB_CREATED_NO_MEM due to a host side create, an old-style VMX will * bring the queue pair into this state. Once vmci_qp_broker_set_page_store * is called to register the user memory, the VMCIQPB_ATTACH_MEM state * will be entered. * * From the attached queue pair, the queue pair can enter the shutdown states * when either side of the queue pair detaches. If the guest side detaches * first, the queue pair will enter the VMCIQPB_SHUTDOWN_NO_MEM state, where * the content of the queue pair will no longer be available. If the host * side detaches first, the queue pair will either enter the * VMCIQPB_SHUTDOWN_MEM, if the guest memory is currently mapped, or * VMCIQPB_SHUTDOWN_NO_MEM, if the guest memory is not mapped * (e.g., the host detaches while a guest is stunned). * * New-style VMX'en will also unmap guest memory, if the guest is * quiesced, e.g., during a snapshot operation. In that case, the guest * memory will no longer be available, and the queue pair will transition from * *_MEM state to a *_NO_MEM state. The VMX may later map the memory once more, * in which case the queue pair will transition from the *_NO_MEM state at that * point back to the *_MEM state. Note that the *_NO_MEM state may have changed, * since the peer may have either attached or detached in the meantime. The * values are laid out such that ++ on a state will move from a *_NO_MEM to a * *_MEM state, and vice versa. */ /* The Kernel specific component of the struct vmci_queue structure. */ struct vmci_queue_kern_if { struct mutex __mutex; /* Protects the queue. */ struct mutex *mutex; /* Shared by producer and consumer queues. */ size_t num_pages; /* Number of pages incl. header. */ bool host; /* Host or guest? */ union { struct { dma_addr_t *pas; void **vas; } g; /* Used by the guest. */ struct { struct page **page; struct page **header_page; } h; /* Used by the host. */ } u; }; /* * This structure is opaque to the clients. */ struct vmci_qp { struct vmci_handle handle; struct vmci_queue *produce_q; struct vmci_queue *consume_q; u64 produce_q_size; u64 consume_q_size; u32 peer; u32 flags; u32 priv_flags; bool guest_endpoint; unsigned int blocked; unsigned int generation; wait_queue_head_t event; }; enum qp_broker_state { VMCIQPB_NEW, VMCIQPB_CREATED_NO_MEM, VMCIQPB_CREATED_MEM, VMCIQPB_ATTACHED_NO_MEM, VMCIQPB_ATTACHED_MEM, VMCIQPB_SHUTDOWN_NO_MEM, VMCIQPB_SHUTDOWN_MEM, VMCIQPB_GONE }; #define QPBROKERSTATE_HAS_MEM(_qpb) (_qpb->state == VMCIQPB_CREATED_MEM || \ _qpb->state == VMCIQPB_ATTACHED_MEM || \ _qpb->state == VMCIQPB_SHUTDOWN_MEM) /* * In the queue pair broker, we always use the guest point of view for * the produce and consume queue values and references, e.g., the * produce queue size stored is the guests produce queue size. The * host endpoint will need to swap these around. The only exception is * the local queue pairs on the host, in which case the host endpoint * that creates the queue pair will have the right orientation, and * the attaching host endpoint will need to swap. */ struct qp_entry { struct list_head list_item; struct vmci_handle handle; u32 peer; u32 flags; u64 produce_size; u64 consume_size; u32 ref_count; }; struct qp_broker_entry { struct vmci_resource resource; struct qp_entry qp; u32 create_id; u32 attach_id; enum qp_broker_state state; bool require_trusted_attach; bool created_by_trusted; bool vmci_page_files; /* Created by VMX using VMCI page files */ struct vmci_queue *produce_q; struct vmci_queue *consume_q; struct vmci_queue_header saved_produce_q; struct vmci_queue_header saved_consume_q; vmci_event_release_cb wakeup_cb; void *client_data; void *local_mem; /* Kernel memory for local queue pair */ }; struct qp_guest_endpoint { struct vmci_resource resource; struct qp_entry qp; u64 num_ppns; void *produce_q; void *consume_q; struct ppn_set ppn_set; }; struct qp_list { struct list_head head; struct mutex mutex; /* Protect queue list. */ }; static struct qp_list qp_broker_list = { .head = LIST_HEAD_INIT(qp_broker_list.head), .mutex = __MUTEX_INITIALIZER(qp_broker_list.mutex), }; static struct qp_list qp_guest_endpoints = { .head = LIST_HEAD_INIT(qp_guest_endpoints.head), .mutex = __MUTEX_INITIALIZER(qp_guest_endpoints.mutex), }; #define INVALID_VMCI_GUEST_MEM_ID 0 #define QPE_NUM_PAGES(_QPE) ((u32) \ (DIV_ROUND_UP(_QPE.produce_size, PAGE_SIZE) + \ DIV_ROUND_UP(_QPE.consume_size, PAGE_SIZE) + 2)) #define QP_SIZES_ARE_VALID(_prod_qsize, _cons_qsize) \ ((_prod_qsize) + (_cons_qsize) >= max(_prod_qsize, _cons_qsize) && \ (_prod_qsize) + (_cons_qsize) <= VMCI_MAX_GUEST_QP_MEMORY) /* * Frees kernel VA space for a given queue and its queue header, and * frees physical data pages. */ static void qp_free_queue(void *q, u64 size) { struct vmci_queue *queue = q; if (queue) { u64 i; /* Given size does not include header, so add in a page here. */ for (i = 0; i < DIV_ROUND_UP(size, PAGE_SIZE) + 1; i++) { dma_free_coherent(&vmci_pdev->dev, PAGE_SIZE, queue->kernel_if->u.g.vas[i], queue->kernel_if->u.g.pas[i]); } vfree(queue); } } /* * Allocates kernel queue pages of specified size with IOMMU mappings, * plus space for the queue structure/kernel interface and the queue * header. */ static void *qp_alloc_queue(u64 size, u32 flags) { u64 i; struct vmci_queue *queue; size_t pas_size; size_t vas_size; size_t queue_size = sizeof(*queue) + sizeof(*queue->kernel_if); u64 num_pages; if (size > SIZE_MAX - PAGE_SIZE) return NULL; num_pages = DIV_ROUND_UP(size, PAGE_SIZE) + 1; if (num_pages > (SIZE_MAX - queue_size) / (sizeof(*queue->kernel_if->u.g.pas) + sizeof(*queue->kernel_if->u.g.vas))) return NULL; pas_size = num_pages * sizeof(*queue->kernel_if->u.g.pas); vas_size = num_pages * sizeof(*queue->kernel_if->u.g.vas); queue_size += pas_size + vas_size; queue = vmalloc(queue_size); if (!queue) return NULL; queue->q_header = NULL; queue->saved_header = NULL; queue->kernel_if = (struct vmci_queue_kern_if *)(queue + 1); queue->kernel_if->mutex = NULL; queue->kernel_if->num_pages = num_pages; queue->kernel_if->u.g.pas = (dma_addr_t *)(queue->kernel_if + 1); queue->kernel_if->u.g.vas = (void **)((u8 *)queue->kernel_if->u.g.pas + pas_size); queue->kernel_if->host = false; for (i = 0; i < num_pages; i++) { queue->kernel_if->u.g.vas[i] = dma_alloc_coherent(&vmci_pdev->dev, PAGE_SIZE, &queue->kernel_if->u.g.pas[i], GFP_KERNEL); if (!queue->kernel_if->u.g.vas[i]) { /* Size excl. the header. */ qp_free_queue(queue, i * PAGE_SIZE); return NULL; } } /* Queue header is the first page. */ queue->q_header = queue->kernel_if->u.g.vas[0]; return queue; } /* * Copies from a given buffer or iovector to a VMCI Queue. Uses * kmap_local_page() to dynamically map required portions of the queue * by traversing the offset -> page translation structure for the queue. * Assumes that offset + size does not wrap around in the queue. */ static int qp_memcpy_to_queue_iter(struct vmci_queue *queue, u64 queue_offset, struct iov_iter *from, size_t size) { struct vmci_queue_kern_if *kernel_if = queue->kernel_if; size_t bytes_copied = 0; while (bytes_copied < size) { const u64 page_index = (queue_offset + bytes_copied) / PAGE_SIZE; const size_t page_offset = (queue_offset + bytes_copied) & (PAGE_SIZE - 1); void *va; size_t to_copy; if (kernel_if->host) va = kmap_local_page(kernel_if->u.h.page[page_index]); else va = kernel_if->u.g.vas[page_index + 1]; /* Skip header. */ if (size - bytes_copied > PAGE_SIZE - page_offset) /* Enough payload to fill up from this page. */ to_copy = PAGE_SIZE - page_offset; else to_copy = size - bytes_copied; if (!copy_from_iter_full((u8 *)va + page_offset, to_copy, from)) { if (kernel_if->host) kunmap_local(va); return VMCI_ERROR_INVALID_ARGS; } bytes_copied += to_copy; if (kernel_if->host) kunmap_local(va); } return VMCI_SUCCESS; } /* * Copies to a given buffer or iovector from a VMCI Queue. Uses * kmap_local_page() to dynamically map required portions of the queue * by traversing the offset -> page translation structure for the queue. * Assumes that offset + size does not wrap around in the queue. */ static int qp_memcpy_from_queue_iter(struct iov_iter *to, const struct vmci_queue *queue, u64 queue_offset, size_t size) { struct vmci_queue_kern_if *kernel_if = queue->kernel_if; size_t bytes_copied = 0; while (bytes_copied < size) { const u64 page_index = (queue_offset + bytes_copied) / PAGE_SIZE; const size_t page_offset = (queue_offset + bytes_copied) & (PAGE_SIZE - 1); void *va; size_t to_copy; int err; if (kernel_if->host) va = kmap_local_page(kernel_if->u.h.page[page_index]); else va = kernel_if->u.g.vas[page_index + 1]; /* Skip header. */ if (size - bytes_copied > PAGE_SIZE - page_offset) /* Enough payload to fill up this page. */ to_copy = PAGE_SIZE - page_offset; else to_copy = size - bytes_copied; err = copy_to_iter((u8 *)va + page_offset, to_copy, to); if (err != to_copy) { if (kernel_if->host) kunmap_local(va); return VMCI_ERROR_INVALID_ARGS; } bytes_copied += to_copy; if (kernel_if->host) kunmap_local(va); } return VMCI_SUCCESS; } /* * Allocates two list of PPNs --- one for the pages in the produce queue, * and the other for the pages in the consume queue. Intializes the list * of PPNs with the page frame numbers of the KVA for the two queues (and * the queue headers). */ static int qp_alloc_ppn_set(void *prod_q, u64 num_produce_pages, void *cons_q, u64 num_consume_pages, struct ppn_set *ppn_set) { u64 *produce_ppns; u64 *consume_ppns; struct vmci_queue *produce_q = prod_q; struct vmci_queue *consume_q = cons_q; u64 i; if (!produce_q || !num_produce_pages || !consume_q || !num_consume_pages || !ppn_set) return VMCI_ERROR_INVALID_ARGS; if (ppn_set->initialized) return VMCI_ERROR_ALREADY_EXISTS; produce_ppns = kmalloc_array(num_produce_pages, sizeof(*produce_ppns), GFP_KERNEL); if (!produce_ppns) return VMCI_ERROR_NO_MEM; consume_ppns = kmalloc_array(num_consume_pages, sizeof(*consume_ppns), GFP_KERNEL); if (!consume_ppns) { kfree(produce_ppns); return VMCI_ERROR_NO_MEM; } for (i = 0; i < num_produce_pages; i++) produce_ppns[i] = produce_q->kernel_if->u.g.pas[i] >> PAGE_SHIFT; for (i = 0; i < num_consume_pages; i++) consume_ppns[i] = consume_q->kernel_if->u.g.pas[i] >> PAGE_SHIFT; ppn_set->num_produce_pages = num_produce_pages; ppn_set->num_consume_pages = num_consume_pages; ppn_set->produce_ppns = produce_ppns; ppn_set->consume_ppns = consume_ppns; ppn_set->initialized = true; return VMCI_SUCCESS; } /* * Frees the two list of PPNs for a queue pair. */ static void qp_free_ppn_set(struct ppn_set *ppn_set) { if (ppn_set->initialized) { /* Do not call these functions on NULL inputs. */ kfree(ppn_set->produce_ppns); kfree(ppn_set->consume_ppns); } memset(ppn_set, 0, sizeof(*ppn_set)); } /* * Populates the list of PPNs in the hypercall structure with the PPNS * of the produce queue and the consume queue. */ static int qp_populate_ppn_set(u8 *call_buf, const struct ppn_set *ppn_set) { if (vmci_use_ppn64()) { memcpy(call_buf, ppn_set->produce_ppns, ppn_set->num_produce_pages * sizeof(*ppn_set->produce_ppns)); memcpy(call_buf + ppn_set->num_produce_pages * sizeof(*ppn_set->produce_ppns), ppn_set->consume_ppns, ppn_set->num_consume_pages * sizeof(*ppn_set->consume_ppns)); } else { int i; u32 *ppns = (u32 *) call_buf; for (i = 0; i < ppn_set->num_produce_pages; i++) ppns[i] = (u32) ppn_set->produce_ppns[i]; ppns = &ppns[ppn_set->num_produce_pages]; for (i = 0; i < ppn_set->num_consume_pages; i++) ppns[i] = (u32) ppn_set->consume_ppns[i]; } return VMCI_SUCCESS; } /* * Allocates kernel VA space of specified size plus space for the queue * and kernel interface. This is different from the guest queue allocator, * because we do not allocate our own queue header/data pages here but * share those of the guest. */ static struct vmci_queue *qp_host_alloc_queue(u64 size) { struct vmci_queue *queue; size_t queue_page_size; u64 num_pages; const size_t queue_size = sizeof(*queue) + sizeof(*(queue->kernel_if)); if (size > min_t(size_t, VMCI_MAX_GUEST_QP_MEMORY, SIZE_MAX - PAGE_SIZE)) return NULL; num_pages = DIV_ROUND_UP(size, PAGE_SIZE) + 1; if (num_pages > (SIZE_MAX - queue_size) / sizeof(*queue->kernel_if->u.h.page)) return NULL; queue_page_size = num_pages * sizeof(*queue->kernel_if->u.h.page); if (queue_size + queue_page_size > KMALLOC_MAX_SIZE) return NULL; queue = kzalloc(queue_size + queue_page_size, GFP_KERNEL); if (queue) { queue->q_header = NULL; queue->saved_header = NULL; queue->kernel_if = (struct vmci_queue_kern_if *)(queue + 1); queue->kernel_if->host = true; queue->kernel_if->mutex = NULL; queue->kernel_if->num_pages = num_pages; queue->kernel_if->u.h.header_page = (struct page **)((u8 *)queue + queue_size); queue->kernel_if->u.h.page = &queue->kernel_if->u.h.header_page[1]; } return queue; } /* * Frees kernel memory for a given queue (header plus translation * structure). */ static void qp_host_free_queue(struct vmci_queue *queue, u64 queue_size) { kfree(queue); } /* * Initialize the mutex for the pair of queues. This mutex is used to * protect the q_header and the buffer from changing out from under any * users of either queue. Of course, it's only any good if the mutexes * are actually acquired. Queue structure must lie on non-paged memory * or we cannot guarantee access to the mutex. */ static void qp_init_queue_mutex(struct vmci_queue *produce_q, struct vmci_queue *consume_q) { /* * Only the host queue has shared state - the guest queues do not * need to synchronize access using a queue mutex. */ if (produce_q->kernel_if->host) { produce_q->kernel_if->mutex = &produce_q->kernel_if->__mutex; consume_q->kernel_if->mutex = &produce_q->kernel_if->__mutex; mutex_init(produce_q->kernel_if->mutex); } } /* * Cleans up the mutex for the pair of queues. */ static void qp_cleanup_queue_mutex(struct vmci_queue *produce_q, struct vmci_queue *consume_q) { if (produce_q->kernel_if->host) { produce_q->kernel_if->mutex = NULL; consume_q->kernel_if->mutex = NULL; } } /* * Acquire the mutex for the queue. Note that the produce_q and * the consume_q share a mutex. So, only one of the two need to * be passed in to this routine. Either will work just fine. */ static void qp_acquire_queue_mutex(struct vmci_queue *queue) { if (queue->kernel_if->host) mutex_lock(queue->kernel_if->mutex); } /* * Release the mutex for the queue. Note that the produce_q and * the consume_q share a mutex. So, only one of the two need to * be passed in to this routine. Either will work just fine. */ static void qp_release_queue_mutex(struct vmci_queue *queue) { if (queue->kernel_if->host) mutex_unlock(queue->kernel_if->mutex); } /* * Helper function to release pages in the PageStoreAttachInfo * previously obtained using get_user_pages. */ static void qp_release_pages(struct page **pages, u64 num_pages, bool dirty) { int i; for (i = 0; i < num_pages; i++) { if (dirty) set_page_dirty_lock(pages[i]); put_page(pages[i]); pages[i] = NULL; } } /* * Lock the user pages referenced by the {produce,consume}Buffer * struct into memory and populate the {produce,consume}Pages * arrays in the attach structure with them. */ static int qp_host_get_user_memory(u64 produce_uva, u64 consume_uva, struct vmci_queue *produce_q, struct vmci_queue *consume_q) { int retval; int err = VMCI_SUCCESS; retval = get_user_pages_fast((uintptr_t) produce_uva, produce_q->kernel_if->num_pages, FOLL_WRITE, produce_q->kernel_if->u.h.header_page); if (retval < (int)produce_q->kernel_if->num_pages) { pr_debug("get_user_pages_fast(produce) failed (retval=%d)", retval); if (retval > 0) qp_release_pages(produce_q->kernel_if->u.h.header_page, retval, false); err = VMCI_ERROR_NO_MEM; goto out; } retval = get_user_pages_fast((uintptr_t) consume_uva, consume_q->kernel_if->num_pages, FOLL_WRITE, consume_q->kernel_if->u.h.header_page); if (retval < (int)consume_q->kernel_if->num_pages) { pr_debug("get_user_pages_fast(consume) failed (retval=%d)", retval); if (retval > 0) qp_release_pages(consume_q->kernel_if->u.h.header_page, retval, false); qp_release_pages(produce_q->kernel_if->u.h.header_page, produce_q->kernel_if->num_pages, false); err = VMCI_ERROR_NO_MEM; } out: return err; } /* * Registers the specification of the user pages used for backing a queue * pair. Enough information to map in pages is stored in the OS specific * part of the struct vmci_queue structure. */ static int qp_host_register_user_memory(struct vmci_qp_page_store *page_store, struct vmci_queue *produce_q, struct vmci_queue *consume_q) { u64 produce_uva; u64 consume_uva; /* * The new style and the old style mapping only differs in * that we either get a single or two UVAs, so we split the * single UVA range at the appropriate spot. */ produce_uva = page_store->pages; consume_uva = page_store->pages + produce_q->kernel_if->num_pages * PAGE_SIZE; return qp_host_get_user_memory(produce_uva, consume_uva, produce_q, consume_q); } /* * Releases and removes the references to user pages stored in the attach * struct. Pages are released from the page cache and may become * swappable again. */ static void qp_host_unregister_user_memory(struct vmci_queue *produce_q, struct vmci_queue *consume_q) { qp_release_pages(produce_q->kernel_if->u.h.header_page, produce_q->kernel_if->num_pages, true); memset(produce_q->kernel_if->u.h.header_page, 0, sizeof(*produce_q->kernel_if->u.h.header_page) * produce_q->kernel_if->num_pages); qp_release_pages(consume_q->kernel_if->u.h.header_page, consume_q->kernel_if->num_pages, true); memset(consume_q->kernel_if->u.h.header_page, 0, sizeof(*consume_q->kernel_if->u.h.header_page) * consume_q->kernel_if->num_pages); } /* * Once qp_host_register_user_memory has been performed on a * queue, the queue pair headers can be mapped into the * kernel. Once mapped, they must be unmapped with * qp_host_unmap_queues prior to calling * qp_host_unregister_user_memory. * Pages are pinned. */ static int qp_host_map_queues(struct vmci_queue *produce_q, struct vmci_queue *consume_q) { int result; if (!produce_q->q_header || !consume_q->q_header) { struct page *headers[2]; if (produce_q->q_header != consume_q->q_header) return VMCI_ERROR_QUEUEPAIR_MISMATCH; if (produce_q->kernel_if->u.h.header_page == NULL || *produce_q->kernel_if->u.h.header_page == NULL) return VMCI_ERROR_UNAVAILABLE; headers[0] = *produce_q->kernel_if->u.h.header_page; headers[1] = *consume_q->kernel_if->u.h.header_page; produce_q->q_header = vmap(headers, 2, VM_MAP, PAGE_KERNEL); if (produce_q->q_header != NULL) { consume_q->q_header = (struct vmci_queue_header *)((u8 *) produce_q->q_header + PAGE_SIZE); result = VMCI_SUCCESS; } else { pr_warn("vmap failed\n"); result = VMCI_ERROR_NO_MEM; } } else { result = VMCI_SUCCESS; } return result; } /* * Unmaps previously mapped queue pair headers from the kernel. * Pages are unpinned. */ static int qp_host_unmap_queues(u32 gid, struct vmci_queue *produce_q, struct vmci_queue *consume_q) { if (produce_q->q_header) { if (produce_q->q_header < consume_q->q_header) vunmap(produce_q->q_header); else vunmap(consume_q->q_header); produce_q->q_header = NULL; consume_q->q_header = NULL; } return VMCI_SUCCESS; } /* * Finds the entry in the list corresponding to a given handle. Assumes * that the list is locked. */ static struct qp_entry *qp_list_find(struct qp_list *qp_list, struct vmci_handle handle) { struct qp_entry *entry; if (vmci_handle_is_invalid(handle)) return NULL; list_for_each_entry(entry, &qp_list->head, list_item) { if (vmci_handle_is_equal(entry->handle, handle)) return entry; } return NULL; } /* * Finds the entry in the list corresponding to a given handle. */ static struct qp_guest_endpoint * qp_guest_handle_to_entry(struct vmci_handle handle) { struct qp_guest_endpoint *entry; struct qp_entry *qp = qp_list_find(&qp_guest_endpoints, handle); entry = qp ? container_of( qp, struct qp_guest_endpoint, qp) : NULL; return entry; } /* * Finds the entry in the list corresponding to a given handle. */ static struct qp_broker_entry * qp_broker_handle_to_entry(struct vmci_handle handle) { struct qp_broker_entry *entry; struct qp_entry *qp = qp_list_find(&qp_broker_list, handle); entry = qp ? container_of( qp, struct qp_broker_entry, qp) : NULL; return entry; } /* * Dispatches a queue pair event message directly into the local event * queue. */ static int qp_notify_peer_local(bool attach, struct vmci_handle handle) { u32 context_id = vmci_get_context_id(); struct vmci_event_qp ev; memset(&ev, 0, sizeof(ev)); ev.msg.hdr.dst = vmci_make_handle(context_id, VMCI_EVENT_HANDLER); ev.msg.hdr.src = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID, VMCI_CONTEXT_RESOURCE_ID); ev.msg.hdr.payload_size = sizeof(ev) - sizeof(ev.msg.hdr); ev.msg.event_data.event = attach ? VMCI_EVENT_QP_PEER_ATTACH : VMCI_EVENT_QP_PEER_DETACH; ev.payload.peer_id = context_id; ev.payload.handle = handle; return vmci_event_dispatch(&ev.msg.hdr); } /* * Allocates and initializes a qp_guest_endpoint structure. * Allocates a queue_pair rid (and handle) iff the given entry has * an invalid handle. 0 through VMCI_RESERVED_RESOURCE_ID_MAX * are reserved handles. Assumes that the QP list mutex is held * by the caller. */ static struct qp_guest_endpoint * qp_guest_endpoint_create(struct vmci_handle handle, u32 peer, u32 flags, u64 produce_size, u64 consume_size, void *produce_q, void *consume_q) { int result; struct qp_guest_endpoint *entry; /* One page each for the queue headers. */ const u64 num_ppns = DIV_ROUND_UP(produce_size, PAGE_SIZE) + DIV_ROUND_UP(consume_size, PAGE_SIZE) + 2; if (vmci_handle_is_invalid(handle)) { u32 context_id = vmci_get_context_id(); handle = vmci_make_handle(context_id, VMCI_INVALID_ID); } entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry) { entry->qp.peer = peer; entry->qp.flags = flags; entry->qp.produce_size = produce_size; entry->qp.consume_size = consume_size; entry->qp.ref_count = 0; entry->num_ppns = num_ppns; entry->produce_q = produce_q; entry->consume_q = consume_q; INIT_LIST_HEAD(&entry->qp.list_item); /* Add resource obj */ result = vmci_resource_add(&entry->resource, VMCI_RESOURCE_TYPE_QPAIR_GUEST, handle); entry->qp.handle = vmci_resource_handle(&entry->resource); if ((result != VMCI_SUCCESS) || qp_list_find(&qp_guest_endpoints, entry->qp.handle)) { pr_warn("Failed to add new resource (handle=0x%x:0x%x), error: %d", handle.context, handle.resource, result); kfree(entry); entry = NULL; } } return entry; } /* * Frees a qp_guest_endpoint structure. */ static void qp_guest_endpoint_destroy(struct qp_guest_endpoint *entry) { qp_free_ppn_set(&entry->ppn_set); qp_cleanup_queue_mutex(entry->produce_q, entry->consume_q); qp_free_queue(entry->produce_q, entry->qp.produce_size); qp_free_queue(entry->consume_q, entry->qp.consume_size); /* Unlink from resource hash table and free callback */ vmci_resource_remove(&entry->resource); kfree(entry); } /* * Helper to make a queue_pairAlloc hypercall when the driver is * supporting a guest device. */ static int qp_alloc_hypercall(const struct qp_guest_endpoint *entry) { struct vmci_qp_alloc_msg *alloc_msg; size_t msg_size; size_t ppn_size; int result; if (!entry || entry->num_ppns <= 2) return VMCI_ERROR_INVALID_ARGS; ppn_size = vmci_use_ppn64() ? sizeof(u64) : sizeof(u32); msg_size = sizeof(*alloc_msg) + (size_t) entry->num_ppns * ppn_size; alloc_msg = kmalloc(msg_size, GFP_KERNEL); if (!alloc_msg) return VMCI_ERROR_NO_MEM; alloc_msg->hdr.dst = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID, VMCI_QUEUEPAIR_ALLOC); alloc_msg->hdr.src = VMCI_ANON_SRC_HANDLE; alloc_msg->hdr.payload_size = msg_size - VMCI_DG_HEADERSIZE; alloc_msg->handle = entry->qp.handle; alloc_msg->peer = entry->qp.peer; alloc_msg->flags = entry->qp.flags; alloc_msg->produce_size = entry->qp.produce_size; alloc_msg->consume_size = entry->qp.consume_size; alloc_msg->num_ppns = entry->num_ppns; result = qp_populate_ppn_set((u8 *)alloc_msg + sizeof(*alloc_msg), &entry->ppn_set); if (result == VMCI_SUCCESS) result = vmci_send_datagram(&alloc_msg->hdr); kfree(alloc_msg); return result; } /* * Helper to make a queue_pairDetach hypercall when the driver is * supporting a guest device. */ static int qp_detatch_hypercall(struct vmci_handle handle) { struct vmci_qp_detach_msg detach_msg; detach_msg.hdr.dst = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID, VMCI_QUEUEPAIR_DETACH); detach_msg.hdr.src = VMCI_ANON_SRC_HANDLE; detach_msg.hdr.payload_size = sizeof(handle); detach_msg.handle = handle; return vmci_send_datagram(&detach_msg.hdr); } /* * Adds the given entry to the list. Assumes that the list is locked. */ static void qp_list_add_entry(struct qp_list *qp_list, struct qp_entry *entry) { if (entry) list_add(&entry->list_item, &qp_list->head); } /* * Removes the given entry from the list. Assumes that the list is locked. */ static void qp_list_remove_entry(struct qp_list *qp_list, struct qp_entry *entry) { if (entry) list_del(&entry->list_item); } /* * Helper for VMCI queue_pair detach interface. Frees the physical * pages for the queue pair. */ static int qp_detatch_guest_work(struct vmci_handle handle) { int result; struct qp_guest_endpoint *entry; u32 ref_count = ~0; /* To avoid compiler warning below */ mutex_lock(&qp_guest_endpoints.mutex); entry = qp_guest_handle_to_entry(handle); if (!entry) { mutex_unlock(&qp_guest_endpoints.mutex); return VMCI_ERROR_NOT_FOUND; } if (entry->qp.flags & VMCI_QPFLAG_LOCAL) { result = VMCI_SUCCESS; if (entry->qp.ref_count > 1) { result = qp_notify_peer_local(false, handle); /* * We can fail to notify a local queuepair * because we can't allocate. We still want * to release the entry if that happens, so * don't bail out yet. */ } } else { result = qp_detatch_hypercall(handle); if (result < VMCI_SUCCESS) { /* * We failed to notify a non-local queuepair. * That other queuepair might still be * accessing the shared memory, so don't * release the entry yet. It will get cleaned * up by VMCIqueue_pair_Exit() if necessary * (assuming we are going away, otherwise why * did this fail?). */ mutex_unlock(&qp_guest_endpoints.mutex); return result; } } /* * If we get here then we either failed to notify a local queuepair, or * we succeeded in all cases. Release the entry if required. */ entry->qp.ref_count--; if (entry->qp.ref_count == 0) qp_list_remove_entry(&qp_guest_endpoints, &entry->qp); /* If we didn't remove the entry, this could change once we unlock. */ if (entry) ref_count = entry->qp.ref_count; mutex_unlock(&qp_guest_endpoints.mutex); if (ref_count == 0) qp_guest_endpoint_destroy(entry); return result; } /* * This functions handles the actual allocation of a VMCI queue * pair guest endpoint. Allocates physical pages for the queue * pair. It makes OS dependent calls through generic wrappers. */ static int qp_alloc_guest_work(struct vmci_handle *handle, struct vmci_queue **produce_q, u64 produce_size, struct vmci_queue **consume_q, u64 consume_size, u32 peer, u32 flags, u32 priv_flags) { const u64 num_produce_pages = DIV_ROUND_UP(produce_size, PAGE_SIZE) + 1; const u64 num_consume_pages = DIV_ROUND_UP(consume_size, PAGE_SIZE) + 1; void *my_produce_q = NULL; void *my_consume_q = NULL; int result; struct qp_guest_endpoint *queue_pair_entry = NULL; if (priv_flags != VMCI_NO_PRIVILEGE_FLAGS) return VMCI_ERROR_NO_ACCESS; mutex_lock(&qp_guest_endpoints.mutex); queue_pair_entry = qp_guest_handle_to_entry(*handle); if (queue_pair_entry) { if (queue_pair_entry->qp.flags & VMCI_QPFLAG_LOCAL) { /* Local attach case. */ if (queue_pair_entry->qp.ref_count > 1) { pr_devel("Error attempting to attach more than once\n"); result = VMCI_ERROR_UNAVAILABLE; goto error_keep_entry; } if (queue_pair_entry->qp.produce_size != consume_size || queue_pair_entry->qp.consume_size != produce_size || queue_pair_entry->qp.flags != (flags & ~VMCI_QPFLAG_ATTACH_ONLY)) { pr_devel("Error mismatched queue pair in local attach\n"); result = VMCI_ERROR_QUEUEPAIR_MISMATCH; goto error_keep_entry; } /* * Do a local attach. We swap the consume and * produce queues for the attacher and deliver * an attach event. */ result = qp_notify_peer_local(true, *handle); if (result < VMCI_SUCCESS) goto error_keep_entry; my_produce_q = queue_pair_entry->consume_q; my_consume_q = queue_pair_entry->produce_q; goto out; } result = VMCI_ERROR_ALREADY_EXISTS; goto error_keep_entry; } my_produce_q = qp_alloc_queue(produce_size, flags); if (!my_produce_q) { pr_warn("Error allocating pages for produce queue\n"); result = VMCI_ERROR_NO_MEM; goto error; } my_consume_q = qp_alloc_queue(consume_size, flags); if (!my_consume_q) { pr_warn("Error allocating pages for consume queue\n"); result = VMCI_ERROR_NO_MEM; goto error; } queue_pair_entry = qp_guest_endpoint_create(*handle, peer, flags, produce_size, consume_size, my_produce_q, my_consume_q); if (!queue_pair_entry) { pr_warn("Error allocating memory in %s\n", __func__); result = VMCI_ERROR_NO_MEM; goto error; } result = qp_alloc_ppn_set(my_produce_q, num_produce_pages, my_consume_q, num_consume_pages, &queue_pair_entry->ppn_set); if (result < VMCI_SUCCESS) { pr_warn("qp_alloc_ppn_set failed\n"); goto error; } /* * It's only necessary to notify the host if this queue pair will be * attached to from another context. */ if (queue_pair_entry->qp.flags & VMCI_QPFLAG_LOCAL) { /* Local create case. */ u32 context_id = vmci_get_context_id(); /* * Enforce similar checks on local queue pairs as we * do for regular ones. The handle's context must * match the creator or attacher context id (here they * are both the current context id) and the * attach-only flag cannot exist during create. We * also ensure specified peer is this context or an * invalid one. */ if (queue_pair_entry->qp.handle.context != context_id || (queue_pair_entry->qp.peer != VMCI_INVALID_ID && queue_pair_entry->qp.peer != context_id)) { result = VMCI_ERROR_NO_ACCESS; goto error; } if (queue_pair_entry->qp.flags & VMCI_QPFLAG_ATTACH_ONLY) { result = VMCI_ERROR_NOT_FOUND; goto error; } } else { result = qp_alloc_hypercall(queue_pair_entry); if (result < VMCI_SUCCESS) { pr_devel("qp_alloc_hypercall result = %d\n", result); goto error; } } qp_init_queue_mutex((struct vmci_queue *)my_produce_q, (struct vmci_queue *)my_consume_q); qp_list_add_entry(&qp_guest_endpoints, &queue_pair_entry->qp); out: queue_pair_entry->qp.ref_count++; *handle = queue_pair_entry->qp.handle; *produce_q = (struct vmci_queue *)my_produce_q; *consume_q = (struct vmci_queue *)my_consume_q; /* * We should initialize the queue pair header pages on a local * queue pair create. For non-local queue pairs, the * hypervisor initializes the header pages in the create step. */ if ((queue_pair_entry->qp.flags & VMCI_QPFLAG_LOCAL) && queue_pair_entry->qp.ref_count == 1) { vmci_q_header_init((*produce_q)->q_header, *handle); vmci_q_header_init((*consume_q)->q_header, *handle); } mutex_unlock(&qp_guest_endpoints.mutex); return VMCI_SUCCESS; error: mutex_unlock(&qp_guest_endpoints.mutex); if (queue_pair_entry) { /* The queues will be freed inside the destroy routine. */ qp_guest_endpoint_destroy(queue_pair_entry); } else { qp_free_queue(my_produce_q, produce_size); qp_free_queue(my_consume_q, consume_size); } return result; error_keep_entry: /* This path should only be used when an existing entry was found. */ mutex_unlock(&qp_guest_endpoints.mutex); return result; } /* * The first endpoint issuing a queue pair allocation will create the state * of the queue pair in the queue pair broker. * * If the creator is a guest, it will associate a VMX virtual address range * with the queue pair as specified by the page_store. For compatibility with * older VMX'en, that would use a separate step to set the VMX virtual * address range, the virtual address range can be registered later using * vmci_qp_broker_set_page_store. In that case, a page_store of NULL should be * used. * * If the creator is the host, a page_store of NULL should be used as well, * since the host is not able to supply a page store for the queue pair. * * For older VMX and host callers, the queue pair will be created in the * VMCIQPB_CREATED_NO_MEM state, and for current VMX callers, it will be * created in VMCOQPB_CREATED_MEM state. */ static int qp_broker_create(struct vmci_handle handle, u32 peer, u32 flags, u32 priv_flags, u64 produce_size, u64 consume_size, struct vmci_qp_page_store *page_store, struct vmci_ctx *context, vmci_event_release_cb wakeup_cb, void *client_data, struct qp_broker_entry **ent) { struct qp_broker_entry *entry = NULL; const u32 context_id = vmci_ctx_get_id(context); bool is_local = flags & VMCI_QPFLAG_LOCAL; int result; u64 guest_produce_size; u64 guest_consume_size; /* Do not create if the caller asked not to. */ if (flags & VMCI_QPFLAG_ATTACH_ONLY) return VMCI_ERROR_NOT_FOUND; /* * Creator's context ID should match handle's context ID or the creator * must allow the context in handle's context ID as the "peer". */ if (handle.context != context_id && handle.context != peer) return VMCI_ERROR_NO_ACCESS; if (VMCI_CONTEXT_IS_VM(context_id) && VMCI_CONTEXT_IS_VM(peer)) return VMCI_ERROR_DST_UNREACHABLE; /* * Creator's context ID for local queue pairs should match the * peer, if a peer is specified. */ if (is_local && peer != VMCI_INVALID_ID && context_id != peer) return VMCI_ERROR_NO_ACCESS; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return VMCI_ERROR_NO_MEM; if (vmci_ctx_get_id(context) == VMCI_HOST_CONTEXT_ID && !is_local) { /* * The queue pair broker entry stores values from the guest * point of view, so a creating host side endpoint should swap * produce and consume values -- unless it is a local queue * pair, in which case no swapping is necessary, since the local * attacher will swap queues. */ guest_produce_size = consume_size; guest_consume_size = produce_size; } else { guest_produce_size = produce_size; guest_consume_size = consume_size; } entry->qp.handle = handle; entry->qp.peer = peer; entry->qp.flags = flags; entry->qp.produce_size = guest_produce_size; entry->qp.consume_size = guest_consume_size; entry->qp.ref_count = 1; entry->create_id = context_id; entry->attach_id = VMCI_INVALID_ID; entry->state = VMCIQPB_NEW; entry->require_trusted_attach = !!(context->priv_flags & VMCI_PRIVILEGE_FLAG_RESTRICTED); entry->created_by_trusted = !!(priv_flags & VMCI_PRIVILEGE_FLAG_TRUSTED); entry->vmci_page_files = false; entry->wakeup_cb = wakeup_cb; entry->client_data = client_data; entry->produce_q = qp_host_alloc_queue(guest_produce_size); if (entry->produce_q == NULL) { result = VMCI_ERROR_NO_MEM; goto error; } entry->consume_q = qp_host_alloc_queue(guest_consume_size); if (entry->consume_q == NULL) { result = VMCI_ERROR_NO_MEM; goto error; } qp_init_queue_mutex(entry->produce_q, entry->consume_q); INIT_LIST_HEAD(&entry->qp.list_item); if (is_local) { u8 *tmp; entry->local_mem = kcalloc(QPE_NUM_PAGES(entry->qp), PAGE_SIZE, GFP_KERNEL); if (entry->local_mem == NULL) { result = VMCI_ERROR_NO_MEM; goto error; } entry->state = VMCIQPB_CREATED_MEM; entry->produce_q->q_header = entry->local_mem; tmp = (u8 *)entry->local_mem + PAGE_SIZE * (DIV_ROUND_UP(entry->qp.produce_size, PAGE_SIZE) + 1); entry->consume_q->q_header = (struct vmci_queue_header *)tmp; } else if (page_store) { /* * The VMX already initialized the queue pair headers, so no * need for the kernel side to do that. */ result = qp_host_register_user_memory(page_store, entry->produce_q, entry->consume_q); if (result < VMCI_SUCCESS) goto error; entry->state = VMCIQPB_CREATED_MEM; } else { /* * A create without a page_store may be either a host * side create (in which case we are waiting for the * guest side to supply the memory) or an old style * queue pair create (in which case we will expect a * set page store call as the next step). */ entry->state = VMCIQPB_CREATED_NO_MEM; } qp_list_add_entry(&qp_broker_list, &entry->qp); if (ent != NULL) *ent = entry; /* Add to resource obj */ result = vmci_resource_add(&entry->resource, VMCI_RESOURCE_TYPE_QPAIR_HOST, handle); if (result != VMCI_SUCCESS) { pr_warn("Failed to add new resource (handle=0x%x:0x%x), error: %d", handle.context, handle.resource, result); goto error; } entry->qp.handle = vmci_resource_handle(&entry->resource); if (is_local) { vmci_q_header_init(entry->produce_q->q_header, entry->qp.handle); vmci_q_header_init(entry->consume_q->q_header, entry->qp.handle); } vmci_ctx_qp_create(context, entry->qp.handle); return VMCI_SUCCESS; error: if (entry != NULL) { qp_host_free_queue(entry->produce_q, guest_produce_size); qp_host_free_queue(entry->consume_q, guest_consume_size); kfree(entry); } return result; } /* * Enqueues an event datagram to notify the peer VM attached to * the given queue pair handle about attach/detach event by the * given VM. Returns Payload size of datagram enqueued on * success, error code otherwise. */ static int qp_notify_peer(bool attach, struct vmci_handle handle, u32 my_id, u32 peer_id) { int rv; struct vmci_event_qp ev; if (vmci_handle_is_invalid(handle) || my_id == VMCI_INVALID_ID || peer_id == VMCI_INVALID_ID) return VMCI_ERROR_INVALID_ARGS; /* * In vmci_ctx_enqueue_datagram() we enforce the upper limit on * number of pending events from the hypervisor to a given VM * otherwise a rogue VM could do an arbitrary number of attach * and detach operations causing memory pressure in the host * kernel. */ memset(&ev, 0, sizeof(ev)); ev.msg.hdr.dst = vmci_make_handle(peer_id, VMCI_EVENT_HANDLER); ev.msg.hdr.src = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID, VMCI_CONTEXT_RESOURCE_ID); ev.msg.hdr.payload_size = sizeof(ev) - sizeof(ev.msg.hdr); ev.msg.event_data.event = attach ? VMCI_EVENT_QP_PEER_ATTACH : VMCI_EVENT_QP_PEER_DETACH; ev.payload.handle = handle; ev.payload.peer_id = my_id; rv = vmci_datagram_dispatch(VMCI_HYPERVISOR_CONTEXT_ID, &ev.msg.hdr, false); if (rv < VMCI_SUCCESS) pr_warn("Failed to enqueue queue_pair %s event datagram for context (ID=0x%x)\n", attach ? "ATTACH" : "DETACH", peer_id); return rv; } /* * The second endpoint issuing a queue pair allocation will attach to * the queue pair registered with the queue pair broker. * * If the attacher is a guest, it will associate a VMX virtual address * range with the queue pair as specified by the page_store. At this * point, the already attach host endpoint may start using the queue * pair, and an attach event is sent to it. For compatibility with * older VMX'en, that used a separate step to set the VMX virtual * address range, the virtual address range can be registered later * using vmci_qp_broker_set_page_store. In that case, a page_store of * NULL should be used, and the attach event will be generated once * the actual page store has been set. * * If the attacher is the host, a page_store of NULL should be used as * well, since the page store information is already set by the guest. * * For new VMX and host callers, the queue pair will be moved to the * VMCIQPB_ATTACHED_MEM state, and for older VMX callers, it will be * moved to the VMCOQPB_ATTACHED_NO_MEM state. */ static int qp_broker_attach(struct qp_broker_entry *entry, u32 peer, u32 flags, u32 priv_flags, u64 produce_size, u64 consume_size, struct vmci_qp_page_store *page_store, struct vmci_ctx *context, vmci_event_release_cb wakeup_cb, void *client_data, struct qp_broker_entry **ent) { const u32 context_id = vmci_ctx_get_id(context); bool is_local = flags & VMCI_QPFLAG_LOCAL; int result; if (entry->state != VMCIQPB_CREATED_NO_MEM && entry->state != VMCIQPB_CREATED_MEM) return VMCI_ERROR_UNAVAILABLE; if (is_local) { if (!(entry->qp.flags & VMCI_QPFLAG_LOCAL) || context_id != entry->create_id) { return VMCI_ERROR_INVALID_ARGS; } } else if (context_id == entry->create_id || context_id == entry->attach_id) { return VMCI_ERROR_ALREADY_EXISTS; } if (VMCI_CONTEXT_IS_VM(context_id) && VMCI_CONTEXT_IS_VM(entry->create_id)) return VMCI_ERROR_DST_UNREACHABLE; /* * If we are attaching from a restricted context then the queuepair * must have been created by a trusted endpoint. */ if ((context->priv_flags & VMCI_PRIVILEGE_FLAG_RESTRICTED) && !entry->created_by_trusted) return VMCI_ERROR_NO_ACCESS; /* * If we are attaching to a queuepair that was created by a restricted * context then we must be trusted. */ if (entry->require_trusted_attach && (!(priv_flags & VMCI_PRIVILEGE_FLAG_TRUSTED))) return VMCI_ERROR_NO_ACCESS; /* * If the creator specifies VMCI_INVALID_ID in "peer" field, access * control check is not performed. */ if (entry->qp.peer != VMCI_INVALID_ID && entry->qp.peer != context_id) return VMCI_ERROR_NO_ACCESS; if (entry->create_id == VMCI_HOST_CONTEXT_ID) { /* * Do not attach if the caller doesn't support Host Queue Pairs * and a host created this queue pair. */ if (!vmci_ctx_supports_host_qp(context)) return VMCI_ERROR_INVALID_RESOURCE; } else if (context_id == VMCI_HOST_CONTEXT_ID) { struct vmci_ctx *create_context; bool supports_host_qp; /* * Do not attach a host to a user created queue pair if that * user doesn't support host queue pair end points. */ create_context = vmci_ctx_get(entry->create_id); supports_host_qp = vmci_ctx_supports_host_qp(create_context); vmci_ctx_put(create_context); if (!supports_host_qp) return VMCI_ERROR_INVALID_RESOURCE; } if ((entry->qp.flags & ~VMCI_QP_ASYMM) != (flags & ~VMCI_QP_ASYMM_PEER)) return VMCI_ERROR_QUEUEPAIR_MISMATCH; if (context_id != VMCI_HOST_CONTEXT_ID) { /* * The queue pair broker entry stores values from the guest * point of view, so an attaching guest should match the values * stored in the entry. */ if (entry->qp.produce_size != produce_size || entry->qp.consume_size != consume_size) { return VMCI_ERROR_QUEUEPAIR_MISMATCH; } } else if (entry->qp.produce_size != consume_size || entry->qp.consume_size != produce_size) { return VMCI_ERROR_QUEUEPAIR_MISMATCH; } if (context_id != VMCI_HOST_CONTEXT_ID) { /* * If a guest attached to a queue pair, it will supply * the backing memory. If this is a pre NOVMVM vmx, * the backing memory will be supplied by calling * vmci_qp_broker_set_page_store() following the * return of the vmci_qp_broker_alloc() call. If it is * a vmx of version NOVMVM or later, the page store * must be supplied as part of the * vmci_qp_broker_alloc call. Under all circumstances * must the initially created queue pair not have any * memory associated with it already. */ if (entry->state != VMCIQPB_CREATED_NO_MEM) return VMCI_ERROR_INVALID_ARGS; if (page_store != NULL) { /* * Patch up host state to point to guest * supplied memory. The VMX already * initialized the queue pair headers, so no * need for the kernel side to do that. */ result = qp_host_register_user_memory(page_store, entry->produce_q, entry->consume_q); if (result < VMCI_SUCCESS) return result; entry->state = VMCIQPB_ATTACHED_MEM; } else { entry->state = VMCIQPB_ATTACHED_NO_MEM; } } else if (entry->state == VMCIQPB_CREATED_NO_MEM) { /* * The host side is attempting to attach to a queue * pair that doesn't have any memory associated with * it. This must be a pre NOVMVM vmx that hasn't set * the page store information yet, or a quiesced VM. */ return VMCI_ERROR_UNAVAILABLE; } else { /* The host side has successfully attached to a queue pair. */ entry->state = VMCIQPB_ATTACHED_MEM; } if (entry->state == VMCIQPB_ATTACHED_MEM) { result = qp_notify_peer(true, entry->qp.handle, context_id, entry->create_id); if (result < VMCI_SUCCESS) pr_warn("Failed to notify peer (ID=0x%x) of attach to queue pair (handle=0x%x:0x%x)\n", entry->create_id, entry->qp.handle.context, entry->qp.handle.resource); } entry->attach_id = context_id; entry->qp.ref_count++; if (wakeup_cb) { entry->wakeup_cb = wakeup_cb; entry->client_data = client_data; } /* * When attaching to local queue pairs, the context already has * an entry tracking the queue pair, so don't add another one. */ if (!is_local) vmci_ctx_qp_create(context, entry->qp.handle); if (ent != NULL) *ent = entry; return VMCI_SUCCESS; } /* * queue_pair_Alloc for use when setting up queue pair endpoints * on the host. */ static int qp_broker_alloc(struct vmci_handle handle, u32 peer, u32 flags, u32 priv_flags, u64 produce_size, u64 consume_size, struct vmci_qp_page_store *page_store, struct vmci_ctx *context, vmci_event_release_cb wakeup_cb, void *client_data, struct qp_broker_entry **ent, bool *swap) { const u32 context_id = vmci_ctx_get_id(context); bool create; struct qp_broker_entry *entry = NULL; bool is_local = flags & VMCI_QPFLAG_LOCAL; int result; if (vmci_handle_is_invalid(handle) || (flags & ~VMCI_QP_ALL_FLAGS) || is_local || !(produce_size || consume_size) || !context || context_id == VMCI_INVALID_ID || handle.context == VMCI_INVALID_ID) { return VMCI_ERROR_INVALID_ARGS; } if (page_store && !VMCI_QP_PAGESTORE_IS_WELLFORMED(page_store)) return VMCI_ERROR_INVALID_ARGS; /* * In the initial argument check, we ensure that non-vmkernel hosts * are not allowed to create local queue pairs. */ mutex_lock(&qp_broker_list.mutex); if (!is_local && vmci_ctx_qp_exists(context, handle)) { pr_devel("Context (ID=0x%x) already attached to queue pair (handle=0x%x:0x%x)\n", context_id, handle.context, handle.resource); mutex_unlock(&qp_broker_list.mutex); return VMCI_ERROR_ALREADY_EXISTS; } if (handle.resource != VMCI_INVALID_ID) entry = qp_broker_handle_to_entry(handle); if (!entry) { create = true; result = qp_broker_create(handle, peer, flags, priv_flags, produce_size, consume_size, page_store, context, wakeup_cb, client_data, ent); } else { create = false; result = qp_broker_attach(entry, peer, flags, priv_flags, produce_size, consume_size, page_store, context, wakeup_cb, client_data, ent); } mutex_unlock(&qp_broker_list.mutex); if (swap) *swap = (context_id == VMCI_HOST_CONTEXT_ID) && !(create && is_local); return result; } /* * This function implements the kernel API for allocating a queue * pair. */ static int qp_alloc_host_work(struct vmci_handle *handle, struct vmci_queue **produce_q, u64 produce_size, struct vmci_queue **consume_q, u64 consume_size, u32 peer, u32 flags, u32 priv_flags, vmci_event_release_cb wakeup_cb, void *client_data) { struct vmci_handle new_handle; struct vmci_ctx *context; struct qp_broker_entry *entry; int result; bool swap; if (vmci_handle_is_invalid(*handle)) { new_handle = vmci_make_handle( VMCI_HOST_CONTEXT_ID, VMCI_INVALID_ID); } else new_handle = *handle; context = vmci_ctx_get(VMCI_HOST_CONTEXT_ID); entry = NULL; result = qp_broker_alloc(new_handle, peer, flags, priv_flags, produce_size, consume_size, NULL, context, wakeup_cb, client_data, &entry, &swap); if (result == VMCI_SUCCESS) { if (swap) { /* * If this is a local queue pair, the attacher * will swap around produce and consume * queues. */ *produce_q = entry->consume_q; *consume_q = entry->produce_q; } else { *produce_q = entry->produce_q; *consume_q = entry->consume_q; } *handle = vmci_resource_handle(&entry->resource); } else { *handle = VMCI_INVALID_HANDLE; pr_devel("queue pair broker failed to alloc (result=%d)\n", result); } vmci_ctx_put(context); return result; } /* * Allocates a VMCI queue_pair. Only checks validity of input * arguments. The real work is done in the host or guest * specific function. */ int vmci_qp_alloc(struct vmci_handle *handle, struct vmci_queue **produce_q, u64 produce_size, struct vmci_queue **consume_q, u64 consume_size, u32 peer, u32 flags, u32 priv_flags, bool guest_endpoint, vmci_event_release_cb wakeup_cb, void *client_data) { if (!handle || !produce_q || !consume_q || (!produce_size && !consume_size) || (flags & ~VMCI_QP_ALL_FLAGS)) return VMCI_ERROR_INVALID_ARGS; if (guest_endpoint) { return qp_alloc_guest_work(handle, produce_q, produce_size, consume_q, consume_size, peer, flags, priv_flags); } else { return qp_alloc_host_work(handle, produce_q, produce_size, consume_q, consume_size, peer, flags, priv_flags, wakeup_cb, client_data); } } /* * This function implements the host kernel API for detaching from * a queue pair. */ static int qp_detatch_host_work(struct vmci_handle handle) { int result; struct vmci_ctx *context; context = vmci_ctx_get(VMCI_HOST_CONTEXT_ID); result = vmci_qp_broker_detach(handle, context); vmci_ctx_put(context); return result; } /* * Detaches from a VMCI queue_pair. Only checks validity of input argument. * Real work is done in the host or guest specific function. */ static int qp_detatch(struct vmci_handle handle, bool guest_endpoint) { if (vmci_handle_is_invalid(handle)) return VMCI_ERROR_INVALID_ARGS; if (guest_endpoint) return qp_detatch_guest_work(handle); else return qp_detatch_host_work(handle); } /* * Returns the entry from the head of the list. Assumes that the list is * locked. */ static struct qp_entry *qp_list_get_head(struct qp_list *qp_list) { if (!list_empty(&qp_list->head)) { struct qp_entry *entry = list_first_entry(&qp_list->head, struct qp_entry, list_item); return entry; } return NULL; } void vmci_qp_broker_exit(void) { struct qp_entry *entry; struct qp_broker_entry *be; mutex_lock(&qp_broker_list.mutex); while ((entry = qp_list_get_head(&qp_broker_list))) { be = (struct qp_broker_entry *)entry; qp_list_remove_entry(&qp_broker_list, entry); kfree(be); } mutex_unlock(&qp_broker_list.mutex); } /* * Requests that a queue pair be allocated with the VMCI queue * pair broker. Allocates a queue pair entry if one does not * exist. Attaches to one if it exists, and retrieves the page * files backing that queue_pair. Assumes that the queue pair * broker lock is held. */ int vmci_qp_broker_alloc(struct vmci_handle handle, u32 peer, u32 flags, u32 priv_flags, u64 produce_size, u64 consume_size, struct vmci_qp_page_store *page_store, struct vmci_ctx *context) { if (!QP_SIZES_ARE_VALID(produce_size, consume_size)) return VMCI_ERROR_NO_RESOURCES; return qp_broker_alloc(handle, peer, flags, priv_flags, produce_size, consume_size, page_store, context, NULL, NULL, NULL, NULL); } /* * VMX'en with versions lower than VMCI_VERSION_NOVMVM use a separate * step to add the UVAs of the VMX mapping of the queue pair. This function * provides backwards compatibility with such VMX'en, and takes care of * registering the page store for a queue pair previously allocated by the * VMX during create or attach. This function will move the queue pair state * to either from VMCIQBP_CREATED_NO_MEM to VMCIQBP_CREATED_MEM or * VMCIQBP_ATTACHED_NO_MEM to VMCIQBP_ATTACHED_MEM. If moving to the * attached state with memory, the queue pair is ready to be used by the * host peer, and an attached event will be generated. * * Assumes that the queue pair broker lock is held. * * This function is only used by the hosted platform, since there is no * issue with backwards compatibility for vmkernel. */ int vmci_qp_broker_set_page_store(struct vmci_handle handle, u64 produce_uva, u64 consume_uva, struct vmci_ctx *context) { struct qp_broker_entry *entry; int result; const u32 context_id = vmci_ctx_get_id(context); if (vmci_handle_is_invalid(handle) || !context || context_id == VMCI_INVALID_ID) return VMCI_ERROR_INVALID_ARGS; /* * We only support guest to host queue pairs, so the VMX must * supply UVAs for the mapped page files. */ if (produce_uva == 0 || consume_uva == 0) return VMCI_ERROR_INVALID_ARGS; mutex_lock(&qp_broker_list.mutex); if (!vmci_ctx_qp_exists(context, handle)) { pr_warn("Context (ID=0x%x) not attached to queue pair (handle=0x%x:0x%x)\n", context_id, handle.context, handle.resource); result = VMCI_ERROR_NOT_FOUND; goto out; } entry = qp_broker_handle_to_entry(handle); if (!entry) { result = VMCI_ERROR_NOT_FOUND; goto out; } /* * If I'm the owner then I can set the page store. * * Or, if a host created the queue_pair and I'm the attached peer * then I can set the page store. */ if (entry->create_id != context_id && (entry->create_id != VMCI_HOST_CONTEXT_ID || entry->attach_id != context_id)) { result = VMCI_ERROR_QUEUEPAIR_NOTOWNER; goto out; } if (entry->state != VMCIQPB_CREATED_NO_MEM && entry->state != VMCIQPB_ATTACHED_NO_MEM) { result = VMCI_ERROR_UNAVAILABLE; goto out; } result = qp_host_get_user_memory(produce_uva, consume_uva, entry->produce_q, entry->consume_q); if (result < VMCI_SUCCESS) goto out; result = qp_host_map_queues(entry->produce_q, entry->consume_q); if (result < VMCI_SUCCESS) { qp_host_unregister_user_memory(entry->produce_q, entry->consume_q); goto out; } if (entry->state == VMCIQPB_CREATED_NO_MEM) entry->state = VMCIQPB_CREATED_MEM; else entry->state = VMCIQPB_ATTACHED_MEM; entry->vmci_page_files = true; if (entry->state == VMCIQPB_ATTACHED_MEM) { result = qp_notify_peer(true, handle, context_id, entry->create_id); if (result < VMCI_SUCCESS) { pr_warn("Failed to notify peer (ID=0x%x) of attach to queue pair (handle=0x%x:0x%x)\n", entry->create_id, entry->qp.handle.context, entry->qp.handle.resource); } } result = VMCI_SUCCESS; out: mutex_unlock(&qp_broker_list.mutex); return result; } /* * Resets saved queue headers for the given QP broker * entry. Should be used when guest memory becomes available * again, or the guest detaches. */ static void qp_reset_saved_headers(struct qp_broker_entry *entry) { entry->produce_q->saved_header = NULL; entry->consume_q->saved_header = NULL; } /* * The main entry point for detaching from a queue pair registered with the * queue pair broker. If more than one endpoint is attached to the queue * pair, the first endpoint will mainly decrement a reference count and * generate a notification to its peer. The last endpoint will clean up * the queue pair state registered with the broker. * * When a guest endpoint detaches, it will unmap and unregister the guest * memory backing the queue pair. If the host is still attached, it will * no longer be able to access the queue pair content. * * If the queue pair is already in a state where there is no memory * registered for the queue pair (any *_NO_MEM state), it will transition to * the VMCIQPB_SHUTDOWN_NO_MEM state. This will also happen, if a guest * endpoint is the first of two endpoints to detach. If the host endpoint is * the first out of two to detach, the queue pair will move to the * VMCIQPB_SHUTDOWN_MEM state. */ int vmci_qp_broker_detach(struct vmci_handle handle, struct vmci_ctx *context) { struct qp_broker_entry *entry; const u32 context_id = vmci_ctx_get_id(context); u32 peer_id; bool is_local = false; int result; if (vmci_handle_is_invalid(handle) || !context || context_id == VMCI_INVALID_ID) { return VMCI_ERROR_INVALID_ARGS; } mutex_lock(&qp_broker_list.mutex); if (!vmci_ctx_qp_exists(context, handle)) { pr_devel("Context (ID=0x%x) not attached to queue pair (handle=0x%x:0x%x)\n", context_id, handle.context, handle.resource); result = VMCI_ERROR_NOT_FOUND; goto out; } entry = qp_broker_handle_to_entry(handle); if (!entry) { pr_devel("Context (ID=0x%x) reports being attached to queue pair(handle=0x%x:0x%x) that isn't present in broker\n", context_id, handle.context, handle.resource); result = VMCI_ERROR_NOT_FOUND; goto out; } if (context_id != entry->create_id && context_id != entry->attach_id) { result = VMCI_ERROR_QUEUEPAIR_NOTATTACHED; goto out; } if (context_id == entry->create_id) { peer_id = entry->attach_id; entry->create_id = VMCI_INVALID_ID; } else { peer_id = entry->create_id; entry->attach_id = VMCI_INVALID_ID; } entry->qp.ref_count--; is_local = entry->qp.flags & VMCI_QPFLAG_LOCAL; if (context_id != VMCI_HOST_CONTEXT_ID) { bool headers_mapped; /* * Pre NOVMVM vmx'en may detach from a queue pair * before setting the page store, and in that case * there is no user memory to detach from. Also, more * recent VMX'en may detach from a queue pair in the * quiesced state. */ qp_acquire_queue_mutex(entry->produce_q); headers_mapped = entry->produce_q->q_header || entry->consume_q->q_header; if (QPBROKERSTATE_HAS_MEM(entry)) { result = qp_host_unmap_queues(INVALID_VMCI_GUEST_MEM_ID, entry->produce_q, entry->consume_q); if (result < VMCI_SUCCESS) pr_warn("Failed to unmap queue headers for queue pair (handle=0x%x:0x%x,result=%d)\n", handle.context, handle.resource, result); qp_host_unregister_user_memory(entry->produce_q, entry->consume_q); } if (!headers_mapped) qp_reset_saved_headers(entry); qp_release_queue_mutex(entry->produce_q); if (!headers_mapped && entry->wakeup_cb) entry->wakeup_cb(entry->client_data); } else { if (entry->wakeup_cb) { entry->wakeup_cb = NULL; entry->client_data = NULL; } } if (entry->qp.ref_count == 0) { qp_list_remove_entry(&qp_broker_list, &entry->qp); if (is_local) kfree(entry->local_mem); qp_cleanup_queue_mutex(entry->produce_q, entry->consume_q); qp_host_free_queue(entry->produce_q, entry->qp.produce_size); qp_host_free_queue(entry->consume_q, entry->qp.consume_size); /* Unlink from resource hash table and free callback */ vmci_resource_remove(&entry->resource); kfree(entry); vmci_ctx_qp_destroy(context, handle); } else { qp_notify_peer(false, handle, context_id, peer_id); if (context_id == VMCI_HOST_CONTEXT_ID && QPBROKERSTATE_HAS_MEM(entry)) { entry->state = VMCIQPB_SHUTDOWN_MEM; } else { entry->state = VMCIQPB_SHUTDOWN_NO_MEM; } if (!is_local) vmci_ctx_qp_destroy(context, handle); } result = VMCI_SUCCESS; out: mutex_unlock(&qp_broker_list.mutex); return result; } /* * Establishes the necessary mappings for a queue pair given a * reference to the queue pair guest memory. This is usually * called when a guest is unquiesced and the VMX is allowed to * map guest memory once again. */ int vmci_qp_broker_map(struct vmci_handle handle, struct vmci_ctx *context, u64 guest_mem) { struct qp_broker_entry *entry; const u32 context_id = vmci_ctx_get_id(context); int result; if (vmci_handle_is_invalid(handle) || !context || context_id == VMCI_INVALID_ID) return VMCI_ERROR_INVALID_ARGS; mutex_lock(&qp_broker_list.mutex); if (!vmci_ctx_qp_exists(context, handle)) { pr_devel("Context (ID=0x%x) not attached to queue pair (handle=0x%x:0x%x)\n", context_id, handle.context, handle.resource); result = VMCI_ERROR_NOT_FOUND; goto out; } entry = qp_broker_handle_to_entry(handle); if (!entry) { pr_devel("Context (ID=0x%x) reports being attached to queue pair (handle=0x%x:0x%x) that isn't present in broker\n", context_id, handle.context, handle.resource); result = VMCI_ERROR_NOT_FOUND; goto out; } if (context_id != entry->create_id && context_id != entry->attach_id) { result = VMCI_ERROR_QUEUEPAIR_NOTATTACHED; goto out; } result = VMCI_SUCCESS; if (context_id != VMCI_HOST_CONTEXT_ID && !QPBROKERSTATE_HAS_MEM(entry)) { struct vmci_qp_page_store page_store; page_store.pages = guest_mem; page_store.len = QPE_NUM_PAGES(entry->qp); qp_acquire_queue_mutex(entry->produce_q); qp_reset_saved_headers(entry); result = qp_host_register_user_memory(&page_store, entry->produce_q, entry->consume_q); qp_release_queue_mutex(entry->produce_q); if (result == VMCI_SUCCESS) { /* Move state from *_NO_MEM to *_MEM */ entry->state++; if (entry->wakeup_cb) entry->wakeup_cb(entry->client_data); } } out: mutex_unlock(&qp_broker_list.mutex); return result; } /* * Saves a snapshot of the queue headers for the given QP broker * entry. Should be used when guest memory is unmapped. * Results: * VMCI_SUCCESS on success, appropriate error code if guest memory * can't be accessed.. */ static int qp_save_headers(struct qp_broker_entry *entry) { int result; if (entry->produce_q->saved_header != NULL && entry->consume_q->saved_header != NULL) { /* * If the headers have already been saved, we don't need to do * it again, and we don't want to map in the headers * unnecessarily. */ return VMCI_SUCCESS; } if (NULL == entry->produce_q->q_header || NULL == entry->consume_q->q_header) { result = qp_host_map_queues(entry->produce_q, entry->consume_q); if (result < VMCI_SUCCESS) return result; } memcpy(&entry->saved_produce_q, entry->produce_q->q_header, sizeof(entry->saved_produce_q)); entry->produce_q->saved_header = &entry->saved_produce_q; memcpy(&entry->saved_consume_q, entry->consume_q->q_header, sizeof(entry->saved_consume_q)); entry->consume_q->saved_header = &entry->saved_consume_q; return VMCI_SUCCESS; } /* * Removes all references to the guest memory of a given queue pair, and * will move the queue pair from state *_MEM to *_NO_MEM. It is usually * called when a VM is being quiesced where access to guest memory should * avoided. */ int vmci_qp_broker_unmap(struct vmci_handle handle, struct vmci_ctx *context, u32 gid) { struct qp_broker_entry *entry; const u32 context_id = vmci_ctx_get_id(context); int result; if (vmci_handle_is_invalid(handle) || !context || context_id == VMCI_INVALID_ID) return VMCI_ERROR_INVALID_ARGS; mutex_lock(&qp_broker_list.mutex); if (!vmci_ctx_qp_exists(context, handle)) { pr_devel("Context (ID=0x%x) not attached to queue pair (handle=0x%x:0x%x)\n", context_id, handle.context, handle.resource); result = VMCI_ERROR_NOT_FOUND; goto out; } entry = qp_broker_handle_to_entry(handle); if (!entry) { pr_devel("Context (ID=0x%x) reports being attached to queue pair (handle=0x%x:0x%x) that isn't present in broker\n", context_id, handle.context, handle.resource); result = VMCI_ERROR_NOT_FOUND; goto out; } if (context_id != entry->create_id && context_id != entry->attach_id) { result = VMCI_ERROR_QUEUEPAIR_NOTATTACHED; goto out; } if (context_id != VMCI_HOST_CONTEXT_ID && QPBROKERSTATE_HAS_MEM(entry)) { qp_acquire_queue_mutex(entry->produce_q); result = qp_save_headers(entry); if (result < VMCI_SUCCESS) pr_warn("Failed to save queue headers for queue pair (handle=0x%x:0x%x,result=%d)\n", handle.context, handle.resource, result); qp_host_unmap_queues(gid, entry->produce_q, entry->consume_q); /* * On hosted, when we unmap queue pairs, the VMX will also * unmap the guest memory, so we invalidate the previously * registered memory. If the queue pair is mapped again at a * later point in time, we will need to reregister the user * memory with a possibly new user VA. */ qp_host_unregister_user_memory(entry->produce_q, entry->consume_q); /* * Move state from *_MEM to *_NO_MEM. */ entry->state--; qp_release_queue_mutex(entry->produce_q); } result = VMCI_SUCCESS; out: mutex_unlock(&qp_broker_list.mutex); return result; } /* * Destroys all guest queue pair endpoints. If active guest queue * pairs still exist, hypercalls to attempt detach from these * queue pairs will be made. Any failure to detach is silently * ignored. */ void vmci_qp_guest_endpoints_exit(void) { struct qp_entry *entry; struct qp_guest_endpoint *ep; mutex_lock(&qp_guest_endpoints.mutex); while ((entry = qp_list_get_head(&qp_guest_endpoints))) { ep = (struct qp_guest_endpoint *)entry; /* Don't make a hypercall for local queue_pairs. */ if (!(entry->flags & VMCI_QPFLAG_LOCAL)) qp_detatch_hypercall(entry->handle); /* We cannot fail the exit, so let's reset ref_count. */ entry->ref_count = 0; qp_list_remove_entry(&qp_guest_endpoints, entry); qp_guest_endpoint_destroy(ep); } mutex_unlock(&qp_guest_endpoints.mutex); } /* * Helper routine that will lock the queue pair before subsequent * operations. * Note: Non-blocking on the host side is currently only implemented in ESX. * Since non-blocking isn't yet implemented on the host personality we * have no reason to acquire a spin lock. So to avoid the use of an * unnecessary lock only acquire the mutex if we can block. */ static void qp_lock(const struct vmci_qp *qpair) { qp_acquire_queue_mutex(qpair->produce_q); } /* * Helper routine that unlocks the queue pair after calling * qp_lock. */ static void qp_unlock(const struct vmci_qp *qpair) { qp_release_queue_mutex(qpair->produce_q); } /* * The queue headers may not be mapped at all times. If a queue is * currently not mapped, it will be attempted to do so. */ static int qp_map_queue_headers(struct vmci_queue *produce_q, struct vmci_queue *consume_q) { int result; if (NULL == produce_q->q_header || NULL == consume_q->q_header) { result = qp_host_map_queues(produce_q, consume_q); if (result < VMCI_SUCCESS) return (produce_q->saved_header && consume_q->saved_header) ? VMCI_ERROR_QUEUEPAIR_NOT_READY : VMCI_ERROR_QUEUEPAIR_NOTATTACHED; } return VMCI_SUCCESS; } /* * Helper routine that will retrieve the produce and consume * headers of a given queue pair. If the guest memory of the * queue pair is currently not available, the saved queue headers * will be returned, if these are available. */ static int qp_get_queue_headers(const struct vmci_qp *qpair, struct vmci_queue_header **produce_q_header, struct vmci_queue_header **consume_q_header) { int result; result = qp_map_queue_headers(qpair->produce_q, qpair->consume_q); if (result == VMCI_SUCCESS) { *produce_q_header = qpair->produce_q->q_header; *consume_q_header = qpair->consume_q->q_header; } else if (qpair->produce_q->saved_header && qpair->consume_q->saved_header) { *produce_q_header = qpair->produce_q->saved_header; *consume_q_header = qpair->consume_q->saved_header; result = VMCI_SUCCESS; } return result; } /* * Callback from VMCI queue pair broker indicating that a queue * pair that was previously not ready, now either is ready or * gone forever. */ static int qp_wakeup_cb(void *client_data) { struct vmci_qp *qpair = (struct vmci_qp *)client_data; qp_lock(qpair); while (qpair->blocked > 0) { qpair->blocked--; qpair->generation++; wake_up(&qpair->event); } qp_unlock(qpair); return VMCI_SUCCESS; } /* * Makes the calling thread wait for the queue pair to become * ready for host side access. Returns true when thread is * woken up after queue pair state change, false otherwise. */ static bool qp_wait_for_ready_queue(struct vmci_qp *qpair) { unsigned int generation; qpair->blocked++; generation = qpair->generation; qp_unlock(qpair); wait_event(qpair->event, generation != qpair->generation); qp_lock(qpair); return true; } /* * Enqueues a given buffer to the produce queue using the provided * function. As many bytes as possible (space available in the queue) * are enqueued. Assumes the queue->mutex has been acquired. Returns * VMCI_ERROR_QUEUEPAIR_NOSPACE if no space was available to enqueue * data, VMCI_ERROR_INVALID_SIZE, if any queue pointer is outside the * queue (as defined by the queue size), VMCI_ERROR_INVALID_ARGS, if * an error occured when accessing the buffer, * VMCI_ERROR_QUEUEPAIR_NOTATTACHED, if the queue pair pages aren't * available. Otherwise, the number of bytes written to the queue is * returned. Updates the tail pointer of the produce queue. */ static ssize_t qp_enqueue_locked(struct vmci_queue *produce_q, struct vmci_queue *consume_q, const u64 produce_q_size, struct iov_iter *from) { s64 free_space; u64 tail; size_t buf_size = iov_iter_count(from); size_t written; ssize_t result; result = qp_map_queue_headers(produce_q, consume_q); if (unlikely(result != VMCI_SUCCESS)) return result; free_space = vmci_q_header_free_space(produce_q->q_header, consume_q->q_header, produce_q_size); if (free_space == 0) return VMCI_ERROR_QUEUEPAIR_NOSPACE; if (free_space < VMCI_SUCCESS) return (ssize_t) free_space; written = (size_t) (free_space > buf_size ? buf_size : free_space); tail = vmci_q_header_producer_tail(produce_q->q_header); if (likely(tail + written < produce_q_size)) { result = qp_memcpy_to_queue_iter(produce_q, tail, from, written); } else { /* Tail pointer wraps around. */ const size_t tmp = (size_t) (produce_q_size - tail); result = qp_memcpy_to_queue_iter(produce_q, tail, from, tmp); if (result >= VMCI_SUCCESS) result = qp_memcpy_to_queue_iter(produce_q, 0, from, written - tmp); } if (result < VMCI_SUCCESS) return result; /* * This virt_wmb() ensures that data written to the queue * is observable before the new producer_tail is. */ virt_wmb(); vmci_q_header_add_producer_tail(produce_q->q_header, written, produce_q_size); return written; } /* * Dequeues data (if available) from the given consume queue. Writes data * to the user provided buffer using the provided function. * Assumes the queue->mutex has been acquired. * Results: * VMCI_ERROR_QUEUEPAIR_NODATA if no data was available to dequeue. * VMCI_ERROR_INVALID_SIZE, if any queue pointer is outside the queue * (as defined by the queue size). * VMCI_ERROR_INVALID_ARGS, if an error occured when accessing the buffer. * Otherwise the number of bytes dequeued is returned. * Side effects: * Updates the head pointer of the consume queue. */ static ssize_t qp_dequeue_locked(struct vmci_queue *produce_q, struct vmci_queue *consume_q, const u64 consume_q_size, struct iov_iter *to, bool update_consumer) { size_t buf_size = iov_iter_count(to); s64 buf_ready; u64 head; size_t read; ssize_t result; result = qp_map_queue_headers(produce_q, consume_q); if (unlikely(result != VMCI_SUCCESS)) return result; buf_ready = vmci_q_header_buf_ready(consume_q->q_header, produce_q->q_header, consume_q_size); if (buf_ready == 0) return VMCI_ERROR_QUEUEPAIR_NODATA; if (buf_ready < VMCI_SUCCESS) return (ssize_t) buf_ready; /* * This virt_rmb() ensures that data from the queue will be read * after we have determined how much is ready to be consumed. */ virt_rmb(); read = (size_t) (buf_ready > buf_size ? buf_size : buf_ready); head = vmci_q_header_consumer_head(produce_q->q_header); if (likely(head + read < consume_q_size)) { result = qp_memcpy_from_queue_iter(to, consume_q, head, read); } else { /* Head pointer wraps around. */ const size_t tmp = (size_t) (consume_q_size - head); result = qp_memcpy_from_queue_iter(to, consume_q, head, tmp); if (result >= VMCI_SUCCESS) result = qp_memcpy_from_queue_iter(to, consume_q, 0, read - tmp); } if (result < VMCI_SUCCESS) return result; if (update_consumer) vmci_q_header_add_consumer_head(produce_q->q_header, read, consume_q_size); return read; } /* * vmci_qpair_alloc() - Allocates a queue pair. * @qpair: Pointer for the new vmci_qp struct. * @handle: Handle to track the resource. * @produce_qsize: Desired size of the producer queue. * @consume_qsize: Desired size of the consumer queue. * @peer: ContextID of the peer. * @flags: VMCI flags. * @priv_flags: VMCI priviledge flags. * * This is the client interface for allocating the memory for a * vmci_qp structure and then attaching to the underlying * queue. If an error occurs allocating the memory for the * vmci_qp structure no attempt is made to attach. If an * error occurs attaching, then the structure is freed. */ int vmci_qpair_alloc(struct vmci_qp **qpair, struct vmci_handle *handle, u64 produce_qsize, u64 consume_qsize, u32 peer, u32 flags, u32 priv_flags) { struct vmci_qp *my_qpair; int retval; struct vmci_handle src = VMCI_INVALID_HANDLE; struct vmci_handle dst = vmci_make_handle(peer, VMCI_INVALID_ID); enum vmci_route route; vmci_event_release_cb wakeup_cb; void *client_data; /* * Restrict the size of a queuepair. The device already * enforces a limit on the total amount of memory that can be * allocated to queuepairs for a guest. However, we try to * allocate this memory before we make the queuepair * allocation hypercall. On Linux, we allocate each page * separately, which means rather than fail, the guest will * thrash while it tries to allocate, and will become * increasingly unresponsive to the point where it appears to * be hung. So we place a limit on the size of an individual * queuepair here, and leave the device to enforce the * restriction on total queuepair memory. (Note that this * doesn't prevent all cases; a user with only this much * physical memory could still get into trouble.) The error * used by the device is NO_RESOURCES, so use that here too. */ if (!QP_SIZES_ARE_VALID(produce_qsize, consume_qsize)) return VMCI_ERROR_NO_RESOURCES; retval = vmci_route(&src, &dst, false, &route); if (retval < VMCI_SUCCESS) route = vmci_guest_code_active() ? VMCI_ROUTE_AS_GUEST : VMCI_ROUTE_AS_HOST; if (flags & (VMCI_QPFLAG_NONBLOCK | VMCI_QPFLAG_PINNED)) { pr_devel("NONBLOCK OR PINNED set"); return VMCI_ERROR_INVALID_ARGS; } my_qpair = kzalloc(sizeof(*my_qpair), GFP_KERNEL); if (!my_qpair) return VMCI_ERROR_NO_MEM; my_qpair->produce_q_size = produce_qsize; my_qpair->consume_q_size = consume_qsize; my_qpair->peer = peer; my_qpair->flags = flags; my_qpair->priv_flags = priv_flags; wakeup_cb = NULL; client_data = NULL; if (VMCI_ROUTE_AS_HOST == route) { my_qpair->guest_endpoint = false; if (!(flags & VMCI_QPFLAG_LOCAL)) { my_qpair->blocked = 0; my_qpair->generation = 0; init_waitqueue_head(&my_qpair->event); wakeup_cb = qp_wakeup_cb; client_data = (void *)my_qpair; } } else { my_qpair->guest_endpoint = true; } retval = vmci_qp_alloc(handle, &my_qpair->produce_q, my_qpair->produce_q_size, &my_qpair->consume_q, my_qpair->consume_q_size, my_qpair->peer, my_qpair->flags, my_qpair->priv_flags, my_qpair->guest_endpoint, wakeup_cb, client_data); if (retval < VMCI_SUCCESS) { kfree(my_qpair); return retval; } *qpair = my_qpair; my_qpair->handle = *handle; return retval; } EXPORT_SYMBOL_GPL(vmci_qpair_alloc); /* * vmci_qpair_detach() - Detatches the client from a queue pair. * @qpair: Reference of a pointer to the qpair struct. * * This is the client interface for detaching from a VMCIQPair. * Note that this routine will free the memory allocated for the * vmci_qp structure too. */ int vmci_qpair_detach(struct vmci_qp **qpair) { int result; struct vmci_qp *old_qpair; if (!qpair || !(*qpair)) return VMCI_ERROR_INVALID_ARGS; old_qpair = *qpair; result = qp_detatch(old_qpair->handle, old_qpair->guest_endpoint); /* * The guest can fail to detach for a number of reasons, and * if it does so, it will cleanup the entry (if there is one). * The host can fail too, but it won't cleanup the entry * immediately, it will do that later when the context is * freed. Either way, we need to release the qpair struct * here; there isn't much the caller can do, and we don't want * to leak. */ memset(old_qpair, 0, sizeof(*old_qpair)); old_qpair->handle = VMCI_INVALID_HANDLE; old_qpair->peer = VMCI_INVALID_ID; kfree(old_qpair); *qpair = NULL; return result; } EXPORT_SYMBOL_GPL(vmci_qpair_detach); /* * vmci_qpair_get_produce_indexes() - Retrieves the indexes of the producer. * @qpair: Pointer to the queue pair struct. * @producer_tail: Reference used for storing producer tail index. * @consumer_head: Reference used for storing the consumer head index. * * This is the client interface for getting the current indexes of the * QPair from the point of the view of the caller as the producer. */ int vmci_qpair_get_produce_indexes(const struct vmci_qp *qpair, u64 *producer_tail, u64 *consumer_head) { struct vmci_queue_header *produce_q_header; struct vmci_queue_header *consume_q_header; int result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); result = qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header); if (result == VMCI_SUCCESS) vmci_q_header_get_pointers(produce_q_header, consume_q_header, producer_tail, consumer_head); qp_unlock(qpair); if (result == VMCI_SUCCESS && ((producer_tail && *producer_tail >= qpair->produce_q_size) || (consumer_head && *consumer_head >= qpair->produce_q_size))) return VMCI_ERROR_INVALID_SIZE; return result; } EXPORT_SYMBOL_GPL(vmci_qpair_get_produce_indexes); /* * vmci_qpair_get_consume_indexes() - Retrieves the indexes of the consumer. * @qpair: Pointer to the queue pair struct. * @consumer_tail: Reference used for storing consumer tail index. * @producer_head: Reference used for storing the producer head index. * * This is the client interface for getting the current indexes of the * QPair from the point of the view of the caller as the consumer. */ int vmci_qpair_get_consume_indexes(const struct vmci_qp *qpair, u64 *consumer_tail, u64 *producer_head) { struct vmci_queue_header *produce_q_header; struct vmci_queue_header *consume_q_header; int result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); result = qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header); if (result == VMCI_SUCCESS) vmci_q_header_get_pointers(consume_q_header, produce_q_header, consumer_tail, producer_head); qp_unlock(qpair); if (result == VMCI_SUCCESS && ((consumer_tail && *consumer_tail >= qpair->consume_q_size) || (producer_head && *producer_head >= qpair->consume_q_size))) return VMCI_ERROR_INVALID_SIZE; return result; } EXPORT_SYMBOL_GPL(vmci_qpair_get_consume_indexes); /* * vmci_qpair_produce_free_space() - Retrieves free space in producer queue. * @qpair: Pointer to the queue pair struct. * * This is the client interface for getting the amount of free * space in the QPair from the point of the view of the caller as * the producer which is the common case. Returns < 0 if err, else * available bytes into which data can be enqueued if > 0. */ s64 vmci_qpair_produce_free_space(const struct vmci_qp *qpair) { struct vmci_queue_header *produce_q_header; struct vmci_queue_header *consume_q_header; s64 result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); result = qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header); if (result == VMCI_SUCCESS) result = vmci_q_header_free_space(produce_q_header, consume_q_header, qpair->produce_q_size); else result = 0; qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_produce_free_space); /* * vmci_qpair_consume_free_space() - Retrieves free space in consumer queue. * @qpair: Pointer to the queue pair struct. * * This is the client interface for getting the amount of free * space in the QPair from the point of the view of the caller as * the consumer which is not the common case. Returns < 0 if err, else * available bytes into which data can be enqueued if > 0. */ s64 vmci_qpair_consume_free_space(const struct vmci_qp *qpair) { struct vmci_queue_header *produce_q_header; struct vmci_queue_header *consume_q_header; s64 result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); result = qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header); if (result == VMCI_SUCCESS) result = vmci_q_header_free_space(consume_q_header, produce_q_header, qpair->consume_q_size); else result = 0; qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_consume_free_space); /* * vmci_qpair_produce_buf_ready() - Gets bytes ready to read from * producer queue. * @qpair: Pointer to the queue pair struct. * * This is the client interface for getting the amount of * enqueued data in the QPair from the point of the view of the * caller as the producer which is not the common case. Returns < 0 if err, * else available bytes that may be read. */ s64 vmci_qpair_produce_buf_ready(const struct vmci_qp *qpair) { struct vmci_queue_header *produce_q_header; struct vmci_queue_header *consume_q_header; s64 result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); result = qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header); if (result == VMCI_SUCCESS) result = vmci_q_header_buf_ready(produce_q_header, consume_q_header, qpair->produce_q_size); else result = 0; qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_produce_buf_ready); /* * vmci_qpair_consume_buf_ready() - Gets bytes ready to read from * consumer queue. * @qpair: Pointer to the queue pair struct. * * This is the client interface for getting the amount of * enqueued data in the QPair from the point of the view of the * caller as the consumer which is the normal case. Returns < 0 if err, * else available bytes that may be read. */ s64 vmci_qpair_consume_buf_ready(const struct vmci_qp *qpair) { struct vmci_queue_header *produce_q_header; struct vmci_queue_header *consume_q_header; s64 result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); result = qp_get_queue_headers(qpair, &produce_q_header, &consume_q_header); if (result == VMCI_SUCCESS) result = vmci_q_header_buf_ready(consume_q_header, produce_q_header, qpair->consume_q_size); else result = 0; qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_consume_buf_ready); /* * vmci_qpair_enqueue() - Throw data on the queue. * @qpair: Pointer to the queue pair struct. * @buf: Pointer to buffer containing data * @buf_size: Length of buffer. * @buf_type: Buffer type (Unused). * * This is the client interface for enqueueing data into the queue. * Returns number of bytes enqueued or < 0 on error. */ ssize_t vmci_qpair_enqueue(struct vmci_qp *qpair, const void *buf, size_t buf_size, int buf_type) { ssize_t result; struct iov_iter from; struct kvec v = {.iov_base = (void *)buf, .iov_len = buf_size}; if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; iov_iter_kvec(&from, ITER_SOURCE, &v, 1, buf_size); qp_lock(qpair); do { result = qp_enqueue_locked(qpair->produce_q, qpair->consume_q, qpair->produce_q_size, &from); if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY && !qp_wait_for_ready_queue(qpair)) result = VMCI_ERROR_WOULD_BLOCK; } while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY); qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_enqueue); /* * vmci_qpair_dequeue() - Get data from the queue. * @qpair: Pointer to the queue pair struct. * @buf: Pointer to buffer for the data * @buf_size: Length of buffer. * @buf_type: Buffer type (Unused). * * This is the client interface for dequeueing data from the queue. * Returns number of bytes dequeued or < 0 on error. */ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair, void *buf, size_t buf_size, int buf_type) { ssize_t result; struct iov_iter to; struct kvec v = {.iov_base = buf, .iov_len = buf_size}; if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; iov_iter_kvec(&to, ITER_DEST, &v, 1, buf_size); qp_lock(qpair); do { result = qp_dequeue_locked(qpair->produce_q, qpair->consume_q, qpair->consume_q_size, &to, true); if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY && !qp_wait_for_ready_queue(qpair)) result = VMCI_ERROR_WOULD_BLOCK; } while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY); qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_dequeue); /* * vmci_qpair_peek() - Peek at the data in the queue. * @qpair: Pointer to the queue pair struct. * @buf: Pointer to buffer for the data * @buf_size: Length of buffer. * @buf_type: Buffer type (Unused on Linux). * * This is the client interface for peeking into a queue. (I.e., * copy data from the queue without updating the head pointer.) * Returns number of bytes dequeued or < 0 on error. */ ssize_t vmci_qpair_peek(struct vmci_qp *qpair, void *buf, size_t buf_size, int buf_type) { struct iov_iter to; struct kvec v = {.iov_base = buf, .iov_len = buf_size}; ssize_t result; if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; iov_iter_kvec(&to, ITER_DEST, &v, 1, buf_size); qp_lock(qpair); do { result = qp_dequeue_locked(qpair->produce_q, qpair->consume_q, qpair->consume_q_size, &to, false); if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY && !qp_wait_for_ready_queue(qpair)) result = VMCI_ERROR_WOULD_BLOCK; } while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY); qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_peek); /* * vmci_qpair_enquev() - Throw data on the queue using iov. * @qpair: Pointer to the queue pair struct. * @iov: Pointer to buffer containing data * @iov_size: Length of buffer. * @buf_type: Buffer type (Unused). * * This is the client interface for enqueueing data into the queue. * This function uses IO vectors to handle the work. Returns number * of bytes enqueued or < 0 on error. */ ssize_t vmci_qpair_enquev(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size, int buf_type) { ssize_t result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); do { result = qp_enqueue_locked(qpair->produce_q, qpair->consume_q, qpair->produce_q_size, &msg->msg_iter); if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY && !qp_wait_for_ready_queue(qpair)) result = VMCI_ERROR_WOULD_BLOCK; } while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY); qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_enquev); /* * vmci_qpair_dequev() - Get data from the queue using iov. * @qpair: Pointer to the queue pair struct. * @iov: Pointer to buffer for the data * @iov_size: Length of buffer. * @buf_type: Buffer type (Unused). * * This is the client interface for dequeueing data from the queue. * This function uses IO vectors to handle the work. Returns number * of bytes dequeued or < 0 on error. */ ssize_t vmci_qpair_dequev(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size, int buf_type) { ssize_t result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); do { result = qp_dequeue_locked(qpair->produce_q, qpair->consume_q, qpair->consume_q_size, &msg->msg_iter, true); if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY && !qp_wait_for_ready_queue(qpair)) result = VMCI_ERROR_WOULD_BLOCK; } while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY); qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_dequev); /* * vmci_qpair_peekv() - Peek at the data in the queue using iov. * @qpair: Pointer to the queue pair struct. * @iov: Pointer to buffer for the data * @iov_size: Length of buffer. * @buf_type: Buffer type (Unused on Linux). * * This is the client interface for peeking into a queue. (I.e., * copy data from the queue without updating the head pointer.) * This function uses IO vectors to handle the work. Returns number * of bytes peeked or < 0 on error. */ ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size, int buf_type) { ssize_t result; if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); do { result = qp_dequeue_locked(qpair->produce_q, qpair->consume_q, qpair->consume_q_size, &msg->msg_iter, false); if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY && !qp_wait_for_ready_queue(qpair)) result = VMCI_ERROR_WOULD_BLOCK; } while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY); qp_unlock(qpair); return result; } EXPORT_SYMBOL_GPL(vmci_qpair_peekv); |
