| 25 390 408 406 391 408 401 401 402 403 59 54 1 54 60 58 54 3 1 60 54 60 60 60 6 6 2 3 6 6 6 54 54 11 11 11 18 1 1 1 1 1 7 6 5 5 1 1 1 1 1 1 1 1 11 12 12 11 1 9 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * IPv6 Address Label subsystem * for the IPv6 "Default" Source Address Selection * * Copyright (C)2007 USAGI/WIDE Project */ /* * Author: * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> */ #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/in6.h> #include <linux/slab.h> #include <net/addrconf.h> #include <linux/if_addrlabel.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> #if 0 #define ADDRLABEL(x...) printk(x) #else #define ADDRLABEL(x...) do { ; } while (0) #endif /* * Policy Table */ struct ip6addrlbl_entry { struct in6_addr prefix; int prefixlen; int ifindex; int addrtype; u32 label; struct hlist_node list; struct rcu_head rcu; }; /* * Default policy table (RFC6724 + extensions) * * prefix addr_type label * ------------------------------------------------------------------------- * ::1/128 LOOPBACK 0 * ::/0 N/A 1 * 2002::/16 N/A 2 * ::/96 COMPATv4 3 * ::ffff:0:0/96 V4MAPPED 4 * fc00::/7 N/A 5 ULA (RFC 4193) * 2001::/32 N/A 6 Teredo (RFC 4380) * 2001:10::/28 N/A 7 ORCHID (RFC 4843) * fec0::/10 N/A 11 Site-local * (deprecated by RFC3879) * 3ffe::/16 N/A 12 6bone * * Note: 0xffffffff is used if we do not have any policies. * Note: Labels for ULA and 6to4 are different from labels listed in RFC6724. */ #define IPV6_ADDR_LABEL_DEFAULT 0xffffffffUL static const __net_initconst struct ip6addrlbl_init_table { const struct in6_addr *prefix; int prefixlen; u32 label; } ip6addrlbl_init_table[] = { { /* ::/0 */ .prefix = &in6addr_any, .label = 1, }, { /* fc00::/7 */ .prefix = &(struct in6_addr){ { { 0xfc } } } , .prefixlen = 7, .label = 5, }, { /* fec0::/10 */ .prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } }, .prefixlen = 10, .label = 11, }, { /* 2002::/16 */ .prefix = &(struct in6_addr){ { { 0x20, 0x02 } } }, .prefixlen = 16, .label = 2, }, { /* 3ffe::/16 */ .prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } }, .prefixlen = 16, .label = 12, }, { /* 2001::/32 */ .prefix = &(struct in6_addr){ { { 0x20, 0x01 } } }, .prefixlen = 32, .label = 6, }, { /* 2001:10::/28 */ .prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } }, .prefixlen = 28, .label = 7, }, { /* ::ffff:0:0 */ .prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } }, .prefixlen = 96, .label = 4, }, { /* ::/96 */ .prefix = &in6addr_any, .prefixlen = 96, .label = 3, }, { /* ::1/128 */ .prefix = &in6addr_loopback, .prefixlen = 128, .label = 0, } }; /* Find label */ static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p, const struct in6_addr *addr, int addrtype, int ifindex) { if (p->ifindex && p->ifindex != ifindex) return false; if (p->addrtype && p->addrtype != addrtype) return false; if (!ipv6_prefix_equal(addr, &p->prefix, p->prefixlen)) return false; return true; } static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex) { struct ip6addrlbl_entry *p; hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { if (__ip6addrlbl_match(p, addr, type, ifindex)) return p; } return NULL; } u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex) { u32 label; struct ip6addrlbl_entry *p; type &= IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK; rcu_read_lock(); p = __ipv6_addr_label(net, addr, type, ifindex); label = p ? p->label : IPV6_ADDR_LABEL_DEFAULT; rcu_read_unlock(); ADDRLABEL(KERN_DEBUG "%s(addr=%pI6, type=%d, ifindex=%d) => %08x\n", __func__, addr, type, ifindex, label); return label; } /* allocate one entry */ static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix, int prefixlen, int ifindex, u32 label) { struct ip6addrlbl_entry *newp; int addrtype; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u)\n", __func__, prefix, prefixlen, ifindex, (unsigned int)label); addrtype = ipv6_addr_type(prefix) & (IPV6_ADDR_MAPPED | IPV6_ADDR_COMPATv4 | IPV6_ADDR_LOOPBACK); switch (addrtype) { case IPV6_ADDR_MAPPED: if (prefixlen > 96) return ERR_PTR(-EINVAL); if (prefixlen < 96) addrtype = 0; break; case IPV6_ADDR_COMPATv4: if (prefixlen != 96) addrtype = 0; break; case IPV6_ADDR_LOOPBACK: if (prefixlen != 128) addrtype = 0; break; } newp = kmalloc(sizeof(*newp), GFP_KERNEL); if (!newp) return ERR_PTR(-ENOMEM); ipv6_addr_prefix(&newp->prefix, prefix, prefixlen); newp->prefixlen = prefixlen; newp->ifindex = ifindex; newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); return newp; } /* add a label */ static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp, int replace) { struct ip6addrlbl_entry *last = NULL, *p = NULL; struct hlist_node *n; int ret = 0; ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp, replace); hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == newp->prefixlen && p->ifindex == newp->ifindex && ipv6_addr_equal(&p->prefix, &newp->prefix)) { if (!replace) { ret = -EEXIST; goto out; } hlist_replace_rcu(&p->list, &newp->list); kfree_rcu(p, rcu); goto out; } else if ((p->prefixlen == newp->prefixlen && !p->ifindex) || (p->prefixlen < newp->prefixlen)) { hlist_add_before_rcu(&newp->list, &p->list); goto out; } last = p; } if (last) hlist_add_behind_rcu(&newp->list, &last->list); else hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head); out: if (!ret) net->ipv6.ip6addrlbl_table.seq++; return ret; } /* add a label */ static int ip6addrlbl_add(struct net *net, const struct in6_addr *prefix, int prefixlen, int ifindex, u32 label, int replace) { struct ip6addrlbl_entry *newp; int ret = 0; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d, label=%u, replace=%d)\n", __func__, prefix, prefixlen, ifindex, (unsigned int)label, replace); newp = ip6addrlbl_alloc(prefix, prefixlen, ifindex, label); if (IS_ERR(newp)) return PTR_ERR(newp); spin_lock(&net->ipv6.ip6addrlbl_table.lock); ret = __ip6addrlbl_add(net, newp, replace); spin_unlock(&net->ipv6.ip6addrlbl_table.lock); if (ret) kfree(newp); return ret; } /* remove a label */ static int __ip6addrlbl_del(struct net *net, const struct in6_addr *prefix, int prefixlen, int ifindex) { struct ip6addrlbl_entry *p = NULL; struct hlist_node *n; int ret = -ESRCH; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == prefixlen && p->ifindex == ifindex && ipv6_addr_equal(&p->prefix, prefix)) { hlist_del_rcu(&p->list); kfree_rcu(p, rcu); ret = 0; break; } } return ret; } static int ip6addrlbl_del(struct net *net, const struct in6_addr *prefix, int prefixlen, int ifindex) { struct in6_addr prefix_buf; int ret; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); ipv6_addr_prefix(&prefix_buf, prefix, prefixlen); spin_lock(&net->ipv6.ip6addrlbl_table.lock); ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex); spin_unlock(&net->ipv6.ip6addrlbl_table.lock); return ret; } /* add default label */ static int __net_init ip6addrlbl_net_init(struct net *net) { struct ip6addrlbl_entry *p = NULL; struct hlist_node *n; int err; int i; ADDRLABEL(KERN_DEBUG "%s\n", __func__); spin_lock_init(&net->ipv6.ip6addrlbl_table.lock); INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { err = ip6addrlbl_add(net, ip6addrlbl_init_table[i].prefix, ip6addrlbl_init_table[i].prefixlen, 0, ip6addrlbl_init_table[i].label, 0); if (err) goto err_ip6addrlbl_add; } return 0; err_ip6addrlbl_add: hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { hlist_del_rcu(&p->list); kfree_rcu(p, rcu); } return err; } static void __net_exit ip6addrlbl_net_exit(struct net *net) { struct ip6addrlbl_entry *p = NULL; struct hlist_node *n; /* Remove all labels belonging to the exiting net */ spin_lock(&net->ipv6.ip6addrlbl_table.lock); hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { hlist_del_rcu(&p->list); kfree_rcu(p, rcu); } spin_unlock(&net->ipv6.ip6addrlbl_table.lock); } static struct pernet_operations ipv6_addr_label_ops = { .init = ip6addrlbl_net_init, .exit = ip6addrlbl_net_exit, }; int __init ipv6_addr_label_init(void) { return register_pernet_subsys(&ipv6_addr_label_ops); } void ipv6_addr_label_cleanup(void) { unregister_pernet_subsys(&ipv6_addr_label_ops); } static const struct nla_policy ifal_policy[IFAL_MAX+1] = { [IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), }, [IFAL_LABEL] = { .len = sizeof(u32), }, }; static bool addrlbl_ifindex_exists(struct net *net, int ifindex) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); rcu_read_unlock(); return dev != NULL; } static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct ifaddrlblmsg *ifal; struct nlattr *tb[IFAL_MAX+1]; struct in6_addr *pfx; u32 label; int err = 0; err = nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy, extack); if (err < 0) return err; ifal = nlmsg_data(nlh); if (ifal->ifal_family != AF_INET6 || ifal->ifal_prefixlen > 128) return -EINVAL; if (!tb[IFAL_ADDRESS]) return -EINVAL; pfx = nla_data(tb[IFAL_ADDRESS]); if (!tb[IFAL_LABEL]) return -EINVAL; label = nla_get_u32(tb[IFAL_LABEL]); if (label == IPV6_ADDR_LABEL_DEFAULT) return -EINVAL; switch (nlh->nlmsg_type) { case RTM_NEWADDRLABEL: if (ifal->ifal_index && !addrlbl_ifindex_exists(net, ifal->ifal_index)) return -EINVAL; err = ip6addrlbl_add(net, pfx, ifal->ifal_prefixlen, ifal->ifal_index, label, nlh->nlmsg_flags & NLM_F_REPLACE); break; case RTM_DELADDRLABEL: err = ip6addrlbl_del(net, pfx, ifal->ifal_prefixlen, ifal->ifal_index); break; default: err = -EOPNOTSUPP; } return err; } static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, int prefixlen, int ifindex, u32 lseq) { struct ifaddrlblmsg *ifal = nlmsg_data(nlh); ifal->ifal_family = AF_INET6; ifal->__ifal_reserved = 0; ifal->ifal_prefixlen = prefixlen; ifal->ifal_flags = 0; ifal->ifal_index = ifindex; ifal->ifal_seq = lseq; }; static int ip6addrlbl_fill(struct sk_buff *skb, struct ip6addrlbl_entry *p, u32 lseq, u32 portid, u32 seq, int event, unsigned int flags) { struct nlmsghdr *nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrlblmsg), flags); if (!nlh) return -EMSGSIZE; ip6addrlbl_putmsg(nlh, p->prefixlen, p->ifindex, lseq); if (nla_put_in6_addr(skb, IFAL_ADDRESS, &p->prefix) < 0 || nla_put_u32(skb, IFAL_LABEL, p->label) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ifaddrlblmsg *ifal; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for address label dump request"); return -EINVAL; } ifal = nlmsg_data(nlh); if (ifal->__ifal_reserved || ifal->ifal_prefixlen || ifal->ifal_flags || ifal->ifal_index || ifal->ifal_seq) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address label dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ifal))) { NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump request"); return -EINVAL; } return 0; } static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct ip6addrlbl_entry *p; int idx = 0, s_idx = cb->args[0]; int err; if (cb->strict_check) { err = ip6addrlbl_valid_dump_req(nlh, cb->extack); if (err < 0) return err; } rcu_read_lock(); hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { if (idx >= s_idx) { err = ip6addrlbl_fill(skb, p, net->ipv6.ip6addrlbl_table.seq, NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, RTM_NEWADDRLABEL, NLM_F_MULTI); if (err < 0) break; } idx++; } rcu_read_unlock(); cb->args[0] = idx; return skb->len; } static inline int ip6addrlbl_msgsize(void) { return NLMSG_ALIGN(sizeof(struct ifaddrlblmsg)) + nla_total_size(16) /* IFAL_ADDRESS */ + nla_total_size(4); /* IFAL_LABEL */ } static int ip6addrlbl_valid_get_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct ifaddrlblmsg *ifal; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for addrlabel get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy, extack); ifal = nlmsg_data(nlh); if (ifal->__ifal_reserved || ifal->ifal_flags || ifal->ifal_seq) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for addrlabel get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy, extack); if (err) return err; for (i = 0; i <= IFAL_MAX; i++) { if (!tb[i]) continue; switch (i) { case IFAL_ADDRESS: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in addrlabel get request"); return -EINVAL; } } return 0; } static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct ifaddrlblmsg *ifal; struct nlattr *tb[IFAL_MAX+1]; struct in6_addr *addr; u32 lseq; int err = 0; struct ip6addrlbl_entry *p; struct sk_buff *skb; err = ip6addrlbl_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) return err; ifal = nlmsg_data(nlh); if (ifal->ifal_family != AF_INET6 || ifal->ifal_prefixlen != 128) return -EINVAL; if (ifal->ifal_index && !addrlbl_ifindex_exists(net, ifal->ifal_index)) return -EINVAL; if (!tb[IFAL_ADDRESS]) return -EINVAL; addr = nla_data(tb[IFAL_ADDRESS]); skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); if (!skb) return -ENOBUFS; err = -ESRCH; rcu_read_lock(); p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); lseq = net->ipv6.ip6addrlbl_table.seq; if (p) err = ip6addrlbl_fill(skb, p, lseq, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWADDRLABEL, 0); rcu_read_unlock(); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(skb); } else { err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); } return err; } int __init ipv6_addr_label_rtnl_register(void) { int ret; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel, NULL, RTNL_FLAG_DOIT_UNLOCKED); if (ret < 0) return ret; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel, NULL, RTNL_FLAG_DOIT_UNLOCKED); if (ret < 0) return ret; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, ip6addrlbl_dump, RTNL_FLAG_DOIT_UNLOCKED); return ret; } |
| 54 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/kernel.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pkt_sched.h> #include <net/caif/caif_layer.h> #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> #include <net/caif/caif_dev.h> #define SRVL_CTRL_PKT_SIZE 1 #define SRVL_FLOW_OFF 0x81 #define SRVL_FLOW_ON 0x80 #define SRVL_SET_PIN 0x82 #define container_obj(layr) container_of(layr, struct cfsrvl, layer) static void cfservl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid) { struct cfsrvl *service = container_obj(layr); if (layr->up == NULL || layr->up->ctrlcmd == NULL) return; switch (ctrl) { case CAIF_CTRLCMD_INIT_RSP: service->open = true; layr->up->ctrlcmd(layr->up, ctrl, phyid); break; case CAIF_CTRLCMD_DEINIT_RSP: case CAIF_CTRLCMD_INIT_FAIL_RSP: service->open = false; layr->up->ctrlcmd(layr->up, ctrl, phyid); break; case _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND: if (phyid != service->dev_info.id) break; if (service->modem_flow_on) layr->up->ctrlcmd(layr->up, CAIF_CTRLCMD_FLOW_OFF_IND, phyid); service->phy_flow_on = false; break; case _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND: if (phyid != service->dev_info.id) return; if (service->modem_flow_on) { layr->up->ctrlcmd(layr->up, CAIF_CTRLCMD_FLOW_ON_IND, phyid); } service->phy_flow_on = true; break; case CAIF_CTRLCMD_FLOW_OFF_IND: if (service->phy_flow_on) { layr->up->ctrlcmd(layr->up, CAIF_CTRLCMD_FLOW_OFF_IND, phyid); } service->modem_flow_on = false; break; case CAIF_CTRLCMD_FLOW_ON_IND: if (service->phy_flow_on) { layr->up->ctrlcmd(layr->up, CAIF_CTRLCMD_FLOW_ON_IND, phyid); } service->modem_flow_on = true; break; case _CAIF_CTRLCMD_PHYIF_DOWN_IND: /* In case interface is down, let's fake a remove shutdown */ layr->up->ctrlcmd(layr->up, CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND, phyid); break; case CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND: layr->up->ctrlcmd(layr->up, ctrl, phyid); break; default: pr_warn("Unexpected ctrl in cfsrvl (%d)\n", ctrl); /* We have both modem and phy flow on, send flow on */ layr->up->ctrlcmd(layr->up, ctrl, phyid); service->phy_flow_on = true; break; } } static int cfservl_modemcmd(struct cflayer *layr, enum caif_modemcmd ctrl) { struct cfsrvl *service = container_obj(layr); caif_assert(layr != NULL); caif_assert(layr->dn != NULL); caif_assert(layr->dn->transmit != NULL); if (!service->supports_flowctrl) return 0; switch (ctrl) { case CAIF_MODEMCMD_FLOW_ON_REQ: { struct cfpkt *pkt; struct caif_payload_info *info; u8 flow_on = SRVL_FLOW_ON; pkt = cfpkt_create(SRVL_CTRL_PKT_SIZE); if (!pkt) return -ENOMEM; if (cfpkt_add_head(pkt, &flow_on, 1) < 0) { pr_err("Packet is erroneous!\n"); cfpkt_destroy(pkt); return -EPROTO; } info = cfpkt_info(pkt); info->channel_id = service->layer.id; info->hdr_len = 1; info->dev_info = &service->dev_info; cfpkt_set_prio(pkt, TC_PRIO_CONTROL); return layr->dn->transmit(layr->dn, pkt); } case CAIF_MODEMCMD_FLOW_OFF_REQ: { struct cfpkt *pkt; struct caif_payload_info *info; u8 flow_off = SRVL_FLOW_OFF; pkt = cfpkt_create(SRVL_CTRL_PKT_SIZE); if (!pkt) return -ENOMEM; if (cfpkt_add_head(pkt, &flow_off, 1) < 0) { pr_err("Packet is erroneous!\n"); cfpkt_destroy(pkt); return -EPROTO; } info = cfpkt_info(pkt); info->channel_id = service->layer.id; info->hdr_len = 1; info->dev_info = &service->dev_info; cfpkt_set_prio(pkt, TC_PRIO_CONTROL); return layr->dn->transmit(layr->dn, pkt); } default: break; } return -EINVAL; } static void cfsrvl_release(struct cflayer *layer) { struct cfsrvl *service = container_of(layer, struct cfsrvl, layer); kfree(service); } void cfsrvl_init(struct cfsrvl *service, u8 channel_id, struct dev_info *dev_info, bool supports_flowctrl) { caif_assert(offsetof(struct cfsrvl, layer) == 0); service->open = false; service->modem_flow_on = true; service->phy_flow_on = true; service->layer.id = channel_id; service->layer.ctrlcmd = cfservl_ctrlcmd; service->layer.modemcmd = cfservl_modemcmd; service->dev_info = *dev_info; service->supports_flowctrl = supports_flowctrl; service->release = cfsrvl_release; } bool cfsrvl_ready(struct cfsrvl *service, int *err) { if (!service->open) { *err = -ENOTCONN; return false; } return true; } u8 cfsrvl_getphyid(struct cflayer *layer) { struct cfsrvl *servl = container_obj(layer); return servl->dev_info.id; } bool cfsrvl_phyid_match(struct cflayer *layer, int phyid) { struct cfsrvl *servl = container_obj(layer); return servl->dev_info.id == phyid; } void caif_free_client(struct cflayer *adap_layer) { struct cfsrvl *servl; if (adap_layer == NULL || adap_layer->dn == NULL) return; servl = container_obj(adap_layer->dn); servl->release(&servl->layer); } EXPORT_SYMBOL(caif_free_client); void caif_client_register_refcnt(struct cflayer *adapt_layer, void (*hold)(struct cflayer *lyr), void (*put)(struct cflayer *lyr)) { struct cfsrvl *service; if (WARN_ON(adapt_layer == NULL || adapt_layer->dn == NULL)) return; service = container_of(adapt_layer->dn, struct cfsrvl, layer); service->hold = hold; service->put = put; } EXPORT_SYMBOL(caif_client_register_refcnt); |
| 54 54 54 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the Netfilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Peter Kese <peter.kese@ijs.si> * Julian Anastasov <ja@ssi.bg> * * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese, * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms * and others. * * Changes: * Paul `Rusty' Russell properly handle non-linear skbs * Harald Welte don't use nfcache */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/sctp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <net/ip.h> #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> /* for icmp_send */ #include <net/gue.h> #include <net/gre.h> #include <net/route.h> #include <net/ip6_checksum.h> #include <net/netns/generic.h> /* net_generic() */ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <linux/netfilter_ipv6.h> #include <net/ip6_route.h> #endif #include <net/ip_vs.h> #include <linux/indirect_call_wrapper.h> EXPORT_SYMBOL(register_ip_vs_scheduler); EXPORT_SYMBOL(unregister_ip_vs_scheduler); EXPORT_SYMBOL(ip_vs_proto_name); EXPORT_SYMBOL(ip_vs_conn_new); EXPORT_SYMBOL(ip_vs_conn_in_get); EXPORT_SYMBOL(ip_vs_conn_out_get); #ifdef CONFIG_IP_VS_PROTO_TCP EXPORT_SYMBOL(ip_vs_tcp_conn_listen); #endif EXPORT_SYMBOL(ip_vs_conn_put); #ifdef CONFIG_IP_VS_DEBUG EXPORT_SYMBOL(ip_vs_get_debug_level); #endif EXPORT_SYMBOL(ip_vs_new_conn_out); #if defined(CONFIG_IP_VS_PROTO_TCP) && defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) \ INDIRECT_CALL_2(f, tcp_snat_handler, udp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_TCP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, tcp_snat_handler, __VA_ARGS__) #elif defined(CONFIG_IP_VS_PROTO_UDP) #define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, udp_snat_handler, __VA_ARGS__) #else #define SNAT_CALL(f, ...) f(__VA_ARGS__) #endif static unsigned int ip_vs_net_id __read_mostly; /* netns cnt used for uniqueness */ static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); /* ID used in ICMP lookups */ #define icmp_id(icmph) (((icmph)->un).echo.id) #define icmpv6_id(icmph) (icmph->icmp6_dataun.u_echo.identifier) const char *ip_vs_proto_name(unsigned int proto) { static char buf[20]; switch (proto) { case IPPROTO_IP: return "IP"; case IPPROTO_UDP: return "UDP"; case IPPROTO_TCP: return "TCP"; case IPPROTO_SCTP: return "SCTP"; case IPPROTO_ICMP: return "ICMP"; #ifdef CONFIG_IP_VS_IPV6 case IPPROTO_ICMPV6: return "ICMPv6"; #endif default: sprintf(buf, "IP_%u", proto); return buf; } } void ip_vs_init_hash_table(struct list_head *table, int rows) { while (--rows >= 0) INIT_LIST_HEAD(&table[rows]); } static inline void ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; struct ip_vs_service *svc; local_bh_disable(); s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); local_bh_enable(); } } static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_cpu_stats *s; local_bh_disable(); s = this_cpu_ptr(cp->dest->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); local_bh_enable(); } static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { if (likely(pd->pp->state_transition)) pd->pp->state_transition(cp, direction, skb, pd); } static inline int ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, struct sk_buff *skb, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = rcu_dereference(svc->pe); if (p->pe && p->pe->fill_param) return p->pe->fill_param(p, skb); return 0; } /* * IPVS persistent scheduling function * It creates a connection entry according to its template if exists, * or selects a server and creates a connection entry plus a template. * Locking: we are svc user (svc->refcnt), so we hold all dests too * Protocols supported: TCP, UDP */ static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, struct sk_buff *skb, __be16 src_port, __be16 dst_port, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp = NULL; struct ip_vs_dest *dest; struct ip_vs_conn *ct; __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ const union nf_inet_addr *src_addr, *dst_addr; if (likely(!ip_vs_iph_inverse(iph))) { src_addr = &iph->saddr; dst_addr = &iph->daddr; } else { src_addr = &iph->daddr; dst_addr = &iph->saddr; } /* Mask saddr with the netmask to adjust template granularity */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &src_addr->in6, (__force __u32) svc->netmask); else #endif snet.ip = src_addr->ip & svc->netmask; IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", IP_VS_DBG_ADDR(svc->af, src_addr), ntohs(src_port), IP_VS_DBG_ADDR(svc->af, dst_addr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* * As far as we know, FTP is a very complicated network protocol, and * it uses control connection and data connections. For active FTP, * FTP server initialize data connection to the client, its source port * is often 20. For passive FTP, FTP server tells the clients the port * that it passively listens to, and the client issues the data * connection. In the tunneling or direct routing mode, the load * balancer is on the client-to-server half of connection, the port * number is unknown to the load balancer. So, a conn template like * <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP * service, and a template like <caddr, 0, vaddr, vport, daddr, dport> * is created for other persistent services. */ { int protocol = iph->protocol; const union nf_inet_addr *vaddr = dst_addr; __be16 vport = 0; if (dst_port == svc->port) { /* non-FTP template: * <protocol, caddr, 0, vaddr, vport, daddr, dport> * FTP template: * <protocol, caddr, 0, vaddr, 0, daddr, 0> */ if (svc->port != FTPPORT) vport = dst_port; } else { /* Note: persistent fwmark-based services and * persistent port zero service are handled here. * fwmark template: * <IPPROTO_IP,caddr,0,fwmark,0,daddr,0> * port zero template: * <protocol,caddr,0,vaddr,0,daddr,0> */ if (svc->fwmark) { protocol = IPPROTO_IP; vaddr = &fwmark; } } /* return *ignored = -1 so NF_DROP can be used */ if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, vaddr, vport, ¶m) < 0) { *ignored = -1; return NULL; } } /* Check if a template already exists */ ct = ip_vs_ct_in_get(¶m); if (!ct || !ip_vs_check_template(ct, NULL)) { struct ip_vs_scheduler *sched; /* * No template found or the dest of the connection * template is not available. * return *ignored=0 i.e. ICMP and NF_DROP */ sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); *ignored = 0; return NULL; } if (dst_port == svc->port && svc->port != FTPPORT) dport = dest->port; /* Create a template * This adds param.pe_data to the template, * and thus param.pe_data will be destroyed * when the template expires */ ct = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, IP_VS_CONN_F_TEMPLATE, dest, skb->mark); if (ct == NULL) { kfree(param.pe_data); *ignored = -1; return NULL; } ct->timeout = svc->timeout; } else { /* set destination with the found template */ dest = ct->dest; kfree(param.pe_data); } dport = dst_port; if (dport == svc->port && dest->port) dport = dest->port; flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a new connection according to the template */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr, src_port, dst_addr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest, skb->mark); if (cp == NULL) { ip_vs_conn_put(ct); *ignored = -1; return NULL; } /* * Add its control */ ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); ip_vs_conn_stats(cp, svc); return cp; } /* * IPVS main scheduling function * It selects a server according to the virtual service, and * creates a connection entry. * Protocols supported: TCP, UDP * * Usage of *ignored * * 1 : protocol tried to schedule (eg. on SYN), found svc but the * svc/scheduler decides that this packet should be accepted with * NF_ACCEPT because it must not be scheduled. * * 0 : scheduler can not find destination, so try bypass or * return ICMP and then NF_DROP (ip_vs_leave). * * -1 : scheduler tried to schedule but fatal error occurred, eg. * ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param * failure such as missing Call-ID, ENOMEM on skb_linearize * or pe_data. In this case we should return NF_DROP without * any attempts to send ICMP with ip_vs_leave. */ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *ignored, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; struct ip_vs_conn *cp = NULL; struct ip_vs_scheduler *sched; struct ip_vs_dest *dest; __be16 _ports[2], *pptr, cport, vport; const void *caddr, *vaddr; unsigned int flags; *ignored = 1; /* * IPv6 frags, only the first hit here. */ pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (pptr == NULL) return NULL; if (likely(!ip_vs_iph_inverse(iph))) { cport = pptr[0]; caddr = &iph->saddr; vport = pptr[1]; vaddr = &iph->daddr; } else { cport = pptr[1]; caddr = &iph->daddr; vport = pptr[0]; vaddr = &iph->saddr; } /* * FTPDATA needs this check when using local real server. * Never schedule Active FTPDATA connections from real server. * For LVS-NAT they must be already created. For other methods * with persistence the connection is created on SYN+ACK. */ if (cport == FTPDATA) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling FTPDATA"); return NULL; } /* * Do not schedule replies from local real server. */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { iph->hdr_flags ^= IP_VS_HDR_INVERSE; cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, svc->ipvs, svc->af, skb, iph); iph->hdr_flags ^= IP_VS_HDR_INVERSE; if (cp) { IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling reply for existing" " connection"); __ip_vs_conn_put(cp); return NULL; } } /* * Persistent service */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) return ip_vs_sched_persist(svc, skb, cport, vport, ignored, iph); *ignored = 0; /* * Non-persistent service */ if (!svc->fwmark && vport != svc->port) { if (!svc->port) pr_err("Schedule: port zero only supported " "in persistent services, " "check your ipvs configuration\n"); return NULL; } sched = rcu_dereference(svc->scheduler); if (sched) { /* read svc->sched_data after svc->scheduler */ smp_rmb(); dest = sched->schedule(svc, skb, iph); } else { dest = NULL; } if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); return NULL; } flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* * Create a connection entry. */ { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, &p); cp = ip_vs_conn_new(&p, dest->af, &dest->addr, dest->port ? dest->port : vport, flags, dest, skb->mark); if (!cp) { *ignored = -1; return NULL; } } IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); ip_vs_conn_stats(cp, svc); return cp; } static inline int ip_vs_addr_is_unicast(struct net *net, int af, union nf_inet_addr *addr) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) return ipv6_addr_type(&addr->in6) & IPV6_ADDR_UNICAST; #endif return (inet_addr_type(net, addr->ip) == RTN_UNICAST); } /* * Pass or drop the packet. * Called by ip_vs_in, when the virtual service is available but * no destination is available for a new connection. */ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { __be16 _ports[2], *pptr, dport; struct netns_ipvs *ipvs = svc->ipvs; struct net *net = ipvs->net; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NF_DROP; dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0]; /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create a cache_bypass connection entry */ if (sysctl_cache_bypass(ipvs) && svc->fwmark && !(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) && ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) { int ret; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } }; /* create a new connection entry */ IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, svc->af, &daddr, 0, IP_VS_CONN_F_BYPASS | flags, NULL, skb->mark); if (!cp) return NF_DROP; } /* statistics */ ip_vs_in_stats(cp, skb); /* set state */ ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp, iph); /* do not touch skb anymore */ if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) atomic_inc(&cp->control->in_pkts); else atomic_inc(&cp->in_pkts); ip_vs_conn_put(cp); return ret; } /* * When the virtual ftp service is presented, packets destined * for other services on the VIP may get here (except services * listed in the ipvs table), pass the packets, because it is * not ipvs job to decide to drop the packets. */ if (svc->port == FTPPORT && dport != FTPPORT) return NF_ACCEPT; if (unlikely(ip_vs_iph_icmp(iph))) return NF_DROP; /* * Notify the client that the destination is unreachable, and * release the socket buffer. * Since it is in IP layer, the TCP socket is not actually * created, the TCP RST packet cannot be sent, instead that * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) { if (!skb->dev) skb->dev = net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } #ifdef CONFIG_SYSCTL static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return ipvs->sysctl_snat_reroute; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return ipvs->sysctl_nat_icmp_send; } #else static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; } static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } #endif __sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset) { return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0)); } static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum) { if (NF_INET_LOCAL_IN == hooknum) return IP_DEFRAG_VS_IN; if (NF_INET_FORWARD == hooknum) return IP_DEFRAG_VS_FWD; return IP_DEFRAG_VS_OUT; } static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs, struct sk_buff *skb, u_int32_t user) { int err; local_bh_disable(); err = ip_defrag(ipvs->net, skb, user); local_bh_enable(); if (!err) ip_send_check(ip_hdr(skb)); return err; } static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, unsigned int hooknum) { if (!sysctl_snat_reroute(ipvs)) return 0; /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ if (NF_INET_LOCAL_IN == hooknum) return 0; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; } /* * Packet has been made sufficiently writable in caller * - inout: 1=in->out, 0=out->in */ void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct iphdr *iph = ip_hdr(skb); unsigned int icmp_offset = iph->ihl*4; struct icmphdr *icmph = (struct icmphdr *)(skb_network_header(skb) + icmp_offset); struct iphdr *ciph = (struct iphdr *)(icmph + 1); if (inout) { iph->saddr = cp->vaddr.ip; ip_send_check(iph); ciph->daddr = cp->vaddr.ip; ip_send_check(ciph); } else { iph->daddr = cp->daddr.ip; ip_send_check(iph); ciph->saddr = cp->daddr.ip; ip_send_check(ciph); } /* the TCP/UDP/SCTP port */ if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol || IPPROTO_SCTP == ciph->protocol) { __be16 *ports = (void *)ciph + ciph->ihl*4; if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->checksum = 0; icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset); skb->ip_summed = CHECKSUM_UNNECESSARY; if (inout) IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMP"); else IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMP"); } #ifdef CONFIG_IP_VS_IPV6 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, int inout) { struct ipv6hdr *iph = ipv6_hdr(skb); unsigned int icmp_offset = 0; unsigned int offs = 0; /* header offset*/ int protocol; struct icmp6hdr *icmph; struct ipv6hdr *ciph; unsigned short fragoffs; ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL); icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset); offs = icmp_offset + sizeof(struct icmp6hdr); ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs); protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL); if (inout) { iph->saddr = cp->vaddr.in6; ciph->daddr = cp->vaddr.in6; } else { iph->daddr = cp->daddr.in6; ciph->saddr = cp->daddr.in6; } /* the TCP/UDP/SCTP port */ if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol)) { __be16 *ports = (void *)(skb_network_header(skb) + offs); IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__, ntohs(inout ? ports[1] : ports[0]), ntohs(inout ? cp->vport : cp->dport)); if (inout) ports[1] = cp->vport; else ports[0] = cp->dport; } /* And finally the ICMP checksum */ icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, skb->len - icmp_offset, IPPROTO_ICMPV6, 0); skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset; skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum); skb->ip_summed = CHECKSUM_PARTIAL; if (inout) IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered outgoing ICMPv6"); else IP_VS_DBG_PKT(11, AF_INET6, pp, skb, (void *)ciph - (void *)iph, "Forwarding altered incoming ICMPv6"); } #endif /* Handle relevant response ICMP messages - forward to the right * destination host. */ static int handle_response_icmp(int af, struct sk_buff *skb, union nf_inet_addr *snet, __u8 protocol, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, unsigned int offset, unsigned int ihl, unsigned int hooknum) { unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n", IP_VS_DBG_ADDR(af, snet)); goto out; } if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol) offset += 2 * sizeof(__u16); if (skb_ensure_writable(skb, offset)) goto out; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_nat_icmp_v6(skb, pp, cp, 1); else #endif ip_vs_nat_icmp(skb, pp, cp, 1); if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; after_nat: /* do the statistics and put it back */ ip_vs_out_stats(cp, skb); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); verdict = NF_ACCEPT; out: __ip_vs_conn_put(cp); return verdict; } /* * Handle ICMP messages in the inside-to-outside direction (outgoing). * Find any that might be relevant, check against existing connections. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; unsigned int offset, ihl; union nf_inet_addr snet; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(cih->protocol); if (!pp) return NF_ACCEPT; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp, pp, ciph.len, ihl, hooknum); } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *ipvsh) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (ipvsh->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &ipvsh->saddr, &ipvsh->daddr); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, ipvsh->len + sizeof(_icmph), true, &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; snet.in6 = ciph.saddr.in6; offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, pp, offset, sizeof(struct ipv6hdr), hooknum); } #endif /* * Check if sctp chunc is ABORT chunk */ static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len) { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, nh_len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return 0; if (sch->type == SCTP_CID_ABORT) return 1; return 0; } static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, nh_len, sizeof(_tcph), &_tcph); if (th == NULL) return 0; return th->rst; } static inline bool is_new_conn(const struct sk_buff *skb, struct ip_vs_iphdr *iph) { switch (iph->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th == NULL) return false; return th->syn; } case IPPROTO_SCTP: { struct sctp_chunkhdr *sch, schunk; sch = skb_header_pointer(skb, iph->len + sizeof(struct sctphdr), sizeof(schunk), &schunk); if (sch == NULL) return false; return sch->type == SCTP_CID_INIT; } default: return false; } } static inline bool is_new_conn_expected(const struct ip_vs_conn *cp, int conn_reuse_mode) { /* Controlled (FTP DATA or persistence)? */ if (cp->control) return false; switch (cp->protocol) { case IPPROTO_TCP: return (cp->state == IP_VS_TCP_S_TIME_WAIT) || (cp->state == IP_VS_TCP_S_CLOSE) || ((conn_reuse_mode & 2) && (cp->state == IP_VS_TCP_S_FIN_WAIT) && (cp->flags & IP_VS_CONN_F_NOOUTPUT)); case IPPROTO_SCTP: return cp->state == IP_VS_SCTP_S_CLOSED; default: return false; } } /* Generic function to create new connections for outgoing RS packets * * Pre-requisites for successful connection creation: * 1) Virtual Service is NOT fwmark based: * In fwmark-VS actual vaddr and vport are unknown to IPVS * 2) Real Server and Virtual Service were NOT configured without port: * This is to allow match of different VS to the same RS ip-addr */ struct ip_vs_conn *ip_vs_new_conn_out(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct sk_buff *skb, const struct ip_vs_iphdr *iph, __be16 dport, __be16 cport) { struct ip_vs_conn_param param; struct ip_vs_conn *ct = NULL, *cp = NULL; const union nf_inet_addr *vaddr, *daddr, *caddr; union nf_inet_addr snet; __be16 vport; unsigned int flags; EnterFunction(12); vaddr = &svc->addr; vport = svc->port; daddr = &iph->saddr; caddr = &iph->daddr; /* check pre-requisites are satisfied */ if (svc->fwmark) return NULL; if (!vport || !dport) return NULL; /* for persistent service first create connection template */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) { /* apply netmask the same way ingress-side does */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) ipv6_addr_prefix(&snet.in6, &caddr->in6, (__force __u32)svc->netmask); else #endif snet.ip = caddr->ip & svc->netmask; /* fill params and create template if not existent */ if (ip_vs_conn_fill_param_persist(svc, skb, iph->protocol, &snet, 0, vaddr, vport, ¶m) < 0) return NULL; ct = ip_vs_ct_in_get(¶m); /* check if template exists and points to the same dest */ if (!ct || !ip_vs_check_template(ct, dest)) { ct = ip_vs_conn_new(¶m, dest->af, daddr, dport, IP_VS_CONN_F_TEMPLATE, dest, 0); if (!ct) { kfree(param.pe_data); return NULL; } ct->timeout = svc->timeout; } else { kfree(param.pe_data); } } /* connection flags */ flags = ((svc->flags & IP_VS_SVC_F_ONEPACKET) && iph->protocol == IPPROTO_UDP) ? IP_VS_CONN_F_ONE_PACKET : 0; /* create connection */ ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, caddr, cport, vaddr, vport, ¶m); cp = ip_vs_conn_new(¶m, dest->af, daddr, dport, flags, dest, 0); if (!cp) { if (ct) ip_vs_conn_put(ct); return NULL; } if (ct) { ip_vs_control_add(cp, ct); ip_vs_conn_put(ct); } ip_vs_conn_stats(cp, svc); /* return connection (will be used to handle outgoing packet) */ IP_VS_DBG_BUF(6, "New connection RS-initiated:%c c:%s:%u v:%s:%u " "d:%s:%u conn->flags:%X conn->refcnt:%d\n", ip_vs_fwd_tag(cp), IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->af, &cp->daddr), ntohs(cp->dport), cp->flags, refcount_read(&cp->refcnt)); LeaveFunction(12); return cp; } /* Handle outgoing packets which are considered requests initiated by * real servers, so that subsequent responses from external client can be * routed to the right real server. * Used also for outgoing responses in OPS mode. * * Connection management is handled by persistent-engine specific callback. */ static struct ip_vs_conn *__ip_vs_rs_conn_out(unsigned int hooknum, struct netns_ipvs *ipvs, int af, struct sk_buff *skb, const struct ip_vs_iphdr *iph) { struct ip_vs_dest *dest; struct ip_vs_conn *cp = NULL; __be16 _ports[2], *pptr; if (hooknum == NF_INET_LOCAL_IN) return NULL; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports); if (!pptr) return NULL; dest = ip_vs_find_real_service(ipvs, af, iph->protocol, &iph->saddr, pptr[0]); if (dest) { struct ip_vs_service *svc; struct ip_vs_pe *pe; svc = rcu_dereference(dest->svc); if (svc) { pe = rcu_dereference(svc->pe); if (pe && pe->conn_out) cp = pe->conn_out(svc, dest, skb, iph, pptr[0], pptr[1]); } } return cp; } /* Handle response packets: rewrite addresses and send away... */ static unsigned int handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph, unsigned int hooknum) { struct ip_vs_protocol *pp = pd->pp; if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) goto after_nat; IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); if (skb_ensure_writable(skb, iph->len)) goto drop; /* mangle the packet */ if (pp->snat_handler && !SNAT_CALL(pp->snat_handler, skb, pp, cp, iph)) goto drop; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ipv6_hdr(skb)->saddr = cp->vaddr.in6; else #endif { ip_hdr(skb)->saddr = cp->vaddr.ip; ip_send_check(ip_hdr(skb)); } /* * nf_iterate does not expect change in the skb->dst->dev. * It looks like it is not fatal to enable this code for hooks * where our handlers are at the end of the chain list and * when all next handlers use skb->dst->dev and not outdev. * It will definitely route properly the inout NAT traffic * when multiple paths are used. */ /* For policy routing, packets originating from this * machine itself may be routed differently to packets * passing through. We want this packet to be routed as * if it came from this machine itself. So re-compute * the routing information. */ if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto drop; IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT"); after_nat: ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); LeaveFunction(11); return NF_ACCEPT; drop: ip_vs_conn_put(cp); kfree_skb(skb); LeaveFunction(11); return NF_STOLEN; } /* * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; struct sock *sk; EnterFunction(11); /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; sk = skb_to_full_sk(skb); /* Bad... Do not break raw sockets */ if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } if (unlikely(!skb_dst(skb))) return NF_ACCEPT; if (!ipvs->enable) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_out_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) return NF_ACCEPT; pp = pd->pp; /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET) #endif if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; ip_vs_fill_iph_skb(AF_INET, skb, false, &iph); } /* * Check if the packet belongs to an existing entry */ cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); /* Check for real-server-started requests */ if (atomic_read(&ipvs->conn_out_counter)) { /* Currently only for UDP: * connection oriented protocols typically use * ephemeral ports for outgoing connections, so * related incoming responses would not match any VS */ if (pp->protocol == IPPROTO_UDP) { cp = __ip_vs_rs_conn_out(hooknum, ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); } } if (sysctl_nat_icmp_send(ipvs) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { __be16 _ports[2], *pptr; pptr = frag_safe_skb_hp(skb, iph.len, sizeof(_ports), _ports); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr, pptr[0])) { /* * Notify the real server: there is no * existing entry if it is not RST * packet or not TCP packet. */ if ((iph.protocol != IPPROTO_TCP && iph.protocol != IPPROTO_SCTP) || ((iph.protocol == IPPROTO_TCP && !is_tcp_reset(skb, iph.len)) || (iph.protocol == IPPROTO_SCTP && !is_sctp_abort(skb, iph.len)))) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (!skb->dev) skb->dev = ipvs->net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); return NF_DROP; } } } IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; } /* * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, * used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); } /* * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_local_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 /* * It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain, * used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); } /* * It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT. * Check if packet is reply for established ip_vs_conn. */ static unsigned int ip_vs_local_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); } #endif static unsigned int ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_protocol *pp = pd->pp; if (!iph->fragoffs) { /* No (second) fragments need to enter here, as nf_defrag_ipv6 * replayed fragment zero will already have created the cp */ /* Schedule and create new connection entry into cpp */ if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph)) return 0; } if (unlikely(!