| 35 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2019 Hammerspace Inc */ #include <linux/module.h> #include <linux/kobject.h> #include <linux/sysfs.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/string.h> #include <linux/nfs_fs.h> #include <linux/rcupdate.h> #include <linux/lockd/lockd.h> #include "nfs4_fs.h" #include "netns.h" #include "sysfs.h" static struct kset *nfs_kset; static void nfs_kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); kfree(kset); } static const struct kobj_ns_type_operations *nfs_netns_object_child_ns_type( const struct kobject *kobj) { return &net_ns_type_operations; } static struct kobj_type nfs_kset_type = { .release = nfs_kset_release, .sysfs_ops = &kobj_sysfs_ops, .child_ns_type = nfs_netns_object_child_ns_type, }; int nfs_sysfs_init(void) { int ret; nfs_kset = kzalloc(sizeof(*nfs_kset), GFP_KERNEL); if (!nfs_kset) return -ENOMEM; ret = kobject_set_name(&nfs_kset->kobj, "nfs"); if (ret) { kfree(nfs_kset); return ret; } nfs_kset->kobj.parent = fs_kobj; nfs_kset->kobj.ktype = &nfs_kset_type; nfs_kset->kobj.kset = NULL; ret = kset_register(nfs_kset); if (ret) { kfree(nfs_kset); return ret; } return 0; } void nfs_sysfs_exit(void) { kset_unregister(nfs_kset); } static ssize_t nfs_netns_identifier_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct nfs_netns_client *c = container_of(kobj, struct nfs_netns_client, kobject); ssize_t ret; rcu_read_lock(); ret = sysfs_emit(buf, "%s\n", rcu_dereference(c->identifier)); rcu_read_unlock(); return ret; } /* Strip trailing '\n' */ static size_t nfs_string_strip(const char *c, size_t len) { while (len > 0 && c[len-1] == '\n') --len; return len; } static ssize_t nfs_netns_identifier_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct nfs_netns_client *c = container_of(kobj, struct nfs_netns_client, kobject); const char *old; char *p; size_t len; len = nfs_string_strip(buf, min_t(size_t, count, CONTAINER_ID_MAXLEN)); if (!len) return 0; p = kmemdup_nul(buf, len, GFP_KERNEL); if (!p) return -ENOMEM; old = rcu_dereference_protected(xchg(&c->identifier, (char __rcu *)p), 1); if (old) { synchronize_rcu(); kfree(old); } return count; } static void nfs_netns_client_release(struct kobject *kobj) { struct nfs_netns_client *c = container_of(kobj, struct nfs_netns_client, kobject); kfree(rcu_dereference_raw(c->identifier)); } static const void *nfs_netns_client_namespace(const struct kobject *kobj) { return container_of(kobj, struct nfs_netns_client, kobject)->net; } static struct kobj_attribute nfs_netns_client_id = __ATTR(identifier, 0644, nfs_netns_identifier_show, nfs_netns_identifier_store); static struct attribute *nfs_netns_client_attrs[] = { &nfs_netns_client_id.attr, NULL, }; ATTRIBUTE_GROUPS(nfs_netns_client); static struct kobj_type nfs_netns_client_type = { .release = nfs_netns_client_release, .default_groups = nfs_netns_client_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_client_namespace, }; static void nfs_netns_object_release(struct kobject *kobj) { struct nfs_netns_client *c = container_of(kobj, struct nfs_netns_client, nfs_net_kobj); kfree(c); } static const void *nfs_netns_namespace(const struct kobject *kobj) { return container_of(kobj, struct nfs_netns_client, nfs_net_kobj)->net; } static struct kobj_type nfs_netns_object_type = { .release = nfs_netns_object_release, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_namespace, }; static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent, struct net *net) { struct nfs_netns_client *p; p = kzalloc(sizeof(*p), GFP_KERNEL); if (p) { p->net = net; p->kobject.kset = nfs_kset; p->nfs_net_kobj.kset = nfs_kset; if (kobject_init_and_add(&p->nfs_net_kobj, &nfs_netns_object_type, parent, "net") != 0) { kobject_put(&p->nfs_net_kobj); return NULL; } if (kobject_init_and_add(&p->kobject, &nfs_netns_client_type, &p->nfs_net_kobj, "nfs_client") == 0) return p; kobject_put(&p->kobject); } return NULL; } void nfs_netns_sysfs_setup(struct nfs_net *netns, struct net *net) { struct nfs_netns_client *clp; clp = nfs_netns_client_alloc(&nfs_kset->kobj, net); if (clp) { netns->nfs_client = clp; kobject_uevent(&clp->kobject, KOBJ_ADD); } } void nfs_netns_sysfs_destroy(struct nfs_net *netns) { struct nfs_netns_client *clp = netns->nfs_client; if (clp) { kobject_uevent(&clp->kobject, KOBJ_REMOVE); kobject_del(&clp->kobject); kobject_put(&clp->kobject); kobject_del(&clp->nfs_net_kobj); kobject_put(&clp->nfs_net_kobj); netns->nfs_client = NULL; } } static bool shutdown_match_client(const struct rpc_task *task, const void *data) { return true; } static void shutdown_client(struct rpc_clnt *clnt) { clnt->cl_shutdown = 1; rpc_cancel_tasks(clnt, -EIO, shutdown_match_client, NULL); } static ssize_t shutdown_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct nfs_server *server = container_of(kobj, struct nfs_server, kobj); bool shutdown = server->flags & NFS_MOUNT_SHUTDOWN; return sysfs_emit(buf, "%d\n", shutdown); } static ssize_t shutdown_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct nfs_server *server; int ret, val; server = container_of(kobj, struct nfs_server, kobj); ret = kstrtoint(buf, 0, &val); if (ret) return ret; if (val != 1) return -EINVAL; /* already shut down? */ if (server->flags & NFS_MOUNT_SHUTDOWN) goto out; server->flags |= NFS_MOUNT_SHUTDOWN; shutdown_client(server->client); shutdown_client(server->nfs_client->cl_rpcclient); if (!IS_ERR(server->client_acl)) shutdown_client(server->client_acl); if (server->nlm_host) shutdown_client(server->nlm_host->h_rpcclnt); out: return count; } static struct kobj_attribute nfs_sysfs_attr_shutdown = __ATTR_RW(shutdown); #define RPC_CLIENT_NAME_SIZE 64 void nfs_sysfs_link_rpc_client(struct nfs_server *server, struct rpc_clnt *clnt, const char *uniq) { char name[RPC_CLIENT_NAME_SIZE]; int ret; strcpy(name, clnt->cl_program->name); strcat(name, uniq ? uniq : ""); strcat(name, "_client"); ret = sysfs_create_link_nowarn(&server->kobj, &clnt->cl_sysfs->kobject, name); if (ret < 0) pr_warn("NFS: can't create link to %s in sysfs (%d)\n", name, ret); } EXPORT_SYMBOL_GPL(nfs_sysfs_link_rpc_client); static void nfs_sysfs_sb_release(struct kobject *kobj) { /* no-op: why? see lib/kobject.c kobject_cleanup() */ } static const void *nfs_netns_server_namespace(const struct kobject *kobj) { return container_of(kobj, struct nfs_server, kobj)->nfs_client->cl_net; } static struct kobj_type nfs_sb_ktype = { .release = nfs_sysfs_sb_release, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_server_namespace, .child_ns_type = nfs_netns_object_child_ns_type, }; void nfs_sysfs_add_server(struct nfs_server *server) { int ret; ret = kobject_init_and_add(&server->kobj, &nfs_sb_ktype, &nfs_kset->kobj, "server-%d", server->s_sysfs_id); if (ret < 0) { pr_warn("NFS: nfs sysfs add server-%d failed (%d)\n", server->s_sysfs_id, ret); return; } ret = sysfs_create_file_ns(&server->kobj, &nfs_sysfs_attr_shutdown.attr, nfs_netns_server_namespace(&server->kobj)); if (ret < 0) pr_warn("NFS: sysfs_create_file_ns for server-%d failed (%d)\n", server->s_sysfs_id, ret); } EXPORT_SYMBOL_GPL(nfs_sysfs_add_server); void nfs_sysfs_move_server_to_sb(struct super_block *s) { struct nfs_server *server = s->s_fs_info; int ret; ret = kobject_rename(&server->kobj, s->s_id); if (ret < 0) pr_warn("NFS: rename sysfs %s failed (%d)\n", server->kobj.name, ret); } void nfs_sysfs_move_sb_to_server(struct nfs_server *server) { const char *s; int ret = -ENOMEM; s = kasprintf(GFP_KERNEL, "server-%d", server->s_sysfs_id); if (s) { ret = kobject_rename(&server->kobj, s); kfree(s); } if (ret < 0) pr_warn("NFS: rename sysfs %s failed (%d)\n", server->kobj.name, ret); } /* unlink, not dec-ref */ void nfs_sysfs_remove_server(struct nfs_server *server) { kobject_del(&server->kobj); } |
| 2 2 2 2 4 4 4 4 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 4 4 4 4 4 4 4 3 2 2 3 15 15 15 4 4 2 2 4 13 13 2 2 2 2 2 2 2 2 4 3 3 4 3 4 4 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2016 Oracle. All Rights Reserved. * Author: Darrick J. Wong <darrick.wong@oracle.com> */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_buf_item.h" #include "xfs_inode.h" #include "xfs_inode_item.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_rmap.h" #include "xfs_refcount.h" #include "xfs_bmap.h" #include "xfs_alloc.h" #include "xfs_buf.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_attr.h" #include "xfs_exchmaps.h" static struct kmem_cache *xfs_defer_pending_cache; /* * Deferred Operations in XFS * * Due to the way locking rules work in XFS, certain transactions (block * mapping and unmapping, typically) have permanent reservations so that * we can roll the transaction to adhere to AG locking order rules and * to unlock buffers between metadata updates. Prior to rmap/reflink, * the mapping code had a mechanism to perform these deferrals for * extents that were going to be freed; this code makes that facility * more generic. * * When adding the reverse mapping and reflink features, it became * necessary to perform complex remapping multi-transactions to comply * with AG locking order rules, and to be able to spread a single * refcount update operation (an operation on an n-block extent can * update as many as n records!) among multiple transactions. XFS can * roll a transaction to facilitate this, but using this facility * requires us to log "intent" items in case log recovery needs to * redo the operation, and to log "done" items to indicate that redo * is not necessary. * * Deferred work is tracked in xfs_defer_pending items. Each pending * item tracks one type of deferred work. Incoming work items (which * have not yet had an intent logged) are attached to a pending item * on the dop_intake list, where they wait for the caller to finish * the deferred operations. * * Finishing a set of deferred operations is an involved process. To * start, we define "rolling a deferred-op transaction" as follows: * * > For each xfs_defer_pending item on the dop_intake list, * - Sort the work items in AG order. XFS locking * order rules require us to lock buffers in AG order. * - Create a log intent item for that type. * - Attach it to the pending item. * - Move the pending item from the dop_intake list to the * dop_pending list. * > Roll the transaction. * * NOTE: To avoid exceeding the transaction reservation, we limit the * number of items that we attach to a given xfs_defer_pending. * * The actual finishing process looks like this: * * > For each xfs_defer_pending in the dop_pending list, * - Roll the deferred-op transaction as above. * - Create a log done item for that type, and attach it to the * log intent item. * - For each work item attached to the log intent item, * * Perform the described action. * * Attach the work item to the log done item. * * If the result of doing the work was -EAGAIN, ->finish work * wants a new transaction. See the "Requesting a Fresh * Transaction while Finishing Deferred Work" section below for * details. * * The key here is that we must log an intent item for all pending * work items every time we roll the transaction, and that we must log * a done item as soon as the work is completed. With this mechanism * we can perform complex remapping operations, chaining intent items * as needed. * * Requesting a Fresh Transaction while Finishing Deferred Work * * If ->finish_item decides that it needs a fresh transaction to * finish the work, it must ask its caller (xfs_defer_finish) for a * continuation. The most likely cause of this circumstance are the * refcount adjust functions deciding that they've logged enough items * to be at risk of exceeding the transaction reservation. * * To get a fresh transaction, we want to log the existing log done * item to prevent the log intent item from replaying, immediately log * a new log intent item with the unfinished work items, roll the * transaction, and re-call ->finish_item wherever it left off. The * log done item and the new log intent item must be in the same * transaction or atomicity cannot be guaranteed; defer_finish ensures * that this happens. * * This requires some coordination between ->finish_item and * defer_finish. Upon deciding to request a new transaction, * ->finish_item should update the current work item to reflect the * unfinished work. Next, it should reset the log done item's list * count to the number of items finished, and return -EAGAIN. * defer_finish sees the -EAGAIN, logs the new log intent item * with the remaining work items, and leaves the xfs_defer_pending * item at the head of the dop_work queue. Then it rolls the * transaction and picks up processing where it left off. It is * required that ->finish_item must be careful to leave enough * transaction reservation to fit the new log intent item. * * This is an example of remapping the extent (E, E+B) into file X at * offset A and dealing with the extent (C, C+B) already being mapped * there: * +-------------------------------------------------+ * | Unmap file X startblock C offset A length B | t0 * | Intent to reduce refcount for extent (C, B) | * | Intent to remove rmap (X, C, A, B) | * | Intent to free extent (D, 1) (bmbt block) | * | Intent to map (X, A, B) at startblock E | * +-------------------------------------------------+ * | Map file X startblock E offset A length B | t1 * | Done mapping (X, E, A, B) | * | Intent to increase refcount for extent (E, B) | * | Intent to add rmap (X, E, A, B) | * +-------------------------------------------------+ * | Reduce refcount for extent (C, B) | t2 * | Done reducing refcount for extent (C, 9) | * | Intent to reduce refcount for extent (C+9, B-9) | * | (ran out of space after 9 refcount updates) | * +-------------------------------------------------+ * | Reduce refcount for extent (C+9, B+9) | t3 * | Done reducing refcount for extent (C+9, B-9) | * | Increase refcount for extent (E, B) | * | Done increasing refcount for extent (E, B) | * | Intent to free extent (C, B) | * | Intent to free extent (F, 1) (refcountbt block) | * | Intent to remove rmap (F, 1, REFC) | * +-------------------------------------------------+ * | Remove rmap (X, C, A, B) | t4 * | Done removing rmap (X, C, A, B) | * | Add rmap (X, E, A, B) | * | Done adding rmap (X, E, A, B) | * | Remove rmap (F, 1, REFC) | * | Done removing rmap (F, 1, REFC) | * +-------------------------------------------------+ * | Free extent (C, B) | t5 * | Done freeing extent (C, B) | * | Free extent (D, 1) | * | Done freeing extent (D, 1) | * | Free extent (F, 1) | * | Done freeing extent (F, 1) | * +-------------------------------------------------+ * * If we should crash before t2 commits, log recovery replays * the following intent items: * * - Intent to reduce refcount for extent (C, B) * - Intent to remove rmap (X, C, A, B) * - Intent to free extent (D, 1) (bmbt block) * - Intent to increase refcount for extent (E, B) * - Intent to add rmap (X, E, A, B) * * In the process of recovering, it should also generate and take care * of these intent items: * * - Intent to free extent (C, B) * - Intent to free extent (F, 1) (refcountbt block) * - Intent to remove rmap (F, 1, REFC) * * Note that the continuation requested between t2 and t3 is likely to * reoccur. */ STATIC struct xfs_log_item * xfs_defer_barrier_create_intent( struct xfs_trans *tp, struct list_head *items, unsigned int count, bool sort) { return NULL; } STATIC void xfs_defer_barrier_abort_intent( struct xfs_log_item *intent) { /* empty */ } STATIC struct xfs_log_item * xfs_defer_barrier_create_done( struct xfs_trans *tp, struct xfs_log_item *intent, unsigned int count) { return NULL; } STATIC int xfs_defer_barrier_finish_item( struct xfs_trans *tp, struct xfs_log_item *done, struct list_head *item, struct xfs_btree_cur **state) { ASSERT(0); return -EFSCORRUPTED; } STATIC void xfs_defer_barrier_cancel_item( struct list_head *item) { ASSERT(0); } static const struct xfs_defer_op_type xfs_barrier_defer_type = { .max_items = 1, .create_intent = xfs_defer_barrier_create_intent, .abort_intent = xfs_defer_barrier_abort_intent, .create_done = xfs_defer_barrier_create_done, .finish_item = xfs_defer_barrier_finish_item, .cancel_item = xfs_defer_barrier_cancel_item, }; /* Create a log intent done item for a log intent item. */ static inline void xfs_defer_create_done( struct xfs_trans *tp, struct xfs_defer_pending *dfp) { struct xfs_log_item *lip; /* If there is no log intent item, there can be no log done item. */ if (!dfp->dfp_intent) return; /* * Mark the transaction dirty, even on error. This ensures the * transaction is aborted, which: * * 1.) releases the log intent item and frees the log done item * 2.) shuts down the filesystem */ tp->t_flags |= XFS_TRANS_DIRTY; lip = dfp->dfp_ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count); if (!lip) return; tp->t_flags |= XFS_TRANS_HAS_INTENT_DONE; xfs_trans_add_item(tp, lip); set_bit(XFS_LI_DIRTY, &lip->li_flags); dfp->dfp_done = lip; } /* * Ensure there's a log intent item associated with this deferred work item if * the operation must be restarted on crash. Returns 1 if there's a log item; * 0 if there isn't; or a negative errno. */ static int xfs_defer_create_intent( struct xfs_trans *tp, struct xfs_defer_pending *dfp, bool sort) { struct xfs_log_item *lip; if (dfp->dfp_intent) return 1; lip = dfp->dfp_ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, sort); if (!lip) return 0; if (IS_ERR(lip)) return PTR_ERR(lip); tp->t_flags |= XFS_TRANS_DIRTY; xfs_trans_add_item(tp, lip); set_bit(XFS_LI_DIRTY, &lip->li_flags); dfp->dfp_intent = lip; return 1; } /* * For each pending item in the intake list, log its intent item and the * associated extents, then add the entire intake list to the end of * the pending list. * * Returns 1 if at least one log item was associated with the deferred work; * 0 if there are no log items; or a negative errno. */ static int xfs_defer_create_intents( struct xfs_trans *tp) { struct xfs_defer_pending *dfp; int ret = 0; list_for_each_entry(dfp, &tp->t_dfops, dfp_list) { int ret2; trace_xfs_defer_create_intent(tp->t_mountp, dfp); ret2 = xfs_defer_create_intent(tp, dfp, true); if (ret2 < 0) return ret2; ret |= ret2; } return ret; } static inline void xfs_defer_pending_abort( struct xfs_mount *mp, struct xfs_defer_pending *dfp) { trace_xfs_defer_pending_abort(mp, dfp); if (dfp->dfp_intent && !dfp->dfp_done) { dfp->dfp_ops->abort_intent(dfp->dfp_intent); dfp->dfp_intent = NULL; } } static inline void xfs_defer_pending_cancel_work( struct xfs_mount *mp, struct xfs_defer_pending *dfp) { struct list_head *pwi; struct list_head *n; trace_xfs_defer_cancel_list(mp, dfp); list_del(&dfp->dfp_list); list_for_each_safe(pwi, n, &dfp->dfp_work) { list_del(pwi); dfp->dfp_count--; trace_xfs_defer_cancel_item(mp, dfp, pwi); dfp->dfp_ops->cancel_item(pwi); } ASSERT(dfp->dfp_count == 0); kmem_cache_free(xfs_defer_pending_cache, dfp); } STATIC void xfs_defer_pending_abort_list( struct xfs_mount *mp, struct list_head *dop_list) { struct xfs_defer_pending *dfp; /* Abort intent items that don't have a done item. */ list_for_each_entry(dfp, dop_list, dfp_list) xfs_defer_pending_abort(mp, dfp); } /* Abort all the intents that were committed. */ STATIC void xfs_defer_trans_abort( struct xfs_trans *tp, struct list_head *dop_pending) { trace_xfs_defer_trans_abort(tp, _RET_IP_); xfs_defer_pending_abort_list(tp->t_mountp, dop_pending); } /* * Capture resources that the caller said not to release ("held") when the * transaction commits. Caller is responsible for zero-initializing @dres. */ static int xfs_defer_save_resources( struct xfs_defer_resources *dres, struct xfs_trans *tp) { struct xfs_buf_log_item *bli; struct xfs_inode_log_item *ili; struct xfs_log_item *lip; BUILD_BUG_ON(NBBY * sizeof(dres->dr_ordered) < XFS_DEFER_OPS_NR_BUFS); list_for_each_entry(lip, &tp->t_items, li_trans) { switch (lip->li_type) { case XFS_LI_BUF: bli = container_of(lip, struct xfs_buf_log_item, bli_item); if (bli->bli_flags & XFS_BLI_HOLD) { if (dres->dr_bufs >= XFS_DEFER_OPS_NR_BUFS) { ASSERT(0); return -EFSCORRUPTED; } if (bli->bli_flags & XFS_BLI_ORDERED) dres->dr_ordered |= (1U << dres->dr_bufs); else xfs_trans_dirty_buf(tp, bli->bli_buf); dres->dr_bp[dres->dr_bufs++] = bli->bli_buf; } break; case XFS_LI_INODE: ili = container_of(lip, struct xfs_inode_log_item, ili_item); if (ili->ili_lock_flags == 0) { if (dres->dr_inos >= XFS_DEFER_OPS_NR_INODES) { ASSERT(0); return -EFSCORRUPTED; } xfs_trans_log_inode(tp, ili->ili_inode, XFS_ILOG_CORE); dres->dr_ip[dres->dr_inos++] = ili->ili_inode; } break; default: break; } } return 0; } /* Attach the held resources to the transaction. */ static void xfs_defer_restore_resources( struct xfs_trans *tp, struct xfs_defer_resources *dres) { unsigned short i; /* Rejoin the joined inodes. */ for (i = 0; i < dres->dr_inos; i++) xfs_trans_ijoin(tp, dres->dr_ip[i], 0); /* Rejoin the buffers and dirty them so the log moves forward. */ for (i = 0; i < dres->dr_bufs; i++) { xfs_trans_bjoin(tp, dres->dr_bp[i]); if (dres->dr_ordered & (1U << i)) xfs_trans_ordered_buf(tp, dres->dr_bp[i]); xfs_trans_bhold(tp, dres->dr_bp[i]); } } /* Roll a transaction so we can do some deferred op processing. */ STATIC int xfs_defer_trans_roll( struct xfs_trans **tpp) { struct xfs_defer_resources dres = { }; int error; error = xfs_defer_save_resources(&dres, *tpp); if (error) return error; trace_xfs_defer_trans_roll(*tpp, _RET_IP_); /* * Roll the transaction. Rolling always given a new transaction (even * if committing the old one fails!) to hand back to the caller, so we * join the held resources to the new transaction so that we always * return with the held resources joined to @tpp, no matter what * happened. */ error = xfs_trans_roll(tpp); xfs_defer_restore_resources(*tpp, &dres); if (error) trace_xfs_defer_trans_roll_error(*tpp, error); return error; } /* * Free up any items left in the list. */ static void xfs_defer_cancel_list( struct xfs_mount *mp, struct list_head *dop_list) { struct xfs_defer_pending *dfp; struct xfs_defer_pending *pli; /* * Free the pending items. Caller should already have arranged * for the intent items to be released. */ list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) xfs_defer_pending_cancel_work(mp, dfp); } static inline void xfs_defer_relog_intent( struct xfs_trans *tp, struct xfs_defer_pending *dfp) { struct xfs_log_item *lip; xfs_defer_create_done(tp, dfp); lip = dfp->dfp_ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done); if (lip) { xfs_trans_add_item(tp, lip); set_bit(XFS_LI_DIRTY, &lip->li_flags); } dfp->dfp_done = NULL; dfp->dfp_intent = lip; } /* * Prevent a log intent item from pinning the tail of the log by logging a * done item to release the intent item; and then log a new intent item. * The caller should provide a fresh transaction and roll it after we're done. */ static void xfs_defer_relog( struct xfs_trans **tpp, struct list_head *dfops) { struct xlog *log = (*tpp)->t_mountp->m_log; struct xfs_defer_pending *dfp; xfs_lsn_t threshold_lsn = NULLCOMMITLSN; ASSERT((*tpp)->t_flags & XFS_TRANS_PERM_LOG_RES); list_for_each_entry(dfp, dfops, dfp_list) { /* * If the log intent item for this deferred op is not a part of * the current log checkpoint, relog the intent item to keep * the log tail moving forward. We're ok with this being racy * because an incorrect decision means we'll be a little slower * at pushing the tail. */ if (dfp->dfp_intent == NULL || xfs_log_item_in_current_chkpt(dfp->dfp_intent)) continue; /* * Figure out where we need the tail to be in order to maintain * the minimum required free space in the log. Only sample * the log threshold once per call. */ if (threshold_lsn == NULLCOMMITLSN) { threshold_lsn = xfs_ail_get_push_target(log->l_ailp); if (threshold_lsn == NULLCOMMITLSN) break; } if (XFS_LSN_CMP(dfp->dfp_intent->li_lsn, threshold_lsn) >= 0) continue; trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp); XFS_STATS_INC((*tpp)->t_mountp, defer_relog); xfs_defer_relog_intent(*tpp, dfp); } } /* * Log an intent-done item for the first pending intent, and finish the work * items. */ int xfs_defer_finish_one( struct xfs_trans *tp, struct xfs_defer_pending *dfp) { const struct xfs_defer_op_type *ops = dfp->dfp_ops; struct xfs_btree_cur *state = NULL; struct list_head *li, *n; int error; trace_xfs_defer_pending_finish(tp->t_mountp, dfp); xfs_defer_create_done(tp, dfp); list_for_each_safe(li, n, &dfp->dfp_work) { list_del(li); dfp->dfp_count--; trace_xfs_defer_finish_item(tp->t_mountp, dfp, li); error = ops->finish_item(tp, dfp->dfp_done, li, &state); if (error == -EAGAIN) { int ret; /* * Caller wants a fresh transaction; put the work item * back on the list and log a new log intent item to * replace the old one. See "Requesting a Fresh * Transaction while Finishing Deferred Work" above. */ list_add(li, &dfp->dfp_work); dfp->dfp_count++; dfp->dfp_done = NULL; dfp->dfp_intent = NULL; ret = xfs_defer_create_intent(tp, dfp, false); if (ret < 0) error = ret; } if (error) goto out; } /* Done with the dfp, free it. */ list_del(&dfp->dfp_list); kmem_cache_free(xfs_defer_pending_cache, dfp); out: if (ops->finish_cleanup) ops->finish_cleanup(tp, state, error); return error; } /* Move all paused deferred work from @tp to @paused_list. */ static void xfs_defer_isolate_paused( struct xfs_trans *tp, struct list_head *paused_list) { struct xfs_defer_pending *dfp; struct xfs_defer_pending *pli; list_for_each_entry_safe(dfp, pli, &tp->t_dfops, dfp_list) { if (!(dfp->dfp_flags & XFS_DEFER_PAUSED)) continue; list_move_tail(&dfp->dfp_list, paused_list); trace_xfs_defer_isolate_paused(tp->t_mountp, dfp); } } /* * Finish all the pending work. This involves logging intent items for * any work items that wandered in since the last transaction roll (if * one has even happened), rolling the transaction, and finishing the * work items in the first item on the logged-and-pending list. * * If an inode is provided, relog it to the new transaction. */ int xfs_defer_finish_noroll( struct xfs_trans **tp) { struct xfs_defer_pending *dfp = NULL; int error = 0; LIST_HEAD(dop_pending); LIST_HEAD(dop_paused); ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES); trace_xfs_defer_finish(*tp, _RET_IP_); /* Until we run out of pending work to finish... */ while (!list_empty(&dop_pending) || !list_empty(&(*tp)->t_dfops)) { /* * Deferred items that are created in the process of finishing * other deferred work items should be queued at the head of * the pending list, which puts them ahead of the deferred work * that was created by the caller. This keeps the number of * pending work items to a minimum, which decreases the amount * of time that any one intent item can stick around in memory, * pinning the log tail. */ int has_intents = xfs_defer_create_intents(*tp); xfs_defer_isolate_paused(*tp, &dop_paused); list_splice_init(&(*tp)->t_dfops, &dop_pending); if (has_intents < 0) { error = has_intents; goto out_shutdown; } if (has_intents || dfp) { error = xfs_defer_trans_roll(tp); if (error) goto out_shutdown; /* Relog intent items to keep the log moving. */ xfs_defer_relog(tp, &dop_pending); xfs_defer_relog(tp, &dop_paused); if ((*tp)->t_flags & XFS_TRANS_DIRTY) { error = xfs_defer_trans_roll(tp); if (error) goto out_shutdown; } } dfp = list_first_entry_or_null(&dop_pending, struct xfs_defer_pending, dfp_list); if (!dfp) break; error = xfs_defer_finish_one(*tp, dfp); if (error && error != -EAGAIN) goto out_shutdown; } /* Requeue the paused items in the outgoing transaction. */ list_splice_tail_init(&dop_paused, &(*tp)->t_dfops); trace_xfs_defer_finish_done(*tp, _RET_IP_); return 0; out_shutdown: list_splice_tail_init(&dop_paused, &dop_pending); xfs_defer_trans_abort(*tp, &dop_pending); xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); trace_xfs_defer_finish_error(*tp, error); xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending); xfs_defer_cancel(*tp); return error; } int xfs_defer_finish( struct xfs_trans **tp) { #ifdef DEBUG struct xfs_defer_pending *dfp; #endif int error; /* * Finish and roll the transaction once more to avoid returning to the * caller with a dirty transaction. */ error = xfs_defer_finish_noroll(tp); if (error) return error; if ((*tp)->t_flags & XFS_TRANS_DIRTY) { error = xfs_defer_trans_roll(tp); if (error) { xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE); return error; } } /* Reset LOWMODE now that we've finished all the dfops. */ #ifdef DEBUG list_for_each_entry(dfp, &(*tp)->t_dfops, dfp_list) ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED); #endif (*tp)->t_flags &= ~XFS_TRANS_LOWMODE; return 0; } void xfs_defer_cancel( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; trace_xfs_defer_cancel(tp, _RET_IP_); xfs_defer_trans_abort(tp, &tp->t_dfops); xfs_defer_cancel_list(mp, &tp->t_dfops); } /* * Return the last pending work item attached to this transaction if it matches * the deferred op type. */ static inline struct xfs_defer_pending * xfs_defer_find_last( struct xfs_trans *tp, const struct xfs_defer_op_type *ops) { struct xfs_defer_pending *dfp = NULL; /* No dfops at all? */ if (list_empty(&tp->t_dfops)) return NULL; dfp = list_last_entry(&tp->t_dfops, struct xfs_defer_pending, dfp_list); /* Wrong type? */ if (dfp->dfp_ops != ops) return NULL; return dfp; } /* * Decide if we can add a deferred work item to the last dfops item attached * to the transaction. */ static inline bool xfs_defer_can_append( struct xfs_defer_pending *dfp, const struct xfs_defer_op_type *ops) { /* Already logged? */ if (dfp->dfp_intent) return false; /* Paused items cannot absorb more work */ if (dfp->dfp_flags & XFS_DEFER_PAUSED) return NULL; /* Already full? */ if (ops->max_items && dfp->dfp_count >= ops->max_items) return false; return true; } /* Create a new pending item at the end of the transaction list. */ static inline struct xfs_defer_pending * xfs_defer_alloc( struct list_head *dfops, const struct xfs_defer_op_type *ops) { struct xfs_defer_pending *dfp; dfp = kmem_cache_zalloc(xfs_defer_pending_cache, GFP_KERNEL | __GFP_NOFAIL); dfp->dfp_ops = ops; INIT_LIST_HEAD(&dfp->dfp_work); list_add_tail(&dfp->dfp_list, dfops); return dfp; } /* Add an item for later deferred processing. */ struct xfs_defer_pending * xfs_defer_add( struct xfs_trans *tp, struct list_head *li, const struct xfs_defer_op_type *ops) { struct xfs_defer_pending *dfp = NULL; ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); dfp = xfs_defer_find_last(tp, ops); if (!dfp || !xfs_defer_can_append(dfp, ops)) dfp = xfs_defer_alloc(&tp->t_dfops, ops); xfs_defer_add_item(dfp, li); trace_xfs_defer_add_item(tp->t_mountp, dfp, li); return dfp; } /* * Add a defer ops barrier to force two otherwise adjacent deferred work items * to be tracked separately and have separate log items. */ void xfs_defer_add_barrier( struct xfs_trans *tp) { struct xfs_defer_pending *dfp; ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); /* If the last defer op added was a barrier, we're done. */ dfp = xfs_defer_find_last(tp, &xfs_barrier_defer_type); if (dfp) return; xfs_defer_alloc(&tp->t_dfops, &xfs_barrier_defer_type); trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL); } /* * Create a pending deferred work item to replay the recovered intent item * and add it to the list. */ void xfs_defer_start_recovery( struct xfs_log_item *lip, struct list_head *r_dfops, const struct xfs_defer_op_type *ops) { struct xfs_defer_pending *dfp = xfs_defer_alloc(r_dfops, ops); dfp->dfp_intent = lip; } /* * Cancel a deferred work item created to recover a log intent item. @dfp * will be freed after this function returns. */ void xfs_defer_cancel_recovery( struct xfs_mount *mp, struct xfs_defer_pending *dfp) { xfs_defer_pending_abort(mp, dfp); xfs_defer_pending_cancel_work(mp, dfp); } /* Replay the deferred work item created from a recovered log intent item. */ int xfs_defer_finish_recovery( struct xfs_mount *mp, struct xfs_defer_pending *dfp, struct list_head *capture_list) { const struct xfs_defer_op_type *ops = dfp->dfp_ops; int error; /* dfp is freed by recover_work and must not be accessed afterwards */ error = ops->recover_work(dfp, capture_list); if (error) trace_xlog_intent_recovery_failed(mp, ops, error); return error; } /* * Move deferred ops from one transaction to another and reset the source to * initial state. This is primarily used to carry state forward across * transaction rolls with pending dfops. */ void xfs_defer_move( struct xfs_trans *dtp, struct xfs_trans *stp) { list_splice_init(&stp->t_dfops, &dtp->t_dfops); /* * Low free space mode was historically controlled by a dfops field. * This meant that low mode state potentially carried across multiple * transaction rolls. Transfer low mode on a dfops move to preserve * that behavior. */ dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE); stp->t_flags &= ~XFS_TRANS_LOWMODE; } /* * Prepare a chain of fresh deferred ops work items to be completed later. Log * recovery requires the ability to put off until later the actual finishing * work so that it can process unfinished items recovered from the log in * correct order. * * Create and log intent items for all the work that we're capturing so that we * can be assured that the items will get replayed if the system goes down * before log recovery gets a chance to finish the work it put off. The entire * deferred ops state is transferred to the capture structure and the * transaction is then ready for the caller to commit it. If there are no * intent items to capture, this function returns NULL. * * If capture_ip is not NULL, the capture structure will obtain an extra * reference to the inode. */ static struct xfs_defer_capture * xfs_defer_ops_capture( struct xfs_trans *tp) { struct xfs_defer_capture *dfc; unsigned short i; int error; if (list_empty(&tp->t_dfops)) return NULL; error = xfs_defer_create_intents(tp); if (error < 0) return ERR_PTR(error); /* Create an object to capture the defer ops. */ dfc = kzalloc(sizeof(*dfc), GFP_KERNEL | __GFP_NOFAIL); INIT_LIST_HEAD(&dfc->dfc_list); INIT_LIST_HEAD(&dfc->dfc_dfops); /* Move the dfops chain and transaction state to the capture struct. */ list_splice_init(&tp->t_dfops, &dfc->dfc_dfops); dfc->dfc_tpflags = tp->t_flags & XFS_TRANS_LOWMODE; tp->t_flags &= ~XFS_TRANS_LOWMODE; /* Capture the remaining block reservations along with the dfops. */ dfc->dfc_blkres = tp->t_blk_res - tp->t_blk_res_used; dfc->dfc_rtxres = tp->t_rtx_res - tp->t_rtx_res_used; /* Preserve the log reservation size. */ dfc->dfc_logres = tp->t_log_res; error = xfs_defer_save_resources(&dfc->dfc_held, tp); if (error) { /* * Resource capture should never fail, but if it does, we * still have to shut down the log and release things * properly. */ xfs_force_shutdown(tp->t_mountp, SHUTDOWN_CORRUPT_INCORE); } /* * Grab extra references to the inodes and buffers because callers are * expected to release their held references after we commit the * transaction. */ for (i = 0; i < dfc->dfc_held.dr_inos; i++) { xfs_assert_ilocked(dfc->dfc_held.dr_ip[i], XFS_ILOCK_EXCL); ihold(VFS_I(dfc->dfc_held.dr_ip[i])); } for (i = 0; i < dfc->dfc_held.dr_bufs; i++) xfs_buf_hold(dfc->dfc_held.dr_bp[i]); return dfc; } /* Release all resources that we used to capture deferred ops. */ void xfs_defer_ops_capture_abort( struct xfs_mount *mp, struct xfs_defer_capture *dfc) { unsigned short i; xfs_defer_pending_abort_list(mp, &dfc->dfc_dfops); xfs_defer_cancel_list(mp, &dfc->dfc_dfops); for (i = 0; i < dfc->dfc_held.dr_bufs; i++) xfs_buf_relse(dfc->dfc_held.dr_bp[i]); for (i = 0; i < dfc->dfc_held.dr_inos; i++) xfs_irele(dfc->dfc_held.dr_ip[i]); kfree(dfc); } /* * Capture any deferred ops and commit the transaction. This is the last step * needed to finish a log intent item that we recovered from the log. If any * of the deferred ops operate on an inode, the caller must pass in that inode * so that the reference can be transferred to the capture structure. The * caller must hold ILOCK_EXCL on the inode, and must unlock it before calling * xfs_defer_ops_continue. */ int xfs_defer_ops_capture_and_commit( struct xfs_trans *tp, struct list_head *capture_list) { struct xfs_mount *mp = tp->t_mountp; struct xfs_defer_capture *dfc; int error; /* If we don't capture anything, commit transaction and exit. */ dfc = xfs_defer_ops_capture(tp); if (IS_ERR(dfc)) { xfs_trans_cancel(tp); return PTR_ERR(dfc); } if (!dfc) return xfs_trans_commit(tp); /* Commit the transaction and add the capture structure to the list. */ error = xfs_trans_commit(tp); if (error) { xfs_defer_ops_capture_abort(mp, dfc); return error; } list_add_tail(&dfc->dfc_list, capture_list); return 0; } /* * Attach a chain of captured deferred ops to a new transaction and free the * capture structure. If an inode was captured, it will be passed back to the * caller with ILOCK_EXCL held and joined to the transaction with lockflags==0. * The caller now owns the inode reference. */ void xfs_defer_ops_continue( struct xfs_defer_capture *dfc, struct xfs_trans *tp, struct xfs_defer_resources *dres) { unsigned int i; ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY)); /* Lock the captured resources to the new transaction. */ if (dfc->dfc_held.dr_inos > 2) { xfs_sort_inodes(dfc->dfc_held.dr_ip, dfc->dfc_held.dr_inos); xfs_lock_inodes(dfc->dfc_held.dr_ip, dfc->dfc_held.dr_inos, XFS_ILOCK_EXCL); } else if (dfc->dfc_held.dr_inos == 2) xfs_lock_two_inodes(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL, dfc->dfc_held.dr_ip[1], XFS_ILOCK_EXCL); else if (dfc->dfc_held.dr_inos == 1) xfs_ilock(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL); for (i = 0; i < dfc->dfc_held.dr_bufs; i++) xfs_buf_lock(dfc->dfc_held.dr_bp[i]); /* Join the captured resources to the new transaction. */ xfs_defer_restore_resources(tp, &dfc->dfc_held); memcpy(dres, &dfc->dfc_held, sizeof(struct xfs_defer_resources)); dres->dr_bufs = 0; /* Move captured dfops chain and state to the transaction. */ list_splice_init(&dfc->dfc_dfops, &tp->t_dfops); tp->t_flags |= dfc->dfc_tpflags; kfree(dfc); } /* Release the resources captured and continued during recovery. */ void xfs_defer_resources_rele( struct xfs_defer_resources *dres) { unsigned short i; for (i = 0; i < dres->dr_inos; i++) { xfs_iunlock(dres->dr_ip[i], XFS_ILOCK_EXCL); xfs_irele(dres->dr_ip[i]); dres->dr_ip[i] = NULL; } for (i = 0; i < dres->dr_bufs; i++) { xfs_buf_relse(dres->dr_bp[i]); dres->dr_bp[i] = NULL; } dres->dr_inos = 0; dres->dr_bufs = 0; dres->dr_ordered = 0; } static inline int __init xfs_defer_init_cache(void) { xfs_defer_pending_cache = kmem_cache_create("xfs_defer_pending", sizeof(struct xfs_defer_pending), 0, 0, NULL); return xfs_defer_pending_cache != NULL ? 0 : -ENOMEM; } static inline void xfs_defer_destroy_cache(void) { kmem_cache_destroy(xfs_defer_pending_cache); xfs_defer_pending_cache = NULL; } /* Set up caches for deferred work items. */ int __init xfs_defer_init_item_caches(void) { int error; error = xfs_defer_init_cache(); if (error) return error; error = xfs_rmap_intent_init_cache(); if (error) goto err; error = xfs_refcount_intent_init_cache(); if (error) goto err; error = xfs_bmap_intent_init_cache(); if (error) goto err; error = xfs_extfree_intent_init_cache(); if (error) goto err; error = xfs_attr_intent_init_cache(); if (error) goto err; error = xfs_exchmaps_intent_init_cache(); if (error) goto err; return 0; err: xfs_defer_destroy_item_caches(); return error; } /* Destroy all the deferred work item caches, if they've been allocated. */ void xfs_defer_destroy_item_caches(void) { xfs_exchmaps_intent_destroy_cache(); xfs_attr_intent_destroy_cache(); xfs_extfree_intent_destroy_cache(); xfs_bmap_intent_destroy_cache(); xfs_refcount_intent_destroy_cache(); xfs_rmap_intent_destroy_cache(); xfs_defer_destroy_cache(); } /* * Mark a deferred work item so that it will be requeued indefinitely without * being finished. Caller must ensure there are no data dependencies on this * work item in the meantime. */ void xfs_defer_item_pause( struct xfs_trans *tp, struct xfs_defer_pending *dfp) { ASSERT(!(dfp->dfp_flags & XFS_DEFER_PAUSED)); dfp->dfp_flags |= XFS_DEFER_PAUSED; trace_xfs_defer_item_pause(tp->t_mountp, dfp); } /* * Release a paused deferred work item so that it will be finished during the * next transaction roll. */ void xfs_defer_item_unpause( struct xfs_trans *tp, struct xfs_defer_pending *dfp) { ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED); dfp->dfp_flags &= ~XFS_DEFER_PAUSED; trace_xfs_defer_item_unpause(tp->t_mountp, dfp); } |
| 2 6 2 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #ifndef RXE_PARAM_H #define RXE_PARAM_H #include <uapi/rdma/rdma_user_rxe.h> #define DEFAULT_MAX_VALUE (1 << 20) static inline enum ib_mtu rxe_mtu_int_to_enum(int mtu) { if (mtu < 256) return 0; else if (mtu < 512) return IB_MTU_256; else if (mtu < 1024) return IB_MTU_512; else if (mtu < 2048) return IB_MTU_1024; else if (mtu < 4096) return IB_MTU_2048; else return IB_MTU_4096; } /* Find the IB mtu for a given network MTU. */ static inline enum ib_mtu eth_mtu_int_to_enum(int mtu) { mtu -= RXE_MAX_HDR_LENGTH; return rxe_mtu_int_to_enum(mtu); } /* default/initial rxe device parameter settings */ enum rxe_device_param { RXE_MAX_MR_SIZE = -1ull, RXE_PAGE_SIZE_CAP = 0xfffff000, RXE_MAX_QP_WR = DEFAULT_MAX_VALUE, RXE_DEVICE_CAP_FLAGS = IB_DEVICE_BAD_PKEY_CNTR | IB_DEVICE_BAD_QKEY_CNTR | IB_DEVICE_AUTO_PATH_MIG | IB_DEVICE_CHANGE_PHY_PORT | IB_DEVICE_UD_AV_PORT_ENFORCE | IB_DEVICE_PORT_ACTIVE_EVENT | IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_RC_RNR_NAK_GEN | IB_DEVICE_SRQ_RESIZE | IB_DEVICE_MEM_MGT_EXTENSIONS | IB_DEVICE_MEM_WINDOW | IB_DEVICE_FLUSH_GLOBAL | IB_DEVICE_FLUSH_PERSISTENT #ifdef CONFIG_64BIT | IB_DEVICE_MEM_WINDOW_TYPE_2B | IB_DEVICE_ATOMIC_WRITE, #else | IB_DEVICE_MEM_WINDOW_TYPE_2B, #endif /* CONFIG_64BIT */ RXE_MAX_SGE = 32, RXE_MAX_WQE_SIZE = sizeof(struct rxe_send_wqe) + sizeof(struct ib_sge) * RXE_MAX_SGE, RXE_MAX_INLINE_DATA = RXE_MAX_WQE_SIZE - sizeof(struct rxe_send_wqe), RXE_MAX_SGE_RD = 32, RXE_MAX_CQ = DEFAULT_MAX_VALUE, RXE_MAX_LOG_CQE = 15, RXE_MAX_PD = DEFAULT_MAX_VALUE, RXE_MAX_QP_RD_ATOM = 128, RXE_MAX_RES_RD_ATOM = 0x3f000, RXE_MAX_QP_INIT_RD_ATOM = 128, RXE_MAX_MCAST_GRP = 8192, RXE_MAX_MCAST_QP_ATTACH = 56, RXE_MAX_TOT_MCAST_QP_ATTACH = 0x70000, RXE_MAX_AH = (1<<15) - 1, /* 32Ki - 1 */ RXE_MIN_AH_INDEX = 1, RXE_MAX_AH_INDEX = RXE_MAX_AH, RXE_MAX_SRQ_WR = DEFAULT_MAX_VALUE, RXE_MIN_SRQ_WR = 1, RXE_MAX_SRQ_SGE = 27, RXE_MIN_SRQ_SGE = 1, RXE_MAX_FMR_PAGE_LIST_LEN = 512, RXE_MAX_PKEYS = 64, RXE_LOCAL_CA_ACK_DELAY = 15, RXE_MAX_UCONTEXT = DEFAULT_MAX_VALUE, RXE_NUM_PORT = 1, RXE_MIN_QP_INDEX = 16, RXE_MAX_QP_INDEX = DEFAULT_MAX_VALUE, RXE_MAX_QP = DEFAULT_MAX_VALUE - RXE_MIN_QP_INDEX, RXE_MIN_SRQ_INDEX = 0x00020001, RXE_MAX_SRQ_INDEX = DEFAULT_MAX_VALUE, RXE_MAX_SRQ = DEFAULT_MAX_VALUE - RXE_MIN_SRQ_INDEX, RXE_MIN_MR_INDEX = 0x00000001, RXE_MAX_MR_INDEX = DEFAULT_MAX_VALUE >> 1, RXE_MAX_MR = RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX, RXE_MIN_MW_INDEX = RXE_MAX_MR_INDEX + 1, RXE_MAX_MW_INDEX = DEFAULT_MAX_VALUE, RXE_MAX_MW = RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX, RXE_MAX_PKT_PER_ACK = 64, RXE_MAX_UNACKED_PSNS = 128, /* Max inflight SKBs per queue pair */ RXE_INFLIGHT_SKBS_PER_QP_HIGH = 64, RXE_INFLIGHT_SKBS_PER_QP_LOW = 16, /* Max number of interations of each work item * before yielding the cpu to let other * work make progress */ RXE_MAX_ITERATIONS = 1024, /* Delay before calling arbiter timer */ RXE_NSEC_ARB_TIMER_DELAY = 200, /* IBTA v1.4 A3.3.1 VENDOR INFORMATION section */ RXE_VENDOR_ID = 0XFFFFFF, }; /* default/initial rxe port parameters */ enum rxe_port_param { RXE_PORT_GID_TBL_LEN = 1024, RXE_PORT_PORT_CAP_FLAGS = IB_PORT_CM_SUP, RXE_PORT_MAX_MSG_SZ = 0x800000, RXE_PORT_BAD_PKEY_CNTR = 0, RXE_PORT_QKEY_VIOL_CNTR = 0, RXE_PORT_LID = 0, RXE_PORT_SM_LID = 0, RXE_PORT_SM_SL = 0, RXE_PORT_LMC = 0, RXE_PORT_MAX_VL_NUM = 1, RXE_PORT_SUBNET_TIMEOUT = 0, RXE_PORT_INIT_TYPE_REPLY = 0, RXE_PORT_ACTIVE_WIDTH = IB_WIDTH_1X, RXE_PORT_ACTIVE_SPEED = 1, RXE_PORT_PKEY_TBL_LEN = 1, RXE_PORT_PHYS_STATE = IB_PORT_PHYS_STATE_POLLING, RXE_PORT_SUBNET_PREFIX = 0xfe80000000000000ULL, }; /* default/initial port info parameters */ enum rxe_port_info_param { RXE_PORT_INFO_VL_CAP = 4, /* 1-8 */ RXE_PORT_INFO_MTU_CAP = 5, /* 4096 */ RXE_PORT_INFO_OPER_VL = 1, /* 1 */ }; #endif /* RXE_PARAM_H */ |
| 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 | // SPDX-License-Identifier: GPL-2.0-only /* * Driver for the ov9650 sensor * * Copyright (C) 2008 Erik Andrén * Copyright (C) 2007 Ilyes Gouta. Based on the m5603x Linux Driver Project. * Copyright (C) 2005 m5603x Linux Driver Project <m5602@x3ng.com.br> * * Portions of code to USB interface and ALi driver software, * Copyright (c) 2006 Willem Duinker * v4l2 interface modeled after the V4L2 driver * for SN9C10x PC Camera Controllers */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "m5602_ov9650.h" static int ov9650_s_ctrl(struct v4l2_ctrl *ctrl); static void ov9650_dump_registers(struct sd *sd); static const unsigned char preinit_ov9650[][3] = { /* [INITCAM] */ {BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02}, {BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_CTRL, 0x00}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x08}, {BRIDGE, M5602_XB_GPIO_DIR, 0x05}, {BRIDGE, M5602_XB_GPIO_DAT, 0x04}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DIR_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DAT_H, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT, 0x00}, {BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a}, /* Reset chip */ {SENSOR, OV9650_COM7, OV9650_REGISTER_RESET}, /* Enable double clock */ {SENSOR, OV9650_CLKRC, 0x80}, /* Do something out of spec with the power */ {SENSOR, OV9650_OFON, 0x40} }; static const unsigned char init_ov9650[][3] = { /* [INITCAM] */ {BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02}, {BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_CTRL, 0x00}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x08}, {BRIDGE, M5602_XB_GPIO_DIR, 0x05}, {BRIDGE, M5602_XB_GPIO_DAT, 0x04}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DIR_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DAT_H, 0x00}, {BRIDGE, M5602_XB_GPIO_DAT, 0x00}, {BRIDGE, M5602_XB_I2C_CLK_DIV, 0x0a}, /* Reset chip */ {SENSOR, OV9650_COM7, OV9650_REGISTER_RESET}, /* One extra reset is needed in order to make the sensor behave properly when resuming from ram, could be a timing issue */ {SENSOR, OV9650_COM7, OV9650_REGISTER_RESET}, /* Enable double clock */ {SENSOR, OV9650_CLKRC, 0x80}, /* Do something out of spec with the power */ {SENSOR, OV9650_OFON, 0x40}, /* Set fast AGC/AEC algorithm with unlimited step size */ {SENSOR, OV9650_COM8, OV9650_FAST_AGC_AEC | OV9650_AEC_UNLIM_STEP_SIZE}, {SENSOR, OV9650_CHLF, 0x10}, {SENSOR, OV9650_ARBLM, 0xbf}, {SENSOR, OV9650_ACOM38, 0x81}, /* Turn off color matrix coefficient double option */ {SENSOR, OV9650_COM16, 0x00}, /* Enable color matrix for RGB/YUV, Delay Y channel, set output Y/UV delay to 1 */ {SENSOR, OV9650_COM13, 0x19}, /* Enable digital BLC, Set output mode to U Y V Y */ {SENSOR, OV9650_TSLB, 0x0c}, /* Limit the AGC/AEC stable upper region */ {SENSOR, OV9650_COM24, 0x00}, /* Enable HREF and some out of spec things */ {SENSOR, OV9650_COM12, 0x73}, /* Set all DBLC offset signs to positive and do some out of spec stuff */ {SENSOR, OV9650_DBLC1, 0xdf}, {SENSOR, OV9650_COM21, 0x06}, {SENSOR, OV9650_RSVD35, 0x91}, /* Necessary, no camera stream without it */ {SENSOR, OV9650_RSVD16, 0x06}, {SENSOR, OV9650_RSVD94, 0x99}, {SENSOR, OV9650_RSVD95, 0x99}, {SENSOR, OV9650_RSVD96, 0x04}, /* Enable full range output */ {SENSOR, OV9650_COM15, 0x0}, /* Enable HREF at optical black, enable ADBLC bias, enable ADBLC, reset timings at format change */ {SENSOR, OV9650_COM6, 0x4b}, /* Subtract 32 from the B channel bias */ {SENSOR, OV9650_BBIAS, 0xa0}, /* Subtract 32 from the Gb channel bias */ {SENSOR, OV9650_GbBIAS, 0xa0}, /* Do not bypass the analog BLC and to some out of spec stuff */ {SENSOR, OV9650_Gr_COM, 0x00}, /* Subtract 32 from the R channel bias */ {SENSOR, OV9650_RBIAS, 0xa0}, /* Subtract 32 from the R channel bias */ {SENSOR, OV9650_RBIAS, 0x0}, {SENSOR, OV9650_COM26, 0x80}, {SENSOR, OV9650_ACOMA9, 0x98}, /* Set the AGC/AEC stable region upper limit */ {SENSOR, OV9650_AEW, 0x68}, /* Set the AGC/AEC stable region lower limit */ {SENSOR, OV9650_AEB, 0x5c}, /* Set the high and low limit nibbles to 3 */ {SENSOR, OV9650_VPT, 0xc3}, /* Set the Automatic Gain Ceiling (AGC) to 128x, drop VSYNC at frame drop, limit exposure timing, drop frame when the AEC step is larger than the exposure gap */ {SENSOR, OV9650_COM9, 0x6e}, /* Set VSYNC negative, Set RESET to SLHS (slave mode horizontal sync) and set PWDN to SLVS (slave mode vertical sync) */ {SENSOR, OV9650_COM10, 0x42}, /* Set horizontal column start high to default value */ {SENSOR, OV9650_HSTART, 0x1a}, /* 210 */ /* Set horizontal column end */ {SENSOR, OV9650_HSTOP, 0xbf}, /* 1534 */ /* Complementing register to the two writes above */ {SENSOR, OV9650_HREF, 0xb2}, /* Set vertical row start high bits */ {SENSOR, OV9650_VSTRT, 0x02}, /* Set vertical row end low bits */ {SENSOR, OV9650_VSTOP, 0x7e}, /* Set complementing vertical frame control */ {SENSOR, OV9650_VREF, 0x10}, {SENSOR, OV9650_ADC, 0x04}, {SENSOR, OV9650_HV, 0x40}, /* Enable denoise, and white-pixel erase */ {SENSOR, OV9650_COM22, OV9650_DENOISE_ENABLE | OV9650_WHITE_PIXEL_ENABLE | OV9650_WHITE_PIXEL_OPTION}, /* Enable VARIOPIXEL */ {SENSOR, OV9650_COM3, OV9650_VARIOPIXEL}, {SENSOR, OV9650_COM4, OV9650_QVGA_VARIOPIXEL}, /* Put the sensor in soft sleep mode */ {SENSOR, OV9650_COM2, OV9650_SOFT_SLEEP | OV9650_OUTPUT_DRIVE_2X}, }; static const unsigned char res_init_ov9650[][3] = { {SENSOR, OV9650_COM2, OV9650_OUTPUT_DRIVE_2X}, {BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x82}, {BRIDGE, M5602_XB_LINE_OF_FRAME_L, 0x00}, {BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82}, {BRIDGE, M5602_XB_PIX_OF_LINE_L, 0x00}, {BRIDGE, M5602_XB_SIG_INI, 0x01} }; /* Vertically and horizontally flips the image if matched, needed for machines where the sensor is mounted upside down */ static const struct dmi_system_id ov9650_flip_dmi_table[] = { { .ident = "ASUS A6Ja", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "A6J") } }, { .ident = "ASUS A6JC", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "A6JC") } }, { .ident = "ASUS A6K", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "A6K") } }, { .ident = "ASUS A6Kt", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "A6Kt") } }, { .ident = "ASUS A6VA", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "A6VA") } }, { .ident = "ASUS A6VC", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "A6VC") } }, { .ident = "ASUS A6VM", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "A6VM") } }, { .ident = "ASUS A7V", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "A7V") } }, { .ident = "Alienware Aurora m9700", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "alienware"), DMI_MATCH(DMI_PRODUCT_NAME, "Aurora m9700") } }, {} }; static struct v4l2_pix_format ov9650_modes[] = { { 176, 144, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE, .sizeimage = 176 * 144, .bytesperline = 176, .colorspace = V4L2_COLORSPACE_SRGB, .priv = 9 }, { 320, 240, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE, .sizeimage = 320 * 240, .bytesperline = 320, .colorspace = V4L2_COLORSPACE_SRGB, .priv = 8 }, { 352, 288, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE, .sizeimage = 352 * 288, .bytesperline = 352, .colorspace = V4L2_COLORSPACE_SRGB, .priv = 9 }, { 640, 480, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE, .sizeimage = 640 * 480, .bytesperline = 640, .colorspace = V4L2_COLORSPACE_SRGB, .priv = 9 } }; static const struct v4l2_ctrl_ops ov9650_ctrl_ops = { .s_ctrl = ov9650_s_ctrl, }; int ov9650_probe(struct sd *sd) { int err = 0; u8 prod_id = 0, ver_id = 0, i; struct gspca_dev *gspca_dev = (struct gspca_dev *)sd; if (force_sensor) { if (force_sensor == OV9650_SENSOR) { pr_info("Forcing an %s sensor\n", ov9650.name); goto sensor_found; } /* If we want to force another sensor, don't try to probe this one */ return -ENODEV; } gspca_dbg(gspca_dev, D_PROBE, "Probing for an ov9650 sensor\n"); /* Run the pre-init before probing the sensor */ for (i = 0; i < ARRAY_SIZE(preinit_ov9650) && !err; i++) { u8 data = preinit_ov9650[i][2]; if (preinit_ov9650[i][0] == SENSOR) err = m5602_write_sensor(sd, preinit_ov9650[i][1], &data, 1); else err = m5602_write_bridge(sd, preinit_ov9650[i][1], data); } if (err < 0) return err; if (m5602_read_sensor(sd, OV9650_PID, &prod_id, 1)) return -ENODEV; if (m5602_read_sensor(sd, OV9650_VER, &ver_id, 1)) return -ENODEV; if ((prod_id == 0x96) && (ver_id == 0x52)) { pr_info("Detected an ov9650 sensor\n"); goto sensor_found; } return -ENODEV; sensor_found: sd->gspca_dev.cam.cam_mode = ov9650_modes; sd->gspca_dev.cam.nmodes = ARRAY_SIZE(ov9650_modes); return 0; } int ov9650_init(struct sd *sd) { int i, err = 0; u8 data; if (dump_sensor) ov9650_dump_registers(sd); for (i = 0; i < ARRAY_SIZE(init_ov9650) && !err; i++) { data = init_ov9650[i][2]; if (init_ov9650[i][0] == SENSOR) err = m5602_write_sensor(sd, init_ov9650[i][1], &data, 1); else err = m5602_write_bridge(sd, init_ov9650[i][1], data); } return 0; } int ov9650_init_controls(struct sd *sd) { struct v4l2_ctrl_handler *hdl = &sd->gspca_dev.ctrl_handler; sd->gspca_dev.vdev.ctrl_handler = hdl; v4l2_ctrl_handler_init(hdl, 9); sd->auto_white_bal = v4l2_ctrl_new_std(hdl, &ov9650_ctrl_ops, V4L2_CID_AUTO_WHITE_BALANCE, 0, 1, 1, 1); sd->red_bal = v4l2_ctrl_new_std(hdl, &ov9650_ctrl_ops, V4L2_CID_RED_BALANCE, 0, 255, 1, RED_GAIN_DEFAULT); sd->blue_bal = v4l2_ctrl_new_std(hdl, &ov9650_ctrl_ops, V4L2_CID_BLUE_BALANCE, 0, 255, 1, BLUE_GAIN_DEFAULT); sd->autoexpo = v4l2_ctrl_new_std_menu(hdl, &ov9650_ctrl_ops, V4L2_CID_EXPOSURE_AUTO, 1, 0, V4L2_EXPOSURE_AUTO); sd->expo = v4l2_ctrl_new_std(hdl, &ov9650_ctrl_ops, V4L2_CID_EXPOSURE, 0, 0x1ff, 4, EXPOSURE_DEFAULT); sd->autogain = v4l2_ctrl_new_std(hdl, &ov9650_ctrl_ops, V4L2_CID_AUTOGAIN, 0, 1, 1, 1); sd->gain = v4l2_ctrl_new_std(hdl, &ov9650_ctrl_ops, V4L2_CID_GAIN, 0, 0x3ff, 1, GAIN_DEFAULT); sd->hflip = v4l2_ctrl_new_std(hdl, &ov9650_ctrl_ops, V4L2_CID_HFLIP, 0, 1, 1, 0); sd->vflip = v4l2_ctrl_new_std(hdl, &ov9650_ctrl_ops, V4L2_CID_VFLIP, 0, 1, 1, 0); if (hdl->error) { pr_err("Could not initialize controls\n"); return hdl->error; } v4l2_ctrl_auto_cluster(3, &sd->auto_white_bal, 0, false); v4l2_ctrl_auto_cluster(2, &sd->autoexpo, 0, false); v4l2_ctrl_auto_cluster(2, &sd->autogain, 0, false); v4l2_ctrl_cluster(2, &sd->hflip); return 0; } int ov9650_start(struct sd *sd) { u8 data; int i, err = 0; struct cam *cam = &sd->gspca_dev.cam; int width = cam->cam_mode[sd->gspca_dev.curr_mode].width; int height = cam->cam_mode[sd->gspca_dev.curr_mode].height; int ver_offs = cam->cam_mode[sd->gspca_dev.curr_mode].priv; int hor_offs = OV9650_LEFT_OFFSET; struct gspca_dev *gspca_dev = (struct gspca_dev *)sd; if ((!dmi_check_system(ov9650_flip_dmi_table) && sd->vflip->val) || (dmi_check_system(ov9650_flip_dmi_table) && !sd->vflip->val)) ver_offs--; if (width <= 320) hor_offs /= 2; /* Synthesize the vsync/hsync setup */ for (i = 0; i < ARRAY_SIZE(res_init_ov9650) && !err; i++) { if (res_init_ov9650[i][0] == BRIDGE) err = m5602_write_bridge(sd, res_init_ov9650[i][1], res_init_ov9650[i][2]); else if (res_init_ov9650[i][0] == SENSOR) { data = res_init_ov9650[i][2]; err = m5602_write_sensor(sd, res_init_ov9650[i][1], &data, 1); } } if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, ((ver_offs >> 8) & 0xff)); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, (ver_offs & 0xff)); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, 0); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, (height >> 8) & 0xff); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, (height & 0xff)); if (err < 0) return err; for (i = 0; i < 2 && !err; i++) err = m5602_write_bridge(sd, M5602_XB_VSYNC_PARA, 0); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_SIG_INI, 0); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_SIG_INI, 2); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_HSYNC_PARA, (hor_offs >> 8) & 0xff); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_HSYNC_PARA, hor_offs & 0xff); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_HSYNC_PARA, ((width + hor_offs) >> 8) & 0xff); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_HSYNC_PARA, ((width + hor_offs) & 0xff)); if (err < 0) return err; err = m5602_write_bridge(sd, M5602_XB_SIG_INI, 0); if (err < 0) return err; switch (width) { case 640: gspca_dbg(gspca_dev, D_CONF, "Configuring camera for VGA mode\n"); data = OV9650_VGA_SELECT | OV9650_RGB_SELECT | OV9650_RAW_RGB_SELECT; err = m5602_write_sensor(sd, OV9650_COM7, &data, 1); break; case 352: gspca_dbg(gspca_dev, D_CONF, "Configuring camera for CIF mode\n"); data = OV9650_CIF_SELECT | OV9650_RGB_SELECT | OV9650_RAW_RGB_SELECT; err = m5602_write_sensor(sd, OV9650_COM7, &data, 1); break; case 320: gspca_dbg(gspca_dev, D_CONF, "Configuring camera for QVGA mode\n"); data = OV9650_QVGA_SELECT | OV9650_RGB_SELECT | OV9650_RAW_RGB_SELECT; err = m5602_write_sensor(sd, OV9650_COM7, &data, 1); break; case 176: gspca_dbg(gspca_dev, D_CONF, "Configuring camera for QCIF mode\n"); data = OV9650_QCIF_SELECT | OV9650_RGB_SELECT | OV9650_RAW_RGB_SELECT; err = m5602_write_sensor(sd, OV9650_COM7, &data, 1); break; } return err; } int ov9650_stop(struct sd *sd) { u8 data = OV9650_SOFT_SLEEP | OV9650_OUTPUT_DRIVE_2X; return m5602_write_sensor(sd, OV9650_COM2, &data, 1); } void ov9650_disconnect(struct sd *sd) { ov9650_stop(sd); sd->sensor = NULL; } static int ov9650_set_exposure(struct gspca_dev *gspca_dev, __s32 val) { struct sd *sd = (struct sd *) gspca_dev; u8 i2c_data; int err; gspca_dbg(gspca_dev, D_CONF, "Set exposure to %d\n", val); /* The 6 MSBs */ i2c_data = (val >> 10) & 0x3f; err = m5602_write_sensor(sd, OV9650_AECHM, &i2c_data, 1); if (err < 0) return err; /* The 8 middle bits */ i2c_data = (val >> 2) & 0xff; err = m5602_write_sensor(sd, OV9650_AECH, &i2c_data, 1); if (err < 0) return err; /* The 2 LSBs */ i2c_data = val & 0x03; err = m5602_write_sensor(sd, OV9650_COM1, &i2c_data, 1); return err; } static int ov9650_set_gain(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Setting gain to %d\n", val); /* The 2 MSB */ /* Read the OV9650_VREF register first to avoid corrupting the VREF high and low bits */ err = m5602_read_sensor(sd, OV9650_VREF, &i2c_data, 1); if (err < 0) return err; /* Mask away all uninteresting bits */ i2c_data = ((val & 0x0300) >> 2) | (i2c_data & 0x3f); err = m5602_write_sensor(sd, OV9650_VREF, &i2c_data, 1); if (err < 0) return err; /* The 8 LSBs */ i2c_data = val & 0xff; err = m5602_write_sensor(sd, OV9650_GAIN, &i2c_data, 1); return err; } static int ov9650_set_red_balance(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set red gain to %d\n", val); i2c_data = val & 0xff; err = m5602_write_sensor(sd, OV9650_RED, &i2c_data, 1); return err; } static int ov9650_set_blue_balance(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set blue gain to %d\n", val); i2c_data = val & 0xff; err = m5602_write_sensor(sd, OV9650_BLUE, &i2c_data, 1); return err; } static int ov9650_set_hvflip(struct gspca_dev *gspca_dev) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; int hflip = sd->hflip->val; int vflip = sd->vflip->val; gspca_dbg(gspca_dev, D_CONF, "Set hvflip to %d %d\n", hflip, vflip); if (dmi_check_system(ov9650_flip_dmi_table)) vflip = !vflip; i2c_data = (hflip << 5) | (vflip << 4); err = m5602_write_sensor(sd, OV9650_MVFP, &i2c_data, 1); if (err < 0) return err; /* When vflip is toggled we need to readjust the bridge hsync/vsync */ if (gspca_dev->streaming) err = ov9650_start(sd); return err; } static int ov9650_set_auto_exposure(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set auto exposure control to %d\n", val); err = m5602_read_sensor(sd, OV9650_COM8, &i2c_data, 1); if (err < 0) return err; val = (val == V4L2_EXPOSURE_AUTO); i2c_data = ((i2c_data & 0xfe) | ((val & 0x01) << 0)); return m5602_write_sensor(sd, OV9650_COM8, &i2c_data, 1); } static int ov9650_set_auto_white_balance(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set auto white balance to %d\n", val); err = m5602_read_sensor(sd, OV9650_COM8, &i2c_data, 1); if (err < 0) return err; i2c_data = ((i2c_data & 0xfd) | ((val & 0x01) << 1)); err = m5602_write_sensor(sd, OV9650_COM8, &i2c_data, 1); return err; } static int ov9650_set_auto_gain(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set auto gain control to %d\n", val); err = m5602_read_sensor(sd, OV9650_COM8, &i2c_data, 1); if (err < 0) return err; i2c_data = ((i2c_data & 0xfb) | ((val & 0x01) << 2)); return m5602_write_sensor(sd, OV9650_COM8, &i2c_data, 1); } static int ov9650_s_ctrl(struct v4l2_ctrl *ctrl) { struct gspca_dev *gspca_dev = container_of(ctrl->handler, struct gspca_dev, ctrl_handler); struct sd *sd = (struct sd *) gspca_dev; int err; if (!gspca_dev->streaming) return 0; switch (ctrl->id) { case V4L2_CID_AUTO_WHITE_BALANCE: err = ov9650_set_auto_white_balance(gspca_dev, ctrl->val); if (err || ctrl->val) return err; err = ov9650_set_red_balance(gspca_dev, sd->red_bal->val); if (err) return err; err = ov9650_set_blue_balance(gspca_dev, sd->blue_bal->val); break; case V4L2_CID_EXPOSURE_AUTO: err = ov9650_set_auto_exposure(gspca_dev, ctrl->val); if (err || ctrl->val == V4L2_EXPOSURE_AUTO) return err; err = ov9650_set_exposure(gspca_dev, sd->expo->val); break; case V4L2_CID_AUTOGAIN: err = ov9650_set_auto_gain(gspca_dev, ctrl->val); if (err || ctrl->val) return err; err = ov9650_set_gain(gspca_dev, sd->gain->val); break; case V4L2_CID_HFLIP: err = ov9650_set_hvflip(gspca_dev); break; default: return -EINVAL; } return err; } static void ov9650_dump_registers(struct sd *sd) { int address; pr_info("Dumping the ov9650 register state\n"); for (address = 0; address < 0xa9; address++) { u8 value; m5602_read_sensor(sd, address, &value, 1); pr_info("register 0x%x contains 0x%x\n", address, value); } pr_info("ov9650 register state dump complete\n"); pr_info("Probing for which registers that are read/write\n"); for (address = 0; address < 0xff; address++) { u8 old_value, ctrl_value; u8 test_value[2] = {0xff, 0xff}; m5602_read_sensor(sd, address, &old_value, 1); m5602_write_sensor(sd, address, test_value, 1); m5602_read_sensor(sd, address, &ctrl_value, 1); if (ctrl_value == test_value[0]) pr_info("register 0x%x is writeable\n", address); else pr_info("register 0x%x is read only\n", address); /* Restore original value */ m5602_write_sensor(sd, address, &old_value, 1); } } |
| 12 1 1 2 8 1 2 2 2 1 3 3 2 5 5 3 3 2 1 3 3 3 3 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sched/act_sample.c - Packet sampling tc action * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> #include <linux/gfp.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <linux/tc_act/tc_sample.h> #include <net/tc_act/tc_sample.h> #include <net/psample.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/if_arp.h> static struct tc_action_ops act_sample_ops; static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = { [TCA_SAMPLE_PARMS] = { .len = sizeof(struct tc_sample) }, [TCA_SAMPLE_RATE] = { .type = NLA_U32 }, [TCA_SAMPLE_TRUNC_SIZE] = { .type = NLA_U32 }, [TCA_SAMPLE_PSAMPLE_GROUP] = { .type = NLA_U32 }, }; static int tcf_sample_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_sample_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_SAMPLE_MAX + 1]; struct psample_group *psample_group; u32 psample_group_num, rate, index; struct tcf_chain *goto_ch = NULL; struct tc_sample *parm; struct tcf_sample *s; bool exists = false; int ret, err; if (!nla) return -EINVAL; ret = nla_parse_nested_deprecated(tb, TCA_SAMPLE_MAX, nla, sample_policy, NULL); if (ret < 0) return ret; if (!tb[TCA_SAMPLE_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_sample_ops, bind, true, 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; } if (!tb[TCA_SAMPLE_RATE] || !tb[TCA_SAMPLE_PSAMPLE_GROUP]) { NL_SET_ERR_MSG(extack, "sample rate and group are required"); err = -EINVAL; goto release_idr; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; rate = nla_get_u32(tb[TCA_SAMPLE_RATE]); if (!rate) { NL_SET_ERR_MSG(extack, "invalid sample rate"); err = -EINVAL; goto put_chain; } psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]); psample_group = psample_group_get(net, psample_group_num); if (!psample_group) { err = -ENOMEM; goto put_chain; } s = to_sample(*a); spin_lock_bh(&s->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); s->rate = rate; s->psample_group_num = psample_group_num; psample_group = rcu_replace_pointer(s->psample_group, psample_group, lockdep_is_held(&s->tcf_lock)); if (tb[TCA_SAMPLE_TRUNC_SIZE]) { s->truncate = true; s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]); } spin_unlock_bh(&s->tcf_lock); if (psample_group) psample_group_put(psample_group); if (goto_ch) tcf_chain_put_by_act(goto_ch); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static void tcf_sample_cleanup(struct tc_action *a) { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; /* last reference to action, no need to lock */ psample_group = rcu_dereference_protected(s->psample_group, 1); RCU_INIT_POINTER(s->psample_group, NULL); if (psample_group) psample_group_put(psample_group); } static bool tcf_sample_dev_ok_push(struct net_device *dev) { switch (dev->type) { case ARPHRD_TUNNEL: case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: return false; default: return true; } } TC_INDIRECT_SCOPE int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; u8 cookie_data[TC_COOKIE_MAX_SIZE]; struct psample_metadata md = {}; struct tc_cookie *user_cookie; int retval; tcf_lastuse_update(&s->tcf_tm); bstats_update(this_cpu_ptr(s->common.cpu_bstats), skb); retval = READ_ONCE(s->tcf_action); psample_group = rcu_dereference_bh(s->psample_group); /* randomly sample packets according to rate */ if (psample_group && (get_random_u32_below(s->rate) == 0)) { if (!skb_at_tc_ingress(skb)) { md.in_ifindex = skb->skb_iif; md.out_ifindex = skb->dev->ifindex; } else { md.in_ifindex = skb->dev->ifindex; } /* on ingress, the mac header gets popped, so push it back */ if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_push(skb, skb->mac_len); rcu_read_lock(); user_cookie = rcu_dereference(a->user_cookie); if (user_cookie) { memcpy(cookie_data, user_cookie->data, user_cookie->len); md.user_cookie = cookie_data; md.user_cookie_len = user_cookie->len; } rcu_read_unlock(); md.trunc_size = s->truncate ? s->trunc_size : skb->len; psample_sample_packet(psample_group, skb, s->rate, &md); if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_pull(skb, skb->mac_len); } return retval; } static void tcf_sample_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_sample *s = to_sample(a); struct tcf_t *tm = &s->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_sample *s = to_sample(a); struct tc_sample opt = { .index = s->tcf_index, .refcnt = refcount_read(&s->tcf_refcnt) - ref, .bindcnt = atomic_read(&s->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&s->tcf_lock); opt.action = s->tcf_action; if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &s->tcf_tm); if (nla_put_64bit(skb, TCA_SAMPLE_TM, sizeof(t), &t, TCA_SAMPLE_PAD)) goto nla_put_failure; if (nla_put_u32(skb, TCA_SAMPLE_RATE, s->rate)) goto nla_put_failure; if (s->truncate) if (nla_put_u32(skb, TCA_SAMPLE_TRUNC_SIZE, s->trunc_size)) goto nla_put_failure; if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num)) goto nla_put_failure; spin_unlock_bh(&s->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&s->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_psample_group_put(void *priv) { struct psample_group *group = priv; psample_group_put(group); } static struct psample_group * tcf_sample_get_group(const struct tc_action *a, tc_action_priv_destructor *destructor) { struct tcf_sample *s = to_sample(a); struct psample_group *group; group = rcu_dereference_protected(s->psample_group, lockdep_is_held(&s->tcf_lock)); if (group) { psample_group_take(group); *destructor = tcf_psample_group_put; } return group; } static void tcf_offload_sample_get_group(struct flow_action_entry *entry, const struct tc_action *act) { entry->sample.psample_group = act->ops->get_psample_group(act, &entry->destructor); entry->destructor_priv = entry->sample.psample_group; } static int tcf_sample_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; entry->id = FLOW_ACTION_SAMPLE; entry->sample.trunc_size = tcf_sample_trunc_size(act); entry->sample.truncate = tcf_sample_truncate(act); entry->sample.rate = tcf_sample_rate(act); tcf_offload_sample_get_group(entry, act); *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_SAMPLE; } return 0; } static struct tc_action_ops act_sample_ops = { .kind = "sample", .id = TCA_ID_SAMPLE, .owner = THIS_MODULE, .act = tcf_sample_act, .stats_update = tcf_sample_stats_update, .dump = tcf_sample_dump, .init = tcf_sample_init, .cleanup = tcf_sample_cleanup, .get_psample_group = tcf_sample_get_group, .offload_act_setup = tcf_sample_offload_act_setup, .size = sizeof(struct tcf_sample), }; MODULE_ALIAS_NET_ACT("sample"); static __net_init int sample_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_sample_ops.net_id); return tc_action_net_init(net, tn, &act_sample_ops); } static void __net_exit sample_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_sample_ops.net_id); } static struct pernet_operations sample_net_ops = { .init = sample_init_net, .exit_batch = sample_exit_net, .id = &act_sample_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init sample_init_module(void) { return tcf_register_action(&act_sample_ops, &sample_net_ops); } static void __exit sample_cleanup_module(void) { tcf_unregister_action(&act_sample_ops, &sample_net_ops); } module_init(sample_init_module); module_exit(sample_cleanup_module); MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>"); MODULE_DESCRIPTION("Packet sampling action"); MODULE_LICENSE("GPL v2"); |
| 2 1 1 21 1 1 1 2 2 1 3 1 1 2 1 1 2 1 1 21 3 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 | /* BNEP implementation for Linux Bluetooth stack (BlueZ). Copyright (C) 2001-2002 Inventel Systemes Written 2001-2002 by David Libault <david.libault@inventel.fr> Copyright (C) 2002 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. */ #include <linux/compat.h> #include <linux/export.h> #include <linux/file.h> #include "bnep.h" static struct bt_sock_list bnep_sk_list = { .lock = __RW_LOCK_UNLOCKED(bnep_sk_list.lock) }; static int bnep_sock_release(struct socket *sock) { struct sock *sk = sock->sk; BT_DBG("sock %p sk %p", sock, sk); if (!sk) return 0; bt_sock_unlink(&bnep_sk_list, sk); sock_orphan(sk); sock_put(sk); return 0; } static int do_bnep_sock_ioctl(struct socket *sock, unsigned int cmd, void __user *argp) { struct bnep_connlist_req cl; struct bnep_connadd_req ca; struct bnep_conndel_req cd; struct bnep_conninfo ci; struct socket *nsock; __u32 supp_feat = BIT(BNEP_SETUP_RESPONSE); int err; BT_DBG("cmd %x arg %p", cmd, argp); switch (cmd) { case BNEPCONNADD: if (!capable(CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ca, argp, sizeof(ca))) return -EFAULT; nsock = sockfd_lookup(ca.sock, &err); if (!nsock) return err; if (nsock->sk->sk_state != BT_CONNECTED) { sockfd_put(nsock); return -EBADFD; } ca.device[sizeof(ca.device)-1] = 0; err = bnep_add_connection(&ca, nsock); if (!err) { if (copy_to_user(argp, &ca, sizeof(ca))) err = -EFAULT; } else sockfd_put(nsock); return err; case BNEPCONNDEL: if (!capable(CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&cd, argp, sizeof(cd))) return -EFAULT; return bnep_del_connection(&cd); case BNEPGETCONNLIST: if (copy_from_user(&cl, argp, sizeof(cl))) return -EFAULT; if (cl.cnum <= 0) return -EINVAL; err = bnep_get_connlist(&cl); if (!err && copy_to_user(argp, &cl, sizeof(cl))) return -EFAULT; return err; case BNEPGETCONNINFO: if (copy_from_user(&ci, argp, sizeof(ci))) return -EFAULT; err = bnep_get_conninfo(&ci); if (!err && copy_to_user(argp, &ci, sizeof(ci))) return -EFAULT; return err; case BNEPGETSUPPFEAT: if (copy_to_user(argp, &supp_feat, sizeof(supp_feat))) return -EFAULT; return 0; default: return -EINVAL; } return 0; } static int bnep_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return do_bnep_sock_ioctl(sock, cmd, (void __user *)arg); } #ifdef CONFIG_COMPAT static int bnep_sock_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); if (cmd == BNEPGETCONNLIST) { struct bnep_connlist_req cl; unsigned __user *p = argp; u32 uci; int err; if (get_user(cl.cnum, p) || get_user(uci, p + 1)) return -EFAULT; cl.ci = compat_ptr(uci); if (cl.cnum <= 0) return -EINVAL; err = bnep_get_connlist(&cl); if (!err && put_user(cl.cnum, p)) err = -EFAULT; return err; } return do_bnep_sock_ioctl(sock, cmd, argp); } #endif static const struct proto_ops bnep_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = bnep_sock_release, .ioctl = bnep_sock_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = bnep_sock_compat_ioctl, #endif .bind = sock_no_bind, .getname = sock_no_getname, .sendmsg = sock_no_sendmsg, .recvmsg = sock_no_recvmsg, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .mmap = sock_no_mmap }; static struct proto bnep_proto = { .name = "BNEP", .owner = THIS_MODULE, .obj_size = sizeof(struct bt_sock) }; static int bnep_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; BT_DBG("sock %p", sock); if (sock->type != SOCK_RAW) return -ESOCKTNOSUPPORT; sk = bt_sock_alloc(net, sock, &bnep_proto, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; sock->ops = &bnep_sock_ops; sock->state = SS_UNCONNECTED; bt_sock_link(&bnep_sk_list, sk); return 0; } static const struct net_proto_family bnep_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = bnep_sock_create }; int __init bnep_sock_init(void) { int err; err = proto_register(&bnep_proto, 0); if (err < 0) return err; err = bt_sock_register(BTPROTO_BNEP, &bnep_sock_family_ops); if (err < 0) { BT_ERR("Can't register BNEP socket"); goto error; } err = bt_procfs_init(&init_net, "bnep", &bnep_sk_list, NULL); if (err < 0) { BT_ERR("Failed to create BNEP proc file"); bt_sock_unregister(BTPROTO_BNEP); goto error; } BT_INFO("BNEP socket layer initialized"); return 0; error: proto_unregister(&bnep_proto); return err; } void __exit bnep_sock_cleanup(void) { bt_procfs_cleanup(&init_net, "bnep"); bt_sock_unregister(BTPROTO_BNEP); proto_unregister(&bnep_proto); } |
| 47 4 3 1 13 7 11 6 6 11 6 5 2 7 4 11 7 4 7 14 14 14 10 12 14 10 9 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/fsnotify_backend.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/exportfs.h> #include <linux/hashtable.h> extern struct kmem_cache *fanotify_mark_cache; extern struct kmem_cache *fanotify_fid_event_cachep; extern struct kmem_cache *fanotify_path_event_cachep; extern struct kmem_cache *fanotify_perm_event_cachep; /* Possible states of the permission event */ enum { FAN_EVENT_INIT, FAN_EVENT_REPORTED, FAN_EVENT_ANSWERED, FAN_EVENT_CANCELED, }; /* * 3 dwords are sufficient for most local fs (64bit ino, 32bit generation). * fh buf should be dword aligned. On 64bit arch, the ext_buf pointer is * stored in either the first or last 2 dwords. */ #define FANOTIFY_INLINE_FH_LEN (3 << 2) #define FANOTIFY_FH_HDR_LEN offsetof(struct fanotify_fh, buf) /* Fixed size struct for file handle */ struct fanotify_fh { u8 type; u8 len; #define FANOTIFY_FH_FLAG_EXT_BUF 1 u8 flags; u8 pad; unsigned char buf[]; } __aligned(4); /* Variable size struct for dir file handle + child file handle + name */ struct fanotify_info { /* size of dir_fh/file_fh including fanotify_fh hdr size */ u8 dir_fh_totlen; u8 dir2_fh_totlen; u8 file_fh_totlen; u8 name_len; u8 name2_len; u8 pad[3]; unsigned char buf[]; /* * (struct fanotify_fh) dir_fh starts at buf[0] * (optional) dir2_fh starts at buf[dir_fh_totlen] * (optional) file_fh starts at buf[dir_fh_totlen + dir2_fh_totlen] * name starts at buf[dir_fh_totlen + dir2_fh_totlen + file_fh_totlen] * ... */ #define FANOTIFY_DIR_FH_SIZE(info) ((info)->dir_fh_totlen) #define FANOTIFY_DIR2_FH_SIZE(info) ((info)->dir2_fh_totlen) #define FANOTIFY_FILE_FH_SIZE(info) ((info)->file_fh_totlen) #define FANOTIFY_NAME_SIZE(info) ((info)->name_len + 1) #define FANOTIFY_NAME2_SIZE(info) ((info)->name2_len + 1) #define FANOTIFY_DIR_FH_OFFSET(info) 0 #define FANOTIFY_DIR2_FH_OFFSET(info) \ (FANOTIFY_DIR_FH_OFFSET(info) + FANOTIFY_DIR_FH_SIZE(info)) #define FANOTIFY_FILE_FH_OFFSET(info) \ (FANOTIFY_DIR2_FH_OFFSET(info) + FANOTIFY_DIR2_FH_SIZE(info)) #define FANOTIFY_NAME_OFFSET(info) \ (FANOTIFY_FILE_FH_OFFSET(info) + FANOTIFY_FILE_FH_SIZE(info)) #define FANOTIFY_NAME2_OFFSET(info) \ (FANOTIFY_NAME_OFFSET(info) + FANOTIFY_NAME_SIZE(info)) #define FANOTIFY_DIR_FH_BUF(info) \ ((info)->buf + FANOTIFY_DIR_FH_OFFSET(info)) #define FANOTIFY_DIR2_FH_BUF(info) \ ((info)->buf + FANOTIFY_DIR2_FH_OFFSET(info)) #define FANOTIFY_FILE_FH_BUF(info) \ ((info)->buf + FANOTIFY_FILE_FH_OFFSET(info)) #define FANOTIFY_NAME_BUF(info) \ ((info)->buf + FANOTIFY_NAME_OFFSET(info)) #define FANOTIFY_NAME2_BUF(info) \ ((info)->buf + FANOTIFY_NAME2_OFFSET(info)) } __aligned(4); static inline bool fanotify_fh_has_ext_buf(struct fanotify_fh *fh) { return (fh->flags & FANOTIFY_FH_FLAG_EXT_BUF); } static inline char **fanotify_fh_ext_buf_ptr(struct fanotify_fh *fh) { BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN % 4); BUILD_BUG_ON(__alignof__(char *) - 4 + sizeof(char *) > FANOTIFY_INLINE_FH_LEN); return (char **)ALIGN((unsigned long)(fh->buf), __alignof__(char *)); } static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh) { return *fanotify_fh_ext_buf_ptr(fh); } static inline void *fanotify_fh_buf(struct fanotify_fh *fh) { return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh->buf; } static inline int fanotify_info_dir_fh_len(struct fanotify_info *info) { if (!info->dir_fh_totlen || WARN_ON_ONCE(info->dir_fh_totlen < FANOTIFY_FH_HDR_LEN)) return 0; return info->dir_fh_totlen - FANOTIFY_FH_HDR_LEN; } static inline struct fanotify_fh *fanotify_info_dir_fh(struct fanotify_info *info) { BUILD_BUG_ON(offsetof(struct fanotify_info, buf) % 4); return (struct fanotify_fh *)FANOTIFY_DIR_FH_BUF(info); } static inline int fanotify_info_dir2_fh_len(struct fanotify_info *info) { if (!info->dir2_fh_totlen || WARN_ON_ONCE(info->dir2_fh_totlen < FANOTIFY_FH_HDR_LEN)) return 0; return info->dir2_fh_totlen - FANOTIFY_FH_HDR_LEN; } static inline struct fanotify_fh *fanotify_info_dir2_fh(struct fanotify_info *info) { return (struct fanotify_fh *)FANOTIFY_DIR2_FH_BUF(info); } static inline int fanotify_info_file_fh_len(struct fanotify_info *info) { if (!info->file_fh_totlen || WARN_ON_ONCE(info->file_fh_totlen < FANOTIFY_FH_HDR_LEN)) return 0; return info->file_fh_totlen - FANOTIFY_FH_HDR_LEN; } static inline struct fanotify_fh *fanotify_info_file_fh(struct fanotify_info *info) { return (struct fanotify_fh *)FANOTIFY_FILE_FH_BUF(info); } static inline char *fanotify_info_name(struct fanotify_info *info) { if (!info->name_len) return NULL; return FANOTIFY_NAME_BUF(info); } static inline char *fanotify_info_name2(struct fanotify_info *info) { if (!info->name2_len) return NULL; return FANOTIFY_NAME2_BUF(info); } static inline void fanotify_info_init(struct fanotify_info *info) { BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN + MAX_HANDLE_SZ > U8_MAX); BUILD_BUG_ON(NAME_MAX > U8_MAX); info->dir_fh_totlen = 0; info->dir2_fh_totlen = 0; info->file_fh_totlen = 0; info->name_len = 0; info->name2_len = 0; } /* These set/copy helpers MUST be called by order */ static inline void fanotify_info_set_dir_fh(struct fanotify_info *info, unsigned int totlen) { if (WARN_ON_ONCE(info->dir2_fh_totlen > 0) || WARN_ON_ONCE(info->file_fh_totlen > 0) || WARN_ON_ONCE(info->name_len > 0) || WARN_ON_ONCE(info->name2_len > 0)) return; info->dir_fh_totlen = totlen; } static inline void fanotify_info_set_dir2_fh(struct fanotify_info *info, unsigned int totlen) { if (WARN_ON_ONCE(info->file_fh_totlen > 0) || WARN_ON_ONCE(info->name_len > 0) || WARN_ON_ONCE(info->name2_len > 0)) return; info->dir2_fh_totlen = totlen; } static inline void fanotify_info_set_file_fh(struct fanotify_info *info, unsigned int totlen) { if (WARN_ON_ONCE(info->name_len > 0) || WARN_ON_ONCE(info->name2_len > 0)) return; info->file_fh_totlen = totlen; } static inline void fanotify_info_copy_name(struct fanotify_info *info, const struct qstr *name) { if (WARN_ON_ONCE(name->len > NAME_MAX) || WARN_ON_ONCE(info->name2_len > 0)) return; info->name_len = name->len; strcpy(fanotify_info_name(info), name->name); } static inline void fanotify_info_copy_name2(struct fanotify_info *info, const struct qstr *name) { if (WARN_ON_ONCE(name->len > NAME_MAX)) return; info->name2_len = name->len; strcpy(fanotify_info_name2(info), name->name); } /* * Common structure for fanotify events. Concrete structs are allocated in * fanotify_handle_event() and freed when the information is retrieved by * userspace. The type of event determines how it was allocated, how it will * be freed and which concrete struct it may be cast to. */ enum fanotify_event_type { FANOTIFY_EVENT_TYPE_FID, /* fixed length */ FANOTIFY_EVENT_TYPE_FID_NAME, /* variable length */ FANOTIFY_EVENT_TYPE_PATH, FANOTIFY_EVENT_TYPE_PATH_PERM, FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */ FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */ __FANOTIFY_EVENT_TYPE_NUM }; #define FANOTIFY_EVENT_TYPE_BITS \ (ilog2(__FANOTIFY_EVENT_TYPE_NUM - 1) + 1) #define FANOTIFY_EVENT_HASH_BITS \ (32 - FANOTIFY_EVENT_TYPE_BITS) struct fanotify_event { struct fsnotify_event fse; struct hlist_node merge_list; /* List for hashed merge */ u32 mask; struct { unsigned int type : FANOTIFY_EVENT_TYPE_BITS; unsigned int hash : FANOTIFY_EVENT_HASH_BITS; }; struct pid *pid; }; static inline void fanotify_init_event(struct fanotify_event *event, unsigned int hash, u32 mask) { fsnotify_init_event(&event->fse); INIT_HLIST_NODE(&event->merge_list); event->hash = hash; event->mask = mask; event->pid = NULL; } #define FANOTIFY_INLINE_FH(name, size) \ struct { \ struct fanotify_fh name; \ /* Space for object_fh.buf[] - access with fanotify_fh_buf() */ \ unsigned char _inline_fh_buf[size]; \ } struct fanotify_fid_event { struct fanotify_event fae; __kernel_fsid_t fsid; FANOTIFY_INLINE_FH(object_fh, FANOTIFY_INLINE_FH_LEN); }; static inline struct fanotify_fid_event * FANOTIFY_FE(struct fanotify_event *event) { return container_of(event, struct fanotify_fid_event, fae); } struct fanotify_name_event { struct fanotify_event fae; __kernel_fsid_t fsid; struct fanotify_info info; }; static inline struct fanotify_name_event * FANOTIFY_NE(struct fanotify_event *event) { return container_of(event, struct fanotify_name_event, fae); } struct fanotify_error_event { struct fanotify_event fae; s32 error; /* Error reported by the Filesystem. */ u32 err_count; /* Suppressed errors count */ __kernel_fsid_t fsid; /* FSID this error refers to. */ FANOTIFY_INLINE_FH(object_fh, MAX_HANDLE_SZ); }; static inline struct fanotify_error_event * FANOTIFY_EE(struct fanotify_event *event) { return container_of(event, struct fanotify_error_event, fae); } static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_FID) return &FANOTIFY_FE(event)->fsid; else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME) return &FANOTIFY_NE(event)->fsid; else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) return &FANOTIFY_EE(event)->fsid; else return NULL; } static inline struct fanotify_fh *fanotify_event_object_fh( struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_FID) return &FANOTIFY_FE(event)->object_fh; else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME) return fanotify_info_file_fh(&FANOTIFY_NE(event)->info); else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) return &FANOTIFY_EE(event)->object_fh; else return NULL; } static inline struct fanotify_info *fanotify_event_info( struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME) return &FANOTIFY_NE(event)->info; else return NULL; } static inline int fanotify_event_object_fh_len(struct fanotify_event *event) { struct fanotify_info *info = fanotify_event_info(event); struct fanotify_fh *fh = fanotify_event_object_fh(event); if (info) return info->file_fh_totlen ? fh->len : 0; else return fh ? fh->len : 0; } static inline int fanotify_event_dir_fh_len(struct fanotify_event *event) { struct fanotify_info *info = fanotify_event_info(event); return info ? fanotify_info_dir_fh_len(info) : 0; } static inline int fanotify_event_dir2_fh_len(struct fanotify_event *event) { struct fanotify_info *info = fanotify_event_info(event); return info ? fanotify_info_dir2_fh_len(info) : 0; } static inline bool fanotify_event_has_object_fh(struct fanotify_event *event) { /* For error events, even zeroed fh are reported. */ if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR) return true; return fanotify_event_object_fh_len(event) > 0; } static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event) { return fanotify_event_dir_fh_len(event) > 0; } static inline bool fanotify_event_has_dir2_fh(struct fanotify_event *event) { return fanotify_event_dir2_fh_len(event) > 0; } static inline bool fanotify_event_has_any_dir_fh(struct fanotify_event *event) { return fanotify_event_has_dir_fh(event) || fanotify_event_has_dir2_fh(event); } struct fanotify_path_event { struct fanotify_event fae; struct path path; }; static inline struct fanotify_path_event * FANOTIFY_PE(struct fanotify_event *event) { return container_of(event, struct fanotify_path_event, fae); } /* * Structure for permission fanotify events. It gets allocated and freed in * fanotify_handle_event() since we wait there for user response. When the * information is retrieved by userspace the structure is moved from * group->notification_list to group->fanotify_data.access_list to wait for * user response. */ struct fanotify_perm_event { struct fanotify_event fae; struct path path; u32 response; /* userspace answer to the event */ unsigned short state; /* state of the event */ int fd; /* fd we passed to userspace for this event */ union { struct fanotify_response_info_header hdr; struct fanotify_response_info_audit_rule audit_rule; }; }; static inline struct fanotify_perm_event * FANOTIFY_PERM(struct fanotify_event *event) { return container_of(event, struct fanotify_perm_event, fae); } static inline bool fanotify_is_perm_event(u32 mask) { return IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS) && mask & FANOTIFY_PERM_EVENTS; } static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) { return container_of(fse, struct fanotify_event, fse); } static inline bool fanotify_is_error_event(u32 mask) { return mask & FAN_FS_ERROR; } static inline const struct path *fanotify_event_path(struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_PATH) return &FANOTIFY_PE(event)->path; else if (event->type == FANOTIFY_EVENT_TYPE_PATH_PERM) return &FANOTIFY_PERM(event)->path; else return NULL; } /* * Use 128 size hash table to speed up events merge. */ #define FANOTIFY_HTABLE_BITS (7) #define FANOTIFY_HTABLE_SIZE (1 << FANOTIFY_HTABLE_BITS) #define FANOTIFY_HTABLE_MASK (FANOTIFY_HTABLE_SIZE - 1) /* * Permission events and overflow event do not get merged - don't hash them. */ static inline bool fanotify_is_hashed_event(u32 mask) { return !(fanotify_is_perm_event(mask) || fsnotify_is_overflow_event(mask)); } static inline unsigned int fanotify_event_hash_bucket( struct fsnotify_group *group, struct fanotify_event *event) { return event->hash & FANOTIFY_HTABLE_MASK; } struct fanotify_mark { struct fsnotify_mark fsn_mark; __kernel_fsid_t fsid; }; static inline struct fanotify_mark *FANOTIFY_MARK(struct fsnotify_mark *mark) { return container_of(mark, struct fanotify_mark, fsn_mark); } static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1, __kernel_fsid_t *fsid2) { return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1]; } static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark) { unsigned int mflags = 0; if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY) mflags |= FAN_MARK_IGNORED_SURV_MODIFY; if (mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF) mflags |= FAN_MARK_EVICTABLE; if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) mflags |= FAN_MARK_IGNORE; return mflags; } |
| 1736 1737 407 35 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * vrf.c: device driver to encapsulate a VRF space * * Copyright (c) 2015 Cumulus Networks. All rights reserved. * Copyright (c) 2015 Shrijeet Mukherjee <shm@cumulusnetworks.com> * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> * * Based on dummy, team and ipvlan drivers */ #include <linux/ethtool.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ip.h> #include <linux/init.h> #include <linux/moduleparam.h> #include <linux/netfilter.h> #include <linux/rtnetlink.h> #include <net/rtnetlink.h> #include <linux/u64_stats_sync.h> #include <linux/hashtable.h> #include <linux/spinlock_types.h> #include <linux/inetdevice.h> #include <net/arp.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #include <net/fib_rules.h> #include <net/sch_generic.h> #include <net/netns/generic.h> #include <net/netfilter/nf_conntrack.h> #include <net/inet_dscp.h> #define DRV_NAME "vrf" #define DRV_VERSION "1.1" #define FIB_RULE_PREF 1000 /* default preference for FIB rules */ #define HT_MAP_BITS 4 #define HASH_INITVAL ((u32)0xcafef00d) struct vrf_map { DECLARE_HASHTABLE(ht, HT_MAP_BITS); spinlock_t vmap_lock; /* shared_tables: * count how many distinct tables do not comply with the strict mode * requirement. * shared_tables value must be 0 in order to enable the strict mode. * * example of the evolution of shared_tables: * | time * add vrf0 --> table 100 shared_tables = 0 | t0 * add vrf1 --> table 101 shared_tables = 0 | t1 * add vrf2 --> table 100 shared_tables = 1 | t2 * add vrf3 --> table 100 shared_tables = 1 | t3 * add vrf4 --> table 101 shared_tables = 2 v t4 * * shared_tables is a "step function" (or "staircase function") * and it is increased by one when the second vrf is associated to a * table. * * at t2, vrf0 and vrf2 are bound to table 100: shared_tables = 1. * * at t3, another dev (vrf3) is bound to the same table 100 but the * value of shared_tables is still 1. * This means that no matter how many new vrfs will register on the * table 100, the shared_tables will not increase (considering only * table 100). * * at t4, vrf4 is bound to table 101, and shared_tables = 2. * * Looking at the value of shared_tables we can immediately know if * the strict_mode can or cannot be enforced. Indeed, strict_mode * can be enforced iff shared_tables = 0. * * Conversely, shared_tables is decreased when a vrf is de-associated * from a table with exactly two associated vrfs. */ u32 shared_tables; bool strict_mode; }; struct vrf_map_elem { struct hlist_node hnode; struct list_head vrf_list; /* VRFs registered to this table */ u32 table_id; int users; int ifindex; }; static unsigned int vrf_net_id; /* per netns vrf data */ struct netns_vrf { /* protected by rtnl lock */ bool add_fib_rules; struct vrf_map vmap; struct ctl_table_header *ctl_hdr; }; struct net_vrf { struct rtable __rcu *rth; struct rt6_info __rcu *rt6; #if IS_ENABLED(CONFIG_IPV6) struct fib6_table *fib6_table; #endif u32 tb_id; struct list_head me_list; /* entry in vrf_map_elem */ int ifindex; }; static void vrf_rx_stats(struct net_device *dev, int len) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->rx_packets); u64_stats_add(&dstats->rx_bytes, len); u64_stats_update_end(&dstats->syncp); } static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb) { vrf_dev->stats.tx_errors++; kfree_skb(skb); } static struct vrf_map *netns_vrf_map(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); return &nn_vrf->vmap; } static struct vrf_map *netns_vrf_map_by_dev(struct net_device *dev) { return netns_vrf_map(dev_net(dev)); } static int vrf_map_elem_get_vrf_ifindex(struct vrf_map_elem *me) { struct list_head *me_head = &me->vrf_list; struct net_vrf *vrf; if (list_empty(me_head)) return -ENODEV; vrf = list_first_entry(me_head, struct net_vrf, me_list); return vrf->ifindex; } static struct vrf_map_elem *vrf_map_elem_alloc(gfp_t flags) { struct vrf_map_elem *me; me = kmalloc(sizeof(*me), flags); if (!me) return NULL; return me; } static void vrf_map_elem_free(struct vrf_map_elem *me) { kfree(me); } static void vrf_map_elem_init(struct vrf_map_elem *me, int table_id, int ifindex, int users) { me->table_id = table_id; me->ifindex = ifindex; me->users = users; INIT_LIST_HEAD(&me->vrf_list); } static struct vrf_map_elem *vrf_map_lookup_elem(struct vrf_map *vmap, u32 table_id) { struct vrf_map_elem *me; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_for_each_possible(vmap->ht, me, hnode, key) { if (me->table_id == table_id) return me; } return NULL; } static void vrf_map_add_elem(struct vrf_map *vmap, struct vrf_map_elem *me) { u32 table_id = me->table_id; u32 key; key = jhash_1word(table_id, HASH_INITVAL); hash_add(vmap->ht, &me->hnode, key); } static void vrf_map_del_elem(struct vrf_map_elem *me) { hash_del(&me->hnode); } static void vrf_map_lock(struct vrf_map *vmap) __acquires(&vmap->vmap_lock) { spin_lock(&vmap->vmap_lock); } static void vrf_map_unlock(struct vrf_map *vmap) __releases(&vmap->vmap_lock) { spin_unlock(&vmap->vmap_lock); } /* called with rtnl lock held */ static int vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); struct vrf_map_elem *new_me, *me; u32 table_id = vrf->tb_id; bool free_new_me = false; int users; int res; /* we pre-allocate elements used in the spin-locked section (so that we * keep the spinlock as short as possible). */ new_me = vrf_map_elem_alloc(GFP_KERNEL); if (!new_me) return -ENOMEM; vrf_map_elem_init(new_me, table_id, dev->ifindex, 0); vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) { me = new_me; vrf_map_add_elem(vmap, me); goto link_vrf; } /* we already have an entry in the vrf_map, so it means there is (at * least) a vrf registered on the specific table. */ free_new_me = true; if (vmap->strict_mode) { /* vrfs cannot share the same table */ NL_SET_ERR_MSG(extack, "Table is used by another VRF"); res = -EBUSY; goto unlock; } link_vrf: users = ++me->users; if (users == 2) ++vmap->shared_tables; list_add(&vrf->me_list, &me->vrf_list); res = 0; unlock: vrf_map_unlock(vmap); /* clean-up, if needed */ if (free_new_me) vrf_map_elem_free(new_me); return res; } /* called with rtnl lock held */ static void vrf_map_unregister_dev(struct net_device *dev) { struct vrf_map *vmap = netns_vrf_map_by_dev(dev); struct net_vrf *vrf = netdev_priv(dev); u32 table_id = vrf->tb_id; struct vrf_map_elem *me; int users; vrf_map_lock(vmap); me = vrf_map_lookup_elem(vmap, table_id); if (!me) goto unlock; list_del(&vrf->me_list); users = --me->users; if (users == 1) { --vmap->shared_tables; } else if (users == 0) { vrf_map_del_elem(me); /* no one will refer to this element anymore */ vrf_map_elem_free(me); } unlock: vrf_map_unlock(vmap); } /* return the vrf device index associated with the table_id */ static int vrf_ifindex_lookup_by_table_id(struct net *net, u32 table_id) { struct vrf_map *vmap = netns_vrf_map(net); struct vrf_map_elem *me; int ifindex; vrf_map_lock(vmap); if (!vmap->strict_mode) { ifindex = -EPERM; goto unlock; } me = vrf_map_lookup_elem(vmap, table_id); if (!me) { ifindex = -ENODEV; goto unlock; } ifindex = vrf_map_elem_get_vrf_ifindex(me); unlock: vrf_map_unlock(vmap); return ifindex; } /* by default VRF devices do not have a qdisc and are expected * to be created with only a single queue. */ static bool qdisc_tx_is_default(const struct net_device *dev) { struct netdev_queue *txq; struct Qdisc *qdisc; if (dev->num_tx_queues > 1) return false; txq = netdev_get_tx_queue(dev, 0); qdisc = rcu_access_pointer(txq->qdisc); return !qdisc->enqueue; } /* Local traffic destined to local address. Reinsert the packet to rx * path, similar to loopback handling. */ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, struct dst_entry *dst) { int len = skb->len; skb_orphan(skb); skb_dst_set(skb, dst); /* set pkt_type to avoid skb hitting packet taps twice - * once on Tx and again in Rx processing */ skb->pkt_type = PACKET_LOOPBACK; skb->protocol = eth_type_trans(skb, dev); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { vrf_rx_stats(dev, len); } else { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); u64_stats_inc(&dstats->rx_drops); u64_stats_update_end(&dstats->syncp); } return NETDEV_TX_OK; } static void vrf_nf_set_untracked(struct sk_buff *skb) { if (skb_get_nfct(skb) == 0) nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } static void vrf_nf_reset_ct(struct sk_buff *skb) { if (skb_get_nfct(skb) == IP_CT_UNTRACKED) nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) static int vrf_ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { const struct ipv6hdr *iph; struct net *net = dev_net(skb->dev); struct flowi6 fl6; int ret = NET_XMIT_DROP; struct dst_entry *dst; struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) goto err; iph = ipv6_hdr(skb); memset(&fl6, 0, sizeof(fl6)); /* needed to match OIF rule */ fl6.flowi6_l3mdev = dev->ifindex; fl6.flowi6_iif = LOOPBACK_IFINDEX; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; fl6.flowlabel = ip6_flowinfo(iph); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = iph->nexthdr; dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst) || dst == dst_null) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (dst->dev == dev) return vrf_local_xmit(skb, dev, dst); skb_dst_set(skb, dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); ret = vrf_ip6_local_out(net, skb->sk, skb); if (unlikely(net_xmit_eval(ret))) dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; return ret; err: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #else static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { vrf_tx_error(dev, skb); return NET_XMIT_DROP; } #endif /* based on ip_local_out; can't use it b/c the dst is switched pointing to us */ static int vrf_ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; vrf_nf_reset_ct(skb); err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, struct net_device *vrf_dev) { struct iphdr *ip4h; int ret = NET_XMIT_DROP; struct flowi4 fl4; struct net *net = dev_net(vrf_dev); struct rtable *rt; if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) goto err; ip4h = ip_hdr(skb); memset(&fl4, 0, sizeof(fl4)); /* needed to match OIF rule */ fl4.flowi4_l3mdev = vrf_dev->ifindex; fl4.flowi4_iif = LOOPBACK_IFINDEX; fl4.flowi4_tos = ip4h->tos & INET_DSCP_MASK; fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; fl4.flowi4_proto = ip4h->protocol; fl4.daddr = ip4h->daddr; fl4.saddr = ip4h->saddr; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; skb_dst_drop(skb); /* if dst.dev is the VRF device again this is locally originated traffic * destined to a local address. Short circuit to Rx path. */ if (rt->dst.dev == vrf_dev) return vrf_local_xmit(skb, vrf_dev, &rt->dst); skb_dst_set(skb, &rt->dst); /* strip the ethernet header added for pass through VRF device */ __skb_pull(skb, skb_network_offset(skb)); if (!ip4h->saddr) { ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0, RT_SCOPE_LINK); } memset(IPCB(skb), 0, sizeof(*IPCB(skb))); ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); if (unlikely(net_xmit_eval(ret))) vrf_dev->stats.tx_errors++; else ret = NET_XMIT_SUCCESS; out: return ret; err: vrf_tx_error(vrf_dev, skb); goto out; } static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev) { switch (skb->protocol) { case htons(ETH_P_IP): return vrf_process_v4_outbound(skb, dev); case htons(ETH_P_IPV6): return vrf_process_v6_outbound(skb, dev); default: vrf_tx_error(dev, skb); return NET_XMIT_DROP; } } static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); int len = skb->len; netdev_tx_t ret = is_ip_tx_frame(skb, dev); u64_stats_update_begin(&dstats->syncp); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { u64_stats_inc(&dstats->tx_packets); u64_stats_add(&dstats->tx_bytes, len); } else { u64_stats_inc(&dstats->tx_drops); } u64_stats_update_end(&dstats->syncp); return ret; } static void vrf_finish_direct(struct sk_buff *skb) { struct net_device *vrf_dev = skb->dev; if (!list_empty(&vrf_dev->ptype_all) && likely(skb_headroom(skb) >= ETH_HLEN)) { struct ethhdr *eth = skb_push(skb, ETH_HLEN); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth_zero_addr(eth->h_dest); eth->h_proto = skb->protocol; rcu_read_lock_bh(); dev_queue_xmit_nit(skb, vrf_dev); rcu_read_unlock_bh(); skb_pull(skb, ETH_HLEN); } vrf_nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) /* modelled after ip6_finish_output2 */ static int vrf_finish_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; const struct in6_addr *nexthop; struct neighbour *neigh; int ret; vrf_nf_reset_ct(skb); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; rcu_read_lock(); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } /* modelled after ip6_output */ static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, vrf_finish_output6, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rt6_info *rt6; rcu_read_lock(); rt6 = rcu_dereference(vrf->rt6); if (likely(rt6)) { dst = &rt6->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output6_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip6_local_out(net, sk, skb); } static int vrf_output6_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IPV6); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output6_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip6_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); if (likely(err == 1)) err = vrf_output6_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert link scope packets */ if (rt6_need_strict(&ipv6_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return vrf_ip6_out_direct(vrf_dev, sk, skb); return vrf_ip6_out_redirect(vrf_dev, skb); } /* holding rtnl */ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { struct rt6_info *rt6 = rtnl_dereference(vrf->rt6); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rt6, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rt6) { dst = &rt6->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rt6_create(struct net_device *dev) { int flags = DST_NOPOLICY | DST_NOXFRM; struct net_vrf *vrf = netdev_priv(dev); struct net *net = dev_net(dev); struct rt6_info *rt6; int rc = -ENOMEM; /* IPv6 can be CONFIG enabled and then disabled runtime */ if (!ipv6_mod_enabled()) return 0; vrf->fib6_table = fib6_new_table(net, vrf->tb_id); if (!vrf->fib6_table) goto out; /* create a dst for routing packets out a VRF device */ rt6 = ip6_dst_alloc(net, dev, flags); if (!rt6) goto out; rt6->dst.output = vrf_output6; rcu_assign_pointer(vrf->rt6, rt6); rc = 0; out: return rc; } #else static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { return skb; } static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) { } static int vrf_rt6_create(struct net_device *dev) { return 0; } #endif /* modelled after ip_finish_output2 */ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = dst_rtable(dst); struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; vrf_nf_reset_ct(skb); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) { dev->stats.tx_errors++; return -ENOMEM; } } rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int ret; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock(); return ret; } rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, vrf_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } /* set dst on skb to send packet to us via dev_xmit path. Allows * packet to go through device based features such as qdisc, netfilter * hooks and packet sockets with skb->dev set to vrf device. */ static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_vrf *vrf = netdev_priv(vrf_dev); struct dst_entry *dst = NULL; struct rtable *rth; rcu_read_lock(); rth = rcu_dereference(vrf->rth); if (likely(rth)) { dst = &rth->dst; dst_hold(dst); } rcu_read_unlock(); if (unlikely(!dst)) { vrf_tx_error(vrf_dev, skb); return NULL; } skb_dst_drop(skb); skb_dst_set(skb, dst); return skb; } static int vrf_output_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { vrf_finish_direct(skb); return vrf_ip_local_out(net, sk, skb); } static int vrf_output_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { int err = 1; skb->protocol = htons(ETH_P_IP); if (!(IPCB(skb)->flags & IPSKB_REROUTED)) err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, vrf_output_direct_finish); if (likely(err == 1)) vrf_finish_direct(skb); return err; } static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) err = vrf_ip_local_out(net, sk, skb); return err; } static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(vrf_dev); int err; skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip_out_direct_finish); if (likely(err == 1)) err = vrf_output_direct(net, sk, skb); if (likely(err == 1)) return skb; return NULL; } static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb) { /* don't divert multicast or local broadcast */ if (ipv4_is_multicast(ip_hdr(skb)->daddr) || ipv4_is_lbcast(ip_hdr(skb)->daddr)) return skb; vrf_nf_set_untracked(skb); if (qdisc_tx_is_default(vrf_dev) || IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return vrf_ip_out_direct(vrf_dev, sk, skb); return vrf_ip_out_redirect(vrf_dev, skb); } /* called with rcu lock held */ static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev, struct sock *sk, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_out(vrf_dev, sk, skb); case AF_INET6: return vrf_ip6_out(vrf_dev, sk, skb); } return skb; } /* holding rtnl */ static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf) { struct rtable *rth = rtnl_dereference(vrf->rth); struct net *net = dev_net(dev); struct dst_entry *dst; RCU_INIT_POINTER(vrf->rth, NULL); synchronize_rcu(); /* move dev in dst's to loopback so this VRF device can be deleted * - based on dst_ifdown */ if (rth) { dst = &rth->dst; netdev_ref_replace(dst->dev, net->loopback_dev, &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } } static int vrf_rtable_create(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); struct rtable *rth; if (!fib_new_table(dev_net(dev), vrf->tb_id)) return -ENOMEM; /* create a dst for routing packets out through a VRF device */ rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1); if (!rth) return -ENOMEM; rth->dst.output = vrf_output; rcu_assign_pointer(vrf->rth, rth); return 0; } /**************************** device handling ********************/ /* cycle interface to flush neighbor cache and move routes across tables */ static void cycle_netdev(struct net_device *dev, struct netlink_ext_ack *extack) { unsigned int flags = dev->flags; int ret; if (!netif_running(dev)) return; ret = dev_change_flags(dev, flags & ~IFF_UP, extack); if (ret >= 0) ret = dev_change_flags(dev, flags, extack); if (ret < 0) { netdev_err(dev, "Failed to cycle device %s; route tables might be wrong!\n", dev->name); } } static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { int ret; /* do not allow loopback device to be enslaved to a VRF. * The vrf device acts as the loopback for the vrf. */ if (port_dev == dev_net(dev)->loopback_dev) { NL_SET_ERR_MSG(extack, "Can not enslave loopback device to a VRF"); return -EOPNOTSUPP; } port_dev->priv_flags |= IFF_L3MDEV_SLAVE; ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack); if (ret < 0) goto err; cycle_netdev(port_dev, extack); return 0; err: port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; return ret; } static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { if (netif_is_l3_master(port_dev)) { NL_SET_ERR_MSG(extack, "Can not enslave an L3 master device to a VRF"); return -EINVAL; } if (netif_is_l3_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev, extack); } /* inverse of do_vrf_add_slave */ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { netdev_upper_dev_unlink(port_dev, dev); port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE; cycle_netdev(port_dev, NULL); return 0; } static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { return do_vrf_del_slave(dev, port_dev); } static void vrf_dev_uninit(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); vrf_rtable_release(dev, vrf); vrf_rt6_release(dev, vrf); } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) goto out_nomem; if (vrf_rt6_create(dev) != 0) goto out_rth; dev->flags = IFF_MASTER | IFF_NOARP; /* similarly, oper state is irrelevant; set to up to avoid confusion */ dev->operstate = IF_OPER_UP; netdev_lockdep_set_classes(dev); return 0; out_rth: vrf_rtable_release(dev, vrf); out_nomem: return -ENOMEM; } static const struct net_device_ops vrf_netdev_ops = { .ndo_init = vrf_dev_init, .ndo_uninit = vrf_dev_uninit, .ndo_start_xmit = vrf_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_add_slave = vrf_add_slave, .ndo_del_slave = vrf_del_slave, }; static u32 vrf_fib_table(const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return vrf->tb_id; } static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook, struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1) skb = NULL; /* kfree_skb(skb) handled by nf code */ return skb; } static int vrf_prepare_mac_header(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto) { struct ethhdr *eth; int err; /* in general, we do not know if there is enough space in the head of * the packet for hosting the mac header. */ err = skb_cow_head(skb, LL_RESERVED_SPACE(vrf_dev)); if (unlikely(err)) /* no space in the skb head */ return -ENOBUFS; __skb_push(skb, ETH_HLEN); eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. */ ether_addr_copy(eth->h_dest, vrf_dev->dev_addr); ether_addr_copy(eth->h_source, vrf_dev->dev_addr); eth->h_proto = htons(proto); /* the destination address of the Ethernet frame corresponds to the * address set on the VRF interface; therefore, the packet is intended * to be processed locally. */ skb->protocol = eth->h_proto; skb->pkt_type = PACKET_HOST; skb_postpush_rcsum(skb, skb->data, ETH_HLEN); skb_pull_inline(skb, ETH_HLEN); return 0; } /* prepare and add the mac header to the packet if it was not set previously. * In this way, packet sniffers such as tcpdump can parse the packet correctly. * If the mac header was already set, the original mac header is left * untouched and the function returns immediately. */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, u16 proto, struct net_device *orig_dev) { if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); } #if IS_ENABLED(CONFIG_IPV6) /* neighbor handling is done with actual device; do not want * to flip skb->dev for those ndisc packets. This really fails * for multiple next protocols (e.g., NEXTHDR_HOP). But it is * a start. */ static bool ipv6_ndisc_frame(const struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); bool rc = false; if (iph->nexthdr == NEXTHDR_ICMP) { const struct icmp6hdr *icmph; struct icmp6hdr _icmph; icmph = skb_header_pointer(skb, sizeof(*iph), sizeof(_icmph), &_icmph); if (!icmph) goto out; switch (icmph->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: rc = true; break; } } out: return rc; } static struct rt6_info *vrf_ip6_route_lookup(struct net *net, const struct net_device *dev, struct flowi6 *fl6, int ifindex, const struct sk_buff *skb, int flags) { struct net_vrf *vrf = netdev_priv(dev); return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags); } static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev, int ifindex) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct flowi6 fl6 = { .flowi6_iif = ifindex, .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), }; struct net *net = dev_net(vrf_dev); struct rt6_info *rt6; rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb, RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE); if (unlikely(!rt6)) return; if (unlikely(&rt6->dst == &net->ipv6.ip6_null_entry->dst)) return; skb_dst_set(skb, &rt6->dst); } static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { int orig_iif = skb->skb_iif; bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); /* loopback, multicast & non-ND link-local traffic; do not push through * packet taps again. Reset pkt_type for upper layers to process skb. * For non-loopback strict packets, determine the dst using the original * ifindex. */ if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; if (skb->pkt_type == PACKET_LOOPBACK) skb->pkt_type = PACKET_HOST; else vrf_ip6_input_dst(skb, vrf_dev, orig_iif); goto out; } /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { struct net_device *orig_dev = skb->dev; vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IPV6, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } IP6CB(skb)->flags |= IP6SKB_L3SLAVE; } if (need_strict) vrf_ip6_input_dst(skb, vrf_dev, orig_iif); skb = vrf_rcv_nfhook(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } #else static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { return skb; } #endif static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { struct net_device *orig_dev = skb->dev; skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; if (ipv4_is_multicast(ip_hdr(skb)->daddr)) goto out; /* loopback traffic; do not push through packet taps again. * Reset pkt_type for upper layers to process skb */ if (skb->pkt_type == PACKET_LOOPBACK) { skb->pkt_type = PACKET_HOST; goto out; } vrf_rx_stats(vrf_dev, skb->len); if (!list_empty(&vrf_dev->ptype_all)) { int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); skb_pull(skb, skb->mac_len); } } skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev); out: return skb; } /* called with rcu lock held */ static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev, struct sk_buff *skb, u16 proto) { switch (proto) { case AF_INET: return vrf_ip_rcv(vrf_dev, skb); case AF_INET6: return vrf_ip6_rcv(vrf_dev, skb); } return skb; } #if IS_ENABLED(CONFIG_IPV6) /* send to link-local or multicast address via interface enslaved to * VRF device. Force lookup to VRF table without changing flow struct * Note: Caller to this function must hold rcu_read_lock() and no refcnt * is taken on the dst by this function. */ static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev, struct flowi6 *fl6) { struct net *net = dev_net(dev); int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_DST_NOREF; struct dst_entry *dst = NULL; struct rt6_info *rt; /* VRF device does not have a link-local address and * sending packets to link-local or mcast addresses over * a VRF device does not make sense */ if (fl6->flowi6_oif == dev->ifindex) { dst = &net->ipv6.ip6_null_entry->dst; return dst; } if (!ipv6_addr_any(&fl6->saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags); if (rt) dst = &rt->dst; return dst; } #endif static const struct l3mdev_ops vrf_l3mdev_ops = { .l3mdev_fib_table = vrf_fib_table, .l3mdev_l3_rcv = vrf_l3_rcv, .l3mdev_l3_out = vrf_l3_out, #if IS_ENABLED(CONFIG_IPV6) .l3mdev_link_scope_lookup = vrf_link_scope_lookup, #endif }; static void vrf_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); } static const struct ethtool_ops vrf_ethtool_ops = { .get_drvinfo = vrf_get_drvinfo, }; static inline size_t vrf_fib_rule_nl_size(void) { size_t sz; sz = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)); sz += nla_total_size(sizeof(u8)); /* FRA_L3MDEV */ sz += nla_total_size(sizeof(u32)); /* FRA_PRIORITY */ sz += nla_total_size(sizeof(u8)); /* FRA_PROTOCOL */ return sz; } static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it) { struct fib_rule_hdr *frh; struct nlmsghdr *nlh; struct sk_buff *skb; int err; if ((family == AF_INET6 || family == RTNL_FAMILY_IP6MR) && !ipv6_mod_enabled()) return 0; skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL); if (!skb) return -ENOMEM; nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0); if (!nlh) goto nla_put_failure; /* rule only needs to appear once */ nlh->nlmsg_flags |= NLM_F_EXCL; frh = nlmsg_data(nlh); memset(frh, 0, sizeof(*frh)); frh->family = family; frh->action = FR_ACT_TO_TBL; if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL)) goto nla_put_failure; if (nla_put_u8(skb, FRA_L3MDEV, 1)) goto nla_put_failure; if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF)) goto nla_put_failure; nlmsg_end(skb, nlh); /* fib_nl_{new,del}rule handling looks for net from skb->sk */ skb->sk = dev_net(dev)->rtnl; if (add_it) { err = fib_nl_newrule(skb, nlh, NULL); if (err == -EEXIST) err = 0; } else { err = fib_nl_delrule(skb, nlh, NULL); if (err == -ENOENT) err = 0; } nlmsg_free(skb); return err; nla_put_failure: nlmsg_free(skb); return -EMSGSIZE; } static int vrf_add_fib_rules(const struct net_device *dev) { int err; err = vrf_fib_rule(dev, AF_INET, true); if (err < 0) goto out_err; err = vrf_fib_rule(dev, AF_INET6, true); if (err < 0) goto ipv6_err; #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IPMR, true); if (err < 0) goto ipmr_err; #endif #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) err = vrf_fib_rule(dev, RTNL_FAMILY_IP6MR, true); if (err < 0) goto ip6mr_err; #endif return 0; #if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES) ip6mr_err: vrf_fib_rule(dev, RTNL_FAMILY_IPMR, false); #endif #if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES) ipmr_err: vrf_fib_rule(dev, AF_INET6, false); #endif ipv6_err: vrf_fib_rule(dev, AF_INET, false); out_err: netdev_err(dev, "Failed to add FIB rules.\n"); return err; } static void vrf_setup(struct net_device *dev) { ether_setup(dev); /* Initialize the device structure. */ dev->netdev_ops = &vrf_netdev_ops; dev->l3mdev_ops = &vrf_l3mdev_ops; dev->ethtool_ops = &vrf_ethtool_ops; dev->needs_free_netdev = true; /* Fill in device structure with ethernet-generic values. */ eth_hw_addr_random(dev); /* don't acquire vrf device's netif_tx_lock when transmitting */ dev->lltx = true; /* don't allow vrf devices to change network namespaces. */ dev->netns_local = true; /* does not make sense for a VLAN to be added to a vrf device */ dev->features |= NETIF_F_VLAN_CHALLENGED; /* enable offload features */ dev->features |= NETIF_F_GSO_SOFTWARE; dev->features |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC; dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->hw_features = dev->features; dev->hw_enc_features = dev->features; /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_NO_RX_HANDLER; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* VRF devices do not care about MTU, but if the MTU is set * too low then the ipv4 and ipv6 protocols are disabled * which breaks networking. */ dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU; dev->mtu = dev->max_mtu; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG(extack, "Invalid hardware address"); return -EADDRNOTAVAIL; } } return 0; } static void vrf_dellink(struct net_device *dev, struct list_head *head) { struct net_device *port_dev; struct list_head *iter; netdev_for_each_lower_dev(dev, port_dev, iter) vrf_del_slave(dev, port_dev); vrf_map_unregister_dev(dev); unregister_netdevice_queue(dev, head); } static int vrf_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_vrf *vrf = netdev_priv(dev); struct netns_vrf *nn_vrf; bool *add_fib_rules; struct net *net; int err; if (!data || !data[IFLA_VRF_TABLE]) { NL_SET_ERR_MSG(extack, "VRF table id is missing"); return -EINVAL; } vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); if (vrf->tb_id == RT_TABLE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VRF_TABLE], "Invalid VRF table id"); return -EINVAL; } dev->priv_flags |= IFF_L3MDEV_MASTER; err = register_netdevice(dev); if (err) goto out; /* mapping between table_id and vrf; * note: such binding could not be done in the dev init function * because dev->ifindex id is not available yet. */ vrf->ifindex = dev->ifindex; err = vrf_map_register_dev(dev, extack); if (err) { unregister_netdevice(dev); goto out; } net = dev_net(dev); nn_vrf = net_generic(net, vrf_net_id); add_fib_rules = &nn_vrf->add_fib_rules; if (*add_fib_rules) { err = vrf_add_fib_rules(dev); if (err) { vrf_map_unregister_dev(dev); unregister_netdevice(dev); goto out; } *add_fib_rules = false; } out: return err; } static size_t vrf_nl_getsize(const struct net_device *dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_TABLE */ } static int vrf_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); return nla_put_u32(skb, IFLA_VRF_TABLE, vrf->tb_id); } static size_t vrf_get_slave_size(const struct net_device *bond_dev, const struct net_device *slave_dev) { return nla_total_size(sizeof(u32)); /* IFLA_VRF_PORT_TABLE */ } static int vrf_fill_slave_info(struct sk_buff *skb, const struct net_device *vrf_dev, const struct net_device *slave_dev) { struct net_vrf *vrf = netdev_priv(vrf_dev); if (nla_put_u32(skb, IFLA_VRF_PORT_TABLE, vrf->tb_id)) return -EMSGSIZE; return 0; } static const struct nla_policy vrf_nl_policy[IFLA_VRF_MAX + 1] = { [IFLA_VRF_TABLE] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vrf_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct net_vrf), .get_size = vrf_nl_getsize, .policy = vrf_nl_policy, .validate = vrf_validate, .fill_info = vrf_fillinfo, .get_slave_size = vrf_get_slave_size, .fill_slave_info = vrf_fill_slave_info, .newlink = vrf_newlink, .dellink = vrf_dellink, .setup = vrf_setup, .maxtype = IFLA_VRF_MAX, }; static int vrf_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* only care about unregister events to drop slave references */ if (event == NETDEV_UNREGISTER) { struct net_device *vrf_dev; if (!netif_is_l3_slave(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); vrf_del_slave(vrf_dev, dev); } out: return NOTIFY_DONE; } static struct notifier_block vrf_notifier_block __read_mostly = { .notifier_call = vrf_device_event, }; static int vrf_map_init(struct vrf_map *vmap) { spin_lock_init(&vmap->vmap_lock); hash_init(vmap->ht); vmap->strict_mode = false; return 0; } #ifdef CONFIG_SYSCTL static bool vrf_strict_mode(struct vrf_map *vmap) { bool strict_mode; vrf_map_lock(vmap); strict_mode = vmap->strict_mode; vrf_map_unlock(vmap); return strict_mode; } static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode) { bool *cur_mode; int res = 0; vrf_map_lock(vmap); cur_mode = &vmap->strict_mode; if (*cur_mode == new_mode) goto unlock; if (*cur_mode) { /* disable strict mode */ *cur_mode = false; } else { if (vmap->shared_tables) { /* we cannot allow strict_mode because there are some * vrfs that share one or more tables. */ res = -EBUSY; goto unlock; } /* no tables are shared among vrfs, so we can go back * to 1:1 association between a vrf with its table. */ *cur_mode = true; } unlock: vrf_map_unlock(vmap); return res; } static int vrf_shared_table_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)table->extra1; struct vrf_map *vmap = netns_vrf_map(net); int proc_strict_mode = 0; struct ctl_table tmp = { .procname = table->procname, .data = &proc_strict_mode, .maxlen = sizeof(int), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; int ret; if (!write) proc_strict_mode = vrf_strict_mode(vmap); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && ret == 0) ret = vrf_strict_mode_change(vmap, (bool)proc_strict_mode); return ret; } static const struct ctl_table vrf_table[] = { { .procname = "strict_mode", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = vrf_shared_table_handler, /* set by the vrf_netns_init */ .extra1 = NULL, }, }; static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { struct ctl_table *table; table = kmemdup(vrf_table, sizeof(vrf_table), GFP_KERNEL); if (!table) return -ENOMEM; /* init the extra1 parameter with the reference to current netns */ table[0].extra1 = net; nn_vrf->ctl_hdr = register_net_sysctl_sz(net, "net/vrf", table, ARRAY_SIZE(vrf_table)); if (!nn_vrf->ctl_hdr) { kfree(table); return -ENOMEM; } return 0; } static void vrf_netns_exit_sysctl(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); const struct ctl_table *table; table = nn_vrf->ctl_hdr->ctl_table_arg; unregister_net_sysctl_table(nn_vrf->ctl_hdr); kfree(table); } #else static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf) { return 0; } static void vrf_netns_exit_sysctl(struct net *net) { } #endif /* Initialize per network namespace state */ static int __net_init vrf_netns_init(struct net *net) { struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id); nn_vrf->add_fib_rules = true; vrf_map_init(&nn_vrf->vmap); return vrf_netns_init_sysctl(net, nn_vrf); } static void __net_exit vrf_netns_exit(struct net *net) { vrf_netns_exit_sysctl(net); } static struct pernet_operations vrf_net_ops __net_initdata = { .init = vrf_netns_init, .exit = vrf_netns_exit, .id = &vrf_net_id, .size = sizeof(struct netns_vrf), }; static int __init vrf_init_module(void) { int rc; register_netdevice_notifier(&vrf_notifier_block); rc = register_pernet_subsys(&vrf_net_ops); if (rc < 0) goto error; rc = l3mdev_table_lookup_register(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); if (rc < 0) goto unreg_pernet; rc = rtnl_link_register(&vrf_link_ops); if (rc < 0) goto table_lookup_unreg; return 0; table_lookup_unreg: l3mdev_table_lookup_unregister(L3MDEV_TYPE_VRF, vrf_ifindex_lookup_by_table_id); unreg_pernet: unregister_pernet_subsys(&vrf_net_ops); error: unregister_netdevice_notifier(&vrf_notifier_block); return rc; } module_init(vrf_init_module); MODULE_AUTHOR("Shrijeet Mukherjee, David Ahern"); MODULE_DESCRIPTION("Device driver to instantiate VRF domains"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); MODULE_VERSION(DRV_VERSION); |
| 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 | // SPDX-License-Identifier: GPL-2.0-only /* * Hauppauge HD PVR USB driver * * Copyright (C) 2008 Janne Grunau (j@jannau.net) * * IR device registration code is * Copyright (C) 2010 Andy Walls <awalls@md.metrocast.net> */ #if IS_ENABLED(CONFIG_I2C) #include <linux/i2c.h> #include <linux/slab.h> #include <linux/export.h> #include "hdpvr.h" #define CTRL_READ_REQUEST 0xb8 #define CTRL_WRITE_REQUEST 0x38 #define REQTYPE_I2C_READ 0xb1 #define REQTYPE_I2C_WRITE 0xb0 #define REQTYPE_I2C_WRITE_STATT 0xd0 #define Z8F0811_IR_TX_I2C_ADDR 0x70 #define Z8F0811_IR_RX_I2C_ADDR 0x71 struct i2c_client *hdpvr_register_ir_i2c(struct hdpvr_device *dev) { struct IR_i2c_init_data *init_data = &dev->ir_i2c_init_data; struct i2c_board_info info = { I2C_BOARD_INFO("ir_z8f0811_hdpvr", Z8F0811_IR_RX_I2C_ADDR), }; /* Our default information for ir-kbd-i2c.c to use */ init_data->ir_codes = RC_MAP_HAUPPAUGE; init_data->internal_get_key_func = IR_KBD_GET_KEY_HAUP_XVR; init_data->type = RC_PROTO_BIT_RC5 | RC_PROTO_BIT_RC6_MCE | RC_PROTO_BIT_RC6_6A_32; init_data->name = "HD-PVR"; init_data->polling_interval = 405; /* ms, duplicated from Windows */ info.platform_data = init_data; return i2c_new_client_device(&dev->i2c_adapter, &info); } static int hdpvr_i2c_read(struct hdpvr_device *dev, int bus, unsigned char addr, char *wdata, int wlen, char *data, int len) { int ret; if ((len > sizeof(dev->i2c_buf)) || (wlen > sizeof(dev->i2c_buf))) return -EINVAL; if (wlen) { memcpy(dev->i2c_buf, wdata, wlen); ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), REQTYPE_I2C_WRITE, CTRL_WRITE_REQUEST, (bus << 8) | addr, 0, dev->i2c_buf, wlen, 1000); if (ret < 0) return ret; } ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), REQTYPE_I2C_READ, CTRL_READ_REQUEST, (bus << 8) | addr, 0, dev->i2c_buf, len, 1000); if (ret == len) { memcpy(data, dev->i2c_buf, len); ret = 0; } else if (ret >= 0) ret = -EIO; return ret; } static int hdpvr_i2c_write(struct hdpvr_device *dev, int bus, unsigned char addr, char *data, int len) { int ret; if (len > sizeof(dev->i2c_buf)) return -EINVAL; memcpy(dev->i2c_buf, data, len); ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), REQTYPE_I2C_WRITE, CTRL_WRITE_REQUEST, (bus << 8) | addr, 0, dev->i2c_buf, len, 1000); if (ret < 0) return ret; ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), REQTYPE_I2C_WRITE_STATT, CTRL_READ_REQUEST, 0, 0, dev->i2c_buf, 2, 1000); if ((ret == 2) && (dev->i2c_buf[1] == (len - 1))) ret = 0; else if (ret >= 0) ret = -EIO; return ret; } static int hdpvr_transfer(struct i2c_adapter *i2c_adapter, struct i2c_msg *msgs, int num) { struct hdpvr_device *dev = i2c_get_adapdata(i2c_adapter); int retval = 0, addr; mutex_lock(&dev->i2c_mutex); addr = msgs[0].addr << 1; if (num == 1) { if (msgs[0].flags & I2C_M_RD) retval = hdpvr_i2c_read(dev, 1, addr, NULL, 0, msgs[0].buf, msgs[0].len); else retval = hdpvr_i2c_write(dev, 1, addr, msgs[0].buf, msgs[0].len); } else if (num == 2) { if (msgs[0].addr != msgs[1].addr) { v4l2_warn(&dev->v4l2_dev, "refusing 2-phase i2c xfer with conflicting target addresses\n"); retval = -EINVAL; goto out; } if ((msgs[0].flags & I2C_M_RD) || !(msgs[1].flags & I2C_M_RD)) { v4l2_warn(&dev->v4l2_dev, "refusing complex xfer with r0=%d, r1=%d\n", msgs[0].flags & I2C_M_RD, msgs[1].flags & I2C_M_RD); retval = -EINVAL; goto out; } /* * Write followed by atomic read is the only complex xfer that * we actually support here. */ retval = hdpvr_i2c_read(dev, 1, addr, msgs[0].buf, msgs[0].len, msgs[1].buf, msgs[1].len); } else { v4l2_warn(&dev->v4l2_dev, "refusing %d-phase i2c xfer\n", num); } out: mutex_unlock(&dev->i2c_mutex); return retval ? retval : num; } static u32 hdpvr_functionality(struct i2c_adapter *adapter) { return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } static const struct i2c_algorithm hdpvr_algo = { .master_xfer = hdpvr_transfer, .functionality = hdpvr_functionality, }; static const struct i2c_adapter hdpvr_i2c_adapter_template = { .name = "Hauppauge HD PVR I2C", .owner = THIS_MODULE, .algo = &hdpvr_algo, }; static int hdpvr_activate_ir(struct hdpvr_device *dev) { char buffer[2]; mutex_lock(&dev->i2c_mutex); hdpvr_i2c_read(dev, 0, 0x54, NULL, 0, buffer, 1); buffer[0] = 0; buffer[1] = 0x8; hdpvr_i2c_write(dev, 1, 0x54, buffer, 2); buffer[1] = 0x18; hdpvr_i2c_write(dev, 1, 0x54, buffer, 2); mutex_unlock(&dev->i2c_mutex); return 0; } int hdpvr_register_i2c_adapter(struct hdpvr_device *dev) { hdpvr_activate_ir(dev); dev->i2c_adapter = hdpvr_i2c_adapter_template; dev->i2c_adapter.dev.parent = &dev->udev->dev; i2c_set_adapdata(&dev->i2c_adapter, dev); return i2c_add_adapter(&dev->i2c_adapter); } #endif |
| 9 1 9 9 1 8 8 8 8 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 | /* * Copyright (c) 2005 Topspin Communications. All rights reserved. * Copyright (c) 2005, 2006 Cisco Systems. All rights reserved. * Copyright (c) 2005 Mellanox Technologies. All rights reserved. * Copyright (c) 2005 Voltaire, Inc. All rights reserved. * Copyright (c) 2005 PathScale, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/module.h> #include <linux/init.h> #include <linux/device.h> #include <linux/err.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/file.h> #include <linux/cdev.h> #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> #include <rdma/ib.h> #include <rdma/uverbs_std_types.h> #include <rdma/rdma_netlink.h> #include "uverbs.h" #include "core_priv.h" #include "rdma_core.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand userspace verbs access"); MODULE_LICENSE("Dual BSD/GPL"); enum { IB_UVERBS_MAJOR = 231, IB_UVERBS_BASE_MINOR = 192, IB_UVERBS_MAX_DEVICES = RDMA_MAX_PORTS, IB_UVERBS_NUM_FIXED_MINOR = 32, IB_UVERBS_NUM_DYNAMIC_MINOR = IB_UVERBS_MAX_DEVICES - IB_UVERBS_NUM_FIXED_MINOR, }; #define IB_UVERBS_BASE_DEV MKDEV(IB_UVERBS_MAJOR, IB_UVERBS_BASE_MINOR) static dev_t dynamic_uverbs_dev; static DEFINE_IDA(uverbs_ida); static int ib_uverbs_add_one(struct ib_device *device); static void ib_uverbs_remove_one(struct ib_device *device, void *client_data); static char *uverbs_devnode(const struct device *dev, umode_t *mode) { if (mode) *mode = 0666; return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev)); } static const struct class uverbs_class = { .name = "infiniband_verbs", .devnode = uverbs_devnode, }; /* * Must be called with the ufile->device->disassociate_srcu held, and the lock * must be held until use of the ucontext is finished. */ struct ib_ucontext *ib_uverbs_get_ucontext_file(struct ib_uverbs_file *ufile) { /* * We do not hold the hw_destroy_rwsem lock for this flow, instead * srcu is used. It does not matter if someone races this with * get_context, we get NULL or valid ucontext. */ struct ib_ucontext *ucontext = smp_load_acquire(&ufile->ucontext); if (!srcu_dereference(ufile->device->ib_dev, &ufile->device->disassociate_srcu)) return ERR_PTR(-EIO); if (!ucontext) return ERR_PTR(-EINVAL); return ucontext; } EXPORT_SYMBOL(ib_uverbs_get_ucontext_file); int uverbs_dealloc_mw(struct ib_mw *mw) { struct ib_pd *pd = mw->pd; int ret; ret = mw->device->ops.dealloc_mw(mw); if (ret) return ret; atomic_dec(&pd->usecnt); kfree(mw); return ret; } static void ib_uverbs_release_dev(struct device *device) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); uverbs_destroy_api(dev->uapi); cleanup_srcu_struct(&dev->disassociate_srcu); mutex_destroy(&dev->lists_mutex); mutex_destroy(&dev->xrcd_tree_mutex); kfree(dev); } void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file, struct ib_ucq_object *uobj) { struct ib_uverbs_event *evt, *tmp; if (ev_file) { spin_lock_irq(&ev_file->ev_queue.lock); list_for_each_entry_safe(evt, tmp, &uobj->comp_list, obj_list) { list_del(&evt->list); kfree(evt); } spin_unlock_irq(&ev_file->ev_queue.lock); uverbs_uobject_put(&ev_file->uobj); } ib_uverbs_release_uevent(&uobj->uevent); } void ib_uverbs_release_uevent(struct ib_uevent_object *uobj) { struct ib_uverbs_async_event_file *async_file = uobj->event_file; struct ib_uverbs_event *evt, *tmp; if (!async_file) return; spin_lock_irq(&async_file->ev_queue.lock); list_for_each_entry_safe(evt, tmp, &uobj->event_list, obj_list) { list_del(&evt->list); kfree(evt); } spin_unlock_irq(&async_file->ev_queue.lock); uverbs_uobject_put(&async_file->uobj); } void ib_uverbs_detach_umcast(struct ib_qp *qp, struct ib_uqp_object *uobj) { struct ib_uverbs_mcast_entry *mcast, *tmp; list_for_each_entry_safe(mcast, tmp, &uobj->mcast_list, list) { ib_detach_mcast(qp, &mcast->gid, mcast->lid); list_del(&mcast->list); kfree(mcast); } } static void ib_uverbs_comp_dev(struct ib_uverbs_device *dev) { complete(&dev->comp); } void ib_uverbs_release_file(struct kref *ref) { struct ib_uverbs_file *file = container_of(ref, struct ib_uverbs_file, ref); struct ib_device *ib_dev; int srcu_key; release_ufile_idr_uobject(file); srcu_key = srcu_read_lock(&file->device->disassociate_srcu); ib_dev = srcu_dereference(file->device->ib_dev, &file->device->disassociate_srcu); if (ib_dev && !ib_dev->ops.disassociate_ucontext) module_put(ib_dev->ops.owner); srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); if (refcount_dec_and_test(&file->device->refcount)) ib_uverbs_comp_dev(file->device); if (file->default_async_file) uverbs_uobject_put(&file->default_async_file->uobj); put_device(&file->device->dev); if (file->disassociate_page) __free_pages(file->disassociate_page, 0); mutex_destroy(&file->umap_lock); mutex_destroy(&file->ucontext_lock); kfree(file); } static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue, struct file *filp, char __user *buf, size_t count, loff_t *pos, size_t eventsz) { struct ib_uverbs_event *event; int ret = 0; spin_lock_irq(&ev_queue->lock); while (list_empty(&ev_queue->event_list)) { if (ev_queue->is_closed) { spin_unlock_irq(&ev_queue->lock); return -EIO; } spin_unlock_irq(&ev_queue->lock); if (filp->f_flags & O_NONBLOCK) return -EAGAIN; if (wait_event_interruptible(ev_queue->poll_wait, (!list_empty(&ev_queue->event_list) || ev_queue->is_closed))) return -ERESTARTSYS; spin_lock_irq(&ev_queue->lock); } event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list); if (eventsz > count) { ret = -EINVAL; event = NULL; } else { list_del(ev_queue->event_list.next); if (event->counter) { ++(*event->counter); list_del(&event->obj_list); } } spin_unlock_irq(&ev_queue->lock); if (event) { if (copy_to_user(buf, event, eventsz)) ret = -EFAULT; else ret = eventsz; } kfree(event); return ret; } static ssize_t ib_uverbs_async_event_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_async_event_file *file = filp->private_data; return ib_uverbs_event_read(&file->ev_queue, filp, buf, count, pos, sizeof(struct ib_uverbs_async_event_desc)); } static ssize_t ib_uverbs_comp_event_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return ib_uverbs_event_read(&comp_ev_file->ev_queue, filp, buf, count, pos, sizeof(struct ib_uverbs_comp_event_desc)); } static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue, struct file *filp, struct poll_table_struct *wait) { __poll_t pollflags = 0; poll_wait(filp, &ev_queue->poll_wait, wait); spin_lock_irq(&ev_queue->lock); if (!list_empty(&ev_queue->event_list)) pollflags = EPOLLIN | EPOLLRDNORM; else if (ev_queue->is_closed) pollflags = EPOLLERR; spin_unlock_irq(&ev_queue->lock); return pollflags; } static __poll_t ib_uverbs_async_event_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_uverbs_async_event_file *file = filp->private_data; return ib_uverbs_event_poll(&file->ev_queue, filp, wait); } static __poll_t ib_uverbs_comp_event_poll(struct file *filp, struct poll_table_struct *wait) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return ib_uverbs_event_poll(&comp_ev_file->ev_queue, filp, wait); } static int ib_uverbs_async_event_fasync(int fd, struct file *filp, int on) { struct ib_uverbs_async_event_file *file = filp->private_data; return fasync_helper(fd, filp, on, &file->ev_queue.async_queue); } static int ib_uverbs_comp_event_fasync(int fd, struct file *filp, int on) { struct ib_uverbs_completion_event_file *comp_ev_file = filp->private_data; return fasync_helper(fd, filp, on, &comp_ev_file->ev_queue.async_queue); } const struct file_operations uverbs_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_comp_event_read, .poll = ib_uverbs_comp_event_poll, .release = uverbs_uobject_fd_release, .fasync = ib_uverbs_comp_event_fasync, }; const struct file_operations uverbs_async_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_async_event_read, .poll = ib_uverbs_async_event_poll, .release = uverbs_async_event_release, .fasync = ib_uverbs_async_event_fasync, }; void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context) { struct ib_uverbs_event_queue *ev_queue = cq_context; struct ib_ucq_object *uobj; struct ib_uverbs_event *entry; unsigned long flags; if (!ev_queue) return; spin_lock_irqsave(&ev_queue->lock, flags); if (ev_queue->is_closed) { spin_unlock_irqrestore(&ev_queue->lock, flags); return; } entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) { spin_unlock_irqrestore(&ev_queue->lock, flags); return; } uobj = cq->uobject; entry->desc.comp.cq_handle = cq->uobject->uevent.uobject.user_handle; entry->counter = &uobj->comp_events_reported; list_add_tail(&entry->list, &ev_queue->event_list); list_add_tail(&entry->obj_list, &uobj->comp_list); spin_unlock_irqrestore(&ev_queue->lock, flags); wake_up_interruptible(&ev_queue->poll_wait); kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN); } void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, __u64 element, __u64 event, struct list_head *obj_list, u32 *counter) { struct ib_uverbs_event *entry; unsigned long flags; if (!async_file) return; spin_lock_irqsave(&async_file->ev_queue.lock, flags); if (async_file->ev_queue.is_closed) { spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); return; } entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) { spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); return; } entry->desc.async.element = element; entry->desc.async.event_type = event; entry->desc.async.reserved = 0; entry->counter = counter; list_add_tail(&entry->list, &async_file->ev_queue.event_list); if (obj_list) list_add_tail(&entry->obj_list, obj_list); spin_unlock_irqrestore(&async_file->ev_queue.lock, flags); wake_up_interruptible(&async_file->ev_queue.poll_wait); kill_fasync(&async_file->ev_queue.async_queue, SIGIO, POLL_IN); } static void uverbs_uobj_event(struct ib_uevent_object *eobj, struct ib_event *event) { ib_uverbs_async_handler(eobj->event_file, eobj->uobject.user_handle, event->event, &eobj->event_list, &eobj->events_reported); } void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.cq->uobject->uevent, event); } void ib_uverbs_qp_event_handler(struct ib_event *event, void *context_ptr) { /* for XRC target qp's, check that qp is live */ if (!event->element.qp->uobject) return; uverbs_uobj_event(&event->element.qp->uobject->uevent, event); } void ib_uverbs_wq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.wq->uobject->uevent, event); } void ib_uverbs_srq_event_handler(struct ib_event *event, void *context_ptr) { uverbs_uobj_event(&event->element.srq->uobject->uevent, event); } static void ib_uverbs_event_handler(struct ib_event_handler *handler, struct ib_event *event) { ib_uverbs_async_handler( container_of(handler, struct ib_uverbs_async_event_file, event_handler), event->element.port_num, event->event, NULL, NULL); } void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue) { spin_lock_init(&ev_queue->lock); INIT_LIST_HEAD(&ev_queue->event_list); init_waitqueue_head(&ev_queue->poll_wait); ev_queue->is_closed = 0; ev_queue->async_queue = NULL; } void ib_uverbs_init_async_event_file( struct ib_uverbs_async_event_file *async_file) { struct ib_uverbs_file *uverbs_file = async_file->uobj.ufile; struct ib_device *ib_dev = async_file->uobj.context->device; ib_uverbs_init_event_queue(&async_file->ev_queue); /* The first async_event_file becomes the default one for the file. */ mutex_lock(&uverbs_file->ucontext_lock); if (!uverbs_file->default_async_file) { /* Pairs with the put in ib_uverbs_release_file */ uverbs_uobject_get(&async_file->uobj); smp_store_release(&uverbs_file->default_async_file, async_file); } mutex_unlock(&uverbs_file->ucontext_lock); INIT_IB_EVENT_HANDLER(&async_file->event_handler, ib_dev, ib_uverbs_event_handler); ib_register_event_handler(&async_file->event_handler); } static ssize_t verify_hdr(struct ib_uverbs_cmd_hdr *hdr, struct ib_uverbs_ex_cmd_hdr *ex_hdr, size_t count, const struct uverbs_api_write_method *method_elm) { if (method_elm->is_ex) { count -= sizeof(*hdr) + sizeof(*ex_hdr); if ((hdr->in_words + ex_hdr->provider_in_words) * 8 != count) return -EINVAL; if (hdr->in_words * 8 < method_elm->req_size) return -ENOSPC; if (ex_hdr->cmd_hdr_reserved) return -EINVAL; if (ex_hdr->response) { if (!hdr->out_words && !ex_hdr->provider_out_words) return -EINVAL; if (hdr->out_words * 8 < method_elm->resp_size) return -ENOSPC; if (!access_ok(u64_to_user_ptr(ex_hdr->response), (hdr->out_words + ex_hdr->provider_out_words) * 8)) return -EFAULT; } else { if (hdr->out_words || ex_hdr->provider_out_words) return -EINVAL; } return 0; } /* not extended command */ if (hdr->in_words * 4 != count) return -EINVAL; if (count < method_elm->req_size + sizeof(*hdr)) { /* * rdma-core v18 and v19 have a bug where they send DESTROY_CQ * with a 16 byte write instead of 24. Old kernels didn't * check the size so they allowed this. Now that the size is * checked provide a compatibility work around to not break * those userspaces. */ if (hdr->command == IB_USER_VERBS_CMD_DESTROY_CQ && count == 16) { hdr->in_words = 6; return 0; } return -ENOSPC; } if (hdr->out_words * 4 < method_elm->resp_size) return -ENOSPC; return 0; } static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_file *file = filp->private_data; const struct uverbs_api_write_method *method_elm; struct uverbs_api *uapi = file->device->uapi; struct ib_uverbs_ex_cmd_hdr ex_hdr; struct ib_uverbs_cmd_hdr hdr; struct uverbs_attr_bundle bundle; int srcu_key; ssize_t ret; if (!ib_safe_file_access(filp)) { pr_err_once("uverbs_write: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n", task_tgid_vnr(current), current->comm); return -EACCES; } if (count < sizeof(hdr)) return -EINVAL; if (copy_from_user(&hdr, buf, sizeof(hdr))) return -EFAULT; method_elm = uapi_get_method(uapi, hdr.command); if (IS_ERR(method_elm)) return PTR_ERR(method_elm); if (method_elm->is_ex) { if (count < (sizeof(hdr) + sizeof(ex_hdr))) return -EINVAL; if (copy_from_user(&ex_hdr, buf + sizeof(hdr), sizeof(ex_hdr))) return -EFAULT; } ret = verify_hdr(&hdr, &ex_hdr, count, method_elm); if (ret) return ret; srcu_key = srcu_read_lock(&file->device->disassociate_srcu); buf += sizeof(hdr); memset(bundle.attr_present, 0, sizeof(bundle.attr_present)); bundle.ufile = file; bundle.context = NULL; /* only valid if bundle has uobject */ bundle.uobject = NULL; if (!method_elm->is_ex) { size_t in_len = hdr.in_words * 4 - sizeof(hdr); size_t out_len = hdr.out_words * 4; u64 response = 0; if (method_elm->has_udata) { bundle.driver_udata.inlen = in_len - method_elm->req_size; in_len = method_elm->req_size; if (bundle.driver_udata.inlen) bundle.driver_udata.inbuf = buf + in_len; else bundle.driver_udata.inbuf = NULL; } else { memset(&bundle.driver_udata, 0, sizeof(bundle.driver_udata)); } if (method_elm->has_resp) { /* * The macros check that if has_resp is set * then the command request structure starts * with a '__aligned u64 response' member. */ ret = get_user(response, (const u64 __user *)buf); if (ret) goto out_unlock; if (method_elm->has_udata) { bundle.driver_udata.outlen = out_len - method_elm->resp_size; out_len = method_elm->resp_size; if (bundle.driver_udata.outlen) bundle.driver_udata.outbuf = u64_to_user_ptr(response + out_len); else bundle.driver_udata.outbuf = NULL; } } else { bundle.driver_udata.outlen = 0; bundle.driver_udata.outbuf = NULL; } ib_uverbs_init_udata_buf_or_null( &bundle.ucore, buf, u64_to_user_ptr(response), in_len, out_len); } else { buf += sizeof(ex_hdr); ib_uverbs_init_udata_buf_or_null(&bundle.ucore, buf, u64_to_user_ptr(ex_hdr.response), hdr.in_words * 8, hdr.out_words * 8); ib_uverbs_init_udata_buf_or_null( &bundle.driver_udata, buf + bundle.ucore.inlen, u64_to_user_ptr(ex_hdr.response) + bundle.ucore.outlen, ex_hdr.provider_in_words * 8, ex_hdr.provider_out_words * 8); } ret = method_elm->handler(&bundle); if (bundle.uobject) uverbs_finalize_object(bundle.uobject, UVERBS_ACCESS_NEW, true, !ret, &bundle); out_unlock: srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); return (ret) ? : count; } static const struct vm_operations_struct rdma_umap_ops; static int ib_uverbs_mmap(struct file *filp, struct vm_area_struct *vma) { struct ib_uverbs_file *file = filp->private_data; struct ib_ucontext *ucontext; int ret = 0; int srcu_key; srcu_key = srcu_read_lock(&file->device->disassociate_srcu); ucontext = ib_uverbs_get_ucontext_file(file); if (IS_ERR(ucontext)) { ret = PTR_ERR(ucontext); goto out; } vma->vm_ops = &rdma_umap_ops; ret = ucontext->device->ops.mmap(ucontext, vma); out: srcu_read_unlock(&file->device->disassociate_srcu, srcu_key); return ret; } /* * The VMA has been dup'd, initialize the vm_private_data with a new tracking * struct */ static void rdma_umap_open(struct vm_area_struct *vma) { struct ib_uverbs_file *ufile = vma->vm_file->private_data; struct rdma_umap_priv *opriv = vma->vm_private_data; struct rdma_umap_priv *priv; if (!opriv) return; /* We are racing with disassociation */ if (!down_read_trylock(&ufile->hw_destroy_rwsem)) goto out_zap; /* * Disassociation already completed, the VMA should already be zapped. */ if (!ufile->ucontext) goto out_unlock; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) goto out_unlock; rdma_umap_priv_init(priv, vma, opriv->entry); up_read(&ufile->hw_destroy_rwsem); return; out_unlock: up_read(&ufile->hw_destroy_rwsem); out_zap: /* * We can't allow the VMA to be created with the actual IO pages, that * would break our API contract, and it can't be stopped at this * point, so zap it. */ vma->vm_private_data = NULL; zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); } static void rdma_umap_close(struct vm_area_struct *vma) { struct ib_uverbs_file *ufile = vma->vm_file->private_data; struct rdma_umap_priv *priv = vma->vm_private_data; if (!priv) return; /* * The vma holds a reference on the struct file that created it, which * in turn means that the ib_uverbs_file is guaranteed to exist at * this point. */ mutex_lock(&ufile->umap_lock); if (priv->entry) rdma_user_mmap_entry_put(priv->entry); list_del(&priv->list); mutex_unlock(&ufile->umap_lock); kfree(priv); } /* * Once the zap_vma_ptes has been called touches to the VMA will come here and * we return a dummy writable zero page for all the pfns. */ static vm_fault_t rdma_umap_fault(struct vm_fault *vmf) { struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data; struct rdma_umap_priv *priv = vmf->vma->vm_private_data; vm_fault_t ret = 0; if (!priv) return VM_FAULT_SIGBUS; /* Read only pages can just use the system zero page. */ if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) { vmf->page = ZERO_PAGE(vmf->address); get_page(vmf->page); return 0; } mutex_lock(&ufile->umap_lock); if (!ufile->disassociate_page) ufile->disassociate_page = alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0); if (ufile->disassociate_page) { /* * This VMA is forced to always be shared so this doesn't have * to worry about COW. */ vmf->page = ufile->disassociate_page; get_page(vmf->page); } else { ret = VM_FAULT_SIGBUS; } mutex_unlock(&ufile->umap_lock); return ret; } static const struct vm_operations_struct rdma_umap_ops = { .open = rdma_umap_open, .close = rdma_umap_close, .fault = rdma_umap_fault, }; void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) { struct rdma_umap_priv *priv, *next_priv; lockdep_assert_held(&ufile->hw_destroy_rwsem); while (1) { struct mm_struct *mm = NULL; /* Get an arbitrary mm pointer that hasn't been cleaned yet */ mutex_lock(&ufile->umap_lock); while (!list_empty(&ufile->umaps)) { int ret; priv = list_first_entry(&ufile->umaps, struct rdma_umap_priv, list); mm = priv->vma->vm_mm; ret = mmget_not_zero(mm); if (!ret) { list_del_init(&priv->list); if (priv->entry) { rdma_user_mmap_entry_put(priv->entry); priv->entry = NULL; } mm = NULL; continue; } break; } mutex_unlock(&ufile->umap_lock); if (!mm) return; /* * The umap_lock is nested under mmap_lock since it used within * the vma_ops callbacks, so we have to clean the list one mm * at a time to get the lock ordering right. Typically there * will only be one mm, so no big deal. */ mmap_read_lock(mm); mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { struct vm_area_struct *vma = priv->vma; if (vma->vm_mm != mm) continue; list_del_init(&priv->list); zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); if (priv->entry) { rdma_user_mmap_entry_put(priv->entry); priv->entry = NULL; } } mutex_unlock(&ufile->umap_lock); mmap_read_unlock(mm); mmput(mm); } } /* * ib_uverbs_open() does not need the BKL: * * - the ib_uverbs_device structures are properly reference counted and * everything else is purely local to the file being created, so * races against other open calls are not a problem; * - there is no ioctl method to race against; * - the open method will either immediately run -ENXIO, or all * required initialization will be done. */ static int ib_uverbs_open(struct inode *inode, struct file *filp) { struct ib_uverbs_device *dev; struct ib_uverbs_file *file; struct ib_device *ib_dev; int ret; int module_dependent; int srcu_key; dev = container_of(inode->i_cdev, struct ib_uverbs_device, cdev); if (!refcount_inc_not_zero(&dev->refcount)) return -ENXIO; get_device(&dev->dev); srcu_key = srcu_read_lock(&dev->disassociate_srcu); mutex_lock(&dev->lists_mutex); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (!ib_dev) { ret = -EIO; goto err; } if (!rdma_dev_access_netns(ib_dev, current->nsproxy->net_ns)) { ret = -EPERM; goto err; } /* In case IB device supports disassociate ucontext, there is no hard * dependency between uverbs device and its low level device. */ module_dependent = !