*cpp)) { /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); /* Fragment couldn't be mapped to a conn entry */ if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); *verdict = NF_ACCEPT; return 0; } return 1; } /* Check the UDP tunnel and return its header length */ static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct udphdr _udph, *udph; struct ip_vs_dest *dest; udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (!udph) goto unk; offset += sizeof(struct udphdr); dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { struct guehdr _gueh, *gueh; gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh); if (!gueh) goto unk; if (gueh->control != 0 || gueh->version != 0) goto unk; /* Later we can support also IPPROTO_IPV6 */ if (gueh->proto_ctype != IPPROTO_IPIP) goto unk; *proto = gueh->proto_ctype; return sizeof(struct udphdr) + sizeof(struct guehdr) + (gueh->hlen << 2); } unk: return 0; } /* Check the GRE tunnel and return its header length */ static int ipvs_gre_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, unsigned int offset, __u16 af, const union nf_inet_addr *daddr, __u8 *proto) { struct gre_base_hdr _greh, *greh; struct ip_vs_dest *dest; greh = skb_header_pointer(skb, offset, sizeof(_greh), &_greh); if (!greh) goto unk; dest = ip_vs_find_tunnel(ipvs, af, daddr, 0); if (!dest) goto unk; if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GRE) { __be16 type; /* Only support version 0 and C (csum) */ if ((greh->flags & ~GRE_CSUM) != 0) goto unk; type = greh->protocol; /* Later we can support also IPPROTO_IPV6 */ if (type != htons(ETH_P_IP)) goto unk; *proto = IPPROTO_IPIP; return gre_calc_hlen(gre_flags_to_tnl_flags(greh->flags)); } unk: return 0; } /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, * forward to the right destination host if relevant. * Currently handles error types - unreachable, quench, ttl exceeded. */ static int ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } iph = ip_hdr(skb); offset = ihl = iph->ihl * 4; ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n", ic->type, ntohs(icmp_id(ic)), &iph->saddr, &iph->daddr); /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if ((ic->type != ICMP_DEST_UNREACH) && (ic->type != ICMP_SOURCE_QUENCH) && (ic->type != ICMP_TIME_EXCEEDED)) { *related = 0; return NF_ACCEPT; } /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; if (cih->protocol == IPPROTO_IPIP) { struct ip_vs_dest *dest; if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; /* Error for our IPIP must arrive at LOCAL_IN */ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) return NF_ACCEPT; dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0); /* Only for known tunnel */ if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; offset += cih->ihl * 4; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ cih->protocol == IPPROTO_GRE) && /* Can be GRE encap */ /* Error for our tunnel must arrive at LOCAL_IN */ (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { __u8 iproto; int ulen; /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; offset2 = offset + cih->ihl * 4; if (cih->protocol == IPPROTO_UDP) { ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "UDP"; } else { ulen = ipvs_gre_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); outer_proto = "GRE"; } if (ulen > 0) { /* Skip IP and UDP/GRE tunnel headers */ offset = offset2 + ulen; /* Now we should be at the original IP header */ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih && cih->version == 4 && cih->ihl >= 5 && iproto == IPPROTO_IPIP) tunnel = true; else return NF_ACCEPT; } } pd = ip_vs_proto_data_get(ipvs, cih->protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && pp->dont_defrag)) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking incoming ICMP for"); offset2 = offset; ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !tunnel, &ciph); offset = ciph.len; /* The embedded headers contain source and dest in reverse order. * For IPIP/UDP/GRE tunnel this is error for request, not for reply. */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET, skb, &ciph); if (!cp) { int v; if (tunnel || !sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } verdict = NF_DROP; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { /* Failed checksum! */ IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n", &iph->saddr); goto out; } if (tunnel) { __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; /* Update the MTU */ if (ic->type == ICMP_DEST_UNREACH && ic->code == ICMP_FRAG_NEEDED) { struct ip_vs_dest *dest = cp->dest; u32 mtu = ntohs(ic->un.frag.mtu); __be16 frag_off = cih->frag_off; /* Strip outer IP and ICMP, go to IPIP/UDP/GRE header */ if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL) goto ignore_tunnel; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n", outer_proto, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); ipv4_update_pmtu(skb, ipvs->net, mtu, 0, 0); /* Client uses PMTUD? */ if (!(frag_off & htons(IP_DF))) goto ignore_tunnel; /* Prefer the resulting PMTU */ if (dest) { struct ip_vs_dest_dst *dest_dst; dest_dst = rcu_dereference(dest->dest_dst); if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } if (mtu > 68 + sizeof(struct iphdr)) mtu -= sizeof(struct iphdr); info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of * original request. */ if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, type, code, ntohl(info)); icmp_send(skb, type, code, info); /* ICMP can be shorter but anyways, account it */ ip_vs_out_stats(cp, skb); ignore_tunnel: consume_skb(skb); verdict = NF_STOLEN; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol || IPPROTO_SCTP == cih->protocol) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #ifdef CONFIG_IP_VS_IPV6 static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, unsigned int hooknum, struct ip_vs_iphdr *iph) { struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, verdict; bool new_cp = false; *related = 1; ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph); if (ic == NULL) return NF_DROP; /* * Work through seeing if this is for us. * These checks are supposed to be in an order that means easy * things are checked first to speed up processing.... however * this means that some packets will manage to get a long way * down this stack and then be rejected, but that's life. */ if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) { *related = 0; return NF_ACCEPT; } /* Fragment header that is before ICMP header tells us that: * it's not an error message since they can't be fragmented. */ if (iph->flags & IP6_FH_F_FRAG) return NF_DROP; IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n", ic->icmp6_type, ntohs(icmpv6_id(ic)), &iph->saddr, &iph->daddr); offset = iph->len + sizeof(_icmph); if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph)) return NF_ACCEPT; pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; /* Cannot handle fragmented embedded protocol */ if (ciph.fragoffs) return NF_ACCEPT; IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, "Checking incoming ICMPv6 for"); /* The embedded headers contain source and dest in reverse order * if not from localhost */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, AF_INET6, skb, &ciph); if (!cp) { int v; if (!sysctl_schedule_icmp(ipvs)) return NF_ACCEPT; if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph)) return v; new_cp = true; } /* VS/TUN, VS/DR and LOCALNODE just let it go */ if ((hooknum == NF_INET_LOCAL_OUT) && (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { verdict = NF_ACCEPT; goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); /* Need to mangle contained IPv6 header in ICMPv6 packet */ offset = ciph.len; if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || IPPROTO_SCTP == ciph.protocol) offset += 2 * sizeof(__u16); /* Also mangle ports */ verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); out: if (likely(!new_cp)) __ip_vs_conn_put(cp); else ip_vs_conn_put(cp); return verdict; } #endif /* * Check if it's for virtual services, look it up, * and send it on its way... */ static unsigned int ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; struct sock *sk; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) return NF_ACCEPT; /* * Big tappo: * - remote client: only PACKET_HOST * - route: used for struct net when skb->dev is unset */ if (unlikely((skb->pkt_type != PACKET_HOST && hooknum != NF_INET_LOCAL_OUT) || !skb_dst(skb))) { ip_vs_fill_iph_skb(af, skb, false, &iph); IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" " ignored in hook %u\n", skb->pkt_type, iph.protocol, IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ sk = skb_to_full_sk(skb); if (unlikely(sk && hooknum == NF_INET_LOCAL_OUT && af == AF_INET)) { if (sk->sk_family == PF_INET && inet_sk(sk)->nodefrag) return NF_ACCEPT; } #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; int verdict = ip_vs_in_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) return verdict; } } else #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; int verdict = ip_vs_in_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } /* Protocol supported? */ pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) { /* The only way we'll see this packet again is if it's * encapsulated, so mark it with ipvs_property=1 so we * skip it if we're ignoring tunneled packets */ if (sysctl_ignore_tunneled(ipvs)) skb->ipvs_property = 1; return NF_ACCEPT; } pp = pd->pp; /* * Check if the packet belongs to an existing connection entry */ cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (conn_reuse_mode && is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { /* Do not reschedule controlling connection * that uses conntrack while it is still * referenced by controlled connection(s). */ resched = !old_ct; } } if (resched) { if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } } /* Check the server status */ if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ if (sysctl_expire_nodest_conn(ipvs)) { bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!old_ct) cp->flags &= ~IP_VS_CONN_F_NFCT; ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); if (old_ct) return NF_DROP; cp = NULL; } else { __ip_vs_conn_put(cp); return NF_DROP; } } if (unlikely(!cp)) { int v; if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) return v; } IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); ip_vs_in_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ else { IP_VS_DBG_RL("warning: packet_xmit is null"); ret = NF_ACCEPT; } /* Increase its packet counter and check if it is needed * to be synchronized * * Sync connection if it is about to close to * encorage the standby servers to update the connections timeout * * For ONE_PKT let ip_vs_sync_conn() do the filter work. */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) pkts = sysctl_sync_threshold(ipvs); else pkts = atomic_inc_return(&cp->in_pkts); if (ipvs->sync_state & IP_VS_STATE_MASTER) ip_vs_sync_conn(ipvs, cp, pkts); else if ((cp->flags & IP_VS_CONN_F_ONE_PACKET) && cp->control) /* increment is done inside ip_vs_sync_conn too */ atomic_inc(&cp->control->in_pkts); ip_vs_conn_put(cp); return ret; } /* * AF_INET handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ static unsigned int ip_vs_remote_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); } /* * AF_INET handler in NF_INET_LOCAL_OUT chain * Schedule and forward packets from local clients */ static unsigned int ip_vs_local_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 /* * AF_INET6 handler in NF_INET_LOCAL_IN chain * Schedule and forward packets from remote clients */ static unsigned int ip_vs_remote_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); } /* * AF_INET6 handler in NF_INET_LOCAL_OUT chain * Schedule and forward packets from local clients */ static unsigned int ip_vs_local_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); } #endif /* * It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP * related packets destined for 0.0.0.0/0. * When fwmark-based virtual service is used, such as transparent * cache cluster, TCP packets can be marked and routed to ip_vs_in, * but ICMP destined for 0.0.0.0/0 cannot not be easily marked and * sent to ip_vs_in_icmp. So, catch them at the NF_INET_FORWARD chain * and send them to ip_vs_in_icmp. */ static unsigned int ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; struct netns_ipvs *ipvs = net_ipvs(state->net); if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp(ipvs, skb, &r, state->hook); } #ifdef CONFIG_IP_VS_IPV6 static unsigned int ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; struct netns_ipvs *ipvs = net_ipvs(state->net); struct ip_vs_iphdr iphdr; ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) return NF_ACCEPT; /* ipvs enabled in this netns ? */ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); } #endif static const struct nf_hook_ops ip_vs_ops4[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_remote_request4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_local_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_local_request4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply4, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #ifdef CONFIG_IP_VS_IPV6 static const struct nf_hook_ops ip_vs_ops6[] = { /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be * applied to IPVS. */ { .hook = ip_vs_remote_request6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { .hook = ip_vs_local_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { .hook = ip_vs_local_request6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ { .hook = ip_vs_forward_icmp_v6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 99, }, /* After packet filtering, change source only for VS/NAT */ { .hook = ip_vs_reply6, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = 100, }, }; #endif int ip_vs_register_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; int ret = 0; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return -EINVAL; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (!(ipvs->hooks_afmask & afmask)) { ret = nf_register_net_hooks(ipvs->net, ops, count); if (ret >= 0) ipvs->hooks_afmask |= afmask; } return ret; } void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af) { const struct nf_hook_ops *ops; unsigned int count; unsigned int afmask; if (af == AF_INET6) { #ifdef CONFIG_IP_VS_IPV6 ops = ip_vs_ops6; count = ARRAY_SIZE(ip_vs_ops6); afmask = 2; #else return; #endif } else { ops = ip_vs_ops4; count = ARRAY_SIZE(ip_vs_ops4); afmask = 1; } if (ipvs->hooks_afmask & afmask) { nf_unregister_net_hooks(ipvs->net, ops, count); ipvs->hooks_afmask &= ~afmask; } } /* * Initialize IP Virtual Server netns mem. */ static int __net_init __ip_vs_init(struct net *net) { struct netns_ipvs *ipvs; ipvs = net_generic(net, ip_vs_net_id); if (ipvs == NULL) return -ENOMEM; /* Hold the beast until a service is registered */ ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; if (ip_vs_estimator_net_init(ipvs) < 0) goto estimator_fail; if (ip_vs_control_net_init(ipvs) < 0) goto control_fail; if (ip_vs_protocol_net_init(ipvs) < 0) goto protocol_fail; if (ip_vs_app_net_init(ipvs) < 0) goto app_fail; if (ip_vs_conn_net_init(ipvs) < 0) goto conn_fail; if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; return 0; /* * Error handling */ sync_fail: ip_vs_conn_net_cleanup(ipvs); conn_fail: ip_vs_app_net_cleanup(ipvs); app_fail: ip_vs_protocol_net_cleanup(ipvs); protocol_fail: ip_vs_control_net_cleanup(ipvs); control_fail: ip_vs_estimator_net_cleanup(ipvs); estimator_fail: net->ipvs = NULL; return -ENOMEM; } static void __net_exit __ip_vs_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; ip_vs_service_nets_cleanup(net_list); /* ip_vs_flush() with locks */ list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_conn_net_cleanup(ipvs); ip_vs_app_net_cleanup(ipvs); ip_vs_protocol_net_cleanup(ipvs); ip_vs_control_net_cleanup(ipvs); ip_vs_estimator_net_cleanup(ipvs); IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; } } static void __net_exit __ip_vs_dev_cleanup_batch(struct list_head *net_list) { struct netns_ipvs *ipvs; struct net *net; EnterFunction(2); list_for_each_entry(net, net_list, exit_list) { ipvs = net_ipvs(net); ip_vs_unregister_hooks(ipvs, AF_INET); ip_vs_unregister_hooks(ipvs, AF_INET6); ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); ip_vs_sync_net_cleanup(ipvs); } LeaveFunction(2); } static struct pernet_operations ipvs_core_ops = { .init = __ip_vs_init, .exit_batch = __ip_vs_cleanup_batch, .id = &ip_vs_net_id, .size = sizeof(struct netns_ipvs), }; static struct pernet_operations ipvs_core_dev_ops = { .exit_batch = __ip_vs_dev_cleanup_batch, }; /* * Initialize IP Virtual Server */ static int __init ip_vs_init(void) { int ret; ret = ip_vs_control_init(); if (ret < 0) { pr_err("can't setup control.\n"); goto exit; } ip_vs_protocol_init(); ret = ip_vs_conn_init(); if (ret < 0) { pr_err("can't setup connection table.\n"); goto cleanup_protocol; } ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ if (ret < 0) goto cleanup_conn; ret = register_pernet_device(&ipvs_core_dev_ops); if (ret < 0) goto cleanup_sub; ret = ip_vs_register_nl_ioctl(); if (ret < 0) { pr_err("can't register netlink/ioctl.\n"); goto cleanup_dev; } pr_info("ipvs loaded.\n"); return ret; cleanup_dev: unregister_pernet_device(&ipvs_core_dev_ops); cleanup_sub: unregister_pernet_subsys(&ipvs_core_ops); cleanup_conn: ip_vs_conn_cleanup(); cleanup_protocol: ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); exit: return ret; } static void __exit ip_vs_cleanup(void) { ip_vs_unregister_nl_ioctl(); unregister_pernet_device(&ipvs_core_dev_ops); unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_conn_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); pr_info("ipvs unloaded.\n"); } module_init(ip_vs_init); module_exit(ip_vs_cleanup); MODULE_LICENSE("GPL"); |
| 5 1 4 4 14 1 13 2 8 3 8 8 8 2 6 4 4 4 4 6 2 4 4 3 1 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * TCPv4 GSO/GRO support */ #include <linux/indirect_call_wrapper.h> #include <linux/skbuff.h> #include <net/tcp.h> #include <net/protocol.h> static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, unsigned int seq, unsigned int mss) { while (skb) { if (before(ts_seq, seq + mss)) { skb_shinfo(skb)->tx_flags |= SKBTX_SW_TSTAMP; skb_shinfo(skb)->tskey = ts_seq; return; } skb = skb->next; seq += mss; } } static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, netdev_features_t features) { if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) return ERR_PTR(-EINVAL); if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); /* Set up checksum pseudo header, usually expect stack to * have done this already. */ th->check = 0; skb->ip_summed = CHECKSUM_PARTIAL; __tcp_v4_send_check(skb, iph->saddr, iph->daddr); } return tcp_gso_segment(skb, features); } struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int sum_truesize = 0; struct tcphdr *th; unsigned int thlen; unsigned int seq; __be32 delta; unsigned int oldlen; unsigned int mss; struct sk_buff *gso_skb = skb; __sum16 newcheck; bool ooo_okay, copy_destructor; th = tcp_hdr(skb); thlen = th->doff * 4; if (thlen < sizeof(*th)) goto out; if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) goto out; if (!pskb_may_pull(skb, thlen)) goto out; oldlen = (u16)~skb->len; __skb_pull(skb, thlen); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss); segs = NULL; goto out; } copy_destructor = gso_skb->destructor == tcp_wfree; ooo_okay = gso_skb->ooo_okay; /* All segments but the first should have ooo_okay cleared */ skb->ooo_okay = 0; segs = skb_segment(skb, features); if (IS_ERR(segs)) goto out; /* Only first segment might have ooo_okay set */ segs->ooo_okay = ooo_okay; /* GSO partial and frag_list segmentation only requires splitting * the frame into an MSS multiple and possibly a remainder, both * cases return a GSO skb. So update the mss now. */ if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; delta = htonl(oldlen + (thlen + mss)); skb = segs; th = tcp_hdr(skb); seq = ntohl(th->seq); if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP)) tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss); newcheck = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); while (skb->next) { th->fin = th->psh = 0; th->check = newcheck; if (skb->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(skb, ~th->check); else th->check = gso_make_checksum(skb, ~th->check); seq += mss; if (copy_destructor) { skb->destructor = gso_skb->destructor; skb->sk = gso_skb->sk; sum_truesize += skb->truesize; } skb = skb->next; th = tcp_hdr(skb); th->seq = htonl(seq); th->cwr = 0; } /* Following permits TCP Small Queues to work well with GSO : * The callback to TCP stack will be called at the time last frag * is freed at TX completion, and not right now when gso_skb * is freed by GSO engine */ if (copy_destructor) { int delta; swap(gso_skb->sk, skb->sk); swap(gso_skb->destructor, skb->destructor); sum_truesize += skb->truesize; delta = sum_truesize - gso_skb->truesize; /* In some pathological cases, delta can be negative. * We need to either use refcount_add() or refcount_sub_and_test() */ if (likely(delta >= 0)) refcount_add(delta, &skb->sk->sk_wmem_alloc); else WARN_ON_ONCE(refcount_sub_and_test(-delta, &skb->sk->sk_wmem_alloc)); } delta = htonl(oldlen + (skb_tail_pointer(skb) - skb_transport_header(skb)) + skb->data_len); th->check = ~csum_fold((__force __wsum)((__force u32)th->check + (__force u32)delta)); if (skb->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(skb, ~th->check); else th->check = gso_make_checksum(skb, ~th->check); out: return segs; } struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct sk_buff *p; struct tcphdr *th; struct tcphdr *th2; unsigned int len; unsigned int thlen; __be32 flags; unsigned int mss = 1; unsigned int hlen; unsigned int off; int flush = 1; int i; off = skb_gro_offset(skb); hlen = off + sizeof(*th); th = skb_gro_header_fast(skb, off); if (skb_gro_header_hard(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) goto out; } thlen = th->doff * 4; if (thlen < sizeof(*th)) goto out; hlen = off + thlen; if (skb_gro_header_hard(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) goto out; } skb_gro_pull(skb, thlen); len = skb_gro_len(skb); flags = tcp_flag_word(th); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; th2 = tcp_hdr(p); if (*(u32 *)&th->source ^ *(u32 *)&th2->source) { NAPI_GRO_CB(p)->same_flow = 0; continue; } goto found; } p = NULL; goto out_check_final; found: /* Include the IP ID check below from the inner most IP hdr */ flush = NAPI_GRO_CB(p)->flush; flush |= (__force int)(flags & TCP_FLAG_CWR); flush |= (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH)); flush |= (__force int)(th->ack_seq ^ th2->ack_seq); for (i = sizeof(*th); i < thlen; i += 4) flush |= *(u32 *)((u8 *)th + i) ^ *(u32 *)((u8 *)th2 + i); /* When we receive our second frame we can made a decision on if we * continue this flow as an atomic flow with a fixed ID or if we use * an incrementing ID. */ if (NAPI_GRO_CB(p)->flush_id != 1 || NAPI_GRO_CB(p)->count != 1 || !NAPI_GRO_CB(p)->is_atomic) flush |= NAPI_GRO_CB(p)->flush_id; else NAPI_GRO_CB(p)->is_atomic = false; mss = skb_shinfo(p)->gso_size; flush |= (len - 1) >= mss; flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq); #ifdef CONFIG_TLS_DEVICE flush |= p->decrypted ^ skb->decrypted; #endif if (flush || skb_gro_receive(p, skb)) { mss = 1; goto out_check_final; } tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH); out_check_final: flush = len < mss; flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN)); if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) pp = p; out: NAPI_GRO_CB(skb)->flush |= (flush != 0); return pp; } int tcp_gro_complete(struct sk_buff *skb) { struct tcphdr *th = tcp_hdr(skb); skb->csum_start = (unsigned char *)th - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; if (th->cwr) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; if (skb->encapsulation) skb->inner_transport_header = skb->transport_header; return 0; } EXPORT_SYMBOL(tcp_gro_complete); INDIRECT_CALLABLE_SCOPE struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb) { /* Don't bother verifying checksum if we're going to flush anyway. */ if (!NAPI_GRO_CB(skb)->flush && skb_gro_checksum_validate(skb, IPPROTO_TCP, inet_gro_compute_pseudo)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } return tcp_gro_receive(head, skb); } INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; if (NAPI_GRO_CB(skb)->is_atomic) skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; return tcp_gro_complete(skb); } static const struct net_offload tcpv4_offload = { .callbacks = { .gso_segment = tcp4_gso_segment, .gro_receive = tcp4_gro_receive, .gro_complete = tcp4_gro_complete, }, }; int __init tcpv4_offload_init(void) { return inet_add_offload(&tcpv4_offload, IPPROTO_TCP); } |
| 1160 1165 1159 1164 864 866 3544 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* CPU control. * (C) 2001, 2002, 2003, 2004 Rusty Russell * * This code is licenced under the GPL. */ #include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> #include <linux/stop_machine.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> #include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS #include <trace/events/cpuhp.h> #include "smpboot.h" /** * struct cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state * @fail: Current CPU hotplug callback state * @thread: Pointer to the hotplug thread * @should_run: Thread should execute * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector * @cpu: CPU number * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; bool rollback; bool single; bool bringup; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; struct completion done_up; struct completion done_down; #endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; #ifdef CONFIG_SMP cpumask_t cpus_booted_once_mask; #endif #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else static inline void cpuhp_lock_acquire(bool bringup) { } static inline void cpuhp_lock_release(bool bringup) { } #endif /** * struct cpuhp_step - Hotplug state machine step * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step * @cant_stop: Bringup/teardown can't be stopped at this step * @multi_instance: State has multiple instances which get added afterwards */ struct cpuhp_step { const char *name; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } startup; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } teardown; /* private: */ struct hlist_head list; /* public: */ bool cant_stop; bool multi_instance; }; static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_hp_states[]; static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { return cpuhp_hp_states + state; } static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step) { return bringup ? !step->startup.single : !step->teardown.single; } /** * cpuhp_invoke_callback - Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked * @node: For multi-instance, do a single entry callback for install/remove * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. * * Return: %0 on success or a negative errno code */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node, struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); int ret, cnt; if (st->fail == state) { st->fail = CPUHP_INVALID; return -EAGAIN; } if (cpuhp_step_empty(bringup, step)) { WARN_ON_ONCE(1); return 0; } if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; trace_cpuhp_enter(cpu, st->target, state, cb); ret = cb(cpu); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } cbm = bringup ? step->startup.multi : step->teardown.multi; /* Single invocation for instance add/remove */ if (node) { WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { if (lastp && node == *lastp) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); if (ret) { if (!lastp) goto err; *lastp = node; return ret; } cnt++; } if (lastp) *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ cbm = !bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return ret; hlist_for_each(node, &step->list) { if (!cnt--) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); /* * Rollback must not fail, */ WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { /* * The extra check for CPUHP_TEARDOWN_CPU is only for documentation * purposes as that state is handled explicitly in cpu_down. */ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; wait_for_completion(done); } static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; complete(done); } /* * The former STARTING/DYING states, ran with IRQs disabled and must not fail. */ static bool cpuhp_is_atomic_state(enum cpuhp_state state) { return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } /* * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_lock); int cpus_read_trylock(void) { return percpu_down_read_trylock(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_trylock); void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_unlock); void cpus_write_lock(void) { percpu_down_write(&cpu_hotplug_lock); } void cpus_write_unlock(void) { percpu_up_write(&cpu_hotplug_lock); } void lockdep_assert_cpus_held(void) { /* * We can't have hotplug operations before userspace starts running, * and some init codepaths will knowingly not take the hotplug lock. * This is all valid, so mute lockdep until it makes sense to report * unheld locks. */ if (system_state < SYSTEM_RUNNING) return; percpu_rwsem_assert_held(&cpu_hotplug_lock); } #ifdef CONFIG_LOCKDEP int lockdep_is_cpus_held(void) { return percpu_rwsem_is_held(&cpu_hotplug_lock); } #endif static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_); } static void lockdep_release_cpus_lock(void) { rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the * hotplug path before performing hotplug operations. So acquiring that lock * guarantees mutual exclusion from any currently running hotplug operations. */ void cpu_hotplug_disable(void) { cpu_maps_update_begin(); cpu_hotplug_disabled++; cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_disable); static void __cpu_hotplug_enable(void) { if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n")) return; cpu_hotplug_disabled--; } void cpu_hotplug_enable(void) { cpu_maps_update_begin(); __cpu_hotplug_enable(); cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #else static void lockdep_acquire_cpus_lock(void) { } static void lockdep_release_cpus_lock(void) { } #endif /* CONFIG_HOTPLUG_CPU */ /* * Architectures that need SMT-specific errata handling during SMT hotplug * should override this. */ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; void __init cpu_smt_disable(bool force) { if (!cpu_smt_possible()) return; if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ void __init cpu_smt_check_topology(void) { if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { if (cpu_smt_control == CPU_SMT_ENABLED) return true; if (topology_is_primary_thread(cpu)) return true; /* * On x86 it's required to boot all logical CPUs at least once so * that the init code can get a chance to set CR4.MCE on each * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } /* Returns true if SMT is not supported of forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; st->rollback = false; st->last = NULL; st->target = target; st->single = false; st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); return prev_state; } static inline void cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) { bool bringup = !st->bringup; st->target = prev_state; /* * Already rolling back. No need invert the bringup value or to change * the current state. */ if (st->rollback) return; st->rollback = true; /* * If we have st->last we need to undo partial multi_instance of this * state first. Otherwise start undo at the previous state. */ if (!st->last) { if (st->bringup) st->state--; else st->state++; } st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) { if (!st->single && st->state == st->target) return; st->result = 0; /* * Make sure the above stores are visible before should_run becomes * true. Paired with the mb() above in cpuhp_thread_fun() */ smp_mb(); st->should_run = true; wake_up_process(st->thread); wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } return ret; } static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the * cpu_smt_allowed() check will now return false if this is not the * primary sibling. */ if (!cpu_smt_allowed(cpu)) return -ECANCELED; if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); } static int bringup_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); int ret; /* * Reset stale stack state from the last time this CPU was online. */ scs_task_reset(idle); kasan_unpoison_task_stack(idle); /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. */ irq_lock_sparse(); /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); irq_unlock_sparse(); if (ret) return ret; return bringup_wait_for_ap(cpu); } static int finish_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); struct mm_struct *mm = idle->active_mm; /* * idle_task_exit() will have switched to &init_mm, now * clean up any remaining active_mm state. */ if (mm != &init_mm) idle->active_mm = &init_mm; mmdrop(mm); return 0; } /* * Hotplug state machine related functions */ /* * Get the next state to run. Empty ones will be skipped. Returns true if a * state must be run. * * st->state will be modified ahead of time, to match state_to_run, as if it * has already ran. */ static bool cpuhp_next_state(bool bringup, enum cpuhp_state *state_to_run, struct cpuhp_cpu_state *st, enum cpuhp_state target) { do { if (bringup) { if (st->state >= target) return false; *state_to_run = ++st->state; } else { if (st->state <= target) return false; *state_to_run = st->state--; } if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run))) break; } while (true); return true; } static int __cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target, bool nofail) { enum cpuhp_state state; int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { int err; err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); if (!err) continue; if (nofail) { pr_warn("CPU %u %s state %s (%d) failed (%d)\n", cpu, bringup ? "UP" : "DOWN", cpuhp_get_step(st->state)->name, st->state, err); ret = -1; } else { ret = err; break; } } return ret; } static inline int cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); } static inline void cpuhp_invoke_callback_range_nofail(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) { if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; /* * When CPU hotplug is disabled, then taking the CPU down is not * possible because takedown_cpu() and the architecture and * subsystem specific mechanisms are not available. So the CPU * which would be completely unplugged again needs to stay around * in the current state. */ return st->state <= CPUHP_BRINGUP_CPU; } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(true, cpu, st, target); if (ret) { pr_debug("CPU UP failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); } return ret; } /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); init_completion(&st->done_up); init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); return st->should_run; } /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. * * Each invocation of this function by the smpboot thread does a single AP * state callback. * * It has 3 modes of operation: * - single: runs st->cb_state * - up: runs ++st->state, while st->state < st->target * - down: runs st->state--, while st->state > st->target * * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); bool bringup = st->bringup; enum cpuhp_state state; if (WARN_ON_ONCE(!st->should_run)) return; /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); /* * The BP holds the hotplug lock, but we're now running on the AP, * ensure that anybody asserting the lock is held, will actually find * it so. */ lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; st->should_run = false; } else { st->should_run = cpuhp_next_state(bringup, &state, st, st->target); if (!st->should_run) goto end; } WARN_ON_ONCE(!cpuhp_is_ap_state(state)); if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); local_irq_enable(); /* * STARTING/DYING must not fail! */ WARN_ON_ONCE(st->result); } else { st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); } if (st->result) { /* * If we fail on a rollback, we're up a creek without no * paddle, no way forward, no way back. We loose, thanks for * playing. */ WARN_ON_ONCE(st->rollback); st->should_run = false; } end: cpuhp_lock_release(bringup); lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; if (!cpu_online(cpu)) return 0; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->rollback = false; st->last = NULL; st->node = node; st->bringup = bringup; st->cb_state = state; st->single = true; __cpuhp_kick_ap(st); /* * If we failed and did a partial, do a rollback. */ if ((ret = st->result) && st->last) { st->rollback = true; st->bringup = !bringup; __cpuhp_kick_ap(st); } /* * Clean up the leftovers so the next hotplug operation wont use stale * data. */ st->node = st->last = NULL; return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state prev_state = st->state; int ret; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; } static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, .create = &cpuhp_create, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; void __init cpuhp_threads_init(void) { BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } /* * * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock * protected region. * * The operation is still serialized against concurrent CPU hotplug via * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ * serialized against other hotplug related activity like adding or * removing of state callbacks and state instances, which invoke either the * startup or the teardown callback of the affected state. * * This is required for subsystems which are unfixable vs. CPU hotplug and * evade lock inversion problems by scheduling work which has to be * completed _before_ cpu_up()/_cpu_down() returns. * * Don't even think about adding anything to this for any new code or even * drivers. It's only purpose is to keep existing lock order trainwrecks * working. * * For cpu_down() there might be valid reasons to finish cleanups which are * not required to be done under cpu_hotplug_lock, but that's a different * story and would be not invoked via this. */ static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) { /* * cpusets delegate hotplug operations to a worker to "solve" the * lock order problems. Wait for the worker, but only if tasks are * _not_ frozen (suspend, hibernate) as that would wait forever. * * The wait is required because otherwise the hotplug operation * returns with inconsistent state, which could even be observed in * user space when a new CPU is brought up. The CPU plug uevent * would be delivered and user space reacting on it would fail to * move tasks to the newly plugged CPU up to the point where the * work has finished because up to that point the newly plugged CPU * is not assignable in cpusets/cgroups. On unplug that's not * necessarily a visible issue, but it is still inconsistent state, * which is the real problem which needs to be "fixed". This can't * prevent the transient state between scheduling the work and * returning from waiting for it. */ if (!tasks_frozen) cpuset_wait_for_hotplug(); } #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) #endif /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id * * This function walks all processes, finds a valid mm struct for each one and * then clears a corresponding bit in mm's cpumask. While this all sounds * trivial, there are various non-obvious corner cases, which this function * tries to solve in a safe manner. * * Also note that the function uses a somewhat relaxed locking scheme, so it may * be called only for an already offlined CPU. */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; /* * This function is called after the cpu is taken down and marked * offline, so its not like new tasks will ever get this cpu set in * their mm mask. -- Peter Zijlstra * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; /* * Main thread might exit, but other threads may still have * a valid mm. Find one. */ t = find_lock_task_mm(p); if (!t) continue; arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); } /* Take this CPU down. */ static int take_cpu_down(void *_param) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; /* * Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going * down, that the current state is CPUHP_TEARDOWN_CPU - 1. */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); /* * Invoke the former CPU_DYING callbacks. DYING must not fail! */ cpuhp_invoke_callback_range_nofail(false, cpu, st, target); /* Give up timekeeping duties */ tick_handover_do_timer(); /* Remove CPU from timer broadcasting */ tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; } static int takedown_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* Park the smpboot threads */ kthread_park(st->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. */ irq_lock_sparse(); /* * So now all preempt/rcu users must observe !cpu_active(). */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ kthread_unpark(st->thread); return err; } BUG_ON(cpu_online(cpu)); /* * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. */ wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); tick_cleanup_dead_cpu(cpu); rcutree_migrate_callbacks(cpu); return 0; } static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); rcu_report_dead(smp_processor_id()); st->state = CPUHP_AP_IDLE_DEAD; /* * We cannot call complete after rcu_report_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), cpuhp_complete_idle_dead, st, 0); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(false, cpu, st, target); if (ret) { pr_debug("CPU DOWN failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, prev_state)); } return ret; } /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; if (num_online_cpus() == 1) return -EBUSY; if (!cpu_present(cpu)) return -EINVAL; cpus_write_lock(); cpuhp_tasks_frozen = tasks_frozen; prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; /* * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); } } out: cpus_write_unlock(); /* * Do post unplug cleanup. This is still protected against * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); arch_smt_update(); cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { if (cpu_hotplug_disabled) return -EBUSY; return _cpu_down(cpu, 0, target); } static int cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } /** * cpu_device_down - Bring down a cpu device * @dev: Pointer to the cpu device to offline * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use remove_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_down(struct device *dev) { return cpu_down(dev->id, CPUHP_OFFLINE); } int remove_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_offline(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(remove_cpu); void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { unsigned int cpu; int error; cpu_maps_update_begin(); /* * Make certain the cpu I'm about to reboot on is online. * * This is inline to what migrate_to_reboot_cpu() already do. */ if (!cpu_online(primary_cpu)) primary_cpu = cpumask_first(cpu_online_mask); for_each_online_cpu(cpu) { if (cpu == primary_cpu) continue; error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (error) { pr_err("Failed to offline CPU%d - error=%d", cpu, error); break; } } /* * Ensure all but the reboot CPU are offline. */ BUG_ON(num_online_cpus() > 1); /* * Make sure the CPUs won't be enabled by someone else after this * point. Kexec will reboot to a new kernel shortly resetting * everything along the way. */ cpu_hotplug_disabled++; cpu_maps_update_done(); } #else #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started * * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); /* * STARTING must not fail! */ cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* * Called from the idle task. Wake up the controlling task which brings the * hotplug thread of the upcoming CPU up and then delegates the rest of the * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; /* * Unpart the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; int ret = 0; cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } /* * The caller of cpu_up() might have raced with another * caller. Nothing to do. */ if (st->state >= target) goto out; if (st->state == CPUHP_OFFLINE) { /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); goto out; } } cpuhp_tasks_frozen = tasks_frozen; cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; } /* * Try to reach the target state. We max out on the BP at * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); arch_smt_update(); cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } static int cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); #if defined(CONFIG_IA64) pr_err("please check additional_cpus= boot parameter\n"); #endif return -EINVAL; } err = try_online_node(cpu_to_node(cpu)); if (err) return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { err = -EBUSY; goto out; } if (!cpu_smt_allowed(cpu)) { err = -EPERM; goto out; } err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } /** * cpu_device_up - Bring up a cpu device * @dev: Pointer to the cpu device to online * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use add_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_up(struct device *dev) { return cpu_up(dev->id, CPUHP_ONLINE); } int add_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_online(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_cpu); /** * bringup_hibernate_cpu - Bring up the CPU that we hibernated on * @sleep_cpu: The cpu we hibernated on and should be brought up. * * On some architectures like arm64, we can hibernate on any CPU, but on * wake up the CPU we hibernated on might be offline as a side effect of * using maxcpus= for example. * * Return: %0 on success or a negative errno code */ int bringup_hibernate_cpu(unsigned int sleep_cpu) { int ret; if (!cpu_online(sleep_cpu)) { pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); ret = cpu_up(sleep_cpu, CPUHP_ONLINE); if (ret) { pr_err("Failed to bring hibernate-CPU up!