(ib_dev->ops.disassociate_ucontext); if (module_dependent) { if (!try_module_get(ib_dev->ops.owner)) { ret = -ENODEV; goto err; } } file = kzalloc(sizeof(*file), GFP_KERNEL); if (!file) { ret = -ENOMEM; if (module_dependent) goto err_module; goto err; } file->device = dev; kref_init(&file->ref); mutex_init(&file->ucontext_lock); spin_lock_init(&file->uobjects_lock); INIT_LIST_HEAD(&file->uobjects); init_rwsem(&file->hw_destroy_rwsem); mutex_init(&file->umap_lock); INIT_LIST_HEAD(&file->umaps); filp->private_data = file; list_add_tail(&file->list, &dev->uverbs_file_list); mutex_unlock(&dev->lists_mutex); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); setup_ufile_idr_uobject(file); return stream_open(inode, filp); err_module: module_put(ib_dev->ops.owner); err: mutex_unlock(&dev->lists_mutex); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); if (refcount_dec_and_test(&dev->refcount)) ib_uverbs_comp_dev(dev); put_device(&dev->dev); return ret; } static int ib_uverbs_close(struct inode *inode, struct file *filp) { struct ib_uverbs_file *file = filp->private_data; uverbs_destroy_ufile_hw(file, RDMA_REMOVE_CLOSE); mutex_lock(&file->device->lists_mutex); list_del_init(&file->list); mutex_unlock(&file->device->lists_mutex); kref_put(&file->ref, ib_uverbs_release_file); return 0; } static const struct file_operations uverbs_fops = { .owner = THIS_MODULE, .write = ib_uverbs_write, .open = ib_uverbs_open, .release = ib_uverbs_close, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static const struct file_operations uverbs_mmap_fops = { .owner = THIS_MODULE, .write = ib_uverbs_write, .mmap = ib_uverbs_mmap, .open = ib_uverbs_open, .release = ib_uverbs_close, .unlocked_ioctl = ib_uverbs_ioctl, .compat_ioctl = compat_ptr_ioctl, }; static int ib_uverbs_get_nl_info(struct ib_device *ibdev, void *client_data, struct ib_client_nl_info *res) { struct ib_uverbs_device *uverbs_dev = client_data; int ret; if (res->port != -1) return -EINVAL; res->abi = ibdev->ops.uverbs_abi_ver; res->cdev = &uverbs_dev->dev; /* * To support DRIVER_ID binding in userspace some of the driver need * upgrading to expose their PCI dependent revision information * through get_context instead of relying on modalias matching. When * the drivers are fixed they can drop this flag. */ if (!ibdev->ops.uverbs_no_driver_id_binding) { ret = nla_put_u32(res->nl_msg, RDMA_NLDEV_ATTR_UVERBS_DRIVER_ID, ibdev->ops.driver_id); if (ret) return ret; } return 0; } static struct ib_client uverbs_client = { .name = "uverbs", .no_kverbs_req = true, .add = ib_uverbs_add_one, .remove = ib_uverbs_remove_one, .get_nl_info = ib_uverbs_get_nl_info, }; MODULE_ALIAS_RDMA_CLIENT("uverbs"); static ssize_t ibdev_show(struct device *device, struct device_attribute *attr, char *buf) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); int ret = -ENODEV; int srcu_key; struct ib_device *ib_dev; srcu_key = srcu_read_lock(&dev->disassociate_srcu); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (ib_dev) ret = sysfs_emit(buf, "%s\n", dev_name(&ib_dev->dev)); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); return ret; } static DEVICE_ATTR_RO(ibdev); static ssize_t abi_version_show(struct device *device, struct device_attribute *attr, char *buf) { struct ib_uverbs_device *dev = container_of(device, struct ib_uverbs_device, dev); int ret = -ENODEV; int srcu_key; struct ib_device *ib_dev; srcu_key = srcu_read_lock(&dev->disassociate_srcu); ib_dev = srcu_dereference(dev->ib_dev, &dev->disassociate_srcu); if (ib_dev) ret = sysfs_emit(buf, "%u\n", ib_dev->ops.uverbs_abi_ver); srcu_read_unlock(&dev->disassociate_srcu, srcu_key); return ret; } static DEVICE_ATTR_RO(abi_version); static struct attribute *ib_dev_attrs[] = { &dev_attr_abi_version.attr, &dev_attr_ibdev.attr, NULL, }; static const struct attribute_group dev_attr_group = { .attrs = ib_dev_attrs, }; static CLASS_ATTR_STRING(abi_version, S_IRUGO, __stringify(IB_USER_VERBS_ABI_VERSION)); static int ib_uverbs_create_uapi(struct ib_device *device, struct ib_uverbs_device *uverbs_dev) { struct uverbs_api *uapi; uapi = uverbs_alloc_api(device); if (IS_ERR(uapi)) return PTR_ERR(uapi); uverbs_dev->uapi = uapi; return 0; } static int ib_uverbs_add_one(struct ib_device *device) { int devnum; dev_t base; struct ib_uverbs_device *uverbs_dev; int ret; if (!device->ops.alloc_ucontext || device->type == RDMA_DEVICE_TYPE_SMI) return -EOPNOTSUPP; uverbs_dev = kzalloc(sizeof(*uverbs_dev), GFP_KERNEL); if (!uverbs_dev) return -ENOMEM; ret = init_srcu_struct(&uverbs_dev->disassociate_srcu); if (ret) { kfree(uverbs_dev); return -ENOMEM; } device_initialize(&uverbs_dev->dev); uverbs_dev->dev.class = &uverbs_class; uverbs_dev->dev.parent = device->dev.parent; uverbs_dev->dev.release = ib_uverbs_release_dev; uverbs_dev->groups[0] = &dev_attr_group; uverbs_dev->dev.groups = uverbs_dev->groups; refcount_set(&uverbs_dev->refcount, 1); init_completion(&uverbs_dev->comp); uverbs_dev->xrcd_tree = RB_ROOT; mutex_init(&uverbs_dev->xrcd_tree_mutex); mutex_init(&uverbs_dev->lists_mutex); INIT_LIST_HEAD(&uverbs_dev->uverbs_file_list); rcu_assign_pointer(uverbs_dev->ib_dev, device); uverbs_dev->num_comp_vectors = device->num_comp_vectors; devnum = ida_alloc_max(&uverbs_ida, IB_UVERBS_MAX_DEVICES - 1, GFP_KERNEL); if (devnum < 0) { ret = -ENOMEM; goto err; } uverbs_dev->devnum = devnum; if (devnum >= IB_UVERBS_NUM_FIXED_MINOR) base = dynamic_uverbs_dev + devnum - IB_UVERBS_NUM_FIXED_MINOR; else base = IB_UVERBS_BASE_DEV + devnum; ret = ib_uverbs_create_uapi(device, uverbs_dev); if (ret) goto err_uapi; uverbs_dev->dev.devt = base; dev_set_name(&uverbs_dev->dev, "uverbs%d", uverbs_dev->devnum); cdev_init(&uverbs_dev->cdev, device->ops.mmap ? &uverbs_mmap_fops : &uverbs_fops); uverbs_dev->cdev.owner = THIS_MODULE; ret = cdev_device_add(&uverbs_dev->cdev, &uverbs_dev->dev); if (ret) goto err_uapi; ib_set_client_data(device, &uverbs_client, uverbs_dev); return 0; err_uapi: ida_free(&uverbs_ida, devnum); err: if (refcount_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); wait_for_completion(&uverbs_dev->comp); put_device(&uverbs_dev->dev); return ret; } static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev, struct ib_device *ib_dev) { struct ib_uverbs_file *file; /* Pending running commands to terminate */ uverbs_disassociate_api_pre(uverbs_dev); mutex_lock(&uverbs_dev->lists_mutex); while (!list_empty(&uverbs_dev->uverbs_file_list)) { file = list_first_entry(&uverbs_dev->uverbs_file_list, struct ib_uverbs_file, list); list_del_init(&file->list); kref_get(&file->ref); /* We must release the mutex before going ahead and calling * uverbs_cleanup_ufile, as it might end up indirectly calling * uverbs_close, for example due to freeing the resources (e.g * mmput). */ mutex_unlock(&uverbs_dev->lists_mutex); uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE); kref_put(&file->ref, ib_uverbs_release_file); mutex_lock(&uverbs_dev->lists_mutex); } mutex_unlock(&uverbs_dev->lists_mutex); uverbs_disassociate_api(uverbs_dev->uapi); } static void ib_uverbs_remove_one(struct ib_device *device, void *client_data) { struct ib_uverbs_device *uverbs_dev = client_data; int wait_clients = 1; cdev_device_del(&uverbs_dev->cdev, &uverbs_dev->dev); ida_free(&uverbs_ida, uverbs_dev->devnum); if (device->ops.disassociate_ucontext) { /* We disassociate HW resources and immediately return. * Userspace will see a EIO errno for all future access. * Upon returning, ib_device may be freed internally and is not * valid any more. * uverbs_device is still available until all clients close * their files, then the uverbs device ref count will be zero * and its resources will be freed. * Note: At this point no more files can be opened since the * cdev was deleted, however active clients can still issue * commands and close their open files. */ ib_uverbs_free_hw_resources(uverbs_dev, device); wait_clients = 0; } if (refcount_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); if (wait_clients) wait_for_completion(&uverbs_dev->comp); put_device(&uverbs_dev->dev); } static int __init ib_uverbs_init(void) { int ret; ret = register_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR, "infiniband_verbs"); if (ret) { pr_err("user_verbs: couldn't register device number\n"); goto out; } ret = alloc_chrdev_region(&dynamic_uverbs_dev, 0, IB_UVERBS_NUM_DYNAMIC_MINOR, "infiniband_verbs"); if (ret) { pr_err("couldn't register dynamic device number\n"); goto out_alloc; } ret = class_register(&uverbs_class); if (ret) { pr_err("user_verbs: couldn't create class infiniband_verbs\n"); goto out_chrdev; } ret = class_create_file(&uverbs_class, &class_attr_abi_version.attr); if (ret) { pr_err("user_verbs: couldn't create abi_version attribute\n"); goto out_class; } ret = ib_register_client(&uverbs_client); if (ret) { pr_err("user_verbs: couldn't register client\n"); goto out_class; } return 0; out_class: class_unregister(&uverbs_class); out_chrdev: unregister_chrdev_region(dynamic_uverbs_dev, IB_UVERBS_NUM_DYNAMIC_MINOR); out_alloc: unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR); out: return ret; } static void __exit ib_uverbs_cleanup(void) { ib_unregister_client(&uverbs_client); class_unregister(&uverbs_class); unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_NUM_FIXED_MINOR); unregister_chrdev_region(dynamic_uverbs_dev, IB_UVERBS_NUM_DYNAMIC_MINOR); mmu_notifier_synchronize(); } module_init(ib_uverbs_init); module_exit(ib_uverbs_cleanup); |
| 11 12 9 1 12 14 15 1 7 12 12 12 12 12 12 2 2 2 2 1 1 1 13 13 3 3 1 2 3 13 13 1 7 7 27 22 5 2 1 13 1 3 7 25 4 6 4 3 2 2 2 10 3 3 3 3 7 7 5 7 1 6 5 3 2 5 2 2 2 2 2 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Sunplus spca504(abc) spca533 spca536 library * Copyright (C) 2005 Michel Xhaard mxhaard@magic.fr * * V4L2 by Jean-Francois Moine <http://moinejf.free.fr> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define MODULE_NAME "sunplus" #include "gspca.h" #include "jpeg.h" MODULE_AUTHOR("Michel Xhaard <mxhaard@users.sourceforge.net>"); MODULE_DESCRIPTION("GSPCA/SPCA5xx USB Camera Driver"); MODULE_LICENSE("GPL"); #define QUALITY 85 /* specific webcam descriptor */ struct sd { struct gspca_dev gspca_dev; /* !! must be the first item */ bool autogain; u8 bridge; #define BRIDGE_SPCA504 0 #define BRIDGE_SPCA504B 1 #define BRIDGE_SPCA504C 2 #define BRIDGE_SPCA533 3 #define BRIDGE_SPCA536 4 u8 subtype; #define AiptekMiniPenCam13 1 #define LogitechClickSmart420 2 #define LogitechClickSmart820 3 #define MegapixV4 4 #define MegaImageVI 5 u8 jpeg_hdr[JPEG_HDR_SZ]; }; static const struct v4l2_pix_format vga_mode[] = { {320, 240, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 320, .sizeimage = 320 * 240 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 2}, {640, 480, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 640, .sizeimage = 640 * 480 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 1}, }; static const struct v4l2_pix_format custom_mode[] = { {320, 240, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 320, .sizeimage = 320 * 240 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 2}, {464, 480, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 464, .sizeimage = 464 * 480 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 1}, }; static const struct v4l2_pix_format vga_mode2[] = { {176, 144, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 176, .sizeimage = 176 * 144 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 4}, {320, 240, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 320, .sizeimage = 320 * 240 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 3}, {352, 288, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 352, .sizeimage = 352 * 288 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 2}, {640, 480, V4L2_PIX_FMT_JPEG, V4L2_FIELD_NONE, .bytesperline = 640, .sizeimage = 640 * 480 * 3 / 8 + 590, .colorspace = V4L2_COLORSPACE_JPEG, .priv = 1}, }; #define SPCA50X_OFFSET_DATA 10 #define SPCA504_PCCAM600_OFFSET_SNAPSHOT 3 #define SPCA504_PCCAM600_OFFSET_COMPRESS 4 #define SPCA504_PCCAM600_OFFSET_MODE 5 #define SPCA504_PCCAM600_OFFSET_DATA 14 /* Frame packet header offsets for the spca533 */ #define SPCA533_OFFSET_DATA 16 #define SPCA533_OFFSET_FRAMSEQ 15 /* Frame packet header offsets for the spca536 */ #define SPCA536_OFFSET_DATA 4 #define SPCA536_OFFSET_FRAMSEQ 1 struct cmd { u8 req; u16 val; u16 idx; }; /* Initialisation data for the Creative PC-CAM 600 */ static const struct cmd spca504_pccam600_init_data[] = { /* {0xa0, 0x0000, 0x0503}, * capture mode */ {0x00, 0x0000, 0x2000}, {0x00, 0x0013, 0x2301}, {0x00, 0x0003, 0x2000}, {0x00, 0x0001, 0x21ac}, {0x00, 0x0001, 0x21a6}, {0x00, 0x0000, 0x21a7}, /* brightness */ {0x00, 0x0020, 0x21a8}, /* contrast */ {0x00, 0x0001, 0x21ac}, /* sat/hue */ {0x00, 0x0000, 0x21ad}, /* hue */ {0x00, 0x001a, 0x21ae}, /* saturation */ {0x00, 0x0002, 0x21a3}, /* gamma */ {0x30, 0x0154, 0x0008}, {0x30, 0x0004, 0x0006}, {0x30, 0x0258, 0x0009}, {0x30, 0x0004, 0x0000}, {0x30, 0x0093, 0x0004}, {0x30, 0x0066, 0x0005}, {0x00, 0x0000, 0x2000}, {0x00, 0x0013, 0x2301}, {0x00, 0x0003, 0x2000}, {0x00, 0x0013, 0x2301}, {0x00, 0x0003, 0x2000}, }; /* Creative PC-CAM 600 specific open data, sent before using the * generic initialisation data from spca504_open_data. */ static const struct cmd spca504_pccam600_open_data[] = { {0x00, 0x0001, 0x2501}, {0x20, 0x0500, 0x0001}, /* snapshot mode */ {0x00, 0x0003, 0x2880}, {0x00, 0x0001, 0x2881}, }; /* Initialisation data for the logitech clicksmart 420 */ static const struct cmd spca504A_clicksmart420_init_data[] = { /* {0xa0, 0x0000, 0x0503}, * capture mode */ {0x00, 0x0000, 0x2000}, {0x00, 0x0013, 0x2301}, {0x00, 0x0003, 0x2000}, {0x00, 0x0001, 0x21ac}, {0x00, 0x0001, 0x21a6}, {0x00, 0x0000, 0x21a7}, /* brightness */ {0x00, 0x0020, 0x21a8}, /* contrast */ {0x00, 0x0001, 0x21ac}, /* sat/hue */ {0x00, 0x0000, 0x21ad}, /* hue */ {0x00, 0x001a, 0x21ae}, /* saturation */ {0x00, 0x0002, 0x21a3}, /* gamma */ {0x30, 0x0004, 0x000a}, {0xb0, 0x0001, 0x0000}, {0xa1, 0x0080, 0x0001}, {0x30, 0x0049, 0x0000}, {0x30, 0x0060, 0x0005}, {0x0c, 0x0004, 0x0000}, {0x00, 0x0000, 0x0000}, {0x00, 0x0000, 0x2000}, {0x00, 0x0013, 0x2301}, {0x00, 0x0003, 0x2000}, }; /* clicksmart 420 open data ? */ static const struct cmd spca504A_clicksmart420_open_data[] = { {0x00, 0x0001, 0x2501}, {0x20, 0x0502, 0x0000}, {0x06, 0x0000, 0x0000}, {0x00, 0x0004, 0x2880}, {0x00, 0x0001, 0x2881}, {0xa0, 0x0000, 0x0503}, }; static const u8 qtable_creative_pccam[2][64] = { { /* Q-table Y-components */ 0x05, 0x03, 0x03, 0x05, 0x07, 0x0c, 0x0f, 0x12, 0x04, 0x04, 0x04, 0x06, 0x08, 0x11, 0x12, 0x11, 0x04, 0x04, 0x05, 0x07, 0x0c, 0x11, 0x15, 0x11, 0x04, 0x05, 0x07, 0x09, 0x0f, 0x1a, 0x18, 0x13, 0x05, 0x07, 0x0b, 0x11, 0x14, 0x21, 0x1f, 0x17, 0x07, 0x0b, 0x11, 0x13, 0x18, 0x1f, 0x22, 0x1c, 0x0f, 0x13, 0x17, 0x1a, 0x1f, 0x24, 0x24, 0x1e, 0x16, 0x1c, 0x1d, 0x1d, 0x22, 0x1e, 0x1f, 0x1e}, { /* Q-table C-components */ 0x05, 0x05, 0x07, 0x0e, 0x1e, 0x1e, 0x1e, 0x1e, 0x05, 0x06, 0x08, 0x14, 0x1e, 0x1e, 0x1e, 0x1e, 0x07, 0x08, 0x11, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x0e, 0x14, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e} }; /* FIXME: This Q-table is identical to the Creative PC-CAM one, * except for one byte. Possibly a typo? * NWG: 18/05/2003. */ static const u8 qtable_spca504_default[2][64] = { { /* Q-table Y-components */ 0x05, 0x03, 0x03, 0x05, 0x07, 0x0c, 0x0f, 0x12, 0x04, 0x04, 0x04, 0x06, 0x08, 0x11, 0x12, 0x11, 0x04, 0x04, 0x05, 0x07, 0x0c, 0x11, 0x15, 0x11, 0x04, 0x05, 0x07, 0x09, 0x0f, 0x1a, 0x18, 0x13, 0x05, 0x07, 0x0b, 0x11, 0x14, 0x21, 0x1f, 0x17, 0x07, 0x0b, 0x11, 0x13, 0x18, 0x1f, 0x22, 0x1c, 0x0f, 0x13, 0x17, 0x1a, 0x1f, 0x24, 0x24, 0x1e, 0x16, 0x1c, 0x1d, 0x1d, 0x1d /* 0x22 */ , 0x1e, 0x1f, 0x1e, }, { /* Q-table C-components */ 0x05, 0x05, 0x07, 0x0e, 0x1e, 0x1e, 0x1e, 0x1e, 0x05, 0x06, 0x08, 0x14, 0x1e, 0x1e, 0x1e, 0x1e, 0x07, 0x08, 0x11, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x0e, 0x14, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e, 0x1e} }; /* read <len> bytes to gspca_dev->usb_buf */ static void reg_r(struct gspca_dev *gspca_dev, u8 req, u16 index, u16 len) { int ret; if (len > USB_BUF_SZ) { gspca_err(gspca_dev, "reg_r: buffer overflow\n"); return; } if (len == 0) { gspca_err(gspca_dev, "reg_r: zero-length read\n"); return; } if (gspca_dev->usb_err < 0) return; ret = usb_control_msg(gspca_dev->dev, usb_rcvctrlpipe(gspca_dev->dev, 0), req, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, /* value */ index, gspca_dev->usb_buf, len, 500); if (ret < 0) { pr_err("reg_r err %d\n", ret); gspca_dev->usb_err = ret; /* * Make sure the buffer is zeroed to avoid uninitialized * values. */ memset(gspca_dev->usb_buf, 0, USB_BUF_SZ); } } /* write one byte */ static void reg_w_1(struct gspca_dev *gspca_dev, u8 req, u16 value, u16 index, u16 byte) { int ret; if (gspca_dev->usb_err < 0) return; gspca_dev->usb_buf[0] = byte; ret = usb_control_msg(gspca_dev->dev, usb_sndctrlpipe(gspca_dev->dev, 0), req, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, gspca_dev->usb_buf, 1, 500); if (ret < 0) { pr_err("reg_w_1 err %d\n", ret); gspca_dev->usb_err = ret; } } /* write req / index / value */ static void reg_w_riv(struct gspca_dev *gspca_dev, u8 req, u16 index, u16 value) { struct usb_device *dev = gspca_dev->dev; int ret; if (gspca_dev->usb_err < 0) return; ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), req, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, NULL, 0, 500); if (ret < 0) { pr_err("reg_w_riv err %d\n", ret); gspca_dev->usb_err = ret; return; } gspca_dbg(gspca_dev, D_USBO, "reg_w_riv: 0x%02x,0x%04x:0x%04x\n", req, index, value); } static void write_vector(struct gspca_dev *gspca_dev, const struct cmd *data, int ncmds) { while (--ncmds >= 0) { reg_w_riv(gspca_dev, data->req, data->idx, data->val); data++; } } static void setup_qtable(struct gspca_dev *gspca_dev, const u8 qtable[2][64]) { int i; /* loop over y components */ for (i = 0; i < 64; i++) reg_w_riv(gspca_dev, 0x00, 0x2800 + i, qtable[0][i]); /* loop over c components */ for (i = 0; i < 64; i++) reg_w_riv(gspca_dev, 0x00, 0x2840 + i, qtable[1][i]); } static void spca504_acknowledged_command(struct gspca_dev *gspca_dev, u8 req, u16 idx, u16 val) { reg_w_riv(gspca_dev, req, idx, val); reg_r(gspca_dev, 0x01, 0x0001, 1); gspca_dbg(gspca_dev, D_FRAM, "before wait 0x%04x\n", gspca_dev->usb_buf[0]); reg_w_riv(gspca_dev, req, idx, val); msleep(200); reg_r(gspca_dev, 0x01, 0x0001, 1); gspca_dbg(gspca_dev, D_FRAM, "after wait 0x%04x\n", gspca_dev->usb_buf[0]); } static void spca504_read_info(struct gspca_dev *gspca_dev) { int i; u8 info[6]; if (gspca_debug < D_STREAM) return; for (i = 0; i < 6; i++) { reg_r(gspca_dev, 0, i, 1); info[i] = gspca_dev->usb_buf[0]; } gspca_dbg(gspca_dev, D_STREAM, "Read info: %d %d %d %d %d %d. Should be 1,0,2,2,0,0\n", info[0], info[1], info[2], info[3], info[4], info[5]); } static void spca504A_acknowledged_command(struct gspca_dev *gspca_dev, u8 req, u16 idx, u16 val, u8 endcode, u8 count) { u16 status; reg_w_riv(gspca_dev, req, idx, val); reg_r(gspca_dev, 0x01, 0x0001, 1); if (gspca_dev->usb_err < 0) return; gspca_dbg(gspca_dev, D_FRAM, "Status 0x%02x Need 0x%02x\n", gspca_dev->usb_buf[0], endcode); if (!count) return; count = 200; while (--count > 0) { msleep(10); /* gsmart mini2 write a each wait setting 1 ms is enough */ /* reg_w_riv(gspca_dev, req, idx, val); */ reg_r(gspca_dev, 0x01, 0x0001, 1); status = gspca_dev->usb_buf[0]; if (status == endcode) { gspca_dbg(gspca_dev, D_FRAM, "status 0x%04x after wait %d\n", status, 200 - count); break; } } } static void spca504B_PollingDataReady(struct gspca_dev *gspca_dev) { int count = 10; while (--count > 0) { reg_r(gspca_dev, 0x21, 0, 1); if ((gspca_dev->usb_buf[0] & 0x01) == 0) break; msleep(10); } } static void spca504B_WaitCmdStatus(struct gspca_dev *gspca_dev) { int count = 50; while (--count > 0) { reg_r(gspca_dev, 0x21, 1, 1); if (gspca_dev->usb_buf[0] != 0) { reg_w_1(gspca_dev, 0x21, 0, 1, 0); reg_r(gspca_dev, 0x21, 1, 1); spca504B_PollingDataReady(gspca_dev); break; } msleep(10); } } static void spca50x_GetFirmware(struct gspca_dev *gspca_dev) { u8 *data; if (gspca_debug < D_STREAM) return; data = gspca_dev->usb_buf; reg_r(gspca_dev, 0x20, 0, 5); gspca_dbg(gspca_dev, D_STREAM, "FirmWare: %d %d %d %d %d\n", data[0], data[1], data[2], data[3], data[4]); reg_r(gspca_dev, 0x23, 0, 64); reg_r(gspca_dev, 0x23, 1, 64); } static void spca504B_SetSizeType(struct gspca_dev *gspca_dev) { struct sd *sd = (struct sd *) gspca_dev; u8 Size; Size = gspca_dev->cam.cam_mode[gspca_dev->curr_mode].priv; switch (sd->bridge) { case BRIDGE_SPCA533: reg_w_riv(gspca_dev, 0x31, 0, 0); spca504B_WaitCmdStatus(gspca_dev); spca504B_PollingDataReady(gspca_dev); spca50x_GetFirmware(gspca_dev); reg_w_1(gspca_dev, 0x24, 0, 8, 2); /* type */ reg_r(gspca_dev, 0x24, 8, 1); reg_w_1(gspca_dev, 0x25, 0, 4, Size); reg_r(gspca_dev, 0x25, 4, 1); /* size */ spca504B_PollingDataReady(gspca_dev); /* Init the cam width height with some values get on init ? */ reg_w_riv(gspca_dev, 0x31, 0x0004, 0x00); spca504B_WaitCmdStatus(gspca_dev); spca504B_PollingDataReady(gspca_dev); break; default: /* case BRIDGE_SPCA504B: */ /* case BRIDGE_SPCA536: */ reg_w_1(gspca_dev, 0x25, 0, 4, Size); reg_r(gspca_dev, 0x25, 4, 1); /* size */ reg_w_1(gspca_dev, 0x27, 0, 0, 6); reg_r(gspca_dev, 0x27, 0, 1); /* type */ spca504B_PollingDataReady(gspca_dev); break; case BRIDGE_SPCA504: Size += 3; if (sd->subtype == AiptekMiniPenCam13) { /* spca504a aiptek */ spca504A_acknowledged_command(gspca_dev, 0x08, Size, 0, 0x80 | (Size & 0x0f), 1); spca504A_acknowledged_command(gspca_dev, 1, 3, 0, 0x9f, 0); } else { spca504_acknowledged_command(gspca_dev, 0x08, Size, 0); } break; case BRIDGE_SPCA504C: /* capture mode */ reg_w_riv(gspca_dev, 0xa0, (0x0500 | (Size & 0x0f)), 0x00); reg_w_riv(gspca_dev, 0x20, 0x01, 0x0500 | (Size & 0x0f)); break; } } static void spca504_wait_status(struct gspca_dev *gspca_dev) { int cnt; cnt = 256; while (--cnt > 0) { /* With this we get the status, when return 0 it's all ok */ reg_r(gspca_dev, 0x06, 0x00, 1); if (gspca_dev->usb_buf[0] == 0) return; msleep(10); } } static void spca504B_setQtable(struct gspca_dev *gspca_dev) { reg_w_1(gspca_dev, 0x26, 0, 0, 3); reg_r(gspca_dev, 0x26, 0, 1); spca504B_PollingDataReady(gspca_dev); } static void setbrightness(struct gspca_dev *gspca_dev, s32 val) { struct sd *sd = (struct sd *) gspca_dev; u16 reg; reg = sd->bridge == BRIDGE_SPCA536 ? 0x20f0 : 0x21a7; reg_w_riv(gspca_dev, 0x00, reg, val); } static void setcontrast(struct gspca_dev *gspca_dev, s32 val) { struct sd *sd = (struct sd *) gspca_dev; u16 reg; reg = sd->bridge == BRIDGE_SPCA536 ? 0x20f1 : 0x21a8; reg_w_riv(gspca_dev, 0x00, reg, val); } static void setcolors(struct gspca_dev *gspca_dev, s32 val) { struct sd *sd = (struct sd *) gspca_dev; u16 reg; reg = sd->bridge == BRIDGE_SPCA536 ? 0x20f6 : 0x21ae; reg_w_riv(gspca_dev, 0x00, reg, val); } static void init_ctl_reg(struct gspca_dev *gspca_dev) { struct sd *sd = (struct sd *) gspca_dev; int pollreg = 1; switch (sd->bridge) { case BRIDGE_SPCA504: case BRIDGE_SPCA504C: pollreg = 0; fallthrough; default: /* case BRIDGE_SPCA533: */ /* case BRIDGE_SPCA504B: */ reg_w_riv(gspca_dev, 0, 0x21ad, 0x00); /* hue */ reg_w_riv(gspca_dev, 0, 0x21ac, 0x01); /* sat/hue */ reg_w_riv(gspca_dev, 0, 0x21a3, 0x00); /* gamma */ break; case BRIDGE_SPCA536: reg_w_riv(gspca_dev, 0, 0x20f5, 0x40); reg_w_riv(gspca_dev, 0, 0x20f4, 0x01); reg_w_riv(gspca_dev, 0, 0x2089, 0x00); break; } if (pollreg) spca504B_PollingDataReady(gspca_dev); } /* this function is called at probe time */ static int sd_config(struct gspca_dev *gspca_dev, const struct usb_device_id *id) { struct sd *sd = (struct sd *) gspca_dev; struct cam *cam; cam = &gspca_dev->cam; sd->bridge = id->driver_info >> 8; sd->subtype = id->driver_info; if (sd->subtype == AiptekMiniPenCam13) { /* try to get the firmware as some cam answer 2.0.1.2.2 * and should be a spca504b then overwrite that setting */ reg_r(gspca_dev, 0x20, 0, 1); switch (gspca_dev->usb_buf[0]) { case 1: break; /* (right bridge/subtype) */ case 2: sd->bridge = BRIDGE_SPCA504B; sd->subtype = 0; break; default: return -ENODEV; } } switch (sd->bridge) { default: /* case BRIDGE_SPCA504B: */ /* case BRIDGE_SPCA504: */ /* case BRIDGE_SPCA536: */ cam->cam_mode = vga_mode; cam->nmodes = ARRAY_SIZE(vga_mode); break; case BRIDGE_SPCA533: cam->cam_mode = custom_mode; if (sd->subtype == MegaImageVI) /* 320x240 only */ cam->nmodes = ARRAY_SIZE(custom_mode) - 1; else cam->nmodes = ARRAY_SIZE(custom_mode); break; case BRIDGE_SPCA504C: cam->cam_mode = vga_mode2; cam->nmodes = ARRAY_SIZE(vga_mode2); break; } return 0; } /* this function is called at probe and resume time */ static int sd_init(struct gspca_dev *gspca_dev) { struct sd *sd = (struct sd *) gspca_dev; switch (sd->bridge) { case BRIDGE_SPCA504B: reg_w_riv(gspca_dev, 0x1d, 0x00, 0); reg_w_riv(gspca_dev, 0x00, 0x2306, 0x01); reg_w_riv(gspca_dev, 0x00, 0x0d04, 0x00); reg_w_riv(gspca_dev, 0x00, 0x2000, 0x00); reg_w_riv(gspca_dev, 0x00, 0x2301, 0x13); reg_w_riv(gspca_dev, 0x00, 0x2306, 0x00); fallthrough; case BRIDGE_SPCA533: spca504B_PollingDataReady(gspca_dev); spca50x_GetFirmware(gspca_dev); break; case BRIDGE_SPCA536: spca50x_GetFirmware(gspca_dev); reg_r(gspca_dev, 0x00, 0x5002, 1); reg_w_1(gspca_dev, 0x24, 0, 0, 0); reg_r(gspca_dev, 0x24, 0, 1); spca504B_PollingDataReady(gspca_dev); reg_w_riv(gspca_dev, 0x34, 0, 0); spca504B_WaitCmdStatus(gspca_dev); break; case BRIDGE_SPCA504C: /* pccam600 */ gspca_dbg(gspca_dev, D_STREAM, "Opening SPCA504 (PC-CAM 600)\n"); reg_w_riv(gspca_dev, 0xe0, 0x0000, 0x0000); reg_w_riv(gspca_dev, 0xe0, 0x0000, 0x0001); /* reset */ spca504_wait_status(gspca_dev); if (sd->subtype == LogitechClickSmart420) write_vector(gspca_dev, spca504A_clicksmart420_open_data, ARRAY_SIZE(spca504A_clicksmart420_open_data)); else write_vector(gspca_dev, spca504_pccam600_open_data, ARRAY_SIZE(spca504_pccam600_open_data)); setup_qtable(gspca_dev, qtable_creative_pccam); break; default: /* case BRIDGE_SPCA504: */ gspca_dbg(gspca_dev, D_STREAM, "Opening SPCA504\n"); if (sd->subtype == AiptekMiniPenCam13) { spca504_read_info(gspca_dev); /* Set AE AWB Banding Type 3-> 50Hz 2-> 60Hz */ spca504A_acknowledged_command(gspca_dev, 0x24, 8, 3, 0x9e, 1); /* Twice sequential need status 0xff->0x9e->0x9d */ spca504A_acknowledged_command(gspca_dev, 0x24, 8, 3, 0x9e, 0); spca504A_acknowledged_command(gspca_dev, 0x24, 0, 0, 0x9d, 1); /******************************/ /* spca504a aiptek */ spca504A_acknowledged_command(gspca_dev, 0x08, 6, 0, 0x86, 1); /* reg_write (dev, 0, 0x2000, 0); */ /* reg_write (dev, 0, 0x2883, 1); */ /* spca504A_acknowledged_command (gspca_dev, 0x08, 6, 0, 0x86, 1); */ /* spca504A_acknowledged_command (gspca_dev, 0x24, 0, 0, 0x9D, 1); */ reg_w_riv(gspca_dev, 0x00, 0x270c, 0x05); /* L92 sno1t.txt */ reg_w_riv(gspca_dev, 0x00, 0x2310, 0x05); spca504A_acknowledged_command(gspca_dev, 0x01, 0x0f, 0, 0xff, 0); } /* setup qtable */ reg_w_riv(gspca_dev, 0, 0x2000, 0); reg_w_riv(gspca_dev, 0, 0x2883, 1); setup_qtable(gspca_dev, qtable_spca504_default); break; } return gspca_dev->usb_err; } static int sd_start(struct gspca_dev *gspca_dev) { struct sd *sd = (struct sd *) gspca_dev; int enable; /* create the JPEG header */ jpeg_define(sd->jpeg_hdr, gspca_dev->pixfmt.height, gspca_dev->pixfmt.width, 0x22); /* JPEG 411 */ jpeg_set_qual(sd->jpeg_hdr, QUALITY); if (sd->bridge == BRIDGE_SPCA504B) spca504B_setQtable(gspca_dev); spca504B_SetSizeType(gspca_dev); switch (sd->bridge) { default: /* case BRIDGE_SPCA504B: */ /* case BRIDGE_SPCA533: */ /* case BRIDGE_SPCA536: */ switch (sd->subtype) { case MegapixV4: case LogitechClickSmart820: case MegaImageVI: reg_w_riv(gspca_dev, 0xf0, 0, 0); spca504B_WaitCmdStatus(gspca_dev); reg_w_riv(gspca_dev, 0xf0, 4, 0); spca504B_WaitCmdStatus(gspca_dev); break; default: reg_w_riv(gspca_dev, 0x31, 0x0004, 0x00); spca504B_WaitCmdStatus(gspca_dev); spca504B_PollingDataReady(gspca_dev); break; } break; case BRIDGE_SPCA504: if (sd->subtype == AiptekMiniPenCam13) { spca504_read_info(gspca_dev); /* Set AE AWB Banding Type 3-> 50Hz 2-> 60Hz */ spca504A_acknowledged_command(gspca_dev, 0x24, 8, 3, 0x9e, 1); /* Twice sequential need status 0xff->0x9e->0x9d */ spca504A_acknowledged_command(gspca_dev, 0x24, 8, 3, 0x9e, 0); spca504A_acknowledged_command(gspca_dev, 0x24, 0, 0, 0x9d, 1); } else { spca504_acknowledged_command(gspca_dev, 0x24, 8, 3); spca504_read_info(gspca_dev); spca504_acknowledged_command(gspca_dev, 0x24, 8, 3); spca504_acknowledged_command(gspca_dev, 0x24, 0, 0); } spca504B_SetSizeType(gspca_dev); reg_w_riv(gspca_dev, 0x00, 0x270c, 0x05); /* L92 sno1t.txt */ reg_w_riv(gspca_dev, 0x00, 0x2310, 0x05); break; case BRIDGE_SPCA504C: if (sd->subtype == LogitechClickSmart420) { write_vector(gspca_dev, spca504A_clicksmart420_init_data, ARRAY_SIZE(spca504A_clicksmart420_init_data)); } else { write_vector(gspca_dev, spca504_pccam600_init_data, ARRAY_SIZE(spca504_pccam600_init_data)); } enable = (sd->autogain ? 0x04 : 0x01); reg_w_riv(gspca_dev, 0x0c, 0x0000, enable); /* auto exposure */ reg_w_riv(gspca_dev, 0xb0, 0x0000, enable); /* auto whiteness */ /* set default exposure compensation and whiteness balance */ reg_w_riv(gspca_dev, 0x30, 0x0001, 800); /* ~ 20 fps */ reg_w_riv(gspca_dev, 0x30, 0x0002, 1600); spca504B_SetSizeType(gspca_dev); break; } init_ctl_reg(gspca_dev); return gspca_dev->usb_err; } static void sd_stopN(struct gspca_dev *gspca_dev) { struct sd *sd = (struct sd *) gspca_dev; switch (sd->bridge) { default: /* case BRIDGE_SPCA533: */ /* case BRIDGE_SPCA536: */ /* case BRIDGE_SPCA504B: */ reg_w_riv(gspca_dev, 0x31, 0, 0); spca504B_WaitCmdStatus(gspca_dev); spca504B_PollingDataReady(gspca_dev); break; case BRIDGE_SPCA504: case BRIDGE_SPCA504C: reg_w_riv(gspca_dev, 0x00, 0x2000, 0x0000); if (sd->subtype == AiptekMiniPenCam13) { /* spca504a aiptek */ /* spca504A_acknowledged_command(gspca_dev, 0x08, 6, 0, 0x86, 1); */ spca504A_acknowledged_command(gspca_dev, 0x24, 0x00, 0x00, 0x9d, 1); spca504A_acknowledged_command(gspca_dev, 0x01, 0x0f, 0x00, 0xff, 1); } else { spca504_acknowledged_command(gspca_dev, 0x24, 0, 0); reg_w_riv(gspca_dev, 0x01, 0x000f, 0x0000); } break; } } static void sd_pkt_scan(struct gspca_dev *gspca_dev, u8 *data, /* isoc packet */ int len) /* iso packet length */ { struct sd *sd = (struct sd *) gspca_dev; int i, sof = 0; static u8 ffd9[] = {0xff, 0xd9}; /* frames are jpeg 4.1.1 without 0xff escape */ switch (sd->bridge) { case BRIDGE_SPCA533: if (data[0] == 0xff) { if (data[1] != 0x01) { /* drop packet */ /* gspca_dev->last_packet_type = DISCARD_PACKET; */ return; } sof = 1; data += SPCA533_OFFSET_DATA; len -= SPCA533_OFFSET_DATA; } else { data += 1; len -= 1; } break; case BRIDGE_SPCA536: if (data[0] == 0xff) { sof = 1; data += SPCA536_OFFSET_DATA; len -= SPCA536_OFFSET_DATA; } else { data += 2; len -= 2; } break; default: /* case BRIDGE_SPCA504: */ /* case BRIDGE_SPCA504B: */ switch (data[0]) { case 0xfe: /* start of frame */ sof = 1; data += SPCA50X_OFFSET_DATA; len -= SPCA50X_OFFSET_DATA; break; case 0xff: /* drop packet */ /* gspca_dev->last_packet_type = DISCARD_PACKET; */ return; default: data += 1; len -= 1; break; } break; case BRIDGE_SPCA504C: switch (data[0]) { case 0xfe: /* start of frame */ sof = 1; data += SPCA504_PCCAM600_OFFSET_DATA; len -= SPCA504_PCCAM600_OFFSET_DATA; break; case 0xff: /* drop packet */ /* gspca_dev->last_packet_type = DISCARD_PACKET; */ return; default: data += 1; len -= 1; break; } break; } if (sof) { /* start of frame */ gspca_frame_add(gspca_dev, LAST_PACKET, ffd9, 2); /* put the JPEG header in the new frame */ gspca_frame_add(gspca_dev, FIRST_PACKET, sd->jpeg_hdr, JPEG_HDR_SZ); } /* add 0x00 after 0xff */ i = 0; do { if (data[i] == 0xff) { gspca_frame_add(gspca_dev, INTER_PACKET, data, i + 1); len -= i; data += i; *data = 0x00; i = 0; } i++; } while (i < len); gspca_frame_add(gspca_dev, INTER_PACKET, data, len); } static int sd_s_ctrl(struct v4l2_ctrl *ctrl) { struct gspca_dev *gspca_dev = container_of(ctrl->handler, struct gspca_dev, ctrl_handler); struct sd *sd = (struct sd *)gspca_dev; gspca_dev->usb_err = 0; if (!gspca_dev->streaming) return 0; switch (ctrl->id) { case V4L2_CID_BRIGHTNESS: setbrightness(gspca_dev, ctrl->val); break; case V4L2_CID_CONTRAST: setcontrast(gspca_dev, ctrl->val); break; case V4L2_CID_SATURATION: setcolors(gspca_dev, ctrl->val); break; case V4L2_CID_AUTOGAIN: sd->autogain = ctrl->val; break; } return gspca_dev->usb_err; } static const struct v4l2_ctrl_ops sd_ctrl_ops = { .s_ctrl = sd_s_ctrl, }; static int sd_init_controls(struct gspca_dev *gspca_dev) { struct v4l2_ctrl_handler *hdl = &gspca_dev->ctrl_handler; gspca_dev->vdev.ctrl_handler = hdl; v4l2_ctrl_handler_init(hdl, 4); v4l2_ctrl_new_std(hdl, &sd_ctrl_ops, V4L2_CID_BRIGHTNESS, -128, 127, 1, 0); v4l2_ctrl_new_std(hdl, &sd_ctrl_ops, V4L2_CID_CONTRAST, 0, 255, 1, 0x20); v4l2_ctrl_new_std(hdl, &sd_ctrl_ops, V4L2_CID_SATURATION, 0, 255, 1, 0x1a); v4l2_ctrl_new_std(hdl, &sd_ctrl_ops, V4L2_CID_AUTOGAIN, 0, 1, 1, 1); if (hdl->error) { pr_err("Could not initialize controls\n"); return hdl->error; } return 0; } /* sub-driver description */ static const struct sd_desc sd_desc = { .name = MODULE_NAME, .config = sd_config, .init = sd_init, .init_controls = sd_init_controls, .start = sd_start, .stopN = sd_stopN, .pkt_scan = sd_pkt_scan, }; /* -- module initialisation -- */ #define BS(bridge, subtype) \ .driver_info = (BRIDGE_ ## bridge << 8) \ | (subtype) static const struct usb_device_id device_table[] = { {USB_DEVICE(0x041e, 0x400b), BS(SPCA504C, 0)}, {USB_DEVICE(0x041e, 0x4012), BS(SPCA504C, 0)}, {USB_DEVICE(0x041e, 0x4013), BS(SPCA504C, 0)}, {USB_DEVICE(0x0458, 0x7006), BS(SPCA504B, 0)}, {USB_DEVICE(0x0461, 0x0821), BS(SPCA533, 0)}, {USB_DEVICE(0x046d, 0x0905), BS(SPCA533, LogitechClickSmart820)}, {USB_DEVICE(0x046d, 0x0960), BS(SPCA504C, LogitechClickSmart420)}, {USB_DEVICE(0x0471, 0x0322), BS(SPCA504B, 0)}, {USB_DEVICE(0x04a5, 0x3003), BS(SPCA504B, 0)}, {USB_DEVICE(0x04a5, 0x3008), BS(SPCA533, 0)}, {USB_DEVICE(0x04a5, 0x300a), BS(SPCA533, 0)}, {USB_DEVICE(0x04f1, 0x1001), BS(SPCA504B, 0)}, {USB_DEVICE(0x04fc, 0x500c), BS(SPCA504B, 0)}, {USB_DEVICE(0x04fc, 0x504a), BS(SPCA504, AiptekMiniPenCam13)}, {USB_DEVICE(0x04fc, 0x504b), BS(SPCA504B, 0)}, {USB_DEVICE(0x04fc, 0x5330), BS(SPCA533, 0)}, {USB_DEVICE(0x04fc, 0x5360), BS(SPCA536, 0)}, {USB_DEVICE(0x04fc, 0xffff), BS(SPCA504B, 0)}, {USB_DEVICE(0x052b, 0x1507), BS(SPCA533, MegapixV4)}, {USB_DEVICE(0x052b, 0x1513), BS(SPCA533, MegapixV4)}, {USB_DEVICE(0x052b, 0x1803), BS(SPCA533, MegaImageVI)}, {USB_DEVICE(0x0546, 0x3155), BS(SPCA533, 0)}, {USB_DEVICE(0x0546, 0x3191), BS(SPCA504B, 0)}, {USB_DEVICE(0x0546, 0x3273), BS(SPCA504B, 0)}, {USB_DEVICE(0x055f, 0xc211), BS(SPCA536, 0)}, {USB_DEVICE(0x055f, 0xc230), BS(SPCA533, 0)}, {USB_DEVICE(0x055f, 0xc232), BS(SPCA533, 0)}, {USB_DEVICE(0x055f, 0xc360), BS(SPCA536, 0)}, {USB_DEVICE(0x055f, 0xc420), BS(SPCA504, 0)}, {USB_DEVICE(0x055f, 0xc430), BS(SPCA533, 0)}, {USB_DEVICE(0x055f, 0xc440), BS(SPCA533, 0)}, {USB_DEVICE(0x055f, 0xc520), BS(SPCA504, 0)}, {USB_DEVICE(0x055f, 0xc530), BS(SPCA533, 0)}, {USB_DEVICE(0x055f, 0xc540), BS(SPCA533, 0)}, {USB_DEVICE(0x055f, 0xc630), BS(SPCA533, 0)}, {USB_DEVICE(0x055f, 0xc650), BS(SPCA533, 0)}, {USB_DEVICE(0x05da, 0x1018), BS(SPCA504B, 0)}, {USB_DEVICE(0x06d6, 0x0031), BS(SPCA533, 0)}, {USB_DEVICE(0x06d6, 0x0041), BS(SPCA504B, 0)}, {USB_DEVICE(0x0733, 0x1311), BS(SPCA533, 0)}, {USB_DEVICE(0x0733, 0x1314), BS(SPCA533, 0)}, {USB_DEVICE(0x0733, 0x2211), BS(SPCA533, 0)}, {USB_DEVICE(0x0733, 0x2221), BS(SPCA533, 0)}, {USB_DEVICE(0x0733, 0x3261), BS(SPCA536, 0)}, {USB_DEVICE(0x0733, 0x3281), BS(SPCA536, 0)}, {USB_DEVICE(0x08ca, 0x0104), BS(SPCA533, 0)}, {USB_DEVICE(0x08ca, 0x0106), BS(SPCA533, 0)}, {USB_DEVICE(0x08ca, 0x2008), BS(SPCA504B, 0)}, {USB_DEVICE(0x08ca, 0x2010), BS(SPCA533, 0)}, {USB_DEVICE(0x08ca, 0x2016), BS(SPCA504B, 0)}, {USB_DEVICE(0x08ca, 0x2018), BS(SPCA504B, 0)}, {USB_DEVICE(0x08ca, 0x2020), BS(SPCA533, 0)}, {USB_DEVICE(0x08ca, 0x2022), BS(SPCA533, 0)}, {USB_DEVICE(0x08ca, 0x2024), BS(SPCA536, 0)}, {USB_DEVICE(0x08ca, 0x2028), BS(SPCA533, 0)}, {USB_DEVICE(0x08ca, 0x2040), BS(SPCA536, 0)}, {USB_DEVICE(0x08ca, 0x2042), BS(SPCA536, 0)}, {USB_DEVICE(0x08ca, 0x2050), BS(SPCA536, 0)}, {USB_DEVICE(0x08ca, 0x2060), BS(SPCA536, 0)}, {USB_DEVICE(0x0d64, 0x0303), BS(SPCA536, 0)}, {} }; MODULE_DEVICE_TABLE(usb, device_table); /* -- device connect -- */ static int sd_probe(struct usb_interface *intf, const struct usb_device_id *id) { return gspca_dev_probe(intf, id, &sd_desc, sizeof(struct sd), THIS_MODULE); } static struct usb_driver sd_driver = { .name = MODULE_NAME, .id_table = device_table, .probe = sd_probe, .disconnect = gspca_disconnect, #ifdef CONFIG_PM .suspend = gspca_suspend, .resume = gspca_resume, .reset_resume = gspca_resume, #endif }; module_usb_driver(sd_driver); |
| 4 4 4 4 4 4 4 4 4 4 4 6 6 4 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> #include <linux/module.h> #include <linux/err.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/uaccess.h> #ifdef CONFIG_BLOCK #include <linux/bio.h> #endif #include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/osd_client.h> #include <linux/ceph/messenger.h> #include <linux/ceph/decode.h> #include <linux/ceph/auth.h> #include <linux/ceph/pagelist.h> #include <linux/ceph/striper.h> #define OSD_OPREPLY_FRONT_LEN 512 static struct kmem_cache *ceph_osd_request_cache; static const struct ceph_connection_operations osd_con_ops; /* * Implement client access to distributed object storage cluster. * * All data objects are stored within a cluster/cloud of OSDs, or * "object storage devices." (Note that Ceph OSDs have _nothing_ to * do with the T10 OSD extensions to SCSI.) Ceph OSDs are simply * remote daemons serving up and coordinating consistent and safe * access to storage. * * Cluster membership and the mapping of data objects onto storage devices * are described by the osd map. * * We keep track of pending OSD requests (read, write), resubmit * requests to different OSDs when the cluster topology/data layout * change, or retry the affected requests when the communications * channel with an OSD is reset. */ static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req); static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req); static void link_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq); static void unlink_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq); static void clear_backoffs(struct ceph_osd *osd); #if 1 static inline bool rwsem_is_wrlocked(struct rw_semaphore *sem) { bool wrlocked = true; if (unlikely(down_read_trylock(sem))) { wrlocked = false; up_read(sem); } return wrlocked; } static inline void verify_osdc_locked(struct ceph_osd_client *osdc) { WARN_ON(!rwsem_is_locked(&osdc->lock)); } static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc) { WARN_ON(!rwsem_is_wrlocked(&osdc->lock)); } static inline void verify_osd_locked(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; WARN_ON(!(mutex_is_locked(&osd->lock) && rwsem_is_locked(&osdc->lock)) && !rwsem_is_wrlocked(&osdc->lock)); } static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { WARN_ON(!mutex_is_locked(&lreq->lock)); } #else static inline void verify_osdc_locked(struct ceph_osd_client *osdc) { } static inline void verify_osdc_wrlocked(struct ceph_osd_client *osdc) { } static inline void verify_osd_locked(struct ceph_osd *osd) { } static inline void verify_lreq_locked(struct ceph_osd_linger_request *lreq) { } #endif /* * calculate the mapping of a file extent onto an object, and fill out the * request accordingly. shorten extent as necessary if it crosses an * object boundary. * * fill osd op in request message. */ static int calc_layout(struct ceph_file_layout *layout, u64 off, u64 *plen, u64 *objnum, u64 *objoff, u64 *objlen) { u64 orig_len = *plen; u32 xlen; /* object extent? */ ceph_calc_file_object_mapping(layout, off, orig_len, objnum, objoff, &xlen); *objlen = xlen; if (*objlen < orig_len) { *plen = *objlen; dout(" skipping last %llu, final file extent %llu~%llu\n", orig_len - *plen, off, *plen); } dout("calc_layout objnum=%llx %llu~%llu\n", *objnum, *objoff, *objlen); return 0; } static void ceph_osd_data_init(struct ceph_osd_data *osd_data) { memset(osd_data, 0, sizeof (*osd_data)); osd_data->type = CEPH_OSD_DATA_TYPE_NONE; } /* * Consumes @pages if @own_pages is true. */ static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { osd_data->type = CEPH_OSD_DATA_TYPE_PAGES; osd_data->pages = pages; osd_data->length = length; osd_data->alignment = alignment; osd_data->pages_from_pool = pages_from_pool; osd_data->own_pages = own_pages; } /* * Consumes a ref on @pagelist. */ static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data, struct ceph_pagelist *pagelist) { osd_data->type = CEPH_OSD_DATA_TYPE_PAGELIST; osd_data->pagelist = pagelist; } #ifdef CONFIG_BLOCK static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, struct ceph_bio_iter *bio_pos, u32 bio_length) { osd_data->type = CEPH_OSD_DATA_TYPE_BIO; osd_data->bio_pos = *bio_pos; osd_data->bio_length = bio_length; } #endif /* CONFIG_BLOCK */ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data, struct ceph_bvec_iter *bvec_pos, u32 num_bvecs) { osd_data->type = CEPH_OSD_DATA_TYPE_BVECS; osd_data->bvec_pos = *bvec_pos; osd_data->num_bvecs = num_bvecs; } static void ceph_osd_iter_init(struct ceph_osd_data *osd_data, struct iov_iter *iter) { osd_data->type = CEPH_OSD_DATA_TYPE_ITER; osd_data->iter = *iter; } static struct ceph_osd_data * osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which) { BUG_ON(which >= osd_req->r_num_ops); return &osd_req->r_ops[which].raw_data_in; } struct ceph_osd_data * osd_req_op_extent_osd_data(struct ceph_osd_request *osd_req, unsigned int which) { return osd_req_op_data(osd_req, which, extent, osd_data); } EXPORT_SYMBOL(osd_req_op_extent_osd_data); void osd_req_op_raw_data_in_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_raw_data_in(osd_req, which); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_raw_data_in_pages); void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_pages); void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_pagelist *pagelist) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_pagelist_init(osd_data, pagelist); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_pagelist); #ifdef CONFIG_BLOCK void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bio_iter *bio_pos, u32 bio_length) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bio_init(osd_data, bio_pos, bio_length); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio); #endif /* CONFIG_BLOCK */ void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, struct bio_vec *bvecs, u32 num_bvecs, u32 bytes) { struct ceph_osd_data *osd_data; struct ceph_bvec_iter it = { .bvecs = bvecs, .iter = { .bi_size = bytes }, }; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs); void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bvec_iter *bvec_pos) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos); /** * osd_req_op_extent_osd_iter - Set up an operation with an iterator buffer * @osd_req: The request to set up * @which: Index of the operation in which to set the iter * @iter: The buffer iterator */ void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req, unsigned int which, struct iov_iter *iter) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); ceph_osd_iter_init(osd_data, iter); } EXPORT_SYMBOL(osd_req_op_extent_osd_iter); static void osd_req_op_cls_request_info_pagelist( struct ceph_osd_request *osd_req, unsigned int which, struct ceph_pagelist *pagelist) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, request_info); ceph_osd_data_pagelist_init(osd_data, pagelist); } void osd_req_op_cls_request_data_pagelist( struct ceph_osd_request *osd_req, unsigned int which, struct ceph_pagelist *pagelist) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, request_data); ceph_osd_data_pagelist_init(osd_data, pagelist); osd_req->r_ops[which].cls.indata_len += pagelist->length; osd_req->r_ops[which].indata_len += pagelist->length; } EXPORT_SYMBOL(osd_req_op_cls_request_data_pagelist); void osd_req_op_cls_request_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, request_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); osd_req->r_ops[which].cls.indata_len += length; osd_req->r_ops[which].indata_len += length; } EXPORT_SYMBOL(osd_req_op_cls_request_data_pages); void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, struct bio_vec *bvecs, u32 num_bvecs, u32 bytes) { struct ceph_osd_data *osd_data; struct ceph_bvec_iter it = { .bvecs = bvecs, .iter = { .bi_size = bytes }, }; osd_data = osd_req_op_data(osd_req, which, cls, request_data); ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); osd_req->r_ops[which].cls.indata_len += bytes; osd_req->r_ops[which].indata_len += bytes; } EXPORT_SYMBOL(osd_req_op_cls_request_data_bvecs); void osd_req_op_cls_response_data_pages(struct ceph_osd_request *osd_req, unsigned int which, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages) { struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, cls, response_data); ceph_osd_data_pages_init(osd_data, pages, length, alignment, pages_from_pool, own_pages); } EXPORT_SYMBOL(osd_req_op_cls_response_data_pages); static u64 ceph_osd_data_length(struct ceph_osd_data *osd_data) { switch (osd_data->type) { case CEPH_OSD_DATA_TYPE_NONE: return 0; case CEPH_OSD_DATA_TYPE_PAGES: return osd_data->length; case CEPH_OSD_DATA_TYPE_PAGELIST: return (u64)osd_data->pagelist->length; #ifdef CONFIG_BLOCK case CEPH_OSD_DATA_TYPE_BIO: return (u64)osd_data->bio_length; #endif /* CONFIG_BLOCK */ case CEPH_OSD_DATA_TYPE_BVECS: return osd_data->bvec_pos.iter.bi_size; case CEPH_OSD_DATA_TYPE_ITER: return iov_iter_count(&osd_data->iter); default: WARN(true, "unrecognized data type %d\n", (int)osd_data->type); return 0; } } static void ceph_osd_data_release(struct ceph_osd_data *osd_data) { if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES && osd_data->own_pages) { int num_pages; num_pages = calc_pages_for((u64)osd_data->alignment, (u64)osd_data->length); ceph_release_page_vector(osd_data->pages, num_pages); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) { ceph_pagelist_release(osd_data->pagelist); } ceph_osd_data_init(osd_data); } static void osd_req_op_data_release(struct ceph_osd_request *osd_req, unsigned int which) { struct ceph_osd_req_op *op; BUG_ON(which >= osd_req->r_num_ops); op = &osd_req->r_ops[which]; switch (op->op) { case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: kfree(op->extent.sparse_ext); ceph_osd_data_release(&op->extent.osd_data); break; case CEPH_OSD_OP_CALL: ceph_osd_data_release(&op->cls.request_info); ceph_osd_data_release(&op->cls.request_data); ceph_osd_data_release(&op->cls.response_data); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: ceph_osd_data_release(&op->xattr.osd_data); break; case CEPH_OSD_OP_STAT: ceph_osd_data_release(&op->raw_data_in); break; case CEPH_OSD_OP_NOTIFY_ACK: ceph_osd_data_release(&op->notify_ack.request_data); break; case CEPH_OSD_OP_NOTIFY: ceph_osd_data_release(&op->notify.request_data); ceph_osd_data_release(&op->notify.response_data); break; case CEPH_OSD_OP_LIST_WATCHERS: ceph_osd_data_release(&op->list_watchers.response_data); break; case CEPH_OSD_OP_COPY_FROM2: ceph_osd_data_release(&op->copy_from.osd_data); break; default: break; } } /* * Assumes @t is zero-initialized. */ static void target_init(struct ceph_osd_request_target *t) { ceph_oid_init(&t->base_oid); ceph_oloc_init(&t->base_oloc); ceph_oid_init(&t->target_oid); ceph_oloc_init(&t->target_oloc); ceph_osds_init(&t->acting); ceph_osds_init(&t->up); t->size = -1; t->min_size = -1; t->osd = CEPH_HOMELESS_OSD; } static void target_copy(struct ceph_osd_request_target *dest, const struct ceph_osd_request_target *src) { ceph_oid_copy(&dest->base_oid, &src->base_oid); ceph_oloc_copy(&dest->base_oloc, &src->base_oloc); ceph_oid_copy(&dest->target_oid, &src->target_oid); ceph_oloc_copy(&dest->target_oloc, &src->target_oloc); dest->pgid = src->pgid; /* struct */ dest->spgid = src->spgid; /* struct */ dest->pg_num = src->pg_num; dest->pg_num_mask = src->pg_num_mask; ceph_osds_copy(&dest->acting, &src->acting); ceph_osds_copy(&dest->up, &src->up); dest->size = src->size; dest->min_size = src->min_size; dest->sort_bitwise = src->sort_bitwise; dest->recovery_deletes = src->recovery_deletes; dest->flags = src->flags; dest->used_replica = src->used_replica; dest->paused = src->paused; dest->epoch = src->epoch; dest->last_force_resend = src->last_force_resend; dest->osd = src->osd; } static void target_destroy(struct ceph_osd_request_target *t) { ceph_oid_destroy(&t->base_oid); ceph_oloc_destroy(&t->base_oloc); ceph_oid_destroy(&t->target_oid); ceph_oloc_destroy(&t->target_oloc); } /* * requests */ static void request_release_checks(struct ceph_osd_request *req) { WARN_ON(!RB_EMPTY_NODE(&req->r_node)); WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node)); WARN_ON(!list_empty(&req->r_private_item)); WARN_ON(req->r_osd); } static void ceph_osdc_release_request(struct kref *kref) { struct ceph_osd_request *req = container_of(kref, struct ceph_osd_request, r_kref); unsigned int which; dout("%s %p (r_request %p r_reply %p)\n", __func__, req, req->r_request, req->r_reply); request_release_checks(req); if (req->r_request) ceph_msg_put(req->r_request); if (req->r_reply) ceph_msg_put(req->r_reply); for (which = 0; which < req->r_num_ops; which++) osd_req_op_data_release(req, which); target_destroy(&req->r_t); ceph_put_snap_context(req->r_snapc); if (req->r_mempool) mempool_free(req, req->r_osdc->req_mempool); else if (req->r_num_ops <= CEPH_OSD_SLAB_OPS) kmem_cache_free(ceph_osd_request_cache, req); else kfree(req); } void ceph_osdc_get_request(struct ceph_osd_request *req) { dout("%s %p (was %d)\n", __func__, req, kref_read(&req->r_kref)); kref_get(&req->r_kref); } EXPORT_SYMBOL(ceph_osdc_get_request); void ceph_osdc_put_request(struct ceph_osd_request *req) { if (req) { dout("%s %p (was %d)\n", __func__, req, kref_read(&req->r_kref)); kref_put(&req->r_kref, ceph_osdc_release_request); } } EXPORT_SYMBOL(ceph_osdc_put_request); static void request_init(struct ceph_osd_request *req) { /* req only, each op is zeroed in osd_req_op_init() */ memset(req, 0, sizeof(*req)); kref_init(&req->r_kref); init_completion(&req->r_completion); RB_CLEAR_NODE(&req->r_node); RB_CLEAR_NODE(&req->r_mc_node); INIT_LIST_HEAD(&req->r_private_item); target_init(&req->r_t); } struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_ops, bool use_mempool, gfp_t gfp_flags) { struct ceph_osd_request *req; if (use_mempool) { BUG_ON(num_ops > CEPH_OSD_SLAB_OPS); req = mempool_alloc(osdc->req_mempool, gfp_flags); } else if (num_ops <= CEPH_OSD_SLAB_OPS) { req = kmem_cache_alloc(ceph_osd_request_cache, gfp_flags); } else { BUG_ON(num_ops > CEPH_OSD_MAX_OPS); req = kmalloc(struct_size(req, r_ops, num_ops), gfp_flags); } if (unlikely(!req)) return NULL; request_init(req); req->r_osdc = osdc; req->r_mempool = use_mempool; req->r_num_ops = num_ops; req->r_snapid = CEPH_NOSNAP; req->r_snapc = ceph_get_snap_context(snapc); dout("%s req %p\n", __func__, req); return req; } EXPORT_SYMBOL(ceph_osdc_alloc_request); static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc) { return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0); } static int __ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp, int num_request_data_items, int num_reply_data_items) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_msg *msg; int msg_size; WARN_ON(req->r_request || req->r_reply); WARN_ON(ceph_oid_empty(&req->r_base_oid)); WARN_ON(ceph_oloc_empty(&req->r_base_oloc)); /* create request message */ msg_size = CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1; /* spgid */ msg_size += 4 + 4 + 4; /* hash, osdmap_epoch, flags */ msg_size += CEPH_ENCODING_START_BLK_LEN + sizeof(struct ceph_osd_reqid); /* reqid */ msg_size += sizeof(struct ceph_blkin_trace_info); /* trace */ msg_size += 4 + sizeof(struct ceph_timespec); /* client_inc, mtime */ msg_size += CEPH_ENCODING_START_BLK_LEN + ceph_oloc_encoding_size(&req->r_base_oloc); /* oloc */ msg_size += 4 + req->r_base_oid.name_len; /* oid */ msg_size += 2 + req->r_num_ops * sizeof(struct ceph_osd_op); msg_size += 8; /* snapid */ msg_size += 8; /* snap_seq */ msg_size += 4 + 8 * (req->r_snapc ? req->r_snapc->num_snaps : 0); msg_size += 4 + 8; /* retry_attempt, features */ if (req->r_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size, num_request_data_items); else msg = ceph_msg_new2(CEPH_MSG_OSD_OP, msg_size, num_request_data_items, gfp, true); if (!msg) return -ENOMEM; memset(msg->front.iov_base, 0, msg->front.iov_len); req->r_request = msg; /* create reply message */ msg_size = OSD_OPREPLY_FRONT_LEN; msg_size += req->r_base_oid.name_len; msg_size += req->r_num_ops * sizeof(struct ceph_osd_op); if (req->r_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size, num_reply_data_items); else msg = ceph_msg_new2(CEPH_MSG_OSD_OPREPLY, msg_size, num_reply_data_items, gfp, true); if (!msg) return -ENOMEM; req->r_reply = msg; return 0; } static bool osd_req_opcode_valid(u16 opcode) { switch (opcode) { #define GENERATE_CASE(op, opcode, str) case CEPH_OSD_OP_##op: return true; __CEPH_FORALL_OSD_OPS(GENERATE_CASE) #undef GENERATE_CASE default: return false; } } static void get_num_data_items(struct ceph_osd_request *req, int *num_request_data_items, int *num_reply_data_items) { struct ceph_osd_req_op *op; *num_request_data_items = 0; *num_reply_data_items = 0; for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) { switch (op->op) { /* request */ case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: case CEPH_OSD_OP_NOTIFY_ACK: case CEPH_OSD_OP_COPY_FROM2: *num_request_data_items += 1; break; /* reply */ case CEPH_OSD_OP_STAT: case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_LIST_WATCHERS: *num_reply_data_items += 1; break; /* both */ case CEPH_OSD_OP_NOTIFY: *num_request_data_items += 1; *num_reply_data_items += 1; break; case CEPH_OSD_OP_CALL: *num_request_data_items += 2; *num_reply_data_items += 1; break; default: WARN_ON(!osd_req_opcode_valid(op->op)); break; } } } /* * oid, oloc and OSD op opcode(s) must be filled in before this function * is called. */ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) { int num_request_data_items, num_reply_data_items; get_num_data_items(req, &num_request_data_items, &num_reply_data_items); return __ceph_osdc_alloc_messages(req, gfp, num_request_data_items, num_reply_data_items); } EXPORT_SYMBOL(ceph_osdc_alloc_messages); /* * This is an osd op init function for opcodes that have no data or * other information associated with them. It also serves as a * common init routine for all the other init functions, below. */ struct ceph_osd_req_op * osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u32 flags) { struct ceph_osd_req_op *op; BUG_ON(which >= osd_req->r_num_ops); BUG_ON(!osd_req_opcode_valid(opcode)); op = &osd_req->r_ops[which]; memset(op, 0, sizeof (*op)); op->op = opcode; op->flags = flags; return op; } EXPORT_SYMBOL(osd_req_op_init); void osd_req_op_extent_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, u64 offset, u64 length, u64 truncate_size, u32 truncate_seq) { struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which, opcode, 0); size_t payload_len = 0; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_SPARSE_READ); op->extent.offset = offset; op->extent.length = length; op->extent.truncate_size = truncate_size; op->extent.truncate_seq = truncate_seq; if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL) payload_len += length; op->indata_len = payload_len; } EXPORT_SYMBOL(osd_req_op_extent_init); void osd_req_op_extent_update(struct ceph_osd_request *osd_req, unsigned int which, u64 length) { struct ceph_osd_req_op *op; u64 previous; BUG_ON(which >= osd_req->r_num_ops); op = &osd_req->r_ops[which]; previous = op->extent.length; if (length == previous) return; /* Nothing to do */ BUG_ON(length > previous); op->extent.length = length; if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL) op->indata_len -= previous - length; } EXPORT_SYMBOL(osd_req_op_extent_update); void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req, unsigned int which, u64 offset_inc) { struct ceph_osd_req_op *op, *prev_op; BUG_ON(which + 1 >= osd_req->r_num_ops); prev_op = &osd_req->r_ops[which]; op = osd_req_op_init(osd_req, which + 1, prev_op->op, prev_op->flags); /* dup previous one */ op->indata_len = prev_op->indata_len; op->outdata_len = prev_op->outdata_len; op->extent = prev_op->extent; /* adjust offset */ op->extent.offset += offset_inc; op->extent.length -= offset_inc; if (op->op == CEPH_OSD_OP_WRITE || op->op == CEPH_OSD_OP_WRITEFULL) op->indata_len -= offset_inc; } EXPORT_SYMBOL(osd_req_op_extent_dup_last); int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, const char *class, const char *method) { struct ceph_osd_req_op *op; struct ceph_pagelist *pagelist; size_t payload_len = 0; size_t size; int ret; op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0); pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; op->cls.class_name = class; size = strlen(class); BUG_ON(size > (size_t) U8_MAX); op->cls.class_len = size; ret = ceph_pagelist_append(pagelist, class, size); if (ret) goto err_pagelist_free; payload_len += size; op->cls.method_name = method; size = strlen(method); BUG_ON(size > (size_t) U8_MAX); op->cls.method_len = size; ret = ceph_pagelist_append(pagelist, method, size); if (ret) goto err_pagelist_free; payload_len += size; osd_req_op_cls_request_info_pagelist(osd_req, which, pagelist); op->indata_len = payload_len; return 0; err_pagelist_free: ceph_pagelist_release(pagelist); return ret; } EXPORT_SYMBOL(osd_req_op_cls_init); int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *name, const void *value, size_t size, u8 cmp_op, u8 cmp_mode) { struct ceph_osd_req_op *op = osd_req_op_init(osd_req, which, opcode, 0); struct ceph_pagelist *pagelist; size_t payload_len; int ret; BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR); pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; payload_len = strlen(name); op->xattr.name_len = payload_len; ret = ceph_pagelist_append(pagelist, name, payload_len); if (ret) goto err_pagelist_free; op->xattr.value_len = size; ret = ceph_pagelist_append(pagelist, value, size); if (ret) goto err_pagelist_free; payload_len += size; op->xattr.cmp_op = cmp_op; op->xattr.cmp_mode = cmp_mode; ceph_osd_data_pagelist_init(&op->xattr.osd_data, pagelist); op->indata_len = payload_len; return 0; err_pagelist_free: ceph_pagelist_release(pagelist); return ret; } EXPORT_SYMBOL(osd_req_op_xattr_init); /* * @watch_opcode: CEPH_OSD_WATCH_OP_* */ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which, u8 watch_opcode, u64 cookie, u32 gen) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0); op->watch.cookie = cookie; op->watch.op = watch_opcode; op->watch.gen = gen; } /* * prot_ver, timeout and notify payload (may be empty) should already be * encoded in @request_pl */ static void osd_req_op_notify_init(struct ceph_osd_request *req, int which, u64 cookie, struct ceph_pagelist *request_pl) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); op->notify.cookie = cookie; ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl); op->indata_len = request_pl->length; } /* * @flags: CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, unsigned int which, u64 expected_object_size, u64 expected_write_size, u32 flags) { struct ceph_osd_req_op *op; op = osd_req_op_init(osd_req, which, CEPH_OSD_OP_SETALLOCHINT, 0); op->alloc_hint.expected_object_size = expected_object_size; op->alloc_hint.expected_write_size = expected_write_size; op->alloc_hint.flags = flags; /* * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed * not worth a feature bit. Set FAILOK per-op flag to make * sure older osds don't trip over an unsupported opcode. */ op->flags |= CEPH_OSD_OP_FLAG_FAILOK; } EXPORT_SYMBOL(osd_req_op_alloc_hint_init); static void ceph_osdc_msg_data_add(struct ceph_msg *msg, struct ceph_osd_data *osd_data) { u64 length = ceph_osd_data_length(osd_data); if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGES) { BUG_ON(length > (u64) SIZE_MAX); if (length) ceph_msg_data_add_pages(msg, osd_data->pages, length, osd_data->alignment, false); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) { BUG_ON(!length); ceph_msg_data_add_pagelist(msg, osd_data->pagelist); #ifdef CONFIG_BLOCK } else if (osd_data->type == CEPH_OSD_DATA_TYPE_BIO) { ceph_msg_data_add_bio(msg, &osd_data->bio_pos, length); #endif } else if (osd_data->type == CEPH_OSD_DATA_TYPE_BVECS) { ceph_msg_data_add_bvecs(msg, &osd_data->bvec_pos); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_ITER) { ceph_msg_data_add_iter(msg, &osd_data->iter); } else { BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_NONE); } } static u32 osd_req_encode_op(struct ceph_osd_op *dst, const struct ceph_osd_req_op *src) { switch (src->op) { case CEPH_OSD_OP_STAT: break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: case CEPH_OSD_OP_ZERO: case CEPH_OSD_OP_TRUNCATE: dst->extent.offset = cpu_to_le64(src->extent.offset); dst->extent.length = cpu_to_le64(src->extent.length); dst->extent.truncate_size = cpu_to_le64(src->extent.truncate_size); dst->extent.truncate_seq = cpu_to_le32(src->extent.truncate_seq); break; case CEPH_OSD_OP_CALL: dst->cls.class_len = src->cls.class_len; dst->cls.method_len = src->cls.method_len; dst->cls.indata_len = cpu_to_le32(src->cls.indata_len); break; case CEPH_OSD_OP_WATCH: dst->watch.cookie = cpu_to_le64(src->watch.cookie); dst->watch.ver = cpu_to_le64(0); dst->watch.op = src->watch.op; dst->watch.gen = cpu_to_le32(src->watch.gen); break; case CEPH_OSD_OP_NOTIFY_ACK: break; case CEPH_OSD_OP_NOTIFY: dst->notify.cookie = cpu_to_le64(src->notify.cookie); break; case CEPH_OSD_OP_LIST_WATCHERS: break; case CEPH_OSD_OP_SETALLOCHINT: dst->alloc_hint.expected_object_size = cpu_to_le64(src->alloc_hint.expected_object_size); dst->alloc_hint.expected_write_size = cpu_to_le64(src->alloc_hint.expected_write_size); dst->alloc_hint.flags = cpu_to_le32(src->alloc_hint.flags); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: dst->xattr.name_len = cpu_to_le32(src->xattr.name_len); dst->xattr.value_len = cpu_to_le32(src->xattr.value_len); dst->xattr.cmp_op = src->xattr.cmp_op; dst->xattr.cmp_mode = src->xattr.cmp_mode; break; case CEPH_OSD_OP_CREATE: case CEPH_OSD_OP_DELETE: break; case CEPH_OSD_OP_COPY_FROM2: dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid); dst->copy_from.src_version = cpu_to_le64(src->copy_from.src_version); dst->copy_from.flags = src->copy_from.flags; dst->copy_from.src_fadvise_flags = cpu_to_le32(src->copy_from.src_fadvise_flags); break; case CEPH_OSD_OP_ASSERT_VER: dst->assert_ver.unused = cpu_to_le64(0); dst->assert_ver.ver = cpu_to_le64(src->assert_ver.ver); break; default: pr_err("unsupported osd opcode %s\n", ceph_osd_op_name(src->op)); WARN_ON(1); return 0; } dst->op = cpu_to_le16(src->op); dst->flags = cpu_to_le32(src->flags); dst->payload_len = cpu_to_le32(src->indata_len); return src->indata_len; } /* * build new request AND message, calculate layout, and adjust file * extent as needed. * * if the file was recently truncated, we include information about its * old and new size so that the object can be updated appropriately. (we * avoid synchronously deleting truncated objects because it's slow.) */ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, struct ceph_file_layout *layout, struct ceph_vino vino, u64 off, u64 *plen, unsigned int which, int num_ops, int opcode, int flags, struct ceph_snap_context *snapc, u32 truncate_seq, u64 truncate_size, bool use_mempool) { struct ceph_osd_request *req; u64 objnum = 0; u64 objoff = 0; u64 objlen = 0; int r; BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE && opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE && opcode != CEPH_OSD_OP_SPARSE_READ); req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool, GFP_NOFS); if (!req) { r = -ENOMEM; goto fail; } /* calculate max write size */ r = calc_layout(layout, off, plen, &objnum, &objoff, &objlen); if (r) goto fail; if (opcode == CEPH_OSD_OP_CREATE || opcode == CEPH_OSD_OP_DELETE) { osd_req_op_init(req, which, opcode, 0); } else { u32 object_size = layout->object_size; u32 object_base = off - objoff; if (!(truncate_seq == 1 && truncate_size == -1ULL)) { if (truncate_size <= object_base) { truncate_size = 0; } else { truncate_size -= object_base; if (truncate_size > object_size) truncate_size = object_size; } } osd_req_op_extent_init(req, which, opcode, objoff, objlen, truncate_size, truncate_seq); } req->r_base_oloc.pool = layout->pool_id; req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns); ceph_oid_printf(&req->r_base_oid, "%llx.%08llx", vino.ino, objnum); req->r_flags = flags | osdc->client->options->read_from_replica; req->r_snapid = vino.snap; if (flags & CEPH_OSD_FLAG_WRITE) req->r_data_offset = off; if (num_ops > 1) { int num_req_ops, num_rep_ops; /* * If this is a multi-op write request, assume that we'll need * request ops. If it's a multi-op read then assume we'll need * reply ops. Anything else and call it -EINVAL. */ if (flags & CEPH_OSD_FLAG_WRITE) { num_req_ops = num_ops; num_rep_ops = 0; } else if (flags & CEPH_OSD_FLAG_READ) { num_req_ops = 0; num_rep_ops = num_ops; } else { r = -EINVAL; goto fail; } r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_req_ops, num_rep_ops); } else { r = ceph_osdc_alloc_messages(req, GFP_NOFS); } if (r) goto fail; return req; fail: ceph_osdc_put_request(req); return ERR_PTR(r); } EXPORT_SYMBOL(ceph_osdc_new_request); int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt) { op->extent.sparse_ext_cnt = cnt; op->extent.sparse_ext = kmalloc_array(cnt, sizeof(*op->extent.sparse_ext), GFP_NOFS); if (!op->extent.sparse_ext) return -ENOMEM; return 0; } EXPORT_SYMBOL(__ceph_alloc_sparse_ext_map); /* * We keep osd requests in an rbtree, sorted by ->r_tid. */ DEFINE_RB_FUNCS(request, struct ceph_osd_request, r_tid, r_node) DEFINE_RB_FUNCS(request_mc, struct ceph_osd_request, r_tid, r_mc_node) /* * Call @fn on each OSD request as long as @fn returns 0. */ static void for_each_request(struct ceph_osd_client *osdc, int (*fn)(struct ceph_osd_request *req, void *arg), void *arg) { struct rb_node *n, *p; for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); if (fn(req, arg)) return; } } for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); if (fn(req, arg)) return; } } static bool osd_homeless(struct ceph_osd *osd) { return osd->o_osd == CEPH_HOMELESS_OSD; } static bool osd_registered(struct ceph_osd *osd) { verify_osdc_locked(osd->o_osdc); return !RB_EMPTY_NODE(&osd->o_node); } /* * Assumes @osd is zero-initialized. */ static void osd_init(struct ceph_osd *osd) { refcount_set(&osd->o_ref, 1); RB_CLEAR_NODE(&osd->o_node); spin_lock_init(&osd->o_requests_lock); osd->o_requests = RB_ROOT; osd->o_linger_requests = RB_ROOT; osd->o_backoff_mappings = RB_ROOT; osd->o_backoffs_by_id = RB_ROOT; INIT_LIST_HEAD(&osd->o_osd_lru); INIT_LIST_HEAD(&osd->o_keepalive_item); osd->o_incarnation = 1; mutex_init(&osd->lock); } static void ceph_init_sparse_read(struct ceph_sparse_read *sr) { kfree(sr->sr_extent); memset(sr, '\0', sizeof(*sr)); sr->sr_state = CEPH_SPARSE_READ_HDR; } static void osd_cleanup(struct ceph_osd *osd) { WARN_ON(!RB_EMPTY_NODE(&osd->o_node)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoff_mappings)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_backoffs_by_id)); WARN_ON(!list_empty(&osd->o_osd_lru)); WARN_ON(!list_empty(&osd->o_keepalive_item)); ceph_init_sparse_read(&osd->o_sparse_read); if (osd->o_auth.authorizer) { WARN_ON(osd_homeless(osd)); ceph_auth_destroy_authorizer(osd->o_auth.authorizer); } } /* * Track open sessions with osds. */ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) { struct ceph_osd *osd; WARN_ON(onum == CEPH_HOMELESS_OSD); osd = kzalloc(sizeof(*osd), GFP_NOIO | __GFP_NOFAIL); osd_init(osd); osd->o_osdc = osdc; osd->o_osd = onum; osd->o_sparse_op_idx = -1; ceph_init_sparse_read(&osd->o_sparse_read); ceph_con_init(&osd->o_con, osd, &osd_con_ops, &osdc->client->msgr); return osd; } static struct ceph_osd *get_osd(struct ceph_osd *osd) { if (refcount_inc_not_zero(&osd->o_ref)) { dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1, refcount_read(&osd->o_ref)); return osd; } else { dout("get_osd %p FAIL\n", osd); return NULL; } } static void put_osd(struct ceph_osd *osd) { dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref), refcount_read(&osd->o_ref) - 1); if (refcount_dec_and_test(&osd->o_ref)) { osd_cleanup(osd); kfree(osd); } } DEFINE_RB_FUNCS(osd, struct ceph_osd, o_osd, o_node) static void __move_osd_to_lru(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); BUG_ON(!list_empty(&osd->o_osd_lru)); spin_lock(&osdc->osd_lru_lock); list_add_tail(&osd->o_osd_lru, &osdc->osd_lru); spin_unlock(&osdc->osd_lru_lock); osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl; } static void maybe_move_osd_to_lru(struct ceph_osd *osd) { if (RB_EMPTY_ROOT(&osd->o_requests) && RB_EMPTY_ROOT(&osd->o_linger_requests)) __move_osd_to_lru(osd); } static void __remove_osd_from_lru(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); spin_lock(&osdc->osd_lru_lock); if (!list_empty(&osd->o_osd_lru)) list_del_init(&osd->o_osd_lru); spin_unlock(&osdc->osd_lru_lock); } /* * Close the connection and assign any leftover requests to the * homeless session. */ static void close_osd(struct ceph_osd *osd) { struct ceph_osd_client *osdc = osd->o_osdc; struct rb_node *n; verify_osdc_wrlocked(osdc); dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); ceph_con_close(&osd->o_con); for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); /* unlink_request() */ dout(" reassigning req %p tid %llu\n", req, req->r_tid); unlink_request(osd, req); link_request(&osdc->homeless_osd, req); } for (n = rb_first(&osd->o_linger_requests); n; ) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); n = rb_next(n); /* unlink_linger() */ dout(" reassigning lreq %p linger_id %llu\n", lreq, lreq->linger_id); unlink_linger(osd, lreq); link_linger(&osdc->homeless_osd, lreq); } clear_backoffs(osd); __remove_osd_from_lru(osd); erase_osd(&osdc->osds, osd); put_osd(osd); } /* * reset osd connect */ static int reopen_osd(struct ceph_osd *osd) { struct ceph_entity_addr *peer_addr; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); if (RB_EMPTY_ROOT(&osd->o_requests) && RB_EMPTY_ROOT(&osd->o_linger_requests)) { close_osd(osd); return -ENODEV; } peer_addr = &osd->o_osdc->osdmap->osd_addr[osd->o_osd]; if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) && !ceph_con_opened(&osd->o_con)) { struct rb_node *n; dout("osd addr hasn't changed and connection never opened, " "letting msgr retry\n"); /* touch each r_stamp for handle_timeout()'s benfit */ for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); req->r_stamp = jiffies; } return -EAGAIN; } ceph_con_close(&osd->o_con); ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, peer_addr); osd->o_incarnation++; return 0; } static struct ceph_osd *lookup_create_osd(struct ceph_osd_client *osdc, int o, bool wrlocked) { struct ceph_osd *osd; if (wrlocked) verify_osdc_wrlocked(osdc); else verify_osdc_locked(osdc); if (o != CEPH_HOMELESS_OSD) osd = lookup_osd(&osdc->osds, o); else osd = &osdc->homeless_osd; if (!osd) { if (!wrlocked) return ERR_PTR(-EAGAIN); osd = create_osd(osdc, o); insert_osd(&osdc->osds, osd); ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, &osdc->osdmap->osd_addr[osd->o_osd]); } dout("%s osdc %p osd%d -> osd %p\n", __func__, osdc, o, osd); return osd; } /* * Create request <-> OSD session relation. * * @req has to be assigned a tid, @osd may be homeless. */ static void link_request(struct ceph_osd *osd, struct ceph_osd_request *req) { verify_osd_locked(osd); WARN_ON(!req->r_tid || req->r_osd); dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd, req, req->r_tid); if (!osd_homeless(osd)) __remove_osd_from_lru(osd); else atomic_inc(&osd->o_osdc->num_homeless); get_osd(osd); spin_lock(&osd->o_requests_lock); insert_request(&osd->o_requests, req); spin_unlock(&osd->o_requests_lock); req->r_osd = osd; } static void unlink_request(struct ceph_osd *osd, struct ceph_osd_request *req) { verify_osd_locked(osd); WARN_ON(req->r_osd != osd); dout("%s osd %p osd%d req %p tid %llu\n", __func__, osd, osd->o_osd, req, req->r_tid); req->r_osd = NULL; spin_lock(&osd->o_requests_lock); erase_request(&osd->o_requests, req); spin_unlock(&osd->o_requests_lock); put_osd(osd); if (!osd_homeless(osd)) maybe_move_osd_to_lru(osd); else atomic_dec(&osd->o_osdc->num_homeless); } static bool __pool_full(struct ceph_pg_pool_info *pi) { return pi->flags & CEPH_POOL_FLAG_FULL; } static bool have_pool_full(struct ceph_osd_client *osdc) { struct rb_node *n; for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); if (__pool_full(pi)) return true; } return false; } static bool pool_full(struct ceph_osd_client *osdc, s64 pool_id) { struct ceph_pg_pool_info *pi; pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id); if (!pi) return false; return __pool_full(pi); } /* * Returns whether a request should be blocked from being sent * based on the current osdmap and osd_client settings. */ static bool target_should_be_paused(struct ceph_osd_client *osdc, const struct ceph_osd_request_target *t, struct ceph_pg_pool_info *pi) { bool pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); bool pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || __pool_full(pi); WARN_ON(pi->id != t->target_oloc.pool); return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) || ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) || (osdc->osdmap->epoch < osdc->epoch_barrier); } static int pick_random_replica(const struct ceph_osds *acting) { int i = get_random_u32_below(acting->size); dout("%s picked osd%d, primary osd%d\n", __func__, acting->osds[i], acting->primary); return i; } /* * Picks the closest replica based on client's location given by * crush_location option. Prefers the primary if the locality is * the same. */ static int pick_closest_replica(struct ceph_osd_client *osdc, const struct ceph_osds *acting) { struct ceph_options *opt = osdc->client->options; int best_i, best_locality; int i = 0, locality; do { locality = ceph_get_crush_locality(osdc->osdmap, acting->osds[i], &opt->crush_locs); if (i == 0 || (locality >= 0 && best_locality < 0) || (locality >= 0 && best_locality >= 0 && locality < best_locality)) { best_i = i; best_locality = locality; } } while (++i < acting->size); dout("%s picked osd%d with locality %d, primary osd%d\n", __func__, acting->osds[best_i], best_locality, acting->primary); return best_i; } enum calc_target_result { CALC_TARGET_NO_ACTION = 0, CALC_TARGET_NEED_RESEND, CALC_TARGET_POOL_DNE, }; static enum calc_target_result calc_target(struct ceph_osd_client *osdc, struct ceph_osd_request_target *t, bool any_change) { struct ceph_pg_pool_info *pi; struct ceph_pg pgid, last_pgid; struct ceph_osds up, acting; bool is_read = t->flags & CEPH_OSD_FLAG_READ; bool is_write = t->flags & CEPH_OSD_FLAG_WRITE; bool force_resend = false; bool unpaused = false; bool legacy_change = false; bool split = false; bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE); bool recovery_deletes = ceph_osdmap_flag(osdc, CEPH_OSDMAP_RECOVERY_DELETES); enum calc_target_result ct_res; t->epoch = osdc->osdmap->epoch; pi = ceph_pg_pool_by_id(osdc->osdmap, t->base_oloc.pool); if (!pi) { t->osd = CEPH_HOMELESS_OSD; ct_res = CALC_TARGET_POOL_DNE; goto out; } if (osdc->osdmap->epoch == pi->last_force_request_resend) { if (t->last_force_resend < pi->last_force_request_resend) { t->last_force_resend = pi->last_force_request_resend; force_resend = true; } else if (t->last_force_resend == 0) { force_resend = true; } } /* apply tiering */ ceph_oid_copy(&t->target_oid, &t->base_oid); ceph_oloc_copy(&t->target_oloc, &t->base_oloc); if ((t->flags & CEPH_OSD_FLAG_IGNORE_OVERLAY) == 0) { if (is_read && pi->read_tier >= 0) t->target_oloc.pool = pi->read_tier; if (is_write && pi->write_tier >= 0) t->target_oloc.pool = pi->write_tier; pi = ceph_pg_pool_by_id(osdc->osdmap, t->target_oloc.pool); if (!pi) { t->osd = CEPH_HOMELESS_OSD; ct_res = CALC_TARGET_POOL_DNE; goto out; } } __ceph_object_locator_to_pg(pi, &t->target_oid, &t->target_oloc, &pgid); last_pgid.pool = pgid.pool; last_pgid.seed = ceph_stable_mod(pgid.seed, t->pg_num, t->pg_num_mask); ceph_pg_to_up_acting_osds(osdc->osdmap, pi, &pgid, &up, &acting); if (any_change && ceph_is_new_interval(&t->acting, &acting, &t->up, &up, t->size, pi->size, t->min_size, pi->min_size, t->pg_num, pi->pg_num, t->sort_bitwise, sort_bitwise, t->recovery_deletes, recovery_deletes, &last_pgid)) force_resend = true; if (t->paused && !target_should_be_paused(osdc, t, pi)) { t->paused = false; unpaused = true; } legacy_change = ceph_pg_compare(&t->pgid, &pgid) || ceph_osds_changed(&t->acting, &acting, t->used_replica || any_change); if (t->pg_num) split = ceph_pg_is_split(&last_pgid, t->pg_num, pi->pg_num); if (legacy_change || force_resend || split) { t->pgid = pgid; /* struct */ ceph_pg_to_primary_shard(osdc->osdmap, pi, &pgid, &t->spgid); ceph_osds_copy(&t->acting, &acting); ceph_osds_copy(&t->up, &up); t->size = pi->size; t->min_size = pi->min_size; t->pg_num = pi->pg_num; t->pg_num_mask = pi->pg_num_mask; t->sort_bitwise = sort_bitwise; t->recovery_deletes = recovery_deletes; if ((t->flags & (CEPH_OSD_FLAG_BALANCE_READS | CEPH_OSD_FLAG_LOCALIZE_READS)) && !is_write && pi->type == CEPH_POOL_TYPE_REP && acting.size > 1) { int pos; WARN_ON(!is_read || acting.osds[0] != acting.primary); if (t->flags & CEPH_OSD_FLAG_BALANCE_READS) { pos = pick_random_replica(&acting); } else { pos = pick_closest_replica(osdc, &acting); } t->osd = acting.osds[pos]; t->used_replica = pos > 0; } else { t->osd = acting.primary; t->used_replica = false; } } if (unpaused || legacy_change || force_resend || split) ct_res = CALC_TARGET_NEED_RESEND; else ct_res = CALC_TARGET_NO_ACTION; out: dout("%s t %p -> %d%d%d%d ct_res %d osd%d\n", __func__, t, unpaused, legacy_change, force_resend, split, ct_res, t->osd); return ct_res; } static struct ceph_spg_mapping *alloc_spg_mapping(void) { struct ceph_spg_mapping *spg; spg = kmalloc(sizeof(*spg), GFP_NOIO); if (!spg) return NULL; RB_CLEAR_NODE(&spg->node); spg->backoffs = RB_ROOT; return spg; } static void free_spg_mapping(struct ceph_spg_mapping *spg) { WARN_ON(!RB_EMPTY_NODE(&spg->node)); WARN_ON(!RB_EMPTY_ROOT(&spg->backoffs)); kfree(spg); } /* * rbtree of ceph_spg_mapping for handling map<spg_t, ...>, similar to * ceph_pg_mapping. Used to track OSD backoffs -- a backoff [range] is * defined only within a specific spgid; it does not pass anything to * children on split, or to another primary. */ DEFINE_RB_FUNCS2(spg_mapping, struct ceph_spg_mapping, spgid, ceph_spg_compare, RB_BYPTR, const struct ceph_spg *, node) static u64 hoid_get_bitwise_key(const struct ceph_hobject_id *hoid) { return hoid->is_max ? 0x100000000ull : hoid->hash_reverse_bits; } static void hoid_get_effective_key(const struct ceph_hobject_id *hoid, void **pkey, size_t *pkey_len) { if (hoid->key_len) { *pkey = hoid->key; *pkey_len = hoid->key_len; } else { *pkey = hoid->oid; *pkey_len = hoid->oid_len; } } static int compare_names(const void *name1, size_t name1_len, const void *name2, size_t name2_len) { int ret; ret = memcmp(name1, name2, min(name1_len, name2_len)); if (!ret) { if (name1_len < name2_len) ret = -1; else if (name1_len > name2_len) ret = 1; } return ret; } static int hoid_compare(const struct ceph_hobject_id *lhs, const struct ceph_hobject_id *rhs) { void *effective_key1, *effective_key2; size_t effective_key1_len, effective_key2_len; int ret; if (lhs->is_max < rhs->is_max) return -1; if (lhs->is_max > rhs->is_max) return 1; if (lhs->pool < rhs->pool) return -1; if (lhs->pool > rhs->pool) return 1; if (hoid_get_bitwise_key(lhs) < hoid_get_bitwise_key(rhs)) return -1; if (hoid_get_bitwise_key(lhs) > hoid_get_bitwise_key(rhs)) return 1; ret = compare_names(lhs->nspace, lhs->nspace_len, rhs->nspace, rhs->nspace_len); if (ret) return ret; hoid_get_effective_key(lhs, &effective_key1, &effective_key1_len); hoid_get_effective_key(rhs, &effective_key2, &effective_key2_len); ret = compare_names(effective_key1, effective_key1_len, effective_key2, effective_key2_len); if (ret) return ret; ret = compare_names(lhs->oid, lhs->oid_len, rhs->oid, rhs->oid_len); if (ret) return ret; if (lhs->snapid < rhs->snapid) return -1; if (lhs->snapid > rhs->snapid) return 1; return 0; } /* * For decoding ->begin and ->end of MOSDBackoff only -- no MIN/MAX * compat stuff here. * * Assumes @hoid is zero-initialized. */ static int decode_hoid(void **p, void *end, struct ceph_hobject_id *hoid) { u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(p, end, 4, "hobject_t", &struct_v, &struct_len); if (ret) return ret; if (struct_v < 4) { pr_err("got struct_v %d < 4 of hobject_t\n", struct_v); goto e_inval; } hoid->key = ceph_extract_encoded_string(p, end, &hoid->key_len, GFP_NOIO); if (IS_ERR(hoid->key)) { ret = PTR_ERR(hoid->key); hoid->key = NULL; return ret; } hoid->oid = ceph_extract_encoded_string(p, end, &hoid->oid_len, GFP_NOIO); if (IS_ERR(hoid->oid)) { ret = PTR_ERR(hoid->oid); hoid->oid = NULL; return ret; } ceph_decode_64_safe(p, end, hoid->snapid, e_inval); ceph_decode_32_safe(p, end, hoid->hash, e_inval); ceph_decode_8_safe(p, end, hoid->is_max, e_inval); hoid->nspace = ceph_extract_encoded_string(p, end, &hoid->nspace_len, GFP_NOIO); if (IS_ERR(hoid->nspace)) { ret = PTR_ERR(hoid->nspace); hoid->nspace = NULL; return ret; } ceph_decode_64_safe(p, end, hoid->pool, e_inval); ceph_hoid_build_hash_cache(hoid); return 0; e_inval: return -EINVAL; } static int hoid_encoding_size(const struct ceph_hobject_id *hoid) { return 8 + 4 + 1 + 8 + /* snapid, hash, is_max, pool */ 4 + hoid->key_len + 4 + hoid->oid_len + 4 + hoid->nspace_len; } static void encode_hoid(void **p, void *end, const struct ceph_hobject_id *hoid) { ceph_start_encoding(p, 4, 3, hoid_encoding_size(hoid)); ceph_encode_string(p, end, hoid->key, hoid->key_len); ceph_encode_string(p, end, hoid->oid, hoid->oid_len); ceph_encode_64(p, hoid->snapid); ceph_encode_32(p, hoid->hash); ceph_encode_8(p, hoid->is_max); ceph_encode_string(p, end, hoid->nspace, hoid->nspace_len); ceph_encode_64(p, hoid->pool); } static void free_hoid(struct ceph_hobject_id *hoid) { if (hoid) { kfree(hoid->key); kfree(hoid->oid); kfree(hoid->nspace); kfree(hoid); } } static struct ceph_osd_backoff *alloc_backoff(void) { struct ceph_osd_backoff *backoff; backoff = kzalloc(sizeof(*backoff), GFP_NOIO); if (!backoff) return NULL; RB_CLEAR_NODE(&backoff->spg_node); RB_CLEAR_NODE(&backoff->id_node); return backoff; } static void free_backoff(struct ceph_osd_backoff *backoff) { WARN_ON(!RB_EMPTY_NODE(&backoff->spg_node)); WARN_ON(!RB_EMPTY_NODE(&backoff->id_node)); free_hoid(backoff->begin); free_hoid(backoff->end); kfree(backoff); } /* * Within a specific spgid, backoffs are managed by ->begin hoid. */ DEFINE_RB_INSDEL_FUNCS2(backoff, struct ceph_osd_backoff, begin, hoid_compare, RB_BYVAL, spg_node); static struct ceph_osd_backoff *lookup_containing_backoff(struct rb_root *root, const struct ceph_hobject_id *hoid) { struct rb_node *n = root->rb_node; while (n) { struct ceph_osd_backoff *cur = rb_entry(n, struct ceph_osd_backoff, spg_node); int cmp; cmp = hoid_compare(hoid, cur->begin); if (cmp < 0) { n = n->rb_left; } else if (cmp > 0) { if (hoid_compare(hoid, cur->end) < 0) return cur; n = n->rb_right; } else { return cur; } } return NULL; } /* * Each backoff has a unique id within its OSD session. */ DEFINE_RB_FUNCS(backoff_by_id, struct ceph_osd_backoff, id, id_node) static void clear_backoffs(struct ceph_osd *osd) { while (!RB_EMPTY_ROOT(&osd->o_backoff_mappings)) { struct ceph_spg_mapping *spg = rb_entry(rb_first(&osd->o_backoff_mappings), struct ceph_spg_mapping, node); while (!RB_EMPTY_ROOT(&spg->backoffs)) { struct ceph_osd_backoff *backoff = rb_entry(rb_first(&spg->backoffs), struct ceph_osd_backoff, spg_node); erase_backoff(&spg->backoffs, backoff); erase_backoff_by_id(&osd->o_backoffs_by_id, backoff); free_backoff(backoff); } erase_spg_mapping(&osd->o_backoff_mappings, spg); free_spg_mapping(spg); } } /* * Set up a temporary, non-owning view into @t. */ static void hoid_fill_from_target(struct ceph_hobject_id *hoid, const struct ceph_osd_request_target *t) { hoid->key = NULL; hoid->key_len = 0; hoid->oid = t->target_oid.name; hoid->oid_len = t->target_oid.name_len; hoid->snapid = CEPH_NOSNAP; hoid->hash = t->pgid.seed; hoid->is_max = false; if (t->target_oloc.pool_ns) { hoid->nspace = t->target_oloc.pool_ns->str; hoid->nspace_len = t->target_oloc.pool_ns->len; } else { hoid->nspace = NULL; hoid->nspace_len = 0; } hoid->pool = t->target_oloc.pool; ceph_hoid_build_hash_cache(hoid); } static bool should_plug_request(struct ceph_osd_request *req) { struct ceph_osd *osd = req->r_osd; struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct ceph_hobject_id hoid; spg = lookup_spg_mapping(&osd->o_backoff_mappings, &req->r_t.spgid); if (!spg) return false; hoid_fill_from_target(&hoid, &req->r_t); backoff = lookup_containing_backoff(&spg->backoffs, &hoid); if (!backoff) return false; dout("%s req %p tid %llu backoff osd%d spgid %llu.%xs%d id %llu\n", __func__, req, req->r_tid, osd->o_osd, backoff->spgid.pgid.pool, backoff->spgid.pgid.seed, backoff->spgid.shard, backoff->id); return true; } /* * Keep get_num_data_items() in sync with this function. */ static void setup_request_data(struct ceph_osd_request *req) { struct ceph_msg *request_msg = req->r_request; struct ceph_msg *reply_msg = req->r_reply; struct ceph_osd_req_op *op; if (req->r_request->num_data_items || req->r_reply->num_data_items) return; WARN_ON(request_msg->data_length || reply_msg->data_length); for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) { switch (op->op) { /* request */ case CEPH_OSD_OP_WRITE: case CEPH_OSD_OP_WRITEFULL: WARN_ON(op->indata_len != op->extent.length); ceph_osdc_msg_data_add(request_msg, &op->extent.osd_data); break; case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: WARN_ON(op->indata_len != op->xattr.name_len + op->xattr.value_len); ceph_osdc_msg_data_add(request_msg, &op->xattr.osd_data); break; case CEPH_OSD_OP_NOTIFY_ACK: ceph_osdc_msg_data_add(request_msg, &op->notify_ack.request_data); break; case CEPH_OSD_OP_COPY_FROM2: ceph_osdc_msg_data_add(request_msg, &op->copy_from.osd_data); break; /* reply */ case CEPH_OSD_OP_STAT: ceph_osdc_msg_data_add(reply_msg, &op->raw_data_in); break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_SPARSE_READ: ceph_osdc_msg_data_add(reply_msg, &op->extent.osd_data); break; case CEPH_OSD_OP_LIST_WATCHERS: ceph_osdc_msg_data_add(reply_msg, &op->list_watchers.response_data); break; /* both */ case CEPH_OSD_OP_CALL: WARN_ON(op->indata_len != op->cls.class_len + op->cls.method_len + op->cls.indata_len); ceph_osdc_msg_data_add(request_msg, &op->cls.request_info); /* optional, can be NONE */ ceph_osdc_msg_data_add(request_msg, &op->cls.request_data); /* optional, can be NONE */ ceph_osdc_msg_data_add(reply_msg, &op->cls.response_data); break; case CEPH_OSD_OP_NOTIFY: ceph_osdc_msg_data_add(request_msg, &op->notify.request_data); ceph_osdc_msg_data_add(reply_msg, &op->notify.response_data); break; } } } static void encode_pgid(void **p, const struct ceph_pg *pgid) { ceph_encode_8(p, 1); ceph_encode_64(p, pgid->pool); ceph_encode_32(p, pgid->seed); ceph_encode_32(p, -1); /* preferred */ } static void encode_spgid(void **p, const struct ceph_spg *spgid) { ceph_start_encoding(p, 1, 1, CEPH_PGID_ENCODING_LEN + 1); encode_pgid(p, &spgid->pgid); ceph_encode_8(p, spgid->shard); } static void encode_oloc(void **p, void *end, const struct ceph_object_locator *oloc) { ceph_start_encoding(p, 5, 4, ceph_oloc_encoding_size(oloc)); ceph_encode_64(p, oloc->pool); ceph_encode_32(p, -1); /* preferred */ ceph_encode_32(p, 0); /* key len */ if (oloc->pool_ns) ceph_encode_string(p, end, oloc->pool_ns->str, oloc->pool_ns->len); else ceph_encode_32(p, 0); } static void encode_request_partial(struct ceph_osd_request *req, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front_alloc_len; u32 data_len = 0; int i; if (req->r_flags & CEPH_OSD_FLAG_WRITE) { /* snapshots aren't writeable */ WARN_ON(req->r_snapid != CEPH_NOSNAP); } else { WARN_ON(req->r_mtime.tv_sec || req->r_mtime.tv_nsec || req->r_data_offset || req->r_snapc); } setup_request_data(req); encode_spgid(&p, &req->r_t.spgid); /* actual spg */ ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */ ceph_encode_32(&p, req->r_osdc->osdmap->epoch); ceph_encode_32(&p, req->r_flags); /* reqid */ ceph_start_encoding(&p, 2, 2, sizeof(struct ceph_osd_reqid)); memset(p, 0, sizeof(struct ceph_osd_reqid)); p += sizeof(struct ceph_osd_reqid); /* trace */ memset(p, 0, sizeof(struct ceph_blkin_trace_info)); p += sizeof(struct ceph_blkin_trace_info); ceph_encode_32(&p, 0); /* client_inc, always 0 */ ceph_encode_timespec64(p, &req->r_mtime); p += sizeof(struct ceph_timespec); encode_oloc(&p, end, &req->r_t.target_oloc); ceph_encode_string(&p, end, req->r_t.target_oid.name, req->r_t.target_oid.name_len); /* ops, can imply data */ ceph_encode_16(&p, req->r_num_ops); for (i = 0; i < req->r_num_ops; i++) { data_len += osd_req_encode_op(p, &req->r_ops[i]); p += sizeof(struct ceph_osd_op); } ceph_encode_64(&p, req->r_snapid); /* snapid */ if (req->r_snapc) { ceph_encode_64(&p, req->r_snapc->seq); ceph_encode_32(&p, req->r_snapc->num_snaps); for (i = 0; i < req->r_snapc->num_snaps; i++) ceph_encode_64(&p, req->r_snapc->snaps[i]); } else { ceph_encode_64(&p, 0); /* snap_seq */ ceph_encode_32(&p, 0); /* snaps len */ } ceph_encode_32(&p, req->r_attempts); /* retry_attempt */ BUG_ON(p > end - 8); /* space for features */ msg->hdr.version = cpu_to_le16(8); /* MOSDOp v8 */ /* front_len is finalized in encode_request_finish() */ msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); msg->hdr.data_len = cpu_to_le32(data_len); /* * The header "data_off" is a hint to the receiver allowing it * to align received data into its buffers such that there's no * need to re-copy it before writing it to disk (direct I/O). */ msg->hdr.data_off = cpu_to_le16(req->r_data_offset); dout("%s req %p msg %p oid %s oid_len %d\n", __func__, req, msg, req->r_t.target_oid.name, req->r_t.target_oid.name_len); } static void encode_request_finish(struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const partial_end = p + msg->front.iov_len; void *const end = p + msg->front_alloc_len; if (CEPH_HAVE_FEATURE(msg->con->peer_features, RESEND_ON_SPLIT)) { /* luminous OSD -- encode features and be done */ p = partial_end; ceph_encode_64(&p, msg->con->peer_features); } else { struct { char spgid[CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1]; __le32 hash; __le32 epoch; __le32 flags; char reqid[CEPH_ENCODING_START_BLK_LEN + sizeof(struct ceph_osd_reqid)]; char trace[sizeof(struct ceph_blkin_trace_info)]; __le32 client_inc; struct ceph_timespec mtime; } __packed head; struct ceph_pg pgid; void *oloc, *oid, *tail; int oloc_len, oid_len, tail_len; int len; /* * Pre-luminous OSD -- reencode v8 into v4 using @head * as a temporary buffer. Encode the raw PG; the rest * is just a matter of moving oloc, oid and tail blobs * around. */ memcpy(&head, p, sizeof(head)); p += sizeof(head); oloc = p; p += CEPH_ENCODING_START_BLK_LEN; pgid.pool = ceph_decode_64(&p); p += 4 + 4; /* preferred, key len */ len = ceph_decode_32(&p); p += len; /* nspace */ oloc_len = p - oloc; oid = p; len = ceph_decode_32(&p); p += len; oid_len = p - oid; tail = p; tail_len = partial_end - p; p = msg->front.iov_base; ceph_encode_copy(&p, &head.client_inc, sizeof(head.client_inc)); ceph_encode_copy(&p, &head.epoch, sizeof(head.epoch)); ceph_encode_copy(&p, &head.flags, sizeof(head.flags)); ceph_encode_copy(&p, &head.mtime, sizeof(head.mtime)); /* reassert_version */ memset(p, 0, sizeof(struct ceph_eversion)); p += sizeof(struct ceph_eversion); BUG_ON(p >= oloc); memmove(p, oloc, oloc_len); p += oloc_len; pgid.seed = le32_to_cpu(head.hash); encode_pgid(&p, &pgid); /* raw pg */ BUG_ON(p >= oid); memmove(p, oid, oid_len); p += oid_len; /* tail -- ops, snapid, snapc, retry_attempt */ BUG_ON(p >= tail); memmove(p, tail, tail_len); p += tail_len; msg->hdr.version = cpu_to_le16(4); /* MOSDOp v4 */ } BUG_ON(p > end); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); dout("%s msg %p tid %llu %u+%u+%u v%d\n", __func__, msg, le64_to_cpu(msg->hdr.tid), le32_to_cpu(msg->hdr.front_len), le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len), le16_to_cpu(msg->hdr.version)); } /* * @req has to be assigned a tid and registered. */ static void send_request(struct ceph_osd_request *req) { struct ceph_osd *osd = req->r_osd; verify_osd_locked(osd); WARN_ON(osd->o_osd != req->r_t.osd); /* backoff? */ if (should_plug_request(req)) return; /* * We may have a previously queued request message hanging * around. Cancel it to avoid corrupting the msgr. */ if (req->r_sent) ceph_msg_revoke(req->r_request); req->r_flags |= CEPH_OSD_FLAG_KNOWN_REDIR; if (req->r_attempts) req->r_flags |= CEPH_OSD_FLAG_RETRY; else WARN_ON(req->r_flags & CEPH_OSD_FLAG_RETRY); encode_request_partial(req, req->r_request); dout("%s req %p tid %llu to pgid %llu.%x spgid %llu.%xs%d osd%d e%u flags 0x%x attempt %d\n", __func__, req, req->r_tid, req->r_t.pgid.pool, req->r_t.pgid.seed, req->r_t.spgid.pgid.pool, req->r_t.spgid.pgid.seed, req->r_t.spgid.shard, osd->o_osd, req->r_t.epoch, req->r_flags, req->r_attempts); req->r_t.paused = false; req->r_stamp = jiffies; req->r_attempts++; req->r_sent = osd->o_incarnation; req->r_request->hdr.tid = cpu_to_le64(req->r_tid); ceph_con_send(&osd->o_con, ceph_msg_get(req->r_request)); } static void maybe_request_map(struct ceph_osd_client *osdc) { bool continuous = false; verify_osdc_locked(osdc); WARN_ON(!osdc->osdmap->epoch); if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) { dout("%s osdc %p continuous\n", __func__, osdc); continuous = true; } else { dout("%s osdc %p onetime\n", __func__, osdc); } if (ceph_monc_want_map(&osdc->client->monc, CEPH_SUB_OSDMAP, osdc->osdmap->epoch + 1, continuous)) ceph_monc_renew_subs(&osdc->client->monc); } static void complete_request(struct ceph_osd_request *req, int err); static void send_map_check(struct ceph_osd_request *req); static void __submit_request(struct ceph_osd_request *req, bool wrlocked) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd *osd; enum calc_target_result ct_res; int err = 0; bool need_send = false; bool promoted = false; WARN_ON(req->r_tid); dout("%s req %p wrlocked %d\n", __func__, req, wrlocked); again: ct_res = calc_target(osdc, &req->r_t, false); if (ct_res == CALC_TARGET_POOL_DNE && !wrlocked) goto promote; osd = lookup_create_osd(osdc, req->r_t.osd, wrlocked); if (IS_ERR(osd)) { WARN_ON(PTR_ERR(osd) != -EAGAIN || wrlocked); goto promote; } if (osdc->abort_err) { dout("req %p abort_err %d\n", req, osdc->abort_err); err = osdc->abort_err; } else if (osdc->osdmap->epoch < osdc->epoch_barrier) { dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch, osdc->epoch_barrier); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) { dout("req %p pausewr\n", req); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_READ) && ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("req %p pauserd\n", req); req->r_t.paused = true; maybe_request_map(osdc); } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && !(req->r_flags & (CEPH_OSD_FLAG_FULL_TRY | CEPH_OSD_FLAG_FULL_FORCE)) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || pool_full(osdc, req->r_t.base_oloc.pool))) { dout("req %p full/pool_full\n", req); if (ceph_test_opt(osdc->client, ABORT_ON_FULL)) { err = -ENOSPC; } else { if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) pr_warn_ratelimited("cluster is full (osdmap FULL)\n"); else pr_warn_ratelimited("pool %lld is full or reached quota\n", req->r_t.base_oloc.pool); req->r_t.paused = true; maybe_request_map(osdc); } } else if (!osd_homeless(osd)) { need_send = true; } else { maybe_request_map(osdc); } mutex_lock(&osd->lock); /* * Assign the tid atomically with send_request() to protect * multiple writes to the same object from racing with each * other, resulting in out of order ops on the OSDs. */ req->r_tid = atomic64_inc_return(&osdc->last_tid); link_request(osd, req); if (need_send) send_request(req); else if (err) complete_request(req, err); mutex_unlock(&osd->lock); if (!err && ct_res == CALC_TARGET_POOL_DNE) send_map_check(req); if (promoted) downgrade_write(&osdc->lock); return; promote: up_read(&osdc->lock); down_write(&osdc->lock); wrlocked = true; promoted = true; goto again; } static void account_request(struct ceph_osd_request *req) { WARN_ON(req->r_flags & (CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK)); WARN_ON(!(req->r_flags & (CEPH_OSD_FLAG_READ | CEPH_OSD_FLAG_WRITE))); req->r_flags |= CEPH_OSD_FLAG_ONDISK; atomic_inc(&req->r_osdc->num_requests); req->r_start_stamp = jiffies; req->r_start_latency = ktime_get(); } static void submit_request(struct ceph_osd_request *req, bool wrlocked) { ceph_osdc_get_request(req); account_request(req); __submit_request(req, wrlocked); } static void finish_request(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; WARN_ON(lookup_request_mc(&osdc->map_checks, req->r_tid)); dout("%s req %p tid %llu\n", __func__, req, req->r_tid); req->r_end_latency = ktime_get(); if (req->r_osd) { ceph_init_sparse_read(&req->r_osd->o_sparse_read); unlink_request(req->r_osd, req); } atomic_dec(&osdc->num_requests); /* * If an OSD has failed or returned and a request has been sent * twice, it's possible to get a reply and end up here while the * request message is queued for delivery. We will ignore the * reply, so not a big deal, but better to try and catch it. */ ceph_msg_revoke(req->r_request); ceph_msg_revoke_incoming(req->r_reply); } static void __complete_request(struct ceph_osd_request *req) { dout("%s req %p tid %llu cb %ps result %d\n", __func__, req, req->r_tid, req->r_callback, req->r_result); if (req->r_callback) req->r_callback(req); complete_all(&req->r_completion); ceph_osdc_put_request(req); } static void complete_request_workfn(struct work_struct *work) { struct ceph_osd_request *req = container_of(work, struct ceph_osd_request, r_complete_work); __complete_request(req); } /* * This is open-coded in handle_reply(). */ static void complete_request(struct ceph_osd_request *req, int err) { dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); req->r_result = err; finish_request(req); INIT_WORK(&req->r_complete_work, complete_request_workfn); queue_work(req->r_osdc->completion_wq, &req->r_complete_work); } static void cancel_map_check(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd_request *lookup_req; verify_osdc_wrlocked(osdc); lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid); if (!lookup_req) return; WARN_ON(lookup_req != req); erase_request_mc(&osdc->map_checks, req); ceph_osdc_put_request(req); } static void cancel_request(struct ceph_osd_request *req) { dout("%s req %p tid %llu\n", __func__, req, req->r_tid); cancel_map_check(req); finish_request(req); complete_all(&req->r_completion); ceph_osdc_put_request(req); } static void abort_request(struct ceph_osd_request *req, int err) { dout("%s req %p tid %llu err %d\n", __func__, req, req->r_tid, err); cancel_map_check(req); complete_request(req, err); } static int abort_fn(struct ceph_osd_request *req, void *arg) { int err = *(int *)arg; abort_request(req, err); return 0; /* continue iteration */ } /* * Abort all in-flight requests with @err and arrange for all future * requests to be failed immediately. */ void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err) { dout("%s osdc %p err %d\n", __func__, osdc, err); down_write(&osdc->lock); for_each_request(osdc, abort_fn, &err); osdc->abort_err = err; up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_abort_requests); void ceph_osdc_clear_abort_err(struct ceph_osd_client *osdc) { down_write(&osdc->lock); osdc->abort_err = 0; up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_clear_abort_err); static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb) { if (likely(eb > osdc->epoch_barrier)) { dout("updating epoch_barrier from %u to %u\n", osdc->epoch_barrier, eb); osdc->epoch_barrier = eb; /* Request map if we're not to the barrier yet */ if (eb > osdc->osdmap->epoch) maybe_request_map(osdc); } } void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb) { down_read(&osdc->lock); if (unlikely(eb > osdc->epoch_barrier)) { up_read(&osdc->lock); down_write(&osdc->lock); update_epoch_barrier(osdc, eb); up_write(&osdc->lock); } else { up_read(&osdc->lock); } } EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier); /* * We can end up releasing caps as a result of abort_request(). * In that case, we probably want to ensure that the cap release message * has an updated epoch barrier in it, so set the epoch barrier prior to * aborting the first request. */ static int abort_on_full_fn(struct ceph_osd_request *req, void *arg) { struct ceph_osd_client *osdc = req->r_osdc; bool *victims = arg; if ((req->r_flags & CEPH_OSD_FLAG_WRITE) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || pool_full(osdc, req->r_t.base_oloc.pool))) { if (!*victims) { update_epoch_barrier(osdc, osdc->osdmap->epoch); *victims = true; } abort_request(req, -ENOSPC); } return 0; /* continue iteration */ } /* * Drop all pending requests that are stalled waiting on a full condition to * clear, and complete them with ENOSPC as the return code. Set the * osdc->epoch_barrier to the latest map epoch that we've seen if any were * cancelled. */ static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc) { bool victims = false; if (ceph_test_opt(osdc->client, ABORT_ON_FULL) && (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc))) for_each_request(osdc, abort_on_full_fn, &victims); } static void check_pool_dne(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osdmap *map = osdc->osdmap; verify_osdc_wrlocked(osdc); WARN_ON(!map->epoch); if (req->r_attempts) { /* * We sent a request earlier, which means that * previously the pool existed, and now it does not * (i.e., it was deleted). */ req->r_map_dne_bound = map->epoch; dout("%s req %p tid %llu pool disappeared\n", __func__, req, req->r_tid); } else { dout("%s req %p tid %llu map_dne_bound %u have %u\n", __func__, req, req->r_tid, req->r_map_dne_bound, map->epoch); } if (req->r_map_dne_bound) { if (map->epoch >= req->r_map_dne_bound) { /* we had a new enough map */ pr_info_ratelimited("tid %llu pool does not exist\n", req->r_tid); complete_request(req, -ENOENT); } } else { send_map_check(req); } } static void map_check_cb(struct ceph_mon_generic_request *greq) { struct ceph_osd_client *osdc = &greq->monc->client->osdc; struct ceph_osd_request *req; u64 tid = greq->private_data; WARN_ON(greq->result || !greq->u.newest); down_write(&osdc->lock); req = lookup_request_mc(&osdc->map_checks, tid); if (!req) { dout("%s tid %llu dne\n", __func__, tid); goto out_unlock; } dout("%s req %p tid %llu map_dne_bound %u newest %llu\n", __func__, req, req->r_tid, req->r_map_dne_bound, greq->u.newest); if (!req->r_map_dne_bound) req->r_map_dne_bound = greq->u.newest; erase_request_mc(&osdc->map_checks, req); check_pool_dne(req); ceph_osdc_put_request(req); out_unlock: up_write(&osdc->lock); } static void send_map_check(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_osd_request *lookup_req; int ret; verify_osdc_wrlocked(osdc); lookup_req = lookup_request_mc(&osdc->map_checks, req->r_tid); if (lookup_req) { WARN_ON(lookup_req != req); return; } ceph_osdc_get_request(req); insert_request_mc(&osdc->map_checks, req); ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap", map_check_cb, req->r_tid); WARN_ON(ret); } /* * lingering requests, watch/notify v2 infrastructure */ static void linger_release(struct kref *kref) { struct ceph_osd_linger_request *lreq = container_of(kref, struct ceph_osd_linger_request, kref); dout("%s lreq %p reg_req %p ping_req %p\n", __func__, lreq, lreq->reg_req, lreq->ping_req); WARN_ON(!RB_EMPTY_NODE(&lreq->node)); WARN_ON(!RB_EMPTY_NODE(&lreq->osdc_node)); WARN_ON(!RB_EMPTY_NODE(&lreq->mc_node)); WARN_ON(!list_empty(&lreq->scan_item)); WARN_ON(!list_empty(&lreq->pending_lworks)); WARN_ON(lreq->osd); if (lreq->request_pl) ceph_pagelist_release(lreq->request_pl); if (lreq->notify_id_pages) ceph_release_page_vector(lreq->notify_id_pages, 1); ceph_osdc_put_request(lreq->reg_req); ceph_osdc_put_request(lreq->ping_req); target_destroy(&lreq->t); kfree(lreq); } static void linger_put(struct ceph_osd_linger_request *lreq) { if (lreq) kref_put(&lreq->kref, linger_release); } static struct ceph_osd_linger_request * linger_get(struct ceph_osd_linger_request *lreq) { kref_get(&lreq->kref); return lreq; } static struct ceph_osd_linger_request * linger_alloc(struct ceph_osd_client *osdc) { struct ceph_osd_linger_request *lreq; lreq = kzalloc(sizeof(*lreq), GFP_NOIO); if (!lreq) return NULL; kref_init(&lreq->kref); mutex_init(&lreq->lock); RB_CLEAR_NODE(&lreq->node); RB_CLEAR_NODE(&lreq->osdc_node); RB_CLEAR_NODE(&lreq->mc_node); INIT_LIST_HEAD(&lreq->scan_item); INIT_LIST_HEAD(&lreq->pending_lworks); init_completion(&lreq->reg_commit_wait); init_completion(&lreq->notify_finish_wait); lreq->osdc = osdc; target_init(&lreq->t); dout("%s lreq %p\n", __func__, lreq); return lreq; } DEFINE_RB_INSDEL_FUNCS(linger, struct ceph_osd_linger_request, linger_id, node) DEFINE_RB_FUNCS(linger_osdc, struct ceph_osd_linger_request, linger_id, osdc_node) DEFINE_RB_FUNCS(linger_mc, struct ceph_osd_linger_request, linger_id, mc_node) /* * Create linger request <-> OSD session relation. * * @lreq has to be registered, @osd may be homeless. */ static void link_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq) { verify_osd_locked(osd); WARN_ON(!lreq->linger_id || lreq->osd); dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd, osd->o_osd, lreq, lreq->linger_id); if (!osd_homeless(osd)) __remove_osd_from_lru(osd); else atomic_inc(&osd->o_osdc->num_homeless); get_osd(osd); insert_linger(&osd->o_linger_requests, lreq); lreq->osd = osd; } static void unlink_linger(struct ceph_osd *osd, struct ceph_osd_linger_request *lreq) { verify_osd_locked(osd); WARN_ON(lreq->osd != osd); dout("%s osd %p osd%d lreq %p linger_id %llu\n", __func__, osd, osd->o_osd, lreq, lreq->linger_id); lreq->osd = NULL; erase_linger(&osd->o_linger_requests, lreq); put_osd(osd); if (!osd_homeless(osd)) maybe_move_osd_to_lru(osd); else atomic_dec(&osd->o_osdc->num_homeless); } static bool __linger_registered(struct ceph_osd_linger_request *lreq) { verify_osdc_locked(lreq->osdc); return !RB_EMPTY_NODE(&lreq->osdc_node); } static bool linger_registered(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; bool registered; down_read(&osdc->lock); registered = __linger_registered(lreq); up_read(&osdc->lock); return registered; } static void linger_register(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; verify_osdc_wrlocked(osdc); WARN_ON(lreq->linger_id); linger_get(lreq); lreq->linger_id = ++osdc->last_linger_id; insert_linger_osdc(&osdc->linger_requests, lreq); } static void linger_unregister(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; verify_osdc_wrlocked(osdc); erase_linger_osdc(&osdc->linger_requests, lreq); linger_put(lreq); } static void cancel_linger_request(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; WARN_ON(!req->r_linger); cancel_request(req); linger_put(lreq); } struct linger_work { struct work_struct work; struct ceph_osd_linger_request *lreq; struct list_head pending_item; unsigned long queued_stamp; union { struct { u64 notify_id; u64 notifier_id; void *payload; /* points into @msg front */ size_t payload_len; struct ceph_msg *msg; /* for ceph_msg_put() */ } notify; struct { int err; } error; }; }; static struct linger_work *lwork_alloc(struct ceph_osd_linger_request *lreq, work_func_t workfn) { struct linger_work *lwork; lwork = kzalloc(sizeof(*lwork), GFP_NOIO); if (!lwork) return NULL; INIT_WORK(&lwork->work, workfn); INIT_LIST_HEAD(&lwork->pending_item); lwork->lreq = linger_get(lreq); return lwork; } static void lwork_free(struct linger_work *lwork) { struct ceph_osd_linger_request *lreq = lwork->lreq; mutex_lock(&lreq->lock); list_del(&lwork->pending_item); mutex_unlock(&lreq->lock); linger_put(lreq); kfree(lwork); } static void lwork_queue(struct linger_work *lwork) { struct ceph_osd_linger_request *lreq = lwork->lreq; struct ceph_osd_client *osdc = lreq->osdc; verify_lreq_locked(lreq); WARN_ON(!list_empty(&lwork->pending_item)); lwork->queued_stamp = jiffies; list_add_tail(&lwork->pending_item, &lreq->pending_lworks); queue_work(osdc->notify_wq, &lwork->work); } static void do_watch_notify(struct work_struct *w) { struct linger_work *lwork = container_of(w, struct linger_work, work); struct ceph_osd_linger_request *lreq = lwork->lreq; if (!linger_registered(lreq)) { dout("%s lreq %p not registered\n", __func__, lreq); goto out; } WARN_ON(!lreq->is_watch); dout("%s lreq %p notify_id %llu notifier_id %llu payload_len %zu\n", __func__, lreq, lwork->notify.notify_id, lwork->notify.notifier_id, lwork->notify.payload_len); lreq->wcb(lreq->data, lwork->notify.notify_id, lreq->linger_id, lwork->notify.notifier_id, lwork->notify.payload, lwork->notify.payload_len); out: ceph_msg_put(lwork->notify.msg); lwork_free(lwork); } static void do_watch_error(struct work_struct *w) { struct linger_work *lwork = container_of(w, struct linger_work, work); struct ceph_osd_linger_request *lreq = lwork->lreq; if (!linger_registered(lreq)) { dout("%s lreq %p not registered\n", __func__, lreq); goto out; } dout("%s lreq %p err %d\n", __func__, lreq, lwork->error.err); lreq->errcb(lreq->data, lreq->linger_id, lwork->error.err); out: lwork_free(lwork); } static void queue_watch_error(struct ceph_osd_linger_request *lreq) { struct linger_work *lwork; lwork = lwork_alloc(lreq, do_watch_error); if (!lwork) { pr_err("failed to allocate error-lwork\n"); return; } lwork->error.err = lreq->last_error; lwork_queue(lwork); } static void linger_reg_commit_complete(struct ceph_osd_linger_request *lreq, int result) { if (!completion_done(&lreq->reg_commit_wait)) { lreq->reg_commit_error = (result <= 0 ? result : 0); complete_all(&lreq->reg_commit_wait); } } static void linger_commit_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->reg_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->reg_req); goto out; } dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq, lreq->linger_id, req->r_result); linger_reg_commit_complete(lreq, req->r_result); lreq->committed = true; if (!lreq->is_watch) { struct ceph_osd_data *osd_data = osd_req_op_data(req, 0, notify, response_data); void *p = page_address(osd_data->pages[0]); WARN_ON(req->r_ops[0].op != CEPH_OSD_OP_NOTIFY || osd_data->type != CEPH_OSD_DATA_TYPE_PAGES); /* make note of the notify_id */ if (req->r_ops[0].outdata_len >= sizeof(u64)) { lreq->notify_id = ceph_decode_64(&p); dout("lreq %p notify_id %llu\n", lreq, lreq->notify_id); } else { dout("lreq %p no notify_id\n", lreq); } } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static int normalize_watch_error(int err) { /* * Translate ENOENT -> ENOTCONN so that a delete->disconnection * notification and a failure to reconnect because we raced with * the delete appear the same to the user. */ if (err == -ENOENT) err = -ENOTCONN; return err; } static void linger_reconnect_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->reg_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->reg_req); goto out; } dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->last_error); if (req->r_result < 0) { if (!lreq->last_error) { lreq->last_error = normalize_watch_error(req->r_result); queue_watch_error(lreq); } } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_request *req; int ret; verify_osdc_wrlocked(osdc); mutex_lock(&lreq->lock); dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); if (lreq->reg_req) { if (lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); ceph_osdc_put_request(lreq->reg_req); } req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); BUG_ON(!req); target_copy(&req->r_t, &lreq->t); req->r_mtime = lreq->mtime; if (lreq->is_watch && lreq->committed) { osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT, lreq->linger_id, ++lreq->register_gen); dout("lreq %p reconnect register_gen %u\n", lreq, req->r_ops[0].watch.gen); req->r_callback = linger_reconnect_cb; } else { if (lreq->is_watch) { osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH, lreq->linger_id, 0); } else { lreq->notify_id = 0; refcount_inc(&lreq->request_pl->refcnt); osd_req_op_notify_init(req, 0, lreq->linger_id, lreq->request_pl); ceph_osd_data_pages_init( osd_req_op_data(req, 0, notify, response_data), lreq->notify_id_pages, PAGE_SIZE, 0, false, false); } dout("lreq %p register\n", lreq); req->r_callback = linger_commit_cb; } ret = ceph_osdc_alloc_messages(req, GFP_NOIO); BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; lreq->reg_req = req; mutex_unlock(&lreq->lock); submit_request(req, true); } static void linger_ping_cb(struct ceph_osd_request *req) { struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); if (req != lreq->ping_req) { dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", __func__, lreq, lreq->linger_id, req, lreq->ping_req); goto out; } dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent, lreq->last_error); if (lreq->register_gen == req->r_ops[0].watch.gen) { if (!req->r_result) { lreq->watch_valid_thru = lreq->ping_sent; } else if (!lreq->last_error) { lreq->last_error = normalize_watch_error(req->r_result); queue_watch_error(lreq); } } else { dout("lreq %p register_gen %u ignoring old pong %u\n", lreq, lreq->register_gen, req->r_ops[0].watch.gen); } out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger_ping(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_request *req; int ret; if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("%s PAUSERD\n", __func__); return; } lreq->ping_sent = jiffies; dout("%s lreq %p linger_id %llu ping_sent %lu register_gen %u\n", __func__, lreq, lreq->linger_id, lreq->ping_sent, lreq->register_gen); if (lreq->ping_req) { if (lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); ceph_osdc_put_request(lreq->ping_req); } req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); BUG_ON(!req); target_copy(&req->r_t, &lreq->t); osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id, lreq->register_gen); req->r_callback = linger_ping_cb; ret = ceph_osdc_alloc_messages(req, GFP_NOIO); BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; lreq->ping_req = req; ceph_osdc_get_request(req); account_request(req); req->r_tid = atomic64_inc_return(&osdc->last_tid); link_request(lreq->osd, req); send_request(req); } static void linger_submit(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd *osd; down_write(&osdc->lock); linger_register(lreq); calc_target(osdc, &lreq->t, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); link_linger(osd, lreq); send_linger(lreq); up_write(&osdc->lock); } static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_linger_request *lookup_lreq; verify_osdc_wrlocked(osdc); lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks, lreq->linger_id); if (!lookup_lreq) return; WARN_ON(lookup_lreq != lreq); erase_linger_mc(&osdc->linger_map_checks, lreq); linger_put(lreq); } /* * @lreq has to be both registered and linked. */ static void __linger_cancel(struct ceph_osd_linger_request *lreq) { if (lreq->ping_req && lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); if (lreq->reg_req && lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); cancel_linger_map_check(lreq); unlink_linger(lreq->osd, lreq); linger_unregister(lreq); } static void linger_cancel(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; down_write(&osdc->lock); if (__linger_registered(lreq)) __linger_cancel(lreq); up_write(&osdc->lock); } static void send_linger_map_check(struct ceph_osd_linger_request *lreq); static void check_linger_pool_dne(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osdmap *map = osdc->osdmap; verify_osdc_wrlocked(osdc); WARN_ON(!map->epoch); if (lreq->register_gen) { lreq->map_dne_bound = map->epoch; dout("%s lreq %p linger_id %llu pool disappeared\n", __func__, lreq, lreq->linger_id); } else { dout("%s lreq %p linger_id %llu map_dne_bound %u have %u\n", __func__, lreq, lreq->linger_id, lreq->map_dne_bound, map->epoch); } if (lreq->map_dne_bound) { if (map->epoch >= lreq->map_dne_bound) { /* we had a new enough map */ pr_info("linger_id %llu pool does not exist\n", lreq->linger_id); linger_reg_commit_complete(lreq, -ENOENT); __linger_cancel(lreq); } } else { send_linger_map_check(lreq); } } static void linger_map_check_cb(struct ceph_mon_generic_request *greq) { struct ceph_osd_client *osdc = &greq->monc->client->osdc; struct ceph_osd_linger_request *lreq; u64 linger_id = greq->private_data; WARN_ON(greq->result || !greq->u.newest); down_write(&osdc->lock); lreq = lookup_linger_mc(&osdc->linger_map_checks, linger_id); if (!lreq) { dout("%s linger_id %llu dne\n", __func__, linger_id); goto out_unlock; } dout("%s lreq %p linger_id %llu map_dne_bound %u newest %llu\n", __func__, lreq, lreq->linger_id, lreq->map_dne_bound, greq->u.newest); if (!lreq->map_dne_bound) lreq->map_dne_bound = greq->u.newest; erase_linger_mc(&osdc->linger_map_checks, lreq); check_linger_pool_dne(lreq); linger_put(lreq); out_unlock: up_write(&osdc->lock); } static void send_linger_map_check(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; struct ceph_osd_linger_request *lookup_lreq; int ret; verify_osdc_wrlocked(osdc); lookup_lreq = lookup_linger_mc(&osdc->linger_map_checks, lreq->linger_id); if (lookup_lreq) { WARN_ON(lookup_lreq != lreq); return; } linger_get(lreq); insert_linger_mc(&osdc->linger_map_checks, lreq); ret = ceph_monc_get_version_async(&osdc->client->monc, "osdmap", linger_map_check_cb, lreq->linger_id); WARN_ON(ret); } static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) { int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, unsigned long timeout) { long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, ceph_timeout_jiffies(timeout)); if (left <= 0) left = left ?: -ETIMEDOUT; else left = lreq->notify_finish_error; /* completed */ return left; } /* * Timeout callback, called every N seconds. When 1 or more OSD * requests has been active for more than N seconds, we send a keepalive * (tag + timestamp) to its OSD to ensure any communications channel * reset is detected. */ static void handle_timeout(struct work_struct *work) { struct ceph_osd_client *osdc = container_of(work, struct ceph_osd_client, timeout_work.work); struct ceph_options *opts = osdc->client->options; unsigned long cutoff = jiffies - opts->osd_keepalive_timeout; unsigned long expiry_cutoff = jiffies - opts->osd_request_timeout; LIST_HEAD(slow_osds); struct rb_node *n, *p; dout("%s osdc %p\n", __func__, osdc); down_write(&osdc->lock); /* * ping osds that are a bit slow. this ensures that if there * is a break in the TCP connection we will notice, and reopen * a connection with that osd (from the fault callback). */ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); bool found = false; for (p = rb_first(&osd->o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); /* abort_request() */ if (time_before(req->r_stamp, cutoff)) { dout(" req %p tid %llu on osd%d is laggy\n", req, req->r_tid, osd->o_osd); found = true; } if (opts->osd_request_timeout && time_before(req->r_start_stamp, expiry_cutoff)) { pr_err_ratelimited("tid %llu on osd%d timeout\n", req->r_tid, osd->o_osd); abort_request(req, -ETIMEDOUT); } } for (p = rb_first(&osd->o_linger_requests); p; p = rb_next(p)) { struct ceph_osd_linger_request *lreq = rb_entry(p, struct ceph_osd_linger_request, node); dout(" lreq %p linger_id %llu is served by osd%d\n", lreq, lreq->linger_id, osd->o_osd); found = true; mutex_lock(&lreq->lock); if (lreq->is_watch && lreq->committed && !lreq->last_error) send_linger_ping(lreq); mutex_unlock(&lreq->lock); } if (found) list_move_tail(&osd->o_keepalive_item, &slow_osds); } if (opts->osd_request_timeout) { for (p = rb_first(&osdc->homeless_osd.o_requests); p; ) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); /* abort_request() */ if (time_before(req->r_start_stamp, expiry_cutoff)) { pr_err_ratelimited("tid %llu on osd%d timeout\n", req->r_tid, osdc->homeless_osd.o_osd); abort_request(req, -ETIMEDOUT); } } } if (atomic_read(&osdc->num_homeless) || !list_empty(&slow_osds)) maybe_request_map(osdc); while (!list_empty(&slow_osds)) { struct ceph_osd *osd = list_first_entry(&slow_osds, struct ceph_osd, o_keepalive_item); list_del_init(&osd->o_keepalive_item); ceph_con_keepalive(&osd->o_con); } up_write(&osdc->lock); schedule_delayed_work(&osdc->timeout_work, osdc->client->options->osd_keepalive_timeout); } static void handle_osds_timeout(struct work_struct *work) { struct ceph_osd_client *osdc = container_of(work, struct ceph_osd_client, osds_timeout_work.work); unsigned long delay = osdc->client->options->osd_idle_ttl / 4; struct ceph_osd *osd, *nosd; dout("%s osdc %p\n", __func__, osdc); down_write(&osdc->lock); list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) { if (time_before(jiffies, osd->lru_ttl)) break; WARN_ON(!RB_EMPTY_ROOT(&osd->o_requests)); WARN_ON(!RB_EMPTY_ROOT(&osd->o_linger_requests)); close_osd(osd); } up_write(&osdc->lock); schedule_delayed_work(&osdc->osds_timeout_work, round_jiffies_relative(delay)); } static int ceph_oloc_decode(void **p, void *end, struct ceph_object_locator *oloc) { u8 struct_v, struct_cv; u32 len; void *struct_end; int ret = 0; ceph_decode_need(p, end, 1 + 1 + 4, e_inval); struct_v = ceph_decode_8(p); struct_cv = ceph_decode_8(p); if (struct_v < 3) { pr_warn("got v %d < 3 cv %d of ceph_object_locator\n", struct_v, struct_cv); goto e_inval; } if (struct_cv > 6) { pr_warn("got v %d cv %d > 6 of ceph_object_locator\n", struct_v, struct_cv); goto e_inval; } len = ceph_decode_32(p); ceph_decode_need(p, end, len, e_inval); struct_end = *p + len; oloc->pool = ceph_decode_64(p); *p += 4; /* skip preferred */ len = ceph_decode_32(p); if (len > 0) { pr_warn("ceph_object_locator::key is set\n"); goto e_inval; } if (struct_v >= 5) { bool changed = false; len = ceph_decode_32(p); if (len > 0) { ceph_decode_need(p, end, len, e_inval); if (!oloc->pool_ns || ceph_compare_string(oloc->pool_ns, *p, len)) changed = true; *p += len; } else { if (oloc->pool_ns) changed = true; } if (changed) { /* redirect changes namespace */ pr_warn("ceph_object_locator::nspace is changed\n"); goto e_inval; } } if (struct_v >= 6) { s64 hash = ceph_decode_64(p); if (hash != -1) { pr_warn("ceph_object_locator::hash is set\n"); goto e_inval; } } /* skip the rest */ *p = struct_end; out: return ret; e_inval: ret = -EINVAL; goto out; } static int ceph_redirect_decode(void **p, void *end, struct ceph_request_redirect *redir) { u8 struct_v, struct_cv; u32 len; void *struct_end; int ret; ceph_decode_need(p, end, 1 + 1 + 4, e_inval); struct_v = ceph_decode_8(p); struct_cv = ceph_decode_8(p); if (struct_cv > 1) { pr_warn("got v %d cv %d > 1 of ceph_request_redirect\n", struct_v, struct_cv); goto e_inval; } len = ceph_decode_32(p); ceph_decode_need(p, end, len, e_inval); struct_end = *p + len; ret = ceph_oloc_decode(p, end, &redir->oloc); if (ret) goto out; len = ceph_decode_32(p); if (len > 0) { pr_warn("ceph_request_redirect::object_name is set\n"); goto e_inval; } /* skip the rest */ *p = struct_end; out: return ret; e_inval: ret = -EINVAL; goto out; } struct MOSDOpReply { struct ceph_pg pgid; u64 flags; int result; u32 epoch; int num_ops; u32 outdata_len[CEPH_OSD_MAX_OPS]; s32 rval[CEPH_OSD_MAX_OPS]; int retry_attempt; struct ceph_eversion replay_version; u64 user_version; struct ceph_request_redirect redirect; }; static int decode_MOSDOpReply(const struct ceph_msg *msg, struct MOSDOpReply *m) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u16 version = le16_to_cpu(msg->hdr.version); struct ceph_eversion bad_replay_version; u8 decode_redir; u32 len; int ret; int i; ceph_decode_32_safe(&p, end, len, e_inval); ceph_decode_need(&p, end, len, e_inval); p += len; /* skip oid */ ret = ceph_decode_pgid(&p, end, &m->pgid); if (ret) return ret; ceph_decode_64_safe(&p, end, m->flags, e_inval); ceph_decode_32_safe(&p, end, m->result, e_inval); ceph_decode_need(&p, end, sizeof(bad_replay_version), e_inval); memcpy(&bad_replay_version, p, sizeof(bad_replay_version)); p += sizeof(bad_replay_version); ceph_decode_32_safe(&p, end, m->epoch, e_inval); ceph_decode_32_safe(&p, end, m->num_ops, e_inval); if (m->num_ops > ARRAY_SIZE(m->outdata_len)) goto e_inval; ceph_decode_need(&p, end, m->num_ops * sizeof(struct ceph_osd_op), e_inval); for (i = 0; i < m->num_ops; i++) { struct ceph_osd_op *op = p; m->outdata_len[i] = le32_to_cpu(op->payload_len); p += sizeof(*op); } ceph_decode_32_safe(&p, end, m->retry_attempt, e_inval); for (i = 0; i < m->num_ops; i++) ceph_decode_32_safe(&p, end, m->rval[i], e_inval); if (version >= 5) { ceph_decode_need(&p, end, sizeof(m->replay_version), e_inval); memcpy(&m->replay_version, p, sizeof(m->replay_version)); p += sizeof(m->replay_version); ceph_decode_64_safe(&p, end, m->user_version, e_inval); } else { m->replay_version = bad_replay_version; /* struct */ m->user_version = le64_to_cpu(m->replay_version.version); } if (version >= 6) { if (version >= 7) ceph_decode_8_safe(&p, end, decode_redir, e_inval); else decode_redir = 1; } else { decode_redir = 0; } if (decode_redir) { ret = ceph_redirect_decode(&p, end, &m->redirect); if (ret) return ret; } else { ceph_oloc_init(&m->redirect.oloc); } return 0; e_inval: return -EINVAL; } /* * Handle MOSDOpReply. Set ->r_result and call the callback if it is * specified. */ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg) { struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_osd_request *req; struct MOSDOpReply m; u64 tid = le64_to_cpu(msg->hdr.tid); u32 data_len = 0; int ret; int i; dout("%s msg %p tid %llu\n", __func__, msg, tid); down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); goto out_unlock_osdc; } WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num)); mutex_lock(&osd->lock); req = lookup_request(&osd->o_requests, tid); if (!req) { dout("%s osd%d tid %llu unknown\n", __func__, osd->o_osd, tid); goto out_unlock_session; } m.redirect.oloc.pool_ns = req->r_t.target_oloc.pool_ns; ret = decode_MOSDOpReply(msg, &m); m.redirect.oloc.pool_ns = NULL; if (ret) { pr_err("failed to decode MOSDOpReply for tid %llu: %d\n", req->r_tid, ret); ceph_msg_dump(msg); goto fail_request; } dout("%s req %p tid %llu flags 0x%llx pgid %llu.%x epoch %u attempt %d v %u'%llu uv %llu\n", __func__, req, req->r_tid, m.flags, m.pgid.pool, m.pgid.seed, m.epoch, m.retry_attempt, le32_to_cpu(m.replay_version.epoch), le64_to_cpu(m.replay_version.version), m.user_version); if (m.retry_attempt >= 0) { if (m.retry_attempt != req->r_attempts - 1) { dout("req %p tid %llu retry_attempt %d != %d, ignoring\n", req, req->r_tid, m.retry_attempt, req->r_attempts - 1); goto out_unlock_session; } } else { WARN_ON(1); /* MOSDOpReply v4 is assumed */ } if (!ceph_oloc_empty(&m.redirect.oloc)) { dout("req %p tid %llu redirect pool %lld\n", req, req->r_tid, m.redirect.oloc.pool); unlink_request(osd, req); mutex_unlock(&osd->lock); /* * Not ceph_oloc_copy() - changing pool_ns is not * supported. */ req->r_t.target_oloc.pool = m.redirect.oloc.pool; req->r_flags |= CEPH_OSD_FLAG_REDIRECTED | CEPH_OSD_FLAG_IGNORE_OVERLAY | CEPH_OSD_FLAG_IGNORE_CACHE; req->r_tid = 0; __submit_request(req, false); goto out_unlock_osdc; } if (m.result == -EAGAIN) { dout("req %p tid %llu EAGAIN\n", req, req->r_tid); unlink_request(osd, req); mutex_unlock(&osd->lock); /* * The object is missing on the replica or not (yet) * readable. Clear pgid to force a resend to the primary * via legacy_change. */ req->r_t.pgid.pool = 0; req->r_t.pgid.seed = 0; WARN_ON(!req->r_t.used_replica); req->r_flags &= ~(CEPH_OSD_FLAG_BALANCE_READS | CEPH_OSD_FLAG_LOCALIZE_READS); req->r_tid = 0; __submit_request(req, false); goto out_unlock_osdc; } if (m.num_ops != req->r_num_ops) { pr_err("num_ops %d != %d for tid %llu\n", m.num_ops, req->r_num_ops, req->r_tid); goto fail_request; } for (i = 0; i < req->r_num_ops; i++) { dout(" req %p tid %llu op %d rval %d len %u\n", req, req->r_tid, i, m.rval[i], m.outdata_len[i]); req->r_ops[i].rval = m.rval[i]; req->r_ops[i].outdata_len = m.outdata_len[i]; data_len += m.outdata_len[i]; } if (data_len != le32_to_cpu(msg->hdr.data_len)) { pr_err("sum of lens %u != %u for tid %llu\n", data_len, le32_to_cpu(msg->hdr.data_len), req->r_tid); goto fail_request; } dout("%s req %p tid %llu result %d data_len %u\n", __func__, req, req->r_tid, m.result, data_len); /* * Since we only ever request ONDISK, we should only ever get * one (type of) reply back. */ WARN_ON(!(m.flags & CEPH_OSD_FLAG_ONDISK)); req->r_version = m.user_version; req->r_result = m.result ?: data_len; finish_request(req); mutex_unlock(&osd->lock); up_read(&osdc->lock); __complete_request(req); return; fail_request: complete_request(req, -EIO); out_unlock_session: mutex_unlock(&osd->lock); out_unlock_osdc: up_read(&osdc->lock); } static void set_pool_was_full(struct ceph_osd_client *osdc) { struct rb_node *n; for (n = rb_first(&osdc->osdmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); pi->was_full = __pool_full(pi); } } static bool pool_cleared_full(struct ceph_osd_client *osdc, s64 pool_id) { struct ceph_pg_pool_info *pi; pi = ceph_pg_pool_by_id(osdc->osdmap, pool_id); if (!pi) return false; return pi->was_full && !__pool_full(pi); } static enum calc_target_result recalc_linger_target(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; enum calc_target_result ct_res; ct_res = calc_target(osdc, &lreq->t, true); if (ct_res == CALC_TARGET_NEED_RESEND) { struct ceph_osd *osd; osd = lookup_create_osd(osdc, lreq->t.osd, true); if (osd != lreq->osd) { unlink_linger(lreq->osd, lreq); link_linger(osd, lreq); } } return ct_res; } /* * Requeue requests whose mapping to an OSD has changed. */ static void scan_requests(struct ceph_osd *osd, bool force_resend, bool cleared_full, bool check_pool_cleared_full, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osd_client *osdc = osd->o_osdc; struct rb_node *n; bool force_resend_writes; for (n = rb_first(&osd->o_linger_requests); n; ) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); enum calc_target_result ct_res; n = rb_next(n); /* recalc_linger_target() */ dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); ct_res = recalc_linger_target(lreq); switch (ct_res) { case CALC_TARGET_NO_ACTION: force_resend_writes = cleared_full || (check_pool_cleared_full && pool_cleared_full(osdc, lreq->t.base_oloc.pool)); if (!force_resend && !force_resend_writes) break; fallthrough; case CALC_TARGET_NEED_RESEND: cancel_linger_map_check(lreq); /* * scan_requests() for the previous epoch(s) * may have already added it to the list, since * it's not unlinked here. */ if (list_empty(&lreq->scan_item)) list_add_tail(&lreq->scan_item, need_resend_linger); break; case CALC_TARGET_POOL_DNE: list_del_init(&lreq->scan_item); check_linger_pool_dne(lreq); break; } } for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); enum calc_target_result ct_res; n = rb_next(n); /* unlink_request(), check_pool_dne() */ dout("%s req %p tid %llu\n", __func__, req, req->r_tid); ct_res = calc_target(osdc, &req->r_t, false); switch (ct_res) { case CALC_TARGET_NO_ACTION: force_resend_writes = cleared_full || (check_pool_cleared_full && pool_cleared_full(osdc, req->r_t.base_oloc.pool)); if (!force_resend && (!(req->r_flags & CEPH_OSD_FLAG_WRITE) || !force_resend_writes)) break; fallthrough; case CALC_TARGET_NEED_RESEND: cancel_map_check(req); unlink_request(osd, req); insert_request(need_resend, req); break; case CALC_TARGET_POOL_DNE: check_pool_dne(req); break; } } } static int handle_one_map(struct ceph_osd_client *osdc, void *p, void *end, bool incremental, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osdmap *newmap; struct rb_node *n; bool skipped_map = false; bool was_full; was_full = ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL); set_pool_was_full(osdc); if (incremental) newmap = osdmap_apply_incremental(&p, end, ceph_msgr2(osdc->client), osdc->osdmap); else newmap = ceph_osdmap_decode(&p, end, ceph_msgr2(osdc->client)); if (IS_ERR(newmap)) return PTR_ERR(newmap); if (newmap != osdc->osdmap) { /* * Preserve ->was_full before destroying the old map. * For pools that weren't in the old map, ->was_full * should be false. */ for (n = rb_first(&newmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pi = rb_entry(n, struct ceph_pg_pool_info, node); struct ceph_pg_pool_info *old_pi; old_pi = ceph_pg_pool_by_id(osdc->osdmap, pi->id); if (old_pi) pi->was_full = old_pi->was_full; else WARN_ON(pi->was_full); } if (osdc->osdmap->epoch && osdc->osdmap->epoch + 1 < newmap->epoch) { WARN_ON(incremental); skipped_map = true; } ceph_osdmap_destroy(osdc->osdmap); osdc->osdmap = newmap; } was_full &= !ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL); scan_requests(&osdc->homeless_osd, skipped_map, was_full, true, need_resend, need_resend_linger); for (n = rb_first(&osdc->osds); n; ) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); n = rb_next(n); /* close_osd() */ scan_requests(osd, skipped_map, was_full, true, need_resend, need_resend_linger); if (!ceph_osd_is_up(osdc->osdmap, osd->o_osd) || memcmp(&osd->o_con.peer_addr, ceph_osd_addr(osdc->osdmap, osd->o_osd), sizeof(struct ceph_entity_addr))) close_osd(osd); } return 0; } static void kick_requests(struct ceph_osd_client *osdc, struct rb_root *need_resend, struct list_head *need_resend_linger) { struct ceph_osd_linger_request *lreq, *nlreq; enum calc_target_result ct_res; struct rb_node *n; /* make sure need_resend targets reflect latest map */ for (n = rb_first(need_resend); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); if (req->r_t.epoch < osdc->osdmap->epoch) { ct_res = calc_target(osdc, &req->r_t, false); if (ct_res == CALC_TARGET_POOL_DNE) { erase_request(need_resend, req); check_pool_dne(req); } } } for (n = rb_first(need_resend); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); struct ceph_osd *osd; n = rb_next(n); erase_request(need_resend, req); /* before link_request() */ osd = lookup_create_osd(osdc, req->r_t.osd, true); link_request(osd, req); if (!req->r_linger) { if (!osd_homeless(osd) && !req->r_t.paused) send_request(req); } else { cancel_linger_request(req); } } list_for_each_entry_safe(lreq, nlreq, need_resend_linger, scan_item) { if (!osd_homeless(lreq->osd)) send_linger(lreq); list_del_init(&lreq->scan_item); } } /* * Process updated osd map. * * The message contains any number of incremental and full maps, normally * indicating some sort of topology change in the cluster. Kick requests * off to different OSDs as needed. */ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u32 nr_maps, maplen; u32 epoch; struct ceph_fsid fsid; struct rb_root need_resend = RB_ROOT; LIST_HEAD(need_resend_linger); bool handled_incremental = false; bool was_pauserd, was_pausewr; bool pauserd, pausewr; int err; dout("%s have %u\n", __func__, osdc->osdmap->epoch); down_write(&osdc->lock); /* verify fsid */ ceph_decode_need(&p, end, sizeof(fsid), bad); ceph_decode_copy(&p, &fsid, sizeof(fsid)); if (ceph_check_fsid(osdc->client, &fsid) < 0) goto bad; was_pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); was_pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc); /* incremental maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d inc maps\n", nr_maps); while (nr_maps > 0) { ceph_decode_need(&p, end, 2*sizeof(u32), bad); epoch = ceph_decode_32(&p); maplen = ceph_decode_32(&p); ceph_decode_need(&p, end, maplen, bad); if (osdc->osdmap->epoch && osdc->osdmap->epoch + 1 == epoch) { dout("applying incremental map %u len %d\n", epoch, maplen); err = handle_one_map(osdc, p, p + maplen, true, &need_resend, &need_resend_linger); if (err) goto bad; handled_incremental = true; } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); } p += maplen; nr_maps--; } if (handled_incremental) goto done; /* full maps */ ceph_decode_32_safe(&p, end, nr_maps, bad); dout(" %d full maps\n", nr_maps); while (nr_maps) { ceph_decode_need(&p, end, 2*sizeof(u32), bad); epoch = ceph_decode_32(&p); maplen = ceph_decode_32(&p); ceph_decode_need(&p, end, maplen, bad); if (nr_maps > 1) { dout("skipping non-latest full map %u len %d\n", epoch, maplen); } else if (osdc->osdmap->epoch >= epoch) { dout("skipping full map %u len %d, " "older than our %u\n", epoch, maplen, osdc->osdmap->epoch); } else { dout("taking full map %u len %d\n", epoch, maplen); err = handle_one_map(osdc, p, p + maplen, false, &need_resend, &need_resend_linger); if (err) goto bad; } p += maplen; nr_maps--; } done: /* * subscribe to subsequent osdmap updates if full to ensure * we find out when we are no longer full and stop returning * ENOSPC. */ pauserd = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD); pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) || ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) || have_pool_full(osdc); if (was_pauserd || was_pausewr || pauserd || pausewr || osdc->osdmap->epoch < osdc->epoch_barrier) maybe_request_map(osdc); kick_requests(osdc, &need_resend, &need_resend_linger); ceph_osdc_abort_on_full(osdc); ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP, osdc->osdmap->epoch); up_write(&osdc->lock); wake_up_all(&osdc->client->auth_wq); return; bad: pr_err("osdc handle_map corrupt msg\n"); ceph_msg_dump(msg); up_write(&osdc->lock); } /* * Resubmit requests pending on the given osd. */ static void kick_osd_requests(struct ceph_osd *osd) { struct rb_node *n; clear_backoffs(osd); for (n = rb_first(&osd->o_requests); n; ) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); n = rb_next(n); /* cancel_linger_request() */ if (!req->r_linger) { if (!req->r_t.paused) send_request(req); } else { cancel_linger_request(req); } } for (n = rb_first(&osd->o_linger_requests); n; n = rb_next(n)) { struct ceph_osd_linger_request *lreq = rb_entry(n, struct ceph_osd_linger_request, node); send_linger(lreq); } } /* * If the osd connection drops, we need to resubmit all requests. */ static void osd_fault(struct ceph_connection *con) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; dout("%s osd %p osd%d\n", __func__, osd, osd->o_osd); down_write(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); goto out_unlock; } if (!reopen_osd(osd)) kick_osd_requests(osd); maybe_request_map(osdc); out_unlock: up_write(&osdc->lock); } struct MOSDBackoff { struct ceph_spg spgid; u32 map_epoch; u8 op; u64 id; struct ceph_hobject_id *begin; struct ceph_hobject_id *end; }; static int decode_MOSDBackoff(const struct ceph_msg *msg, struct MOSDBackoff *m) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(&p, end, 1, "spg_t", &struct_v, &struct_len); if (ret) return ret; ret = ceph_decode_pgid(&p, end, &m->spgid.pgid); if (ret) return ret; ceph_decode_8_safe(&p, end, m->spgid.shard, e_inval); ceph_decode_32_safe(&p, end, m->map_epoch, e_inval); ceph_decode_8_safe(&p, end, m->op, e_inval); ceph_decode_64_safe(&p, end, m->id, e_inval); m->begin = kzalloc(sizeof(*m->begin), GFP_NOIO); if (!m->begin) return -ENOMEM; ret = decode_hoid(&p, end, m->begin); if (ret) { free_hoid(m->begin); return ret; } m->end = kzalloc(sizeof(*m->end), GFP_NOIO); if (!m->end) { free_hoid(m->begin); return -ENOMEM; } ret = decode_hoid(&p, end, m->end); if (ret) { free_hoid(m->begin); free_hoid(m->end); return ret; } return 0; e_inval: return -EINVAL; } static struct ceph_msg *create_backoff_message( const struct ceph_osd_backoff *backoff, u32 map_epoch) { struct ceph_msg *msg; void *p, *end; int msg_size; msg_size = CEPH_ENCODING_START_BLK_LEN + CEPH_PGID_ENCODING_LEN + 1; /* spgid */ msg_size += 4 + 1 + 8; /* map_epoch, op, id */ msg_size += CEPH_ENCODING_START_BLK_LEN + hoid_encoding_size(backoff->begin); msg_size += CEPH_ENCODING_START_BLK_LEN + hoid_encoding_size(backoff->end); msg = ceph_msg_new(CEPH_MSG_OSD_BACKOFF, msg_size, GFP_NOIO, true); if (!msg) return NULL; p = msg->front.iov_base; end = p + msg->front_alloc_len; encode_spgid(&p, &backoff->spgid); ceph_encode_32(&p, map_epoch); ceph_encode_8(&p, CEPH_OSD_BACKOFF_OP_ACK_BLOCK); ceph_encode_64(&p, backoff->id); encode_hoid(&p, end, backoff->begin); encode_hoid(&p, end, backoff->end); BUG_ON(p != end); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.version = cpu_to_le16(1); /* MOSDBackoff v1 */ msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); return msg; } static void handle_backoff_block(struct ceph_osd *osd, struct MOSDBackoff *m) { struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct ceph_msg *msg; dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); spg = lookup_spg_mapping(&osd->o_backoff_mappings, &m->spgid); if (!spg) { spg = alloc_spg_mapping(); if (!spg) { pr_err("%s failed to allocate spg\n", __func__); return; } spg->spgid = m->spgid; /* struct */ insert_spg_mapping(&osd->o_backoff_mappings, spg); } backoff = alloc_backoff(); if (!backoff) { pr_err("%s failed to allocate backoff\n", __func__); return; } backoff->spgid = m->spgid; /* struct */ backoff->id = m->id; backoff->begin = m->begin; m->begin = NULL; /* backoff now owns this */ backoff->end = m->end; m->end = NULL; /* ditto */ insert_backoff(&spg->backoffs, backoff); insert_backoff_by_id(&osd->o_backoffs_by_id, backoff); /* * Ack with original backoff's epoch so that the OSD can * discard this if there was a PG split. */ msg = create_backoff_message(backoff, m->map_epoch); if (!msg) { pr_err("%s failed to allocate msg\n", __func__); return; } ceph_con_send(&osd->o_con, msg); } static bool target_contained_by(const struct ceph_osd_request_target *t, const struct ceph_hobject_id *begin, const struct ceph_hobject_id *end) { struct ceph_hobject_id hoid; int cmp; hoid_fill_from_target(&hoid, t); cmp = hoid_compare(&hoid, begin); return !cmp || (cmp > 0 && hoid_compare(&hoid, end) < 0); } static void handle_backoff_unblock(struct ceph_osd *osd, const struct MOSDBackoff *m) { struct ceph_spg_mapping *spg; struct ceph_osd_backoff *backoff; struct rb_node *n; dout("%s osd%d spgid %llu.%xs%d id %llu\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); backoff = lookup_backoff_by_id(&osd->o_backoffs_by_id, m->id); if (!backoff) { pr_err("%s osd%d spgid %llu.%xs%d id %llu backoff dne\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); return; } if (hoid_compare(backoff->begin, m->begin) && hoid_compare(backoff->end, m->end)) { pr_err("%s osd%d spgid %llu.%xs%d id %llu bad range?\n", __func__, osd->o_osd, m->spgid.pgid.pool, m->spgid.pgid.seed, m->spgid.shard, m->id); /* unblock it anyway... */ } spg = lookup_spg_mapping(&osd->o_backoff_mappings, &backoff->spgid); BUG_ON(!spg); erase_backoff(&spg->backoffs, backoff); erase_backoff_by_id(&osd->o_backoffs_by_id, backoff); free_backoff(backoff); if (RB_EMPTY_ROOT(&spg->backoffs)) { erase_spg_mapping(&osd->o_backoff_mappings, spg); free_spg_mapping(spg); } for (n = rb_first(&osd->o_requests); n; n = rb_next(n)) { struct ceph_osd_request *req = rb_entry(n, struct ceph_osd_request, r_node); if (!ceph_spg_compare(&req->r_t.spgid, &m->spgid)) { /* * Match against @m, not @backoff -- the PG may * have split on the OSD. */ if (target_contained_by(&req->r_t, m->begin, m->end)) { /* * If no other installed backoff applies, * resend. */ send_request(req); } } } } static void handle_backoff(struct ceph_osd *osd, struct ceph_msg *msg) { struct ceph_osd_client *osdc = osd->o_osdc; struct MOSDBackoff m; int ret; down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown\n", __func__, osd->o_osd); up_read(&osdc->lock); return; } WARN_ON(osd->o_osd != le64_to_cpu(msg->hdr.src.num)); mutex_lock(&osd->lock); ret = decode_MOSDBackoff(msg, &m); if (ret) { pr_err("failed to decode MOSDBackoff: %d\n", ret); ceph_msg_dump(msg); goto out_unlock; } switch (m.op) { case CEPH_OSD_BACKOFF_OP_BLOCK: handle_backoff_block(osd, &m); break; case CEPH_OSD_BACKOFF_OP_UNBLOCK: handle_backoff_unblock(osd, &m); break; default: pr_err("%s osd%d unknown op %d\n", __func__, osd->o_osd, m.op); } free_hoid(m.begin); free_hoid(m.end); out_unlock: mutex_unlock(&osd->lock); up_read(&osdc->lock); } /* * Process osd watch notifications */ static void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg) { void *p = msg->front.iov_base; void *const end = p + msg->front.iov_len; struct ceph_osd_linger_request *lreq; struct linger_work *lwork; u8 proto_ver, opcode; u64 cookie, notify_id; u64 notifier_id = 0; s32 return_code = 0; void *payload = NULL; u32 payload_len = 0; ceph_decode_8_safe(&p, end, proto_ver, bad); ceph_decode_8_safe(&p, end, opcode, bad); ceph_decode_64_safe(&p, end, cookie, bad); p += 8; /* skip ver */ ceph_decode_64_safe(&p, end, notify_id, bad); if (proto_ver >= 1) { ceph_decode_32_safe(&p, end, payload_len, bad); ceph_decode_need(&p, end, payload_len, bad); payload = p; p += payload_len; } if (le16_to_cpu(msg->hdr.version) >= 2) ceph_decode_32_safe(&p, end, return_code, bad); if (le16_to_cpu(msg->hdr.version) >= 3) ceph_decode_64_safe(&p, end, notifier_id, bad); down_read(&osdc->lock); lreq = lookup_linger_osdc(&osdc->linger_requests, cookie); if (!lreq) { dout("%s opcode %d cookie %llu dne\n", __func__, opcode, cookie); goto out_unlock_osdc; } mutex_lock(&lreq->lock); dout("%s opcode %d cookie %llu lreq %p is_watch %d\n", __func__, opcode, cookie, lreq, lreq->is_watch); if (opcode == CEPH_WATCH_EVENT_DISCONNECT) { if (!lreq->last_error) { lreq->last_error = -ENOTCONN; queue_watch_error(lreq); } } else if (!lreq->is_watch) { /* CEPH_WATCH_EVENT_NOTIFY_COMPLETE */ if (lreq->notify_id && lreq->notify_id != notify_id) { dout("lreq %p notify_id %llu != %llu, ignoring\n", lreq, lreq->notify_id, notify_id); } else if (!completion_done(&lreq->notify_finish_wait)) { struct ceph_msg_data *data = msg->num_data_items ? &msg->data[0] : NULL; if (data) { if (lreq->preply_pages) { WARN_ON(data->type != CEPH_MSG_DATA_PAGES); *lreq->preply_pages = data->pages; *lreq->preply_len = data->length; data->own_pages = false; } } lreq->notify_finish_error = return_code; complete_all(&lreq->notify_finish_wait); } } else { /* CEPH_WATCH_EVENT_NOTIFY */ lwork = lwork_alloc(lreq, do_watch_notify); if (!lwork) { pr_err("failed to allocate notify-lwork\n"); goto out_unlock_lreq; } lwork->notify.notify_id = notify_id; lwork->notify.notifier_id = notifier_id; lwork->notify.payload = payload; lwork->notify.payload_len = payload_len; lwork->notify.msg = ceph_msg_get(msg); lwork_queue(lwork); } out_unlock_lreq: mutex_unlock(&lreq->lock); out_unlock_osdc: up_read(&osdc->lock); return; bad: pr_err("osdc handle_watch_notify corrupt msg\n"); } /* * Register request, send initial attempt. */ void ceph_osdc_start_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { down_read(&osdc->lock); submit_request(req, false); up_read(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_start_request); /* * Unregister request. If @req was registered, it isn't completed: * r_result isn't set and __complete_request() isn't invoked. * * If @req wasn't registered, this call may have raced with * handle_reply(), in which case r_result would already be set and * __complete_request() would be getting invoked, possibly even * concurrently with this call. */ void ceph_osdc_cancel_request(struct ceph_osd_request *req) { struct ceph_osd_client *osdc = req->r_osdc; down_write(&osdc->lock); if (req->r_osd) cancel_request(req); up_write(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_cancel_request); /* * @timeout: in jiffies, 0 means "wait forever" */ static int wait_request_timeout(struct ceph_osd_request *req, unsigned long timeout) { long left; dout("%s req %p tid %llu\n", __func__, req, req->r_tid); left = wait_for_completion_killable_timeout(&req->r_completion, ceph_timeout_jiffies(timeout)); if (left <= 0) { left = left ?: -ETIMEDOUT; ceph_osdc_cancel_request(req); } else { left = req->r_result; /* completed */ } return left; } /* * wait for a request to complete */ int ceph_osdc_wait_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { return wait_request_timeout(req, 0); } EXPORT_SYMBOL(ceph_osdc_wait_request); /* * sync - wait for all in-flight requests to flush. avoid starvation. */ void ceph_osdc_sync(struct ceph_osd_client *osdc) { struct rb_node *n, *p; u64 last_tid = atomic64_read(&osdc->last_tid); again: down_read(&osdc->lock); for (n = rb_first(&osdc->osds); n; n = rb_next(n)) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); mutex_lock(&osd->lock); for (p = rb_first(&osd->o_requests); p; p = rb_next(p)) { struct ceph_osd_request *req = rb_entry(p, struct ceph_osd_request, r_node); if (req->r_tid > last_tid) break; if (!