\n"); return ret; } } return 0; } void bringup_nonboot_cpus(unsigned int setup_max_cpus) { unsigned int cpu; for_each_present_cpu(cpu) { if (num_online_cpus() >= setup_max_cpus) break; if (!cpu_online(cpu)) cpu_up(cpu, CPUHP_ONLINE); } } #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; int freeze_secondary_cpus(int primary) { int cpu, error = 0; cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) primary = housekeeping_any_cpu(HK_FLAG_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); } /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); for_each_online_cpu(cpu) { if (cpu == primary) continue; if (pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; } trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { pr_err("Error taking CPU%d down: %d\n", cpu, error); break; } } if (!error) BUG_ON(num_online_cpus() > 1); else pr_err("Non-boot CPUs are not disabled\n"); /* * Make sure the CPUs won't be enabled by someone else. We need to do * this even in case of failure as all freeze_secondary_cpus() users are * supposed to do thaw_secondary_cpus() on the failure path. */ cpu_hotplug_disabled++; cpu_maps_update_done(); return error; } void __weak arch_thaw_secondary_cpus_begin(void) { } void __weak arch_thaw_secondary_cpus_end(void) { } void thaw_secondary_cpus(void) { int cpu, error; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); __cpu_hotplug_enable(); if (cpumask_empty(frozen_cpus)) goto out; pr_info("Enabling non-boot CPUs ...\n"); arch_thaw_secondary_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); } arch_thaw_secondary_cpus_end(); cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; return 0; } core_initcall(alloc_frozen_cpus); /* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the * duration* of the execution of the callbacks. * Hence we need to prevent the freezer from racing with regular CPU hotplug. * * This synchronization is implemented by mutually excluding regular CPU * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ * Hibernate notifications. */ static int cpu_hotplug_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: cpu_hotplug_enable(); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int __init cpu_hotplug_pm_sync_init(void) { /* * cpu_hotplug_pm_callback has higher priority than x86 * bsp_pm_callback which depends on cpu_hotplug_pm_callback * to disable cpu hotplug to avoid cpu hotplug race. */ pm_notifier(cpu_hotplug_pm_callback, 0); return 0; } core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ int __boot_cpu_id; #endif /* CONFIG_SMP */ /* Boot processor state steps */ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_OFFLINE] = { .name = "offline", .startup.single = NULL, .teardown.single = NULL, }, #ifdef CONFIG_SMP [CPUHP_CREATE_THREADS]= { .name = "threads:prepare", .startup.single = smpboot_create_threads, .teardown.single = NULL, .cant_stop = true, }, [CPUHP_PERF_PREPARE] = { .name = "perf:prepare", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_RANDOM_PREPARE] = { .name = "random:prepare", .startup.single = random_prepare_cpu, .teardown.single = NULL, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, .teardown.single = NULL, }, [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", .startup.single = smpcfd_prepare_cpu, .teardown.single = smpcfd_dead_cpu, }, [CPUHP_RELAY_PREPARE] = { .name = "relay:prepare", .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SLAB_PREPARE] = { .name = "slab:prepare", .startup.single = slab_prepare_cpu, .teardown.single = slab_dead_cpu, }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, .teardown.single = rcutree_dead_cpu, }, /* * On the tear-down path, timers_dead_cpu() must be invoked * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, /* Kicks the plugged cpu into life */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", }, /* * Last state before CPU enters the idle loop to die. Transient state * for synchronization. */ [CPUHP_AP_OFFLINE] = { .name = "ap:offline", .cant_stop = true, }, /* First state is scheduler control. Interrupts are disabled */ [CPUHP_AP_SCHED_STARTING] = { .name = "sched:starting", .startup.single = sched_cpu_starting, .teardown.single = sched_cpu_dying, }, [CPUHP_AP_RCUTREE_DYING] = { .name = "RCU/tree:dying", .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, [CPUHP_AP_HRTIMERS_DYING] = { .name = "hrtimers:dying", .startup.single = NULL, .teardown.single = hrtimers_cpu_dying, }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { .name = "ap:online", }, /* * Handled on control processor until the plugged processor manages * this itself. */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup.single = NULL, .teardown.single = takedown_cpu, .cant_stop = true, }, [CPUHP_AP_SCHED_WAIT_EMPTY] = { .name = "sched:waitempty", .startup.single = NULL, .teardown.single = sched_cpu_wait_empty, }, /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", .startup.single = irq_affinity_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_AP_WATCHDOG_ONLINE] = { .name = "lockup_detector:online", .startup.single = lockup_detector_online_cpu, .teardown.single = lockup_detector_offline_cpu, }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, [CPUHP_AP_RANDOM_ONLINE] = { .name = "random:online", .startup.single = random_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, .teardown.single = rcutree_offline_cpu, }, #endif /* * The dynamically registered state space is here */ #ifdef CONFIG_SMP /* Last state is scheduler control setting the cpu active */ [CPUHP_AP_ACTIVE] = { .name = "sched:active", .startup.single = sched_cpu_activate, .teardown.single = sched_cpu_deactivate, }, #endif /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup.single = NULL, .teardown.single = NULL, }, }; /* Sanity check for callbacks */ static int cpuhp_cb_check(enum cpuhp_state state) { if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) return -EINVAL; return 0; } /* * Returns a free for dynamic slot assignment of the Online state. The states * are protected by the cpuhp_slot_states mutex and an empty slot is identified * by having no name assigned. */ static int cpuhp_reserve_state(enum cpuhp_state state) { enum cpuhp_state i, end; struct cpuhp_step *step; switch (state) { case CPUHP_AP_ONLINE_DYN: step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN; end = CPUHP_AP_ONLINE_DYN_END; break; case CPUHP_BP_PREPARE_DYN: step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; default: return -EINVAL; } for (i = state; i <= end; i++, step++) { if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); return -ENOSPC; } static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { /* (Un)Install the callbacks for further cpu hotplug operations */ struct cpuhp_step *sp; int ret = 0; /* * If name is NULL, then the state gets removed. * * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; state = ret; } sp = cpuhp_get_step(state); if (name && sp->name) return -EBUSY; sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); return ret; } static void *cpuhp_get_teardown_cb(enum cpuhp_state state) { return cpuhp_get_step(state)->teardown.single; } /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. */ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_step *sp = cpuhp_get_step(state); int ret; /* * If there's nothing to do, we done. * Relies on the union for multi_instance. */ if (cpuhp_step_empty(bringup, sp)) return 0; /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ #ifdef CONFIG_SMP if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; } /* * Called from __cpuhp_setup_state on a recoverable failure. * * Note: The teardown callbacks for rollback are not allowed to fail! */ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, struct hlist_node *node) { int cpu; /* Roll back the already executed steps on the other cpus */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpu >= failedcpu) break; /* Did we invoke the startup call on that cpu ? */ if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } } int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp; int cpu; int ret; lockdep_assert_cpus_held(); sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, node); if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); goto unlock; } } add_node: ret = 0; hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); return ret; } int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { int ret; cpus_read_lock(); ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @name: Name of the step * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state * @startup: startup callback function * @teardown: teardown callback function * @multi_instance: State is set up for multiple instances which get * added afterwards. * * The caller needs to hold cpus read locked while calling this function. * Return: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN; * 0 for all other states * On failure: proper (negative) error code */ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int cpu, ret = 0; bool dynstate; lockdep_assert_cpus_held(); if (cpuhp_cb_check(state) || !name) return -EINVAL; mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; } if (ret || !invoke || !startup) goto out; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, NULL); if (ret) { if (teardown) cpuhp_rollback_install(cpu, state, NULL); cpuhp_store_callbacks(state, NULL, NULL, NULL, false); goto out; } } out: mutex_unlock(&cpuhp_state_mutex); /* * If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN, * return the dynamically allocated state in case of success. */ if (!ret && dynstate) return state; return ret; } EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int ret; cpus_read_lock(); ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, teardown, multi_instance); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); if (!sp->multi_instance) return -EINVAL; cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", state); goto remove; } if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, NULL); } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); } EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) { cpus_read_lock(); __cpuhp_remove_state_cpuslocked(state, invoke); cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); #ifdef CONFIG_HOTPLUG_SMT static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = true; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = false; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; cpu_maps_update_begin(); for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; /* * As this needs to hold the cpu maps lock it's impossible * to call device_offline() because that ends up calling * cpu_down() which takes cpu maps lock. cpu maps lock * needs to be held as this might race against in kernel * abusers of the hotplug machinery (thermal management). * * So nothing would update device:offline state. That would * leave the sysfs entry stale and prevent onlining after * smt control has been changed to 'off' again. This is * called under the sysfs hotplug lock, so it is properly * serialized against the regular offline usage. */ cpuhp_offline_cpu_device(cpu); } if (!ret) cpu_smt_control = ctrlval; cpu_maps_update_done(); return ret; } int cpuhp_smt_enable(void) { int cpu, ret = 0; cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; /* See comment in cpuhp_smt_disable() */ cpuhp_online_cpu_device(cpu); } cpu_maps_update_done(); return ret; } #endif #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->state); } static DEVICE_ATTR_RO(state); static ssize_t target_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int target, ret; ret = kstrtoint(buf, 10, &target); if (ret) return ret; #ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) return -EINVAL; #else if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) return -EINVAL; #endif ret = lock_device_hotplug_sysfs(); if (ret) return ret; mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(target); ret = !sp->name || sp->cant_stop ? -EINVAL : 0; mutex_unlock(&cpuhp_state_mutex); if (ret) goto out; if (st->state < target) ret = cpu_up(dev->id, target); else if (st->state > target) ret = cpu_down(dev->id, target); else if (WARN_ON(st->target != target)) st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; } static ssize_t target_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->target); } static DEVICE_ATTR_RW(target); static ssize_t fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int fail, ret; ret = kstrtoint(buf, 10, &fail); if (ret) return ret; if (fail == CPUHP_INVALID) { st->fail = fail; return count; } if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) return -EINVAL; /* * Cannot fail STARTING/DYING callbacks. */ if (cpuhp_is_atomic_state(fail)) return -EINVAL; /* * DEAD callbacks cannot fail... * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter * triggering STARTING callbacks, a failure in this state would * hinder rollback. */ if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU) return -EINVAL; /* * Cannot fail anything that doesn't have callbacks. */ mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(fail); if (!sp->startup.single && !sp->teardown.single) ret = -EINVAL; mutex_unlock(&cpuhp_state_mutex); if (ret) return ret; st->fail = fail; return count; } static ssize_t fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->fail); } static DEVICE_ATTR_RW(fail); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, &dev_attr_fail.attr, NULL }; static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", NULL }; static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) { ssize_t cur, res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { cur = sprintf(buf, "%3d: %s\n", i, sp->name); buf += cur; res += cur; } } mutex_unlock(&cpuhp_state_mutex); return res; } static DEVICE_ATTR_RO(states); static struct attribute *cpuhp_cpu_root_attrs[] = { &dev_attr_states.attr, NULL }; static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", NULL }; #ifdef CONFIG_HOTPLUG_SMT static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ctrlval, ret; if (sysfs_streq(buf, "on")) ctrlval = CPU_SMT_ENABLED; else if (sysfs_streq(buf, "off")) ctrlval = CPU_SMT_DISABLED; else if (sysfs_streq(buf, "forceoff")) ctrlval = CPU_SMT_FORCE_DISABLED; else return -EINVAL; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; ret = lock_device_hotplug_sysfs(); if (ret) return ret; if (ctrlval != cpu_smt_control) { switch (ctrlval) { case CPU_SMT_ENABLED: ret = cpuhp_smt_enable(); break; case CPU_SMT_DISABLED: case CPU_SMT_FORCE_DISABLED: ret = cpuhp_smt_disable(ctrlval); break; } } unlock_device_hotplug(); return ret ? ret : count; } #else /* !CONFIG_HOTPLUG_SMT */ static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return -ENODEV; } #endif /* CONFIG_HOTPLUG_SMT */ static const char *smt_states[] = { [CPU_SMT_ENABLED] = "on", [CPU_SMT_DISABLED] = "off", [CPU_SMT_FORCE_DISABLED] = "forceoff", [CPU_SMT_NOT_SUPPORTED] = "notsupported", [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", }; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *state = smt_states[cpu_smt_control]; return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return __store_smt_control(dev, attr, buf, count); } static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); static struct attribute *cpuhp_smt_attrs[] = { &dev_attr_control.attr, &dev_attr_active.attr, NULL }; static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", NULL }; static int __init cpu_smt_sysfs_init(void) { return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); } static int __init cpuhp_sysfs_init(void) { int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_cpu_root_attr_group); if (ret) return ret; for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); if (!dev) continue; ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); if (ret) return ret; } return 0; } device_initcall(cpuhp_sysfs_init); #endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ /* cpu_bit_bitmap[0] is empty - so we can back into it */ #define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x)) #define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) #define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) #define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { MASK_DECLARE_8(0), MASK_DECLARE_8(8), MASK_DECLARE_8(16), MASK_DECLARE_8(24), #if BITS_PER_LONG > 32 MASK_DECLARE_8(32), MASK_DECLARE_8(40), MASK_DECLARE_8(48), MASK_DECLARE_8(56), #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE struct cpumask __cpu_possible_mask __read_mostly = {CPU_BITS_ALL}; #else struct cpumask __cpu_possible_mask __read_mostly; #endif EXPORT_SYMBOL(__cpu_possible_mask); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); struct cpumask __cpu_dying_mask __read_mostly; EXPORT_SYMBOL(__cpu_dying_mask); atomic_t __num_online_cpus __read_mostly; EXPORT_SYMBOL(__num_online_cpus); void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); } void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); } void init_cpu_online(const struct cpumask *src) { cpumask_copy(&__cpu_online_mask, src); } void set_cpu_online(unsigned int cpu, bool online) { /* * atomic_inc/dec() is required to handle the horrid abuse of this * function by the reboot and kexec code which invoke it from * IPI/NMI broadcasts when shutting down CPUs. Invocation from * regular CPU hotplug is properly serialized. * * Note, that the fact that __num_online_cpus is of type atomic_t * does not protect readers which are not serialized against * concurrent hotplug operations. */ if (online) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) atomic_inc(&__num_online_cpus); } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) atomic_dec(&__num_online_cpus); } } /* * Activate the first processor. */ void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); #ifdef CONFIG_SMP __boot_cpu_id = cpu; #endif } /* * Must be called _AFTER_ setting up the per_cpu areas */ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, CPU_MITIGATIONS_AUTO, CPU_MITIGATIONS_AUTO_NOSMT, }; static enum cpu_mitigations cpu_mitigations __ro_after_init = IS_ENABLED(CONFIG_CPU_MITIGATIONS) ? CPU_MITIGATIONS_AUTO : CPU_MITIGATIONS_OFF; static int __init mitigations_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) cpu_mitigations = CPU_MITIGATIONS_OFF; else if (!strcmp(arg, "auto")) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; else pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); return 0; } early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) { return cpu_mitigations == CPU_MITIGATIONS_OFF; } EXPORT_SYMBOL_GPL(cpu_mitigations_off); /* mitigations=auto,nosmt */ bool cpu_mitigations_auto_nosmt(void) { return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); |
| 170 170 145 11 12 12 12 123 121 55 12 12 12 11 2 12 1 2 194 3 196 3 165 29 312 309 112 112 200 315 6 6 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 | /* License: GPL */ #include <linux/mutex.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <linux/module.h> #include <net/sock.h> #include <linux/kernel.h> #include <linux/tcp.h> #include <linux/workqueue.h> #include <linux/nospec.h> #include <linux/cookie.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; DEFINE_COOKIE(sock_cookie); u64 __sock_gen_cookie(struct sock *sk) { while (1) { u64 res = atomic64_read(&sk->sk_cookie); if (res) return res; res = gen_cookie_next(&sock_cookie); atomic64_cmpxchg(&sk->sk_cookie, 0, res); } } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie) { u64 res; if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE) return 0; res = sock_gen_cookie(sk); if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1]) return -ESTALE; return 0; } EXPORT_SYMBOL_GPL(sock_diag_check_cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie) { u64 res = sock_gen_cookie(sk); cookie[0] = (u32)res; cookie[1] = (u32)(res >> 32); } EXPORT_SYMBOL_GPL(sock_diag_save_cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) { u32 mem[SK_MEMINFO_VARS]; sk_get_meminfo(sk, mem); return nla_put(skb, attrtype, sizeof(mem), &mem); } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; struct sk_filter *filter; struct nlattr *attr; unsigned int flen; int err = 0; if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (!filter) goto out; fprog = filter->prog->orig_prog; if (!fprog) goto out; flen = bpf_classic_proglen(fprog); attr = nla_reserve(skb, attrtype, flen); if (attr == NULL) { err = -EMSGSIZE; goto out; } memcpy(nla_data(attr), fprog->filter, flen); out: rcu_read_unlock(); return err; } EXPORT_SYMBOL(sock_diag_put_filterinfo); struct broadcast_sk { struct sock *sk; struct work_struct work; }; static size_t sock_diag_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct inet_diag_msg) + nla_total_size(sizeof(u8)) /* INET_DIAG_PROTOCOL */ + nla_total_size_64bit(sizeof(struct tcp_info))); /* INET_DIAG_INFO */ } static void sock_diag_broadcast_destroy_work(struct work_struct *work) { struct broadcast_sk *bsk = container_of(work, struct broadcast_sk, work); struct sock *sk = bsk->sk; const struct sock_diag_handler *hndl; struct sk_buff *skb; const enum sknetlink_groups group = sock_diag_destroy_group(sk); int err = -1; WARN_ON(group == SKNLGRP_NONE); skb = nlmsg_new(sock_diag_nlmsg_size(), GFP_KERNEL); if (!skb) goto out; mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[sk->sk_family]; if (hndl && hndl->get_info) err = hndl->get_info(skb, sk); mutex_unlock(&sock_diag_table_mutex); if (!err) nlmsg_multicast(sock_net(sk)->diag_nlsk, skb, 0, group, GFP_KERNEL); else kfree_skb(skb); out: sk_destruct(sk); kfree(bsk); } void sock_diag_broadcast_destroy(struct sock *sk) { /* Note, this function is often called from an interrupt context. */ struct broadcast_sk *bsk = kmalloc(sizeof(struct broadcast_sk), GFP_ATOMIC); if (!bsk) return sk_destruct(sk); bsk->sk = sk; INIT_WORK(&bsk->work, sock_diag_broadcast_destroy_work); queue_work(broadcast_wq, &bsk->work); } void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) { mutex_lock(&sock_diag_table_mutex); inet_rcv_compat = fn; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) { mutex_lock(&sock_diag_table_mutex); inet_rcv_compat = NULL; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); int sock_diag_register(const struct sock_diag_handler *hndl) { int err = 0; if (hndl->family >= AF_MAX) return -EINVAL; mutex_lock(&sock_diag_table_mutex); if (sock_diag_handlers[hndl->family]) err = -EBUSY; else WRITE_ONCE(sock_diag_handlers[hndl->family], hndl); mutex_unlock(&sock_diag_table_mutex); return err; } EXPORT_SYMBOL_GPL(sock_diag_register); void sock_diag_unregister(const struct sock_diag_handler *hnld) { int family = hnld->family; if (family >= AF_MAX) return; mutex_lock(&sock_diag_table_mutex); BUG_ON(sock_diag_handlers[family] != hnld); WRITE_ONCE(sock_diag_handlers[family], NULL); mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister); static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) { int err; struct sock_diag_req *req = nlmsg_data(nlh); const struct sock_diag_handler *hndl; if (nlmsg_len(nlh) < sizeof(*req)) return -EINVAL; if (req->sdiag_family >= AF_MAX) return -EINVAL; req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX); if (READ_ONCE(sock_diag_handlers[req->sdiag_family]) == NULL) sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; if (hndl == NULL) err = -ENOENT; else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY) err = hndl->dump(skb, nlh); else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy) err = hndl->destroy(skb, nlh); else err = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return err; } static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int ret; switch (nlh->nlmsg_type) { case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) sock_load_diag_module(AF_INET, 0); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) ret = inet_rcv_compat(skb, nlh); else ret = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return ret; case SOCK_DIAG_BY_FAMILY: case SOCK_DESTROY: return __sock_diag_cmd(skb, nlh); default: return -EINVAL; } } static DEFINE_MUTEX(sock_diag_mutex); static void sock_diag_rcv(struct sk_buff *skb) { mutex_lock(&sock_diag_mutex); netlink_rcv_skb(skb, &sock_diag_rcv_msg); mutex_unlock(&sock_diag_mutex); } static int sock_diag_bind(struct net *net, int group) { switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!READ_ONCE(sock_diag_handlers[AF_INET])) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!READ_ONCE(sock_diag_handlers[AF_INET6])) sock_load_diag_module(AF_INET6, 0); break; } return 0; } int sock_diag_destroy(struct sock *sk, int err) { if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!sk->sk_prot->diag_destroy) return -EOPNOTSUPP; return sk->sk_prot->diag_destroy(sk, err); } EXPORT_SYMBOL_GPL(sock_diag_destroy); static int __net_init diag_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .groups = SKNLGRP_MAX, .input = sock_diag_rcv, .bind = sock_diag_bind, .flags = NL_CFG_F_NONROOT_RECV, }; net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg); return net->diag_nlsk == NULL ? -ENOMEM : 0; } static void __net_exit diag_net_exit(struct net *net) { netlink_kernel_release(net->diag_nlsk); net->diag_nlsk = NULL; } static struct pernet_operations diag_net_ops = { .init = diag_net_init, .exit = diag_net_exit, }; static int __init sock_diag_init(void) { broadcast_wq = alloc_workqueue("sock_diag_events", 0, 0); BUG_ON(!broadcast_wq); return register_pernet_subsys(&diag_net_ops); } device_initcall(sock_diag_init); |
| 504 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 raw table, a port of the IPv4 raw table to IPv6 * * Copyright (C) 2003 Jozsef Kadlecsik <kadlec@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/slab.h> #define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)) static bool raw_before_defrag __read_mostly; MODULE_PARM_DESC(raw_before_defrag, "Enable raw table before defrag"); module_param(raw_before_defrag, bool, 0000); static const struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_RAW, }; static const struct xt_table packet_raw_before_defrag = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_RAW_BEFORE_DEFRAG, }; /* The work comes in here from netfilter.c. */ static unsigned int ip6table_raw_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip6t_do_table(skb, state, priv); } static struct nf_hook_ops *rawtable_ops __read_mostly; static int ip6table_raw_table_init(struct net *net) { struct ip6t_replace *repl; const struct xt_table *table = &packet_raw; int ret; if (raw_before_defrag) table = &packet_raw_before_defrag; repl = ip6t_alloc_initial_table(table); if (repl == NULL) return -ENOMEM; ret = ip6t_register_table(net, table, repl, rawtable_ops); kfree(repl); return ret; } static void __net_exit ip6table_raw_net_pre_exit(struct net *net) { ip6t_unregister_table_pre_exit(net, "raw"); } static void __net_exit ip6table_raw_net_exit(struct net *net) { ip6t_unregister_table_exit(net, "raw"); } static struct pernet_operations ip6table_raw_net_ops = { .pre_exit = ip6table_raw_net_pre_exit, .exit = ip6table_raw_net_exit, }; static int __init ip6table_raw_init(void) { const struct xt_table *table = &packet_raw; int ret; if (raw_before_defrag) { table = &packet_raw_before_defrag; pr_info("Enabling raw table before defrag\n"); } ret = xt_register_template(table, ip6table_raw_table_init); if (ret < 0) return ret; /* Register hooks */ rawtable_ops = xt_hook_ops_alloc(table, ip6table_raw_hook); if (IS_ERR(rawtable_ops)) { xt_unregister_template(table); return PTR_ERR(rawtable_ops); } ret = register_pernet_subsys(&ip6table_raw_net_ops); if (ret < 0) { kfree(rawtable_ops); xt_unregister_template(table); return ret; } return ret; } static void __exit ip6table_raw_fini(void) { unregister_pernet_subsys(&ip6table_raw_net_ops); xt_unregister_template(&packet_raw); kfree(rawtable_ops); } module_init(ip6table_raw_init); module_exit(ip6table_raw_fini); MODULE_LICENSE("GPL"); |
| 96 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_64_H #define _ASM_X86_PGTABLE_64_H #include <linux/const.h> #include <asm/pgtable_64_types.h> #ifndef __ASSEMBLY__ /* * This file contains the functions and defines necessary to modify and use * the x86-64 page table tree. */ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> #include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) #if CONFIG_PGTABLE_LEVELS >= 5 #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %p(%016lx)\n", \ __FILE__, __LINE__, &(e), p4d_val(e)) #endif #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; #define mm_p4d_folded mm_p4d_folded static inline bool mm_p4d_folded(struct mm_struct *mm) { return !pgtable_l5_enabled(); } void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); static inline void native_set_pte(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { native_set_pte(ptep, pte); } static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) { native_set_pmd(pmd, native_make_pmd(0)); } static inline pte_t native_ptep_get_and_clear(pte_t *xp) { #ifdef CONFIG_SMP return native_make_pte(xchg(&xp->pte, 0)); #else /* native_local_ptep_get_and_clear, but duplicated because of cyclic dependency */ pte_t ret = *xp; native_pte_clear(NULL, 0, xp); return ret; #endif } static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { #ifdef CONFIG_SMP return native_make_pmd(xchg(&xp->pmd, 0)); #else /* native_local_pmdp_get_and_clear, but duplicated because of cyclic dependency */ pmd_t ret = *xp; native_pmd_clear(xp); return ret; #endif } static inline void native_set_pud(pud_t *pudp, pud_t pud) { WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) { native_set_pud(pud, native_make_pud(0)); } static inline pud_t native_pudp_get_and_clear(pud_t *xp) { #ifdef CONFIG_SMP return native_make_pud(xchg(&xp->pud, 0)); #else /* native_local_pudp_get_and_clear, * but duplicated because of cyclic dependency */ pud_t ret = *xp; native_pud_clear(xp); return ret; #endif } static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) { native_set_p4d(p4d, native_make_p4d(0)); } static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) { native_set_pgd(pgd, native_make_pgd(0)); } /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ /* PGD - Level 4 access */ /* PUD - Level 3 access */ /* PMD - Level 2 access */ /* PTE - Level 1 access */ /* * Encode and de-code a swap entry * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|F|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above * there. We also need to avoid using A and D because of an * erratum where they can be incorrectly set by hardware on * non-present PTEs. * * SD Bits 1-4 are not used in non-present format and available for * special use described below: * * SD (1) in swp entry is used to store soft dirty bit, which helps us * remember soft dirty over page migration * * F (2) in swp entry is used to record when a pagetable is * writeprotected by userfaultfd WP support. * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. * * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define SWP_TYPE_BITS 5 #define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) /* We always extract/encode the offset by shifting it all the way up, and then down again */ #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) /* Extract the high bits for type */ #define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) /* Shift up (to get rid of type), then down to get value */ #define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) /* * Shift the offset up "too far" by TYPE bits, then down again * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define __swp_entry(type, offset) ((swp_entry_t) { \ (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) #define __swp_entry_to_pte(x) (__pte((x).val)) #define __swp_entry_to_pmd(x) (__pmd((x).val)) extern int kern_addr_valid(unsigned long addr); extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 /* fs/proc/kcore.c */ #define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) #define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK) #define __HAVE_ARCH_PTE_SAME #define vmemmap ((struct page *)VMEMMAP_START) extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { if (end >> __VIRTUAL_MASK_SHIFT) return false; return true; } #include <asm/pgtable-invert.h> #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ |
| 35 35 31 35 35 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/mutex.h> #include <net/sock.h> #include "nf_internals.h" /* Sockopts only registered and called from user context, so net locking would be overkill. Also, [gs]etsockopt calls may sleep. */ static DEFINE_MUTEX(nf_sockopt_mutex); static LIST_HEAD(nf_sockopts); /* Do exclusive ranges overlap? */ static inline int overlap(int min1, int max1, int min2, int max2) { return max1 > min2 && min1 < max2; } /* Functions to register sockopt ranges (exclusive). */ int nf_register_sockopt(struct nf_sockopt_ops *reg) { struct nf_sockopt_ops *ops; int ret = 0; mutex_lock(&nf_sockopt_mutex); list_for_each_entry(ops, &nf_sockopts, list) { if (ops->pf == reg->pf && (overlap(ops->set_optmin, ops->set_optmax, reg->set_optmin, reg->set_optmax) || overlap(ops->get_optmin, ops->get_optmax, reg->get_optmin, reg->get_optmax))) { pr_debug("nf_sock overlap: %u-%u/%u-%u v %u-%u/%u-%u\n", ops->set_optmin, ops->set_optmax, ops->get_optmin, ops->get_optmax, reg->set_optmin, reg->set_optmax, reg->get_optmin, reg->get_optmax); ret = -EBUSY; goto out; } } list_add(®->list, &nf_sockopts); out: mutex_unlock(&nf_sockopt_mutex); return ret; } EXPORT_SYMBOL(nf_register_sockopt); void nf_unregister_sockopt(struct nf_sockopt_ops *reg) { mutex_lock(&nf_sockopt_mutex); list_del(®->list); mutex_unlock(&nf_sockopt_mutex); } EXPORT_SYMBOL(nf_unregister_sockopt); static struct nf_sockopt_ops *nf_sockopt_find(struct sock *sk, u_int8_t pf, int val, int get) { struct nf_sockopt_ops *ops; mutex_lock(&nf_sockopt_mutex); list_for_each_entry(ops, &nf_sockopts, list) { if (ops->pf == pf) { if (!try_module_get(ops->owner)) goto out_nosup; if (get) { if (val >= ops->get_optmin && val < ops->get_optmax) goto out; } else { if (val >= ops->set_optmin && val < ops->set_optmax) goto out; } module_put(ops->owner); } } out_nosup: ops = ERR_PTR(-ENOPROTOOPT); out: mutex_unlock(&nf_sockopt_mutex); return ops; } int nf_setsockopt(struct sock *sk, u_int8_t pf, int val, sockptr_t opt, unsigned int len) { struct nf_sockopt_ops *ops; int ret; ops = nf_sockopt_find(sk, pf, val, 0); if (IS_ERR(ops)) return PTR_ERR(ops); ret = ops->set(sk, val, opt, len); module_put(ops->owner); return ret; } EXPORT_SYMBOL(nf_setsockopt); int nf_getsockopt(struct sock *sk, u_int8_t pf, int val, char __user *opt, int *len) { struct nf_sockopt_ops *ops; int ret; ops = nf_sockopt_find(sk, pf, val, 1); if (IS_ERR(ops)) return PTR_ERR(ops); ret = ops->get(sk, val, opt, len); module_put(ops->owner); return ret; } EXPORT_SYMBOL(nf_getsockopt); |
| 2885 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H #include <linux/kernel.h> /* * This is largely generic for little-endian machines, but the * optimal byte mask counting is probably going to be something * that is architecture-specific. If you have a reliably fast * bit count instruction, that might be better than the multiply * and shift, for example. */ struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } #ifdef CONFIG_64BIT /* * Jan Achrenius on G+: microoptimized version of * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" * that works for the bytemasks without having to * mask them first. */ static inline long count_masked_bytes(unsigned long mask) { return mask*0x0001020304050608ul >> 56; } #else /* 32-bit case */ /* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ static inline long count_masked_bytes(long mask) { /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ long a = (0x0ff0001+mask) >> 23; /* Fix the 1 for 00 case */ return a & mask; } #endif /* Return nonzero if it has a zero */ static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) { return bits; } static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } /* The mask we created is directly usable as a bytemask */ #define zero_bytemask(mask) (mask) static inline unsigned long find_zero(unsigned long mask) { return count_masked_bytes(mask); } /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret, dummy; asm( "1:\tmov %2,%0\n" "2:\n" ".section .fixup,\"ax\"\n" "3:\t" "lea %2,%1\n\t" "and %3,%1\n\t" "mov (%1),%0\n\t" "leal %2,%%ecx\n\t" "andl %4,%%ecx\n\t" "shll $3,%%ecx\n\t" "shr %%cl,%0\n\t" "jmp 2b\n" ".previous\n" _ASM_EXTABLE(1b, 3b) :"=&r" (ret),"=&c" (dummy) :"m" (*(unsigned long *)addr), "i" (-sizeof(unsigned long)), "i" (sizeof(unsigned long)-1)); return ret; } #endif /* _ASM_WORD_AT_A_TIME_H */ |