(req->r_flags & CEPH_OSD_FLAG_WRITE)) continue; ceph_osdc_get_request(req); mutex_unlock(&osd->lock); up_read(&osdc->lock); dout("%s waiting on req %p tid %llu last_tid %llu\n", __func__, req, req->r_tid, last_tid); wait_for_completion(&req->r_completion); ceph_osdc_put_request(req); goto again; } mutex_unlock(&osd->lock); } up_read(&osdc->lock); dout("%s done last_tid %llu\n", __func__, last_tid); } EXPORT_SYMBOL(ceph_osdc_sync); /* * Returns a handle, caller owns a ref. */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, rados_watchcb2_t wcb, rados_watcherrcb_t errcb, void *data) { struct ceph_osd_linger_request *lreq; int ret; lreq = linger_alloc(osdc); if (!lreq) return ERR_PTR(-ENOMEM); lreq->is_watch = true; lreq->wcb = wcb; lreq->errcb = errcb; lreq->data = data; lreq->watch_valid_thru = jiffies; ceph_oid_copy(&lreq->t.base_oid, oid); ceph_oloc_copy(&lreq->t.base_oloc, oloc); lreq->t.flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&lreq->mtime); linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (ret) { linger_cancel(lreq); goto err_put_lreq; } return lreq; err_put_lreq: linger_put(lreq); return ERR_PTR(ret); } EXPORT_SYMBOL(ceph_osdc_watch); /* * Releases a ref. * * Times out after mount_timeout to preserve rbd unmap behaviour * introduced in 2894e1d76974 ("rbd: timeout watch teardown on unmap * with mount_timeout"). */ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, struct ceph_osd_linger_request *lreq) { struct ceph_options *opts = osdc->client->options; struct ceph_osd_request *req; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&req->r_mtime); osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH, lreq->linger_id, 0); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); linger_cancel(lreq); linger_put(lreq); ret = wait_request_timeout(req, opts->mount_timeout); out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_unwatch); static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which, u64 notify_id, u64 cookie, void *payload, u32 payload_len) { struct ceph_osd_req_op *op; struct ceph_pagelist *pl; int ret; op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0); pl = ceph_pagelist_alloc(GFP_NOIO); if (!pl) return -ENOMEM; ret = ceph_pagelist_encode_64(pl, notify_id); ret |= ceph_pagelist_encode_64(pl, cookie); if (payload) { ret |= ceph_pagelist_encode_32(pl, payload_len); ret |= ceph_pagelist_append(pl, payload, payload_len); } else { ret |= ceph_pagelist_encode_32(pl, 0); } if (ret) { ceph_pagelist_release(pl); return -ENOMEM; } ceph_osd_data_pagelist_init(&op->notify_ack.request_data, pl); op->indata_len = pl->length; return 0; } int ceph_osdc_notify_ack(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, u64 notify_id, u64 cookie, void *payload, u32 payload_len) { struct ceph_osd_request *req; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = CEPH_OSD_FLAG_READ; ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload, payload_len); if (ret) goto out_put_req; ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_notify_ack); /* * @timeout: in seconds * * @preply_{pages,len} are initialized both on success and error. * The caller is responsible for: * * ceph_release_page_vector(reply_pages, calc_pages_for(0, reply_len)) */ int ceph_osdc_notify(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, void *payload, u32 payload_len, u32 timeout, struct page ***preply_pages, size_t *preply_len) { struct ceph_osd_linger_request *lreq; int ret; WARN_ON(!timeout); if (preply_pages) { *preply_pages = NULL; *preply_len = 0; } lreq = linger_alloc(osdc); if (!lreq) return -ENOMEM; lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO); if (!lreq->request_pl) { ret = -ENOMEM; goto out_put_lreq; } ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */ ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout); ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len); ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len); if (ret) { ret = -ENOMEM; goto out_put_lreq; } /* for notify_id */ lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO); if (IS_ERR(lreq->notify_id_pages)) { ret = PTR_ERR(lreq->notify_id_pages); lreq->notify_id_pages = NULL; goto out_put_lreq; } lreq->preply_pages = preply_pages; lreq->preply_len = preply_len; ceph_oid_copy(&lreq->t.base_oid, oid); ceph_oloc_copy(&lreq->t.base_oloc, oloc); lreq->t.flags = CEPH_OSD_FLAG_READ; linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (!ret) ret = linger_notify_finish_wait(lreq, msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); linger_cancel(lreq); out_put_lreq: linger_put(lreq); return ret; } EXPORT_SYMBOL(ceph_osdc_notify); /* * Return the number of milliseconds since the watch was last * confirmed, or an error. If there is an error, the watch is no * longer valid, and should be destroyed with ceph_osdc_unwatch(). */ int ceph_osdc_watch_check(struct ceph_osd_client *osdc, struct ceph_osd_linger_request *lreq) { unsigned long stamp, age; int ret; down_read(&osdc->lock); mutex_lock(&lreq->lock); stamp = lreq->watch_valid_thru; if (!list_empty(&lreq->pending_lworks)) { struct linger_work *lwork = list_first_entry(&lreq->pending_lworks, struct linger_work, pending_item); if (time_before(lwork->queued_stamp, stamp)) stamp = lwork->queued_stamp; } age = jiffies - stamp; dout("%s lreq %p linger_id %llu age %lu last_error %d\n", __func__, lreq, lreq->linger_id, age, lreq->last_error); /* we are truncating to msecs, so return a safe upper bound */ ret = lreq->last_error ?: 1 + jiffies_to_msecs(age); mutex_unlock(&lreq->lock); up_read(&osdc->lock); return ret; } static int decode_watcher(void **p, void *end, struct ceph_watch_item *item) { u8 struct_v; u32 struct_len; int ret; ret = ceph_start_decoding(p, end, 2, "watch_item_t", &struct_v, &struct_len); if (ret) goto bad; ret = -EINVAL; ceph_decode_copy_safe(p, end, &item->name, sizeof(item->name), bad); ceph_decode_64_safe(p, end, item->cookie, bad); ceph_decode_skip_32(p, end, bad); /* skip timeout seconds */ if (struct_v >= 2) { ret = ceph_decode_entity_addr(p, end, &item->addr); if (ret) goto bad; } else { ret = 0; } dout("%s %s%llu cookie %llu addr %s\n", __func__, ENTITY_NAME(item->name), item->cookie, ceph_pr_addr(&item->addr)); bad: return ret; } static int decode_watchers(void **p, void *end, struct ceph_watch_item **watchers, u32 *num_watchers) { u8 struct_v; u32 struct_len; int i; int ret; ret = ceph_start_decoding(p, end, 1, "obj_list_watch_response_t", &struct_v, &struct_len); if (ret) return ret; *num_watchers = ceph_decode_32(p); *watchers = kcalloc(*num_watchers, sizeof(**watchers), GFP_NOIO); if (!*watchers) return -ENOMEM; for (i = 0; i < *num_watchers; i++) { ret = decode_watcher(p, end, *watchers + i); if (ret) { kfree(*watchers); return ret; } } return 0; } /* * On success, the caller is responsible for: * * kfree(watchers); */ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, struct ceph_watch_item **watchers, u32 *num_watchers) { struct ceph_osd_request *req; struct page **pages; int ret; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = CEPH_OSD_FLAG_READ; pages = ceph_alloc_page_vector(1, GFP_NOIO); if (IS_ERR(pages)) { ret = PTR_ERR(pages); goto out_put_req; } osd_req_op_init(req, 0, CEPH_OSD_OP_LIST_WATCHERS, 0); ceph_osd_data_pages_init(osd_req_op_data(req, 0, list_watchers, response_data), pages, PAGE_SIZE, 0, false, true); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); if (ret >= 0) { void *p = page_address(pages[0]); void *const end = p + req->r_ops[0].outdata_len; ret = decode_watchers(&p, end, watchers, num_watchers); } out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_list_watchers); /* * Call all pending notify callbacks - for use after a watch is * unregistered, to make sure no more callbacks for it will be invoked */ void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc) { dout("%s osdc %p\n", __func__, osdc); flush_workqueue(osdc->notify_wq); } EXPORT_SYMBOL(ceph_osdc_flush_notifies); void ceph_osdc_maybe_request_map(struct ceph_osd_client *osdc) { down_read(&osdc->lock); maybe_request_map(osdc); up_read(&osdc->lock); } EXPORT_SYMBOL(ceph_osdc_maybe_request_map); /* * Execute an OSD class method on an object. * * @flags: CEPH_OSD_FLAG_* * @resp_len: in/out param for reply length */ int ceph_osdc_call(struct ceph_osd_client *osdc, struct ceph_object_id *oid, struct ceph_object_locator *oloc, const char *class, const char *method, unsigned int flags, struct page *req_page, size_t req_len, struct page **resp_pages, size_t *resp_len) { struct ceph_osd_request *req; int ret; if (req_len > PAGE_SIZE) return -E2BIG; req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO); if (!req) return -ENOMEM; ceph_oid_copy(&req->r_base_oid, oid); ceph_oloc_copy(&req->r_base_oloc, oloc); req->r_flags = flags; ret = osd_req_op_cls_init(req, 0, class, method); if (ret) goto out_put_req; if (req_page) osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len, 0, false, false); if (resp_pages) osd_req_op_cls_response_data_pages(req, 0, resp_pages, *resp_len, 0, false, false); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) goto out_put_req; ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); if (ret >= 0) { ret = req->r_ops[0].rval; if (resp_pages) *resp_len = req->r_ops[0].outdata_len; } out_put_req: ceph_osdc_put_request(req); return ret; } EXPORT_SYMBOL(ceph_osdc_call); /* * reset all osd connections */ void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc) { struct rb_node *n; down_write(&osdc->lock); for (n = rb_first(&osdc->osds); n; ) { struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node); n = rb_next(n); if (!reopen_osd(osd)) kick_osd_requests(osd); } up_write(&osdc->lock); } /* * init, shutdown */ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) { int err; dout("init\n"); osdc->client = client; init_rwsem(&osdc->lock); osdc->osds = RB_ROOT; INIT_LIST_HEAD(&osdc->osd_lru); spin_lock_init(&osdc->osd_lru_lock); osd_init(&osdc->homeless_osd); osdc->homeless_osd.o_osdc = osdc; osdc->homeless_osd.o_osd = CEPH_HOMELESS_OSD; osdc->last_linger_id = CEPH_LINGER_ID_START; osdc->linger_requests = RB_ROOT; osdc->map_checks = RB_ROOT; osdc->linger_map_checks = RB_ROOT; INIT_DELAYED_WORK(&osdc->timeout_work, handle_timeout); INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout); err = -ENOMEM; osdc->osdmap = ceph_osdmap_alloc(); if (!osdc->osdmap) goto out; osdc->req_mempool = mempool_create_slab_pool(10, ceph_osd_request_cache); if (!osdc->req_mempool) goto out_map; err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP, PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op"); if (err < 0) goto out_mempool; err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY, PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op_reply"); if (err < 0) goto out_msgpool; err = -ENOMEM; osdc->notify_wq = create_singlethread_workqueue("ceph-watch-notify"); if (!osdc->notify_wq) goto out_msgpool_reply; osdc->completion_wq = create_singlethread_workqueue("ceph-completion"); if (!osdc->completion_wq) goto out_notify_wq; schedule_delayed_work(&osdc->timeout_work, osdc->client->options->osd_keepalive_timeout); schedule_delayed_work(&osdc->osds_timeout_work, round_jiffies_relative(osdc->client->options->osd_idle_ttl)); return 0; out_notify_wq: destroy_workqueue(osdc->notify_wq); out_msgpool_reply: ceph_msgpool_destroy(&osdc->msgpool_op_reply); out_msgpool: ceph_msgpool_destroy(&osdc->msgpool_op); out_mempool: mempool_destroy(osdc->req_mempool); out_map: ceph_osdmap_destroy(osdc->osdmap); out: return err; } void ceph_osdc_stop(struct ceph_osd_client *osdc) { destroy_workqueue(osdc->completion_wq); destroy_workqueue(osdc->notify_wq); cancel_delayed_work_sync(&osdc->timeout_work); cancel_delayed_work_sync(&osdc->osds_timeout_work); down_write(&osdc->lock); while (!RB_EMPTY_ROOT(&osdc->osds)) { struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds), struct ceph_osd, o_node); close_osd(osd); } up_write(&osdc->lock); WARN_ON(refcount_read(&osdc->homeless_osd.o_ref) != 1); osd_cleanup(&osdc->homeless_osd); WARN_ON(!list_empty(&osdc->osd_lru)); WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_requests)); WARN_ON(!RB_EMPTY_ROOT(&osdc->map_checks)); WARN_ON(!RB_EMPTY_ROOT(&osdc->linger_map_checks)); WARN_ON(atomic_read(&osdc->num_requests)); WARN_ON(atomic_read(&osdc->num_homeless)); ceph_osdmap_destroy(osdc->osdmap); mempool_destroy(osdc->req_mempool); ceph_msgpool_destroy(&osdc->msgpool_op); ceph_msgpool_destroy(&osdc->msgpool_op_reply); } int osd_req_op_copy_from_init(struct ceph_osd_request *req, u64 src_snapid, u64 src_version, struct ceph_object_id *src_oid, struct ceph_object_locator *src_oloc, u32 src_fadvise_flags, u32 dst_fadvise_flags, u32 truncate_seq, u64 truncate_size, u8 copy_from_flags) { struct ceph_osd_req_op *op; struct page **pages; void *p, *end; pages = ceph_alloc_page_vector(1, GFP_KERNEL); if (IS_ERR(pages)) return PTR_ERR(pages); op = osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2, dst_fadvise_flags); op->copy_from.snapid = src_snapid; op->copy_from.src_version = src_version; op->copy_from.flags = copy_from_flags; op->copy_from.src_fadvise_flags = src_fadvise_flags; p = page_address(pages[0]); end = p + PAGE_SIZE; ceph_encode_string(&p, end, src_oid->name, src_oid->name_len); encode_oloc(&p, end, src_oloc); ceph_encode_32(&p, truncate_seq); ceph_encode_64(&p, truncate_size); op->indata_len = PAGE_SIZE - (end - p); ceph_osd_data_pages_init(&op->copy_from.osd_data, pages, op->indata_len, 0, false, true); return 0; } EXPORT_SYMBOL(osd_req_op_copy_from_init); int __init ceph_osdc_setup(void) { size_t size = sizeof(struct ceph_osd_request) + CEPH_OSD_SLAB_OPS * sizeof(struct ceph_osd_req_op); BUG_ON(ceph_osd_request_cache); ceph_osd_request_cache = kmem_cache_create("ceph_osd_request", size, 0, 0, NULL); return ceph_osd_request_cache ? 0 : -ENOMEM; } void ceph_osdc_cleanup(void) { BUG_ON(!ceph_osd_request_cache); kmem_cache_destroy(ceph_osd_request_cache); ceph_osd_request_cache = NULL; } /* * handle incoming message */ static void osd_dispatch(struct ceph_connection *con, struct ceph_msg *msg) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; int type = le16_to_cpu(msg->hdr.type); switch (type) { case CEPH_MSG_OSD_MAP: ceph_osdc_handle_map(osdc, msg); break; case CEPH_MSG_OSD_OPREPLY: handle_reply(osd, msg); break; case CEPH_MSG_OSD_BACKOFF: handle_backoff(osd, msg); break; case CEPH_MSG_WATCH_NOTIFY: handle_watch_notify(osdc, msg); break; default: pr_err("received unknown message type %d %s\n", type, ceph_msg_type_name(type)); } ceph_msg_put(msg); } /* How much sparse data was requested? */ static u64 sparse_data_requested(struct ceph_osd_request *req) { u64 len = 0; if (req->r_flags & CEPH_OSD_FLAG_READ) { int i; for (i = 0; i < req->r_num_ops; ++i) { struct ceph_osd_req_op *op = &req->r_ops[i]; if (op->op == CEPH_OSD_OP_SPARSE_READ) len += op->extent.length; } } return len; } /* * Lookup and return message for incoming reply. Don't try to do * anything about a larger than preallocated data portion of the * message at the moment - for now, just skip the message. */ static struct ceph_msg *get_reply(struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip) { struct ceph_osd *osd = con->private; struct ceph_osd_client *osdc = osd->o_osdc; struct ceph_msg *m = NULL; struct ceph_osd_request *req; int front_len = le32_to_cpu(hdr->front_len); int data_len = le32_to_cpu(hdr->data_len); u64 tid = le64_to_cpu(hdr->tid); u64 srlen; down_read(&osdc->lock); if (!osd_registered(osd)) { dout("%s osd%d unknown, skipping\n", __func__, osd->o_osd); *skip = 1; goto out_unlock_osdc; } WARN_ON(osd->o_osd != le64_to_cpu(hdr->src.num)); mutex_lock(&osd->lock); req = lookup_request(&osd->o_requests, tid); if (!req) { dout("%s osd%d tid %llu unknown, skipping\n", __func__, osd->o_osd, tid); *skip = 1; goto out_unlock_session; } ceph_msg_revoke_incoming(req->r_reply); if (front_len > req->r_reply->front_alloc_len) { pr_warn("%s osd%d tid %llu front %d > preallocated %d\n", __func__, osd->o_osd, req->r_tid, front_len, req->r_reply->front_alloc_len); m = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, front_len, GFP_NOFS, false); if (!m) goto out_unlock_session; ceph_msg_put(req->r_reply); req->r_reply = m; } srlen = sparse_data_requested(req); if (!srlen && data_len > req->r_reply->data_length) { pr_warn("%s osd%d tid %llu data %d > preallocated %zu, skipping\n", __func__, osd->o_osd, req->r_tid, data_len, req->r_reply->data_length); m = NULL; *skip = 1; goto out_unlock_session; } m = ceph_msg_get(req->r_reply); m->sparse_read_total = srlen; dout("get_reply tid %lld %p\n", tid, m); out_unlock_session: mutex_unlock(&osd->lock); out_unlock_osdc: up_read(&osdc->lock); return m; } static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) { struct ceph_msg *m; int type = le16_to_cpu(hdr->type); u32 front_len = le32_to_cpu(hdr->front_len); u32 data_len = le32_to_cpu(hdr->data_len); m = ceph_msg_new2(type, front_len, 1, GFP_NOIO, false); if (!m) return NULL; if (data_len) { struct page **pages; pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); if (IS_ERR(pages)) { ceph_msg_put(m); return NULL; } ceph_msg_data_add_pages(m, pages, data_len, 0, true); } return m; } static struct ceph_msg *osd_alloc_msg(struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip) { struct ceph_osd *osd = con->private; int type = le16_to_cpu(hdr->type); *skip = 0; switch (type) { case CEPH_MSG_OSD_MAP: case CEPH_MSG_OSD_BACKOFF: case CEPH_MSG_WATCH_NOTIFY: return alloc_msg_with_page_vector(hdr); case CEPH_MSG_OSD_OPREPLY: return get_reply(con, hdr, skip); default: pr_warn("%s osd%d unknown msg type %d, skipping\n", __func__, osd->o_osd, type); *skip = 1; return NULL; } } /* * Wrappers to refcount containing ceph_osd struct */ static struct ceph_connection *osd_get_con(struct ceph_connection *con) { struct ceph_osd *osd = con->private; if (get_osd(osd)) return con; return NULL; } static void osd_put_con(struct ceph_connection *con) { struct ceph_osd *osd = con->private; put_osd(osd); } /* * authentication */ /* * Note: returned pointer is the address of a structure that's * managed separately. Caller must *not* attempt to free it. */ static struct ceph_auth_handshake * osd_get_authorizer(struct ceph_connection *con, int *proto, int force_new) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = __ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD, force_new, proto, NULL, NULL); if (ret) return ERR_PTR(ret); return auth; } static int osd_add_authorizer_challenge(struct ceph_connection *con, void *challenge_buf, int challenge_buf_len) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; return ceph_auth_add_authorizer_challenge(ac, o->o_auth.authorizer, challenge_buf, challenge_buf_len); } static int osd_verify_authorizer_reply(struct ceph_connection *con) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_verify_authorizer_reply(ac, auth->authorizer, auth->authorizer_reply_buf, auth->authorizer_reply_buf_len, NULL, NULL, NULL, NULL); } static int osd_invalidate_authorizer(struct ceph_connection *con) { struct ceph_osd *o = con->private; struct ceph_osd_client *osdc = o->o_osdc; struct ceph_auth_client *ac = osdc->client->monc.auth; ceph_auth_invalidate_authorizer(ac, CEPH_ENTITY_TYPE_OSD); return ceph_monc_validate_auth(&osdc->client->monc); } static int osd_get_auth_request(struct ceph_connection *con, void *buf, int *buf_len, void **authorizer, int *authorizer_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD, buf, buf_len); if (ret) return ret; *authorizer = auth->authorizer_buf; *authorizer_len = auth->authorizer_buf_len; return 0; } static int osd_handle_auth_reply_more(struct ceph_connection *con, void *reply, int reply_len, void *buf, int *buf_len, void **authorizer, int *authorizer_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; int ret; ret = ceph_auth_handle_svc_reply_more(ac, auth, reply, reply_len, buf, buf_len); if (ret) return ret; *authorizer = auth->authorizer_buf; *authorizer_len = auth->authorizer_buf_len; return 0; } static int osd_handle_auth_done(struct ceph_connection *con, u64 global_id, void *reply, int reply_len, u8 *session_key, int *session_key_len, u8 *con_secret, int *con_secret_len) { struct ceph_osd *o = con->private; struct ceph_auth_client *ac = o->o_osdc->client->monc.auth; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_handle_svc_reply_done(ac, auth, reply, reply_len, session_key, session_key_len, con_secret, con_secret_len); } static int osd_handle_auth_bad_method(struct ceph_connection *con, int used_proto, int result, const int *allowed_protos, int proto_cnt, const int *allowed_modes, int mode_cnt) { struct ceph_osd *o = con->private; struct ceph_mon_client *monc = &o->o_osdc->client->monc; int ret; if (ceph_auth_handle_bad_authorizer(monc->auth, CEPH_ENTITY_TYPE_OSD, used_proto, result, allowed_protos, proto_cnt, allowed_modes, mode_cnt)) { ret = ceph_monc_validate_auth(monc); if (ret) return ret; } return -EACCES; } static void osd_reencode_message(struct ceph_msg *msg) { int type = le16_to_cpu(msg->hdr.type); if (type == CEPH_MSG_OSD_OP) encode_request_finish(msg); } static int osd_sign_message(struct ceph_msg *msg) { struct ceph_osd *o = msg->con->private; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_sign_message(auth, msg); } static int osd_check_message_signature(struct ceph_msg *msg) { struct ceph_osd *o = msg->con->private; struct ceph_auth_handshake *auth = &o->o_auth; return ceph_auth_check_message_signature(auth, msg); } static void advance_cursor(struct ceph_msg_data_cursor *cursor, size_t len, bool zero) { while (len) { struct page *page; size_t poff, plen; page = ceph_msg_data_next(cursor, &poff, &plen); if (plen > len) plen = len; if (zero) zero_user_segment(page, poff, poff + plen); len -= plen; ceph_msg_data_advance(cursor, plen); } } static int prep_next_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor) { struct ceph_osd *o = con->private; struct ceph_sparse_read *sr = &o->o_sparse_read; struct ceph_osd_request *req; struct ceph_osd_req_op *op; spin_lock(&o->o_requests_lock); req = lookup_request(&o->o_requests, le64_to_cpu(con->in_msg->hdr.tid)); if (!req) { spin_unlock(&o->o_requests_lock); return -EBADR; } if (o->o_sparse_op_idx < 0) { dout("%s: [%d] starting new sparse read req\n", __func__, o->o_osd); } else { u64 end; op = &req->r_ops[o->o_sparse_op_idx]; WARN_ON_ONCE(op->extent.sparse_ext); /* hand back buffer we took earlier */ op->extent.sparse_ext = sr->sr_extent; sr->sr_extent = NULL; op->extent.sparse_ext_cnt = sr->sr_count; sr->sr_ext_len = 0; dout("%s: [%d] completed extent array len %d cursor->resid %zd\n", __func__, o->o_osd, op->extent.sparse_ext_cnt, cursor->resid); /* Advance to end of data for this operation */ end = ceph_sparse_ext_map_end(op); if (end < sr->sr_req_len) advance_cursor(cursor, sr->sr_req_len - end, false); } ceph_init_sparse_read(sr); /* find next op in this request (if any) */ while (++o->o_sparse_op_idx < req->r_num_ops) { op = &req->r_ops[o->o_sparse_op_idx]; if (op->op == CEPH_OSD_OP_SPARSE_READ) goto found; } /* reset for next sparse read request */ spin_unlock(&o->o_requests_lock); o->o_sparse_op_idx = -1; return 0; found: sr->sr_req_off = op->extent.offset; sr->sr_req_len = op->extent.length; sr->sr_pos = sr->sr_req_off; dout("%s: [%d] new sparse read op at idx %d 0x%llx~0x%llx\n", __func__, o->o_osd, o->o_sparse_op_idx, sr->sr_req_off, sr->sr_req_len); /* hand off request's sparse extent map buffer */ sr->sr_ext_len = op->extent.sparse_ext_cnt; op->extent.sparse_ext_cnt = 0; sr->sr_extent = op->extent.sparse_ext; op->extent.sparse_ext = NULL; spin_unlock(&o->o_requests_lock); return 1; } #ifdef __BIG_ENDIAN static inline void convert_extent_map(struct ceph_sparse_read *sr) { int i; for (i = 0; i < sr->sr_count; i++) { struct ceph_sparse_extent *ext = &sr->sr_extent[i]; ext->off = le64_to_cpu((__force __le64)ext->off); ext->len = le64_to_cpu((__force __le64)ext->len); } } #else static inline void convert_extent_map(struct ceph_sparse_read *sr) { } #endif static int osd_sparse_read(struct ceph_connection *con, struct ceph_msg_data_cursor *cursor, char **pbuf) { struct ceph_osd *o = con->private; struct ceph_sparse_read *sr = &o->o_sparse_read; u32 count = sr->sr_count; u64 eoff, elen, len = 0; int i, ret; switch (sr->sr_state) { case CEPH_SPARSE_READ_HDR: next_op: ret = prep_next_sparse_read(con, cursor); if (ret <= 0) return ret; /* number of extents */ ret = sizeof(sr->sr_count); *pbuf = (char *)&sr->sr_count; sr->sr_state = CEPH_SPARSE_READ_EXTENTS; break; case CEPH_SPARSE_READ_EXTENTS: /* Convert sr_count to host-endian */ count = le32_to_cpu((__force __le32)sr->sr_count); sr->sr_count = count; dout("[%d] got %u extents\n", o->o_osd, count); if (count > 0) { if (!sr->sr_extent || count > sr->sr_ext_len) { /* no extent array provided, or too short */ kfree(sr->sr_extent); sr->sr_extent = kmalloc_array(count, sizeof(*sr->sr_extent), GFP_NOIO); if (!sr->sr_extent) { pr_err("%s: failed to allocate %u extents\n", __func__, count); return -ENOMEM; } sr->sr_ext_len = count; } ret = count * sizeof(*sr->sr_extent); *pbuf = (char *)sr->sr_extent; sr->sr_state = CEPH_SPARSE_READ_DATA_LEN; break; } /* No extents? Read data len */ fallthrough; case CEPH_SPARSE_READ_DATA_LEN: convert_extent_map(sr); ret = sizeof(sr->sr_datalen); *pbuf = (char *)&sr->sr_datalen; sr->sr_state = CEPH_SPARSE_READ_DATA_PRE; break; case CEPH_SPARSE_READ_DATA_PRE: /* Convert sr_datalen to host-endian */ sr->sr_datalen = le32_to_cpu((__force __le32)sr->sr_datalen); for (i = 0; i < count; i++) len += sr->sr_extent[i].len; if (sr->sr_datalen != len) { pr_warn_ratelimited("data len %u != extent len %llu\n", sr->sr_datalen, len); return -EREMOTEIO; } sr->sr_state = CEPH_SPARSE_READ_DATA; fallthrough; case CEPH_SPARSE_READ_DATA: if (sr->sr_index >= count) { sr->sr_state = CEPH_SPARSE_READ_HDR; goto next_op; } eoff = sr->sr_extent[sr->sr_index].off; elen = sr->sr_extent[sr->sr_index].len; dout("[%d] ext %d off 0x%llx len 0x%llx\n", o->o_osd, sr->sr_index, eoff, elen); if (elen > INT_MAX) { dout("Sparse read extent length too long (0x%llx)\n", elen); return -EREMOTEIO; } /* zero out anything from sr_pos to start of extent */ if (sr->sr_pos < eoff) advance_cursor(cursor, eoff - sr->sr_pos, true); /* Set position to end of extent */ sr->sr_pos = eoff + elen; /* send back the new length and nullify the ptr */ cursor->sr_resid = elen; ret = elen; *pbuf = NULL; /* Bump the array index */ ++sr->sr_index; break; } return ret; } static const struct ceph_connection_operations osd_con_ops = { .get = osd_get_con, .put = osd_put_con, .sparse_read = osd_sparse_read, .alloc_msg = osd_alloc_msg, .dispatch = osd_dispatch, .fault = osd_fault, .reencode_message = osd_reencode_message, .get_authorizer = osd_get_authorizer, .add_authorizer_challenge = osd_add_authorizer_challenge, .verify_authorizer_reply = osd_verify_authorizer_reply, .invalidate_authorizer = osd_invalidate_authorizer, .sign_message = osd_sign_message, .check_message_signature = osd_check_message_signature, .get_auth_request = osd_get_auth_request, .handle_auth_reply_more = osd_handle_auth_reply_more, .handle_auth_done = osd_handle_auth_done, .handle_auth_bad_method = osd_handle_auth_bad_method, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM udp #if !defined(_TRACE_UDP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_UDP_H #include <linux/udp.h> #include <linux/tracepoint.h> #include <trace/events/net_probe_common.h> TRACE_EVENT(udp_fail_queue_rcv_skb, TP_PROTO(int rc, struct sock *sk, struct sk_buff *skb), TP_ARGS(rc, sk, skb), TP_STRUCT__entry( __field(int, rc) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( const struct udphdr *uh = (const struct udphdr *)udp_hdr(skb); __entry->rc = rc; /* for filtering use */ __entry->sport = ntohs(uh->source); __entry->dport = ntohs(uh->dest); __entry->family = sk->sk_family; memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS_SKB(skb, uh, __entry->saddr, __entry->daddr); ), TP_printk("rc=%d family=%s src=%pISpc dest=%pISpc", __entry->rc, show_family_name(__entry->family), __entry->saddr, __entry->daddr) ); #endif /* _TRACE_UDP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 4 102 54 102 8 102 25 67 59 65 95 11 55 36 86 87 31 65 88 5 72 29 95 95 4 4 2 2 6 6 25 66 85 6 32 71 94 79 84 84 3 81 94 79 91 1 1 1 4 4 3 5 97 98 4 92 91 1 91 91 70 75 92 92 92 69 42 92 5 5 90 34 61 92 39 47 90 70 70 92 91 23 93 17 3 87 105 80 35 103 4 29 34 53 47 69 19 8 6 27 13 13 89 23 37 91 92 85 137 97 51 16 82 58 58 72 93 13 42 67 4 4 1 5 106 81 25 107 8 33 101 16 89 16 87 103 70 39 94 9 94 95 8 26 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/direct-io.c * * Copyright (C) 2002, Linus Torvalds. * * O_DIRECT * * 04Jul2002 Andrew Morton * Initial version * 11Sep2002 janetinc@us.ibm.com * added readv/writev support. * 29Oct2002 Andrew Morton * rewrote bio_add_page() support. * 30Oct2002 pbadari@us.ibm.com * added support for non-aligned IO. * 06Nov2002 pbadari@us.ibm.com * added asynchronous IO support. * 21Jul2003 nathans@sgi.com * added IO completion notifier. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/wait.h> #include <linux/err.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> #include <linux/rwsem.h> #include <linux/uio.h> #include <linux/atomic.h> #include "internal.h" /* * How many user pages to map in one call to iov_iter_extract_pages(). This * determines the size of a structure in the slab cache */ #define DIO_PAGES 64 /* * Flags for dio_complete() */ #define DIO_COMPLETE_ASYNC 0x01 /* This is async IO */ #define DIO_COMPLETE_INVALIDATE 0x02 /* Can invalidate pages */ /* * This code generally works in units of "dio_blocks". A dio_block is * somewhere between the hard sector size and the filesystem block size. it * is determined on a per-invocation basis. When talking to the filesystem * we need to convert dio_blocks to fs_blocks by scaling the dio_block quantity * down by dio->blkfactor. Similarly, fs-blocksize quantities are converted * to bio_block quantities by shifting left by blkfactor. * * If blkfactor is zero then the user's request was aligned to the filesystem's * blocksize. */ /* dio_state only used in the submission path */ struct dio_submit { struct bio *bio; /* bio under assembly */ unsigned blkbits; /* doesn't change */ unsigned blkfactor; /* When we're using an alignment which is finer than the filesystem's soft blocksize, this specifies how much finer. blkfactor=2 means 1/4-block alignment. Does not change */ unsigned start_zero_done; /* flag: sub-blocksize zeroing has been performed at the start of a write */ int pages_in_io; /* approximate total IO pages */ sector_t block_in_file; /* Current offset into the underlying file in dio_block units. */ unsigned blocks_available; /* At block_in_file. changes */ int reap_counter; /* rate limit reaping */ sector_t final_block_in_request;/* doesn't change */ int boundary; /* prev block is at a boundary */ get_block_t *get_block; /* block mapping function */ loff_t logical_offset_in_bio; /* current first logical block in bio */ sector_t final_block_in_bio; /* current final block in bio + 1 */ sector_t next_block_for_io; /* next block to be put under IO, in dio_blocks units */ /* * Deferred addition of a page to the dio. These variables are * private to dio_send_cur_page(), submit_page_section() and * dio_bio_add_page(). */ struct page *cur_page; /* The page */ unsigned cur_page_offset; /* Offset into it, in bytes */ unsigned cur_page_len; /* Nr of bytes at cur_page_offset */ sector_t cur_page_block; /* Where it starts */ loff_t cur_page_fs_offset; /* Offset in file */ struct iov_iter *iter; /* * Page queue. These variables belong to dio_refill_pages() and * dio_get_page(). */ unsigned head; /* next page to process */ unsigned tail; /* last valid page + 1 */ size_t from, to; }; /* dio_state communicated between submission path and end_io */ struct dio { int flags; /* doesn't change */ blk_opf_t opf; /* request operation type and flags */ struct gendisk *bio_disk; struct inode *inode; loff_t i_size; /* i_size when submitted */ dio_iodone_t *end_io; /* IO completion function */ bool is_pinned; /* T if we have pins on the pages */ void *private; /* copy from map_bh.b_private */ /* BIO completion state */ spinlock_t bio_lock; /* protects BIO fields below */ int page_errors; /* err from iov_iter_extract_pages() */ int is_async; /* is IO async ? */ bool defer_completion; /* defer AIO completion to workqueue? */ bool should_dirty; /* if pages should be dirtied */ int io_error; /* IO error in completion path */ unsigned long refcount; /* direct_io_worker() and bios */ struct bio *bio_list; /* singly linked via bi_private */ struct task_struct *waiter; /* waiting task (NULL if none) */ /* AIO related stuff */ struct kiocb *iocb; /* kiocb */ ssize_t result; /* IO result */ /* * pages[] (and any fields placed after it) are not zeroed out at * allocation time. Don't add new fields after pages[] unless you * wish that they not be zeroed. */ union { struct page *pages[DIO_PAGES]; /* page buffer */ struct work_struct complete_work;/* deferred AIO completion */ }; } ____cacheline_aligned_in_smp; static struct kmem_cache *dio_cache __ro_after_init; /* * How many pages are in the queue? */ static inline unsigned dio_pages_present(struct dio_submit *sdio) { return sdio->tail - sdio->head; } /* * Go grab and pin some userspace pages. Typically we'll get 64 at a time. */ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) { struct page **pages = dio->pages; const enum req_op dio_op = dio->opf & REQ_OP_MASK; ssize_t ret; ret = iov_iter_extract_pages(sdio->iter, &pages, LONG_MAX, DIO_PAGES, 0, &sdio->from); if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) { /* * A memory fault, but the filesystem has some outstanding * mapped blocks. We need to use those blocks up to avoid * leaking stale data in the file. */ if (dio->page_errors == 0) dio->page_errors = ret; dio->pages[0] = ZERO_PAGE(0); sdio->head = 0; sdio->tail = 1; sdio->from = 0; sdio->to = PAGE_SIZE; return 0; } if (ret >= 0) { ret += sdio->from; sdio->head = 0; sdio->tail = (ret + PAGE_SIZE - 1) / PAGE_SIZE; sdio->to = ((ret - 1) & (PAGE_SIZE - 1)) + 1; return 0; } return ret; } /* * Get another userspace page. Returns an ERR_PTR on error. Pages are * buffered inside the dio so that we can call iov_iter_extract_pages() * against a decent number of pages, less frequently. To provide nicer use of * the L1 cache. */ static inline struct page *dio_get_page(struct dio *dio, struct dio_submit *sdio) { if (dio_pages_present(sdio) == 0) { int ret; ret = dio_refill_pages(dio, sdio); if (ret) return ERR_PTR(ret); BUG_ON(dio_pages_present(sdio) == 0); } return dio->pages[sdio->head]; } static void dio_pin_page(struct dio *dio, struct page *page) { if (dio->is_pinned) folio_add_pin(page_folio(page)); } static void dio_unpin_page(struct dio *dio, struct page *page) { if (dio->is_pinned) unpin_user_page(page); } /* * dio_complete() - called when all DIO BIO I/O has been completed * * This drops i_dio_count, lets interested parties know that a DIO operation * has completed, and calculates the resulting return code for the operation. * * It lets the filesystem know if it registered an interest earlier via * get_block. Pass the private field of the map buffer_head so that * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; int err; /* * AIO submission can race with bio completion to get here while * expecting to have the last io completed by bio completion. * In that case -EIOCBQUEUED is in fact not an error we want * to preserve through this call. */ if (ret == -EIOCBQUEUED) ret = 0; if (dio->result) { transferred = dio->result; /* Check for short read case */ if (dio_op == REQ_OP_READ && ((offset + transferred) > dio->i_size)) transferred = dio->i_size - offset; /* ignore EFAULT if some IO has been done */ if (unlikely(ret == -EFAULT) && transferred) ret = 0; } if (ret == 0) ret = dio->page_errors; if (ret == 0) ret = dio->io_error; if (ret == 0) ret = transferred; if (dio->end_io) { // XXX: ki_pos?? err = dio->end_io(dio->iocb, offset, ret, dio->private); if (err) ret = err; } /* * Try again to invalidate clean pages which might have been cached by * non-direct readahead, or faulted in by get_user_pages() if the source * of the write was an mmap'ed region of the file we're writing. Either * one is a pretty crazy thing to do, so we don't support it 100%. If * this invalidation fails, tough, the write still worked... * * And this page cache invalidation has to be after dio->end_io(), as * some filesystems convert unwritten extents to real allocations in * end_io() when necessary, otherwise a racing buffer read would cache * zeros from unwritten extents. */ if (flags & DIO_COMPLETE_INVALIDATE && ret > 0 && dio_op == REQ_OP_WRITE) kiocb_invalidate_post_direct_write(dio->iocb, ret); inode_dio_end(dio->inode); if (flags & DIO_COMPLETE_ASYNC) { /* * generic_write_sync expects ki_pos to have been updated * already, but the submission path only does this for * synchronous I/O. */ dio->iocb->ki_pos += transferred; if (ret > 0 && dio_op == REQ_OP_WRITE) ret = generic_write_sync(dio->iocb, ret); dio->iocb->ki_complete(dio->iocb, ret); } kmem_cache_free(dio_cache, dio); return ret; } static void dio_aio_complete_work(struct work_struct *work) { struct dio *dio = container_of(work, struct dio, complete_work); dio_complete(dio, 0, DIO_COMPLETE_ASYNC | DIO_COMPLETE_INVALIDATE); } static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio); /* * Asynchronous IO callback. */ static void dio_bio_end_aio(struct bio *bio) { struct dio *dio = bio->bi_private; const enum req_op dio_op = dio->opf & REQ_OP_MASK; unsigned long remaining; unsigned long flags; bool defer_completion = false; /* cleanup the bio */ dio_bio_complete(dio, bio); spin_lock_irqsave(&dio->bio_lock, flags); remaining = --dio->refcount; if (remaining == 1 && dio->waiter) wake_up_process(dio->waiter); spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { /* * Defer completion when defer_completion is set or * when the inode has pages mapped and this is AIO write. * We need to invalidate those pages because there is a * chance they contain stale data in the case buffered IO * went in between AIO submission and completion into the * same region. */ if (dio->result) defer_completion = dio->defer_completion || (dio_op == REQ_OP_WRITE && dio->inode->i_mapping->nrpages); if (defer_completion) { INIT_WORK(&dio->complete_work, dio_aio_complete_work); queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); } else { dio_complete(dio, 0, DIO_COMPLETE_ASYNC); } } } /* * The BIO completion handler simply queues the BIO up for the process-context * handler. * * During I/O bi_private points at the dio. After I/O, bi_private is used to * implement a singly-linked list of completed BIOs, at dio->bio_list. */ static void dio_bio_end_io(struct bio *bio) { struct dio *dio = bio->bi_private; unsigned long flags; spin_lock_irqsave(&dio->bio_lock, flags); bio->bi_private = dio->bio_list; dio->bio_list = bio; if (--dio->refcount == 1 && dio->waiter) wake_up_process(dio->waiter); spin_unlock_irqrestore(&dio->bio_lock, flags); } static inline void dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, struct block_device *bdev, sector_t first_sector, int nr_vecs) { struct bio *bio; /* * bio_alloc() is guaranteed to return a bio when allowed to sleep and * we request a valid number of vectors. */ bio = bio_alloc(bdev, nr_vecs, dio->opf, GFP_KERNEL); bio->bi_iter.bi_sector = first_sector; if (dio->is_async) bio->bi_end_io = dio_bio_end_aio; else bio->bi_end_io = dio_bio_end_io; if (dio->is_pinned) bio_set_flag(bio, BIO_PAGE_PINNED); bio->bi_write_hint = file_inode(dio->iocb->ki_filp)->i_write_hint; sdio->bio = bio; sdio->logical_offset_in_bio = sdio->cur_page_fs_offset; } /* * In the AIO read case we speculatively dirty the pages before starting IO. * During IO completion, any of these pages which happen to have been written * back will be redirtied by bio_check_pages_dirty(). * * bios hold a dio reference between submit_bio and ->end_io. */ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; struct bio *bio = sdio->bio; unsigned long flags; bio->bi_private = dio; spin_lock_irqsave(&dio->bio_lock, flags); dio->refcount++; spin_unlock_irqrestore(&dio->bio_lock, flags); if (dio->is_async && dio_op == REQ_OP_READ && dio->should_dirty) bio_set_pages_dirty(bio); dio->bio_disk = bio->bi_bdev->bd_disk; submit_bio(bio); sdio->bio = NULL; sdio->boundary = 0; sdio->logical_offset_in_bio = 0; } /* * Release any resources in case of a failure */ static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio) { if (dio->is_pinned) unpin_user_pages(dio->pages + sdio->head, sdio->tail - sdio->head); sdio->head = sdio->tail; } /* * Wait for the next BIO to complete. Remove it and return it. NULL is * returned once all BIOs have been completed. This must only be called once * all bios have been issued so that dio->refcount can only decrease. This * requires that the caller hold a reference on the dio. */ static struct bio *dio_await_one(struct dio *dio) { unsigned long flags; struct bio *bio = NULL; spin_lock_irqsave(&dio->bio_lock, flags); /* * Wait as long as the list is empty and there are bios in flight. bio * completion drops the count, maybe adds to the list, and wakes while * holding the bio_lock so we don't need set_current_state()'s barrier * and can call it after testing our condition. */ while (dio->refcount > 1 && dio->bio_list == NULL) { __set_current_state(TASK_UNINTERRUPTIBLE); dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); blk_io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); dio->waiter = NULL; } if (dio->bio_list) { bio = dio->bio_list; dio->bio_list = bio->bi_private; } spin_unlock_irqrestore(&dio->bio_lock, flags); return bio; } /* * Process one completed BIO. No locks are held. */ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) { blk_status_t err = bio->bi_status; const enum req_op dio_op = dio->opf & REQ_OP_MASK; bool should_dirty = dio_op == REQ_OP_READ && dio->should_dirty; if (err) { if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT)) dio->io_error = -EAGAIN; else dio->io_error = -EIO; } if (dio->is_async && should_dirty) { bio_check_pages_dirty(bio); /* transfers ownership */ } else { bio_release_pages(bio, should_dirty); bio_put(bio); } return err; } /* * Wait on and process all in-flight BIOs. This must only be called once * all bios have been issued so that the refcount can only decrease. * This just waits for all bios to make it through dio_bio_complete. IO * errors are propagated through dio->io_error and should be propagated via * dio_complete(). */ static void dio_await_completion(struct dio *dio) { struct bio *bio; do { bio = dio_await_one(dio); if (bio) dio_bio_complete(dio, bio); } while (bio); } /* * A really large O_DIRECT read or write can generate a lot of BIOs. So * to keep the memory consumption sane we periodically reap any completed BIOs * during the BIO generation phase. * * This also helps to limit the peak amount of pinned userspace memory. */ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio) { int ret = 0; if (sdio->reap_counter++ >= 64) { while (dio->bio_list) { unsigned long flags; struct bio *bio; int ret2; spin_lock_irqsave(&dio->bio_lock, flags); bio = dio->bio_list; dio->bio_list = bio->bi_private; spin_unlock_irqrestore(&dio->bio_lock, flags); ret2 = blk_status_to_errno(dio_bio_complete(dio, bio)); if (ret == 0) ret = ret2; } sdio->reap_counter = 0; } return ret; } static int dio_set_defer_completion(struct dio *dio) { struct super_block *sb = dio->inode->i_sb; if (dio->defer_completion) return 0; dio->defer_completion = true; if (!sb->s_dio_done_wq) return sb_init_dio_done_wq(sb); return 0; } /* * Call into the fs to map some more disk blocks. We record the current number * of available blocks at sdio->blocks_available. These are in units of the * fs blocksize, i_blocksize(inode). * * The fs is allowed to map lots of blocks at once. If it wants to do that, * it uses the passed inode-relative block number as the file offset, as usual. * * get_block() is passed the number of i_blkbits-sized blocks which direct_io * has remaining to do. The fs should not map more than this number of blocks. * * If the fs has mapped a lot of blocks, it should populate bh->b_size to * indicate how much contiguous disk space has been made available at * bh->b_blocknr. * * If *any* of the mapped blocks are new, then the fs must set buffer_new(). * This isn't very efficient... * * In the case of filesystem holes: the fs may return an arbitrarily-large * hole by returning an appropriate value in b_size and by clearing * buffer_mapped(). However the direct-io code will only process holes one * block at a time - it will repeatedly call get_block() as it walks the hole. */ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, struct buffer_head *map_bh) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; int ret; sector_t fs_startblk; /* Into file, in filesystem-sized blocks */ sector_t fs_endblk; /* Into file, in filesystem-sized blocks */ unsigned long fs_count; /* Number of filesystem-sized blocks */ int create; unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor; loff_t i_size; /* * If there was a memory error and we've overwritten all the * mapped blocks then we can now return that memory error */ ret = dio->page_errors; if (ret == 0) { BUG_ON(sdio->block_in_file >= sdio->final_block_in_request); fs_startblk = sdio->block_in_file >> sdio->blkfactor; fs_endblk = (sdio->final_block_in_request - 1) >> sdio->blkfactor; fs_count = fs_endblk - fs_startblk + 1; map_bh->b_state = 0; map_bh->b_size = fs_count << i_blkbits; /* * For writes that could fill holes inside i_size on a * DIO_SKIP_HOLES filesystem we forbid block creations: only * overwrites are permitted. We will return early to the caller * once we see an unmapped buffer head returned, and the caller * will fall back to buffered I/O. * * Otherwise the decision is left to the get_blocks method, * which may decide to handle it or also return an unmapped * buffer head. */ create = dio_op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { i_size = i_size_read(dio->inode); if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits) create = 0; } ret = (*sdio->get_block)(dio->inode, fs_startblk, map_bh, create); /* Store for completion */ dio->private = map_bh->b_private; if (ret == 0 && buffer_defer_completion(map_bh)) ret = dio_set_defer_completion(dio); } return ret; } /* * There is no bio. Make one now. */ static inline int dio_new_bio(struct dio *dio, struct dio_submit *sdio, sector_t start_sector, struct buffer_head *map_bh) { sector_t sector; int ret, nr_pages; ret = dio_bio_reap(dio, sdio); if (ret) goto out; sector = start_sector << (sdio->blkbits - 9); nr_pages = bio_max_segs(sdio->pages_in_io); BUG_ON(nr_pages <= 0); dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages); sdio->boundary = 0; out: return ret; } /* * Attempt to put the current chunk of 'cur_page' into the current BIO. If * that was successful then update final_block_in_bio and take a ref against * the just-added page. * * Return zero on success. Non-zero means the caller needs to start a new BIO. */ static inline int dio_bio_add_page(struct dio *dio, struct dio_submit *sdio) { int ret; ret = bio_add_page(sdio->bio, sdio->cur_page, sdio->cur_page_len, sdio->cur_page_offset); if (ret == sdio->cur_page_len) { /* * Decrement count only, if we are done with this page */ if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE) sdio->pages_in_io--; dio_pin_page(dio, sdio->cur_page); sdio->final_block_in_bio = sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits); ret = 0; } else { ret = 1; } return ret; } /* * Put cur_page under IO. The section of cur_page which is described by * cur_page_offset,cur_page_len is put into a BIO. The section of cur_page * starts on-disk at cur_page_block. * * We take a ref against the page here (on behalf of its presence in the bio). * * The caller of this function is responsible for removing cur_page from the * dio, and for dropping the refcount which came from that presence. */ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio, struct buffer_head *map_bh) { int ret = 0; if (sdio->bio) { loff_t cur_offset = sdio->cur_page_fs_offset; loff_t bio_next_offset = sdio->logical_offset_in_bio + sdio->bio->bi_iter.bi_size; /* * See whether this new request is contiguous with the old. * * Btrfs cannot handle having logically non-contiguous requests * submitted. For example if you have * * Logical: [0-4095][HOLE][8192-12287] * Physical: [0-4095] [4096-8191] * * We cannot submit those pages together as one BIO. So if our * current logical offset in the file does not equal what would * be the next logical offset in the bio, submit the bio we * have. */ if (sdio->final_block_in_bio != sdio->cur_page_block || cur_offset != bio_next_offset) dio_bio_submit(dio, sdio); } if (sdio->bio == NULL) { ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh); if (ret) goto out; } if (dio_bio_add_page(dio, sdio) != 0) { dio_bio_submit(dio, sdio); ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh); if (ret == 0) { ret = dio_bio_add_page(dio, sdio); BUG_ON(ret != 0); } } out: return ret; } /* * An autonomous function to put a chunk of a page under deferred IO. * * The caller doesn't actually know (or care) whether this piece of page is in * a BIO, or is under IO or whatever. We just take care of all possible * situations here. The separation between the logic of do_direct_IO() and * that of submit_page_section() is important for clarity. Please don't break. * * The chunk of page starts on-disk at blocknr. * * We perform deferred IO, by recording the last-submitted page inside our * private part of the dio structure. If possible, we just expand the IO * across that page here. * * If that doesn't work out then we put the old page into the bio and add this * page to the dio instead. */ static inline int submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, unsigned offset, unsigned len, sector_t blocknr, struct buffer_head *map_bh) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; int ret = 0; int boundary = sdio->boundary; /* dio_send_cur_page may clear it */ if (dio_op == REQ_OP_WRITE) { /* * Read accounting is performed in submit_bio() */ task_io_account_write(len); } /* * Can we just grow the current page's presence in the dio? */ if (sdio->cur_page == page && sdio->cur_page_offset + sdio->cur_page_len == offset && sdio->cur_page_block + (sdio->cur_page_len >> sdio->blkbits) == blocknr) { sdio->cur_page_len += len; goto out; } /* * If there's a deferred page already there then send it. */ if (sdio->cur_page) { ret = dio_send_cur_page(dio, sdio, map_bh); dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; if (ret) return ret; } dio_pin_page(dio, page); /* It is in dio */ sdio->cur_page = page; sdio->cur_page_offset = offset; sdio->cur_page_len = len; sdio->cur_page_block = blocknr; sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits; out: /* * If boundary then we want to schedule the IO now to * avoid metadata seeks. */ if (boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); if (sdio->bio) dio_bio_submit(dio, sdio); dio_unpin_page(dio, sdio->cur_page); sdio->cur_page = NULL; } return ret; } /* * If we are not writing the entire block and get_block() allocated * the block for us, we need to fill-in the unused portion of the * block with zeros. This happens only if user-buffer, fileoffset or * io length is not filesystem block-size multiple. * * `end' is zero if we're doing the start of the IO, 1 at the end of the * IO. */ static inline void dio_zero_block(struct dio *dio, struct dio_submit *sdio, int end, struct buffer_head *map_bh) { unsigned dio_blocks_per_fs_block; unsigned this_chunk_blocks; /* In dio_blocks */ unsigned this_chunk_bytes; struct page *page; sdio->start_zero_done = 1; if (!sdio->blkfactor || !buffer_new(map_bh)) return; dio_blocks_per_fs_block = 1 << sdio->blkfactor; this_chunk_blocks = sdio->block_in_file & (dio_blocks_per_fs_block - 1); if (!this_chunk_blocks) return; /* * We need to zero out part of an fs block. It is either at the * beginning or the end of the fs block. */ if (end) this_chunk_blocks = dio_blocks_per_fs_block - this_chunk_blocks; this_chunk_bytes = this_chunk_blocks << sdio->blkbits; page = ZERO_PAGE(0); if (submit_page_section(dio, sdio, page, 0, this_chunk_bytes, sdio->next_block_for_io, map_bh)) return; sdio->next_block_for_io += this_chunk_blocks; } /* * Walk the user pages, and the file, mapping blocks to disk and generating * a sequence of (page,offset,len,block) mappings. These mappings are injected * into submit_page_section(), which takes care of the next stage of submission * * Direct IO against a blockdev is different from a file. Because we can * happily perform page-sized but 512-byte aligned IOs. It is important that * blockdev IO be able to have fine alignment and large sizes. * * So what we do is to permit the ->get_block function to populate bh.b_size * with the size of IO which is permitted at this offset and this i_blkbits. * * For best results, the blockdev should be set up with 512-byte i_blkbits and * it should set b_size to PAGE_SIZE or more inside get_block(). This gives * fine alignment but still allows this function to work in PAGE_SIZE units. */ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, struct buffer_head *map_bh) { const enum req_op dio_op = dio->opf & REQ_OP_MASK; const unsigned blkbits = sdio->blkbits; const unsigned i_blkbits = blkbits + sdio->blkfactor; int ret = 0; while (sdio->block_in_file < sdio->final_block_in_request) { struct page *page; size_t from, to; page = dio_get_page(dio, sdio); if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } from = sdio->head ? 0 : sdio->from; to = (sdio->head == sdio->tail - 1) ? sdio->to : PAGE_SIZE; sdio->head++; while (from < to) { unsigned this_chunk_bytes; /* # of bytes mapped */ unsigned this_chunk_blocks; /* # of blocks */ unsigned u; if (sdio->blocks_available == 0) { /* * Need to go and map some more disk */ unsigned long blkmask; unsigned long dio_remainder; ret = get_more_blocks(dio, sdio, map_bh); if (ret) { dio_unpin_page(dio, page); goto out; } if (!buffer_mapped(map_bh)) goto do_holes; sdio->blocks_available = map_bh->b_size >> blkbits; sdio->next_block_for_io = map_bh->b_blocknr << sdio->blkfactor; if (buffer_new(map_bh)) { clean_bdev_aliases( map_bh->b_bdev, map_bh->b_blocknr, map_bh->b_size >> i_blkbits); } if (!sdio->blkfactor) goto do_holes; blkmask = (1 << sdio->blkfactor) - 1; dio_remainder = (sdio->block_in_file & blkmask); /* * If we are at the start of IO and that IO * starts partway into a fs-block, * dio_remainder will be non-zero. If the IO * is a read then we can simply advance the IO * cursor to the first block which is to be * read. But if the IO is a write and the * block was newly allocated we cannot do that; * the start of the fs block must be zeroed out * on-disk */ if (!buffer_new(map_bh)) sdio->next_block_for_io += dio_remainder; sdio->blocks_available -= dio_remainder; } do_holes: /* Handle holes */ if (!buffer_mapped(map_bh)) { loff_t i_size_aligned; /* AKPM: eargh, -ENOTBLK is a hack */ if (dio_op == REQ_OP_WRITE) { dio_unpin_page(dio, page); return -ENOTBLK; } /* * Be sure to account for a partial block as the * last block in the file */ i_size_aligned = ALIGN(i_size_read(dio->inode), 1 << blkbits); if (sdio->block_in_file >= i_size_aligned >> blkbits) { /* We hit eof */ dio_unpin_page(dio, page); goto out; } zero_user(page, from, 1 << blkbits); sdio->block_in_file++; from += 1 << blkbits; dio->result += 1 << blkbits; goto next_block; } /* * If we're performing IO which has an alignment which * is finer than the underlying fs, go check to see if * we must zero out the start of this block. */ if (unlikely(sdio->blkfactor && !sdio->start_zero_done)) dio_zero_block(dio, sdio, 0, map_bh); /* * Work out, in this_chunk_blocks, how much disk we * can add to this page */ this_chunk_blocks = sdio->blocks_available; u = (to - from) >> blkbits; if (this_chunk_blocks > u) this_chunk_blocks = u; u = sdio->final_block_in_request - sdio->block_in_file; if (this_chunk_blocks > u) this_chunk_blocks = u; this_chunk_bytes = this_chunk_blocks << blkbits; BUG_ON(this_chunk_bytes == 0); if (this_chunk_blocks == sdio->blocks_available) sdio->boundary = buffer_boundary(map_bh); ret = submit_page_section(dio, sdio, page, from, this_chunk_bytes, sdio->next_block_for_io, map_bh); if (ret) { dio_unpin_page(dio, page); goto out; } sdio->next_block_for_io += this_chunk_blocks; sdio->block_in_file += this_chunk_blocks; from += this_chunk_bytes; dio->result += this_chunk_bytes; sdio->blocks_available -= this_chunk_blocks; next_block: BUG_ON(sdio->block_in_file > sdio->final_block_in_request); if (sdio->block_in_file == sdio->final_block_in_request) break; } /* Drop the pin which was taken in get_user_pages() */ dio_unpin_page(dio, page); } out: return ret; } static inline int drop_refcount(struct dio *dio) { int ret2; unsigned long flags; /* * Sync will always be dropping the final ref and completing the * operation. AIO can if it was a broken operation described above or * in fact if all the bios race to complete before we get here. In * that case dio_complete() translates the EIOCBQUEUED into the proper * return code that the caller will hand to ->complete(). * * This is managed by the bio_lock instead of being an atomic_t so that * completion paths can drop their ref and use the remaining count to * decide to wake the submission path atomically. */ spin_lock_irqsave(&dio->bio_lock, flags); ret2 = --dio->refcount; spin_unlock_irqrestore(&dio->bio_lock, flags); return ret2; } /* * This is a library function for use by filesystem drivers. * * The locking rules are governed by the flags parameter: * - if the flags value contains DIO_LOCKING we use a fancy locking * scheme for dumb filesystems. * For writes this function is called under i_mutex and returns with * i_mutex held, for reads, i_mutex is not held on entry, but it is * taken and dropped again before returning. * - if the flags value does NOT contain DIO_LOCKING we don't use any * internal locking but rather rely on the filesystem to synchronize * direct I/O reads/writes versus each other and truncate. * * To help with locking against truncate we incremented the i_dio_count * counter before starting direct I/O, and decrement it once we are done. * Truncate can wait for it to reach zero to provide exclusion. It is * expected that filesystem provide exclusion between new direct I/O * and truncates. For DIO_LOCKING filesystems this is done by i_mutex, * but other filesystems need to take care of this on their own. * * NOTE: if you pass "sdio" to anything by pointer make sure that function * is always inlined. Otherwise gcc is unable to split the structure into * individual fields and will generate much worse code. This is important * for the whole file. */ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags) { unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; unsigned blocksize_mask = (1 << blkbits) - 1; ssize_t retval = -EINVAL; const size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; const loff_t end = offset + count; struct dio *dio; struct dio_submit sdio = { NULL, }; struct buffer_head map_bh = { 0, }; struct blk_plug plug; unsigned long align = offset | iov_iter_alignment(iter); /* watch out for a 0 len io from a tricksy fs */ if (iov_iter_rw(iter) == READ && !count) return 0; dio = kmem_cache_alloc(dio_cache, GFP_KERNEL); if (!dio) return -ENOMEM; /* * Believe it or not, zeroing out the page array caused a .5% * performance regression in a database benchmark. So, we take * care to only zero out what's needed. */ memset(dio, 0, offsetof(struct dio, pages)); dio->flags = flags; if (dio->flags & DIO_LOCKING && iov_iter_rw(iter) == READ) { /* will be released by direct_io_worker */ inode_lock(inode); } dio->is_pinned = iov_iter_extract_will_pin(iter); /* Once we sampled i_size check for reads beyond EOF */ dio->i_size = i_size_read(inode); if (iov_iter_rw(iter) == READ && offset >= dio->i_size) { retval = 0; goto fail_dio; } if (align & blocksize_mask) { if (bdev) blkbits = blksize_bits(bdev_logical_block_size(bdev)); blocksize_mask = (1 << blkbits) - 1; if (align & blocksize_mask) goto fail_dio; } if (dio->flags & DIO_LOCKING && iov_iter_rw(iter) == READ) { struct address_space *mapping = iocb->ki_filp->f_mapping; retval = filemap_write_and_wait_range(mapping, offset, end - 1); if (retval) goto fail_dio; } /* * For file extending writes updating i_size before data writeouts * complete can expose uninitialized blocks in dumb filesystems. * In that case we need to wait for I/O completion even if asked * for an asynchronous write. */ if (is_sync_kiocb(iocb)) dio->is_async = false; else if (iov_iter_rw(iter) == WRITE && end > i_size_read(inode)) dio->is_async = false; else dio->is_async = true; dio->inode = inode; if (iov_iter_rw(iter) == WRITE) { dio->opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; if (iocb->ki_flags & IOCB_NOWAIT) dio->opf |= REQ_NOWAIT; } else { dio->opf = REQ_OP_READ; } /* * For AIO O_(D)SYNC writes we need to defer completions to a workqueue * so that we can call ->fsync. */ if (dio->is_async && iov_iter_rw(iter) == WRITE) { retval = 0; if (iocb_is_dsync(iocb)) retval = dio_set_defer_completion(dio); else if (!dio->inode->i_sb->s_dio_done_wq) { /* * In case of AIO write racing with buffered read we * need to defer completion. We can't decide this now, * however the workqueue needs to be initialized here. */ retval = sb_init_dio_done_wq(dio->inode->i_sb); } if (retval) goto fail_dio; } /* * Will be decremented at I/O completion time. */ inode_dio_begin(inode); sdio.blkbits = blkbits; sdio.blkfactor = i_blkbits - blkbits; sdio.block_in_file = offset >> blkbits; sdio.get_block = get_block; dio->end_io = end_io; sdio.final_block_in_bio = -1; sdio.next_block_for_io = -1; dio->iocb = iocb; spin_lock_init(&dio->bio_lock); dio->refcount = 1; dio->should_dirty = user_backed_iter(iter) && iov_iter_rw(iter) == READ; sdio.iter = iter; sdio.final_block_in_request = end >> blkbits; /* * In case of non-aligned buffers, we may need 2 more * pages since we need to zero out first and last block. */ if (unlikely(sdio.blkfactor)) sdio.pages_in_io = 2; sdio.pages_in_io += iov_iter_npages(iter, INT_MAX); blk_start_plug(&plug); retval = do_direct_IO(dio, &sdio, &map_bh); if (retval) dio_cleanup(dio, &sdio); if (retval == -ENOTBLK) { /* * The remaining part of the request will be * handled by buffered I/O when we return */ retval = 0; } /* * There may be some unwritten disk at the end of a part-written * fs-block-sized block. Go zero that now. */ dio_zero_block(dio, &sdio, 1, &map_bh); if (sdio.cur_page) { ssize_t ret2; ret2 = dio_send_cur_page(dio, &sdio, &map_bh); if (retval == 0) retval = ret2; dio_unpin_page(dio, sdio.cur_page); sdio.cur_page = NULL; } if (sdio.bio) dio_bio_submit(dio, &sdio); blk_finish_plug(&plug); /* * It is possible that, we return short IO due to end of file. * In that case, we need to release all the pages we got hold on. */ dio_cleanup(dio, &sdio); /* * All block lookups have been performed. For READ requests * we can let i_mutex go now that its achieved its purpose * of protecting us from looking up uninitialized blocks. */ if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING)) inode_unlock(dio->inode); /* * The only time we want to leave bios in flight is when a successful * partial aio read or full aio write have been setup. In that case * bio completion will call aio_complete. The only time it's safe to * call aio_complete is when we return -EIOCBQUEUED, so we key on that. * This had *better* be the only place that raises -EIOCBQUEUED. */ BUG_ON(retval == -EIOCBQUEUED); if (dio->is_async && retval == 0 && dio->result && (iov_iter_rw(iter) == READ || dio->result == count)) retval = -EIOCBQUEUED; else dio_await_completion(dio); if (drop_refcount(dio) == 0) { retval = dio_complete(dio, retval, DIO_COMPLETE_INVALIDATE); } else BUG_ON(retval != -EIOCBQUEUED); return retval; fail_dio: if (dio->flags & DIO_LOCKING && iov_iter_rw(iter) == READ) inode_unlock(inode); kmem_cache_free(dio_cache, dio); return retval; } EXPORT_SYMBOL(__blockdev_direct_IO); static __init int dio_init(void) { dio_cache = KMEM_CACHE(dio, SLAB_PANIC); return 0; } module_init(dio_init) |
| 2 59 61 61 1 1 1 2 3 3 51 5 54 2 54 2 6 1 4 5 44 2 2 5 41 11 11 11 5 11 3 11 7 7 2 1 1 53 13 53 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 | /* * linux/fs/hfs/mdb.c * * Copyright (C) 1995-1997 Paul H. Hargrove * (C) 2003 Ardis Technologies <roman@ardistech.com> * This file may be distributed under the terms of the GNU General Public License. * * This file contains functions for reading/writing the MDB. */ #include <linux/cdrom.h> #include <linux/blkdev.h> #include <linux/nls.h> #include <linux/slab.h> #include "hfs_fs.h" #include "btree.h" /*================ File-local data types ================*/ /* * The HFS Master Directory Block (MDB). * * Also known as the Volume Information Block (VIB), this structure is * the HFS equivalent of a superblock. * * Reference: _Inside Macintosh: Files_ pages 2-59 through 2-62 * * modified for HFS Extended */ static int hfs_get_last_session(struct super_block *sb, sector_t *start, sector_t *size) { struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk); /* default values */ *start = 0; *size = bdev_nr_sectors(sb->s_bdev); if (HFS_SB(sb)->session >= 0) { struct cdrom_tocentry te; if (!cdi) return -EINVAL; te.cdte_track = HFS_SB(sb)->session; te.cdte_format = CDROM_LBA; if (cdrom_read_tocentry(cdi, &te) || (te.cdte_ctrl & CDROM_DATA_TRACK) != 4) { pr_err("invalid session number or type of track\n"); return -EINVAL; } *start = (sector_t)te.cdte_addr.lba << 2; } else if (cdi) { struct cdrom_multisession ms_info; ms_info.addr_format = CDROM_LBA; if (cdrom_multisession(cdi, &ms_info) == 0 && ms_info.xa_flag) *start = (sector_t)ms_info.addr.lba << 2; } return 0; } /* * hfs_mdb_get() * * Build the in-core MDB for a filesystem, including * the B-trees and the volume bitmap. */ int hfs_mdb_get(struct super_block *sb) { struct buffer_head *bh; struct hfs_mdb *mdb, *mdb2; unsigned int block; char *ptr; int off2, len, size, sect; sector_t part_start, part_size; loff_t off; __be16 attrib; /* set the device driver to 512-byte blocks */ size = sb_min_blocksize(sb, HFS_SECTOR_SIZE); if (!size) return -EINVAL; if (hfs_get_last_session(sb, &part_start, &part_size)) return -EINVAL; while (1) { /* See if this is an HFS filesystem */ bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb); if (!bh) goto out; if (mdb->drSigWord == cpu_to_be16(HFS_SUPER_MAGIC)) break; brelse(bh); /* check for a partition block * (should do this only for cdrom/loop though) */ if (hfs_part_find(sb, &part_start, &part_size)) goto out; } HFS_SB(sb)->alloc_blksz = size = be32_to_cpu(mdb->drAlBlkSiz); if (!size || (size & (HFS_SECTOR_SIZE - 1))) { pr_err("bad allocation block size %d\n", size); goto out_bh; } size = min(HFS_SB(sb)->alloc_blksz, (u32)PAGE_SIZE); /* size must be a multiple of 512 */ while (size & (size - 1)) size -= HFS_SECTOR_SIZE; sect = be16_to_cpu(mdb->drAlBlSt) + part_start; /* align block size to first sector */ while (sect & ((size - 1) >> HFS_SECTOR_SIZE_BITS)) size >>= 1; /* align block size to weird alloc size */ while (HFS_SB(sb)->alloc_blksz & (size - 1)) size >>= 1; brelse(bh); if (!sb_set_blocksize(sb, size)) { pr_err("unable to set blocksize to %u\n", size); goto out; } bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb); if (!bh) goto out; if (mdb->drSigWord != cpu_to_be16(HFS_SUPER_MAGIC)) goto out_bh; HFS_SB(sb)->mdb_bh = bh; HFS_SB(sb)->mdb = mdb; /* These parameters are read from the MDB, and never written */ HFS_SB(sb)->part_start = part_start; HFS_SB(sb)->fs_ablocks = be16_to_cpu(mdb->drNmAlBlks); HFS_SB(sb)->fs_div = HFS_SB(sb)->alloc_blksz >> sb->s_blocksize_bits; HFS_SB(sb)->clumpablks = be32_to_cpu(mdb->drClpSiz) / HFS_SB(sb)->alloc_blksz; if (!HFS_SB(sb)->clumpablks) HFS_SB(sb)->clumpablks = 1; HFS_SB(sb)->fs_start = (be16_to_cpu(mdb->drAlBlSt) + part_start) >> (sb->s_blocksize_bits - HFS_SECTOR_SIZE_BITS); /* These parameters are read from and written to the MDB */ HFS_SB(sb)->free_ablocks = be16_to_cpu(mdb->drFreeBks); HFS_SB(sb)->next_id = be32_to_cpu(mdb->drNxtCNID); HFS_SB(sb)->root_files = be16_to_cpu(mdb->drNmFls); HFS_SB(sb)->root_dirs = be16_to_cpu(mdb->drNmRtDirs); HFS_SB(sb)->file_count = be32_to_cpu(mdb->drFilCnt); HFS_SB(sb)->folder_count = be32_to_cpu(mdb->drDirCnt); /* TRY to get the alternate (backup) MDB. */ sect = part_start + part_size - 2; bh = sb_bread512(sb, sect, mdb2); if (bh) { if (mdb2->drSigWord == cpu_to_be16(HFS_SUPER_MAGIC)) { HFS_SB(sb)->alt_mdb_bh = bh; HFS_SB(sb)->alt_mdb = mdb2; } else brelse(bh); } if (!HFS_SB(sb)->alt_mdb) { pr_warn("unable to locate alternate MDB\n"); pr_warn("continuing without an alternate MDB\n"); } HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL); if (!HFS_SB(sb)->bitmap) goto out; /* read in the bitmap */ block = be16_to_cpu(mdb->drVBMSt) + part_start; off = (loff_t)block << HFS_SECTOR_SIZE_BITS; size = (HFS_SB(sb)->fs_ablocks + 8) / 8; ptr = (u8 *)HFS_SB(sb)->bitmap; while (size) { bh = sb_bread(sb, off >> sb->s_blocksize_bits); if (!bh) { pr_err("unable to read volume bitmap\n"); goto out; } off2 = off & (sb->s_blocksize - 1); len = min((int)sb->s_blocksize - off2, size); memcpy(ptr, bh->b_data + off2, len); brelse(bh); ptr += len; off += len; size -= len; } HFS_SB(sb)->ext_tree = hfs_btree_open(sb, HFS_EXT_CNID, hfs_ext_keycmp); if (!HFS_SB(sb)->ext_tree) { pr_err("unable to open extent tree\n"); goto out; } HFS_SB(sb)->cat_tree = hfs_btree_open(sb, HFS_CAT_CNID, hfs_cat_keycmp); if (!HFS_SB(sb)->cat_tree) { pr_err("unable to open catalog tree\n"); goto out; } attrib = mdb->drAtrb; if (!(attrib & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. mounting read-only.\n"); sb->s_flags |= SB_RDONLY; } if ((attrib & cpu_to_be16(HFS_SB_ATTRIB_SLOCK))) { pr_warn("filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= SB_RDONLY; } if (!sb_rdonly(sb)) { /* Mark the volume uncleanly unmounted in case we crash */ attrib &= cpu_to_be16(~HFS_SB_ATTRIB_UNMNT); attrib |= cpu_to_be16(HFS_SB_ATTRIB_INCNSTNT); mdb->drAtrb = attrib; be32_add_cpu(&mdb->drWrCnt, 1); mdb->drLsMod = hfs_mtime(); mark_buffer_dirty(HFS_SB(sb)->mdb_bh); sync_dirty_buffer(HFS_SB(sb)->mdb_bh); } return 0; out_bh: brelse(bh); out: hfs_mdb_put(sb); return -EIO; } /* * hfs_mdb_commit() * * Description: * This updates the MDB on disk. * It does not check, if the superblock has been modified, or * if the filesystem has been mounted read-only. It is mainly * called by hfs_sync_fs() and flush_mdb(). * Input Variable(s): * struct hfs_mdb *mdb: Pointer to the hfs MDB * int backup; * Output Variable(s): * NONE * Returns: * void * Preconditions: * 'mdb' points to a "valid" (struct hfs_mdb). * Postconditions: * The HFS MDB and on disk will be updated, by copying the possibly * modified fields from the in memory MDB (in native byte order) to * the disk block buffer. * If 'backup' is non-zero then the alternate MDB is also written * and the function doesn't return until it is actually on disk. */ void hfs_mdb_commit(struct super_block *sb) { struct hfs_mdb *mdb = HFS_SB(sb)->mdb; if (sb_rdonly(sb)) return; lock_buffer(HFS_SB(sb)->mdb_bh); if (test_and_clear_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags)) { /* These parameters may have been modified, so write them back */ mdb->drLsMod = hfs_mtime(); mdb->drFreeBks = cpu_to_be16(HFS_SB(sb)->free_ablocks); mdb->drNxtCNID = cpu_to_be32(HFS_SB(sb)->next_id); mdb->drNmFls = cpu_to_be16(HFS_SB(sb)->root_files); mdb->drNmRtDirs = cpu_to_be16(HFS_SB(sb)->root_dirs); mdb->drFilCnt = cpu_to_be32(HFS_SB(sb)->file_count); mdb->drDirCnt = cpu_to_be32(HFS_SB(sb)->folder_count); /* write MDB to disk */ mark_buffer_dirty(HFS_SB(sb)->mdb_bh); } /* write the backup MDB, not returning until it is written. * we only do this when either the catalog or extents overflow * files grow. */ if (test_and_clear_bit(HFS_FLG_ALT_MDB_DIRTY, &HFS_SB(sb)->flags) && HFS_SB(sb)->alt_mdb) { hfs_inode_write_fork(HFS_SB(sb)->ext_tree->inode, mdb->drXTExtRec, &mdb->drXTFlSize, NULL); hfs_inode_write_fork(HFS_SB(sb)->cat_tree->inode, mdb->drCTExtRec, &mdb->drCTFlSize, NULL); lock_buffer(HFS_SB(sb)->alt_mdb_bh); memcpy(HFS_SB(sb)->alt_mdb, HFS_SB(sb)->mdb, HFS_SECTOR_SIZE); HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); unlock_buffer(HFS_SB(sb)->alt_mdb_bh); mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh); sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh); } if (test_and_clear_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags)) { struct buffer_head *bh; sector_t block; char *ptr; int off, size, len; block = be16_to_cpu(HFS_SB(sb)->mdb->drVBMSt) + HFS_SB(sb)->part_start; off = (block << HFS_SECTOR_SIZE_BITS) & (sb->s_blocksize - 1); block >>= sb->s_blocksize_bits - HFS_SECTOR_SIZE_BITS; size = (HFS_SB(sb)->fs_ablocks + 7) / 8; ptr = (u8 *)HFS_SB(sb)->bitmap; while (size) { bh = sb_bread(sb, block); if (!bh) { pr_err("unable to read volume bitmap\n"); break; } len = min((int)sb->s_blocksize - off, size); lock_buffer(bh); memcpy(bh->b_data + off, ptr, len); unlock_buffer(bh); mark_buffer_dirty(bh); brelse(bh); block++; off = 0; ptr += len; size -= len; } } unlock_buffer(HFS_SB(sb)->mdb_bh); } void hfs_mdb_close(struct super_block *sb) { /* update volume attributes */ if (sb_rdonly(sb)) return; HFS_SB(sb)->mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); HFS_SB(sb)->mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); mark_buffer_dirty(HFS_SB(sb)->mdb_bh); } /* * hfs_mdb_put() * * Release the resources associated with the in-core MDB. */ void hfs_mdb_put(struct super_block *sb) { if (!HFS_SB(sb)) return; /* free the B-trees */ hfs_btree_close(HFS_SB(sb)->ext_tree); hfs_btree_close(HFS_SB(sb)->cat_tree); /* free the buffers holding the primary and alternate MDBs */ brelse(HFS_SB(sb)->mdb_bh); brelse(HFS_SB(sb)->alt_mdb_bh); unload_nls(HFS_SB(sb)->nls_io); unload_nls(HFS_SB(sb)->nls_disk); kfree(HFS_SB(sb)->bitmap); kfree(HFS_SB(sb)); sb->s_fs_info = NULL; } |