| 24 22 22 22 24 24 24 24 1 1 23 24 19 18 1 89 49 57 34 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/switchdev.h> #include "br_private.h" static struct static_key_false br_switchdev_tx_fwd_offload; static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p, const struct sk_buff *skb) { if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) return false; return (p->flags & BR_TX_FWD_OFFLOAD) && (p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom); } bool br_switchdev_frame_uses_tx_fwd_offload(struct sk_buff *skb) { if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) return false; return BR_INPUT_SKB_CB(skb)->tx_fwd_offload; } void br_switchdev_frame_set_offload_fwd_mark(struct sk_buff *skb) { skb->offload_fwd_mark = br_switchdev_frame_uses_tx_fwd_offload(skb); } /* Mark the frame for TX forwarding offload if this egress port supports it */ void nbp_switchdev_frame_mark_tx_fwd_offload(const struct net_bridge_port *p, struct sk_buff *skb) { if (nbp_switchdev_can_offload_tx_fwd(p, skb)) BR_INPUT_SKB_CB(skb)->tx_fwd_offload = true; } /* Lazily adds the hwdom of the egress bridge port to the bit mask of hwdoms * that the skb has been already forwarded to, to avoid further cloning to * other ports in the same hwdom by making nbp_switchdev_allowed_egress() * return false. */ void nbp_switchdev_frame_mark_tx_fwd_to_hwdom(const struct net_bridge_port *p, struct sk_buff *skb) { if (nbp_switchdev_can_offload_tx_fwd(p, skb)) set_bit(p->hwdom, &BR_INPUT_SKB_CB(skb)->fwd_hwdoms); } void nbp_switchdev_frame_mark(const struct net_bridge_port *p, struct sk_buff *skb) { if (p->hwdom) BR_INPUT_SKB_CB(skb)->src_hwdom = p->hwdom; } bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, const struct sk_buff *skb) { struct br_input_skb_cb *cb = BR_INPUT_SKB_CB(skb); return !test_bit(p->hwdom, &cb->fwd_hwdoms) && (!skb->offload_fwd_mark || cb->src_hwdom != p->hwdom); } /* Flags that can be offloaded to hardware */ #define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | \ BR_MCAST_FLOOD | BR_BCAST_FLOOD) int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long flags, unsigned long mask, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = p->dev, }; struct switchdev_notifier_port_attr_info info = { .attr = &attr, }; int err; mask &= BR_PORT_FLAGS_HW_OFFLOAD; if (!mask) return 0; attr.id = SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS; attr.u.brport_flags.val = flags; attr.u.brport_flags.mask = mask; /* We run from atomic context here */ err = call_switchdev_notifiers(SWITCHDEV_PORT_ATTR_SET, p->dev, &info.info, extack); err = notifier_to_errno(err); if (err == -EOPNOTSUPP) return 0; if (err) { if (extack && !extack->_msg) NL_SET_ERR_MSG_MOD(extack, "bridge flag offload is not supported"); return -EOPNOTSUPP; } attr.id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS; attr.flags = SWITCHDEV_F_DEFER; err = switchdev_port_attr_set(p->dev, &attr, extack); if (err) { if (extack && !extack->_msg) NL_SET_ERR_MSG_MOD(extack, "error setting offload flag on port"); return err; } return 0; } void br_switchdev_fdb_notify(struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, int type) { const struct net_bridge_port *dst = READ_ONCE(fdb->dst); struct switchdev_notifier_fdb_info info = { .addr = fdb->key.addr.addr, .vid = fdb->key.vlan_id, .added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags), .is_local = test_bit(BR_FDB_LOCAL, &fdb->flags), .offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags), }; struct net_device *dev = (!dst || info.is_local) ? br->dev : dst->dev; switch (type) { case RTM_DELNEIGH: call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_DEVICE, dev, &info.info, NULL); break; case RTM_NEWNEIGH: call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_DEVICE, dev, &info.info, NULL); break; } } int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, struct netlink_ext_ack *extack) { struct switchdev_obj_port_vlan v = { .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .flags = flags, .vid = vid, }; return switchdev_port_obj_add(dev, &v.obj, extack); } int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid) { struct switchdev_obj_port_vlan v = { .obj.orig_dev = dev, .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, }; return switchdev_port_obj_del(dev, &v.obj); } static int nbp_switchdev_hwdom_set(struct net_bridge_port *joining) { struct net_bridge *br = joining->br; struct net_bridge_port *p; int hwdom; /* joining is yet to be added to the port list. */ list_for_each_entry(p, &br->port_list, list) { if (netdev_phys_item_id_same(&joining->ppid, &p->ppid)) { joining->hwdom = p->hwdom; return 0; } } hwdom = find_next_zero_bit(&br->busy_hwdoms, BR_HWDOM_MAX, 1); if (hwdom >= BR_HWDOM_MAX) return -EBUSY; set_bit(hwdom, &br->busy_hwdoms); joining->hwdom = hwdom; return 0; } static void nbp_switchdev_hwdom_put(struct net_bridge_port *leaving) { struct net_bridge *br = leaving->br; struct net_bridge_port *p; /* leaving is no longer in the port list. */ list_for_each_entry(p, &br->port_list, list) { if (p->hwdom == leaving->hwdom) return; } clear_bit(leaving->hwdom, &br->busy_hwdoms); } static int nbp_switchdev_add(struct net_bridge_port *p, struct netdev_phys_item_id ppid, bool tx_fwd_offload, struct netlink_ext_ack *extack) { int err; if (p->offload_count) { /* Prevent unsupported configurations such as a bridge port * which is a bonding interface, and the member ports are from * different hardware switches. */ if (!netdev_phys_item_id_same(&p->ppid, &ppid)) { NL_SET_ERR_MSG_MOD(extack, "Same bridge port cannot be offloaded by two physical switches"); return -EBUSY; } /* Tolerate drivers that call switchdev_bridge_port_offload() * more than once for the same bridge port, such as when the * bridge port is an offloaded bonding/team interface. */ p->offload_count++; return 0; } p->ppid = ppid; p->offload_count = 1; err = nbp_switchdev_hwdom_set(p); if (err) return err; if (tx_fwd_offload) { p->flags |= BR_TX_FWD_OFFLOAD; static_branch_inc(&br_switchdev_tx_fwd_offload); } return 0; } static void nbp_switchdev_del(struct net_bridge_port *p) { if (WARN_ON(!p->offload_count)) return; p->offload_count--; if (p->offload_count) return; if (p->hwdom) nbp_switchdev_hwdom_put(p); if (p->flags & BR_TX_FWD_OFFLOAD) { p->flags &= ~BR_TX_FWD_OFFLOAD; static_branch_dec(&br_switchdev_tx_fwd_offload); } } static int nbp_switchdev_sync_objs(struct net_bridge_port *p, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, struct netlink_ext_ack *extack) { struct net_device *br_dev = p->br->dev; struct net_device *dev = p->dev; int err; err = br_vlan_replay(br_dev, dev, ctx, true, blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; err = br_mdb_replay(br_dev, dev, ctx, true, blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; err = br_fdb_replay(br_dev, ctx, true, atomic_nb); if (err && err != -EOPNOTSUPP) return err; return 0; } static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb) { struct net_device *br_dev = p->br->dev; struct net_device *dev = p->dev; br_vlan_replay(br_dev, dev, ctx, false, blocking_nb, NULL); br_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); br_fdb_replay(br_dev, ctx, false, atomic_nb); } /* Let the bridge know that this port is offloaded, so that it can assign a * switchdev hardware domain to it. */ int br_switchdev_port_offload(struct net_bridge_port *p, struct net_device *dev, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb, bool tx_fwd_offload, struct netlink_ext_ack *extack) { struct netdev_phys_item_id ppid; int err; err = dev_get_port_parent_id(dev, &ppid, false); if (err) return err; err = nbp_switchdev_add(p, ppid, tx_fwd_offload, extack); if (err) return err; err = nbp_switchdev_sync_objs(p, ctx, atomic_nb, blocking_nb, extack); if (err) goto out_switchdev_del; return 0; out_switchdev_del: nbp_switchdev_del(p); return err; } void br_switchdev_port_unoffload(struct net_bridge_port *p, const void *ctx, struct notifier_block *atomic_nb, struct notifier_block *blocking_nb) { nbp_switchdev_unsync_objs(p, ctx, atomic_nb, blocking_nb); nbp_switchdev_del(p); } |
| 7 3 4 6 3 3 1 1 1 81 81 81 34 7 22 16 6 1 5 5 5 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> * (C) 2006-2010 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/timer.h> #include <linux/netfilter.h> #include <linux/in.h> #include <linux/icmp.h> #include <linux/seq_file.h> #include <net/ip.h> #include <net/checksum.h> #include <linux/netfilter_ipv4.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" static const unsigned int nf_ct_icmp_timeout = 30*HZ; bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmphdr *hp; struct icmphdr _hdr; hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (hp == NULL) return false; tuple->dst.u.icmp.type = hp->type; tuple->src.u.icmp.id = hp->un.echo.id; tuple->dst.u.icmp.code = hp->code; return true; } /* Add 1; spaces filled with 0. */ static const u_int8_t invmap[] = { [ICMP_ECHO] = ICMP_ECHOREPLY + 1, [ICMP_ECHOREPLY] = ICMP_ECHO + 1, [ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1, [ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1, [ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1, [ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1, [ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1, [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1 }; bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { if (orig->dst.u.icmp.type >= sizeof(invmap) || !invmap[orig->dst.u.icmp.type]) return false; tuple->src.u.icmp.id = orig->src.u.icmp.id; tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1; tuple->dst.u.icmp.code = orig->dst.u.icmp.code; return true; } /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_icmp_packet(struct nf_conn *ct, struct sk_buff *skb, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ unsigned int *timeout = nf_ct_timeout_lookup(ct); static const u_int8_t valid_new[] = { [ICMP_ECHO] = 1, [ICMP_TIMESTAMP] = 1, [ICMP_INFO_REQUEST] = 1, [ICMP_ADDRESS] = 1 }; if (state->pf != NFPROTO_IPV4) return -NF_ACCEPT; if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { /* Can't create a new ICMP `conn' with this. */ pr_debug("icmp: can't create new conn with type %u\n", ct->tuplehash[0].tuple.dst.u.icmp.type); nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple); return -NF_ACCEPT; } if (!timeout) timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Check inner header is related to any of the existing connections */ int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state, u8 l4proto, union nf_inet_addr *outer_daddr) { struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_zone *zone; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; union nf_inet_addr *ct_daddr; enum ip_conntrack_dir dir; struct nf_conn *ct; WARN_ON(skb_nfct(skb)); zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuplepr(skb, dataoff, state->pf, state->net, &origtuple)) return -NF_ACCEPT; /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ if (!nf_ct_invert_tuple(&innertuple, &origtuple)) return -NF_ACCEPT; h = nf_conntrack_find_get(state->net, zone, &innertuple); if (!h) return -NF_ACCEPT; /* Consider: A -> T (=This machine) -> B * Conntrack entry will look like this: * Original: A->B * Reply: B->T (SNAT case) OR A * * When this function runs, we got packet that looks like this: * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..). * * Above nf_conntrack_find_get() makes lookup based on inner_hdr, * so we should expect that destination of the found connection * matches outer header destination address. * * In above example, we can consider these two cases: * 1. Error coming in reply direction from B or M (middle box) to * T (SNAT case) or A. * Inner saddr will be B, dst will be T or A. * The found conntrack will be reply tuple (B->T/A). * 2. Error coming in original direction from A or M to B. * Inner saddr will be A, inner daddr will be B. * The found conntrack will be original tuple (A->B). * * In both cases, conntrack[dir].dst == inner.dst. * * A bogus packet could look like this: * Inner: B->T * Outer: B->X (other machine reachable by T). * * In this case, lookup yields connection A->B and will * set packet from B->X as *RELATED*, even though no connection * from X was ever seen. */ ct = nf_ct_tuplehash_to_ctrack(h); dir = NF_CT_DIRECTION(h); ct_daddr = &ct->tuplehash[dir].tuple.dst.u3; if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) { if (state->pf == AF_INET) { nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI4 != inner %pI4", &outer_daddr->ip, &ct_daddr->ip); } else if (state->pf == AF_INET6) { nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI6 != inner %pI6", &outer_daddr->ip6, &ct_daddr->ip6); } nf_ct_put(ct); return -NF_ACCEPT; } ctinfo = IP_CT_RELATED; if (dir == IP_CT_DIR_REPLY) ctinfo += IP_CT_IS_REPLY; /* Update skb to refer to this connection */ nf_ct_set(skb, ct, ctinfo); return NF_ACCEPT; } static void icmp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state, IPPROTO_ICMP, "%s", msg); } /* Small and modified version of icmp_rcv */ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { union nf_inet_addr outer_daddr; const struct icmphdr *icmph; struct icmphdr _ih; /* Not enough header? */ icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmph == NULL) { icmp_error_log(skb, state, "short packet"); return -NF_ACCEPT; } /* See nf_conntrack_proto_tcp.c */ if (state->net->ct.sysctl_checksum && state->hook == NF_INET_PRE_ROUTING && nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) { icmp_error_log(skb, state, "bad hw icmp checksum"); return -NF_ACCEPT; } /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ if (icmph->type > NR_ICMP_TYPES) { icmp_error_log(skb, state, "invalid icmp type"); return -NF_ACCEPT; } /* Need to track icmp error message? */ if (!icmp_is_err(icmph->type)) return NF_ACCEPT; memset(&outer_daddr, 0, sizeof(outer_daddr)); outer_daddr.ip = ip_hdr(skb)->daddr; dataoff += sizeof(*icmph); return nf_conntrack_inet_error(tmpl, skb, dataoff, state, IPPROTO_ICMP, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static int icmp_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *t) { if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) || nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) || nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_ICMP_TYPE] = { .type = NLA_U8 }, [CTA_PROTO_ICMP_CODE] = { .type = NLA_U8 }, [CTA_PROTO_ICMP_ID] = { .type = NLA_U16 }, }; static int icmp_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) { if (!tb[CTA_PROTO_ICMP_TYPE]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); if (tuple->dst.u.icmp.type >= sizeof(invmap) || !invmap[tuple->dst.u.icmp.type]) return -EINVAL; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) { if (!tb[CTA_PROTO_ICMP_CODE]) return -EINVAL; tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) { if (!tb[CTA_PROTO_ICMP_ID]) return -EINVAL; tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); } return 0; } static unsigned int icmp_nlattr_tuple_size(void) { static unsigned int size __read_mostly; if (!size) size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); return size; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; struct nf_icmp_net *in = nf_icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { if (!timeout) timeout = &in->timeout; *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; } else if (timeout) { /* Set default ICMP timeout. */ *timeout = in->timeout; } return 0; } static int icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_icmp_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmp_pernet(net); in->timeout = nf_ct_icmp_timeout; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = { .l4proto = IPPROTO_ICMP, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmp_tuple_to_nlattr, .nlattr_tuple_size = icmp_nlattr_tuple_size, .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmp_timeout_nlattr_to_obj, .obj_to_nlattr = icmp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_ICMP_MAX, .obj_size = sizeof(unsigned int), .nla_policy = icmp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 429 430 180 180 180 970 3004 180 73 73 72 73 65 73 9 70 73 7 73 73 73 72 73 73 73 73 73 73 72 459 458 23 24 253 253 254 253 501 481 253 246 274 253 253 253 251 254 252 251 253 254 254 254 251 254 251 253 253 254 252 253 253 253 254 253 254 253 254 253 254 253 254 252 251 254 254 252 254 252 254 253 78 78 78 78 73 78 78 77 78 78 78 78 78 78 78 78 78 78 78 78 70 78 78 7 78 78 78 77 77 78 78 77 73 78 78 78 73 620 621 618 618 617 620 4202 4209 4206 1502 4210 4202 4211 4206 4208 4203 1503 4214 4203 4201 4197 4201 4210 4214 4205 4210 4214 4209 4214 4205 4205 1506 206 2987 15 95 96 436 435 232 206 435 436 5 205 232 433 435 435 232 204 206 437 230 206 205 480 482 232 251 250 95 96 96 206 31 31 31 2669 1959 1 1950 746 744 746 741 745 3 3 3 15 15 15 15 1 14 15 15 3 15 15 3 223 2550 2683 15 486 8 480 7 3002 2998 2999 3003 2998 3010 3001 3012 3 3 2993 2994 3004 3012 2801 245 3013 2810 240 245 2993 253 254 362 367 363 8 8 8 8 8 15702 270 15688 471 470 72 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NUMA unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL * and ZONE_HIGHMEM. */ void *high_memory; EXPORT_SYMBOL(high_memory); /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif #ifndef arch_faults_on_old_pte static inline bool arch_faults_on_old_pte(void) { /* * Those arches which don't have hw access flag feature need to * implement their own helper. By default, "true" means pagefault * will be hit on old pte. */ return true; } #endif #ifndef arch_wants_old_prefaulted_pte static inline bool arch_wants_old_prefaulted_pte(void) { /* * Transitioning a PTE from 'old' to 'young' can be expensive on * some architectures, even if it's performed in hardware. By * default, "false" means prefaulted entries will be 'young'. */ return false; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ static int __init init_zero_pfn(void) { zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { trace_rss_stat(mm, member, count); } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) { if (current->rss_stat.count[i]) { add_mm_counter(mm, i, current->rss_stat.count[i]); current->rss_stat.count[i] = 0; } } current->rss_stat.events = 0; } static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) { struct task_struct *task = current; if (likely(task->mm == mm)) task->rss_stat.count[member] += val; else add_mm_counter(mm, member, val); } #define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) #define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) /* sync counter once per 64 page faults */ #define TASK_RSS_EVENTS_THRESH (64) static void check_sync_rss_stat(struct task_struct *task) { if (unlikely(task != current)) return; if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) sync_mm_rss(task->mm); } #else /* SPLIT_RSS_COUNTING */ #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) static void check_sync_rss_stat(struct task_struct *task) { } #endif /* SPLIT_RSS_COUNTING */ /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /* * This function frees user-level page tables of a process. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { struct vm_area_struct *next = vma->vm_next; unsigned long addr = vma->vm_start; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } else { /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } vma = next; } } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); pmd_populate(mm, pmd, new); new = NULL; } spin_unlock(ptl); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; if (current->mm == mm) sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } /* * This function is called to print an error when a bad pte * is found. For example, we might have a PFN-mapped pte in * a region that doesn't allow it. * * The calling function must still handle the error. */ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, mapping ? mapping->a_ops->readpage : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page. * * There are 2 broad cases. Firstly, an architecture may define a pte_special() * pte bit, in which case this function is trivial. Secondly, an architecture * may not have a spare pte bit, which requires a more complicated scheme, * described below. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true) are refcounted and considered * normal pages by the VM. The disadvantage is that pages are refcounted * (which can be slower and simply not an option for some PFNMAP users). The * advantage is that we don't have to follow the strict linearity rule of * PFNMAP mappings in order to support COWable mappings. * */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { unsigned long pfn = pte_pfn(pte); if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) return NULL; print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn)) return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); /* * There is no pmd_special() but there may be special pmds, e.g. * in a direct-access (dax) mapping, so let's just replicate the * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here. */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (pmd_devmap(pmd)) return NULL; if (is_huge_zero_pmd(pmd)) return NULL; if (unlikely(pfn > highest_memmap_pfn)) return NULL; /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #endif static void restore_exclusive_pte(struct vm_area_struct *vma, struct page *page, unsigned long address, pte_t *ptep) { pte_t pte; swp_entry_t entry; pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); if (pte_swp_soft_dirty(*ptep)) pte = pte_mksoft_dirty(pte); entry = pte_to_swp_entry(*ptep); if (pte_swp_uffd_wp(*ptep)) pte = pte_mkuffd_wp(pte); else if (is_writable_device_exclusive_entry(entry)) pte = maybe_mkwrite(pte_mkdirty(pte), vma); set_pte_at(vma->vm_mm, address, ptep, pte); /* * No need to take a page reference as one was already * created when the swap entry was made. */ if (PageAnon(page)) page_add_anon_rmap(page, vma, address, false); else /* * Currently device exclusive access only supports anonymous * memory so the entry shouldn't point to a filebacked page. */ WARN_ON_ONCE(!PageAnon(page)); if (vma->vm_flags & VM_LOCKED) mlock_vma_page(page); /* * No need to invalidate - it was non-present before. However * secondary CPUs may have mappings that need invalidating. */ update_mmu_cache(vma, address, ptep); } /* * Tries to restore an exclusive pte if the page lock can be acquired without * sleeping. */ static int try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma, unsigned long addr) { swp_entry_t entry = pte_to_swp_entry(*src_pte); struct page *page = pfn_swap_entry_to_page(entry); if (trylock_page(page)) { restore_exclusive_pte(vma, page, addr, src_pte); unlock_page(page); return 0; } return -EBUSY; } /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; swp_entry_t entry = pte_to_swp_entry(pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) return -EIO; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { page = pfn_swap_entry_to_page(entry); rss[mm_counter(page)]++; if (is_writable_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both * parent and child to be set to read. */ entry = make_readable_migration_entry( swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*src_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { page = pfn_swap_entry_to_page(entry); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ get_page(page); rss[mm_counter(page)]++; page_dup_rmap(page, false); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (is_writable_device_private_entry(entry) && is_cow_mapping(vm_flags)) { entry = make_readable_device_private_entry( swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_exclusive_entry(entry)) { /* * Make device exclusive entries present by restoring the * original entry then copying as for a present pte. Device * exclusive entries currently only support private writable * (ie. COW) mappings. */ VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags)); if (try_restore_exclusive_pte(src_pte, src_vma, addr)) return -EBUSY; return -ENOENT; } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page if necessary. * * NOTE! The usual case is that this doesn't need to do * anything, and can just return a positive value. That * will let the caller know that it can just increase * the page refcount and re-use the pte the traditional * way. * * But _if_ we need to copy it because it needs to be * pinned in the parent (and the child should get its own * copy rather than just a reference to the same page), * we'll do that here and return zero to let the caller * know we're done. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc, pte_t pte, struct page *page) { struct page *new_page; /* * What we want to do is to check whether this page may * have been pinned by the parent process. If so, * instead of wrprotect the pte on both sides, we copy * the page immediately so that we'll always guarantee * the pinned page won't be randomly replaced in the * future. * * The page pinning checks are just "has this mm ever * seen pinning", along with the (inexact) check of * the page count. That might give false positives for * for pinning, but it will work correctly. */ if (likely(!page_needs_cow_for_dma(src_vma, page))) return 1; /* * The vma->anon_vma of the child process may be NULL * because the entire vma does not contain anonymous pages. * A BUG will occur when the copy_present_page() passes * a copy of a non-anonymous page of that vma to the * page_add_new_anon_rmap() to set up new anonymous rmap. * Return 1 if the page is not an anonymous page. */ if (!PageAnon(page)) return 1; new_page = *prealloc; if (!new_page) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); page_add_new_anon_rmap(new_page, dst_vma, addr, false); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; /* All done, just insert the new page copy in the child */ pte = mk_pte(new_page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, *src_pte)) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_wrprotect(pte_mkuffd_wp(pte)); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } /* * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page * is required to copy this pte. */ static inline int copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc) { struct mm_struct *src_mm = src_vma->vm_mm; unsigned long vm_flags = src_vma->vm_flags; pte_t pte = *src_pte; struct page *page; page = vm_normal_page(src_vma, addr, pte); if (page) { int retval; retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, pte, page); if (retval <= 0) return retval; get_page(page); page_dup_rmap(page, false); rss[mm_counter(page)]++; } /* * If it's a COW mapping, write protect it both * in the parent and the child */ if (is_cow_mapping(vm_flags) && pte_write(pte)) { ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } /* * If it's a shared mapping, mark it clean in * the child */ if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static inline struct page * page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr) { struct page *new_page; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); if (!new_page) return NULL; if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } cgroup_throttle_swaprate(new_page, GFP_KERNEL); return new_page; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; struct page *prealloc = NULL; again: progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } if (pte_none(*src_pte)) { progress++; continue; } if (unlikely(!pte_present(*src_pte))) { ret = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (ret == -EIO) { entry = pte_to_swp_entry(*src_pte); break; } else if (ret == -EBUSY) { break; } else if (!ret) { progress += 8; continue; } /* * Device exclusive entry restored, continue by copying * the now present pte. */ WARN_ON_ONCE(ret != -ENOENT); } /* copy_present_pte() will clear `*prealloc' if consumed */ ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, addr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. */ if (unlikely(ret == -EAGAIN)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ put_page(prealloc); prealloc = NULL; } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap(orig_src_pte); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (ret == -EIO) { VM_WARN_ON_ONCE(!entry.val); if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret == -EBUSY) { goto out; } else if (ret == -EAGAIN) { prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; } else if (ret) { VM_WARN_ON_ONCE(1); } /* We've captured and resolved the error. Reset, try again. */ ret = 0; if (addr != end) goto again; out: if (unlikely(prealloc)) put_page(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; /* * Don't copy ptes where a page fault will fill them correctly. * Fork becomes much lighter when there are big shared or private * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && !src_vma->anon_vma) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ ret = track_pfn_copy(src_vma); if (ret) return ret; } /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_vma, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ mmap_assert_write_locked(src_mm); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ if (!details) return true; /* Or, we zap COWed pages only if the caller wants to */ return !details->check_mapping; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { struct mm_struct *mm = tlb->mm; int force_flush = 0; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; swp_entry_t entry; tlb_change_page_size(tlb, PAGE_SIZE); again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = start_pte; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; if (pte_none(ptent)) continue; if (need_resched()) break; if (pte_present(ptent)) { struct page *page; page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping && details->check_mapping != page_rmapping(page)) continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; if (!PageAnon(page)) { if (pte_dirty(ptent)) { force_flush = 1; set_page_dirty(page); } if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); } rss[mm_counter(page)]--; page_remove_rmap(page, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(__tlb_remove_page(tlb, page))) { force_flush = 1; addr += PAGE_SIZE; break; } continue; } entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry) || is_device_exclusive_entry(entry)) { struct page *page = pfn_swap_entry_to_page(entry); if (unlikely(details && details->check_mapping)) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping != page_rmapping(page)) continue; } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; if (is_device_private_entry(entry)) page_remove_rmap(page, false); put_page(page); continue; } if (!non_swap_entry(entry)) { /* Genuine swap entry, hence a private anon page */ if (!should_zap_cows(details)) continue; rss[MM_SWAPENTS]--; } else if (is_migration_entry(entry)) { struct page *page; page = pfn_swap_entry_to_page(entry); if (details && details->check_mapping && details->check_mapping != page_rmapping(page)) continue; rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Restart if we didn't do everything. */ if (force_flush) { force_flush = 0; tlb_flush_mmu(tlb); } if (addr != end) { cond_resched(); goto again; } return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } else if (details && details->single_page && PageTransCompound(details->single_page) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* * Take and drop THP pmd lock so that we cannot return * prematurely, while zap_huge_pmd() has cleared *pmd, * but not yet decremented compound_mapcount(). */ spin_unlock(ptl); } /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is * none or trans huge it can change under us. This is * because MADV_DONTNEED holds the mmap_lock in read * mode. */ if (pmd_none_or_trans_huge_or_clear_bad(pmd)) goto next; next = zap_pte_range(tlb, vma, pmd, addr, next, details); next: cond_resched(); } while (pmd++, addr = next, addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; if (start >= vma->vm_end) return; end = min(vma->vm_end, end_addr); if (end <= vma->vm_start) return; if (vma->vm_file) uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn(vma, 0, 0); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { i_mmap_lock_write(vma->vm_file->f_mapping); __unmap_hugepage_range_final(tlb, vma, start, end, NULL); i_mmap_unlock_write(vma->vm_file->f_mapping); } } else unmap_page_range(tlb, vma, start, end, details); } } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); mmu_notifier_invalidate_range_end(&range); } /** * zap_page_range - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap * * Caller must protect the VMA list */ void zap_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long size) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, start, start + size); tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) unmap_single_vma(&tlb, vma, start, range.end, NULL); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of shared cache invalidation * * The range must fit into one VMA. */ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, address + size); tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); unmap_single_vma(&tlb, vma, address, range.end, details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped * @address: starting address of pages to zap * @size: number of bytes to zap * * This function only unmaps ptes assigned to VM_PFNMAP vmas. * * The entire address range must be fully contained within the vma. * */ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (address < vma->vm_start || address + size > vma->vm_end || !(vma->vm_flags & VM_PFNMAP)) return; zap_page_range_single(vma, address, size, NULL); } EXPORT_SYMBOL_GPL(zap_vma_ptes); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static int validate_page_before_insert(struct page *page) { if (PageAnon(page) || PageSlab(page) || page_has_type(page)) return -EINVAL; flush_dcache_page(page); return 0; } static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { if (!pte_none(*pte)) return -EBUSY; /* Ok, finally just insert the thing.. */ get_page(page); inc_mm_counter_fast(mm, mm_counter_file(page)); page_add_file_rmap(page, false); set_pte_at(mm, addr, pte, mk_pte(page, prot)); return 0; } /* * This is the old fallback for page remapping. * * For historical reasons, it only allows reserved pages. Only * old drivers should use this, and they needed to mark their * pages reserved for the old functions anyway. */ static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(mm, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } #ifdef pte_index static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; if (!page_count(page)) return -EINVAL; err = validate_page_before_insert(page); if (err) return err; return insert_page_into_pte_locked(mm, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. Arch *must* define pte_index. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(mm, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } #endif /* ifdef pte_index */ /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { #ifdef pte_index const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; if (addr < vma->vm_start || end_addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); #else unsigned long idx = 0, pgcount = *num; int err = -EINVAL; for (; idx < pgcount; ++idx) { err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); if (err) break; } *num = pgcount - idx; return err; #endif /* ifdef pte_index */ } EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!page_count(page)) return -EINVAL; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; for (i = 0; i < count; i++) { ret = vm_insert_page(vma, uaddr, pages[offset + i]); if (ret < 0) return ret; uaddr += PAGE_SIZE; } return 0; } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; if (!pte_none(*pte)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; } entry = pte_mkyoung(*pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * See vmf_insert_mixed_prot() for a discussion of the implication of using * a value of @pgprot different from that of @vma->vm_page_prot. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (pfn_t_devmap(pfn)) return true; if (pfn_t_special(pfn)) return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot, bool mkwrite) { int err; BUG_ON(!vm_mixed_ok(vma, pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } /** * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_mixed(), except that it allows drivers * to override pgprot on a per-page basis. * * Typically this function should be used by drivers to set caching- and * encryption bits different than those of @vma->vm_page_prot, because * the caching- or encryption mode may not be known at mmap() time. * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot) { return __vm_insert_mixed(vma, addr, pfn, pgprot, false); } EXPORT_SYMBOL(vmf_insert_mixed_prot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true); } EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; /* * Physically remapped pages are special. Tell the * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). * VM_PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * VM_DONTEXPAND * Disable vma merging and expanding with mremap(). * VM_DONTDUMP * Omit vma from core dump, even when VM_IO turned off. * * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow_mapping(vma->vm_flags)) { if (addr != vma->vm_start || end != vma->vm_end) return -EINVAL; vma->vm_pgoff = pfn; } vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pgd++, addr = next, addr != end); return 0; } /* * Variant of remap_pfn_range that does not call track_pfn_remap. The caller * must have pre-validated the caching bits of the pgprot_t. */ int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int error = remap_pfn_range_internal(vma, addr, pfn, size, prot); if (!error) return 0; /* * A partial pfn range mapping is dangerous: it does not * maintain page reference counts, and callers may free * pages due to the error. So zap it early. */ zap_page_range_single(vma, addr, size, NULL); return error; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int err; err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); if (err) untrack_pfn(vma, pfn, PAGE_ALIGN(size)); return err; } EXPORT_SYMBOL(remap_pfn_range); /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { unsigned long vm_len, pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start + len < start) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ len += start & ~PAGE_MASK; pfn = start >> PAGE_SHIFT; pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vma->vm_pgoff > pages) return -EINVAL; pfn += vma->vm_pgoff; pages -= vma->vm_pgoff; /* Can we fit all of the mapping? */ vm_len = vma->vm_end - vma->vm_start; if (vm_len >> PAGE_SHIFT > pages) return -EINVAL; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte, *mapped_pte; int err = 0; spinlock_t *ptl; if (create) { mapped_pte = pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { mapped_pte = pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); } BUG_ON(pmd_huge(*pmd)); arch_enter_lazy_mmu_mode(); if (fn) { do { if (create || !pte_none(*pte)) { err = fn(pte++, addr, data); if (err) break; } } while (addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(mapped_pte, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_huge(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (pmd_none(*pmd) && !create) continue; if (WARN_ON_ONCE(pmd_leaf(*pmd))) return -EINVAL; if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) { if (!create) continue; pmd_clear_bad(pmd); } err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (pud_none(*pud) && !create) continue; if (WARN_ON_ONCE(pud_leaf(*pud))) return -EINVAL; if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) { if (!create) continue; pud_clear_bad(pud); } err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (p4d_none(*p4d) && !create) continue; if (WARN_ON_ONCE(p4d_leaf(*p4d))) return -EINVAL; if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) { if (!create) continue; p4d_clear_bad(p4d); } err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none(*pgd) && !create) continue; if (WARN_ON_ONCE(pgd_leaf(*pgd))) return -EINVAL; if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) { if (!create) continue; pgd_clear_bad(pgd); } err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, pte_t *page_table, pte_t orig_pte) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spinlock_t *ptl = pte_lockptr(mm, pmd); spin_lock(ptl); same = pte_same(*page_table, orig_pte); spin_unlock(ptl); } #endif pte_unmap(page_table); return same; } /* * Return: * 0: copied succeeded * -EHWPOISON: copy failed due to hwpoison in source page * -EAGAIN: copied failed (some other reason) */ static inline int cow_user_page(struct page *dst, struct page *src, struct vm_fault *vmf) { int ret; void *kaddr; void __user *uaddr; bool locked = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { if (copy_mc_user_highpage(dst, src, addr, vma)) { memory_failure_queue(page_to_pfn(src), 0); return -EHWPOISON; } return 0; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_atomic(dst); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ update_mmu_tlb(vma, addr, vmf->pte); ret = -EAGAIN; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache(vma, addr, vmf->pte); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (locked) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ update_mmu_tlb(vma, addr, vmf->pte); ret = -EAGAIN; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = 0; pte_unlock: if (locked) pte_unmap_unlock(vmf->pte, vmf->ptl); kunmap_atomic(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) { vm_fault_t ret; struct page *page = vmf->page; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { lock_page(page); if (!page->mapping) { unlock_page(page); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_PAGE(!PageLocked(page), page); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct page *page = vmf->page; bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = set_page_dirty(page); VM_BUG_ON_PAGE(PageAnon(page), page); /* * Take a local copy of the address_space - page.mapping may be zeroed * by truncate after unlock_page(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on unlock_page()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = page_rmapping(page); unlock_page(page); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_RETRY; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ if (page) page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * Handle the case of a page which we actually need to copy to a new page. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct page *old_page = vmf->page; struct page *new_page = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; int ret; if (unlikely(anon_vma_prepare(vma))) goto oom; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { new_page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!new_page) goto oom; } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!new_page) goto oom; ret = cow_user_page(new_page, old_page, vmf); if (ret) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. * The -EHWPOISON case will not be retried. */ put_page(new_page); if (old_page) put_page(old_page); return ret == -EHWPOISON ? VM_FAULT_HWPOISON : 0; } } if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { dec_mm_counter_fast(mm, mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } } else { inc_mm_counter_fast(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* * Clear the pte entry and flush it first, before updating the * pte with the new entry, to keep TLBs on different CPUs in * sync. This code used to set the new PTE then flush TLBs, but * that left a window where the new PTE could be loaded into * some TLBs while the old PTE remains in others. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * page_remove_rmap with the ptp_clear_flush above. * Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in page_remove_rmap. * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ page_remove_rmap(old_page, false); } /* Free the old page.. */ new_page = old_page; page_copied = 1; } else { update_mmu_tlb(vma, vmf->address, vmf->pte); } if (new_page) put_page(new_page); pte_unmap_unlock(vmf->pte, vmf->ptl); /* * No need to double call mmu_notifier->invalidate_range() callback as * the above ptep_clear_flush_notify() did already call it. */ mmu_notifier_invalidate_range_only_end(&range); if (old_page) { /* * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ if (page_copied && (vma->vm_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ if (PageMlocked(old_page)) munlock_vma_page(old_page); unlock_page(old_page); } if (page_copied) free_swap_cache(old_page); put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: if (old_page) put_page(old_page); return VM_FAULT_OOM; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(*vmf->pte, vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf); } wp_page_reuse(vmf); return VM_FAULT_WRITE; } static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = VM_FAULT_WRITE; get_page(vmf->page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } tmp = finish_mkwrite_fault(vmf); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { unlock_page(vmf->page); put_page(vmf->page); return tmp; } } else { wp_page_reuse(vmf); lock_page(vmf->page); } ret |= fault_dirty_shared_page(vmf); put_page(vmf->page); return ret; } /* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus we can safely just mark it writable once we've done any necessary * COW. * * We also mark the page dirty at this point even though the page will * change only once the write actually happens. This avoids a few races, * and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; if (userfaultfd_pte_wp(vma, *vmf->pte)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) return wp_pfn_shared(vmf); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } /* * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ if (PageAnon(vmf->page)) { struct page *page = vmf->page; /* PageKsm() doesn't necessarily raise the page refcount */ if (PageKsm(page) || page_count(page) != 1) goto copy; if (!trylock_page(page)) goto copy; if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { unlock_page(page); goto copy; } /* * Ok, we've got the only map reference, and the only * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ unlock_page(page); wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); } copy: /* * Ok, we need to copy. Oh, well.. */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; vma_interval_tree_foreach(vma, root, details->first_index, details->last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; zba = details->first_index; if (zba < vba) zba = vba; zea = details->last_index; if (zea > vea) zea = vea; unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, details); } } /** * unmap_mapping_page() - Unmap single page from processes. * @page: The locked page to be unmapped. * * Unmap this page from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a page, it may find that * the page has been remapped again: and then uses unmap_mapping_page() * to unmap it finally. */ void unmap_mapping_page(struct page *page) { struct address_space *mapping = page->mapping; struct zap_details details = { }; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageTail(page)); details.check_mapping = mapping; details.first_index = page->index; details.last_index = page->index + thp_nr_pages(page) - 1; details.single_page = page; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; details.check_mapping = even_cows ? NULL : mapping; details.first_index = start; details.last_index = start + nr - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } EXPORT_SYMBOL_GPL(unmap_mapping_pages); /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * Restore a potential device exclusive pte to a working pte entry */ static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) { struct page *page = vmf->page; struct vm_area_struct *vma = vmf->vma; struct mmu_notifier_range range; /* * We need a reference to lock the page because we don't hold * the PTL so a racing thread can remove the device-exclusive * entry and unmap it. If the page is free the entry must * have been removed already. If it happens to have already * been re-allocated after being freed all we do is lock and * unlock it. */ if (!get_page_unless_zero(page)) return 0; if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) { put_page(page); return VM_FAULT_RETRY; } mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, vma->vm_mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); mmu_notifier_invalidate_range_start(&range); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) restore_exclusive_pte(vma, page, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); unlock_page(page); put_page(page); mmu_notifier_invalidate_range_end(&range); return 0; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; struct swap_info_struct *si = NULL; swp_entry_t entry; pte_t pte; int locked; int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_exclusive_entry(entry)) { vmf->page = pfn_swap_entry_to_page(entry); ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { vmf->page = pfn_swap_entry_to_page(entry); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } /* Prevent swapoff from happening to us. */ si = get_swap_device(entry); if (unlikely(!si)) goto out; delayacct_set_flag(current, DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; if (!page) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (page) { __SetPageLocked(page); __SetPageSwapBacked(page); if (mem_cgroup_swapin_charge_page(page, vma->vm_mm, GFP_KERNEL, entry)) { ret = VM_FAULT_OOM; goto out_page; } mem_cgroup_swapin_uncharge_swap(entry); shadow = get_shadow_from_swap_cache(entry); if (shadow) workingset_refault(page, shadow); lru_cache_add(page); /* To provide entry to swap_readpage() */ set_page_private(page, entry.val); swap_readpage(page, true); set_page_private(page, 0); } } else { page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); swapcache = page; } if (!page) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; } /* * Make sure try_to_free_swap or reuse_swap_page or swapoff did not * release the swapcache from under us. The page pin, and pte_same * test below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not changed. */ if (unlikely((!PageSwapCache(page) || page_private(page) != entry.val)) && swapcache) goto out_page; page = ksm_might_need_to_copy(page, vma, vmf->address); if (unlikely(!page)) { ret = VM_FAULT_OOM; page = swapcache; goto out_page; } cgroup_throttle_swaprate(page, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; if (unlikely(!PageUptodate(page))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* * The page isn't present yet, go ahead with the fault. * * Be careful about the sequence of operations here. * To get its accounting right, reuse_swap_page() must be called * while the page is counted on swap but not yet in mapcount i.e. * before page_add_anon_rmap() and swap_free(); try_to_free_swap() * must be called after the swap_free(), or it will never succeed. */ inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; exclusive = RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) { pte = pte_mkuffd_wp(pte); pte = pte_wrprotect(pte); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); vmf->orig_pte = pte; /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); } swap_free(entry); if (mem_cgroup_swap_full(page) || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (page != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the swap_free * so that the swap count won't change under a * parallel locked swapcache. */ unlock_page(swapcache); put_page(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: if (si) put_swap_device(si); return ret; out_nomap: pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); out_release: put_page(page); if (page != swapcache && swapcache) { unlock_page(swapcache); put_page(swapcache); } if (si) put_swap_device(si); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; vm_fault_t ret = 0; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(). We can't run * pte_offset_map() on pmds where a huge pmd might be created * from a different thread. * * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when * parallel threads are excluded by other means. * * Here we only have mmap_read_lock(mm). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* See comment in handle_pte_fault() */ if (unlikely(pmd_trans_unstable(vmf->pmd))) return 0; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } goto setpte; } /* Allocate our own private page. */ if (unlikely(anon_vma_prepare(vma))) goto oom; page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!page) goto oom; if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_cache(vma, vmf->address, vmf->pte); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: put_page(page); goto unlock; oom_free_page: put_page(page); oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_page_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; if (unlikely(PageHWPoison(vmf->page))) { struct page *page = vmf->page; vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { if (page_mapped(page)) unmap_mapping_pages(page_mapping(page), page->index, 1, false); /* Retry if a clean page was removed from the cache. */ if (invalidate_inode_page(page)) poisonret = VM_FAULT_NOPAGE; unlock_page(page); } put_page(page); vmf->page = NULL; return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) lock_page(vmf->page); else VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); return ret; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; int i; vm_fault_t ret = VM_FAULT_FALLBACK; if (!transhuge_vma_suitable(vma, haddr)) return ret; page = compound_head(page); if (compound_order(page) != HPAGE_PMD_ORDER) return ret; /* * Just backoff if any subpage of a THP is corrupted otherwise * the corrupted page may mapped by PMD silently to escape the * check. This kind of THP just can be PTE mapped. Access to * the corrupted subpage should trigger SIGBUS as expected. */ if (unlikely(PageHasHWPoisoned(page))) return ret; /* * Archs like ppc64 need additional space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; for (i = 0; i < HPAGE_PMD_NR; i++) flush_icache_page(vma, page + i); entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); page_add_file_rmap(page, true); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { return VM_FAULT_FALLBACK; } #endif void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; bool prefault = vmf->address != addr; pte_t entry; flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); else entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, addr, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page, false); } set_pte_at(vma->vm_mm, addr, vmf->pte, entry); } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; vm_fault_t ret; /* Did we COW the page? */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) page = vmf->cow_page; else page = vmf->page; /* * check even for read faults because we might have lost our CoWed * page */ if (!(vma->vm_flags & VM_SHARED)) { ret = check_stable_address_space(vma->vm_mm); if (ret) return ret; } if (pmd_none(*vmf->pmd)) { if (PageTransCompound(page)) { ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (vmf->prealloc_pte) { vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (likely(pmd_none(*vmf->pmd))) { mm_inc_nr_ptes(vma->vm_mm); pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } spin_unlock(vmf->ptl); } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { return VM_FAULT_OOM; } } /* * See comment in handle_pte_fault() for how this scenario happens, we * need to return NOPAGE so that we drop this page. */ if (pmd_devmap_trans_unstable(vmf->pmd)) return VM_FAULT_NOPAGE; vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); ret = 0; /* Re-check under ptl */ if (likely(pte_none(*vmf->pte))) do_set_pte(vmf, page, vmf->address); else ret = VM_FAULT_NOPAGE; update_mmu_tlb(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } static unsigned long fault_around_bytes __read_mostly = rounddown_pow_of_two(65536); #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { *val = fault_around_bytes; return 0; } /* * fault_around_bytes must be rounded down to the nearest page order as it's * what do_fault_around() expects to see. */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; if (val > PAGE_SIZE) fault_around_bytes = rounddown_pow_of_two(val); else fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, &fault_around_bytes_fops); return 0; } late_initcall(fault_around_debugfs); #endif /* * do_fault_around() tries to map few pages around the fault address. The hope * is that the pages will be needed soon and this will lower the number of * faults to handle. * * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * * This function is called with the page table lock taken. In the split ptlock * case the page table lock only protects only those entries which belong to * the page table corresponding to the fault address. * * This function doesn't cross the VMA boundaries, in order to call map_pages() * only once. * * fault_around_bytes defines how many bytes we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to * fault_around_bytes rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { unsigned long address = vmf->address, nr_pages, mask; pgoff_t start_pgoff = vmf->pgoff; pgoff_t end_pgoff; int off; nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; address = max(address & mask, vmf->vma->vm_start); off = ((vmf->address - address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); start_pgoff -= off; /* * end_pgoff is either the end of the page table, the end of * the vma or nr_pages from start_pgoff, depending what is nearest. */ end_pgoff = start_pgoff - ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, start_pgoff + nr_pages - 1); if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } return vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); } static vm_fault_t do_read_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; /* * Let's call ->map_pages() first and use ->fault() as fallback * if page by the offset is not ready to be mapped (cold cache or * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { if (likely(!userfaultfd_minor(vmf->vma))) { ret = do_fault_around(vmf); if (ret) return ret; } } ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; ret |= finish_fault(vmf); unlock_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) put_page(vmf->page); return ret; } static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!vmf->cow_page) return VM_FAULT_OOM; if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; if (ret & VM_FAULT_DONE_COW) return ret; copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma); __SetPageUptodate(vmf->cow_page); ret |= finish_fault(vmf); unlock_page(vmf->page); put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; return ret; uncharge_out: put_page(vmf->cow_page); return ret; } static vm_fault_t do_shared_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret, tmp; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; /* * Check if the backing address space wants to know that the page is * about to become writable */ if (vma->vm_ops->page_mkwrite) { unlock_page(vmf->page); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } } ret |= finish_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) { unlock_page(vmf->page); put_page(vmf->page); return ret; } ret |= fault_dirty_shared_page(vmf); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ static vm_fault_t do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *vm_mm = vma->vm_mm; vm_fault_t ret; /* * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) { /* * If we find a migration pmd entry or a none pmd entry, which * should never happen, return SIGBUS */ if (unlikely(!pmd_present(*vmf->pmd))) ret = VM_FAULT_SIGBUS; else { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * Make sure this is not a temporary clearing of pte * by holding ptl and checking again. A R/M/W update * of pte involves: take ptl, clearing the pte so that * we don't have concurrent modification by hardware * followed by an update. */ if (unlikely(pte_none(*vmf->pte))) ret = VM_FAULT_SIGBUS; else ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } return ret; } int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) { get_page(page); count_vm_numa_event(NUMA_HINT_FAULTS); if (page_nid == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; } return mpol_misplaced(page, vma, addr); } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL; int page_nid = NUMA_NO_NODE; int last_cpupid; int target_nid; pte_t pte, old_pte; bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; /* * The "pte" at this point cannot be used safely without * validation through pte_unmap_same(). It's of NUMA type but * the pfn may be screwed if the read is non atomic. */ vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* Get the normal PTE */ old_pte = ptep_get(vmf->pte); pte = pte_modify(old_pte, vma->vm_page_prot); page = vm_normal_page(vma, vmf->address, pte); if (!page) goto out_map; /* TODO: handle PTE-mapped THP */ if (PageCompound(page)) goto out_map; /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses * the case where a mapping is writable but the process never writes * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ if (!was_writable) flags |= TNF_NO_GROUP; /* * Flag if the page is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; last_cpupid = page_cpupid_last(page); page_nid = page_to_nid(page); target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); if (target_nid == NUMA_NO_NODE) { put_page(page); goto out_map; } pte_unmap_unlock(vmf->pte, vmf->ptl); /* Migrate to the requested node */ if (migrate_misplaced_page(page, vma, target_nid)) { page_nid = target_nid; flags |= TNF_MIGRATED; task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } flags |= TNF_MIGRATE_FAIL; vmf->pte = pte_offset_map(vmf->pmd, vmf->address); spin_lock(vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } out_map: /* * Make it present again, depending on how arch implements * non-accessible ptes, some can allow access by kernel mode. */ old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_anonymous_page(vmf); if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); return VM_FAULT_FALLBACK; } /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) { if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); return do_huge_pmd_wp_page(vmf); } if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } static vm_fault_t create_huge_pud(struct vm_fault *vmf) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) return VM_FAULT_FALLBACK; if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) goto split; if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vmf->vma, vmf->pud, vmf->address); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. * * There is also a hook called "update_mmu_cache()" that architectures * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. * See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table * for an instant, it will be difficult to retract from * concurrent faults and from rmap lookups. */ vmf->pte = NULL; } else { /* * If a huge pmd materialized under us just retry later. Use * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead * of pmd_trans_huge() to ensure the pmd didn't become * pmd_trans_huge under us and then back to pmd_none, as a * result of MADV_DONTNEED running immediately after a huge pmd * fault in a different thread of this mm, in turn leading to a * misleading pmd_trans_huge() retval. All we have to ensure is * that it is a regular pmd that we can walk with * pte_offset_map() and we can do that through an atomic read * in C, which is what pmd_trans_unstable() provides. */ if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; /* * A regular pmd is established and it can't morph into a huge * pmd from under us anymore at this point because we hold the * mmap_lock read mode and khugepaged takes it in write mode. * So now it's safe to run pte_offset_map(). */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; /* * some architectures can have larger ptes than wordsize, * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and * CONFIG_32BIT=y, so READ_ONCE cannot guarantee atomic * accesses. The code below just needs a consistent view * for the ifs and we later double check anyway with the * ptl lock held. So here a barrier will do. */ barrier(); if (pte_none(vmf->orig_pte)) { pte_unmap(vmf->pte); vmf->pte = NULL; } } if (!vmf->pte) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); else return do_fault(vmf); } if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); entry = vmf->orig_pte; if (unlikely(!pte_same(*vmf->pte, entry))) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } if (vmf->flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) return do_wp_page(vmf); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { /* Skip spurious TLB flush for retried page fault */ if (vmf->flags & FAULT_FLAG_TRIED) goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. * This still avoids useless tlb flushes for .text page faults * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) flush_tlb_fix_spurious_fault(vmf->vma, vmf->address); } unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { struct vm_fault vmf = { .vma = vma, .address = address & PAGE_MASK, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return VM_FAULT_OOM; vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pud_t orig_pud = *vmf.pud; barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { /* NUMA case for anonymous PUDs would go here */ if (dirty && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pud_set_accessed(&vmf, orig_pud); return 0; } } } vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; /* Huge pud page fault raced with pmd_alloc? */ if (pud_trans_unstable(vmf.pud)) goto retry_pud; if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { vmf.orig_pmd = *vmf.pmd; barrier(); if (unlikely(is_swap_pmd(vmf.orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(vmf.orig_pmd)); if (is_pmd_migration_entry(vmf.orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) { if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf); if (dirty && !pmd_write(vmf.orig_pmd)) { ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pmd_set_accessed(&vmf); return 0; } } } return handle_pte_fault(&vmf); } /** * mm_account_fault - Do page fault accounting * * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to * the task who triggered this page fault. * @address: the faulted address. * @flags: the fault flags. * @ret: the fault retcode. * * This will take care of most of the page fault accounting. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter * updates. However, note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; /* * We don't do accounting for some specific faults: * * - Unsuccessful faults (e.g. when the address wasn't valid). That * includes arch_vma_access_permitted() failing before reaching here. * So this is not a "this many hardware page faults" counter. We * should use the hw profiling for that. * * - Incomplete faults (VM_FAULT_RETRY). They will only be counted * once they're completed. */ if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) return; /* * We define the fault as a major fault when the final successful fault * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't * handle it immediately previously). */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); if (major) current->maj_flt++; else current->min_flt++; /* * If the fault is done for GUP, regs will be NULL. We only do the * accounting for the per thread fault counters who triggered the * fault, and we skip the perf event updates. */ if (!regs) return; if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { vm_fault_t ret; __set_current_state(TASK_RUNNING); count_vm_event(PGFAULT); count_memcg_event_mm(vma->vm_mm, PGFAULT); /* do counter updates before entering really critical section. */ check_sync_rss_stat(current); if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) return VM_FAULT_SIGSEGV; /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); if (unlikely(is_vm_hugetlb_page(vma))) ret = hugetlb_fault(vma->vm_mm, vma, address, flags); else ret = __handle_mm_fault(vma, address, flags); if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* * The task may have entered a memcg OOM situation but * if the allocation error was handled gracefully (no * VM_FAULT_OOM), there is no need to kill anything. * Just clean up the OOM state peacefully. */ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } mm_account_fault(regs, address, flags, ret); return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. * We've already handled the fast-path in-line. */ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { p4d_t *new = p4d_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) /* Another has populated it */ p4d_free(mm, new); else pgd_populate(mm, pgd, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_P4D_FOLDED */ #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. * We've already handled the fast-path in-line. */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); } else /* Another has populated it */ pmd_free(mm, new); spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) goto out; pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); if (pmd_huge(*pmd)) { if (!pmdpp) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PMD_MASK, (address & PMD_MASK) + PMD_SIZE); mmu_notifier_invalidate_range_start(range); } *ptlp = pmd_lock(mm, pmd); if (pmd_huge(*pmd)) { *pmdpp = pmd; return 0; } spin_unlock(*ptlp); if (range) mmu_notifier_invalidate_range_end(range); } if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PAGE_MASK, (address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(range); } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; *ptepp = ptep; return 0; unlock: pte_unmap_unlock(ptep, *ptlp); if (range) mmu_notifier_invalidate_range_end(range); out: return -EINVAL; } /** * follow_pte - look up PTE at a user virtual address * @mm: the mm_struct of the target address space * @address: user virtual address * @ptepp: location to store found PTE * @ptlp: location to store the lock for the PTE * * On a successful return, the pointer to the PTE is stored in @ptepp; * the corresponding lock is taken and its location is stored in @ptlp. * The contents of the PTE are only stable until @ptlp is released; * any further use, if any, must be protected against invalidation * with MMU notifiers. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read. * * KVM uses this function. While it is arguably less bad than ``follow_pfn``, * it is not a good general-purpose API. * * Return: zero on success, -ve otherwise. */ int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp) { return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); } EXPORT_SYMBOL_GPL(follow_pte); /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping * @address: user virtual address * @pfn: location to store found PFN * * Only IO mappings and raw PFN mappings are allowed. * * This function does not allow the caller to read the permissions * of the PTE. Do not use it. * * Return: zero and the pfn at @pfn on success, -ve otherwise. */ int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn) { int ret = -EINVAL; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) return ret; ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); if (ret) return ret; *pfn = pte_pfn(*ptep); pte_unmap_unlock(ptep, ptl); return 0; } EXPORT_SYMBOL(follow_pfn); #ifdef CONFIG_HAVE_IOREMAP_PROT int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys) { int ret = -EINVAL; pte_t *ptep, pte; spinlock_t *ptl; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out; if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) goto out; pte = *ptep; /* Never return PFNs of anon folios in COW mappings. */ if (vm_normal_page(vma, address, pte)) goto unlock; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; *prot = pgprot_val(pte_pgprot(pte)); *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: return ret; } /** * generic_access_phys - generic implementation for iomem mmap access * @vma: the vma to access * @addr: userspace address, not relative offset within @vma * @buf: buffer to read/write * @len: length of transfer * @write: set to FOLL_WRITE when writing, otherwise reading * * This is a generic implementation for &vm_operations_struct.access for an * iomem mapping. This callback is used by access_process_vm() when the @vma is * not page based. */ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; unsigned long prot = 0; void __iomem *maddr; pte_t *ptep, pte; spinlock_t *ptl; int offset = offset_in_page(addr); int ret = -EINVAL; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) return -EINVAL; retry: if (follow_pte(vma->vm_mm, addr, &ptep, &ptl)) return -EINVAL; pte = *ptep; pte_unmap_unlock(ptep, ptl); prot = pgprot_val(pte_pgprot(pte)); phys_addr = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; if ((write & FOLL_WRITE) && !pte_write(pte)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; if (follow_pte(vma->vm_mm, addr, &ptep, &ptl)) goto out_unmap; if (!pte_same(pte, *ptep)) { pte_unmap_unlock(ptep, ptl); iounmap(maddr); goto retry; } if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); ret = len; pte_unmap_unlock(ptep, ptl); out_unmap: iounmap(maddr); return ret; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* * Access another process' address space as given in mm. */ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct vm_area_struct *vma; void *old_buf = buf; int write = gup_flags & FOLL_WRITE; if (mmap_read_lock_killable(mm)) return 0; /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, ret, offset; void *maddr; struct page *page = NULL; ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT break; #else /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ vma = vma_lookup(mm, addr); if (!vma) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, len, write); if (ret <= 0) break; bytes = ret; #endif } else { bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; maddr = kmap(page); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); set_page_dirty_lock(page); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } kunmap(page); put_page(page); } len -= bytes; buf += bytes; addr += bytes; } mmap_read_unlock(mm); return buf - old_buf; } /** * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { return __access_remote_vm(mm, addr, buf, len, gup_flags); } /* * Access another process' address space. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = __access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(access_process_vm); /* * Print the name of a VMA. */ void print_vma_addr(char *prefix, unsigned long ip) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; /* * we might be running from an atomic context so we cannot sleep */ if (!mmap_read_trylock(mm)) return; vma = find_vma(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; char *buf = (char *)__get_free_page(GFP_NOWAIT); if (buf) { char *p; p = file_path(f, buf, PAGE_SIZE); if (IS_ERR(p)) p = "?"; printk("%s%s[%lx+%lx]", prefix, kbasename(p), vma->vm_start, vma->vm_end - vma->vm_start); free_page((unsigned long)buf); } } mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void __might_fault(const char *file, int line) { /* * Some code (nfs/sunrpc) uses socket ops on kernel memory while * holding the mmap_lock, this is safe because kernel memory doesn't * get paged out, therefore we'll never actually fault, and the * below annotations will generate false positives. */ if (uaccess_kernel()) return; if (pagefault_disabled()) return; __might_sleep(file, line, 0); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); #endif } EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) /* * Process all subpages of the specified huge page with the specified * operation. The target subpage will be processed last to keep its * cache lines hot. */ static inline void process_huge_page( unsigned long addr_hint, unsigned int pages_per_huge_page, void (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { int i, n, base, l; unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); /* Process target subpage last to keep its cache lines hot */ might_sleep(); n = (addr_hint - addr) / PAGE_SIZE; if (2 * n <= pages_per_huge_page) { /* If target subpage in first half of huge page */ base = 0; l = n; /* Process subpages at the end of huge page */ for (i = pages_per_huge_page - 1; i >= 2 * n; i--) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } else { /* If target subpage in second half of huge page */ base = pages_per_huge_page - 2 * (pages_per_huge_page - n); l = pages_per_huge_page - n; /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } /* * Process remaining subpages in left-right-left-right pattern * towards the target subpage */ for (i = 0; i < l; i++) { int left_idx = base + i; int right_idx = base + 2 * l - 1 - i; cond_resched(); process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); cond_resched(); process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); } } static void clear_gigantic_page(struct page *page, unsigned long addr, unsigned int pages_per_huge_page) { int i; struct page *p = page; might_sleep(); for (i = 0; i < pages_per_huge_page; i++, p = mem_map_next(p, page, i)) { cond_resched(); clear_user_highpage(p, addr + i * PAGE_SIZE); } } static void clear_subpage(unsigned long addr, int idx, void *arg) { struct page *page = arg; clear_user_highpage(page + idx, addr); } void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { clear_gigantic_page(page, addr, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page); } static void copy_user_gigantic_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { int i; struct page *dst_base = dst; struct page *src_base = src; for (i = 0; i < pages_per_huge_page; ) { cond_resched(); copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); i++; dst = mem_map_next(dst, dst_base, i); src = mem_map_next(src, src_base, i); } } struct copy_subpage_arg { struct page *dst; struct page *src; struct vm_area_struct *vma; }; static void copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; copy_user_highpage(copy_arg->dst + idx, copy_arg->src + idx, addr, copy_arg->vma); } void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); struct copy_subpage_arg arg = { .dst = dst, .src = src, .vma = vma, }; if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { copy_user_gigantic_page(dst, src, addr, vma, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); } long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, unsigned int pages_per_huge_page, bool allow_pagefault) { void *src = (void *)usr_src; void *page_kaddr; unsigned long i, rc = 0; unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; struct page *subpage = dst_page; for (i = 0; i < pages_per_huge_page; i++, subpage = mem_map_next(subpage, dst_page, i)) { if (allow_pagefault) page_kaddr = kmap(subpage); else page_kaddr = kmap_atomic(subpage); rc = copy_from_user(page_kaddr, (const void __user *)(src + i * PAGE_SIZE), PAGE_SIZE); if (allow_pagefault) kunmap(subpage); else kunmap_atomic(page_kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) break; flush_dcache_page(subpage); cond_resched(); } return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; void __init ptlock_cache_init(void) { page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, SLAB_PANIC, NULL); } bool ptlock_alloc(struct page *page) { spinlock_t *ptl; ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; page->ptl = ptl; return true; } void ptlock_free(struct page *page) { kmem_cache_free(page_ptl_cachep, page->ptl); } #endif |
| 46 711 811 48 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_NULLS_H #define _LINUX_LIST_NULLS_H #include <linux/poison.h> #include <linux/const.h> /* * Special version of lists, where end of list is not a NULL pointer, * but a 'nulls' marker, which can have many different values. * (up to 2^31 different values guaranteed on all platforms) * * In the standard hlist, termination of a list is the NULL pointer. * In this special 'nulls' variant, we use the fact that objects stored in * a list are aligned on a word (4 or 8 bytes alignment). * We therefore use the last significant bit of 'ptr' : * Set to 1 : This is a 'nulls' end-of-list marker (ptr >> 1) * Set to 0 : This is a pointer to some object (ptr) */ struct hlist_nulls_head { struct hlist_nulls_node *first; }; struct hlist_nulls_node { struct hlist_nulls_node *next, **pprev; }; #define NULLS_MARKER(value) (1UL | (((long)value) << 1)) #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \ ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_nulls_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ }) /** * ptr_is_a_nulls - Test if a ptr is a nulls * @ptr: ptr to be tested * */ static inline int is_a_nulls(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr & 1); } /** * get_nulls_value - Get the 'nulls' value of the end of chain * @ptr: end of chain * * Should be called only if is_a_nulls(ptr); */ static inline unsigned long get_nulls_value(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr) >> 1; } /** * hlist_nulls_unhashed - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. */ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) { return !h->pprev; } /** * hlist_nulls_unhashed_lockless - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. Unlike hlist_nulls_unhashed(), this * function may be used locklessly. */ static inline int hlist_nulls_unhashed_lockless(const struct hlist_nulls_node *h) { return !READ_ONCE(h->pprev); } static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); h->first = n; if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } static inline void __hlist_nulls_del(struct hlist_nulls_node *n) { struct hlist_nulls_node *next = n->next; struct hlist_nulls_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) WRITE_ONCE(next->pprev, pprev); } static inline void hlist_nulls_del(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry(tpos, pos, head, member) \ for (pos = (head)->first; \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_nulls_for_each_entry_from - iterate over a hlist continuing from current point * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry_from(tpos, pos, member) \ for (; (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) #endif |
| 13 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kernfs.h - pseudo filesystem decoupled from vfs locking */ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H #include <linux/kernel.h> #include <linux/err.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/idr.h> #include <linux/lockdep.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/wait.h> struct file; struct dentry; struct iattr; struct seq_file; struct vm_area_struct; struct super_block; struct file_system_type; struct poll_table_struct; struct fs_context; struct kernfs_fs_context; struct kernfs_open_node; struct kernfs_iattrs; enum kernfs_node_type { KERNFS_DIR = 0x0001, KERNFS_FILE = 0x0002, KERNFS_LINK = 0x0004, }; #define KERNFS_TYPE_MASK 0x000f #define KERNFS_FLAG_MASK ~KERNFS_TYPE_MASK #define KERNFS_MAX_USER_XATTRS 128 #define KERNFS_USER_XATTR_SIZE_LIMIT (128 << 10) enum kernfs_node_flag { KERNFS_ACTIVATED = 0x0010, KERNFS_NS = 0x0020, KERNFS_HAS_SEQ_SHOW = 0x0040, KERNFS_HAS_MMAP = 0x0080, KERNFS_LOCKDEP = 0x0100, KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, KERNFS_HAS_RELEASE = 0x2000, }; /* @flags for kernfs_create_root() */ enum kernfs_root_flag { /* * kernfs_nodes are created in the deactivated state and invisible. * They require explicit kernfs_activate() to become visible. This * can be used to make related nodes become visible atomically * after all nodes are created successfully. */ KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001, /* * For regular files, if the opener has CAP_DAC_OVERRIDE, open(2) * succeeds regardless of the RW permissions. sysfs had an extra * layer of enforcement where open(2) fails with -EACCES regardless * of CAP_DAC_OVERRIDE if the permission doesn't have the * respective read or write access at all (none of S_IRUGO or * S_IWUGO) or the respective operation isn't implemented. The * following flag enables that behavior. */ KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK = 0x0002, /* * The filesystem supports exportfs operation, so userspace can use * fhandle to access nodes of the fs. */ KERNFS_ROOT_SUPPORT_EXPORTOP = 0x0004, /* * Support user xattrs to be written to nodes rooted at this root. */ KERNFS_ROOT_SUPPORT_USER_XATTR = 0x0008, }; /* type-specific structures for kernfs_node union members */ struct kernfs_elem_dir { unsigned long subdirs; /* children rbtree starts here and goes through kn->rb */ struct rb_root children; /* * The kernfs hierarchy this directory belongs to. This fits * better directly in kernfs_node but is here to save space. */ struct kernfs_root *root; /* * Monotonic revision counter, used to identify if a directory * node has changed during negative dentry revalidation. */ unsigned long rev; }; struct kernfs_elem_symlink { struct kernfs_node *target_kn; }; struct kernfs_elem_attr { const struct kernfs_ops *ops; struct kernfs_open_node *open; loff_t size; struct kernfs_node *notify_next; /* for kernfs_notify() */ }; /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are * private to kernfs and shouldn't be accessed directly by kernfs users. * * As long as count reference is held, the kernfs_node itself is * accessible. Dereferencing elem or any other outer entity requires * active reference. */ struct kernfs_node { atomic_t count; atomic_t active; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* * Use kernfs_get_parent() and kernfs_name/path() instead of * accessing the following two fields directly. If the node is * never moved to a different parent, it is safe to access the * parent directly. */ struct kernfs_node *parent; const char *name; struct rb_node rb; const void *ns; /* namespace tag */ unsigned int hash; /* ns + name hash */ union { struct kernfs_elem_dir dir; struct kernfs_elem_symlink symlink; struct kernfs_elem_attr attr; }; void *priv; /* * 64bit unique ID. On 64bit ino setups, id is the ino. On 32bit, * the low 32bits are ino and upper generation. */ u64 id; unsigned short flags; umode_t mode; struct kernfs_iattrs *iattr; }; /* * kernfs_syscall_ops may be specified on kernfs_create_root() to support * syscalls. These optional callbacks are invoked on the matching syscalls * and can perform any kernfs operations which don't necessarily have to be * the exact operation requested. An active reference is held for each * kernfs_node parameter. */ struct kernfs_syscall_ops { int (*show_options)(struct seq_file *sf, struct kernfs_root *root); int (*mkdir)(struct kernfs_node *parent, const char *name, umode_t mode); int (*rmdir)(struct kernfs_node *kn); int (*rename)(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name); int (*show_path)(struct seq_file *sf, struct kernfs_node *kn, struct kernfs_root *root); }; struct kernfs_root { /* published fields */ struct kernfs_node *kn; unsigned int flags; /* KERNFS_ROOT_* flags */ /* private fields, do not use outside kernfs proper */ struct idr ino_idr; u32 last_id_lowbits; u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_rwsem */ struct list_head supers; wait_queue_head_t deactivate_waitq; }; struct kernfs_open_file { /* published fields */ struct kernfs_node *kn; struct file *file; struct seq_file *seq_file; void *priv; /* private fields, do not use outside kernfs proper */ struct mutex mutex; struct mutex prealloc_mutex; int event; struct list_head list; char *prealloc_buf; size_t atomic_write_len; bool mmapped:1; bool released:1; const struct vm_operations_struct *vm_ops; }; struct kernfs_ops { /* * Optional open/release methods. Both are called with * @of->seq_file populated. */ int (*open)(struct kernfs_open_file *of); void (*release)(struct kernfs_open_file *of); /* * Read is handled by either seq_file or raw_read(). * * If seq_show() is present, seq_file path is active. Other seq * operations are optional and if not implemented, the behavior is * equivalent to single_open(). @sf->private points to the * associated kernfs_open_file. * * read() is bounced through kernel buffer and a read larger than * PAGE_SIZE results in partial operation of PAGE_SIZE. */ int (*seq_show)(struct seq_file *sf, void *v); void *(*seq_start)(struct seq_file *sf, loff_t *ppos); void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); void (*seq_stop)(struct seq_file *sf, void *v); ssize_t (*read)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); /* * write() is bounced through kernel buffer. If atomic_write_len * is not set, a write larger than PAGE_SIZE results in partial * operations of PAGE_SIZE chunks. If atomic_write_len is set, * writes upto the specified size are executed atomically but * larger ones are rejected with -E2BIG. */ size_t atomic_write_len; /* * "prealloc" causes a buffer to be allocated at open for * all read/write requests. As ->seq_show uses seq_read() * which does its own allocation, it is incompatible with * ->prealloc. Provide ->read and ->write with ->prealloc. */ bool prealloc; ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; #endif }; /* * The kernfs superblock creation/mount parameter context. */ struct kernfs_fs_context { struct kernfs_root *root; /* Root of the hierarchy being mounted */ void *ns_tag; /* Namespace tag of the mount (or NULL) */ unsigned long magic; /* File system specific magic number */ /* The following are set/used by kernfs_mount() */ bool new_sb_created; /* Set to T if we allocated a new sb */ }; #ifdef CONFIG_KERNFS static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) { return kn->flags & KERNFS_TYPE_MASK; } static inline ino_t kernfs_id_ino(u64 id) { /* id is ino if ino_t is 64bit; otherwise, low 32bits */ if (sizeof(ino_t) >= sizeof(u64)) return id; else return (u32)id; } static inline u32 kernfs_id_gen(u64 id) { /* gen is fixed at 1 if ino_t is 64bit; otherwise, high 32bits */ if (sizeof(ino_t) >= sizeof(u64)) return 1; else return id >> 32; } static inline ino_t kernfs_ino(struct kernfs_node *kn) { return kernfs_id_ino(kn->id); } static inline ino_t kernfs_gen(struct kernfs_node *kn) { return kernfs_id_gen(kn->id); } /** * kernfs_enable_ns - enable namespace under a directory * @kn: directory of interest, should be empty * * This is to be called right after @kn is created to enable namespace * under it. All children of @kn must have non-NULL namespace tags and * only the ones which match the super_block's tag will be visible. */ static inline void kernfs_enable_ns(struct kernfs_node *kn) { WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR); WARN_ON_ONCE(!RB_EMPTY_ROOT(&kn->dir.children)); kn->flags |= KERNFS_NS; } /** * kernfs_ns_enabled - test whether namespace is enabled * @kn: the node to test * * Test whether namespace filtering is enabled for the children of @ns. */ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) { return kn->flags & KERNFS_NS; } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); void pr_cont_kernfs_path(struct kernfs_node *kn); struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn); struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns); struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns); void kernfs_get(struct kernfs_node *kn); void kernfs_put(struct kernfs_node *kn); struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); struct dentry *kernfs_node_dentry(struct kernfs_node *kn, struct super_block *sb); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); void kernfs_destroy_root(struct kernfs_root *root); struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns); struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name); struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key); struct kernfs_node *kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target); void kernfs_activate(struct kernfs_node *kn); void kernfs_remove(struct kernfs_node *kn); void kernfs_break_active_protection(struct kernfs_node *kn); void kernfs_unbreak_active_protection(struct kernfs_node *kn); bool kernfs_remove_self(struct kernfs_node *kn); int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns); int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); __poll_t kernfs_generic_poll(struct kernfs_open_file *of, struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn); int kernfs_xattr_get(struct kernfs_node *kn, const char *name, void *value, size_t size); int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags); const void *kernfs_super_ns(struct super_block *sb); int kernfs_get_tree(struct fs_context *fc); void kernfs_free_fs_context(struct fs_context *fc); void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) { return 0; } /* whatever */ static inline void kernfs_enable_ns(struct kernfs_node *kn) { } static inline bool kernfs_ns_enabled(struct kernfs_node *kn) { return false; } static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } static inline int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { } static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { } static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { return NULL; } static inline struct kernfs_node * kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { return NULL; } static inline struct kernfs_node * kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns) { return NULL; } static inline void kernfs_get(struct kernfs_node *kn) { } static inline void kernfs_put(struct kernfs_node *kn) { } static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { return NULL; } static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) { return NULL; } static inline struct inode * kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) { return NULL; } static inline struct kernfs_root * kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) { return ERR_PTR(-ENOSYS); } static inline void kernfs_destroy_root(struct kernfs_root *root) { } static inline struct kernfs_node * kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const void *ns) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * __kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { return ERR_PTR(-ENOSYS); } static inline struct kernfs_node * kernfs_create_link(struct kernfs_node *parent, const char *name, struct kernfs_node *target) { return ERR_PTR(-ENOSYS); } static inline void kernfs_activate(struct kernfs_node *kn) { } static inline void kernfs_remove(struct kernfs_node *kn) { } static inline bool kernfs_remove_self(struct kernfs_node *kn) { return false; } static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn, const char *name, const void *ns) { return -ENOSYS; } static inline int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { return -ENOSYS; } static inline int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { return -ENOSYS; } static inline void kernfs_notify(struct kernfs_node *kn) { } static inline int kernfs_xattr_get(struct kernfs_node *kn, const char *name, void *value, size_t size) { return -ENOSYS; } static inline int kernfs_xattr_set(struct kernfs_node *kn, const char *name, const void *value, size_t size, int flags) { return -ENOSYS; } static inline const void *kernfs_super_ns(struct super_block *sb) { return NULL; } static inline int kernfs_get_tree(struct fs_context *fc) { return -ENOSYS; } static inline void kernfs_free_fs_context(struct fs_context *fc) { } static inline void kernfs_kill_sb(struct super_block *sb) { } static inline void kernfs_init(void) { } #endif /* CONFIG_KERNFS */ /** * kernfs_path - build full path of a given node * @kn: kernfs_node of interest * @buf: buffer to copy @kn's name into * @buflen: size of @buf * * If @kn is NULL result will be "(null)". * * Returns the length of the full path. If the full length is equal to or * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ static inline int kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { return kernfs_path_from_node(kn, NULL, buf, buflen); } static inline struct kernfs_node * kernfs_find_and_get(struct kernfs_node *kn, const char *name) { return kernfs_find_and_get_ns(kn, name, NULL); } static inline struct kernfs_node * kernfs_walk_and_get(struct kernfs_node *kn, const char *path) { return kernfs_walk_and_get_ns(kn, path, NULL); } static inline struct kernfs_node * kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode, void *priv) { return kernfs_create_dir_ns(parent, name, mode, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, priv, NULL); } static inline struct kernfs_node * kernfs_create_file_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns) { struct lock_class_key *key = NULL; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = (struct lock_class_key *)&ops->lockdep_key; #endif return __kernfs_create_file(parent, name, mode, uid, gid, size, ops, priv, ns, key); } static inline struct kernfs_node * kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, loff_t size, const struct kernfs_ops *ops, void *priv) { return kernfs_create_file_ns(parent, name, mode, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, size, ops, priv, NULL); } static inline int kernfs_remove_by_name(struct kernfs_node *parent, const char *name) { return kernfs_remove_by_name_ns(parent, name, NULL); } static inline int kernfs_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name) { return kernfs_rename_ns(kn, new_parent, new_name, NULL); } #endif /* __LINUX_KERNFS_H */ |
| 54 54 54 54 54 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_app.c: Application module support for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * Most code here is taken from ip_masq_app.c in kernel 2.2. The difference * is that ip_vs_app module handles the reverse direction (incoming requests * and outgoing responses). * * IP_MASQ_APP application masquerading module * * Author: Juan Jose Ciarlante, <jjciarla@raiz.uncu.edu.ar> */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/netfilter.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/tcp.h> #include <linux/stat.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mutex.h> #include <net/ip_vs.h> EXPORT_SYMBOL(register_ip_vs_app); EXPORT_SYMBOL(unregister_ip_vs_app); EXPORT_SYMBOL(register_ip_vs_app_inc); static DEFINE_MUTEX(__ip_vs_app_mutex); /* * Get an ip_vs_app object */ static inline int ip_vs_app_get(struct ip_vs_app *app) { return try_module_get(app->module); } static inline void ip_vs_app_put(struct ip_vs_app *app) { module_put(app->module); } static void ip_vs_app_inc_destroy(struct ip_vs_app *inc) { kfree(inc->timeout_table); kfree(inc); } static void ip_vs_app_inc_rcu_free(struct rcu_head *head) { struct ip_vs_app *inc = container_of(head, struct ip_vs_app, rcu_head); ip_vs_app_inc_destroy(inc); } /* * Allocate/initialize app incarnation and register it in proto apps. */ static int ip_vs_app_inc_new(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, __u16 port) { struct ip_vs_protocol *pp; struct ip_vs_app *inc; int ret; if (!(pp = ip_vs_proto_get(proto))) return -EPROTONOSUPPORT; if (!pp->unregister_app) return -EOPNOTSUPP; inc = kmemdup(app, sizeof(*inc), GFP_KERNEL); if (!inc) return -ENOMEM; INIT_LIST_HEAD(&inc->p_list); INIT_LIST_HEAD(&inc->incs_list); inc->app = app; inc->port = htons(port); atomic_set(&inc->usecnt, 0); if (app->timeouts) { inc->timeout_table = ip_vs_create_timeout_table(app->timeouts, app->timeouts_size); if (!inc->timeout_table) { ret = -ENOMEM; goto out; } } ret = pp->register_app(ipvs, inc); if (ret) goto out; list_add(&inc->a_list, &app->incs_list); IP_VS_DBG(9, "%s App %s:%u registered\n", pp->name, inc->name, ntohs(inc->port)); return 0; out: ip_vs_app_inc_destroy(inc); return ret; } /* * Release app incarnation */ static void ip_vs_app_inc_release(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_protocol *pp; if (!(pp = ip_vs_proto_get(inc->protocol))) return; if (pp->unregister_app) pp->unregister_app(ipvs, inc); IP_VS_DBG(9, "%s App %s:%u unregistered\n", pp->name, inc->name, ntohs(inc->port)); list_del(&inc->a_list); call_rcu(&inc->rcu_head, ip_vs_app_inc_rcu_free); } /* * Get reference to app inc (only called from softirq) * */ int ip_vs_app_inc_get(struct ip_vs_app *inc) { int result; result = ip_vs_app_get(inc->app); if (result) atomic_inc(&inc->usecnt); return result; } /* * Put the app inc (only called from timer or net softirq) */ void ip_vs_app_inc_put(struct ip_vs_app *inc) { atomic_dec(&inc->usecnt); ip_vs_app_put(inc->app); } /* * Register an application incarnation in protocol applications */ int register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, __u16 port) { int result; mutex_lock(&__ip_vs_app_mutex); result = ip_vs_app_inc_new(ipvs, app, proto, port); mutex_unlock(&__ip_vs_app_mutex); return result; } /* Register application for netns */ struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app) { struct ip_vs_app *a; int err = 0; mutex_lock(&__ip_vs_app_mutex); /* increase the module use count */ if (!ip_vs_use_count_inc()) { err = -ENOENT; goto out_unlock; } list_for_each_entry(a, &ipvs->app_list, a_list) { if (!strcmp(app->name, a->name)) { err = -EEXIST; /* decrease the module use count */ ip_vs_use_count_dec(); goto out_unlock; } } a = kmemdup(app, sizeof(*app), GFP_KERNEL); if (!a) { err = -ENOMEM; /* decrease the module use count */ ip_vs_use_count_dec(); goto out_unlock; } INIT_LIST_HEAD(&a->incs_list); list_add(&a->a_list, &ipvs->app_list); out_unlock: mutex_unlock(&__ip_vs_app_mutex); return err ? ERR_PTR(err) : a; } /* * ip_vs_app unregistration routine * We are sure there are no app incarnations attached to services * Caller should use synchronize_rcu() or rcu_barrier() */ void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app) { struct ip_vs_app *a, *anxt, *inc, *nxt; mutex_lock(&__ip_vs_app_mutex); list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) { if (app && strcmp(app->name, a->name)) continue; list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) { ip_vs_app_inc_release(ipvs, inc); } list_del(&a->a_list); kfree(a); /* decrease the module use count */ ip_vs_use_count_dec(); } mutex_unlock(&__ip_vs_app_mutex); } /* * Bind ip_vs_conn to its ip_vs_app (called by cp constructor) */ int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp) { return pp->app_conn_bind(cp); } /* * Unbind cp from application incarnation (called by cp destructor) */ void ip_vs_unbind_app(struct ip_vs_conn *cp) { struct ip_vs_app *inc = cp->app; if (!inc) return; if (inc->unbind_conn) inc->unbind_conn(inc, cp); if (inc->done_conn) inc->done_conn(inc, cp); ip_vs_app_inc_put(inc); cp->app = NULL; } /* * Fixes th->seq based on ip_vs_seq info. */ static inline void vs_fix_seq(const struct ip_vs_seq *vseq, struct tcphdr *th) { __u32 seq = ntohl(th->seq); /* * Adjust seq with delta-offset for all packets after * the most recent resized pkt seq and with previous_delta offset * for all packets before most recent resized pkt seq. */ if (vseq->delta || vseq->previous_delta) { if(after(seq, vseq->init_seq)) { th->seq = htonl(seq + vseq->delta); IP_VS_DBG(9, "%s(): added delta (%d) to seq\n", __func__, vseq->delta); } else { th->seq = htonl(seq + vseq->previous_delta); IP_VS_DBG(9, "%s(): added previous_delta (%d) to seq\n", __func__, vseq->previous_delta); } } } /* * Fixes th->ack_seq based on ip_vs_seq info. */ static inline void vs_fix_ack_seq(const struct ip_vs_seq *vseq, struct tcphdr *th) { __u32 ack_seq = ntohl(th->ack_seq); /* * Adjust ack_seq with delta-offset for * the packets AFTER most recent resized pkt has caused a shift * for packets before most recent resized pkt, use previous_delta */ if (vseq->delta || vseq->previous_delta) { /* since ack_seq is the number of octet that is expected to receive next, so compare it with init_seq+delta */ if(after(ack_seq, vseq->init_seq+vseq->delta)) { th->ack_seq = htonl(ack_seq - vseq->delta); IP_VS_DBG(9, "%s(): subtracted delta " "(%d) from ack_seq\n", __func__, vseq->delta); } else { th->ack_seq = htonl(ack_seq - vseq->previous_delta); IP_VS_DBG(9, "%s(): subtracted " "previous_delta (%d) from ack_seq\n", __func__, vseq->previous_delta); } } } /* * Updates ip_vs_seq if pkt has been resized * Assumes already checked proto==IPPROTO_TCP and diff!=0. */ static inline void vs_seq_update(struct ip_vs_conn *cp, struct ip_vs_seq *vseq, unsigned int flag, __u32 seq, int diff) { /* spinlock is to keep updating cp->flags atomic */ spin_lock_bh(&cp->lock); if (!(cp->flags & flag) || after(seq, vseq->init_seq)) { vseq->previous_delta = vseq->delta; vseq->delta += diff; vseq->init_seq = seq; cp->flags |= flag; } spin_unlock_bh(&cp->lock); } static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, struct ip_vs_app *app, struct ip_vs_iphdr *ipvsh) { int diff; const unsigned int tcp_offset = ip_hdrlen(skb); struct tcphdr *th; __u32 seq; if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) return 0; th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); /* * Remember seq number in case this pkt gets resized */ seq = ntohl(th->seq); /* * Fix seq stuff if flagged as so. */ if (cp->flags & IP_VS_CONN_F_OUT_SEQ) vs_fix_seq(&cp->out_seq, th); if (cp->flags & IP_VS_CONN_F_IN_SEQ) vs_fix_ack_seq(&cp->in_seq, th); /* * Call private output hook function */ if (app->pkt_out == NULL) return 1; if (!app->pkt_out(app, cp, skb, &diff, ipvsh)) return 0; /* * Update ip_vs seq stuff if len has changed. */ if (diff != 0) vs_seq_update(cp, &cp->out_seq, IP_VS_CONN_F_OUT_SEQ, seq, diff); return 1; } /* * Output pkt hook. Will call bound ip_vs_app specific function * called by ipvs packet handler, assumes previously checked cp!=NULL * returns false if it can't handle packet (oom) */ int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) { struct ip_vs_app *app; /* * check if application module is bound to * this ip_vs_conn. */ if ((app = cp->app) == NULL) return 1; /* TCP is complicated */ if (cp->protocol == IPPROTO_TCP) return app_tcp_pkt_out(cp, skb, app, ipvsh); /* * Call private output hook function */ if (app->pkt_out == NULL) return 1; return app->pkt_out(app, cp, skb, NULL, ipvsh); } static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, struct ip_vs_app *app, struct ip_vs_iphdr *ipvsh) { int diff; const unsigned int tcp_offset = ip_hdrlen(skb); struct tcphdr *th; __u32 seq; if (skb_ensure_writable(skb, tcp_offset + sizeof(*th))) return 0; th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset); /* * Remember seq number in case this pkt gets resized */ seq = ntohl(th->seq); /* * Fix seq stuff if flagged as so. */ if (cp->flags & IP_VS_CONN_F_IN_SEQ) vs_fix_seq(&cp->in_seq, th); if (cp->flags & IP_VS_CONN_F_OUT_SEQ) vs_fix_ack_seq(&cp->out_seq, th); /* * Call private input hook function */ if (app->pkt_in == NULL) return 1; if (!app->pkt_in(app, cp, skb, &diff, ipvsh)) return 0; /* * Update ip_vs seq stuff if len has changed. */ if (diff != 0) vs_seq_update(cp, &cp->in_seq, IP_VS_CONN_F_IN_SEQ, seq, diff); return 1; } /* * Input pkt hook. Will call bound ip_vs_app specific function * called by ipvs packet handler, assumes previously checked cp!=NULL. * returns false if can't handle packet (oom). */ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) { struct ip_vs_app *app; /* * check if application module is bound to * this ip_vs_conn. */ if ((app = cp->app) == NULL) return 1; /* TCP is complicated */ if (cp->protocol == IPPROTO_TCP) return app_tcp_pkt_in(cp, skb, app, ipvsh); /* * Call private input hook function */ if (app->pkt_in == NULL) return 1; return app->pkt_in(app, cp, skb, NULL, ipvsh); } #ifdef CONFIG_PROC_FS /* * /proc/net/ip_vs_app entry function */ static struct ip_vs_app *ip_vs_app_idx(struct netns_ipvs *ipvs, loff_t pos) { struct ip_vs_app *app, *inc; list_for_each_entry(app, &ipvs->app_list, a_list) { list_for_each_entry(inc, &app->incs_list, a_list) { if (pos-- == 0) return inc; } } return NULL; } static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_app_mutex); return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN; } static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_app *inc, *app; struct list_head *e; struct net *net = seq_file_net(seq); struct netns_ipvs *ipvs = net_ipvs(net); ++*pos; if (v == SEQ_START_TOKEN) return ip_vs_app_idx(ipvs, 0); inc = v; app = inc->app; if ((e = inc->a_list.next) != &app->incs_list) return list_entry(e, struct ip_vs_app, a_list); /* go on to next application */ for (e = app->a_list.next; e != &ipvs->app_list; e = e->next) { app = list_entry(e, struct ip_vs_app, a_list); list_for_each_entry(inc, &app->incs_list, a_list) { return inc; } } return NULL; } static void ip_vs_app_seq_stop(struct seq_file *seq, void *v) { mutex_unlock(&__ip_vs_app_mutex); } static int ip_vs_app_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "prot port usecnt name\n"); else { const struct ip_vs_app *inc = v; seq_printf(seq, "%-3s %-7u %-6d %-17s\n", ip_vs_proto_name(inc->protocol), ntohs(inc->port), atomic_read(&inc->usecnt), inc->name); } return 0; } static const struct seq_operations ip_vs_app_seq_ops = { .start = ip_vs_app_seq_start, .next = ip_vs_app_seq_next, .stop = ip_vs_app_seq_stop, .show = ip_vs_app_seq_show, }; #endif int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { INIT_LIST_HEAD(&ipvs->app_list); #ifdef CONFIG_PROC_FS if (!proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; #endif return 0; } void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { unregister_ip_vs_app(ipvs, NULL /* all */); #ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_app", ipvs->net->proc_net); #endif } |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 | /* * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <net/sock.h> #include <linux/in.h> #include <linux/ipv6.h> #include <linux/if_arp.h> #include <linux/jhash.h> #include <linux/ratelimit.h> #include "rds.h" static struct rhashtable bind_hash_table; static const struct rhashtable_params ht_parms = { .nelem_hint = 768, .key_len = RDS_BOUND_KEY_LEN, .key_offset = offsetof(struct rds_sock, rs_bound_key), .head_offset = offsetof(struct rds_sock, rs_bound_node), .max_size = 16384, .min_size = 1024, }; /* Create a key for the bind hash table manipulation. Port is in network byte * order. */ static inline void __rds_create_bind_key(u8 *key, const struct in6_addr *addr, __be16 port, __u32 scope_id) { memcpy(key, addr, sizeof(*addr)); key += sizeof(*addr); memcpy(key, &port, sizeof(port)); key += sizeof(port); memcpy(key, &scope_id, sizeof(scope_id)); } /* * Return the rds_sock bound at the given local address. * * The rx path can race with rds_release. We notice if rds_release() has * marked this socket and don't return a rs ref to the rx path. */ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __u32 scope_id) { u8 key[RDS_BOUND_KEY_LEN]; struct rds_sock *rs; __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, ntohs(port)); return rs; } /* returns -ve errno or +ve port */ static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr, __be16 *port, __u32 scope_id) { int ret = -EADDRINUSE; u16 rover, last; u8 key[RDS_BOUND_KEY_LEN]; if (*port != 0) { rover = be16_to_cpu(*port); if (rover == RDS_FLAG_PROBE_PORT) return -EINVAL; last = rover; } else { rover = max_t(u16, prandom_u32(), 2); last = rover - 1; } do { if (rover == 0) rover++; if (rover == RDS_FLAG_PROBE_PORT) continue; __rds_create_bind_key(key, addr, cpu_to_be16(rover), scope_id); if (rhashtable_lookup_fast(&bind_hash_table, key, ht_parms)) continue; memcpy(rs->rs_bound_key, key, sizeof(rs->rs_bound_key)); rs->rs_bound_addr = *addr; net_get_random_once(&rs->rs_hash_initval, sizeof(rs->rs_hash_initval)); rs->rs_bound_port = cpu_to_be16(rover); rs->rs_bound_node.next = NULL; rds_sock_addref(rs); if (!rhashtable_insert_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms)) { *port = rs->rs_bound_port; rs->rs_bound_scope_id = scope_id; ret = 0; rdsdebug("rs %p binding to %pI6c:%d\n", rs, addr, (int)ntohs(*port)); break; } else { rs->rs_bound_addr = in6addr_any; rds_sock_put(rs); ret = -ENOMEM; break; } } while (rover++ != last); return ret; } void rds_remove_bound(struct rds_sock *rs) { if (ipv6_addr_any(&rs->rs_bound_addr)) return; rdsdebug("rs %p unbinding from %pI6c:%d\n", rs, &rs->rs_bound_addr, ntohs(rs->rs_bound_port)); rhashtable_remove_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms); rds_sock_put(rs); rs->rs_bound_addr = in6addr_any; } int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); struct in6_addr v6addr, *binding_addr; struct rds_transport *trans; __u32 scope_id = 0; int ret = 0; __be16 port; /* We allow an RDS socket to be bound to either IPv4 or IPv6 * address. */ if (addr_len < offsetofend(struct sockaddr, sa_family)) return -EINVAL; if (uaddr->sa_family == AF_INET) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; if (addr_len < sizeof(struct sockaddr_in) || sin->sin_addr.s_addr == htonl(INADDR_ANY) || sin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || ipv4_is_multicast(sin->sin_addr.s_addr)) return -EINVAL; ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr); binding_addr = &v6addr; port = sin->sin_port; #if IS_ENABLED(CONFIG_IPV6) } else if (uaddr->sa_family == AF_INET6) { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)uaddr; int addr_type; if (addr_len < sizeof(struct sockaddr_in6)) return -EINVAL; addr_type = ipv6_addr_type(&sin6->sin6_addr); if (!(addr_type & IPV6_ADDR_UNICAST)) { __be32 addr4; if (!(addr_type & IPV6_ADDR_MAPPED)) return -EINVAL; /* It is a mapped address. Need to do some sanity * checks. */ addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || ipv4_is_multicast(addr4)) return -EINVAL; } /* The scope ID must be specified for link local address. */ if (addr_type & IPV6_ADDR_LINKLOCAL) { if (sin6->sin6_scope_id == 0) return -EINVAL; scope_id = sin6->sin6_scope_id; } binding_addr = &sin6->sin6_addr; port = sin6->sin6_port; #endif } else { return -EINVAL; } lock_sock(sk); /* RDS socket does not allow re-binding. */ if (!ipv6_addr_any(&rs->rs_bound_addr)) { ret = -EINVAL; goto out; } /* Socket is connected. The binding address should have the same * scope ID as the connected address, except the case when one is * non-link local address (scope_id is 0). */ if (!ipv6_addr_any(&rs->rs_conn_addr) && scope_id && rs->rs_bound_scope_id && scope_id != rs->rs_bound_scope_id) { ret = -EINVAL; goto out; } /* The transport can be set using SO_RDS_TRANSPORT option before the * socket is bound. */ if (rs->rs_transport) { trans = rs->rs_transport; if (!trans->laddr_check || trans->laddr_check(sock_net(sock->sk), binding_addr, scope_id) != 0) { ret = -ENOPROTOOPT; goto out; } } else { trans = rds_trans_get_preferred(sock_net(sock->sk), binding_addr, scope_id); if (!trans) { ret = -EADDRNOTAVAIL; pr_info_ratelimited("RDS: %s could not find a transport for %pI6c, load rds_tcp or rds_rdma?\n", __func__, binding_addr); goto out; } rs->rs_transport = trans; } sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) rs->rs_transport = NULL; out: release_sock(sk); return ret; } void rds_bind_lock_destroy(void) { rhashtable_destroy(&bind_hash_table); } int rds_bind_lock_init(void) { return rhashtable_init(&bind_hash_table, &ht_parms); } |
| 674 671 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * * Copyright (C) 2000,2001,2002 Stephen Rothwell * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure */ #include <linux/fs.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/dnotify.h> #include <linux/init.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/fdtable.h> #include <linux/fsnotify_backend.h> int dir_notify_enable __read_mostly = 1; static struct kmem_cache *dnotify_struct_cache __read_mostly; static struct kmem_cache *dnotify_mark_cache __read_mostly; static struct fsnotify_group *dnotify_group __read_mostly; /* * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ struct dnotify_mark { struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; /* * When a process starts or stops watching an inode the set of events which * dnotify cares about for that inode may change. This function runs the * list of everything receiving dnotify events about this directory and calculates * the set of all those events. After it updates what dnotify is interested in * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask = 0; struct dnotify_struct *dn; struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); if (fsn_mark->mask == new_mask) return; fsn_mark->mask = new_mask; fsnotify_recalc_mask(fsn_mark->connector); } /* * Mains fsnotify call where events are delivered to dnotify. * Find the dnotify mark on the relevant inode, run the list of dnotify structs * on that mark and determine which of them has expressed interest in receiving * events of this type. When found send the correct process and signal and * destroy the dnotify struct if it was not registered to receive multiple * events. */ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = mask & ~FS_EVENT_ON_CHILD; /* not a dir, dnotify doesn't care */ if (!dir && !(mask & FS_ISDIR)) return 0; dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); spin_lock(&inode_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; continue; } fown = &dn->dn_filp->f_owner; send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(inode_mark); } } spin_unlock(&inode_mark->lock); return 0; } static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); BUG_ON(dn_mark->dn); kmem_cache_free(dnotify_mark_cache, dn_mark); } static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_inode_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; /* * Called every time a file is closed. Looks first for a dnotify mark on the * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { struct fsnotify_mark *fsn_mark; struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; bool free = false; inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) return; fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group); if (!fsn_mark) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_groups mark_mutex */ if (dn_mark->dn == NULL) { fsnotify_detach_mark(fsn_mark); free = true; } fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ static __u32 convert_arg(unsigned long arg) { __u32 new_mask = FS_EVENT_ON_CHILD; if (arg & DN_MULTISHOT) new_mask |= FS_DN_MULTISHOT; if (arg & DN_DELETE) new_mask |= (FS_DELETE | FS_MOVED_FROM); if (arg & DN_MODIFY) new_mask |= FS_MODIFY; if (arg & DN_ACCESS) new_mask |= FS_ACCESS; if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); return new_mask; } /* * If multiple processes watch the same inode with dnotify there is only one * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { odn->dn_fd = fd; odn->dn_mask |= mask; return -EEXIST; } odn = odn->dn_next; } dn->dn_mask = mask; dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; dn->dn_next = dn_mark->dn; dn_mark->dn = dn; return 0; } /* * When a process calls fcntl to attach a dnotify watch to a directory it ends * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be * attached to the fsnotify_mark. */ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg) { struct dnotify_mark *new_dn_mark, *dn_mark; struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; struct file *f; int destroy = 0, error = 0; __u32 mask; /* we use these to tell if we need to kfree */ new_fsn_mark = NULL; dn = NULL; if (!dir_notify_enable) { error = -EINVAL; goto out_err; } /* a 0 mask means we are explicitly removing the watch */ if ((arg & ~DN_MULTISHOT) == 0) { dnotify_flush(filp, id); error = 0; goto out_err; } /* dnotify only works on directories */ inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) { error = -ENOTDIR; goto out_err; } /* * convert the userspace DN_* "arg" to the internal FS_* * defined in fsnotify */ mask = convert_arg(arg); error = security_path_notify(&filp->f_path, mask, FSNOTIFY_OBJ_TYPE_INODE); if (error) goto out_err; /* expect most fcntl to add new rather than augment old */ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL); if (!dn) { error = -ENOMEM; goto out_err; } /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { error = -ENOMEM; goto out_err; } /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); new_fsn_mark->mask = mask; new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group); if (fsn_mark) { dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); spin_lock(&fsn_mark->lock); } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); fsn_mark = new_fsn_mark; dn_mark = new_dn_mark; /* we used new_fsn_mark, so don't free it */ new_fsn_mark = NULL; } rcu_read_lock(); f = lookup_fd_rcu(fd); rcu_read_unlock(); /* if (f != filp) means that we lost a race and another task/thread * actually closed the fd we are still playing with before we grabbed * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the * fd is the only time we clean up the marks we need to get our mark * off the list. */ if (f != filp) { /* if we added ourselves, shoot ourselves, it's possible that * the flush actually did shoot this fsn_mark. That's fine too * since multiple calls to destroy_mark is perfectly safe, if * we found a dn_mark already attached to the inode, just sod * off silently as the flush at close time dealt with it. */ if (dn_mark == new_dn_mark) destroy = 1; error = 0; goto out; } __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); error = attach_dn(dn, dn_mark, id, fd, filp, mask); /* !error means that we attached the dn to the dn_mark, so don't free it */ if (!error) dn = NULL; /* -EEXIST means that we didn't add this new dn and used an old one. * that isn't an error (and the unused dn should be freed) */ else if (error == -EEXIST) error = 0; dnotify_recalc_inode_mask(fsn_mark); out: spin_unlock(&fsn_mark->lock); if (destroy) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); out_err: if (new_fsn_mark) fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); return error; } static int __init dnotify_init(void) { dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, FSNOTIFY_GROUP_NOFS); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); return 0; } module_init(dnotify_init) |
| 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | // SPDX-License-Identifier: GPL-2.0-only /* * Common code for control of lockd and nfsv4 grace periods. * * Transplanted from lockd code */ #include <linux/module.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/fs.h> static unsigned int grace_net_id; static DEFINE_SPINLOCK(grace_lock); /** * locks_start_grace * @net: net namespace that this lock manager belongs to * @lm: who this grace period is for * * A grace period is a period during which locks should not be given * out. Currently grace periods are only enforced by the two lock * managers (lockd and nfsd), using the locks_in_grace() function to * check when they are in a grace period. * * This function is called to start a grace period. */ void locks_start_grace(struct net *net, struct lock_manager *lm) { struct list_head *grace_list = net_generic(net, grace_net_id); spin_lock(&grace_lock); if (list_empty(&lm->list)) list_add(&lm->list, grace_list); else WARN(1, "double list_add attempt detected in net %x %s\n", net->ns.inum, (net == &init_net) ? "(init_net)" : ""); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_start_grace); /** * locks_end_grace * @lm: who this grace period is for * * Call this function to state that the given lock manager is ready to * resume regular locking. The grace period will not end until all lock * managers that called locks_start_grace() also call locks_end_grace(). * Note that callers count on it being safe to call this more than once, * and the second call should be a no-op. */ void locks_end_grace(struct lock_manager *lm) { spin_lock(&grace_lock); list_del_init(&lm->list); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_end_grace); static bool __state_in_grace(struct net *net, bool open) { struct list_head *grace_list = net_generic(net, grace_net_id); struct lock_manager *lm; if (!open) return !list_empty(grace_list); spin_lock(&grace_lock); list_for_each_entry(lm, grace_list, list) { if (lm->block_opens) { spin_unlock(&grace_lock); return true; } } spin_unlock(&grace_lock); return false; } /** * locks_in_grace * @net: network namespace * * Lock managers call this function to determine when it is OK for them * to answer ordinary lock requests, and when they should accept only * lock reclaims. */ bool locks_in_grace(struct net *net) { return __state_in_grace(net, false); } EXPORT_SYMBOL_GPL(locks_in_grace); bool opens_in_grace(struct net *net) { return __state_in_grace(net, true); } EXPORT_SYMBOL_GPL(opens_in_grace); static int __net_init grace_init_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); INIT_LIST_HEAD(grace_list); return 0; } static void __net_exit grace_exit_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); WARN_ONCE(!list_empty(grace_list), "net %x %s: grace_list is not empty\n", net->ns.inum, __func__); } static struct pernet_operations grace_net_ops = { .init = grace_init_net, .exit = grace_exit_net, .id = &grace_net_id, .size = sizeof(struct list_head), }; static int __init init_grace(void) { return register_pernet_subsys(&grace_net_ops); } static void __exit exit_grace(void) { unregister_pernet_subsys(&grace_net_ops); } MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>"); MODULE_LICENSE("GPL"); module_init(init_grace) module_exit(exit_grace) |
| 3081 1079 2631 685 83 360 549 7 22 4 1 2158 861 9 9 35 100 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * They do not exist because they would lead to subtle race conditions: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list might be non-empty when list_empty_rcu() checks it, but it * might have become empty by the time that list_first_entry_rcu() rereads * the ->next pointer, which would result in a SEGV. * * When not using RCU, it is OK for list_first_entry() to re-read that * pointer because both functions should be protected by some lock that * blocks writers. * * When using RCU, list_empty() uses READ_ONCE() to fetch the * RCU-protected ->next pointer and then compares it to the address of the * list head. However, it neither dereferences this pointer nor provides * this pointer to its caller. Thus, READ_ONCE() suffices (that is, * rcu_dereference() is not needed), which means that list_empty() can be * used anywhere you would want to use list_empty_rcu(). Just don't * expect anything useful to happen if you do a subsequent lockless * call to list_first_entry_rcu()!!! * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the first element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 21 21 21 21 21 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/pnode.c * * (C) Copyright IBM Corporation 2005. * Author : Ram Pai (linuxram@us.ibm.com) */ #include <linux/mnt_namespace.h> #include <linux/mount.h> #include <linux/fs.h> #include <linux/nsproxy.h> #include <uapi/linux/mount.h> #include "internal.h" #include "pnode.h" /* return the next shared peer mount of @p */ static inline struct mount *next_peer(struct mount *p) { return list_entry(p->mnt_share.next, struct mount, mnt_share); } static inline struct mount *first_slave(struct mount *p) { return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave); } static inline struct mount *last_slave(struct mount *p) { return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave); } static inline struct mount *next_slave(struct mount *p) { return list_entry(p->mnt_slave.next, struct mount, mnt_slave); } static struct mount *get_peer_under_root(struct mount *mnt, struct mnt_namespace *ns, const struct path *root) { struct mount *m = mnt; do { /* Check the namespace first for optimization */ if (m->mnt_ns == ns && is_path_reachable(m, m->mnt.mnt_root, root)) return m; m = next_peer(m); } while (m != mnt); return NULL; } /* * Get ID of closest dominating peer group having a representative * under the given root. * * Caller must hold namespace_sem */ int get_dominating_id(struct mount *mnt, const struct path *root) { struct mount *m; for (m = mnt->mnt_master; m != NULL; m = m->mnt_master) { struct mount *d = get_peer_under_root(m, mnt->mnt_ns, root); if (d) return d->mnt_group_id; } return 0; } static int do_make_slave(struct mount *mnt) { struct mount *master, *slave_mnt; if (list_empty(&mnt->mnt_share)) { if (IS_MNT_SHARED(mnt)) { mnt_release_group_id(mnt); CLEAR_MNT_SHARED(mnt); } master = mnt->mnt_master; if (!master) { struct list_head *p = &mnt->mnt_slave_list; while (!list_empty(p)) { slave_mnt = list_first_entry(p, struct mount, mnt_slave); list_del_init(&slave_mnt->mnt_slave); slave_mnt->mnt_master = NULL; } return 0; } } else { struct mount *m; /* * slave 'mnt' to a peer mount that has the * same root dentry. If none is available then * slave it to anything that is available. */ for (m = master = next_peer(mnt); m != mnt; m = next_peer(m)) { if (m->mnt.mnt_root == mnt->mnt.mnt_root) { master = m; break; } } list_del_init(&mnt->mnt_share); mnt->mnt_group_id = 0; CLEAR_MNT_SHARED(mnt); } list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave) slave_mnt->mnt_master = master; list_move(&mnt->mnt_slave, &master->mnt_slave_list); list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev); INIT_LIST_HEAD(&mnt->mnt_slave_list); mnt->mnt_master = master; return 0; } /* * vfsmount lock must be held for write */ void change_mnt_propagation(struct mount *mnt, int type) { if (type == MS_SHARED) { set_mnt_shared(mnt); return; } do_make_slave(mnt); if (type != MS_SLAVE) { list_del_init(&mnt->mnt_slave); mnt->mnt_master = NULL; if (type == MS_UNBINDABLE) mnt->mnt.mnt_flags |= MNT_UNBINDABLE; else mnt->mnt.mnt_flags &= ~MNT_UNBINDABLE; } } /* * get the next mount in the propagation tree. * @m: the mount seen last * @origin: the original mount from where the tree walk initiated * * Note that peer groups form contiguous segments of slave lists. * We rely on that in get_source() to be able to find out if * vfsmount found while iterating with propagation_next() is * a peer of one we'd found earlier. */ static struct mount *propagation_next(struct mount *m, struct mount *origin) { /* are there any slaves of this mount? */ if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) return first_slave(m); while (1) { struct mount *master = m->mnt_master; if (master == origin->mnt_master) { struct mount *next = next_peer(m); return (next == origin) ? NULL : next; } else if (m->mnt_slave.next != &master->mnt_slave_list) return next_slave(m); /* back at master */ m = master; } } static struct mount *skip_propagation_subtree(struct mount *m, struct mount *origin) { /* * Advance m such that propagation_next will not return * the slaves of m. */ if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) m = last_slave(m); return m; } static struct mount *next_group(struct mount *m, struct mount *origin) { while (1) { while (1) { struct mount *next; if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) return first_slave(m); next = next_peer(m); if (m->mnt_group_id == origin->mnt_group_id) { if (next == origin) return NULL; } else if (m->mnt_slave.next != &next->mnt_slave) break; m = next; } /* m is the last peer */ while (1) { struct mount *master = m->mnt_master; if (m->mnt_slave.next != &master->mnt_slave_list) return next_slave(m); m = next_peer(master); if (master->mnt_group_id == origin->mnt_group_id) break; if (master->mnt_slave.next == &m->mnt_slave) break; m = master; } if (m == origin) return NULL; } } /* all accesses are serialized by namespace_sem */ static struct mount *last_dest, *first_source, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; static inline bool peers(struct mount *m1, struct mount *m2) { return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; } static int propagate_one(struct mount *m) { struct mount *child; int type; /* skip ones added by this propagate_mnt() */ if (IS_MNT_NEW(m)) return 0; /* skip if mountpoint isn't covered by it */ if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) return 0; if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { struct mount *n, *p; bool done; for (n = m; ; n = p) { p = n->mnt_master; if (p == dest_master || IS_MNT_MARKED(p)) break; } do { struct mount *parent = last_source->mnt_parent; if (peers(last_source, first_source)) break; done = parent->mnt_master == p; if (done && peers(n, parent)) break; last_source = last_source->mnt_master; } while (!done); type = CL_SLAVE; /* beginning of peer group among the slaves? */ if (IS_MNT_SHARED(m)) type |= CL_MAKE_SHARED; } child = copy_tree(last_source, last_source->mnt.mnt_root, type); if (IS_ERR(child)) return PTR_ERR(child); read_seqlock_excl(&mount_lock); mnt_set_mountpoint(m, mp, child); if (m->mnt_master != dest_master) SET_MNT_MARK(m->mnt_master); read_sequnlock_excl(&mount_lock); last_dest = m; last_source = child; hlist_add_head(&child->mnt_hash, list); return count_mounts(m->mnt_ns, child); } /* * mount 'source_mnt' under the destination 'dest_mnt' at * dentry 'dest_dentry'. And propagate that mount to * all the peer and slave mounts of 'dest_mnt'. * Link all the new mounts into a propagation tree headed at * source_mnt. Also link all the new mounts using ->mnt_list * headed at source_mnt's ->mnt_list * * @dest_mnt: destination mount. * @dest_dentry: destination dentry. * @source_mnt: source mount. * @tree_list : list of heads of trees to be attached. */ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, struct mount *source_mnt, struct hlist_head *tree_list) { struct mount *m, *n; int ret = 0; /* * we don't want to bother passing tons of arguments to * propagate_one(); everything is serialized by namespace_sem, * so globals will do just fine. */ last_dest = dest_mnt; first_source = source_mnt; last_source = source_mnt; mp = dest_mp; list = tree_list; dest_master = dest_mnt->mnt_master; /* all peers of dest_mnt, except dest_mnt itself */ for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) { ret = propagate_one(n); if (ret) goto out; } /* all slave groups */ for (m = next_group(dest_mnt, dest_mnt); m; m = next_group(m, dest_mnt)) { /* everything in that slave group */ n = m; do { ret = propagate_one(n); if (ret) goto out; n = next_peer(n); } while (n != m); } out: read_seqlock_excl(&mount_lock); hlist_for_each_entry(n, tree_list, mnt_hash) { m = n->mnt_parent; if (m->mnt_master != dest_mnt->mnt_master) CLEAR_MNT_MARK(m->mnt_master); } read_sequnlock_excl(&mount_lock); return ret; } static struct mount *find_topper(struct mount *mnt) { /* If there is exactly one mount covering mnt completely return it. */ struct mount *child; if (!list_is_singular(&mnt->mnt_mounts)) return NULL; child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child); if (child->mnt_mountpoint != mnt->mnt.mnt_root) return NULL; return child; } /* * return true if the refcount is greater than count */ static inline int do_refcount_check(struct mount *mnt, int count) { return mnt_get_count(mnt) > count; } /* * check if the mount 'mnt' can be unmounted successfully. * @mnt: the mount to be checked for unmount * NOTE: unmounting 'mnt' would naturally propagate to all * other mounts its parent propagates to. * Check if any of these mounts that **do not have submounts** * have more references than 'refcnt'. If so return busy. * * vfsmount lock must be held for write */ int propagate_mount_busy(struct mount *mnt, int refcnt) { struct mount *m, *child, *topper; struct mount *parent = mnt->mnt_parent; if (mnt == parent) return do_refcount_check(mnt, refcnt); /* * quickly check if the current mount can be unmounted. * If not, we don't have to go checking for all other * mounts */ if (!list_empty(&mnt->mnt_mounts) || do_refcount_check(mnt, refcnt)) return 1; for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { int count = 1; child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); if (!child) continue; /* Is there exactly one mount on the child that covers * it completely whose reference should be ignored? */ topper = find_topper(child); if (topper) count += 1; else if (!list_empty(&child->mnt_mounts)) continue; if (do_refcount_check(child, count)) return 1; } return 0; } /* * Clear MNT_LOCKED when it can be shown to be safe. * * mount_lock lock must be held for write */ void propagate_mount_unlock(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m, *child; BUG_ON(parent == mnt); for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); if (child) child->mnt.mnt_flags &= ~MNT_LOCKED; } } static void umount_one(struct mount *mnt, struct list_head *to_umount) { CLEAR_MNT_MARK(mnt); mnt->mnt.mnt_flags |= MNT_UMOUNT; list_del_init(&mnt->mnt_child); list_del_init(&mnt->mnt_umounting); list_move_tail(&mnt->mnt_list, to_umount); } /* * NOTE: unmounting 'mnt' naturally propagates to all other mounts its * parent propagates to. */ static bool __propagate_umount(struct mount *mnt, struct list_head *to_umount, struct list_head *to_restore) { bool progress = false; struct mount *child; /* * The state of the parent won't change if this mount is * already unmounted or marked as without children. */ if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED)) goto out; /* Verify topper is the only grandchild that has not been * speculatively unmounted. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (child->mnt_mountpoint == mnt->mnt.mnt_root) continue; if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child)) continue; /* Found a mounted child */ goto children; } /* Mark mounts that can be unmounted if not locked */ SET_MNT_MARK(mnt); progress = true; /* If a mount is without children and not locked umount it. */ if (!IS_MNT_LOCKED(mnt)) { umount_one(mnt, to_umount); } else { children: list_move_tail(&mnt->mnt_umounting, to_restore); } out: return progress; } static void umount_list(struct list_head *to_umount, struct list_head *to_restore) { struct mount *mnt, *child, *tmp; list_for_each_entry(mnt, to_umount, mnt_list) { list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) { /* topper? */ if (child->mnt_mountpoint == mnt->mnt.mnt_root) list_move_tail(&child->mnt_umounting, to_restore); else umount_one(child, to_umount); } } } static void restore_mounts(struct list_head *to_restore) { /* Restore mounts to a clean working state */ while (!list_empty(to_restore)) { struct mount *mnt, *parent; struct mountpoint *mp; mnt = list_first_entry(to_restore, struct mount, mnt_umounting); CLEAR_MNT_MARK(mnt); list_del_init(&mnt->mnt_umounting); /* Should this mount be reparented? */ mp = mnt->mnt_mp; parent = mnt->mnt_parent; while (parent->mnt.mnt_flags & MNT_UMOUNT) { mp = parent->mnt_mp; parent = parent->mnt_parent; } if (parent != mnt->mnt_parent) mnt_change_mountpoint(parent, mp, mnt); } } static void cleanup_umount_visitations(struct list_head *visited) { while (!list_empty(visited)) { struct mount *mnt = list_first_entry(visited, struct mount, mnt_umounting); list_del_init(&mnt->mnt_umounting); } } /* * collect all mounts that receive propagation from the mount in @list, * and return these additional mounts in the same list. * @list: the list of mounts to be unmounted. * * vfsmount lock must be held for write */ int propagate_umount(struct list_head *list) { struct mount *mnt; LIST_HEAD(to_restore); LIST_HEAD(to_umount); LIST_HEAD(visited); /* Find candidates for unmounting */ list_for_each_entry_reverse(mnt, list, mnt_list) { struct mount *parent = mnt->mnt_parent; struct mount *m; /* * If this mount has already been visited it is known that it's * entire peer group and all of their slaves in the propagation * tree for the mountpoint has already been visited and there is * no need to visit them again. */ if (!list_empty(&mnt->mnt_umounting)) continue; list_add_tail(&mnt->mnt_umounting, &visited); for (m = propagation_next(parent, parent); m; m = propagation_next(m, parent)) { struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint); if (!child) continue; if (!list_empty(&child->mnt_umounting)) { /* * If the child has already been visited it is * know that it's entire peer group and all of * their slaves in the propgation tree for the * mountpoint has already been visited and there * is no need to visit this subtree again. */ m = skip_propagation_subtree(m, parent); continue; } else if (child->mnt.mnt_flags & MNT_UMOUNT) { /* * We have come accross an partially unmounted * mount in list that has not been visited yet. * Remember it has been visited and continue * about our merry way. */ list_add_tail(&child->mnt_umounting, &visited); continue; } /* Check the child and parents while progress is made */ while (__propagate_umount(child, &to_umount, &to_restore)) { /* Is the parent a umount candidate? */ child = child->mnt_parent; if (list_empty(&child->mnt_umounting)) break; } } } umount_list(&to_umount, &to_restore); restore_mounts(&to_restore); cleanup_umount_visitations(&visited); list_splice_tail(&to_umount, list); return 0; } |
| 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SR-IPv6 implementation -- HMAC functions * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #include <linux/errno.h> #include <linux/kernel.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/mroute6.h> #include <linux/slab.h> #include <linux/rhashtable.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.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/xfrm.h> #include <crypto/hash.h> #include <net/seg6.h> #include <net/genetlink.h> #include <net/seg6_hmac.h> #include <linux/random.h> static DEFINE_PER_CPU(char [SEG6_HMAC_RING_SIZE], hmac_ring); static int seg6_hmac_cmpfn(struct rhashtable_compare_arg *arg, const void *obj) { const struct seg6_hmac_info *hinfo = obj; return (hinfo->hmackeyid != *(__u32 *)arg->key); } static inline void seg6_hinfo_release(struct seg6_hmac_info *hinfo) { kfree_rcu(hinfo, rcu); } static void seg6_free_hi(void *ptr, void *arg) { struct seg6_hmac_info *hinfo = (struct seg6_hmac_info *)ptr; if (hinfo) seg6_hinfo_release(hinfo); } static const struct rhashtable_params rht_params = { .head_offset = offsetof(struct seg6_hmac_info, node), .key_offset = offsetof(struct seg6_hmac_info, hmackeyid), .key_len = sizeof(u32), .automatic_shrinking = true, .obj_cmpfn = seg6_hmac_cmpfn, }; static struct seg6_hmac_algo hmac_algos[] = { { .alg_id = SEG6_HMAC_ALGO_SHA1, .name = "hmac(sha1)", }, { .alg_id = SEG6_HMAC_ALGO_SHA256, .name = "hmac(sha256)", }, }; static struct sr6_tlv_hmac *seg6_get_tlv_hmac(struct ipv6_sr_hdr *srh) { struct sr6_tlv_hmac *tlv; if (srh->hdrlen < (srh->first_segment + 1) * 2 + 5) return NULL; if (!sr_has_hmac(srh)) return NULL; tlv = (struct sr6_tlv_hmac *) ((char *)srh + ((srh->hdrlen + 1) << 3) - 40); if (tlv->tlvhdr.type != SR6_TLV_HMAC || tlv->tlvhdr.len != 38) return NULL; return tlv; } static struct seg6_hmac_algo *__hmac_get_algo(u8 alg_id) { struct seg6_hmac_algo *algo; int i, alg_count; alg_count = ARRAY_SIZE(hmac_algos); for (i = 0; i < alg_count; i++) { algo = &hmac_algos[i]; if (algo->alg_id == alg_id) return algo; } return NULL; } static int __do_hmac(struct seg6_hmac_info *hinfo, const char *text, u8 psize, u8 *output, int outlen) { struct seg6_hmac_algo *algo; struct crypto_shash *tfm; struct shash_desc *shash; int ret, dgsize; algo = __hmac_get_algo(hinfo->alg_id); if (!algo) return -ENOENT; tfm = *this_cpu_ptr(algo->tfms); dgsize = crypto_shash_digestsize(tfm); if (dgsize > outlen) { pr_debug("sr-ipv6: __do_hmac: digest size too big (%d / %d)\n", dgsize, outlen); return -ENOMEM; } ret = crypto_shash_setkey(tfm, hinfo->secret, hinfo->slen); if (ret < 0) { pr_debug("sr-ipv6: crypto_shash_setkey failed: err %d\n", ret); goto failed; } shash = *this_cpu_ptr(algo->shashs); shash->tfm = tfm; ret = crypto_shash_digest(shash, text, psize, output); if (ret < 0) { pr_debug("sr-ipv6: crypto_shash_digest failed: err %d\n", ret); goto failed; } return dgsize; failed: return ret; } int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr, struct in6_addr *saddr, u8 *output) { __be32 hmackeyid = cpu_to_be32(hinfo->hmackeyid); u8 tmp_out[SEG6_HMAC_MAX_DIGESTSIZE]; int plen, i, dgsize, wrsize; char *ring, *off; /* a 160-byte buffer for digest output allows to store highest known * hash function (RadioGatun) with up to 1216 bits */ /* saddr(16) + first_seg(1) + flags(1) + keyid(4) + seglist(16n) */ plen = 16 + 1 + 1 + 4 + (hdr->first_segment + 1) * 16; /* this limit allows for 14 segments */ if (plen >= SEG6_HMAC_RING_SIZE) return -EMSGSIZE; /* Let's build the HMAC text on the ring buffer. The text is composed * as follows, in order: * * 1. Source IPv6 address (128 bits) * 2. first_segment value (8 bits) * 3. Flags (8 bits) * 4. HMAC Key ID (32 bits) * 5. All segments in the segments list (n * 128 bits) */ local_bh_disable(); ring = this_cpu_ptr(hmac_ring); off = ring; /* source address */ memcpy(off, saddr, 16); off += 16; /* first_segment value */ *off++ = hdr->first_segment; /* flags */ *off++ = hdr->flags; /* HMAC Key ID */ memcpy(off, &hmackeyid, 4); off += 4; /* all segments in the list */ for (i = 0; i < hdr->first_segment + 1; i++) { memcpy(off, hdr->segments + i, 16); off += 16; } dgsize = __do_hmac(hinfo, ring, plen, tmp_out, SEG6_HMAC_MAX_DIGESTSIZE); local_bh_enable(); if (dgsize < 0) return dgsize; wrsize = SEG6_HMAC_FIELD_LEN; if (wrsize > dgsize) wrsize = dgsize; memset(output, 0, SEG6_HMAC_FIELD_LEN); memcpy(output, tmp_out, wrsize); return 0; } EXPORT_SYMBOL(seg6_hmac_compute); /* checks if an incoming SR-enabled packet's HMAC status matches * the incoming policy. * * called with rcu_read_lock() */ bool seg6_hmac_validate_skb(struct sk_buff *skb) { u8 hmac_output[SEG6_HMAC_FIELD_LEN]; struct net *net = dev_net(skb->dev); struct seg6_hmac_info *hinfo; struct sr6_tlv_hmac *tlv; struct ipv6_sr_hdr *srh; struct inet6_dev *idev; idev = __in6_dev_get(skb->dev); srh = (struct ipv6_sr_hdr *)skb_transport_header(skb); tlv = seg6_get_tlv_hmac(srh); /* mandatory check but no tlv */ if (idev->cnf.seg6_require_hmac > 0 && !tlv) return false; /* no check */ if (idev->cnf.seg6_require_hmac < 0) return true; /* check only if present */ if (idev->cnf.seg6_require_hmac == 0 && !tlv) return true; /* now, seg6_require_hmac >= 0 && tlv */ hinfo = seg6_hmac_info_lookup(net, be32_to_cpu(tlv->hmackeyid)); if (!hinfo) return false; if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output)) return false; if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0) return false; return true; } EXPORT_SYMBOL(seg6_hmac_validate_skb); /* called with rcu_read_lock() */ struct seg6_hmac_info *seg6_hmac_info_lookup(struct net *net, u32 key) { struct seg6_pernet_data *sdata = seg6_pernet(net); struct seg6_hmac_info *hinfo; hinfo = rhashtable_lookup_fast(&sdata->hmac_infos, &key, rht_params); return hinfo; } EXPORT_SYMBOL(seg6_hmac_info_lookup); int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo) { struct seg6_pernet_data *sdata = seg6_pernet(net); int err; err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node, rht_params); return err; } EXPORT_SYMBOL(seg6_hmac_info_add); int seg6_hmac_info_del(struct net *net, u32 key) { struct seg6_pernet_data *sdata = seg6_pernet(net); struct seg6_hmac_info *hinfo; int err = -ENOENT; hinfo = rhashtable_lookup_fast(&sdata->hmac_infos, &key, rht_params); if (!hinfo) goto out; err = rhashtable_remove_fast(&sdata->hmac_infos, &hinfo->node, rht_params); if (err) goto out; seg6_hinfo_release(hinfo); out: return err; } EXPORT_SYMBOL(seg6_hmac_info_del); int seg6_push_hmac(struct net *net, struct in6_addr *saddr, struct ipv6_sr_hdr *srh) { struct seg6_hmac_info *hinfo; struct sr6_tlv_hmac *tlv; int err = -ENOENT; tlv = seg6_get_tlv_hmac(srh); if (!tlv) return -EINVAL; rcu_read_lock(); hinfo = seg6_hmac_info_lookup(net, be32_to_cpu(tlv->hmackeyid)); if (!hinfo) goto out; memset(tlv->hmac, 0, SEG6_HMAC_FIELD_LEN); err = seg6_hmac_compute(hinfo, srh, saddr, tlv->hmac); out: rcu_read_unlock(); return err; } EXPORT_SYMBOL(seg6_push_hmac); static int seg6_hmac_init_algo(void) { struct seg6_hmac_algo *algo; struct crypto_shash *tfm; struct shash_desc *shash; int i, alg_count, cpu; int ret = -ENOMEM; alg_count = ARRAY_SIZE(hmac_algos); for (i = 0; i < alg_count; i++) { struct crypto_shash **p_tfm; int shsize; algo = &hmac_algos[i]; algo->tfms = alloc_percpu(struct crypto_shash *); if (!algo->tfms) goto error_out; for_each_possible_cpu(cpu) { tfm = crypto_alloc_shash(algo->name, 0, 0); if (IS_ERR(tfm)) { ret = PTR_ERR(tfm); goto error_out; } p_tfm = per_cpu_ptr(algo->tfms, cpu); *p_tfm = tfm; } p_tfm = raw_cpu_ptr(algo->tfms); tfm = *p_tfm; shsize = sizeof(*shash) + crypto_shash_descsize(tfm); algo->shashs = alloc_percpu(struct shash_desc *); if (!algo->shashs) goto error_out; for_each_possible_cpu(cpu) { shash = kzalloc_node(shsize, GFP_KERNEL, cpu_to_node(cpu)); if (!shash) goto error_out; *per_cpu_ptr(algo->shashs, cpu) = shash; } } return 0; error_out: seg6_hmac_exit(); return ret; } int __init seg6_hmac_init(void) { return seg6_hmac_init_algo(); } int __net_init seg6_hmac_net_init(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); rhashtable_init(&sdata->hmac_infos, &rht_params); return 0; } void seg6_hmac_exit(void) { struct seg6_hmac_algo *algo = NULL; struct crypto_shash *tfm; struct shash_desc *shash; int i, alg_count, cpu; alg_count = ARRAY_SIZE(hmac_algos); for (i = 0; i < alg_count; i++) { algo = &hmac_algos[i]; if (algo->shashs) { for_each_possible_cpu(cpu) { shash = *per_cpu_ptr(algo->shashs, cpu); kfree(shash); } free_percpu(algo->shashs); } if (algo->tfms) { for_each_possible_cpu(cpu) { tfm = *per_cpu_ptr(algo->tfms, cpu); crypto_free_shash(tfm); } free_percpu(algo->tfms); } } } EXPORT_SYMBOL(seg6_hmac_exit); void __net_exit seg6_hmac_net_exit(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); rhashtable_free_and_destroy(&sdata->hmac_infos, seg6_free_hi, NULL); } EXPORT_SYMBOL(seg6_hmac_net_exit); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * acpi.h - ACPI Interface * * Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> */ #ifndef _LINUX_ACPI_H #define _LINUX_ACPI_H #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ #include <linux/irqdomain.h> #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/property.h> #include <linux/uuid.h> #ifndef _LINUX #define _LINUX #endif #include <acpi/acpi.h> #ifdef CONFIG_ACPI #include <linux/list.h> #include <linux/mod_devicetable.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mutex.h> #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> #include <acpi/acpi_numa.h> #include <acpi/acpi_io.h> #include <asm/acpi.h> static inline acpi_handle acpi_device_handle(struct acpi_device *adev) { return adev ? adev->handle : NULL; } #define ACPI_COMPANION(dev) to_acpi_device_node((dev)->fwnode) #define ACPI_COMPANION_SET(dev, adev) set_primary_fwnode(dev, (adev) ? \ acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) #define ACPI_HANDLE_FWNODE(fwnode) \ acpi_device_handle(to_acpi_device_node(fwnode)) static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; fwnode = kzalloc(sizeof(struct fwnode_handle), GFP_KERNEL); if (!fwnode) return NULL; fwnode_init(fwnode, &acpi_static_fwnode_ops); return fwnode; } static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode) { if (WARN_ON(!is_acpi_static_node(fwnode))) return; kfree(fwnode); } /** * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with * the PCI-defined class-code information * * @_cls : the class, subclass, prog-if triple for this device * @_msk : the class mask for this device * * This macro is used to create a struct acpi_device_id that matches a * specific PCI class. The .id and .driver_data fields will be left * initialized with the default value. */ #define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (_cls), .cls_msk = (_msk), static inline bool has_acpi_companion(struct device *dev) { return is_acpi_device_node(dev->fwnode); } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { ACPI_COMPANION_SET(dev, acpi_find_child_device(parent, addr, false)); } static inline const char *acpi_dev_name(struct acpi_device *adev) { return dev_name(&adev->dev); } struct device *acpi_get_first_physical_node(struct acpi_device *adev); enum acpi_irq_model_id { ACPI_IRQ_MODEL_PIC = 0, ACPI_IRQ_MODEL_IOAPIC, ACPI_IRQ_MODEL_IOSAPIC, ACPI_IRQ_MODEL_PLATFORM, ACPI_IRQ_MODEL_GIC, ACPI_IRQ_MODEL_COUNT }; extern enum acpi_irq_model_id acpi_irq_model; enum acpi_interrupt_id { ACPI_INTERRUPT_PMI = 1, ACPI_INTERRUPT_INIT, ACPI_INTERRUPT_CPEI, ACPI_INTERRUPT_COUNT }; #define ACPI_SPACE_MEM 0 enum acpi_address_range_id { ACPI_ADDRESS_RANGE_MEMORY = 1, ACPI_ADDRESS_RANGE_RESERVED = 2, ACPI_ADDRESS_RANGE_ACPI = 3, ACPI_ADDRESS_RANGE_NVS = 4, ACPI_ADDRESS_RANGE_COUNT }; /* Table Handlers */ union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; struct acpi_prmt_module_header prmt; }; typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); typedef int (*acpi_tbl_entry_handler)(union acpi_subtable_headers *header, const unsigned long end); /* Debugger support */ struct acpi_debugger_ops { int (*create_thread)(acpi_osd_exec_callback function, void *context); ssize_t (*write_log)(const char *msg); ssize_t (*read_cmd)(char *buffer, size_t length); int (*wait_command_ready)(bool single_step, char *buffer, size_t length); int (*notify_command_complete)(void); }; struct acpi_debugger { const struct acpi_debugger_ops *ops; struct module *owner; struct mutex lock; }; #ifdef CONFIG_ACPI_DEBUGGER int __init acpi_debugger_init(void); int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops); void acpi_unregister_debugger(const struct acpi_debugger_ops *ops); int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context); ssize_t acpi_debugger_write_log(const char *msg); ssize_t acpi_debugger_read_cmd(char *buffer, size_t buffer_length); int acpi_debugger_wait_command_ready(void); int acpi_debugger_notify_command_complete(void); #else static inline int acpi_debugger_init(void) { return -ENODEV; } static inline int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops) { return -ENODEV; } static inline void acpi_unregister_debugger(const struct acpi_debugger_ops *ops) { } static inline int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context) { return -ENODEV; } static inline int acpi_debugger_write_log(const char *msg) { return -ENODEV; } static inline int acpi_debugger_read_cmd(char *buffer, u32 buffer_length) { return -ENODEV; } static inline int acpi_debugger_wait_command_ready(void) { return -ENODEV; } static inline int acpi_debugger_notify_command_complete(void) { return -ENODEV; } #endif #define BAD_MADT_ENTRY(entry, end) ( \ (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ ((struct acpi_subtable_header *)entry)->length < sizeof(*entry)) struct acpi_subtable_proc { int id; acpi_tbl_entry_handler handler; int count; }; void __iomem *__acpi_map_table(unsigned long phys, unsigned long size); void __acpi_unmap_table(void __iomem *map, unsigned long size); int early_acpi_boot_init(void); int acpi_boot_init (void); void acpi_boot_table_prepare (void); void acpi_boot_table_init (void); int acpi_mps_check (void); int acpi_numa_init (void); int acpi_locate_initial_tables (void); void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); int acpi_table_parse(char *id, acpi_tbl_table_handler handler); int __init acpi_table_parse_entries(char *id, unsigned long table_size, int entry_id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init acpi_table_parse_entries_array(char *id, unsigned long table_size, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); /* the following numa functions are architecture-dependent */ void acpi_numa_slit_init (struct acpi_table_slit *slit); #if defined(CONFIG_X86) || defined(CONFIG_IA64) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else static inline void acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { } #endif void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); #ifdef CONFIG_ARM64 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size); #else static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } static inline void acpi_arch_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size) { } #endif int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) #endif static inline bool invalid_logical_cpuid(u32 cpuid) { return (int)cpuid < 0; } static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) { return phys_id == PHYS_CPUID_INVALID; } /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); /* Processor _CTS control */ struct acpi_processor_power; #ifdef CONFIG_ACPI_PROCESSOR_CSTATE bool acpi_processor_claim_cst_control(void); int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info); #else static inline bool acpi_processor_claim_cst_control(void) { return false; } static inline int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info) { return -ENODEV; } #endif #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu); int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base); int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); void acpi_irq_stats_init(void); extern u32 acpi_irq_handled; extern u32 acpi_irq_not_handled; extern unsigned int acpi_sci_irq; extern bool acpi_no_s5; #define INVALID_ACPI_IRQ ((unsigned)-1) static inline bool acpi_sci_irq_valid(void) { return acpi_sci_irq != INVALID_ACPI_IRQ; } extern int sbf_port; extern unsigned long acpi_realmode_flags; int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity); int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); void acpi_set_irq_model(enum acpi_irq_model_id model, struct fwnode_handle *fwnode); struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, unsigned int size, struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data); #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else static inline int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) { return -1; } #endif /* * This function undoes the effect of one call to acpi_register_gsi(). * If this matches the last registration, any IRQ resources for gsi * are freed. */ void acpi_unregister_gsi (u32 gsi); struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); #ifdef CONFIG_PCI void acpi_penalize_sci_irq(int irq, int trigger, int polarity); #else static inline void acpi_penalize_sci_irq(int irq, int trigger, int polarity) { } #endif void acpi_pci_irq_disable (struct pci_dev *dev); extern int ec_read(u8 addr, u8 *val); extern int ec_write(u8 addr, u8 val); extern int ec_transaction(u8 command, const u8 *wdata, unsigned wdata_len, u8 *rdata, unsigned rdata_len); extern acpi_handle ec_get_handle(void); extern bool acpi_is_pnp_device(struct acpi_device *); #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE) typedef void (*wmi_notify_handler) (u32 value, void *context); extern acpi_status wmi_evaluate_method(const char *guid, u8 instance, u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out); extern acpi_status wmi_query_block(const char *guid, u8 instance, struct acpi_buffer *out); extern acpi_status wmi_set_block(const char *guid, u8 instance, const struct acpi_buffer *in); extern acpi_status wmi_install_notify_handler(const char *guid, wmi_notify_handler handler, void *data); extern acpi_status wmi_remove_notify_handler(const char *guid); extern acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out); extern bool wmi_has_guid(const char *guid); extern char *wmi_get_acpi_device_uid(const char *guid); #endif /* CONFIG_ACPI_WMI */ #define ACPI_VIDEO_OUTPUT_SWITCHING 0x0001 #define ACPI_VIDEO_DEVICE_POSTING 0x0002 #define ACPI_VIDEO_ROM_AVAILABLE 0x0004 #define ACPI_VIDEO_BACKLIGHT 0x0008 #define ACPI_VIDEO_BACKLIGHT_FORCE_VENDOR 0x0010 #define ACPI_VIDEO_BACKLIGHT_FORCE_VIDEO 0x0020 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VENDOR 0x0040 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VIDEO 0x0080 #define ACPI_VIDEO_BACKLIGHT_DMI_VENDOR 0x0100 #define ACPI_VIDEO_BACKLIGHT_DMI_VIDEO 0x0200 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VENDOR 0x0400 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VIDEO 0x0800 extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); extern int acpi_blacklisted(void); extern void acpi_osi_setup(char *str); extern bool acpi_osi_is_win8(void); #ifdef CONFIG_ACPI_NUMA int acpi_map_pxm_to_node(int pxm); int acpi_get_node(acpi_handle handle); /** * pxm_to_online_node - Map proximity ID to online node * @pxm: ACPI proximity ID * * This is similar to pxm_to_node(), but always returns an online * node. When the mapped node from a given proximity ID is offline, it * looks up the node distance table and returns the nearest online node. * * ACPI device drivers, which are called after the NUMA initialization has * completed in the kernel, can call this interface to obtain their device * NUMA topology from ACPI tables. Such drivers do not have to deal with * offline nodes. A node may be offline when SRAT memory entry does not exist, * or NUMA is disabled, ex. "numa=off" on x86. */ static inline int pxm_to_online_node(int pxm) { int node = pxm_to_node(pxm); return numa_map_to_online_node(node); } #else static inline int pxm_to_online_node(int pxm) { return 0; } static inline int acpi_map_pxm_to_node(int pxm) { return 0; } static inline int acpi_get_node(acpi_handle handle) { return 0; } #endif extern int acpi_paddr_to_node(u64 start_addr, u64 size); extern int pnpacpi_disabled; #define PXM_INVAL (-1) bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable); unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); int acpi_dev_get_dma_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_get_memory_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types); static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, void *arg) { return acpi_dev_filter_resource_type(ares, (unsigned long)arg); } struct acpi_device *acpi_resource_consumer(struct resource *res); int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, u32 level); int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION void __init acpi_no_s4_hw_signature(void); #endif #ifdef CONFIG_PM_SLEEP void __init acpi_old_suspend_ordering(void); void __init acpi_nvs_nosave(void); void __init acpi_nvs_nosave_s3(void); void __init acpi_sleep_no_blacklist(void); #endif /* CONFIG_PM_SLEEP */ int acpi_register_wakeup_handler( int wake_irq, bool (*wakeup)(void *context), void *context); void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context); struct acpi_osc_context { char *uuid_str; /* UUID string */ int rev; struct acpi_buffer cap; /* list of DWORD capabilities */ struct acpi_buffer ret; /* free by caller if success */ }; acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ #define OSC_CONTROL_DWORD 2 /* DWORD 3 */ /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */ #define OSC_QUERY_ENABLE 0x00000001 /* input */ #define OSC_REQUEST_ERROR 0x00000002 /* return */ #define OSC_INVALID_UUID_ERROR 0x00000004 /* return */ #define OSC_INVALID_REVISION_ERROR 0x00000008 /* return */ #define OSC_CAPABILITIES_MASK_ERROR 0x00000010 /* return */ /* Platform-Wide Capabilities _OSC: Capabilities DWORD 2: Support Field */ #define OSC_SB_PAD_SUPPORT 0x00000001 #define OSC_SB_PPC_OST_SUPPORT 0x00000002 #define OSC_SB_PR3_SUPPORT 0x00000004 #define OSC_SB_HOTPLUG_OST_SUPPORT 0x00000008 #define OSC_SB_APEI_SUPPORT 0x00000010 #define OSC_SB_CPC_SUPPORT 0x00000020 #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_PRM_SUPPORT 0x00200000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; extern bool osc_sb_cppc_not_supported; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 #define OSC_USB_DP_TUNNELING 0x00000002 #define OSC_USB_PCIE_TUNNELING 0x00000004 #define OSC_USB_XDOMAIN 0x00000008 extern u32 osc_sb_native_usb4_control; /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */ #define OSC_PCI_EXT_CONFIG_SUPPORT 0x00000001 #define OSC_PCI_ASPM_SUPPORT 0x00000002 #define OSC_PCI_CLOCK_PM_SUPPORT 0x00000004 #define OSC_PCI_SEGMENT_GROUPS_SUPPORT 0x00000008 #define OSC_PCI_MSI_SUPPORT 0x00000010 #define OSC_PCI_EDR_SUPPORT 0x00000080 #define OSC_PCI_HPX_TYPE_3_SUPPORT 0x00000100 #define OSC_PCI_SUPPORT_MASKS 0x0000019f /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */ #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 0x00000001 #define OSC_PCI_SHPC_NATIVE_HP_CONTROL 0x00000002 #define OSC_PCI_EXPRESS_PME_CONTROL 0x00000004 #define OSC_PCI_EXPRESS_AER_CONTROL 0x00000008 #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 #define OSC_PCI_CONTROL_MASKS 0x000000bf #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 #define ACPI_GSB_ACCESS_ATTRIB_WORD 0x00000008 #define ACPI_GSB_ACCESS_ATTRIB_BLOCK 0x0000000A #define ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE 0x0000000B #define ACPI_GSB_ACCESS_ATTRIB_WORD_CALL 0x0000000C #define ACPI_GSB_ACCESS_ATTRIB_BLOCK_CALL 0x0000000D #define ACPI_GSB_ACCESS_ATTRIB_RAW_BYTES 0x0000000E #define ACPI_GSB_ACCESS_ATTRIB_RAW_PROCESS 0x0000000F /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ defined(CONFIG_ACPI_CONTAINER) #define ACPI_HOTPLUG_OST #endif /* _OST Source Event Code (OSPM Action) */ #define ACPI_OST_EC_OSPM_SHUTDOWN 0x100 #define ACPI_OST_EC_OSPM_EJECT 0x103 #define ACPI_OST_EC_OSPM_INSERTION 0x200 /* _OST General Processing Status Code */ #define ACPI_OST_SC_SUCCESS 0x0 #define ACPI_OST_SC_NON_SPECIFIC_FAILURE 0x1 #define ACPI_OST_SC_UNRECOGNIZED_NOTIFY 0x2 /* _OST OS Shutdown Processing (0x100) Status Code */ #define ACPI_OST_SC_OS_SHUTDOWN_DENIED 0x80 #define ACPI_OST_SC_OS_SHUTDOWN_IN_PROGRESS 0x81 #define ACPI_OST_SC_OS_SHUTDOWN_COMPLETED 0x82 #define ACPI_OST_SC_OS_SHUTDOWN_NOT_SUPPORTED 0x83 /* _OST Ejection Request (0x3, 0x103) Status Code */ #define ACPI_OST_SC_EJECT_NOT_SUPPORTED 0x80 #define ACPI_OST_SC_DEVICE_IN_USE 0x81 #define ACPI_OST_SC_DEVICE_BUSY 0x82 #define ACPI_OST_SC_EJECT_DEPENDENCY_BUSY 0x83 #define ACPI_OST_SC_EJECT_IN_PROGRESS 0x84 /* _OST Insertion Request (0x200) Status Code */ #define ACPI_OST_SC_INSERT_IN_PROGRESS 0x80 #define ACPI_OST_SC_DRIVER_LOAD_FAILURE 0x81 #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 enum acpi_predicate { all_versions, less_than_or_equal, equal, greater_than_or_equal, }; /* Table must be terminted by a NULL entry */ struct acpi_platform_list { char oem_id[ACPI_OEM_ID_SIZE+1]; char oem_table_id[ACPI_OEM_TABLE_ID_SIZE+1]; u32 oem_revision; char *table; enum acpi_predicate pred; char *reason; u32 data; }; int acpi_match_platform_list(const struct acpi_platform_list *plat); extern void acpi_early_init(void); extern void acpi_subsystem_init(void); extern void arch_post_acpi_subsys_init(void); extern int acpi_nvs_register(__u64 start, __u64 size); extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data); const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev); const void *acpi_device_get_match_data(const struct device *dev); extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, struct property_entry *); #define ACPI_PTR(_ptr) (_ptr) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { adev->flags.visited = true; } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { adev->flags.visited = false; } enum acpi_reconfig_event { ACPI_RECONFIG_DEVICE_ADD = 0, ACPI_RECONFIG_DEVICE_REMOVE, }; int acpi_reconfig_notifier_register(struct notifier_block *nb); int acpi_reconfig_notifier_unregister(struct notifier_block *nb); #ifdef CONFIG_ACPI_GTDT int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count); int acpi_gtdt_map_ppi(int type); bool acpi_gtdt_c3stop(int type); int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count); #endif #ifndef ACPI_HAVE_ARCH_SET_ROOT_POINTER static inline void acpi_arch_set_root_pointer(u64 addr) { } #endif #ifndef ACPI_HAVE_ARCH_GET_ROOT_POINTER static inline u64 acpi_arch_get_root_pointer(void) { return 0; } #endif int acpi_get_local_address(acpi_handle handle, u32 *addr); #else /* !CONFIG_ACPI */ #define acpi_disabled 1 #define ACPI_COMPANION(dev) (NULL) #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) #define ACPI_HANDLE_FWNODE(fwnode) (NULL) #define ACPI_DEVICE_CLASS(_cls, _msk) .cls = (0), .cls_msk = (0), #include <acpi/acpi_numa.h> struct fwnode_handle; static inline bool acpi_dev_found(const char *hid) { return false; } static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) { return false; } struct acpi_device; static inline bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2) { return false; } static inline struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) { return NULL; } static inline bool acpi_reduced_hardware(void) { return false; } static inline void acpi_dev_put(struct acpi_device *adev) {} static inline bool is_acpi_node(const struct fwnode_handle *fwnode) { return false; } static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_device *to_acpi_device_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_data_node *to_acpi_data_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return false; } static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return NULL; } static inline bool has_acpi_companion(struct device *dev) { return false; } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { } static inline const char *acpi_dev_name(struct acpi_device *adev) { return NULL; } static inline struct device *acpi_get_first_physical_node(struct acpi_device *adev) { return NULL; } static inline void acpi_early_init(void) { } static inline void acpi_subsystem_init(void) { } static inline int early_acpi_boot_init(void) { return 0; } static inline int acpi_boot_init(void) { return 0; } static inline void acpi_boot_table_prepare(void) { } static inline void acpi_boot_table_init(void) { } static inline int acpi_mps_check(void) { return 0; } static inline int acpi_check_resource_conflict(struct resource *res) { return 0; } static inline int acpi_check_region(resource_size_t start, resource_size_t n, const char *name) { return 0; } struct acpi_table_header; static inline int acpi_table_parse(char *id, int (*handler)(struct acpi_table_header *)) { return -ENODEV; } static inline int acpi_nvs_register(__u64 start, __u64 size) { return 0; } static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data) { return 0; } struct acpi_device_id; static inline const struct acpi_device_id *acpi_match_device( const struct acpi_device_id *ids, const struct device *dev) { return NULL; } static inline const void *acpi_device_get_match_data(const struct device *dev) { return NULL; } static inline bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv) { return false; } static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { return NULL; } static inline int acpi_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) { return -ENODEV; } static inline int acpi_device_modalias(struct device *dev, char *buf, int size) { return -ENODEV; } static inline struct platform_device * acpi_create_platform_device(struct acpi_device *adev, struct property_entry *properties) { return NULL; } static inline bool acpi_dma_supported(const struct acpi_device *adev) { return false; } static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) { return DEV_DMA_NOT_SUPPORTED; } static inline int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset, u64 *size) { return -ENODEV; } static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { return 0; } static inline int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, const u32 *input_id) { return 0; } #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { } static inline int acpi_reconfig_notifier_register(struct notifier_block *nb) { return -EINVAL; } static inline int acpi_reconfig_notifier_unregister(struct notifier_block *nb) { return -EINVAL; } static inline struct acpi_device *acpi_resource_consumer(struct resource *res) { return NULL; } static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) { return -ENODEV; } static inline int acpi_register_wakeup_handler(int wake_irq, bool (*wakeup)(void *context), void *context) { return -ENXIO; } static inline void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context) { } #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_ioapic_add(acpi_handle root); #else static inline int acpi_ioapic_add(acpi_handle root) { return 0; } #endif #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, u32 val_a, u32 val_b)); acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); #ifdef CONFIG_X86 struct acpi_s2idle_dev_ops { struct list_head list_node; void (*prepare)(void); void (*restore)(void); }; int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); #endif /* CONFIG_X86 */ #ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else static inline void arch_reserve_mem_area(acpi_physical_address addr, size_t size) { } #endif /* CONFIG_X86 */ #else #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0) #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM) int acpi_dev_suspend(struct device *dev, bool wakeup); int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); bool acpi_storage_d3(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return 0; } static inline bool acpi_storage_d3(struct device *dev) { return false; } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) int acpi_subsys_prepare(struct device *dev); void acpi_subsys_complete(struct device *dev); int acpi_subsys_suspend_late(struct device *dev); int acpi_subsys_suspend_noirq(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); int acpi_subsys_poweroff(struct device *dev); void acpi_ec_mark_gpe_for_wake(void); void acpi_ec_set_gpe_wake_mask(u8 action); #else static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} static inline int acpi_subsys_suspend_late(struct device *dev) { return 0; } static inline int acpi_subsys_suspend_noirq(struct device *dev) { return 0; } static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } static inline void acpi_ec_mark_gpe_for_wake(void) {} static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif #ifdef CONFIG_ACPI __printf(3, 4) void acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...); void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status); #else /* !CONFIG_ACPI */ static inline __printf(3, 4) void acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {} static inline void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status) {} #endif /* !CONFIG_ACPI */ #if defined(CONFIG_ACPI) && defined(CONFIG_DYNAMIC_DEBUG) __printf(3, 4) void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const char *fmt, ...); #endif /* * acpi_handle_<level>: Print message with ACPI prefix and object path * * These interfaces acquire the global namespace mutex to obtain an object * path. In interrupt context, it shows the object path as <n/a>. */ #define acpi_handle_emerg(handle, fmt, ...) \ acpi_handle_printk(KERN_EMERG, handle, fmt, ##__VA_ARGS__) #define acpi_handle_alert(handle, fmt, ...) \ acpi_handle_printk(KERN_ALERT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_crit(handle, fmt, ...) \ acpi_handle_printk(KERN_CRIT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_err(handle, fmt, ...) \ acpi_handle_printk(KERN_ERR, handle, fmt, ##__VA_ARGS__) #define acpi_handle_warn(handle, fmt, ...) \ acpi_handle_printk(KERN_WARNING, handle, fmt, ##__VA_ARGS__) #define acpi_handle_notice(handle, fmt, ...) \ acpi_handle_printk(KERN_NOTICE, handle, fmt, ##__VA_ARGS__) #define acpi_handle_info(handle, fmt, ...) \ acpi_handle_printk(KERN_INFO, handle, fmt, ##__VA_ARGS__) #if defined(DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__) #else #if defined(CONFIG_DYNAMIC_DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ _dynamic_func_call(fmt, __acpi_handle_debug, \ handle, pr_fmt(fmt), ##__VA_ARGS__) #else #define acpi_handle_debug(handle, fmt, ...) \ ({ \ if (0) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__); \ 0; \ }) #endif #endif #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index) { return -ENXIO; } #endif static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { return acpi_dev_gpio_irq_get_by(adev, NULL, index); } /* Device properties */ #ifdef CONFIG_ACPI int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args); static inline int acpi_node_get_property_reference( const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, name, index, NR_FWNODE_REFERENCE_ARGS, args); } static inline bool acpi_dev_has_props(const struct acpi_device *adev) { return !list_empty(&adev->data.properties); } struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, const union acpi_object *properties); int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, struct acpi_probe_entry *); #define ACPI_TABLE_ID_LEN 5 /** * struct acpi_probe_entry - boot-time probing entry * @id: ACPI table name * @type: Optional subtable type to match * (if @id contains subtables) * @subtable_valid: Optional callback to check the validity of * the subtable * @probe_table: Callback to the driver being probed when table * match is successful * @probe_subtbl: Callback to the driver being probed when table and * subtable match (and optional callback is successful) * @driver_data: Sideband data provided back to the driver */ struct acpi_probe_entry { __u8 id[ACPI_TABLE_ID_LEN]; __u8 type; acpi_probe_entry_validate_subtbl subtable_valid; union { acpi_tbl_table_handler probe_table; acpi_tbl_entry_handler probe_subtbl; }; kernel_ulong_t driver_data; }; #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_table = fn, \ .driver_data = data, \ } #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id, \ subtable, valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_subtbl = fn, \ .driver_data = data, \ } #define ACPI_PROBE_TABLE(name) __##name##_acpi_probe_table #define ACPI_PROBE_TABLE_END(name) __##name##_acpi_probe_table_end int __acpi_probe_device_table(struct acpi_probe_entry *start, int nr); #define acpi_probe_device_table(t) \ ({ \ extern struct acpi_probe_entry ACPI_PROBE_TABLE(t), \ ACPI_PROBE_TABLE_END(t); \ __acpi_probe_device_table(&ACPI_PROBE_TABLE(t), \ (&ACPI_PROBE_TABLE_END(t) - \ &ACPI_PROBE_TABLE(t))); \ }) #else static inline int acpi_dev_get_property(struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return -ENXIO; } static inline int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return -ENXIO; } static inline struct fwnode_handle * acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { return NULL; } static inline struct fwnode_handle * acpi_node_get_parent(const struct fwnode_handle *fwnode) { return NULL; } static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { return ERR_PTR(-ENXIO); } static inline int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint) { return -ENXIO; } #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ = { (void *) table_id, \ (void *) subtable, \ (void *) valid, \ (void *) fn, \ (void *) data } #define acpi_probe_device_table(t) ({ int __r = 0; __r;}) #endif #ifdef CONFIG_ACPI_TABLE_UPGRADE void acpi_table_upgrade(void); #else static inline void acpi_table_upgrade(void) { } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_ACPI_WATCHDOG) extern bool acpi_has_watchdog(void); #else static inline bool acpi_has_watchdog(void) { return false; } #endif #ifdef CONFIG_ACPI_SPCR_TABLE extern bool qdf2400_e44_present; int acpi_parse_spcr(bool enable_earlycon, bool enable_console); #else static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console) { return 0; } #endif #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); #else static inline int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_LPIT int lpit_read_residency_count_address(u64 *address); #else static inline int lpit_read_residency_count_address(u64 *address) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_PPTT int acpi_pptt_cpu_is_thread(unsigned int cpu); int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); int find_acpi_cpu_cache_topology(unsigned int cpu, int level); #else static inline int acpi_pptt_cpu_is_thread(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology(unsigned int cpu, int level) { return -EINVAL; } static inline int find_acpi_cpu_topology_package(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) { return -EINVAL; } #endif #ifdef CONFIG_ACPI extern void acpi_device_notify(struct device *dev); extern void acpi_device_notify_remove(struct device *dev); #else static inline void acpi_device_notify(struct device *dev) { } static inline void acpi_device_notify_remove(struct device *dev) { } #endif #endif /*_LINUX_ACPI_H*/ |
| 70 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dccp/timer.c * * An implementation of the DCCP protocol * Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include <linux/dccp.h> #include <linux/skbuff.h> #include <linux/export.h> #include "dccp.h" /* sysctl variables governing numbers of retransmission attempts */ int sysctl_dccp_request_retries __read_mostly = TCP_SYN_RETRIES; int sysctl_dccp_retries1 __read_mostly = TCP_RETR1; int sysctl_dccp_retries2 __read_mostly = TCP_RETR2; static void dccp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; sk_error_report(sk); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_done(sk); __DCCP_INC_STATS(DCCP_MIB_ABORTONTIMEOUT); } /* A write timeout has occurred. Process the after effects. */ static int dccp_write_timeout(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); int retry_until; if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) { if (icsk->icsk_retransmits != 0) dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_dccp_request_retries; } else { if (icsk->icsk_retransmits >= sysctl_dccp_retries1) { /* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu black hole detection. :-( It is place to make it. It is not made. I do not want to make it. It is disguisting. It does not work in any case. Let me to cite the same draft, which requires for us to implement this: "The one security concern raised by this memo is that ICMP black holes are often caused by over-zealous security administrators who block all ICMP messages. It is vitally important that those who design and deploy security systems understand the impact of strict filtering on upper-layer protocols. The safest web site in the world is worthless if most TCP implementations cannot transfer data from it. It would be far nicer to have all of the black holes fixed rather than fixing all of the TCP implementations." Golden words :-). */ dst_negative_advice(sk); } retry_until = sysctl_dccp_retries2; /* * FIXME: see tcp_write_timout and tcp_out_of_resources */ } if (icsk->icsk_retransmits >= retry_until) { /* Has it gone just too far? */ dccp_write_err(sk); return 1; } return 0; } /* * The DCCP retransmit timer. */ static void dccp_retransmit_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); /* * More than 4MSL (8 minutes) has passed, a RESET(aborted) was * sent, no need to retransmit, this sock is dead. */ if (dccp_write_timeout(sk)) return; /* * We want to know the number of packets retransmitted, not the * total number of retransmissions of clones of original packets. */ if (icsk->icsk_retransmits == 0) __DCCP_INC_STATS(DCCP_MIB_TIMEOUTS); if (dccp_retransmit_skb(sk) != 0) { /* * Retransmission failed because of local congestion, * do not backoff. */ if (--icsk->icsk_retransmits == 0) icsk->icsk_retransmits = 1; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL), DCCP_RTO_MAX); return; } icsk->icsk_backoff++; icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, DCCP_RTO_MAX); if (icsk->icsk_retransmits > sysctl_dccp_retries1) __sk_dst_reset(sk); } static void dccp_write_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_retransmit_timer); struct sock *sk = &icsk->icsk_inet.sk; int event = 0; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later */ sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + (HZ / 20)); goto out; } if (sk->sk_state == DCCP_CLOSED || !icsk->icsk_pending) goto out; if (time_after(icsk->icsk_timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); goto out; } event = icsk->icsk_pending; icsk->icsk_pending = 0; switch (event) { case ICSK_TIME_RETRANS: dccp_retransmit_timer(sk); break; } out: bh_unlock_sock(sk); sock_put(sk); } static void dccp_keepalive_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); pr_err("dccp should not use a keepalive timer !\n"); sock_put(sk); } /* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */ static void dccp_delack_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_delack_timer); struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN); goto out; } if (sk->sk_state == DCCP_CLOSED || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) goto out; if (time_after(icsk->icsk_ack.timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); goto out; } icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } dccp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } out: bh_unlock_sock(sk); sock_put(sk); } /** * dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface * @t: pointer to the tasklet associated with this handler * * See the comments above %ccid_dequeueing_decision for supported modes. */ static void dccp_write_xmitlet(struct tasklet_struct *t) { struct dccp_sock *dp = from_tasklet(dp, t, dccps_xmitlet); struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) sk_reset_timer(sk, &dccp_sk(sk)->dccps_xmit_timer, jiffies + 1); else dccp_write_xmit(sk); bh_unlock_sock(sk); sock_put(sk); } static void dccp_write_xmit_timer(struct timer_list *t) { struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer); dccp_write_xmitlet(&dp->dccps_xmitlet); } void dccp_init_xmit_timers(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); tasklet_setup(&dp->dccps_xmitlet, dccp_write_xmitlet); timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0); inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer, &dccp_keepalive_timer); } static ktime_t dccp_timestamp_seed; /** * dccp_timestamp - 10s of microseconds time source * Returns the number of 10s of microseconds since loading DCCP. This is native * DCCP time difference format (RFC 4340, sec. 13). * Please note: This will wrap around about circa every 11.9 hours. */ u32 dccp_timestamp(void) { u64 delta = (u64)ktime_us_delta(ktime_get_real(), dccp_timestamp_seed); do_div(delta, 10); return delta; } EXPORT_SYMBOL_GPL(dccp_timestamp); void __init dccp_timestamping_init(void) { dccp_timestamp_seed = ktime_get_real(); } |
| 72 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_TLB_H #define _ASM_X86_TLB_H #define tlb_start_vma(tlb, vma) do { } while (0) #define tlb_end_vma(tlb, vma) do { } while (0) #define tlb_flush tlb_flush static inline void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> static inline void tlb_flush(struct mmu_gather *tlb) { unsigned long start = 0UL, end = TLB_FLUSH_ALL; unsigned int stride_shift = tlb_get_unmap_shift(tlb); if (!tlb->fullmm && !tlb->need_flush_all) { start = tlb->start; end = tlb->end; } flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables); } /* * While x86 architecture in general requires an IPI to perform TLB * shootdown, enablement code for several hypervisors overrides * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing * a hypercall. To keep software pagetable walkers safe in this case we * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h * for more details. */ static inline void __tlb_remove_table(void *table) { free_page_and_swap_cache(table); } #endif /* _ASM_X86_TLB_H */ |
| 2 2 954 952 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 | // SPDX-License-Identifier: GPL-2.0-or-later /* * "LAPB via ethernet" driver release 001 * * This code REQUIRES 2.1.15 or higher/ NET3.038 * * This is a "pseudo" network driver to allow LAPB over Ethernet. * * This driver can use any ethernet destination address, and can be * limited to accept frames from one dedicated ethernet card only. * * History * LAPBETH 001 Jonathan Naylor Cloned from bpqether.c * 2000-10-29 Henner Eisen lapb_data_indication() return status. * 2000-11-14 Henner Eisen dev_hold/put, NETDEV_GOING_DOWN support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/stat.h> #include <linux/module.h> #include <linux/lapb.h> #include <linux/init.h> #include <net/x25device.h> static const u8 bcast_addr[6] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; /* If this number is made larger, check that the temporary string buffer * in lapbeth_new_device is large enough to store the probe device name. */ #define MAXLAPBDEV 100 struct lapbethdev { struct list_head node; struct net_device *ethdev; /* link to ethernet device */ struct net_device *axdev; /* lapbeth device (lapb#) */ bool up; spinlock_t up_lock; /* Protects "up" */ struct sk_buff_head rx_queue; struct napi_struct napi; }; static LIST_HEAD(lapbeth_devices); static void lapbeth_connected(struct net_device *dev, int reason); static void lapbeth_disconnected(struct net_device *dev, int reason); /* ------------------------------------------------------------------------ */ /* Get the LAPB device for the ethernet device */ static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev) { struct lapbethdev *lapbeth; list_for_each_entry_rcu(lapbeth, &lapbeth_devices, node, lockdep_rtnl_is_held()) { if (lapbeth->ethdev == dev) return lapbeth; } return NULL; } static __inline__ int dev_is_ethdev(struct net_device *dev) { return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); } /* ------------------------------------------------------------------------ */ static int lapbeth_napi_poll(struct napi_struct *napi, int budget) { struct lapbethdev *lapbeth = container_of(napi, struct lapbethdev, napi); struct sk_buff *skb; int processed = 0; for (; processed < budget; ++processed) { skb = skb_dequeue(&lapbeth->rx_queue); if (!skb) break; netif_receive_skb_core(skb); } if (processed < budget) napi_complete(napi); return processed; } /* Receive a LAPB frame via an ethernet interface. */ static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { int len, err; struct lapbethdev *lapbeth; if (dev_net(dev) != &init_net) goto drop; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return NET_RX_DROP; if (!pskb_may_pull(skb, 2)) goto drop; rcu_read_lock(); lapbeth = lapbeth_get_x25_dev(dev); if (!lapbeth) goto drop_unlock_rcu; spin_lock_bh(&lapbeth->up_lock); if (!lapbeth->up) goto drop_unlock; len = skb->data[0] + skb->data[1] * 256; dev->stats.rx_packets++; dev->stats.rx_bytes += len; skb_pull(skb, 2); /* Remove the length bytes */ skb_trim(skb, len); /* Set the length of the data */ err = lapb_data_received(lapbeth->axdev, skb); if (err != LAPB_OK) { printk(KERN_DEBUG "lapbether: lapb_data_received err - %d\n", err); goto drop_unlock; } out: spin_unlock_bh(&lapbeth->up_lock); rcu_read_unlock(); return 0; drop_unlock: kfree_skb(skb); goto out; drop_unlock_rcu: rcu_read_unlock(); drop: kfree_skb(skb); return 0; } static int lapbeth_data_indication(struct net_device *dev, struct sk_buff *skb) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; if (skb_cow(skb, 1)) { kfree_skb(skb); return NET_RX_DROP; } skb_push(skb, 1); ptr = skb->data; *ptr = X25_IFACE_DATA; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); return NET_RX_SUCCESS; } /* Send a LAPB frame via an ethernet interface */ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb, struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; spin_lock_bh(&lapbeth->up_lock); if (!lapbeth->up) goto drop; /* There should be a pseudo header of 1 byte added by upper layers. * Check to make sure it is there before reading it. */ if (skb->len < 1) goto drop; switch (skb->data[0]) { case X25_IFACE_DATA: break; case X25_IFACE_CONNECT: err = lapb_connect_request(dev); if (err == LAPB_CONNECTED) lapbeth_connected(dev, LAPB_OK); else if (err != LAPB_OK) pr_err("lapb_connect_request error: %d\n", err); goto drop; case X25_IFACE_DISCONNECT: err = lapb_disconnect_request(dev); if (err == LAPB_NOTCONNECTED) lapbeth_disconnected(dev, LAPB_OK); else if (err != LAPB_OK) pr_err("lapb_disconnect_request err: %d\n", err); fallthrough; default: goto drop; } skb_pull(skb, 1); err = lapb_data_request(dev, skb); if (err != LAPB_OK) { pr_err("lapb_data_request error - %d\n", err); goto drop; } out: spin_unlock_bh(&lapbeth->up_lock); return NETDEV_TX_OK; drop: kfree_skb(skb); goto out; } static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) { struct lapbethdev *lapbeth = netdev_priv(ndev); unsigned char *ptr; struct net_device *dev; int size = skb->len; ptr = skb_push(skb, 2); *ptr++ = size % 256; *ptr++ = size / 256; ndev->stats.tx_packets++; ndev->stats.tx_bytes += size; skb->dev = dev = lapbeth->ethdev; skb->protocol = htons(ETH_P_DEC); skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0); dev_queue_xmit(skb); } static void lapbeth_connected(struct net_device *dev, int reason) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); if (!skb) return; ptr = skb_put(skb, 1); *ptr = X25_IFACE_CONNECT; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); } static void lapbeth_disconnected(struct net_device *dev, int reason) { struct lapbethdev *lapbeth = netdev_priv(dev); unsigned char *ptr; struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); if (!skb) return; ptr = skb_put(skb, 1); *ptr = X25_IFACE_DISCONNECT; skb->protocol = x25_type_trans(skb, dev); skb_queue_tail(&lapbeth->rx_queue, skb); napi_schedule(&lapbeth->napi); } /* Set AX.25 callsign */ static int lapbeth_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = addr; memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); return 0; } static const struct lapb_register_struct lapbeth_callbacks = { .connect_confirmation = lapbeth_connected, .connect_indication = lapbeth_connected, .disconnect_confirmation = lapbeth_disconnected, .disconnect_indication = lapbeth_disconnected, .data_indication = lapbeth_data_indication, .data_transmit = lapbeth_data_transmit, }; /* open/close a device */ static int lapbeth_open(struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; napi_enable(&lapbeth->napi); err = lapb_register(dev, &lapbeth_callbacks); if (err != LAPB_OK) { napi_disable(&lapbeth->napi); pr_err("lapb_register error: %d\n", err); return -ENODEV; } spin_lock_bh(&lapbeth->up_lock); lapbeth->up = true; spin_unlock_bh(&lapbeth->up_lock); return 0; } static int lapbeth_close(struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; spin_lock_bh(&lapbeth->up_lock); lapbeth->up = false; spin_unlock_bh(&lapbeth->up_lock); err = lapb_unregister(dev); if (err != LAPB_OK) pr_err("lapb_unregister error: %d\n", err); napi_disable(&lapbeth->napi); return 0; } /* ------------------------------------------------------------------------ */ static const struct net_device_ops lapbeth_netdev_ops = { .ndo_open = lapbeth_open, .ndo_stop = lapbeth_close, .ndo_start_xmit = lapbeth_xmit, .ndo_set_mac_address = lapbeth_set_mac_address, }; static void lapbeth_setup(struct net_device *dev) { dev->netdev_ops = &lapbeth_netdev_ops; dev->needs_free_netdev = true; dev->type = ARPHRD_X25; dev->hard_header_len = 0; dev->mtu = 1000; dev->addr_len = 0; } /* Setup a new device. */ static int lapbeth_new_device(struct net_device *dev) { struct net_device *ndev; struct lapbethdev *lapbeth; int rc = -ENOMEM; ASSERT_RTNL(); if (dev->type != ARPHRD_ETHER) return -EINVAL; ndev = alloc_netdev(sizeof(*lapbeth), "lapb%d", NET_NAME_UNKNOWN, lapbeth_setup); if (!ndev) goto out; /* When transmitting data: * first this driver removes a pseudo header of 1 byte, * then the lapb module prepends an LAPB header of at most 3 bytes, * then this driver prepends a length field of 2 bytes, * then the underlying Ethernet device prepends its own header. */ ndev->needed_headroom = -1 + 3 + 2 + dev->hard_header_len + dev->needed_headroom; ndev->needed_tailroom = dev->needed_tailroom; lapbeth = netdev_priv(ndev); lapbeth->axdev = ndev; dev_hold(dev); lapbeth->ethdev = dev; lapbeth->up = false; spin_lock_init(&lapbeth->up_lock); skb_queue_head_init(&lapbeth->rx_queue); netif_napi_add(ndev, &lapbeth->napi, lapbeth_napi_poll, 16); rc = -EIO; if (register_netdevice(ndev)) goto fail; list_add_rcu(&lapbeth->node, &lapbeth_devices); rc = 0; out: return rc; fail: dev_put(dev); free_netdev(ndev); goto out; } /* Free a lapb network device. */ static void lapbeth_free_device(struct lapbethdev *lapbeth) { dev_put(lapbeth->ethdev); list_del_rcu(&lapbeth->node); unregister_netdevice(lapbeth->axdev); } /* Handle device status changes. * * Called from notifier with RTNL held. */ static int lapbeth_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct lapbethdev *lapbeth; struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev_net(dev) != &init_net) return NOTIFY_DONE; if (!dev_is_ethdev(dev) && !lapbeth_get_x25_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: /* New ethernet device -> new LAPB interface */ if (!lapbeth_get_x25_dev(dev)) lapbeth_new_device(dev); break; case NETDEV_GOING_DOWN: /* ethernet device closes -> close LAPB interface */ lapbeth = lapbeth_get_x25_dev(dev); if (lapbeth) dev_close(lapbeth->axdev); break; case NETDEV_UNREGISTER: /* ethernet device disappears -> remove LAPB interface */ lapbeth = lapbeth_get_x25_dev(dev); if (lapbeth) lapbeth_free_device(lapbeth); break; } return NOTIFY_DONE; } /* ------------------------------------------------------------------------ */ static struct packet_type lapbeth_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_DEC), .func = lapbeth_rcv, }; static struct notifier_block lapbeth_dev_notifier = { .notifier_call = lapbeth_device_event, }; static const char banner[] __initconst = KERN_INFO "LAPB Ethernet driver version 0.02\n"; static int __init lapbeth_init_driver(void) { dev_add_pack(&lapbeth_packet_type); register_netdevice_notifier(&lapbeth_dev_notifier); printk(banner); return 0; } module_init(lapbeth_init_driver); static void __exit lapbeth_cleanup_driver(void) { struct lapbethdev *lapbeth; struct list_head *entry, *tmp; dev_remove_pack(&lapbeth_packet_type); unregister_netdevice_notifier(&lapbeth_dev_notifier); rtnl_lock(); list_for_each_safe(entry, tmp, &lapbeth_devices) { lapbeth = list_entry(entry, struct lapbethdev, node); dev_put(lapbeth->ethdev); unregister_netdevice(lapbeth->axdev); } rtnl_unlock(); } module_exit(lapbeth_cleanup_driver); MODULE_AUTHOR("Jonathan Naylor <g4klx@g4klx.demon.co.uk>"); MODULE_DESCRIPTION("The unofficial LAPB over Ethernet driver"); MODULE_LICENSE("GPL"); |
| 10 8 5 3 10 10 5 5 5 8 8 8 12 1 10 1 1 6 5 5 5 5 5 2 2 3 3 2 1 6 2 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 | // SPDX-License-Identifier: GPL-2.0-or-later /* L2TPv3 IP encapsulation support * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/ioctls.h> #include <linux/icmp.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/random.h> #include <linux/socket.h> #include <linux/l2tp.h> #include <linux/in.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> #include "l2tp_core.h" struct l2tp_ip_sock { /* inet_sock has to be the first member of l2tp_ip_sock */ struct inet_sock inet; u32 conn_id; u32 peer_conn_id; }; static DEFINE_RWLOCK(l2tp_ip_lock); static struct hlist_head l2tp_ip_table; static struct hlist_head l2tp_ip_bind_table; static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) { return (struct l2tp_ip_sock *)sk; } static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr, __be32 raddr, int dif, u32 tunnel_id) { struct sock *sk; sk_for_each_bound(sk, &l2tp_ip_bind_table) { const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); const struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_bound_dev_if && dif && sk->sk_bound_dev_if != dif) continue; if (inet->inet_rcv_saddr && laddr && inet->inet_rcv_saddr != laddr) continue; if (inet->inet_daddr && raddr && inet->inet_daddr != raddr) continue; if (l2tp->conn_id != tunnel_id) continue; goto found; } sk = NULL; found: return sk; } /* When processing receive frames, there are two cases to * consider. Data frames consist of a non-zero session-id and an * optional cookie. Control frames consist of a regular L2TP header * preceded by 32-bits of zeros. * * L2TPv3 Session Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Cookie (optional, maximum 64 bits)... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 Control Message Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | (32 bits of zeros) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Control Connection ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns | Nr | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * All control frames are passed to userspace. */ static int l2tp_ip_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct sock *sk; u32 session_id; u32 tunnel_id; unsigned char *ptr, *optr; struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; if (!pskb_may_pull(skb, 4)) goto discard; /* Point to L2TP header */ optr = skb->data; ptr = skb->data; session_id = ntohl(*((__be32 *)ptr)); ptr += 4; /* RFC3931: L2TP/IP packets have the first 4 bytes containing * the session_id. If it is 0, the packet is a L2TP control * frame and the session_id value can be discarded. */ if (session_id == 0) { __skb_pull(skb, 4); goto pass_up; } /* Ok, this is a data packet. Lookup the session. */ session = l2tp_session_get(net, session_id); if (!session) goto discard; tunnel = session->tunnel; if (!tunnel) goto discard_sess; if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); return 0; pass_up: /* Get the tunnel_id from the L2TP header */ if (!pskb_may_pull(skb, 12)) goto discard; if ((skb->data[0] & 0xc0) != 0xc0) goto discard; tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = (struct iphdr *)skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb), tunnel_id); if (!sk) { read_unlock_bh(&l2tp_ip_lock); goto discard; } sock_hold(sk); read_unlock_bh(&l2tp_ip_lock); if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); discard_sess: l2tp_session_dec_refcount(session); goto discard; discard_put: sock_put(sk); discard: kfree_skb(skb); return 0; } static int l2tp_ip_hash(struct sock *sk) { if (sk_unhashed(sk)) { write_lock_bh(&l2tp_ip_lock); sk_add_node(sk, &l2tp_ip_table); write_unlock_bh(&l2tp_ip_lock); } return 0; } static void l2tp_ip_unhash(struct sock *sk) { if (sk_unhashed(sk)) return; write_lock_bh(&l2tp_ip_lock); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); } static int l2tp_ip_open(struct sock *sk) { /* Prevent autobind. We don't have ports. */ inet_sk(sk)->inet_num = IPPROTO_L2TP; l2tp_ip_hash(sk); return 0; } static void l2tp_ip_close(struct sock *sk, long timeout) { write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); sk_common_release(sk); } static void l2tp_ip_destroy_sock(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); struct sk_buff *skb; while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); if (tunnel) l2tp_tunnel_delete(tunnel); } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr; struct net *net = sock_net(sk); int ret; int chk_addr_ret; if (addr_len < sizeof(struct sockaddr_l2tpip)) return -EINVAL; if (addr->l2tp_family != AF_INET) return -EINVAL; lock_sock(sk); ret = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; if (sk->sk_state != TCP_CLOSE) goto out; chk_addr_ret = inet_addr_type(net, addr->l2tp_addr.s_addr); ret = -EADDRNOTAVAIL; if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; if (addr->l2tp_addr.s_addr) { inet->inet_rcv_saddr = addr->l2tp_addr.s_addr; inet->inet_saddr = addr->l2tp_addr.s_addr; } if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ write_lock_bh(&l2tp_ip_lock); if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0, sk->sk_bound_dev_if, addr->l2tp_conn_id)) { write_unlock_bh(&l2tp_ip_lock); ret = -EADDRINUSE; goto out; } sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; sk_add_bind_node(sk, &l2tp_ip_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); out: release_sock(sk); return ret; } static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; int rc; if (addr_len < sizeof(*lsa)) return -EINVAL; if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) return -EINVAL; lock_sock(sk); /* Must bind first - autobinding does not work */ if (sock_flag(sk, SOCK_ZAPPED)) { rc = -EINVAL; goto out_sk; } rc = __ip4_datagram_connect(sk, uaddr, addr_len); if (rc < 0) goto out_sk; l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_add_bind_node(sk, &l2tp_ip_bind_table); write_unlock_bh(&l2tp_ip_lock); out_sk: release_sock(sk); return rc; } static int l2tp_ip_disconnect(struct sock *sk, int flags) { if (sock_flag(sk, SOCK_ZAPPED)) return 0; return __udp_disconnect(sk, flags); } static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk); struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; memset(lsa, 0, sizeof(*lsa)); lsa->l2tp_family = AF_INET; if (peer) { if (!inet->inet_dport) return -ENOTCONN; lsa->l2tp_conn_id = lsk->peer_conn_id; lsa->l2tp_addr.s_addr = inet->inet_daddr; } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; lsa->l2tp_conn_id = lsk->conn_id; lsa->l2tp_addr.s_addr = addr; } return sizeof(*lsa); } static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) { int rc; /* Charge it to the socket, dropping if the queue is full. */ rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) goto drop; return 0; drop: IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); return 0; } /* Userspace will call sendmsg() on the tunnel socket to send L2TP * control frames. */ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct sk_buff *skb; int rc; struct inet_sock *inet = inet_sk(sk); struct rtable *rt = NULL; struct flowi4 *fl4; int connected = 0; __be32 daddr; lock_sock(sk); rc = -ENOTCONN; if (sock_flag(sk, SOCK_DEAD)) goto out; /* Get and verify the address. */ if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_l2tpip *, lip, msg->msg_name); rc = -EINVAL; if (msg->msg_namelen < sizeof(*lip)) goto out; if (lip->l2tp_family != AF_INET) { rc = -EAFNOSUPPORT; if (lip->l2tp_family != AF_UNSPEC) goto out; } daddr = lip->l2tp_addr.s_addr; } else { rc = -EDESTADDRREQ; if (sk->sk_state != TCP_ESTABLISHED) goto out; daddr = inet->inet_daddr; connected = 1; } /* Allocate a socket buffer */ rc = -ENOMEM; skb = sock_wmalloc(sk, 2 + NET_SKB_PAD + sizeof(struct iphdr) + 4 + len, 0, GFP_KERNEL); if (!skb) goto error; /* Reserve space for headers, putting IP header on 4-byte boundary. */ skb_reserve(skb, 2 + NET_SKB_PAD); skb_reset_network_header(skb); skb_reserve(skb, sizeof(struct iphdr)); skb_reset_transport_header(skb); /* Insert 0 session_id */ *((__be32 *)skb_put(skb, 4)) = 0; /* Copy user data into skb */ rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc < 0) { kfree_skb(skb); goto error; } fl4 = &inet->cork.fl.u.ip4; if (connected) rt = (struct rtable *)__sk_dst_check(sk, 0); rcu_read_lock(); if (!rt) { const struct ip_options_rcu *inet_opt; inet_opt = rcu_dereference(inet->inet_opt); /* Use correct destination address if we have options. */ if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; if (connected) { sk_setup_caps(sk, &rt->dst); } else { skb_dst_set(skb, &rt->dst); goto xmit; } } /* We don't need to clone dst here, it is guaranteed to not disappear. * __dev_xmit_skb() might force a refcount if needed. */ skb_dst_set_noref(skb, &rt->dst); xmit: /* Queue the packet to IP for output */ rc = ip_queue_xmit(sk, skb, &inet->cork.fl); rcu_read_unlock(); error: if (rc >= 0) rc = len; out: release_sock(sk); return rc; no_route: rcu_read_unlock(); IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); rc = -EHOSTUNREACH; goto out; } static int l2tp_ip_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); size_t copied = 0; int err = -EOPNOTSUPP; DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; if (flags & MSG_OOB) goto out; skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto done; sock_recv_timestamp(msg, sk, skb); /* Copy the address. */ if (sin) { sin->sin_family = AF_INET; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; sin->sin_port = 0; memset(&sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); if (flags & MSG_TRUNC) copied = skb->len; done: skb_free_datagram(sk, skb); out: return err ? err : copied; } int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct sk_buff *skb; int amount; switch (cmd) { case SIOCOUTQ: amount = sk_wmem_alloc_get(sk); break; case SIOCINQ: spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; spin_unlock_bh(&sk->sk_receive_queue.lock); break; default: return -ENOIOCTLCMD; } return put_user(amount, (int __user *)arg); } EXPORT_SYMBOL_GPL(l2tp_ioctl); static struct proto l2tp_ip_prot = { .name = "L2TP/IP", .owner = THIS_MODULE, .init = l2tp_ip_open, .close = l2tp_ip_close, .bind = l2tp_ip_bind, .connect = l2tp_ip_connect, .disconnect = l2tp_ip_disconnect, .ioctl = l2tp_ioctl, .destroy = l2tp_ip_destroy_sock, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .sendmsg = l2tp_ip_sendmsg, .recvmsg = l2tp_ip_recvmsg, .backlog_rcv = l2tp_ip_backlog_recv, .hash = l2tp_ip_hash, .unhash = l2tp_ip_unhash, .obj_size = sizeof(struct l2tp_ip_sock), }; static const struct proto_ops l2tp_ip_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = inet_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = l2tp_ip_getname, .poll = datagram_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; static struct inet_protosw l2tp_ip_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_L2TP, .prot = &l2tp_ip_prot, .ops = &l2tp_ip_ops, }; static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, }; static int __init l2tp_ip_init(void) { int err; pr_info("L2TP IP encapsulation support (L2TPv3)\n"); err = proto_register(&l2tp_ip_prot, 1); if (err != 0) goto out; err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); if (err) goto out1; inet_register_protosw(&l2tp_ip_protosw); return 0; out1: proto_unregister(&l2tp_ip_prot); out: return err; } static void __exit l2tp_ip_exit(void) { inet_unregister_protosw(&l2tp_ip_protosw); inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip_prot); } module_init(l2tp_ip_init); module_exit(l2tp_ip_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP over IP"); MODULE_VERSION("1.0"); /* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like * enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); MODULE_ALIAS_NET_PF_PROTO(PF_INET, IPPROTO_L2TP); |
| 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> * * Architecture independence: * Copyright (c) 2005, Bull S.A. * Written by Pierre Peiffer <pierre.peiffer@bull.net> */ /* * Extents support for EXT4 * * TODO: * - ext4*_error() should be used in some situations * - analyze all BUG()/BUG_ON(), use -EIO where appropriate * - smart tree reduction */ #include <linux/fs.h> #include <linux/time.h> #include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fiemap.h> #include <linux/backing-dev.h> #include <linux/iomap.h> #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" #include <trace/events/ext4.h> /* * used by extent splitting. */ #define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \ due to ENOSPC */ #define EXT4_EXT_MARK_UNWRIT1 0x2 /* mark first half unwritten */ #define EXT4_EXT_MARK_UNWRIT2 0x4 /* mark second half unwritten */ #define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */ #define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */ static __le32 ext4_extent_block_csum(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)eh, EXT4_EXTENT_TAIL_OFFSET(eh)); return cpu_to_le32(csum); } static int ext4_extent_block_csum_verify(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent_tail *et; if (!ext4_has_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); if (et->et_checksum != ext4_extent_block_csum(inode, eh)) return 0; return 1; } static void ext4_extent_block_csum_set(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent_tail *et; if (!ext4_has_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); et->et_checksum = ext4_extent_block_csum(inode, eh); } static int ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, ext4_lblk_t split, int split_flag, int flags); static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) { /* * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; } /* * Make sure 'handle' has at least 'check_cred' credits. If not, restart * transaction with 'restart_cred' credits. The function drops i_data_sem * when restarting transaction and gets it after transaction is restarted. * * The function returns 0 on success, 1 if transaction had to be restarted, * and < 0 in case of fatal error. */ int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, int check_cred, int restart_cred, int revoke_cred) { int ret; int dropped = 0; ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred, revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped)); if (dropped) down_write(&EXT4_I(inode)->i_data_sem); return ret; } /* * could return: * - EROFS * - ENOMEM */ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { int err = 0; if (path->p_bh) { /* path points to block */ BUFFER_TRACE(path->p_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, path->p_bh, EXT4_JTR_NONE); /* * The extent buffer's verified bit will be set again in * __ext4_ext_dirty(). We could leave an inconsistent * buffer if the extents updating procudure break off du * to some error happens, force to check it again. */ if (!err) clear_buffer_verified(path->p_bh); } /* path points to leaf/index in inode body */ /* we use in-core data, no need to protect them */ return err; } /* * could return: * - EROFS * - ENOMEM * - EIO */ static int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { int err; WARN_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (path->p_bh) { ext4_extent_block_csum_set(inode, ext_block_hdr(path->p_bh)); /* path points to block */ err = __ext4_handle_dirty_metadata(where, line, handle, inode, path->p_bh); /* Extents updating done, re-set verified flag */ if (!err) set_buffer_verified(path->p_bh); } else { /* path points to leaf/index in inode body */ err = ext4_mark_inode_dirty(handle, inode); } return err; } #define ext4_ext_dirty(handle, inode, path) \ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { if (path) { int depth = path->p_depth; struct ext4_extent *ex; /* * Try to predict block placement assuming that we are * filling in a file which will eventually be * non-sparse --- i.e., in the case of libbfd writing * an ELF object sections out-of-order but in a way * the eventually results in a contiguous object or * executable file, or some database extending a table * space file. However, this is actually somewhat * non-ideal if we are writing a sparse file such as * qemu or KVM writing a raw image file that is going * to stay fairly sparse, since it will end up * fragmenting the file system's free space. Maybe we * should have some hueristics or some way to allow * userspace to pass a hint to file system, * especially if the latter case turns out to be * common. */ ex = path[depth].p_ext; if (ex) { ext4_fsblk_t ext_pblk = ext4_ext_pblock(ex); ext4_lblk_t ext_block = le32_to_cpu(ex->ee_block); if (block > ext_block) return ext_pblk + (block - ext_block); else return ext_pblk - (ext_block - block); } /* it looks like index is empty; * try to find starting block from index itself */ if (path[depth].p_bh) return path[depth].p_bh->b_blocknr; } /* OK. use inode's group */ return ext4_inode_to_goal_block(inode); } /* * Allocation for a meta data block */ static ext4_fsblk_t ext4_ext_new_meta_block(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex, int *err, unsigned int flags) { ext4_fsblk_t goal, newblock; goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block)); newblock = ext4_new_meta_blocks(handle, inode, goal, flags, NULL, err); return newblock; } static inline int ext4_ext_space_block(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent); #ifdef AGGRESSIVE_TEST if (!check && size > 6) size = 6; #endif return size; } static inline int ext4_ext_space_block_idx(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent_idx); #ifdef AGGRESSIVE_TEST if (!check && size > 5) size = 5; #endif return size; } static inline int ext4_ext_space_root(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent); #ifdef AGGRESSIVE_TEST if (!check && size > 3) size = 3; #endif return size; } static inline int ext4_ext_space_root_idx(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent_idx); #ifdef AGGRESSIVE_TEST if (!check && size > 4) size = 4; #endif return size; } static inline int ext4_force_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, ext4_lblk_t lblk, int nofail) { struct ext4_ext_path *path = *ppath; int unwritten = ext4_ext_is_unwritten(path[path->p_depth].p_ext); int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO; if (nofail) flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL; return ext4_split_extent_at(handle, inode, ppath, lblk, unwritten ? EXT4_EXT_MARK_UNWRIT1|EXT4_EXT_MARK_UNWRIT2 : 0, flags); } static int ext4_ext_max_entries(struct inode *inode, int depth) { int max; if (depth == ext_depth(inode)) { if (depth == 0) max = ext4_ext_space_root(inode, 1); else max = ext4_ext_space_root_idx(inode, 1); } else { if (depth == 0) max = ext4_ext_space_block(inode, 1); else max = ext4_ext_space_block_idx(inode, 1); } return max; } static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); /* * We allow neither: * - zero length * - overflow/wrap-around */ if (lblock + len <= lblock) return 0; return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, struct ext4_extent_idx *ext_idx) { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, struct ext4_extent_header *eh, ext4_lblk_t lblk, ext4_fsblk_t *pblk, int depth) { unsigned short entries; ext4_lblk_t lblock = 0; ext4_lblk_t cur = 0; if (eh->eh_entries == 0) return 1; entries = le16_to_cpu(eh->eh_entries); if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); /* * The logical block in the first entry should equal to * the number in the index block. */ if (depth != ext_depth(inode) && lblk != le32_to_cpu(ext->ee_block)) return 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); if (lblock < cur) { *pblk = ext4_ext_pblock(ext); return 0; } cur = lblock + ext4_ext_get_actual_len(ext); ext++; entries--; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); /* * The logical block in the first entry should equal to * the number in the parent index block. */ if (depth != ext_depth(inode) && lblk != le32_to_cpu(ext_idx->ei_block)) return 0; while (entries) { if (!ext4_valid_extent_idx(inode, ext_idx)) return 0; /* Check for overlapping index extents */ lblock = le32_to_cpu(ext_idx->ei_block); if (lblock < cur) { *pblk = ext4_idx_pblock(ext_idx); return 0; } ext_idx++; entries--; cur = lblock + 1; } } return 1; } static int __ext4_ext_check(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_header *eh, int depth, ext4_fsblk_t pblk, ext4_lblk_t lblk) { const char *error_msg; int max = 0, err = -EFSCORRUPTED; if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) { error_msg = "invalid magic"; goto corrupted; } if (unlikely(le16_to_cpu(eh->eh_depth) != depth)) { error_msg = "unexpected eh_depth"; goto corrupted; } if (unlikely(eh->eh_max == 0)) { error_msg = "invalid eh_max"; goto corrupted; } max = ext4_ext_max_entries(inode, depth); if (unlikely(le16_to_cpu(eh->eh_max) > max)) { error_msg = "too large eh_max"; goto corrupted; } if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) { error_msg = "invalid eh_entries"; goto corrupted; } if (unlikely((eh->eh_entries == 0) && (depth > 0))) { error_msg = "eh_entries is 0 but eh_depth is > 0"; goto corrupted; } if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; } if (unlikely(depth > 32)) { error_msg = "too large eh_depth"; goto corrupted; } /* Verify checksum on non-root extent tree nodes */ if (ext_depth(inode) != depth && !ext4_extent_block_csum_verify(inode, eh)) { error_msg = "extent tree corrupted"; err = -EFSBADCRC; goto corrupted; } return 0; corrupted: ext4_error_inode_err(inode, function, line, 0, -err, "pblk %llu bad header/extent: %s - magic %x, " "entries %u, max %u(%u), depth %u(%u)", (unsigned long long) pblk, error_msg, le16_to_cpu(eh->eh_magic), le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), max, le16_to_cpu(eh->eh_depth), depth); return err; } #define ext4_ext_check(inode, eh, depth, pblk) \ __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk), 0) int ext4_ext_check_inode(struct inode *inode) { return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0); } static void ext4_cache_extents(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); ext4_lblk_t prev = 0; int i; for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { unsigned int status = EXTENT_STATUS_WRITTEN; ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); int len = ext4_ext_get_actual_len(ex); if (prev && (prev != lblk)) ext4_es_cache_extent(inode, prev, lblk - prev, ~0, EXTENT_STATUS_HOLE); if (ext