| 6 5 5 3 3 7 7 2 7 7 8 1 1 1 1 1 2 7 7 6 1 5 2 17 17 4 11 6 10 1 2 8 1 1 6 5 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/media/radio/si470x/radio-si470x-usb.c * * USB driver for radios with Silicon Labs Si470x FM Radio Receivers * * Copyright (c) 2009 Tobias Lorenz <tobias.lorenz@gmx.net> */ /* * ToDo: * - add firmware download/update support */ /* driver definitions */ #define DRIVER_AUTHOR "Tobias Lorenz <tobias.lorenz@gmx.net>" #define DRIVER_CARD "Silicon Labs Si470x FM Radio" #define DRIVER_DESC "USB radio driver for Si470x FM Radio Receivers" #define DRIVER_VERSION "1.0.10" /* kernel includes */ #include <linux/usb.h> #include <linux/hid.h> #include <linux/slab.h> #include "radio-si470x.h" /* USB Device ID List */ static const struct usb_device_id si470x_usb_driver_id_table[] = { /* Silicon Labs USB FM Radio Reference Design */ { USB_DEVICE_AND_INTERFACE_INFO(0x10c4, 0x818a, USB_CLASS_HID, 0, 0) }, /* ADS/Tech FM Radio Receiver (formerly Instant FM Music) */ { USB_DEVICE_AND_INTERFACE_INFO(0x06e1, 0xa155, USB_CLASS_HID, 0, 0) }, /* KWorld USB FM Radio SnapMusic Mobile 700 (FM700) */ { USB_DEVICE_AND_INTERFACE_INFO(0x1b80, 0xd700, USB_CLASS_HID, 0, 0) }, /* Sanei Electric, Inc. FM USB Radio (sold as DealExtreme.com PCear) */ { USB_DEVICE_AND_INTERFACE_INFO(0x10c5, 0x819a, USB_CLASS_HID, 0, 0) }, /* Axentia ALERT FM USB Receiver */ { USB_DEVICE_AND_INTERFACE_INFO(0x12cf, 0x7111, USB_CLASS_HID, 0, 0) }, /* Terminating entry */ { } }; MODULE_DEVICE_TABLE(usb, si470x_usb_driver_id_table); /************************************************************************** * Module Parameters **************************************************************************/ /* Radio Nr */ static int radio_nr = -1; module_param(radio_nr, int, 0444); MODULE_PARM_DESC(radio_nr, "Radio Nr"); /* USB timeout */ static unsigned int usb_timeout = 500; module_param(usb_timeout, uint, 0644); MODULE_PARM_DESC(usb_timeout, "USB timeout (ms): *500*"); /* RDS buffer blocks */ static unsigned int rds_buf = 100; module_param(rds_buf, uint, 0444); MODULE_PARM_DESC(rds_buf, "RDS buffer entries: *100*"); /* RDS maximum block errors */ static unsigned short max_rds_errors = 1; /* 0 means 0 errors requiring correction */ /* 1 means 1-2 errors requiring correction (used by original USBRadio.exe) */ /* 2 means 3-5 errors requiring correction */ /* 3 means 6+ errors or errors in checkword, correction not possible */ module_param(max_rds_errors, ushort, 0644); MODULE_PARM_DESC(max_rds_errors, "RDS maximum block errors: *1*"); /************************************************************************** * USB HID Reports **************************************************************************/ /* Reports 1-16 give direct read/write access to the 16 Si470x registers */ /* with the (REPORT_ID - 1) corresponding to the register address across USB */ /* endpoint 0 using GET_REPORT and SET_REPORT */ #define REGISTER_REPORT_SIZE (RADIO_REGISTER_SIZE + 1) #define REGISTER_REPORT(reg) ((reg) + 1) /* Report 17 gives direct read/write access to the entire Si470x register */ /* map across endpoint 0 using GET_REPORT and SET_REPORT */ #define ENTIRE_REPORT_SIZE (RADIO_REGISTER_NUM * RADIO_REGISTER_SIZE + 1) #define ENTIRE_REPORT 17 /* Report 18 is used to send the lowest 6 Si470x registers up the HID */ /* interrupt endpoint 1 to Windows every 20 milliseconds for status */ #define RDS_REPORT_SIZE (RDS_REGISTER_NUM * RADIO_REGISTER_SIZE + 1) #define RDS_REPORT 18 /* Report 19: LED state */ #define LED_REPORT_SIZE 3 #define LED_REPORT 19 /* Report 19: stream */ #define STREAM_REPORT_SIZE 3 #define STREAM_REPORT 19 /* Report 20: scratch */ #define SCRATCH_PAGE_SIZE 63 #define SCRATCH_REPORT_SIZE (SCRATCH_PAGE_SIZE + 1) #define SCRATCH_REPORT 20 /* Reports 19-22: flash upgrade of the C8051F321 */ #define WRITE_REPORT_SIZE 4 #define WRITE_REPORT 19 #define FLASH_REPORT_SIZE 64 #define FLASH_REPORT 20 #define CRC_REPORT_SIZE 3 #define CRC_REPORT 21 #define RESPONSE_REPORT_SIZE 2 #define RESPONSE_REPORT 22 /* Report 23: currently unused, but can accept 60 byte reports on the HID */ /* interrupt out endpoint 2 every 1 millisecond */ #define UNUSED_REPORT 23 #define MAX_REPORT_SIZE 64 /************************************************************************** * Software/Hardware Versions from Scratch Page **************************************************************************/ #define RADIO_HW_VERSION 1 /************************************************************************** * LED State Definitions **************************************************************************/ #define LED_COMMAND 0x35 #define NO_CHANGE_LED 0x00 #define ALL_COLOR_LED 0x01 /* streaming state */ #define BLINK_GREEN_LED 0x02 /* connect state */ #define BLINK_RED_LED 0x04 #define BLINK_ORANGE_LED 0x10 /* disconnect state */ #define SOLID_GREEN_LED 0x20 /* tuning/seeking state */ #define SOLID_RED_LED 0x40 /* bootload state */ #define SOLID_ORANGE_LED 0x80 /************************************************************************** * Stream State Definitions **************************************************************************/ #define STREAM_COMMAND 0x36 #define STREAM_VIDPID 0x00 #define STREAM_AUDIO 0xff /************************************************************************** * Bootloader / Flash Commands **************************************************************************/ /* unique id sent to bootloader and required to put into a bootload state */ #define UNIQUE_BL_ID 0x34 /* mask for the flash data */ #define FLASH_DATA_MASK 0x55 /* bootloader commands */ #define GET_SW_VERSION_COMMAND 0x00 #define SET_PAGE_COMMAND 0x01 #define ERASE_PAGE_COMMAND 0x02 #define WRITE_PAGE_COMMAND 0x03 #define CRC_ON_PAGE_COMMAND 0x04 #define READ_FLASH_BYTE_COMMAND 0x05 #define RESET_DEVICE_COMMAND 0x06 #define GET_HW_VERSION_COMMAND 0x07 #define BLANK 0xff /* bootloader command responses */ #define COMMAND_OK 0x01 #define COMMAND_FAILED 0x02 #define COMMAND_PENDING 0x03 /************************************************************************** * General Driver Functions - REGISTER_REPORTs **************************************************************************/ /* * si470x_get_report - receive a HID report */ static int si470x_get_report(struct si470x_device *radio, void *buf, int size) { unsigned char *report = buf; int retval; retval = usb_control_msg(radio->usbdev, usb_rcvctrlpipe(radio->usbdev, 0), HID_REQ_GET_REPORT, USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_IN, report[0], 2, buf, size, usb_timeout); if (retval < 0) dev_warn(&radio->intf->dev, "si470x_get_report: usb_control_msg returned %d\n", retval); return retval; } /* * si470x_set_report - send a HID report */ static int si470x_set_report(struct si470x_device *radio, void *buf, int size) { unsigned char *report = buf; int retval; retval = usb_control_msg(radio->usbdev, usb_sndctrlpipe(radio->usbdev, 0), HID_REQ_SET_REPORT, USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_OUT, report[0], 2, buf, size, usb_timeout); if (retval < 0) dev_warn(&radio->intf->dev, "si470x_set_report: usb_control_msg returned %d\n", retval); return retval; } /* * si470x_get_register - read register */ static int si470x_get_register(struct si470x_device *radio, int regnr) { int retval; radio->usb_buf[0] = REGISTER_REPORT(regnr); retval = si470x_get_report(radio, radio->usb_buf, REGISTER_REPORT_SIZE); if (retval >= 0) radio->registers[regnr] = get_unaligned_be16(&radio->usb_buf[1]); return (retval < 0) ? -EINVAL : 0; } /* * si470x_set_register - write register */ static int si470x_set_register(struct si470x_device *radio, int regnr) { int retval; radio->usb_buf[0] = REGISTER_REPORT(regnr); put_unaligned_be16(radio->registers[regnr], &radio->usb_buf[1]); retval = si470x_set_report(radio, radio->usb_buf, REGISTER_REPORT_SIZE); return (retval < 0) ? -EINVAL : 0; } /************************************************************************** * General Driver Functions - ENTIRE_REPORT **************************************************************************/ /* * si470x_get_all_registers - read entire registers */ static int si470x_get_all_registers(struct si470x_device *radio) { int retval; unsigned char regnr; radio->usb_buf[0] = ENTIRE_REPORT; retval = si470x_get_report(radio, radio->usb_buf, ENTIRE_REPORT_SIZE); if (retval >= 0) for (regnr = 0; regnr < RADIO_REGISTER_NUM; regnr++) radio->registers[regnr] = get_unaligned_be16( &radio->usb_buf[regnr * RADIO_REGISTER_SIZE + 1]); return (retval < 0) ? -EINVAL : 0; } /************************************************************************** * General Driver Functions - LED_REPORT **************************************************************************/ /* * si470x_set_led_state - sets the led state */ static int si470x_set_led_state(struct si470x_device *radio, unsigned char led_state) { int retval; radio->usb_buf[0] = LED_REPORT; radio->usb_buf[1] = LED_COMMAND; radio->usb_buf[2] = led_state; retval = si470x_set_report(radio, radio->usb_buf, LED_REPORT_SIZE); return (retval < 0) ? -EINVAL : 0; } /************************************************************************** * General Driver Functions - SCRATCH_REPORT **************************************************************************/ /* * si470x_get_scratch_versions - gets the scratch page and version infos */ static int si470x_get_scratch_page_versions(struct si470x_device *radio) { int retval; radio->usb_buf[0] = SCRATCH_REPORT; retval = si470x_get_report(radio, radio->usb_buf, SCRATCH_REPORT_SIZE); if (retval < 0) dev_warn(&radio->intf->dev, "si470x_get_scratch: si470x_get_report returned %d\n", retval); else { radio->software_version = radio->usb_buf[1]; radio->hardware_version = radio->usb_buf[2]; } return (retval < 0) ? -EINVAL : 0; } /************************************************************************** * RDS Driver Functions **************************************************************************/ /* * si470x_int_in_callback - rds callback and processing function * * TODO: do we need to use mutex locks in some sections? */ static void si470x_int_in_callback(struct urb *urb) { struct si470x_device *radio = urb->context; int retval; unsigned char regnr; unsigned char blocknum; unsigned short bler; /* rds block errors */ unsigned short rds; unsigned char tmpbuf[3]; if (urb->status) { if (urb->status == -ENOENT || urb->status == -ECONNRESET || urb->status == -ESHUTDOWN) { return; } else { dev_warn(&radio->intf->dev, "non-zero urb status (%d)\n", urb->status); goto resubmit; /* Maybe we can recover. */ } } /* Sometimes the device returns len 0 packets */ if (urb->actual_length != RDS_REPORT_SIZE) goto resubmit; radio->registers[STATUSRSSI] = get_unaligned_be16(&radio->int_in_buffer[1]); if (radio->registers[STATUSRSSI] & STATUSRSSI_STC) complete(&radio->completion); if ((radio->registers[SYSCONFIG1] & SYSCONFIG1_RDS)) { /* Update RDS registers with URB data */ for (regnr = 1; regnr < RDS_REGISTER_NUM; regnr++) radio->registers[STATUSRSSI + regnr] = get_unaligned_be16(&radio->int_in_buffer[ regnr * RADIO_REGISTER_SIZE + 1]); /* get rds blocks */ if ((radio->registers[STATUSRSSI] & STATUSRSSI_RDSR) == 0) { /* No RDS group ready, better luck next time */ goto resubmit; } if ((radio->registers[STATUSRSSI] & STATUSRSSI_RDSS) == 0) { /* RDS decoder not synchronized */ goto resubmit; } for (blocknum = 0; blocknum < 4; blocknum++) { switch (blocknum) { default: bler = (radio->registers[STATUSRSSI] & STATUSRSSI_BLERA) >> 9; rds = radio->registers[RDSA]; break; case 1: bler = (radio->registers[READCHAN] & READCHAN_BLERB) >> 14; rds = radio->registers[RDSB]; break; case 2: bler = (radio->registers[READCHAN] & READCHAN_BLERC) >> 12; rds = radio->registers[RDSC]; break; case 3: bler = (radio->registers[READCHAN] & READCHAN_BLERD) >> 10; rds = radio->registers[RDSD]; break; } /* Fill the V4L2 RDS buffer */ put_unaligned_le16(rds, &tmpbuf); tmpbuf[2] = blocknum; /* offset name */ tmpbuf[2] |= blocknum << 3; /* received offset */ if (bler > max_rds_errors) tmpbuf[2] |= 0x80; /* uncorrectable errors */ else if (bler > 0) tmpbuf[2] |= 0x40; /* corrected error(s) */ /* copy RDS block to internal buffer */ memcpy(&radio->buffer[radio->wr_index], &tmpbuf, 3); radio->wr_index += 3; /* wrap write pointer */ if (radio->wr_index >= radio->buf_size) radio->wr_index = 0; /* check for overflow */ if (radio->wr_index == radio->rd_index) { /* increment and wrap read pointer */ radio->rd_index += 3; if (radio->rd_index >= radio->buf_size) radio->rd_index = 0; } } if (radio->wr_index != radio->rd_index) wake_up_interruptible(&radio->read_queue); } resubmit: /* Resubmit if we're still running. */ if (radio->int_in_running && radio->usbdev) { retval = usb_submit_urb(radio->int_in_urb, GFP_ATOMIC); if (retval) { dev_warn(&radio->intf->dev, "resubmitting urb failed (%d)", retval); radio->int_in_running = 0; } } radio->status_rssi_auto_update = radio->int_in_running; } static int si470x_fops_open(struct file *file) { return v4l2_fh_open(file); } static int si470x_fops_release(struct file *file) { return v4l2_fh_release(file); } static void si470x_usb_release(struct v4l2_device *v4l2_dev) { struct si470x_device *radio = container_of(v4l2_dev, struct si470x_device, v4l2_dev); usb_free_urb(radio->int_in_urb); v4l2_ctrl_handler_free(&radio->hdl); v4l2_device_unregister(&radio->v4l2_dev); kfree(radio->int_in_buffer); kfree(radio->buffer); kfree(radio->usb_buf); kfree(radio); } /************************************************************************** * Video4Linux Interface **************************************************************************/ /* * si470x_vidioc_querycap - query device capabilities */ static int si470x_vidioc_querycap(struct file *file, void *priv, struct v4l2_capability *capability) { struct si470x_device *radio = video_drvdata(file); strscpy(capability->driver, DRIVER_NAME, sizeof(capability->driver)); strscpy(capability->card, DRIVER_CARD, sizeof(capability->card)); usb_make_path(radio->usbdev, capability->bus_info, sizeof(capability->bus_info)); return 0; } static int si470x_start_usb(struct si470x_device *radio) { int retval; /* initialize interrupt urb */ usb_fill_int_urb(radio->int_in_urb, radio->usbdev, usb_rcvintpipe(radio->usbdev, radio->int_in_endpoint->bEndpointAddress), radio->int_in_buffer, le16_to_cpu(radio->int_in_endpoint->wMaxPacketSize), si470x_int_in_callback, radio, radio->int_in_endpoint->bInterval); radio->int_in_running = 1; mb(); retval = usb_submit_urb(radio->int_in_urb, GFP_KERNEL); if (retval) { dev_info(&radio->intf->dev, "submitting int urb failed (%d)\n", retval); radio->int_in_running = 0; } radio->status_rssi_auto_update = radio->int_in_running; /* start radio */ retval = si470x_start(radio); if (retval < 0) return retval; v4l2_ctrl_handler_setup(&radio->hdl); return retval; } /************************************************************************** * USB Interface **************************************************************************/ /* * si470x_usb_driver_probe - probe for the device */ static int si470x_usb_driver_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct si470x_device *radio; struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor *endpoint; int i, int_end_size, retval; unsigned char version_warning = 0; /* private data allocation and initialization */ radio = kzalloc(sizeof(struct si470x_device), GFP_KERNEL); if (!radio) { retval = -ENOMEM; goto err_initial; } radio->usb_buf = kmalloc(MAX_REPORT_SIZE, GFP_KERNEL); if (radio->usb_buf == NULL) { retval = -ENOMEM; goto err_radio; } radio->usbdev = interface_to_usbdev(intf); radio->intf = intf; radio->band = 1; /* Default to 76 - 108 MHz */ mutex_init(&radio->lock); init_completion(&radio->completion); radio->get_register = si470x_get_register; radio->set_register = si470x_set_register; radio->fops_open = si470x_fops_open; radio->fops_release = si470x_fops_release; radio->vidioc_querycap = si470x_vidioc_querycap; iface_desc = intf->cur_altsetting; /* Set up interrupt endpoint information. */ for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; if (usb_endpoint_is_int_in(endpoint)) radio->int_in_endpoint = endpoint; } if (!radio->int_in_endpoint) { dev_info(&intf->dev, "could not find interrupt in endpoint\n"); retval = -EIO; goto err_usbbuf; } int_end_size = le16_to_cpu(radio->int_in_endpoint->wMaxPacketSize); radio->int_in_buffer = kmalloc(int_end_size, GFP_KERNEL); if (!radio->int_in_buffer) { dev_info(&intf->dev, "could not allocate int_in_buffer"); retval = -ENOMEM; goto err_usbbuf; } radio->int_in_urb = usb_alloc_urb(0, GFP_KERNEL); if (!radio->int_in_urb) { retval = -ENOMEM; goto err_intbuffer; } radio->v4l2_dev.release = si470x_usb_release; /* * The si470x SiLabs reference design uses the same USB IDs as * 'Thanko's Raremono' si4734 based receiver. So check here which we * have: attempt to read the device ID from the si470x: the lower 12 * bits should be 0x0242 for the si470x. * * We use this check to determine which device we are dealing with. */ if (id->idVendor == 0x10c4 && id->idProduct == 0x818a) { retval = usb_control_msg(radio->usbdev, usb_rcvctrlpipe(radio->usbdev, 0), HID_REQ_GET_REPORT, USB_TYPE_CLASS | USB_RECIP_INTERFACE | USB_DIR_IN, 1, 2, radio->usb_buf, 3, 500); if (retval != 3 || (get_unaligned_be16(&radio->usb_buf[1]) & 0xfff) != 0x0242) { dev_info(&intf->dev, "this is not a si470x device.\n"); retval = -ENODEV; goto err_urb; } } retval = v4l2_device_register(&intf->dev, &radio->v4l2_dev); if (retval < 0) { dev_err(&intf->dev, "couldn't register v4l2_device\n"); goto err_urb; } v4l2_ctrl_handler_init(&radio->hdl, 2); v4l2_ctrl_new_std(&radio->hdl, &si470x_ctrl_ops, V4L2_CID_AUDIO_MUTE, 0, 1, 1, 1); v4l2_ctrl_new_std(&radio->hdl, &si470x_ctrl_ops, V4L2_CID_AUDIO_VOLUME, 0, 15, 1, 15); if (radio->hdl.error) { retval = radio->hdl.error; dev_err(&intf->dev, "couldn't register control\n"); goto err_dev; } radio->videodev = si470x_viddev_template; radio->videodev.ctrl_handler = &radio->hdl; radio->videodev.lock = &radio->lock; radio->videodev.v4l2_dev = &radio->v4l2_dev; radio->videodev.release = video_device_release_empty; radio->videodev.device_caps = V4L2_CAP_HW_FREQ_SEEK | V4L2_CAP_READWRITE | V4L2_CAP_TUNER | V4L2_CAP_RADIO | V4L2_CAP_RDS_CAPTURE; video_set_drvdata(&radio->videodev, radio); /* get device and chip versions */ if (si470x_get_all_registers(radio) < 0) { retval = -EIO; goto err_ctrl; } dev_info(&intf->dev, "DeviceID=0x%4.4hx ChipID=0x%4.4hx\n", radio->registers[DEVICEID], radio->registers[SI_CHIPID]); if ((radio->registers[SI_CHIPID] & SI_CHIPID_FIRMWARE) < RADIO_FW_VERSION) { dev_warn(&intf->dev, "This driver is known to work with firmware version %u, but the device has firmware version %u.\n", RADIO_FW_VERSION, radio->registers[SI_CHIPID] & SI_CHIPID_FIRMWARE); version_warning = 1; } /* get software and hardware versions */ if (si470x_get_scratch_page_versions(radio) < 0) { retval = -EIO; goto err_ctrl; } dev_info(&intf->dev, "software version %d, hardware version %d\n", radio->software_version, radio->hardware_version); if (radio->hardware_version < RADIO_HW_VERSION) { dev_warn(&intf->dev, "This driver is known to work with hardware version %u, but the device has hardware version %u.\n", RADIO_HW_VERSION, radio->hardware_version); version_warning = 1; } /* give out version warning */ if (version_warning == 1) { dev_warn(&intf->dev, "If you have some trouble using this driver, please report to V4L ML at linux-media@vger.kernel.org\n"); } /* set led to connect state */ si470x_set_led_state(radio, BLINK_GREEN_LED); /* rds buffer allocation */ radio->buf_size = rds_buf * 3; radio->buffer = kmalloc(radio->buf_size, GFP_KERNEL); if (!radio->buffer) { retval = -EIO; goto err_ctrl; } /* rds buffer configuration */ radio->wr_index = 0; radio->rd_index = 0; init_waitqueue_head(&radio->read_queue); usb_set_intfdata(intf, radio); /* start radio */ retval = si470x_start_usb(radio); if (retval < 0 && !radio->int_in_running) goto err_buf; else if (retval < 0) /* in case of radio->int_in_running == 1 */ goto err_all; /* set initial frequency */ si470x_set_freq(radio, 87.5 * FREQ_MUL); /* available in all regions */ /* register video device */ retval = video_register_device(&radio->videodev, VFL_TYPE_RADIO, radio_nr); if (retval) { dev_err(&intf->dev, "Could not register video device\n"); goto err_all; } return 0; err_all: usb_kill_urb(radio->int_in_urb); err_buf: kfree(radio->buffer); err_ctrl: v4l2_ctrl_handler_free(&radio->hdl); err_dev: v4l2_device_unregister(&radio->v4l2_dev); err_urb: usb_free_urb(radio->int_in_urb); err_intbuffer: kfree(radio->int_in_buffer); err_usbbuf: kfree(radio->usb_buf); err_radio: kfree(radio); err_initial: return retval; } /* * si470x_usb_driver_suspend - suspend the device */ static int si470x_usb_driver_suspend(struct usb_interface *intf, pm_message_t message) { struct si470x_device *radio = usb_get_intfdata(intf); dev_info(&intf->dev, "suspending now...\n"); /* shutdown interrupt handler */ if (radio->int_in_running) { radio->int_in_running = 0; if (radio->int_in_urb) usb_kill_urb(radio->int_in_urb); } /* cancel read processes */ wake_up_interruptible(&radio->read_queue); /* stop radio */ si470x_stop(radio); return 0; } /* * si470x_usb_driver_resume - resume the device */ static int si470x_usb_driver_resume(struct usb_interface *intf) { struct si470x_device *radio = usb_get_intfdata(intf); int ret; dev_info(&intf->dev, "resuming now...\n"); /* start radio */ ret = si470x_start_usb(radio); if (ret == 0) v4l2_ctrl_handler_setup(&radio->hdl); return ret; } /* * si470x_usb_driver_disconnect - disconnect the device */ static void si470x_usb_driver_disconnect(struct usb_interface *intf) { struct si470x_device *radio = usb_get_intfdata(intf); mutex_lock(&radio->lock); v4l2_device_disconnect(&radio->v4l2_dev); video_unregister_device(&radio->videodev); usb_kill_urb(radio->int_in_urb); usb_set_intfdata(intf, NULL); mutex_unlock(&radio->lock); v4l2_device_put(&radio->v4l2_dev); } /* * si470x_usb_driver - usb driver interface * * A note on suspend/resume: this driver had only empty suspend/resume * functions, and when I tried to test suspend/resume it always disconnected * instead of resuming (using my ADS InstantFM stick). So I've decided to * remove these callbacks until someone else with better hardware can * implement and test this. */ static struct usb_driver si470x_usb_driver = { .name = DRIVER_NAME, .probe = si470x_usb_driver_probe, .disconnect = si470x_usb_driver_disconnect, .suspend = si470x_usb_driver_suspend, .resume = si470x_usb_driver_resume, .reset_resume = si470x_usb_driver_resume, .id_table = si470x_usb_driver_id_table, }; module_usb_driver(si470x_usb_driver); MODULE_LICENSE("GPL"); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_VERSION(DRIVER_VERSION); |
| 1 1 1 5 2 3 1 3 2 1 2 2 2 4 4 4 9 1 7 7 8 8 2 4 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple USB RGB LED driver * * Copyright 2016 Heiner Kallweit <hkallweit1@gmail.com> * Based on drivers/hid/hid-thingm.c and * drivers/usb/misc/usbled.c */ #include <linux/hid.h> #include <linux/hidraw.h> #include <linux/leds.h> #include <linux/module.h> #include <linux/mutex.h> #include "hid-ids.h" enum hidled_report_type { RAW_REQUEST, OUTPUT_REPORT }; enum hidled_type { RISO_KAGAKU, DREAM_CHEEKY, THINGM, DELCOM, LUXAFOR, }; static unsigned const char riso_kagaku_tbl[] = { /* R+2G+4B -> riso kagaku color index */ [0] = 0, /* black */ [1] = 2, /* red */ [2] = 1, /* green */ [3] = 5, /* yellow */ [4] = 3, /* blue */ [5] = 6, /* magenta */ [6] = 4, /* cyan */ [7] = 7 /* white */ }; #define RISO_KAGAKU_IX(r, g, b) riso_kagaku_tbl[((r)?1:0)+((g)?2:0)+((b)?4:0)] union delcom_packet { __u8 data[8]; struct { __u8 major_cmd; __u8 minor_cmd; __u8 data_lsb; __u8 data_msb; } tx; struct { __u8 cmd; } rx; struct { __le16 family_code; __le16 security_code; __u8 fw_version; } fw; }; #define DELCOM_GREEN_LED 0 #define DELCOM_RED_LED 1 #define DELCOM_BLUE_LED 2 struct hidled_device; struct hidled_rgb; struct hidled_config { enum hidled_type type; const char *name; const char *short_name; enum led_brightness max_brightness; int num_leds; size_t report_size; enum hidled_report_type report_type; int (*init)(struct hidled_device *ldev); int (*write)(struct led_classdev *cdev, enum led_brightness br); }; struct hidled_led { struct led_classdev cdev; struct hidled_rgb *rgb; char name[32]; }; struct hidled_rgb { struct hidled_device *ldev; struct hidled_led red; struct hidled_led green; struct hidled_led blue; u8 num; }; struct hidled_device { const struct hidled_config *config; struct hid_device *hdev; struct hidled_rgb *rgb; u8 *buf; struct mutex lock; }; #define MAX_REPORT_SIZE 16 #define to_hidled_led(arg) container_of(arg, struct hidled_led, cdev) static bool riso_kagaku_switch_green_blue; module_param(riso_kagaku_switch_green_blue, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(riso_kagaku_switch_green_blue, "switch green and blue RGB component for Riso Kagaku devices"); static int hidled_send(struct hidled_device *ldev, __u8 *buf) { int ret; mutex_lock(&ldev->lock); /* * buffer provided to hid_hw_raw_request must not be on the stack * and must not be part of a data structure */ memcpy(ldev->buf, buf, ldev->config->report_size); if (ldev->config->report_type == RAW_REQUEST) ret = hid_hw_raw_request(ldev->hdev, buf[0], ldev->buf, ldev->config->report_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); else if (ldev->config->report_type == OUTPUT_REPORT) ret = hid_hw_output_report(ldev->hdev, ldev->buf, ldev->config->report_size); else ret = -EINVAL; mutex_unlock(&ldev->lock); if (ret < 0) return ret; return ret == ldev->config->report_size ? 0 : -EMSGSIZE; } /* reading data is supported for report type RAW_REQUEST only */ static int hidled_recv(struct hidled_device *ldev, __u8 *buf) { int ret; if (ldev->config->report_type != RAW_REQUEST) return -EINVAL; mutex_lock(&ldev->lock); memcpy(ldev->buf, buf, ldev->config->report_size); ret = hid_hw_raw_request(ldev->hdev, buf[0], ldev->buf, ldev->config->report_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret < 0) goto err; ret = hid_hw_raw_request(ldev->hdev, buf[0], ldev->buf, ldev->config->report_size, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); memcpy(buf, ldev->buf, ldev->config->report_size); err: mutex_unlock(&ldev->lock); return ret < 0 ? ret : 0; } static u8 riso_kagaku_index(struct hidled_rgb *rgb) { enum led_brightness r, g, b; r = rgb->red.cdev.brightness; g = rgb->green.cdev.brightness; b = rgb->blue.cdev.brightness; if (riso_kagaku_switch_green_blue) return RISO_KAGAKU_IX(r, b, g); else return RISO_KAGAKU_IX(r, g, b); } static int riso_kagaku_write(struct led_classdev *cdev, enum led_brightness br) { struct hidled_led *led = to_hidled_led(cdev); struct hidled_rgb *rgb = led->rgb; __u8 buf[MAX_REPORT_SIZE] = {}; buf[1] = riso_kagaku_index(rgb); return hidled_send(rgb->ldev, buf); } static int dream_cheeky_write(struct led_classdev *cdev, enum led_brightness br) { struct hidled_led *led = to_hidled_led(cdev); struct hidled_rgb *rgb = led->rgb; __u8 buf[MAX_REPORT_SIZE] = {}; buf[1] = rgb->red.cdev.brightness; buf[2] = rgb->green.cdev.brightness; buf[3] = rgb->blue.cdev.brightness; buf[7] = 0x1a; buf[8] = 0x05; return hidled_send(rgb->ldev, buf); } static int dream_cheeky_init(struct hidled_device *ldev) { __u8 buf[MAX_REPORT_SIZE] = {}; /* Dream Cheeky magic */ buf[1] = 0x1f; buf[2] = 0x02; buf[4] = 0x5f; buf[7] = 0x1a; buf[8] = 0x03; return hidled_send(ldev, buf); } static int _thingm_write(struct led_classdev *cdev, enum led_brightness br, u8 offset) { struct hidled_led *led = to_hidled_led(cdev); __u8 buf[MAX_REPORT_SIZE] = { 1, 'c' }; buf[2] = led->rgb->red.cdev.brightness; buf[3] = led->rgb->green.cdev.brightness; buf[4] = led->rgb->blue.cdev.brightness; buf[7] = led->rgb->num + offset; return hidled_send(led->rgb->ldev, buf); } static int thingm_write_v1(struct led_classdev *cdev, enum led_brightness br) { return _thingm_write(cdev, br, 0); } static int thingm_write(struct led_classdev *cdev, enum led_brightness br) { return _thingm_write(cdev, br, 1); } static const struct hidled_config hidled_config_thingm_v1 = { .name = "ThingM blink(1) v1", .short_name = "thingm", .max_brightness = 255, .num_leds = 1, .report_size = 9, .report_type = RAW_REQUEST, .write = thingm_write_v1, }; static int thingm_init(struct hidled_device *ldev) { __u8 buf[MAX_REPORT_SIZE] = { 1, 'v' }; int ret; ret = hidled_recv(ldev, buf); if (ret) return ret; /* Check for firmware major version 1 */ if (buf[3] == '1') ldev->config = &hidled_config_thingm_v1; return 0; } static inline int delcom_get_lednum(const struct hidled_led *led) { if (led == &led->rgb->red) return DELCOM_RED_LED; else if (led == &led->rgb->green) return DELCOM_GREEN_LED; else return DELCOM_BLUE_LED; } static int delcom_enable_led(struct hidled_led *led) { union delcom_packet dp = { .tx.major_cmd = 101, .tx.minor_cmd = 12 }; dp.tx.data_lsb = 1 << delcom_get_lednum(led); dp.tx.data_msb = 0; return hidled_send(led->rgb->ldev, dp.data); } static int delcom_set_pwm(struct hidled_led *led) { union delcom_packet dp = { .tx.major_cmd = 101, .tx.minor_cmd = 34 }; dp.tx.data_lsb = delcom_get_lednum(led); dp.tx.data_msb = led->cdev.brightness; return hidled_send(led->rgb->ldev, dp.data); } static int delcom_write(struct led_classdev *cdev, enum led_brightness br) { struct hidled_led *led = to_hidled_led(cdev); int ret; /* * enable LED * We can't do this in the init function already because the device * is internally reset later. */ ret = delcom_enable_led(led); if (ret) return ret; return delcom_set_pwm(led); } static int delcom_init(struct hidled_device *ldev) { union delcom_packet dp = { .rx.cmd = 104 }; int ret; ret = hidled_recv(ldev, dp.data); if (ret) return ret; /* * Several Delcom devices share the same USB VID/PID * Check for family id 2 for Visual Signal Indicator */ return le16_to_cpu(dp.fw.family_code) == 2 ? 0 : -ENODEV; } static int luxafor_write(struct led_classdev *cdev, enum led_brightness br) { struct hidled_led *led = to_hidled_led(cdev); __u8 buf[MAX_REPORT_SIZE] = { [1] = 1 }; buf[2] = led->rgb->num + 1; buf[3] = led->rgb->red.cdev.brightness; buf[4] = led->rgb->green.cdev.brightness; buf[5] = led->rgb->blue.cdev.brightness; return hidled_send(led->rgb->ldev, buf); } static const struct hidled_config hidled_configs[] = { { .type = RISO_KAGAKU, .name = "Riso Kagaku Webmail Notifier", .short_name = "riso_kagaku", .max_brightness = 1, .num_leds = 1, .report_size = 6, .report_type = OUTPUT_REPORT, .write = riso_kagaku_write, }, { .type = DREAM_CHEEKY, .name = "Dream Cheeky Webmail Notifier", .short_name = "dream_cheeky", .max_brightness = 63, .num_leds = 1, .report_size = 9, .report_type = RAW_REQUEST, .init = dream_cheeky_init, .write = dream_cheeky_write, }, { .type = THINGM, .name = "ThingM blink(1)", .short_name = "thingm", .max_brightness = 255, .num_leds = 2, .report_size = 9, .report_type = RAW_REQUEST, .init = thingm_init, .write = thingm_write, }, { .type = DELCOM, .name = "Delcom Visual Signal Indicator G2", .short_name = "delcom", .max_brightness = 100, .num_leds = 1, .report_size = 8, .report_type = RAW_REQUEST, .init = delcom_init, .write = delcom_write, }, { .type = LUXAFOR, .name = "Greynut Luxafor", .short_name = "luxafor", .max_brightness = 255, .num_leds = 6, .report_size = 9, .report_type = OUTPUT_REPORT, .write = luxafor_write, }, }; static int hidled_init_led(struct hidled_led *led, const char *color_name, struct hidled_rgb *rgb, unsigned int minor) { const struct hidled_config *config = rgb->ldev->config; if (config->num_leds > 1) snprintf(led->name, sizeof(led->name), "%s%u:%s:led%u", config->short_name, minor, color_name, rgb->num); else snprintf(led->name, sizeof(led->name), "%s%u:%s", config->short_name, minor, color_name); led->cdev.name = led->name; led->cdev.max_brightness = config->max_brightness; led->cdev.brightness_set_blocking = config->write; led->cdev.flags = LED_HW_PLUGGABLE; led->rgb = rgb; return devm_led_classdev_register(&rgb->ldev->hdev->dev, &led->cdev); } static int hidled_init_rgb(struct hidled_rgb *rgb, unsigned int minor) { int ret; /* Register the red diode */ ret = hidled_init_led(&rgb->red, "red", rgb, minor); if (ret) return ret; /* Register the green diode */ ret = hidled_init_led(&rgb->green, "green", rgb, minor); if (ret) return ret; /* Register the blue diode */ return hidled_init_led(&rgb->blue, "blue", rgb, minor); } static int hidled_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct hidled_device *ldev; unsigned int minor; int ret, i; ldev = devm_kzalloc(&hdev->dev, sizeof(*ldev), GFP_KERNEL); if (!ldev) return -ENOMEM; ldev->buf = devm_kmalloc(&hdev->dev, MAX_REPORT_SIZE, GFP_KERNEL); if (!ldev->buf) return -ENOMEM; ret = hid_parse(hdev); if (ret) return ret; ldev->hdev = hdev; mutex_init(&ldev->lock); for (i = 0; !ldev->config && i < ARRAY_SIZE(hidled_configs); i++) if (hidled_configs[i].type == id->driver_data) ldev->config = &hidled_configs[i]; if (!ldev->config) return -EINVAL; if (ldev->config->init) { ret = ldev->config->init(ldev); if (ret) return ret; } ldev->rgb = devm_kcalloc(&hdev->dev, ldev->config->num_leds, sizeof(struct hidled_rgb), GFP_KERNEL); if (!ldev->rgb) return -ENOMEM; ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW); if (ret) return ret; minor = ((struct hidraw *) hdev->hidraw)->minor; for (i = 0; i < ldev->config->num_leds; i++) { ldev->rgb[i].ldev = ldev; ldev->rgb[i].num = i; ret = hidled_init_rgb(&ldev->rgb[i], minor); if (ret) { hid_hw_stop(hdev); return ret; } } hid_info(hdev, "%s initialized\n", ldev->config->name); return 0; } static const struct hid_device_id hidled_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_RISO_KAGAKU, USB_DEVICE_ID_RI_KA_WEBMAIL), .driver_data = RISO_KAGAKU }, { HID_USB_DEVICE(USB_VENDOR_ID_DREAM_CHEEKY, USB_DEVICE_ID_DREAM_CHEEKY_WN), .driver_data = DREAM_CHEEKY }, { HID_USB_DEVICE(USB_VENDOR_ID_DREAM_CHEEKY, USB_DEVICE_ID_DREAM_CHEEKY_FA), .driver_data = DREAM_CHEEKY }, { HID_USB_DEVICE(USB_VENDOR_ID_THINGM, USB_DEVICE_ID_BLINK1), .driver_data = THINGM }, { HID_USB_DEVICE(USB_VENDOR_ID_DELCOM, USB_DEVICE_ID_DELCOM_VISUAL_IND), .driver_data = DELCOM }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_LUXAFOR), .driver_data = LUXAFOR }, { } }; MODULE_DEVICE_TABLE(hid, hidled_table); static struct hid_driver hidled_driver = { .name = "hid-led", .probe = hidled_probe, .id_table = hidled_table, }; module_hid_driver(hidled_driver); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Heiner Kallweit <hkallweit1@gmail.com>"); MODULE_DESCRIPTION("Simple USB RGB LED driver"); |
| 1 24 5 2 1 3 4 2 2 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2007-2012 Siemens AG * * Written by: * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Sergey Lapin <slapin@ossfans.org> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #include <linux/if_arp.h> #include <net/mac802154.h> #include <net/ieee802154_netdev.h> #include <net/cfg802154.h> #include "ieee802154_i.h" #include "driver-ops.h" void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); struct ieee802154_local *local = sdata->local; int res; ASSERT_RTNL(); BUG_ON(dev->type != ARPHRD_IEEE802154); res = drv_set_channel(local, page, chan); if (res) { pr_debug("set_channel failed\n"); } else { local->phy->current_channel = chan; local->phy->current_page = page; } } int mac802154_get_params(struct net_device *dev, struct ieee802154_llsec_params *params) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_get_params(&sdata->sec, params); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_set_params(struct net_device *dev, const struct ieee802154_llsec_params *params, int changed) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_set_params(&sdata->sec, params, changed); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_add_key(struct net_device *dev, const struct ieee802154_llsec_key_id *id, const struct ieee802154_llsec_key *key) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_key_add(&sdata->sec, id, key); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_del_key(struct net_device *dev, const struct ieee802154_llsec_key_id *id) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_key_del(&sdata->sec, id); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_add_dev(struct net_device *dev, const struct ieee802154_llsec_device *llsec_dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_dev_add(&sdata->sec, llsec_dev); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_del_dev(struct net_device *dev, __le64 dev_addr) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_dev_del(&sdata->sec, dev_addr); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_add_devkey(struct net_device *dev, __le64 device_addr, const struct ieee802154_llsec_device_key *key) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_devkey_add(&sdata->sec, device_addr, key); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_del_devkey(struct net_device *dev, __le64 device_addr, const struct ieee802154_llsec_device_key *key) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_devkey_del(&sdata->sec, device_addr, key); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_add_seclevel(struct net_device *dev, const struct ieee802154_llsec_seclevel *sl) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_seclevel_add(&sdata->sec, sl); mutex_unlock(&sdata->sec_mtx); return res; } int mac802154_del_seclevel(struct net_device *dev, const struct ieee802154_llsec_seclevel *sl) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); int res; BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); res = mac802154_llsec_seclevel_del(&sdata->sec, sl); mutex_unlock(&sdata->sec_mtx); return res; } void mac802154_lock_table(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_lock(&sdata->sec_mtx); } void mac802154_get_table(struct net_device *dev, struct ieee802154_llsec_table **t) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); BUG_ON(dev->type != ARPHRD_IEEE802154); *t = &sdata->sec.table; } void mac802154_unlock_table(struct net_device *dev) { struct ieee802154_sub_if_data *sdata = IEEE802154_DEV_TO_SUB_IF(dev); BUG_ON(dev->type != ARPHRD_IEEE802154); mutex_unlock(&sdata->sec_mtx); } |
| 27 27 5 5 8 4 8 4 1 3 23 23 2 3 13 23 2 2 2 2 2 2 2 2 2 8 2 1 1 1 1 1 1 1 2 3 3 3 3 3 3 3 3 2 1 1 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 | // SPDX-License-Identifier: GPL-2.0-or-later /* * PPP synchronous tty channel driver for Linux. * * This is a ppp channel driver that can be used with tty device drivers * that are frame oriented, such as synchronous HDLC devices. * * Complete PPP frames without encoding/decoding are exchanged between * the channel driver and the device driver. * * The async map IOCTL codes are implemented to keep the user mode * applications happy if they call them. Synchronous PPP does not use * the async maps. * * Copyright 1999 Paul Mackerras. * * Also touched by the grubby hands of Paul Fulghum paulkf@microgate.com * * This driver provides the encapsulation and framing for sending * and receiving PPP frames over sync serial lines. It relies on * the generic PPP layer to give it frames to send and to process * received frames. It implements the PPP line discipline. * * Part of the code in this driver was inspired by the old async-only * PPP driver, written by Michael Callahan and Al Longyear, and * subsequently hacked by Paul Mackerras. * * ==FILEVERSION 20040616== */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/tty.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/ppp_defs.h> #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/refcount.h> #include <linux/unaligned.h> #include <linux/uaccess.h> #define PPP_VERSION "2.4.2" /* Structure for storing local state. */ struct syncppp { struct tty_struct *tty; unsigned int flags; unsigned int rbits; int mru; spinlock_t xmit_lock; spinlock_t recv_lock; unsigned long xmit_flags; u32 xaccm[8]; u32 raccm; unsigned int bytes_sent; unsigned int bytes_rcvd; struct sk_buff *tpkt; unsigned long last_xmit; struct sk_buff_head rqueue; struct tasklet_struct tsk; refcount_t refcnt; struct completion dead_cmp; struct ppp_channel chan; /* interface to generic ppp layer */ }; /* Bit numbers in xmit_flags */ #define XMIT_WAKEUP 0 #define XMIT_FULL 1 /* Bits in rbits */ #define SC_RCV_BITS (SC_RCV_B7_1|SC_RCV_B7_0|SC_RCV_ODDP|SC_RCV_EVNP) #define PPPSYNC_MAX_RQLEN 32 /* arbitrary */ /* * Prototypes. */ static struct sk_buff* ppp_sync_txmunge(struct syncppp *ap, struct sk_buff *); static int ppp_sync_send(struct ppp_channel *chan, struct sk_buff *skb); static int ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg); static void ppp_sync_process(struct tasklet_struct *t); static int ppp_sync_push(struct syncppp *ap); static void ppp_sync_flush_output(struct syncppp *ap); static void ppp_sync_input(struct syncppp *ap, const u8 *buf, const u8 *flags, int count); static const struct ppp_channel_ops sync_ops = { .start_xmit = ppp_sync_send, .ioctl = ppp_sync_ioctl, }; /* * Utility procedure to print a buffer in hex/ascii */ static void ppp_print_buffer (const char *name, const __u8 *buf, int count) { if (name != NULL) printk(KERN_DEBUG "ppp_synctty: %s, count = %d\n", name, count); print_hex_dump_bytes("", DUMP_PREFIX_NONE, buf, count); } /* * Routines implementing the synchronous PPP line discipline. */ /* * We have a potential race on dereferencing tty->disc_data, * because the tty layer provides no locking at all - thus one * cpu could be running ppp_synctty_receive while another * calls ppp_synctty_close, which zeroes tty->disc_data and * frees the memory that ppp_synctty_receive is using. The best * way to fix this is to use a rwlock in the tty struct, but for now * we use a single global rwlock for all ttys in ppp line discipline. * * FIXME: Fixed in tty_io nowadays. */ static DEFINE_RWLOCK(disc_data_lock); static struct syncppp *sp_get(struct tty_struct *tty) { struct syncppp *ap; read_lock(&disc_data_lock); ap = tty->disc_data; if (ap != NULL) refcount_inc(&ap->refcnt); read_unlock(&disc_data_lock); return ap; } static void sp_put(struct syncppp *ap) { if (refcount_dec_and_test(&ap->refcnt)) complete(&ap->dead_cmp); } /* * Called when a tty is put into sync-PPP line discipline. */ static int ppp_sync_open(struct tty_struct *tty) { struct syncppp *ap; int err; int speed; if (tty->ops->write == NULL) return -EOPNOTSUPP; ap = kzalloc(sizeof(*ap), GFP_KERNEL); err = -ENOMEM; if (!ap) goto out; /* initialize the syncppp structure */ ap->tty = tty; ap->mru = PPP_MRU; spin_lock_init(&ap->xmit_lock); spin_lock_init(&ap->recv_lock); ap->xaccm[0] = ~0U; ap->xaccm[3] = 0x60000000U; ap->raccm = ~0U; skb_queue_head_init(&ap->rqueue); tasklet_setup(&ap->tsk, ppp_sync_process); refcount_set(&ap->refcnt, 1); init_completion(&ap->dead_cmp); ap->chan.private = ap; ap->chan.ops = &sync_ops; ap->chan.mtu = PPP_MRU; ap->chan.hdrlen = 2; /* for A/C bytes */ speed = tty_get_baud_rate(tty); ap->chan.speed = speed; err = ppp_register_channel(&ap->chan); if (err) goto out_free; tty->disc_data = ap; tty->receive_room = 65536; return 0; out_free: kfree(ap); out: return err; } /* * Called when the tty is put into another line discipline * or it hangs up. We have to wait for any cpu currently * executing in any of the other ppp_synctty_* routines to * finish before we can call ppp_unregister_channel and free * the syncppp struct. This routine must be called from * process context, not interrupt or softirq context. */ static void ppp_sync_close(struct tty_struct *tty) { struct syncppp *ap; write_lock_irq(&disc_data_lock); ap = tty->disc_data; tty->disc_data = NULL; write_unlock_irq(&disc_data_lock); if (!ap) return; /* * We have now ensured that nobody can start using ap from now * on, but we have to wait for all existing users to finish. * Note that ppp_unregister_channel ensures that no calls to * our channel ops (i.e. ppp_sync_send/ioctl) are in progress * by the time it returns. */ if (!refcount_dec_and_test(&ap->refcnt)) wait_for_completion(&ap->dead_cmp); tasklet_kill(&ap->tsk); ppp_unregister_channel(&ap->chan); skb_queue_purge(&ap->rqueue); kfree_skb(ap->tpkt); kfree(ap); } /* * Called on tty hangup in process context. * * Wait for I/O to driver to complete and unregister PPP channel. * This is already done by the close routine, so just call that. */ static void ppp_sync_hangup(struct tty_struct *tty) { ppp_sync_close(tty); } /* * Read does nothing - no data is ever available this way. * Pppd reads and writes packets via /dev/ppp instead. */ static ssize_t ppp_sync_read(struct tty_struct *tty, struct file *file, u8 *buf, size_t count, void **cookie, unsigned long offset) { return -EAGAIN; } /* * Write on the tty does nothing, the packets all come in * from the ppp generic stuff. */ static ssize_t ppp_sync_write(struct tty_struct *tty, struct file *file, const u8 *buf, size_t count) { return -EAGAIN; } static int ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct syncppp *ap = sp_get(tty); int __user *p = (int __user *)arg; int err, val; if (!ap) return -ENXIO; err = -EFAULT; switch (cmd) { case PPPIOCGCHAN: err = -EFAULT; if (put_user(ppp_channel_index(&ap->chan), p)) break; err = 0; break; case PPPIOCGUNIT: err = -EFAULT; if (put_user(ppp_unit_number(&ap->chan), p)) break; err = 0; break; case TCFLSH: /* flush our buffers and the serial port's buffer */ if (arg == TCIOFLUSH || arg == TCOFLUSH) ppp_sync_flush_output(ap); err = n_tty_ioctl_helper(tty, cmd, arg); break; case FIONREAD: val = 0; if (put_user(val, p)) break; err = 0; break; default: err = tty_mode_ioctl(tty, cmd, arg); break; } sp_put(ap); return err; } /* May sleep, don't call from interrupt level or with interrupts disabled */ static void ppp_sync_receive(struct tty_struct *tty, const u8 *buf, const u8 *cflags, size_t count) { struct syncppp *ap = sp_get(tty); unsigned long flags; if (!ap) return; spin_lock_irqsave(&ap->recv_lock, flags); ppp_sync_input(ap, buf, cflags, count); spin_unlock_irqrestore(&ap->recv_lock, flags); if (!skb_queue_empty(&ap->rqueue)) tasklet_schedule(&ap->tsk); sp_put(ap); tty_unthrottle(tty); } static void ppp_sync_wakeup(struct tty_struct *tty) { struct syncppp *ap = sp_get(tty); clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (!ap) return; set_bit(XMIT_WAKEUP, &ap->xmit_flags); tasklet_schedule(&ap->tsk); sp_put(ap); } static struct tty_ldisc_ops ppp_sync_ldisc = { .owner = THIS_MODULE, .num = N_SYNC_PPP, .name = "pppsync", .open = ppp_sync_open, .close = ppp_sync_close, .hangup = ppp_sync_hangup, .read = ppp_sync_read, .write = ppp_sync_write, .ioctl = ppp_synctty_ioctl, .receive_buf = ppp_sync_receive, .write_wakeup = ppp_sync_wakeup, }; static int __init ppp_sync_init(void) { int err; err = tty_register_ldisc(&ppp_sync_ldisc); if (err != 0) printk(KERN_ERR "PPP_sync: error %d registering line disc.\n", err); return err; } /* * The following routines provide the PPP channel interface. */ static int ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) { struct syncppp *ap = chan->private; int err, val; u32 accm[8]; void __user *argp = (void __user *)arg; u32 __user *p = argp; err = -EFAULT; switch (cmd) { case PPPIOCGFLAGS: val = ap->flags | ap->rbits; if (put_user(val, (int __user *) argp)) break; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, (int __user *) argp)) break; ap->flags = val & ~SC_RCV_BITS; spin_lock_irq(&ap->recv_lock); ap->rbits = val & SC_RCV_BITS; spin_unlock_irq(&ap->recv_lock); err = 0; break; case PPPIOCGASYNCMAP: if (put_user(ap->xaccm[0], p)) break; err = 0; break; case PPPIOCSASYNCMAP: if (get_user(ap->xaccm[0], p)) break; err = 0; break; case PPPIOCGRASYNCMAP: if (put_user(ap->raccm, p)) break; err = 0; break; case PPPIOCSRASYNCMAP: if (get_user(ap->raccm, p)) break; err = 0; break; case PPPIOCGXASYNCMAP: if (copy_to_user(argp, ap->xaccm, sizeof(ap->xaccm))) break; err = 0; break; case PPPIOCSXASYNCMAP: if (copy_from_user(accm, argp, sizeof(accm))) break; accm[2] &= ~0x40000000U; /* can't escape 0x5e */ accm[3] |= 0x60000000U; /* must escape 0x7d, 0x7e */ memcpy(ap->xaccm, accm, sizeof(ap->xaccm)); err = 0; break; case PPPIOCGMRU: if (put_user(ap->mru, (int __user *) argp)) break; err = 0; break; case PPPIOCSMRU: if (get_user(val, (int __user *) argp)) break; if (val > U16_MAX) { err = -EINVAL; break; } if (val < PPP_MRU) val = PPP_MRU; ap->mru = val; err = 0; break; default: err = -ENOTTY; } return err; } /* * This is called at softirq level to deliver received packets * to the ppp_generic code, and to tell the ppp_generic code * if we can accept more output now. */ static void ppp_sync_process(struct tasklet_struct *t) { struct syncppp *ap = from_tasklet(ap, t, tsk); struct sk_buff *skb; /* process received packets */ while ((skb = skb_dequeue(&ap->rqueue)) != NULL) { if (skb->len == 0) { /* zero length buffers indicate error */ ppp_input_error(&ap->chan, 0); kfree_skb(skb); } else ppp_input(&ap->chan, skb); } /* try to push more stuff out */ if (test_bit(XMIT_WAKEUP, &ap->xmit_flags) && ppp_sync_push(ap)) ppp_output_wakeup(&ap->chan); } /* * Procedures for encapsulation and framing. */ static struct sk_buff* ppp_sync_txmunge(struct syncppp *ap, struct sk_buff *skb) { int proto; unsigned char *data; int islcp; data = skb->data; proto = get_unaligned_be16(data); /* LCP packets with codes between 1 (configure-request) * and 7 (code-reject) must be sent as though no options * have been negotiated. */ islcp = proto == PPP_LCP && 1 <= data[2] && data[2] <= 7; /* compress protocol field if option enabled */ if (data[0] == 0 && (ap->flags & SC_COMP_PROT) && !islcp) skb_pull(skb,1); /* prepend address/control fields if necessary */ if ((ap->flags & SC_COMP_AC) == 0 || islcp) { if (skb_headroom(skb) < 2) { struct sk_buff *npkt = dev_alloc_skb(skb->len + 2); if (npkt == NULL) { kfree_skb(skb); return NULL; } skb_reserve(npkt,2); skb_copy_from_linear_data(skb, skb_put(npkt, skb->len), skb->len); consume_skb(skb); skb = npkt; } skb_push(skb,2); skb->data[0] = PPP_ALLSTATIONS; skb->data[1] = PPP_UI; } ap->last_xmit = jiffies; if (skb && ap->flags & SC_LOG_OUTPKT) ppp_print_buffer ("send buffer", skb->data, skb->len); return skb; } /* * Transmit-side routines. */ /* * Send a packet to the peer over an sync tty line. * Returns 1 iff the packet was accepted. * If the packet was not accepted, we will call ppp_output_wakeup * at some later time. */ static int ppp_sync_send(struct ppp_channel *chan, struct sk_buff *skb) { struct syncppp *ap = chan->private; ppp_sync_push(ap); if (test_and_set_bit(XMIT_FULL, &ap->xmit_flags)) return 0; /* already full */ skb = ppp_sync_txmunge(ap, skb); if (skb != NULL) ap->tpkt = skb; else clear_bit(XMIT_FULL, &ap->xmit_flags); ppp_sync_push(ap); return 1; } /* * Push as much data as possible out to the tty. */ static int ppp_sync_push(struct syncppp *ap) { int sent, done = 0; struct tty_struct *tty = ap->tty; int tty_stuffed = 0; if (!spin_trylock_bh(&ap->xmit_lock)) return 0; for (;;) { if (test_and_clear_bit(XMIT_WAKEUP, &ap->xmit_flags)) tty_stuffed = 0; if (!tty_stuffed && ap->tpkt) { set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); sent = tty->ops->write(tty, ap->tpkt->data, ap->tpkt->len); if (sent < 0) goto flush; /* error, e.g. loss of CD */ if (sent < ap->tpkt->len) { tty_stuffed = 1; } else { consume_skb(ap->tpkt); ap->tpkt = NULL; clear_bit(XMIT_FULL, &ap->xmit_flags); done = 1; } continue; } /* haven't made any progress */ spin_unlock_bh(&ap->xmit_lock); if (!(test_bit(XMIT_WAKEUP, &ap->xmit_flags) || (!tty_stuffed && ap->tpkt))) break; if (!spin_trylock_bh(&ap->xmit_lock)) break; } return done; flush: if (ap->tpkt) { kfree_skb(ap->tpkt); ap->tpkt = NULL; clear_bit(XMIT_FULL, &ap->xmit_flags); done = 1; } spin_unlock_bh(&ap->xmit_lock); return done; } /* * Flush output from our internal buffers. * Called for the TCFLSH ioctl. */ static void ppp_sync_flush_output(struct syncppp *ap) { int done = 0; spin_lock_bh(&ap->xmit_lock); if (ap->tpkt != NULL) { kfree_skb(ap->tpkt); ap->tpkt = NULL; clear_bit(XMIT_FULL, &ap->xmit_flags); done = 1; } spin_unlock_bh(&ap->xmit_lock); if (done) ppp_output_wakeup(&ap->chan); } /* * Receive-side routines. */ /* called when the tty driver has data for us. * * Data is frame oriented: each call to ppp_sync_input is considered * a whole frame. If the 1st flag byte is non-zero then the whole * frame is considered to be in error and is tossed. */ static void ppp_sync_input(struct syncppp *ap, const u8 *buf, const u8 *flags, int count) { struct sk_buff *skb; unsigned char *p; if (count == 0) return; if (ap->flags & SC_LOG_INPKT) ppp_print_buffer ("receive buffer", buf, count); /* stuff the chars in the skb */ skb = dev_alloc_skb(ap->mru + PPP_HDRLEN + 2); if (!skb) { printk(KERN_ERR "PPPsync: no memory (input pkt)\n"); goto err; } /* Try to get the payload 4-byte aligned */ if (buf[0] != PPP_ALLSTATIONS) skb_reserve(skb, 2 + (buf[0] & 1)); if (flags && *flags) { /* error flag set, ignore frame */ goto err; } else if (count > skb_tailroom(skb)) { /* packet overflowed MRU */ goto err; } skb_put_data(skb, buf, count); /* strip address/control field if present */ p = skb->data; if (skb->len >= 2 && p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) { /* chop off address/control */ if (skb->len < 3) goto err; p = skb_pull(skb, 2); } /* PPP packet length should be >= 2 bytes when protocol field is not * compressed. */ if (!(p[0] & 0x01) && skb->len < 2) goto err; /* queue the frame to be processed */ skb_queue_tail(&ap->rqueue, skb); return; err: /* queue zero length packet as error indication */ if (skb || (skb = dev_alloc_skb(0))) { skb_trim(skb, 0); skb_queue_tail(&ap->rqueue, skb); } } static void __exit ppp_sync_cleanup(void) { tty_unregister_ldisc(&ppp_sync_ldisc); } module_init(ppp_sync_init); module_exit(ppp_sync_cleanup); MODULE_DESCRIPTION("PPP synchronous TTY channel module"); MODULE_LICENSE("GPL"); MODULE_ALIAS_LDISC(N_SYNC_PPP); |
| 1984 2000 542 544 240 240 224 225 379 650 377 379 650 379 379 654 650 258 11 248 103 87 18 22 10 22 1 1 1 13 26 26 4309 4307 4309 4312 20 22 4182 4177 80 81 698 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/gfp.h> #include <linux/hugetlb.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/fixmap.h> #include <asm/mtrr.h> #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; EXPORT_SYMBOL(physical_mask); #endif #ifdef CONFIG_HIGHPTE #define PGTABLE_HIGHMEM __GFP_HIGHMEM #else #define PGTABLE_HIGHMEM 0 #endif #ifndef CONFIG_PARAVIRT static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) { tlb_remove_page(tlb, table); } #endif gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM; pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, __userpte_alloc_gfp); } static int __init setup_userpte(char *arg) { if (!arg) return -EINVAL; /* * "userpte=nohigh" disables allocation of user pagetables in * high memory. */ if (strcmp(arg, "nohigh") == 0) __userpte_alloc_gfp &= ~__GFP_HIGHMEM; else return -EINVAL; return 0; } early_param("userpte", setup_userpte); void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) { pagetable_pte_dtor(page_ptdesc(pte)); paravirt_release_pte(page_to_pfn(pte)); paravirt_tlb_remove_table(tlb, pte); } #if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { struct ptdesc *ptdesc = virt_to_ptdesc(pmd); paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT); /* * NOTE! For PAE, any changes to the top page-directory-pointer-table * entries need a full cr3 reload to flush. */ #ifdef CONFIG_X86_PAE tlb->need_flush_all = 1; #endif pagetable_pmd_dtor(ptdesc); paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc)); } #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { struct ptdesc *ptdesc = virt_to_ptdesc(pud); pagetable_pud_dtor(ptdesc); paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); paravirt_tlb_remove_table(tlb, virt_to_page(pud)); } #if CONFIG_PGTABLE_LEVELS > 4 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d) { paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT); paravirt_tlb_remove_table(tlb, virt_to_page(p4d)); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* CONFIG_PGTABLE_LEVELS > 2 */ static inline void pgd_list_add(pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); list_add(&ptdesc->pt_list, &pgd_list); } static inline void pgd_list_del(pgd_t *pgd) { struct ptdesc *ptdesc = virt_to_ptdesc(pgd); list_del(&ptdesc->pt_list); } #define UNSHARED_PTRS_PER_PGD \ (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD) #define MAX_UNSHARED_PTRS_PER_PGD \ MAX_T(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD) static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) { virt_to_ptdesc(pgd)->pt_mm = mm; } struct mm_struct *pgd_page_get_mm(struct page *page) { return page_ptdesc(page)->pt_mm; } static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) { /* If the pgd points to a shared pagetable level (either the ptes in non-PAE, or shared PMD in PAE), then just copy the references from swapper_pg_dir. */ if (CONFIG_PGTABLE_LEVELS == 2 || (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) || CONFIG_PGTABLE_LEVELS >= 4) { clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); } /* list required to sync kernel mapping updates */ if (!SHARED_KERNEL_PMD) { pgd_set_mm(pgd, mm); pgd_list_add(pgd); } } static void pgd_dtor(pgd_t *pgd) { if (SHARED_KERNEL_PMD) return; spin_lock(&pgd_lock); pgd_list_del(pgd); spin_unlock(&pgd_lock); } /* * List of all pgd's needed for non-PAE so it can invalidate entries * in both cached and uncached pgd's; not needed for PAE since the * kernel pmd is shared. If PAE were not to share the pmd a similar * tactic would be needed. This is essentially codepath-based locking * against pageattr.c; it is the unique case in which a valid change * of kernel pagetables can't be lazily synchronized by vmalloc faults. * vmalloc faults work because attached pagetables are never freed. * -- nyc */ #ifdef CONFIG_X86_PAE /* * In PAE mode, we need to do a cr3 reload (=tlb flush) when * updating the top-level pagetable entries to guarantee the * processor notices the update. Since this is expensive, and * all 4 top-level entries are used almost immediately in a * new process's life, we just pre-populate them here. * * Also, if we're in a paravirt environment where the kernel pmd is * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate * and initialize the kernel pmds here. */ #define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD #define MAX_PREALLOCATED_PMDS MAX_UNSHARED_PTRS_PER_PGD /* * We allocate separate PMDs for the kernel part of the user page-table * when PTI is enabled. We need them to map the per-process LDT into the * user-space page-table. */ #define PREALLOCATED_USER_PMDS (boot_cpu_has(X86_FEATURE_PTI) ? \ KERNEL_PGD_PTRS : 0) #define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) { paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); /* Note: almost everything apart from _PAGE_PRESENT is reserved at the pmd (PDPT) level. */ set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT)); /* * According to Intel App note "TLBs, Paging-Structure Caches, * and Their Invalidation", April 2007, document 317080-001, * section 8.1: in PAE mode we explicitly have to flush the * TLB via cr3 if the top-level pgd is changed... */ flush_tlb_mm(mm); } #else /* !CONFIG_X86_PAE */ /* No need to prepopulate any pagetable entries in non-PAE modes. */ #define PREALLOCATED_PMDS 0 #define MAX_PREALLOCATED_PMDS 0 #define PREALLOCATED_USER_PMDS 0 #define MAX_PREALLOCATED_USER_PMDS 0 #endif /* CONFIG_X86_PAE */ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; struct ptdesc *ptdesc; for (i = 0; i < count; i++) if (pmds[i]) { ptdesc = virt_to_ptdesc(pmds[i]); pagetable_pmd_dtor(ptdesc); pagetable_free(ptdesc); mm_dec_nr_pmds(mm); } } static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count) { int i; bool failed = false; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp &= ~__GFP_ACCOUNT; gfp &= ~__GFP_HIGHMEM; for (i = 0; i < count; i++) { pmd_t *pmd = NULL; struct ptdesc *ptdesc = pagetable_alloc(gfp, 0); if (!ptdesc) failed = true; if (ptdesc && !pagetable_pmd_ctor(ptdesc)) { pagetable_free(ptdesc); ptdesc = NULL; failed = true; } if (ptdesc) { mm_inc_nr_pmds(mm); pmd = ptdesc_address(ptdesc); } pmds[i] = pmd; } if (failed) { free_pmds(mm, pmds, count); return -ENOMEM; } return 0; } /* * Mop up any pmd pages which may still be attached to the pgd. * Normally they will be freed by munmap/exit_mmap, but any pmd we * preallocate which never got a corresponding vma will need to be * freed manually. */ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) { pgd_t pgd = *pgdp; if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); mm_dec_nr_pmds(mm); } } static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) { int i; for (i = 0; i < PREALLOCATED_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i]); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!boot_cpu_has(X86_FEATURE_PTI)) return; pgdp = kernel_to_user_pgdp(pgdp); for (i = 0; i < PREALLOCATED_USER_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]); #endif } static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) { p4d_t *p4d; pud_t *pud; int i; p4d = p4d_offset(pgd, 0); pud = pud_offset(p4d, 0); for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) { pmd_t *pmd = pmds[i]; if (i >= KERNEL_PGD_BOUNDARY) memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]), sizeof(pmd_t) * PTRS_PER_PMD); pud_populate(mm, pud, pmd); } } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir); pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd); p4d_t *u_p4d; pud_t *u_pud; int i; u_p4d = p4d_offset(u_pgd, 0); u_pud = pud_offset(u_p4d, 0); s_pgd += KERNEL_PGD_BOUNDARY; u_pud += KERNEL_PGD_BOUNDARY; for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) { pmd_t *pmd = pmds[i]; memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd), sizeof(pmd_t) * PTRS_PER_PMD); pud_populate(mm, u_pud, pmd); } } #else static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { } #endif /* * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also * assumes that pgd should be in one page. * * But kernel with PAE paging that is not running as a Xen domain * only needs to allocate 32 bytes for pgd instead of one page. */ #ifdef CONFIG_X86_PAE #include <linux/slab.h> #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #define PGD_ALIGN 32 static struct kmem_cache *pgd_cache; void __init pgtable_cache_init(void) { /* * When PAE kernel is running as a Xen domain, it does not use * shared kernel pmd. And this requires a whole page for pgd. */ if (!SHARED_KERNEL_PMD) return; /* * when PAE kernel is not running as a Xen domain, it uses * shared kernel pmd. Shared kernel pmd does not require a whole * page for pgd. We are able to just allocate a 32-byte for pgd. * During boot time, we create a 32-byte slab for pgd table allocation. */ pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN, SLAB_PANIC, NULL); } static inline pgd_t *_pgd_alloc(void) { /* * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain. * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, PGD_ALLOCATION_ORDER); /* * Now PAE kernel is not running as a Xen domain. We can allocate * a 32-byte slab for pgd to save memory space. */ return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER); } static inline void _pgd_free(pgd_t *pgd) { if (!SHARED_KERNEL_PMD) free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); else kmem_cache_free(pgd_cache, pgd); } #else static inline pgd_t *_pgd_alloc(void) { return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER, PGD_ALLOCATION_ORDER); } static inline void _pgd_free(pgd_t *pgd) { free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); } #endif /* CONFIG_X86_PAE */ pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS]; pmd_t *pmds[MAX_PREALLOCATED_PMDS]; pgd = _pgd_alloc(); if (pgd == NULL) goto out; mm->pgd = pgd; if (sizeof(pmds) != 0 && preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0) goto out_free_pgd; if (sizeof(u_pmds) != 0 && preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0) goto out_free_pmds; if (paravirt_pgd_alloc(mm) != 0) goto out_free_user_pmds; /* * Make sure that pre-populating the pmds is atomic with * respect to anything walking the pgd_list, so that they * never see a partially populated pgd. */ spin_lock(&pgd_lock); pgd_ctor(mm, pgd); if (sizeof(pmds) != 0) pgd_prepopulate_pmd(mm, pgd, pmds); if (sizeof(u_pmds) != 0) pgd_prepopulate_user_pmd(mm, pgd, u_pmds); spin_unlock(&pgd_lock); return pgd; out_free_user_pmds: if (sizeof(u_pmds) != 0) free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS); out_free_pmds: if (sizeof(pmds) != 0) free_pmds(mm, pmds, PREALLOCATED_PMDS); out_free_pgd: _pgd_free(pgd); out: return NULL; } void pgd_free(struct mm_struct *mm, pgd_t *pgd) { pgd_mop_up_pmds(mm, pgd); pgd_dtor(pgd); paravirt_pgd_free(mm, pgd); _pgd_free(pgd); } /* * Used to set accessed or dirty bits in the page table entries * on other architectures. On x86, the accessed and dirty bits * are tracked by hardware. However, do_wp_page calls this function * to also make the pte writeable at the same time the dirty bit is * set. In that case we do actually need to write the PTE. */ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { int changed = !pte_same(*ptep, entry); if (changed && dirty) set_pte(ptep, entry); return changed; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { int changed = !pmd_same(*pmdp, entry); VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, * #PF is architecturally guaranteed to do that and in the * worst-case we'll generate a spurious fault. */ } return changed; } int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { int changed = !pud_same(*pudp, entry); VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, * #PF is architecturally guaranteed to do that and in the * worst-case we'll generate a spurious fault. */ } return changed; } #endif int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { int ret = 0; if (pte_young(*ptep)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *) &ptep->pte); return ret; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { int ret = 0; if (pmd_young(*pmdp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pmdp); return ret; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp) { int ret = 0; if (pud_young(*pudp)) ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pudp); return ret; } #endif int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { /* * On x86 CPUs, clearing the accessed bit without a TLB flush * doesn't cause data corruption. [ It could cause incorrect * page aging and the (mistaken) reclaim of hot pages, but the * chance of that should be relatively low. ] * * So as a performance optimization don't flush the TLB when * clearing the accessed bit, it will eventually be flushed by * a context switch or a VM operation anyway. [ In the rare * event of it not getting flushed for a long time the delay * shouldn't really matter because there's no real memory * pressure for swapout to react to. ] */ return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { int young; VM_BUG_ON(address & ~HPAGE_PMD_MASK); young = pmdp_test_and_clear_young(vma, address, pmdp); if (young) flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return young; } pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { VM_WARN_ON_ONCE(!pmd_present(*pmdp)); /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. */ return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp)); } #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, pud_t *pudp) { VM_WARN_ON_ONCE(!pud_present(*pudp)); pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp)); flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); return old; } #endif /** * reserve_top_address - reserves a hole in the top of kernel address space * @reserve - size of hole to reserve * * Can be used to relocate the fixmap area and poke a hole in the top * of kernel address space to make room for a hypervisor. */ void __init reserve_top_address(unsigned long reserve) { #ifdef CONFIG_X86_32 BUG_ON(fixmaps_set > 0); __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", -reserve, __FIXADDR_TOP + PAGE_SIZE); #endif } int fixmaps_set; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) { unsigned long address = __fix_to_virt(idx); #ifdef CONFIG_X86_64 /* * Ensure that the static initial page tables are covering the * fixmap completely. */ BUILD_BUG_ON(__end_of_permanent_fixed_addresses > (FIXMAP_PMD_NUM * PTRS_PER_PTE)); #endif if (idx >= __end_of_fixed_addresses) { BUG(); return; } set_pte_vaddr(address, pte); fixmaps_set++; } void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) { /* Sanitize 'prot' against any unsupported bits: */ pgprot_val(flags) &= __default_kernel_pte_mask; __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #ifdef CONFIG_X86_5LEVEL /** * p4d_set_huge - setup kernel P4D mapping * * No 512GB pages yet -- always return 0 */ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } /** * p4d_clear_huge - clear kernel P4D mapping when it is set * * No 512GB pages yet -- always return 0 */ void p4d_clear_huge(p4d_t *p4d) { } #endif /** * pud_set_huge - setup kernel PUD mapping * * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this * function sets up a huge page only if the complete range has the same MTRR * caching mode. * * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger * page mapping attempt fails. * * Returns 1 on success and 0 on failure. */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { u8 uniform; mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform); if (!uniform) return 0; /* Bail out if we are we on a populated non-leaf entry: */ if (pud_present(*pud) && !pud_leaf(*pud)) return 0; set_pte((pte_t *)pud, pfn_pte( (u64)addr >> PAGE_SHIFT, __pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE))); return 1; } /** * pmd_set_huge - setup kernel PMD mapping * * See text over pud_set_huge() above. * * Returns 1 on success and 0 on failure. */ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { u8 uniform; mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform); if (!uniform) { pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n", __func__, addr, addr + PMD_SIZE); return 0; } /* Bail out if we are we on a populated non-leaf entry: */ if (pmd_present(*pmd) && !pmd_leaf(*pmd)) return 0; set_pte((pte_t *)pmd, pfn_pte( (u64)addr >> PAGE_SHIFT, __pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE))); return 1; } /** * pud_clear_huge - clear kernel PUD mapping when it is set * * Returns 1 on success and 0 on failure (no PUD map is found). */ int pud_clear_huge(pud_t *pud) { if (pud_leaf(*pud)) { pud_clear(pud); return 1; } return 0; } /** * pmd_clear_huge - clear kernel PMD mapping when it is set * * Returns 1 on success and 0 on failure (no PMD map is found). */ int pmd_clear_huge(pmd_t *pmd) { if (pmd_leaf(*pmd)) { pmd_clear(pmd); return 1; } return 0; } #ifdef CONFIG_X86_64 /** * pud_free_pmd_page - Clear pud entry and free pmd page. * @pud: Pointer to a PUD. * @addr: Virtual address associated with pud. * * Context: The pud range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. * * NOTE: Callers must allow a single page allocation. */ int pud_free_pmd_page(pud_t *pud, unsigned long addr) { pmd_t *pmd, *pmd_sv; pte_t *pte; int i; pmd = pud_pgtable(*pud); pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL); if (!pmd_sv) return 0; for (i = 0; i < PTRS_PER_PMD; i++) { pmd_sv[i] = pmd[i]; if (!pmd_none(pmd[i])) pmd_clear(&pmd[i]); } pud_clear(pud); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); for (i = 0; i < PTRS_PER_PMD; i++) { if (!pmd_none(pmd_sv[i])) { pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]); free_page((unsigned long)pte); } } free_page((unsigned long)pmd_sv); pagetable_pmd_dtor(virt_to_ptdesc(pmd)); free_page((unsigned long)pmd); return 1; } /** * pmd_free_pte_page - Clear pmd entry and free pte page. * @pmd: Pointer to a PMD. * @addr: Virtual address associated with pmd. * * Context: The pmd range has been unmapped and TLB purged. * Return: 1 if clearing the entry succeeded. 0 otherwise. */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { pte_t *pte; pte = (pte_t *)pmd_page_vaddr(*pmd); pmd_clear(pmd); /* INVLPG to clear all paging-structure caches */ flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1); free_page((unsigned long)pte); return 1; } #else /* !CONFIG_X86_64 */ /* * Disable free page handling on x86-PAE. This assures that ioremap() * does not update sync'd pmd entries. See vmalloc_sync_one(). */ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return pmd_none(*pmd); } #endif /* CONFIG_X86_64 */ #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHADOW_STACK) return pte_mkwrite_shstk(pte); pte = pte_mkwrite_novma(pte); return pte_clear_saveddirty(pte); } pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (vma->vm_flags & VM_SHADOW_STACK) return pmd_mkwrite_shstk(pmd); pmd = pmd_mkwrite_novma(pmd); return pmd_clear_saveddirty(pmd); } void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte) { /* * Hardware before shadow stack can (rarely) set Dirty=1 * on a Write=0 PTE. So the below condition * only indicates a software bug when shadow stack is * supported by the HW. This checking is covered in * pte_shstk(). */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pte_shstk(pte)); } void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd) { /* See note in arch_check_zapped_pte() */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pmd_shstk(pmd)); } void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud) { /* See note in arch_check_zapped_pte() */ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pud_shstk(pud)); } |
| 1 1 1 18 7 11 11 10 5 3 2 2 1 1 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 | // SPDX-License-Identifier: GPL-2.0 /* * Support for async notification of waitid */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "io_uring.h" #include "cancel.h" #include "waitid.h" #include "../kernel/exit.h" static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts); #define IO_WAITID_CANCEL_FLAG BIT(31) #define IO_WAITID_REF_MASK GENMASK(30, 0) struct io_waitid { struct file *file; int which; pid_t upid; int options; atomic_t refs; struct wait_queue_head *head; struct siginfo __user *infop; struct waitid_info info; }; static void io_waitid_free(struct io_kiocb *req) { struct io_waitid_async *iwa = req->async_data; put_pid(iwa->wo.wo_pid); kfree(req->async_data); req->async_data = NULL; req->flags &= ~REQ_F_ASYNC_DATA; } #ifdef CONFIG_COMPAT static bool io_waitid_compat_copy_si(struct io_waitid *iw, int signo) { struct compat_siginfo __user *infop; bool ret; infop = (struct compat_siginfo __user *) iw->infop; if (!user_write_access_begin(infop, sizeof(*infop))) return false; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(iw->info.cause, &infop->si_code, Efault); unsafe_put_user(iw->info.pid, &infop->si_pid, Efault); unsafe_put_user(iw->info.uid, &infop->si_uid, Efault); unsafe_put_user(iw->info.status, &infop->si_status, Efault); ret = true; done: user_write_access_end(); return ret; Efault: ret = false; goto done; } #endif static bool io_waitid_copy_si(struct io_kiocb *req, int signo) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); bool ret; if (!iw->infop) return true; #ifdef CONFIG_COMPAT if (req->ctx->compat) return io_waitid_compat_copy_si(iw, signo); #endif if (!user_write_access_begin(iw->infop, sizeof(*iw->infop))) return false; unsafe_put_user(signo, &iw->infop->si_signo, Efault); unsafe_put_user(0, &iw->infop->si_errno, Efault); unsafe_put_user(iw->info.cause, &iw->infop->si_code, Efault); unsafe_put_user(iw->info.pid, &iw->infop->si_pid, Efault); unsafe_put_user(iw->info.uid, &iw->infop->si_uid, Efault); unsafe_put_user(iw->info.status, &iw->infop->si_status, Efault); ret = true; done: user_write_access_end(); return ret; Efault: ret = false; goto done; } static int io_waitid_finish(struct io_kiocb *req, int ret) { int signo = 0; if (ret > 0) { signo = SIGCHLD; ret = 0; } if (!io_waitid_copy_si(req, signo)) ret = -EFAULT; io_waitid_free(req); return ret; } static void io_waitid_complete(struct io_kiocb *req, int ret) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct io_tw_state ts = {}; /* anyone completing better be holding a reference */ WARN_ON_ONCE(!(atomic_read(&iw->refs) & IO_WAITID_REF_MASK)); lockdep_assert_held(&req->ctx->uring_lock); hlist_del_init(&req->hash_node); ret = io_waitid_finish(req, ret); if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); io_req_task_complete(req, &ts); } static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct io_waitid_async *iwa = req->async_data; /* * Mark us canceled regardless of ownership. This will prevent a * potential retry from a spurious wakeup. */ atomic_or(IO_WAITID_CANCEL_FLAG, &iw->refs); /* claim ownership */ if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) return false; spin_lock_irq(&iw->head->lock); list_del_init(&iwa->wo.child_wait.entry); spin_unlock_irq(&iw->head->lock); io_waitid_complete(req, -ECANCELED); return true; } int io_waitid_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd, unsigned int issue_flags) { struct hlist_node *tmp; struct io_kiocb *req; int nr = 0; if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED)) return -ENOENT; io_ring_submit_lock(ctx, issue_flags); hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { if (req->cqe.user_data != cd->data && !(cd->flags & IORING_ASYNC_CANCEL_ANY)) continue; if (__io_waitid_cancel(ctx, req)) nr++; if (!(cd->flags & IORING_ASYNC_CANCEL_ALL)) break; } io_ring_submit_unlock(ctx, issue_flags); if (nr) return nr; return -ENOENT; } bool io_waitid_remove_all(struct io_ring_ctx *ctx, struct task_struct *task, bool cancel_all) { struct hlist_node *tmp; struct io_kiocb *req; bool found = false; lockdep_assert_held(&ctx->uring_lock); hlist_for_each_entry_safe(req, tmp, &ctx->waitid_list, hash_node) { if (!io_match_task_safe(req, task, cancel_all)) continue; hlist_del_init(&req->hash_node); __io_waitid_cancel(ctx, req); found = true; } return found; } static inline bool io_waitid_drop_issue_ref(struct io_kiocb *req) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct io_waitid_async *iwa = req->async_data; if (!atomic_sub_return(1, &iw->refs)) return false; /* * Wakeup triggered, racing with us. It was prevented from * completing because of that, queue up the tw to do that. */ req->io_task_work.func = io_waitid_cb; io_req_task_work_add(req); remove_wait_queue(iw->head, &iwa->wo.child_wait); return true; } static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts) { struct io_waitid_async *iwa = req->async_data; struct io_ring_ctx *ctx = req->ctx; int ret; io_tw_lock(ctx, ts); ret = __do_wait(&iwa->wo); /* * If we get -ERESTARTSYS here, we need to re-arm and check again * to ensure we get another callback. If the retry works, then we can * just remove ourselves from the waitqueue again and finish the * request. */ if (unlikely(ret == -ERESTARTSYS)) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); /* Don't retry if cancel found it meanwhile */ ret = -ECANCELED; if (!(atomic_read(&iw->refs) & IO_WAITID_CANCEL_FLAG)) { iw->head = ¤t->signal->wait_chldexit; add_wait_queue(iw->head, &iwa->wo.child_wait); ret = __do_wait(&iwa->wo); if (ret == -ERESTARTSYS) { /* retry armed, drop our ref */ io_waitid_drop_issue_ref(req); return; } remove_wait_queue(iw->head, &iwa->wo.child_wait); } } io_waitid_complete(req, ret); } static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); struct io_waitid_async *iwa = container_of(wo, struct io_waitid_async, wo); struct io_kiocb *req = iwa->req; struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct task_struct *p = key; if (!pid_child_should_wake(wo, p)) return 0; /* cancel is in progress */ if (atomic_fetch_inc(&iw->refs) & IO_WAITID_REF_MASK) return 1; req->io_task_work.func = io_waitid_cb; io_req_task_work_add(req); list_del_init(&wait->entry); return 1; } int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); if (sqe->addr || sqe->buf_index || sqe->addr3 || sqe->waitid_flags) return -EINVAL; iw->which = READ_ONCE(sqe->len); iw->upid = READ_ONCE(sqe->fd); iw->options = READ_ONCE(sqe->file_index); iw->infop = u64_to_user_ptr(READ_ONCE(sqe->addr2)); return 0; } int io_waitid(struct io_kiocb *req, unsigned int issue_flags) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); struct io_ring_ctx *ctx = req->ctx; struct io_waitid_async *iwa; int ret; if (io_alloc_async_data(req)) return -ENOMEM; iwa = req->async_data; iwa->req = req; ret = kernel_waitid_prepare(&iwa->wo, iw->which, iw->upid, &iw->info, iw->options, NULL); if (ret) goto done; /* * Mark the request as busy upfront, in case we're racing with the * wakeup. If we are, then we'll notice when we drop this initial * reference again after arming. */ atomic_set(&iw->refs, 1); /* * Cancel must hold the ctx lock, so there's no risk of cancelation * finding us until a) we remain on the list, and b) the lock is * dropped. We only need to worry about racing with the wakeup * callback. */ io_ring_submit_lock(ctx, issue_flags); hlist_add_head(&req->hash_node, &ctx->waitid_list); init_waitqueue_func_entry(&iwa->wo.child_wait, io_waitid_wait); iwa->wo.child_wait.private = req->task; iw->head = ¤t->signal->wait_chldexit; add_wait_queue(iw->head, &iwa->wo.child_wait); ret = __do_wait(&iwa->wo); if (ret == -ERESTARTSYS) { /* * Nobody else grabbed a reference, it'll complete when we get * a waitqueue callback, or if someone cancels it. */ if (!io_waitid_drop_issue_ref(req)) { io_ring_submit_unlock(ctx, issue_flags); return IOU_ISSUE_SKIP_COMPLETE; } /* * Wakeup triggered, racing with us. It was prevented from * completing because of that, queue up the tw to do that. */ io_ring_submit_unlock(ctx, issue_flags); return IOU_ISSUE_SKIP_COMPLETE; } hlist_del_init(&req->hash_node); remove_wait_queue(iw->head, &iwa->wo.child_wait); ret = io_waitid_finish(req, ret); io_ring_submit_unlock(ctx, issue_flags); done: if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); return IOU_OK; } |
| 14722 2081 13092 89 90 90 16 89 396 2 379 375 10 11 10 9 385 7 376 376 2 21 19 2 18 95 149 1420 12684 317 318 318 29 29 28 28 28 29 27 1 1 695 98 828 59 270 172 328 152 155 142 689 691 825 52 812 39 54 457 165 14906 20 12859 12907 12952 931 12148 13001 1156 15047 5 9 17 5 17 22 25 27 3 12 13 1 2 11 17 4 15 13 13 4 4 2 11 9 9 6 4 21 1 11 2 11 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, Oracle * (C) 2002-2004 Ingo Molnar, Red Hat * * pid-structures are backing objects for tasks sharing a given ID to chain * against. There is very little to them aside from hashing them and * parking tasks using given ID's on a list. * * The hash is always changed with the tasklist_lock write-acquired, * and the hash is only accessed with the tasklist_lock at least * read-acquired, so there's no additional SMP locking needed here. * * We have a list of bitmap pages, which bitmaps represent the PID space. * Allocating and freeing PIDs is completely lockless. The worst-case * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). * * Pid namespaces: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/memblock.h> #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> #include <linux/pidfs.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, { .first = NULL }, }, .level = 0, .numbers = { { .nr = 0, .ns = &init_pid_ns, }, } }; int pid_max = PID_MAX_DEFAULT; int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; /* * Pseudo filesystems start inode numbering after one. We use Reserved * PIDs as a natural offset. */ static u64 pidfs_ino = RESERVED_PIDS; /* * PID-map pages start out as NULL, they get allocated upon * first use and are never deallocated. This way a low pid_max * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { .ns.count = REFCOUNT_INIT(2), .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, .user_ns = &init_user_ns, .ns.inum = PROC_PID_INIT_INO, #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) .memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC, #endif }; EXPORT_SYMBOL_GPL(init_pid_ns); /* * Note: disable interrupts while the pidmap_lock is held as an * interrupt might come in and do read_lock(&tasklist_lock). * * If we don't disable interrupts there is a nasty deadlock between * detach_pid()->free_pid() and another cpu that does * spin_lock(&pidmap_lock) followed by an interrupt routine that does * read_lock(&tasklist_lock); * * After we clean up the tasklist_lock and know there are no * irq handlers that take it we can leave the interrupts enabled. * For now it is easier to be safe than to prove it can't happen. */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); } void free_pid(struct pid *pid) { /* We can be called with write_lock_irq(&tasklist_lock) held */ int i; unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(ns->child_reaper); break; case PIDNS_ADDING: /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; break; } idr_remove(&ns->idr, upid->nr); } spin_unlock_irqrestore(&pidmap_lock, flags); call_rcu(&pid->rcu, delayed_put_pid); } struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size) { struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; /* * set_tid_size contains the size of the set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but set_tid_size must * never be greater than the current ns->level + 1. */ if (set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL); pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); tmp = ns; pid->level = ns->level; for (i = ns->level; i >= 0; i--) { int tid = 0; if (set_tid_size) { tid = set_tid[ns->level - i]; retval = -EINVAL; if (tid < 1 || tid >= pid_max) goto out_free; /* * Also fail if a PID != 1 is requested and * no PID 1 exists. */ if (tid != 1 && !tmp->child_reaper) goto out_free; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_free; set_tid_size--; } idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * init really needs pid 1, but after reaching the * maximum wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max, GFP_ATOMIC); } spin_unlock_irq(&pidmap_lock); idr_preload_end(); if (nr < 0) { retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; tmp = tmp->parent; } /* * ENOMEM is not the most obvious choice especially for the case * where the child subreaper has already exited and the pid * namespace denies the creation of any new processes. But ENOMEM * is what we have exposed to userspace for a long time and it is * documented behavior for pid namespaces. So we can't easily * change it even if there were an error code better suited. */ retval = -ENOMEM; get_pid_ns(ns); refcount_set(&pid->count, 1); spin_lock_init(&pid->lock); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; pid->stashed = NULL; pid->ino = ++pidfs_ino; for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock_irq(&pidmap_lock); return pid; out_unlock: spin_unlock_irq(&pidmap_lock); put_pid_ns(ns); out_free: spin_lock_irq(&pidmap_lock); while (++i <= ns->level) { upid = pid->numbers + i; idr_remove(&upid->ns->idr, upid->nr); } /* On failure to allocate the first pid, reset the state */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); spin_unlock_irq(&pidmap_lock); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); } void disable_pid_allocation(struct pid_namespace *ns) { spin_lock_irq(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock_irq(&pidmap_lock); } struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); } EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type) { return (type == PIDTYPE_PID) ? &task->thread_pid : &task->signal->pids[type]; } /* * attach_pid() must be called with the tasklist_lock write-held. */ void attach_pid(struct task_struct *task, enum pid_type type) { struct pid *pid = *task_pid_ptr(task, type); hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]); } static void __change_pid(struct task_struct *task, enum pid_type type, struct pid *new) { struct pid **pid_ptr = task_pid_ptr(task, type); struct pid *pid; int tmp; pid = *pid_ptr; hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; if (type == PIDTYPE_PID) { WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID)); wake_up_all(&pid->wait_pidfd); } for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; free_pid(pid); } void detach_pid(struct task_struct *task, enum pid_type type) { __change_pid(task, type, NULL); } void change_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(task, type, pid); attach_pid(task, type); } void exchange_tids(struct task_struct *left, struct task_struct *right) { struct pid *pid1 = left->thread_pid; struct pid *pid2 = right->thread_pid; struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID]; struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID]; /* Swap the single entry tid lists */ hlists_swap_heads_rcu(head1, head2); /* Swap the per task_struct pid */ rcu_assign_pointer(left->thread_pid, pid2); rcu_assign_pointer(right->thread_pid, pid1); /* Swap the cached value */ WRITE_ONCE(left->pid, pid_nr(pid2)); WRITE_ONCE(right->pid, pid_nr(pid1)); } /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { WARN_ON_ONCE(type == PIDTYPE_PID); hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pid_links[(type)]); } return result; } EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct task_struct *find_get_task_by_vpid(pid_t nr) { struct task_struct *task; rcu_read_lock(); task = find_task_by_vpid(nr); if (task) get_task_struct(task); rcu_read_unlock(); return task; } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(find_get_pid); pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; } EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns); rcu_read_unlock(); return nr; } EXPORT_SYMBOL(__task_pid_nr_ns); struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); } EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); } EXPORT_SYMBOL_GPL(find_ge_pid); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) { struct fd f; struct pid *pid; f = fdget(fd); if (!fd_file(f)) return ERR_PTR(-EBADF); pid = pidfd_pid(fd_file(f)); if (!IS_ERR(pid)) { get_pid(pid); *flags = fd_file(f)->f_flags; } fdput(f); return pid; } /** * pidfd_get_task() - Get the task associated with a pidfd * * @pidfd: pidfd for which to get the task * @flags: flags associated with this pidfd * * Return the task associated with @pidfd. The function takes a reference on * the returned task. The caller is responsible for releasing that reference. * * Return: On success, the task_struct associated with the pidfd. * On error, a negative errno number will be returned. */ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) { unsigned int f_flags; struct pid *pid; struct task_struct *task; pid = pidfd_get_pid(pidfd, &f_flags); if (IS_ERR(pid)) return ERR_CAST(pid); task = get_pid_task(pid, PIDTYPE_TGID); put_pid(pid); if (!task) return ERR_PTR(-ESRCH); *flags = f_flags; return task; } /** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set. * * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * * This symbol should not be explicitly exported to loadable modules. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ static int pidfd_create(struct pid *pid, unsigned int flags) { int pidfd; struct file *pidfd_file; pidfd = pidfd_prepare(pid, flags, &pidfd_file); if (pidfd < 0) return pidfd; fd_install(pidfd, pidfd_file); return pidfd; } /** * sys_pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for * the task identified by @pid. Without PIDFD_THREAD flag the target task * must be a thread-group leader. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; struct pid *p; if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) return -EINVAL; if (pid <= 0) return -EINVAL; p = find_get_pid(pid); if (!p) return -ESRCH; fd = pidfd_create(p, flags); put_pid(p); return fd; } void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ pid_max = min(pid_max_max, max_t(int, pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = kmem_cache_create("pid", struct_size_t(struct pid, numbers, 1), __alignof__(struct pid), SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); } static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; int ret; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret); if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = fget_task(task, fd); else file = ERR_PTR(-EPERM); up_read(&task->signal->exec_update_lock); if (!file) { /* * It is possible that the target thread is exiting; it can be * either: * 1. before exit_signals(), which gives a real fd * 2. before exit_files() takes the task_lock() gives a real fd * 3. after exit_files() releases task_lock(), ->files is NULL; * this has PF_EXITING, since it was set in exit_signals(), * __pidfd_fget() returns EBADF. * In case 3 we get EBADF, but that really means ESRCH, since * the task is currently exiting and has freed its files * struct, so we fix it up. */ if (task->flags & PF_EXITING) file = ERR_PTR(-ESRCH); else file = ERR_PTR(-EBADF); } return file; } static int pidfd_getfd(struct pid *pid, int fd) { struct task_struct *task; struct file *file; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; file = __pidfd_fget(task, fd); put_task_struct(task); if (IS_ERR(file)) return PTR_ERR(file); ret = receive_fd(file, NULL, O_CLOEXEC); fput(file); return ret; } /** * sys_pidfd_getfd() - Get a file descriptor from another process * * @pidfd: the pidfd file descriptor of the process * @fd: the file descriptor number to get * @flags: flags on how to get the fd (reserved) * * This syscall gets a copy of a file descriptor from another process * based on the pidfd, and file descriptor number. It requires that * the calling process has the ability to ptrace the process represented * by the pidfd. The process which is having its file descriptor copied * is otherwise unaffected. * * Return: On success, a cloexec file descriptor is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, unsigned int, flags) { struct pid *pid; struct fd f; int ret; /* flags is currently unused - make sure it's unset */ if (flags) return -EINVAL; f = fdget(pidfd); if (!fd_file(f)) return -EBADF; pid = pidfd_pid(fd_file(f)); if (IS_ERR(pid)) ret = PTR_ERR(pid); else ret = pidfd_getfd(pid, fd); fdput(f); return ret; } |
| 1008 1012 2 870 377 129 1 106 102 376 348 26 984 983 985 856 601 825 985 988 1 1 1 34 1 1024 35 113 964 1021 1020 1 1024 1 1019 1019 1 977 8 593 594 578 17 573 21 576 12 5 12 589 7 592 328 591 592 592 591 594 44 44 44 93 94 93 94 94 37 37 37 37 36 37 36 20 58 57 58 54 58 115 115 7 108 108 100 4 3 97 7 93 39 55 3 53 22 16 42 39 35 37 35 16 54 7 67 2 178 119 2 67 61 21 1138 715 717 715 2 636 165 1094 832 210 978 1041 361 16 64 1038 2 39 169 931 206 924 40 177 177 178 131 119 12 76 58 86 432 439 436 373 76 75 76 76 76 76 441 441 467 52 440 470 469 5 1 465 5 466 6 388 8 82 38 23 4 13 3 9 7 430 9 442 7 10 460 449 87 36 438 438 48 412 1 179 321 435 4 434 435 426 19 318 179 72 10 6 2 61 61 60 56 7 301 203 20 4 378 378 12 51 335 336 365 481 411 457 48 436 4 423 11 431 82 431 432 423 20 59 383 428 431 432 307 13 169 13 180 135 409 10 318 316 3 312 75 21 19 56 56 56 121 122 4 2 116 19 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 output functions * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/net/ipv4/ip_output.c * * Changes: * A.N.Kuznetsov : airthmetics in fragmentation. * extension headers are implemented. * route changes now work. * ip6_forward does not confuse sniffers. * etc. * * H. von Brand : Added missing #include <linux/string.h> * Imran Patel : frag id should be in NBO * Kazunori MIYAZAWA @USAGI * : add ip6_append_data and related functions * for datagram xmit */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/in6.h> #include <linux/tcp.h> #include <linux/route.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/bpf-cgroup.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/sock.h> #include <net/snmp.h> #include <net/gso.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/rawv6.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/checksum.h> #include <linux/mroute6.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct inet6_dev *idev = ip6_dst_idev(dst); unsigned int hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *daddr, *nexthop; struct ipv6hdr *hdr; struct neighbour *neigh; int ret; /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { /* Make sure idev stays alive */ rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return -ENOMEM; } rcu_read_unlock(); } hdr = ipv6_hdr(skb); daddr = &hdr->daddr; if (ipv6_addr_is_multicast(daddr)) { if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && ((mroute6_is_socket(net, skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, daddr, &hdr->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing is not supported in any case. */ if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, dev_loopback_xmit); if (hdr->hop_limit == 0) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len); if (IPV6_ADDR_MC_SCOPE(daddr) <= IPV6_ADDR_SCOPE_NODELOCAL && !(dev->flags & IFF_LOOPBACK)) { kfree_skb(skb); return 0; } } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); rcu_read_lock(); nexthop = rt6_nexthop(dst_rt6_info(dst), daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); if (unlikely(IS_ERR_OR_NULL(neigh))) { if (unlikely(!neigh)) neigh = __neigh_create(&nd_tbl, nexthop, dev, false); if (IS_ERR(neigh)) { rcu_read_unlock(); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES); kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL); return -EINVAL; } } sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); rcu_read_unlock(); return ret; } static int ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { struct sk_buff *segs, *nskb; netdev_features_t features; int ret = 0; /* Please see corresponding comment in ip_finish_output_gso * describing the cases where GSO segment length exceeds the * egress MTU. */ features = netif_skb_features(skb); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); return -ENOMEM; } consume_skb(skb); skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); /* Last GSO segment can be smaller than gso_size (and MTU). * Adding a fragment header would produce an "atomic fragment", * which is considered harmful (RFC-8021). Avoid that. */ err = segs->len > mtu ? ip6_fragment(net, sk, segs, ip6_finish_output2) : ip6_finish_output2(net, sk, segs); if (err && ret == 0) ret = err; } return ret; } static int ip6_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && !skb_gso_validate_network_len(skb, mtu)) return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); return ip6_finish_output2(net, sk, skb); } static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip6_skb_dst_mtu(skb); if (skb_is_gso(skb)) return ip6_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(net, sk, skb, ip6_finish_output2); return ip6_finish_output2(net, sk, skb); } static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_SUCCESS: case NET_XMIT_CN: return __ip6_finish_output(net, sk, skb) ? : ret; default: kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS); return ret; } } int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; if (unlikely(!idev || READ_ONCE(idev->cnf.disable_ipv6))) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DISABLED); return 0; } return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, indev, dev, ip6_finish_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } EXPORT_SYMBOL(ip6_output); bool ip6_autoflowlabel(struct net *net, const struct sock *sk) { if (!inet6_test_bit(AUTOFLOWLABEL_SET, sk)) return ip6_default_np_autolabel(net); return inet6_test_bit(AUTOFLOWLABEL, sk); } /* * xmit an sk_buff (used by TCP, SCTP and DCCP) * Note : socket lock is not held for SYNACK packets, but might be modified * by calls to skb_set_owner_w() and ipv6_local_error(), * which are using proper atomic operations or spinlocks. */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority) { struct net *net = sock_net(sk); const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct inet6_dev *idev = ip6_dst_idev(dst); struct hop_jumbo_hdr *hop_jumbo; int hoplen = sizeof(*hop_jumbo); unsigned int head_room; struct ipv6hdr *hdr; u8 proto = fl6->flowi6_proto; int seg_len = skb->len; int hlimit = -1; u32 mtu; head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev); if (opt) head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { /* Make sure idev stays alive */ rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return -ENOBUFS; } rcu_read_unlock(); } if (opt) { seg_len += opt->opt_nflen + opt->opt_flen; if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop, &fl6->saddr); } if (unlikely(seg_len > IPV6_MAXPLEN)) { hop_jumbo = skb_push(skb, hoplen); hop_jumbo->nexthdr = proto; hop_jumbo->hdrlen = 0; hop_jumbo->tlv_type = IPV6_TLV_JUMBO; hop_jumbo->tlv_len = 4; hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen); proto = IPPROTO_HOPOPTS; seg_len = 0; IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO; } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); /* * Fill in the IPv6 header */ if (np) hlimit = READ_ONCE(np->hop_limit); if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, ip6_autoflowlabel(net, sk), fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; hdr->hop_limit = hlimit; hdr->saddr = fl6->saddr; hdr->daddr = *first_hop; skb->protocol = htons(ETH_P_IPV6); skb->priority = priority; skb->mark = mark; mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out((struct sock *)sk, skb); if (unlikely(!skb)) return 0; /* hooks should never assume socket lock is held. * we promote our socket to non const */ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, (struct sock *)sk, skb, NULL, dev, dst_output); } skb->dev = dev; /* ipv6_local_error() does not require socket lock, * we promote our socket to non const */ ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu); IP6_INC_STATS(net, idev, IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } EXPORT_SYMBOL(ip6_xmit); static int ip6_call_ra_chain(struct sk_buff *skb, int sel) { struct ip6_ra_chain *ra; struct sock *last = NULL; read_lock(&ip6_ra_lock); for (ra = ip6_ra_chain; ra; ra = ra->next) { struct sock *sk = ra->sk; if (sk && ra->sel == sel && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == skb->dev->ifindex)) { if (inet6_test_bit(RTALERT_ISOLATE, sk) && !net_eq(sock_net(sk), dev_net(skb->dev))) { continue; } if (last) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) rawv6_rcv(last, skb2); } last = sk; } } if (last) { rawv6_rcv(last, skb); read_unlock(&ip6_ra_lock); return 1; } read_unlock(&ip6_ra_lock); return 0; } static int ip6_forward_proxy_check(struct sk_buff *skb) { struct ipv6hdr *hdr = ipv6_hdr(skb); u8 nexthdr = hdr->nexthdr; __be16 frag_off; int offset; if (ipv6_ext_hdr(nexthdr)) { offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off); if (offset < 0) return 0; } else offset = sizeof(struct ipv6hdr); if (nexthdr == IPPROTO_ICMPV6) { struct icmp6hdr *icmp6; if (!pskb_may_pull(skb, (skb_network_header(skb) + offset + 1 - skb->data))) return 0; icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); switch (icmp6->icmp6_type) { case NDISC_ROUTER_SOLICITATION: case NDISC_ROUTER_ADVERTISEMENT: case NDISC_NEIGHBOUR_SOLICITATION: case NDISC_NEIGHBOUR_ADVERTISEMENT: case NDISC_REDIRECT: /* For reaction involving unicast neighbor discovery * message destined to the proxied address, pass it to * input function. */ return 1; default: break; } } /* * The proxying router can't forward traffic sent to a link-local * address, so signal the sender and discard the packet. This * behavior is clarified by the MIPv6 specification. */ if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) { dst_link_failure(skb); return -1; } return 0; } static inline int ip6_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_NET_SWITCHDEV if (skb->offload_l3_fwd_mark) { consume_skb(skb); return 0; } #endif skb_clear_tstamp(skb); return dst_output(net, sk, skb); } static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) return false; /* ipv6 conntrack defrag sets max_frag_size + ignore_df */ if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) return true; if (skb->ignore_df) return false; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) return false; return true; } int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); struct inet6_dev *idev; SKB_DR(reason); u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) goto error; if (skb->pkt_type != PACKET_HOST) goto drop; if (unlikely(skb->sk)) goto drop; if (skb_warn_if_lro(skb)) goto drop; if (!READ_ONCE(net->ipv6.devconf_all->disable_policy) && (!idev || !READ_ONCE(idev->cnf.disable_policy)) && !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } skb_forward_csum(skb); /* * We DO NOT make any processing on * RA packets, pushing them to user level AS IS * without ane WARRANTY that application will be able * to interpret them. The reason is that we * cannot make anything clever here. * * We are not end-node, so that if packet contains * AH/ESP, we cannot make anything. * Defragmentation also would be mistake, RA packets * cannot be fragmented, because there is no warranty * that different fragments will go along one path. --ANK */ if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { if (ip6_call_ra_chain(skb, ntohs(opt->ra))) return 0; } /* * check and decrement ttl */ if (hdr->hop_limit <= 1) { icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); return -ETIMEDOUT; } /* XXX: idev->cnf.proxy_ndp? */ if (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) { /* It's tempting to decrease the hop limit * here by 1, as we do at the end of the * function too. * * But that would be incorrect, as proxying is * not forwarding. The ip6_input function * will handle this packet locally, and it * depends on the hop limit being unchanged. * * One example is the NDP hop limit, that * always has to stay 255, but other would be * similar checks around RA packets, where the * user can even change the desired limit. */ return ip6_input(skb); } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); SKB_DR_SET(reason, XFRM_POLICY); goto drop; } dst = skb_dst(skb); /* IPv6 specs say nothing about it, but it is clear that we cannot send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ if (IP6CB(skb)->iif == dst->dev->ifindex && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct inet_peer *peer; struct rt6_info *rt; /* * incoming and outgoing devices are the same * send a redirect. */ rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_GATEWAY) target = &rt->rt6i_gateway; else target = &hdr->daddr; peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1); /* Limit redirects both by destination (here) and by source (inside ndisc_send_redirect) */ if (inet_peer_xrlim_allow(peer, 1*HZ)) ndisc_send_redirect(skb, target); if (peer) inet_putpeer(peer); } else { int addrtype = ipv6_addr_type(&hdr->saddr); /* This check is security critical. */ if (addrtype == IPV6_ADDR_ANY || addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK)) goto error; if (addrtype & IPV6_ADDR_LINKLOCAL) { icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOT_NEIGHBOUR, 0); goto error; } } __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); mtu = ip6_dst_mtu_maybe_forward(dst, true); if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS); __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG); return -EMSGSIZE; } if (skb_cow(skb, dst->dev->hard_header_len)) { __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS); goto drop; } hdr = ipv6_hdr(skb); /* Mangling hops number delayed to point after skb COW */ hdr->hop_limit--; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, net, NULL, skb, skb->dev, dst->dev, ip6_forward_finish); error: __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); SKB_DR_SET(reason, IP_INADDRERRORS); drop: kfree_skb_reason(skb, reason); return -EINVAL; } static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; skb_dst_drop(to); skb_dst_set(to, dst_clone(skb_dst(from))); to->dev = from->dev; to->mark = from->mark; skb_copy_hash(to, from); #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif nf_copy(to, from); skb_ext_copy(to, from); skb_copy_secmark(to, from); } int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter) { unsigned int first_len; struct frag_hdr *fh; /* BUILD HEADER */ *prevhdr = NEXTHDR_FRAGMENT; iter->tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC); if (!iter->tmp_hdr) return -ENOMEM; iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->hlen = hlen; iter->frag_id = frag_id; iter->nexthdr = nexthdr; __skb_pull(skb, hlen); fh = __skb_push(skb, sizeof(struct frag_hdr)); __skb_push(skb, hlen); skb_reset_network_header(skb); memcpy(skb_network_header(skb), iter->tmp_hdr, hlen); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); fh->identification = frag_id; first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); return 0; } EXPORT_SYMBOL(ip6_fraglist_init); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter) { struct sk_buff *frag = iter->frag; unsigned int hlen = iter->hlen; struct frag_hdr *fh; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); fh = __skb_push(frag, sizeof(struct frag_hdr)); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iter->tmp_hdr, hlen); iter->offset += skb->len - hlen - sizeof(struct frag_hdr); fh->nexthdr = iter->nexthdr; fh->reserved = 0; fh->frag_off = htons(iter->offset); if (frag->next) fh->frag_off |= htons(IP6_MF); fh->identification = iter->frag_id; ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); ip6_copy_metadata(frag, skb); } EXPORT_SYMBOL(ip6_fraglist_prepare); void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state) { state->prevhdr = prevhdr; state->nexthdr = nexthdr; state->frag_id = frag_id; state->hlen = hlen; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->hroom = hdr_room; state->troom = needed_tailroom; state->offset = 0; } EXPORT_SYMBOL(ip6_frag_init); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state) { u8 *prevhdr = state->prevhdr, *fragnexthdr_offset; struct sk_buff *frag; struct frag_hdr *fh; unsigned int len; len = state->left; /* IF: it doesn't fit, use 'mtu' - the data space left */ if (len > state->mtu) len = state->mtu; /* IF: we are not sending up to and including the packet end then align the next start on an eight byte boundary */ if (len < state->left) len &= ~7; /* Allocate buffer */ frag = alloc_skb(len + state->hlen + sizeof(struct frag_hdr) + state->hroom + state->troom, GFP_ATOMIC); if (!frag) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip6_copy_metadata(frag, skb); skb_reserve(frag, state->hroom); skb_put(frag, len + state->hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + state->hlen); frag->transport_header = (frag->network_header + state->hlen + sizeof(struct frag_hdr)); /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(frag, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(frag), state->hlen); fragnexthdr_offset = skb_network_header(frag); fragnexthdr_offset += prevhdr - skb_network_header(skb); *fragnexthdr_offset = NEXTHDR_FRAGMENT; /* * Build fragment header. */ fh->nexthdr = state->nexthdr; fh->reserved = 0; fh->identification = state->frag_id; /* * Copy a block of the IP datagram. */ BUG_ON(skb_copy_bits(skb, state->ptr, skb_transport_header(frag), len)); state->left -= len; fh->frag_off = htons(state->offset); if (state->left > 0) fh->frag_off |= htons(IP6_MF); ipv6_hdr(frag)->payload_len = htons(frag->len - sizeof(struct ipv6hdr)); state->ptr += len; state->offset += len; return frag; } EXPORT_SYMBOL(ip6_frag_next); int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct sk_buff *frag; struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; u8 tstamp_type = skb->tstamp_type; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; ktime_t tstamp = skb->tstamp; int hroom, err = 0; __be32 frag_id; u8 *prevhdr, nexthdr = 0; err = ip6_find_1stfragopt(skb, &prevhdr); if (err < 0) goto fail; hlen = err; nexthdr = *prevhdr; nexthdr_offset = prevhdr - skb_network_header(skb); mtu = ip6_skb_dst_mtu(skb); /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ if (unlikely(!skb->ignore_df && skb->len > mtu)) goto fail_toobig; if (IP6CB(skb)->frag_max_size) { if (IP6CB(skb)->frag_max_size > mtu) goto fail_toobig; /* don't send fragments larger than what we received */ mtu = IP6CB(skb)->frag_max_size; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; } if (np) { u32 frag_size = READ_ONCE(np->frag_size); if (frag_size && frag_size < mtu) mtu = frag_size; } if (mtu < hlen + sizeof(struct frag_hdr) + 8) goto fail_toobig; mtu -= hlen + sizeof(struct frag_hdr); frag_id = ipv6_select_ident(net, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr); if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; prevhdr = skb_network_header(skb) + nexthdr_offset; hroom = LL_RESERVED_SPACE(rt->dst.dev); if (skb_has_frag_list(skb)) { unsigned int first_len = skb_pagelen(skb); struct ip6_fraglist_iter iter; struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || skb_cloned(skb) || skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < (hlen + hroom + sizeof(struct frag_hdr))) goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } skb->truesize -= frag->truesize; } err = ip6_fraglist_init(skb, hlen, prevhdr, nexthdr, frag_id, &iter); if (err < 0) goto fail; /* We prevent @rt from being freed. */ rcu_read_lock(); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) ip6_fraglist_prepare(skb, &iter); skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip6_fraglist_next(&iter); } kfree(iter.tmp_hdr); if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); rcu_read_unlock(); return 0; } kfree_skb_list(iter.frag); IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); rcu_read_unlock(); return err; slow_path_clean: skb_walk_frags(skb, frag2) { if (frag2 == frag) break; frag2->sk = NULL; frag2->destructor = NULL; skb->truesize += frag2->truesize; } } slow_path: /* * Fragment the datagram. */ ip6_frag_init(skb, hlen, mtu, rt->dst.dev->needed_tailroom, LL_RESERVED_SPACE(rt->dst.dev), prevhdr, nexthdr, frag_id, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { frag = ip6_frag_next(skb, &state); if (IS_ERR(frag)) { err = PTR_ERR(frag); goto fail; } /* * Put this fragment into the sending queue. */ skb_set_delivery_time(frag, tstamp, tstamp_type); err = output(net, sk, frag); if (err) goto fail; IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGCREATES); } IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGOKS); consume_skb(skb); return err; fail_toobig: icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; fail: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return err; } static inline int ip6_rt_check(const struct rt6key *rt_key, const struct in6_addr *fl_addr, const struct in6_addr *addr_cache) { return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) && (!addr_cache || !ipv6_addr_equal(fl_addr, addr_cache)); } static struct dst_entry *ip6_sk_dst_check(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { struct ipv6_pinfo *np = inet6_sk(sk); struct rt6_info *rt; if (!dst) goto out; if (dst->ops->family != AF_INET6) { dst_release(dst); return NULL; } rt = dst_rt6_info(dst); /* Yes, checking route validity in not connected * case is not very simple. Take into account, * that we do not support routing by source, TOS, * and MSG_DONTROUTE --ANK (980726) * * 1. ip6_rt_check(): If route was host route, * check that cached destination is current. * If it is network route, we still may * check its validity using saved pointer * to the last used address: daddr_cache. * We do not want to save whole address now, * (because main consumer of this service * is tcp, which has not this problem), * so that the last trick works only on connected * sockets. * 2. oif also should be the same. */ if (ip6_rt_check(&rt->rt6i_dst, &fl6->daddr, np->daddr_cache) || #ifdef CONFIG_IPV6_SUBTREES ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) || #endif (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) { dst_release(dst); dst = NULL; } out: return dst; } static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD struct neighbour *n; struct rt6_info *rt; #endif int err; int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, * the route-specific preferred source forces the * ip6_route_output call _before_ ip6_route_get_saddr. * * In source specific routing (no src=any default route), * ip6_route_output will fail given src=any saddr, though, so * that's why we try it again later. */ if (ipv6_addr_any(&fl6->saddr)) { struct fib6_info *from; struct rt6_info *rt; *dst = ip6_route_output(net, sk, fl6); rt = (*dst)->error ? NULL : dst_rt6_info(*dst); rcu_read_lock(); from = rt ? rcu_dereference(rt->from) : NULL; err = ip6_route_get_saddr(net, from, &fl6->daddr, sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0, fl6->flowi6_l3mdev, &fl6->saddr); rcu_read_unlock(); if (err) goto out_err_release; /* If we had an erroneous initial result, pretend it * never existed and let the SA-enabled version take * over. */ if ((*dst)->error) { dst_release(*dst); *dst = NULL; } if (fl6->flowi6_oif) flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) goto out_err_release; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * Here if the dst entry we've looked up * has a neighbour entry that is in the INCOMPLETE * state and the src address from the flow is * marked as OPTIMISTIC, we release the found * dst entry and replace it instead with the * dst entry of the nexthop router */ rt = dst_rt6_info(*dst); rcu_read_lock(); n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); err = n && !(READ_ONCE(n->nud_state) & NUD_VALID) ? -EINVAL : 0; rcu_read_unlock(); if (err) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; ifp = ipv6_get_ifaddr(net, &fl6->saddr, (*dst)->dev, 1); redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC); if (ifp) in6_ifa_put(ifp); if (redirect) { /* * We need to get the dst entry for the * default router instead */ dst_release(*dst); memcpy(&fl_gw6, fl6, sizeof(struct flowi6)); memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr)); *dst = ip6_route_output(net, sk, &fl_gw6); err = (*dst)->error; if (err) goto out_err_release; } } #endif if (ipv6_addr_v4mapped(&fl6->saddr) && !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) { err = -EAFNOSUPPORT; goto out_err_release; } return 0; out_err_release: dst_release(*dst); *dst = NULL; if (err == -ENETUNREACH) IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES); return err; } /** * ip6_dst_lookup - perform route lookup on flow * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @dst: pointer to dst_entry * for result * @fl6: flow to lookup * * This function performs a route lookup on the given flow. * * It returns zero on success, or a standard errno code on error. */ int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { *dst = NULL; return ip6_dst_lookup_tail(net, sk, dst, fl6); } EXPORT_SYMBOL_GPL(ip6_dst_lookup); /** * ip6_dst_lookup_flow - perform route lookup on flow with ipsec * @net: Network namespace to perform lookup in * @sk: socket which provides route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup * * This function performs a route lookup on the given flow. * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err; err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); /** * ip6_sk_dst_lookup_flow - perform socket cached route lookup on flow * @sk: socket which provides the dst cache and route info * @fl6: flow to lookup * @final_dst: final destination address for ipsec lookup * @connected: whether @sk is connected or not * * This function performs a route lookup on the given flow with the * possibility of using the cached route in the socket if it is valid. * It will take the socket dst lock when operating on the dst cache. * As a result, this function can only be used in process context. * * In addition, for a connected socket, cache the dst in the socket * if the current cache is not valid. * * It returns a valid dst pointer on success, or a pointer encoded * error code. */ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected) { struct dst_entry *dst = sk_dst_check(sk, inet6_sk(sk)->dst_cookie); dst = ip6_sk_dst_check(sk, dst, fl6); if (dst) return dst; dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); if (connected && !IS_ERR(dst)) ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); return dst; } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src, gfp_t gfp) { return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL; } static void ip6_append_data_mtu(unsigned int *mtu, int *maxfraglen, unsigned int fragheaderlen, struct sk_buff *skb, struct rt6_info *rt, unsigned int orig_mtu) { if (!(rt->dst.flags & DST_XFRM_TUNNEL)) { if (!skb) { /* first fragment, reserve header_len */ *mtu = orig_mtu - rt->dst.header_len; } else { /* * this fragment is not first, the headers * space is regarded as data space. */ *mtu = orig_mtu; } *maxfraglen = ((*mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); } } static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6, struct rt6_info *rt) { struct ipv6_pinfo *np = inet6_sk(sk); unsigned int mtu, frag_size; struct ipv6_txoptions *nopt, *opt = ipc6->opt; /* callers pass dst together with a reference, set it first so * ip6_cork_release() can put it down even in case of an error. */ cork->base.dst = &rt->dst; /* * setup for corking */ if (opt) { if (WARN_ON(v6_cork->opt)) return -EINVAL; nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); if (unlikely(!nopt)) return -ENOBUFS; nopt->tot_len = sizeof(*opt); nopt->opt_flen = opt->opt_flen; nopt->opt_nflen = opt->opt_nflen; nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation); if (opt->dst0opt && !nopt->dst0opt) return -ENOBUFS; nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation); if (opt->dst1opt && !nopt->dst1opt) return -ENOBUFS; nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation); if (opt->hopopt && !nopt->hopopt) return -ENOBUFS; nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation); if (opt->srcrt && !nopt->srcrt) return -ENOBUFS; /* need source address above miyazawa*/ } v6_cork->hop_limit = ipc6->hlimit; v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst); else mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ? READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst)); frag_size = READ_ONCE(np->frag_size); if (frag_size && frag_size < mtu) mtu = frag_size; cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; cork->base.mark = ipc6->sockc.mark; sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags); cork->base.length = 0; cork->base.transmit_time = ipc6->sockc.transmit_time; return 0; } static int __ip6_append_data(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork_full, struct inet6_cork *v6_cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; struct inet_cork *cork = &cork_full->base; struct flowi6 *fl6 = &cork_full->fl.u.ip6; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu; struct ubuf_info *uarg = NULL; int exthdrlen = 0; int dst_exthdrlen = 0; int hh_len; int copy; int err; int offset = 0; bool zc = false; u32 tskey = 0; struct rt6_info *rt = dst_rt6_info(cork->dst); bool paged, hold_tskey, extra_uref = false; struct ipv6_txoptions *opt = v6_cork->opt; int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; skb = skb_peek_tail(queue); if (!skb) { exthdrlen = opt ? opt->opt_flen : 0; dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } paged = !!cork->gso_size; mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + rt->rt6i_nfheader_len; if (mtu <= fragheaderlen || ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr)) goto emsgsize; maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr); /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit * the first fragment */ if (headersize + transhdrlen > mtu) goto emsgsize; if (cork->length + length > mtu - headersize && ipc6->dontfrag && (sk->sk_protocol == IPPROTO_UDP || sk->sk_protocol == IPPROTO_ICMPV6 || sk->sk_protocol == IPPROTO_RAW)) { ipv6_local_rxpmtu(sk, fl6, mtu - headersize + sizeof(struct ipv6hdr)); goto emsgsize; } if (ip6_sk_ignore_df(sk)) maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; else maxnonfragsize = mtu; if (cork->length + length > maxnonfragsize - headersize) { emsgsize: pmtu = max_t(int, mtu - headersize + sizeof(struct ipv6hdr), 0); ipv6_local_error(sk, EMSGSIZE, fl6, pmtu); return -EMSGSIZE; } /* CHECKSUM_PARTIAL only with no extension headers and when * we are not going to fragment */ if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && headersize == sizeof(struct ipv6hdr) && length <= mtu - headersize && (!(flags & MSG_MORE) || cork->gso_size) && rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; if ((flags & MSG_ZEROCOPY) && length) { struct msghdr *msg = from; if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) return -EINVAL; /* Leave uarg NULL if can't zerocopy, callers should * be able to handle it. */ if ((rt->dst.dev->features & NETIF_F_SG) && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; uarg = msg->msg_ubuf; } } else if (sock_flag(sk, SOCK_ZEROCOPY)) { uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); if (!uarg) return -ENOBUFS; extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ if (rt->dst.dev->features & NETIF_F_SG && csummode == CHECKSUM_PARTIAL) { paged = true; zc = true; } else { uarg_to_msgzc(uarg)->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } } else if ((flags & MSG_SPLICE_PAGES) && length) { if (inet_test_bit(HDRINCL, sk)) return -EPERM; if (rt->dst.dev->features & NETIF_F_SG && getfrag == ip_generic_getfrag) /* We need an empty buffer to attach stuff to */ paged = true; else flags &= ~MSG_SPLICE_PAGES; } hold_tskey = cork->tx_flags & SKBTX_ANY_TSTAMP && READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID; if (hold_tskey) tskey = atomic_inc_return(&sk->sk_tskey) - 1; /* * Let's try using as much space as possible. * Use MTU if total length of the message fits into the MTU. * Otherwise, we need to reserve fragment header and * fragment alignment (= 8-15 octects, in total). * * Note that we may need to "move" the data from the tail * of the buffer to the new fragment when we split * the message. * * FIXME: It may be fragmented into multiple chunks * at once if non-fragmentable extension headers * are too large. * --yoshfuji */ cork->length += length; if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; if (copy <= 0) { char *data; unsigned int datalen; unsigned int fraglen; unsigned int fraggap; unsigned int alloclen, alloc_extra; unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ if (skb) fraggap = skb->len - maxfraglen; else fraggap = 0; /* update mtu and maxfraglen if necessary */ if (!skb || !skb_prev) ip6_append_data_mtu(&mtu, &maxfraglen, fragheaderlen, skb, rt, orig_mtu); skb_prev = skb; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len; alloc_extra += dst_exthdrlen; alloc_extra += rt->dst.trailer_len; /* We just reserve space for fragment header. * Note: this may be overallocation if the message * (without MSG_MORE) fits into the MTU. */ alloc_extra += sizeof(struct frag_hdr); if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else if (!paged && (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = fragheaderlen + transhdrlen; pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; if (datalen != length + fraggap) { /* * this is not the last fragment, the trailer * space is regarded as data space. */ datalen += rt->dst.trailer_len; } fraglen = datalen + fragheaderlen; copy = datalen - transhdrlen - fraggap - pagedlen; /* [!] NOTE: copy may be negative if pagedlen>0 * because then the equation may reduces to -fraggap. */ if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) { err = -EINVAL; goto error; } if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } if (!skb) goto error; /* * Fill in the control structures */ skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = csummode; skb->csum = 0; /* reserve for fragmentation and ipsec header */ skb_reserve(skb, hh_len + sizeof(struct frag_hdr) + dst_exthdrlen); /* * Find where to start putting bytes */ data = skb_put(skb, fraglen - pagedlen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits( skb_prev, maxfraglen, data + transhdrlen, fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); data += fraggap; pskb_trim_unique(skb_prev, maxfraglen); } if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } else if (flags & MSG_SPLICE_PAGES) { copy = 0; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; /* Only the initial fragment is time stamped */ skb_shinfo(skb)->tx_flags = cork->tx_flags; cork->tx_flags = 0; skb_shinfo(skb)->tskey = tskey; tskey = 0; skb_zcopy_set(skb, uarg, &extra_uref); if ((flags & MSG_CONFIRM) && !skb_prev) skb_set_dst_pending_confirm(skb, 1); /* * Put the packet on the pending queue */ if (!skb->destructor) { skb->destructor = sock_wfree; skb->sk = sk; wmem_alloc_delta += skb->truesize; } __skb_queue_tail(queue, skb); continue; } if (copy > length) copy = length; if (!(rt->dst.dev->features&NETIF_F_SG) && skb_tailroom(skb) >= copy) { unsigned int off; off = skb->len; if (getfrag(from, skb_put(skb, copy), offset, copy, off, skb) < 0) { __skb_trim(skb, off); err = -EFAULT; goto error; } } else if (flags & MSG_SPLICE_PAGES) { struct msghdr *msg = from; err = -EIO; if (WARN_ON_ONCE(copy > msg->msg_iter.count)) goto error; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) goto error; copy = err; wmem_alloc_delta += copy; } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; if (i == MAX_SKB_FRAGS) goto error; __skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, 0); skb_shinfo(skb)->nr_frags = ++i; get_page(pfrag->page); } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, page_address(pfrag->page) + pfrag->offset, offset, copy, skb->len, skb) < 0) goto error_efault; pfrag->offset += copy; skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; wmem_alloc_delta += copy; } else { err = skb_zerocopy_iter_dgram(skb, from, copy); if (err < 0) goto error; } offset += copy; length -= copy; } if (wmem_alloc_delta) refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: err = -EFAULT; error: net_zcopy_put_abort(uarg, extra_uref); cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); if (hold_tskey) atomic_dec(&sk->sk_tskey); return err; } int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int exthdrlen; int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { /* * setup for corking */ dst_hold(&rt->dst); err = ip6_setup_cork(sk, &inet->cork, &np->cork, ipc6, rt); if (err) return err; inet->cork.fl.u.ip6 = *fl6; exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; } else { transhdrlen = 0; } return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork, &np->cork, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags, ipc6); } EXPORT_SYMBOL_GPL(ip6_append_data); static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) { struct dst_entry *dst = cork->base.dst; cork->base.dst = NULL; skb_dst_set(skb, dst); } static void ip6_cork_release(struct inet_cork_full *cork, struct inet6_cork *v6_cork) { if (v6_cork->opt) { struct ipv6_txoptions *opt = v6_cork->opt; kfree(opt->dst0opt); kfree(opt->dst1opt); kfree(opt->hopopt); kfree(opt->srcrt); kfree(opt); v6_cork->opt = NULL; } if (cork->base.dst) { dst_release(cork->base.dst); cork->base.dst = NULL; } } struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct in6_addr *final_dst; struct net *net = sock_net(sk); struct ipv6hdr *hdr; struct ipv6_txoptions *opt = v6_cork->opt; struct rt6_info *rt = dst_rt6_info(cork->base.dst); struct flowi6 *fl6 = &cork->fl.u.ip6; unsigned char proto = fl6->flowi6_proto; skb = __skb_dequeue(queue); if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); /* move skb->data to ip header from ext header */ if (skb->data < skb_network_header(skb)) __skb_pull(skb, skb_network_offset(skb)); while ((tmp_skb = __skb_dequeue(queue)) != NULL) { __skb_pull(tmp_skb, skb_network_header_len(skb)); *tail_skb = tmp_skb; tail_skb = &(tmp_skb->next); skb->len += tmp_skb->len; skb->data_len += tmp_skb->len; skb->truesize += tmp_skb->truesize; tmp_skb->destructor = NULL; tmp_skb->sk = NULL; } /* Allow local fragmentation. */ skb->ignore_df = ip6_sk_ignore_df(sk); __skb_pull(skb, skb_network_header_len(skb)); final_dst = &fl6->daddr; if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst, &fl6->saddr); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, ip6_autoflowlabel(net, sk), fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; hdr->daddr = *final_dst; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; if (sk_is_tcp(sk)) skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC); else skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid); ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; if (sk->sk_socket->type == SOCK_RAW && !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } ip6_cork_release(cork, v6_cork); out: return skb; } int ip6_send_skb(struct sk_buff *skb) { struct net *net = sock_net(skb->sk); struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return err; } int ip6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; skb = ip6_finish_skb(sk); if (!skb) return 0; return ip6_send_skb(skb); } EXPORT_SYMBOL_GPL(ip6_push_pending_frames); static void __ip6_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) { if (skb_dst(skb)) IP6_INC_STATS(sock_net(sk), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); } ip6_cork_release(cork, v6_cork); } void ip6_flush_pending_frames(struct sock *sk) { __ip6_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } EXPORT_SYMBOL_GPL(ip6_flush_pending_frames); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, size_t length, int transhdrlen, struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork) { struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); int err; if (flags & MSG_PROBE) { dst_release(&rt->dst); return NULL; } __skb_queue_head_init(&queue); cork->base.flags = 0; cork->base.addr = 0; cork->base.opt = NULL; v6_cork.opt = NULL; err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt); if (err) { ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); } if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_test_bit(DONTFRAG, sk); err = __ip6_append_data(sk, &queue, cork, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags, ipc6); if (err) { __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork); return ERR_PTR(err); } return __ip6_make_skb(sk, &queue, cork, &v6_cork); } |
| 23 14 23 9 23 7 2 2 2 23 23 23 23 23 24 1 23 21 2 14 8 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 | // SPDX-License-Identifier: GPL-2.0-only /* * RDMA transport layer based on the trans_fd.c implementation. * * Copyright (C) 2008 by Tom Tucker <tom@opengridcomputing.com> * Copyright (C) 2006 by Russ Cox <rsc@swtch.com> * Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net> * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/in.h> #include <linux/module.h> #include <linux/net.h> #include <linux/ipv6.h> #include <linux/kthread.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/un.h> #include <linux/uaccess.h> #include <linux/inet.h> #include <linux/file.h> #include <linux/parser.h> #include <linux/semaphore.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> #define P9_PORT 5640 #define P9_RDMA_SQ_DEPTH 32 #define P9_RDMA_RQ_DEPTH 32 #define P9_RDMA_SEND_SGE 4 #define P9_RDMA_RECV_SGE 4 #define P9_RDMA_IRD 0 #define P9_RDMA_ORD 0 #define P9_RDMA_TIMEOUT 30000 /* 30 seconds */ #define P9_RDMA_MAXSIZE (1024*1024) /* 1MB */ /** * struct p9_trans_rdma - RDMA transport instance * * @state: tracks the transport state machine for connection setup and tear down * @cm_id: The RDMA CM ID * @pd: Protection Domain pointer * @qp: Queue Pair pointer * @cq: Completion Queue pointer * @timeout: Number of uSecs to wait for connection management events * @privport: Whether a privileged port may be used * @port: The port to use * @sq_depth: The depth of the Send Queue * @sq_sem: Semaphore for the SQ * @rq_depth: The depth of the Receive Queue. * @rq_sem: Semaphore for the RQ * @excess_rc : Amount of posted Receive Contexts without a pending request. * See rdma_request() * @addr: The remote peer's address * @req_lock: Protects the active request list * @cm_done: Completion event for connection management tracking */ struct p9_trans_rdma { enum { P9_RDMA_INIT, P9_RDMA_ADDR_RESOLVED, P9_RDMA_ROUTE_RESOLVED, P9_RDMA_CONNECTED, P9_RDMA_FLUSHING, P9_RDMA_CLOSING, P9_RDMA_CLOSED, } state; struct rdma_cm_id *cm_id; struct ib_pd *pd; struct ib_qp *qp; struct ib_cq *cq; long timeout; bool privport; u16 port; int sq_depth; struct semaphore sq_sem; int rq_depth; struct semaphore rq_sem; atomic_t excess_rc; struct sockaddr_in addr; spinlock_t req_lock; struct completion cm_done; }; struct p9_rdma_req; /** * struct p9_rdma_context - Keeps track of in-process WR * * @cqe: completion queue entry * @busa: Bus address to unmap when the WR completes * @req: Keeps track of requests (send) * @rc: Keepts track of replies (receive) */ struct p9_rdma_context { struct ib_cqe cqe; dma_addr_t busa; union { struct p9_req_t *req; struct p9_fcall rc; }; }; /** * struct p9_rdma_opts - Collection of mount options * @port: port of connection * @privport: Whether a privileged port may be used * @sq_depth: The requested depth of the SQ. This really doesn't need * to be any deeper than the number of threads used in the client * @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth * @timeout: Time to wait in msecs for CM events */ struct p9_rdma_opts { short port; bool privport; int sq_depth; int rq_depth; long timeout; }; /* * Option Parsing (code inspired by NFS code) */ enum { /* Options that take integer arguments */ Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout, /* Options that take no argument */ Opt_privport, Opt_err, }; static match_table_t tokens = { {Opt_port, "port=%u"}, {Opt_sq_depth, "sq=%u"}, {Opt_rq_depth, "rq=%u"}, {Opt_timeout, "timeout=%u"}, {Opt_privport, "privport"}, {Opt_err, NULL}, }; static int p9_rdma_show_options(struct seq_file *m, struct p9_client *clnt) { struct p9_trans_rdma *rdma = clnt->trans; if (rdma->port != P9_PORT) seq_printf(m, ",port=%u", rdma->port); if (rdma->sq_depth != P9_RDMA_SQ_DEPTH) seq_printf(m, ",sq=%u", rdma->sq_depth); if (rdma->rq_depth != P9_RDMA_RQ_DEPTH) seq_printf(m, ",rq=%u", rdma->rq_depth); if (rdma->timeout != P9_RDMA_TIMEOUT) seq_printf(m, ",timeout=%lu", rdma->timeout); if (rdma->privport) seq_puts(m, ",privport"); return 0; } /** * parse_opts - parse mount options into rdma options structure * @params: options string passed from mount * @opts: rdma transport-specific structure to parse options into * * Returns 0 upon success, -ERRNO upon failure */ static int parse_opts(char *params, struct p9_rdma_opts *opts) { char *p; substring_t args[MAX_OPT_ARGS]; int option; char *options, *tmp_options; opts->port = P9_PORT; opts->sq_depth = P9_RDMA_SQ_DEPTH; opts->rq_depth = P9_RDMA_RQ_DEPTH; opts->timeout = P9_RDMA_TIMEOUT; opts->privport = false; if (!params) return 0; tmp_options = kstrdup(params, GFP_KERNEL); if (!tmp_options) { p9_debug(P9_DEBUG_ERROR, "failed to allocate copy of option string\n"); return -ENOMEM; } options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token; int r; if (!*p) continue; token = match_token(p, tokens, args); if ((token != Opt_err) && (token != Opt_privport)) { r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); continue; } } switch (token) { case Opt_port: opts->port = option; break; case Opt_sq_depth: opts->sq_depth = option; break; case Opt_rq_depth: opts->rq_depth = option; break; case Opt_timeout: opts->timeout = option; break; case Opt_privport: opts->privport = true; break; default: continue; } } /* RQ must be at least as large as the SQ */ opts->rq_depth = max(opts->rq_depth, opts->sq_depth); kfree(tmp_options); return 0; } static int p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct p9_client *c = id->context; struct p9_trans_rdma *rdma = c->trans; switch (event->event) { case RDMA_CM_EVENT_ADDR_RESOLVED: BUG_ON(rdma->state != P9_RDMA_INIT); rdma->state = P9_RDMA_ADDR_RESOLVED; break; case RDMA_CM_EVENT_ROUTE_RESOLVED: BUG_ON(rdma->state != P9_RDMA_ADDR_RESOLVED); rdma->state = P9_RDMA_ROUTE_RESOLVED; break; case RDMA_CM_EVENT_ESTABLISHED: BUG_ON(rdma->state != P9_RDMA_ROUTE_RESOLVED); rdma->state = P9_RDMA_CONNECTED; break; case RDMA_CM_EVENT_DISCONNECTED: if (rdma) rdma->state = P9_RDMA_CLOSED; c->status = Disconnected; break; case RDMA_CM_EVENT_TIMEWAIT_EXIT: break; case RDMA_CM_EVENT_ADDR_CHANGE: case RDMA_CM_EVENT_ROUTE_ERROR: case RDMA_CM_EVENT_DEVICE_REMOVAL: case RDMA_CM_EVENT_MULTICAST_JOIN: case RDMA_CM_EVENT_MULTICAST_ERROR: case RDMA_CM_EVENT_REJECTED: case RDMA_CM_EVENT_CONNECT_REQUEST: case RDMA_CM_EVENT_CONNECT_RESPONSE: case RDMA_CM_EVENT_CONNECT_ERROR: case RDMA_CM_EVENT_ADDR_ERROR: case RDMA_CM_EVENT_UNREACHABLE: c->status = Disconnected; rdma_disconnect(rdma->cm_id); break; default: BUG(); } complete(&rdma->cm_done); return 0; } static void recv_done(struct ib_cq *cq, struct ib_wc *wc) { struct p9_client *client = cq->cq_context; struct p9_trans_rdma *rdma = client->trans; struct p9_rdma_context *c = container_of(wc->wr_cqe, struct p9_rdma_context, cqe); struct p9_req_t *req; int err = 0; int16_t tag; req = NULL; ib_dma_unmap_single(rdma->cm_id->device, c->busa, client->msize, DMA_FROM_DEVICE); if (wc->status != IB_WC_SUCCESS) goto err_out; c->rc.size = wc->byte_len; err = p9_parse_header(&c->rc, NULL, NULL, &tag, 1); if (err) goto err_out; req = p9_tag_lookup(client, tag); if (!req) goto err_out; /* Check that we have not yet received a reply for this request. */ if (unlikely(req->rc.sdata)) { pr_err("Duplicate reply for request %d", tag); goto err_out; } req->rc.size = c->rc.size; req->rc.sdata = c->rc.sdata; p9_client_cb(client, req, REQ_STATUS_RCVD); out: up(&rdma->rq_sem); kfree(c); return; err_out: p9_debug(P9_DEBUG_ERROR, "req %p err %d status %d\n", req, err, wc->status); rdma->state = P9_RDMA_FLUSHING; client->status = Disconnected; goto out; } static void send_done(struct ib_cq *cq, struct ib_wc *wc) { struct p9_client *client = cq->cq_context; struct p9_trans_rdma *rdma = client->trans; struct p9_rdma_context *c = container_of(wc->wr_cqe, struct p9_rdma_context, cqe); ib_dma_unmap_single(rdma->cm_id->device, c->busa, c->req->tc.size, DMA_TO_DEVICE); up(&rdma->sq_sem); p9_req_put(client, c->req); kfree(c); } static void qp_event_handler(struct ib_event *event, void *context) { p9_debug(P9_DEBUG_ERROR, "QP event %d context %p\n", event->event, context); } static void rdma_destroy_trans(struct p9_trans_rdma *rdma) { if (!rdma) return; if (rdma->qp && !IS_ERR(rdma->qp)) ib_destroy_qp(rdma->qp); if (rdma->pd && !IS_ERR(rdma->pd)) ib_dealloc_pd(rdma->pd); if (rdma->cq && !IS_ERR(rdma->cq)) ib_free_cq(rdma->cq); if (rdma->cm_id && !IS_ERR(rdma->cm_id)) rdma_destroy_id(rdma->cm_id); kfree(rdma); } static int post_recv(struct p9_client *client, struct p9_rdma_context *c) { struct p9_trans_rdma *rdma = client->trans; struct ib_recv_wr wr; struct ib_sge sge; int ret; c->busa = ib_dma_map_single(rdma->cm_id->device, c->rc.sdata, client->msize, DMA_FROM_DEVICE); if (ib_dma_mapping_error(rdma->cm_id->device, c->busa)) goto error; c->cqe.done = recv_done; sge.addr = c->busa; sge.length = client->msize; sge.lkey = rdma->pd->local_dma_lkey; wr.next = NULL; wr.wr_cqe = &c->cqe; wr.sg_list = &sge; wr.num_sge = 1; ret = ib_post_recv(rdma->qp, &wr, NULL); if (ret) ib_dma_unmap_single(rdma->cm_id->device, c->busa, client->msize, DMA_FROM_DEVICE); return ret; error: p9_debug(P9_DEBUG_ERROR, "EIO\n"); return -EIO; } static int rdma_request(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_rdma *rdma = client->trans; struct ib_send_wr wr; struct ib_sge sge; int err = 0; unsigned long flags; struct p9_rdma_context *c = NULL; struct p9_rdma_context *rpl_context = NULL; /* When an error occurs between posting the recv and the send, * there will be a receive context posted without a pending request. * Since there is no way to "un-post" it, we remember it and skip * post_recv() for the next request. * So here, * see if we are this `next request' and need to absorb an excess rc. * If yes, then drop and free our own, and do not recv_post(). **/ if (unlikely(atomic_read(&rdma->excess_rc) > 0)) { if ((atomic_sub_return(1, &rdma->excess_rc) >= 0)) { /* Got one! */ p9_fcall_fini(&req->rc); req->rc.sdata = NULL; goto dont_need_post_recv; } else { /* We raced and lost. */ atomic_inc(&rdma->excess_rc); } } /* Allocate an fcall for the reply */ rpl_context = kmalloc(sizeof *rpl_context, GFP_NOFS); if (!rpl_context) { err = -ENOMEM; goto recv_error; } rpl_context->rc.sdata = req->rc.sdata; /* * Post a receive buffer for this request. We need to ensure * there is a reply buffer available for every outstanding * request. A flushed request can result in no reply for an * outstanding request, so we must keep a count to avoid * overflowing the RQ. */ if (down_interruptible(&rdma->rq_sem)) { err = -EINTR; goto recv_error; } err = post_recv(client, rpl_context); if (err) { p9_debug(P9_DEBUG_ERROR, "POST RECV failed: %d\n", err); goto recv_error; } /* remove posted receive buffer from request structure */ req->rc.sdata = NULL; dont_need_post_recv: /* Post the request */ c = kmalloc(sizeof *c, GFP_NOFS); if (!c) { err = -ENOMEM; goto send_error; } c->req = req; c->busa = ib_dma_map_single(rdma->cm_id->device, c->req->tc.sdata, c->req->tc.size, DMA_TO_DEVICE); if (ib_dma_mapping_error(rdma->cm_id->device, c->busa)) { err = -EIO; goto send_error; } c->cqe.done = send_done; sge.addr = c->busa; sge.length = c->req->tc.size; sge.lkey = rdma->pd->local_dma_lkey; wr.next = NULL; wr.wr_cqe = &c->cqe; wr.opcode = IB_WR_SEND; wr.send_flags = IB_SEND_SIGNALED; wr.sg_list = &sge; wr.num_sge = 1; if (down_interruptible(&rdma->sq_sem)) { err = -EINTR; goto dma_unmap; } /* Mark request as `sent' *before* we actually send it, * because doing if after could erase the REQ_STATUS_RCVD * status in case of a very fast reply. */ WRITE_ONCE(req->status, REQ_STATUS_SENT); err = ib_post_send(rdma->qp, &wr, NULL); if (err) goto dma_unmap; /* Success */ return 0; dma_unmap: ib_dma_unmap_single(rdma->cm_id->device, c->busa, c->req->tc.size, DMA_TO_DEVICE); /* Handle errors that happened during or while preparing the send: */ send_error: WRITE_ONCE(req->status, REQ_STATUS_ERROR); kfree(c); p9_debug(P9_DEBUG_ERROR, "Error %d in rdma_request()\n", err); /* Ach. * We did recv_post(), but not send. We have one recv_post in excess. */ atomic_inc(&rdma->excess_rc); return err; /* Handle errors that happened during or while preparing post_recv(): */ recv_error: kfree(rpl_context); spin_lock_irqsave(&rdma->req_lock, flags); if (err != -EINTR && rdma->state < P9_RDMA_CLOSING) { rdma->state = P9_RDMA_CLOSING; spin_unlock_irqrestore(&rdma->req_lock, flags); rdma_disconnect(rdma->cm_id); } else spin_unlock_irqrestore(&rdma->req_lock, flags); return err; } static void rdma_close(struct p9_client *client) { struct p9_trans_rdma *rdma; if (!client) return; rdma = client->trans; if (!rdma) return; client->status = Disconnected; rdma_disconnect(rdma->cm_id); rdma_destroy_trans(rdma); } /** * alloc_rdma - Allocate and initialize the rdma transport structure * @opts: Mount options structure */ static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts) { struct p9_trans_rdma *rdma; rdma = kzalloc(sizeof(struct p9_trans_rdma), GFP_KERNEL); if (!rdma) return NULL; rdma->port = opts->port; rdma->privport = opts->privport; rdma->sq_depth = opts->sq_depth; rdma->rq_depth = opts->rq_depth; rdma->timeout = opts->timeout; spin_lock_init(&rdma->req_lock); init_completion(&rdma->cm_done); sema_init(&rdma->sq_sem, rdma->sq_depth); sema_init(&rdma->rq_sem, rdma->rq_depth); atomic_set(&rdma->excess_rc, 0); return rdma; } static int rdma_cancel(struct p9_client *client, struct p9_req_t *req) { /* Nothing to do here. * We will take care of it (if we have to) in rdma_cancelled() */ return 1; } /* A request has been fully flushed without a reply. * That means we have posted one buffer in excess. */ static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req) { struct p9_trans_rdma *rdma = client->trans; atomic_inc(&rdma->excess_rc); return 0; } static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma) { struct sockaddr_in cl = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), }; int port, err = -EINVAL; for (port = P9_DEF_MAX_RESVPORT; port >= P9_DEF_MIN_RESVPORT; port--) { cl.sin_port = htons((ushort)port); err = rdma_bind_addr(rdma->cm_id, (struct sockaddr *)&cl); if (err != -EADDRINUSE) break; } return err; } /** * rdma_create_trans - Transport method for creating a transport instance * @client: client instance * @addr: IP address string * @args: Mount options string */ static int rdma_create_trans(struct p9_client *client, const char *addr, char *args) { int err; struct p9_rdma_opts opts; struct p9_trans_rdma *rdma; struct rdma_conn_param conn_param; struct ib_qp_init_attr qp_attr; if (addr == NULL) return -EINVAL; /* Parse the transport specific mount options */ err = parse_opts(args, &opts); if (err < 0) return err; /* Create and initialize the RDMA transport structure */ rdma = alloc_rdma(&opts); if (!rdma) return -ENOMEM; /* Create the RDMA CM ID */ rdma->cm_id = rdma_create_id(&init_net, p9_cm_event_handler, client, RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(rdma->cm_id)) goto error; /* Associate the client with the transport */ client->trans = rdma; /* Bind to a privileged port if we need to */ if (opts.privport) { err = p9_rdma_bind_privport(rdma); if (err < 0) { pr_err("%s (%d): problem binding to privport: %d\n", __func__, task_pid_nr(current), -err); goto error; } } /* Resolve the server's address */ rdma->addr.sin_family = AF_INET; rdma->addr.sin_addr.s_addr = in_aton(addr); rdma->addr.sin_port = htons(opts.port); err = rdma_resolve_addr(rdma->cm_id, NULL, (struct sockaddr *)&rdma->addr, rdma->timeout); if (err) goto error; err = wait_for_completion_interruptible(&rdma->cm_done); if (err || (rdma->state != P9_RDMA_ADDR_RESOLVED)) goto error; /* Resolve the route to the server */ err = rdma_resolve_route(rdma->cm_id, rdma->timeout); if (err) goto error; err = wait_for_completion_interruptible(&rdma->cm_done); if (err || (rdma->state != P9_RDMA_ROUTE_RESOLVED)) goto error; /* Create the Completion Queue */ rdma->cq = ib_alloc_cq_any(rdma->cm_id->device, client, opts.sq_depth + opts.rq_depth + 1, IB_POLL_SOFTIRQ); if (IS_ERR(rdma->cq)) goto error; /* Create the Protection Domain */ rdma->pd = ib_alloc_pd(rdma->cm_id->device, 0); if (IS_ERR(rdma->pd)) goto error; /* Create the Queue Pair */ memset(&qp_attr, 0, sizeof qp_attr); qp_attr.event_handler = qp_event_handler; qp_attr.qp_context = client; qp_attr.cap.max_send_wr = opts.sq_depth; qp_attr.cap.max_recv_wr = opts.rq_depth; qp_attr.cap.max_send_sge = P9_RDMA_SEND_SGE; qp_attr.cap.max_recv_sge = P9_RDMA_RECV_SGE; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = rdma->cq; qp_attr.recv_cq = rdma->cq; err = rdma_create_qp(rdma->cm_id, rdma->pd, &qp_attr); if (err) goto error; rdma->qp = rdma->cm_id->qp; /* Request a connection */ memset(&conn_param, 0, sizeof(conn_param)); conn_param.private_data = NULL; conn_param.private_data_len = 0; conn_param.responder_resources = P9_RDMA_IRD; conn_param.initiator_depth = P9_RDMA_ORD; err = rdma_connect(rdma->cm_id, &conn_param); if (err) goto error; err = wait_for_completion_interruptible(&rdma->cm_done); if (err || (rdma->state != P9_RDMA_CONNECTED)) goto error; client->status = Connected; return 0; error: rdma_destroy_trans(rdma); return -ENOTCONN; } static struct p9_trans_module p9_rdma_trans = { .name = "rdma", .maxsize = P9_RDMA_MAXSIZE, .pooled_rbuffers = true, .def = 0, .owner = THIS_MODULE, .create = rdma_create_trans, .close = rdma_close, .request = rdma_request, .cancel = rdma_cancel, .cancelled = rdma_cancelled, .show_options = p9_rdma_show_options, }; /** * p9_trans_rdma_init - Register the 9P RDMA transport driver */ static int __init p9_trans_rdma_init(void) { v9fs_register_trans(&p9_rdma_trans); return 0; } static void __exit p9_trans_rdma_exit(void) { v9fs_unregister_trans(&p9_rdma_trans); } module_init(p9_trans_rdma_init); module_exit(p9_trans_rdma_exit); MODULE_ALIAS_9P("rdma"); MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>"); MODULE_DESCRIPTION("RDMA Transport for 9P"); MODULE_LICENSE("Dual BSD/GPL"); |
| 4226 1 1 4118 109 4026 4026 3135 34 3120 19 19 4317 2792 353 4315 4323 2836 4311 4315 4304 4312 1401 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | / |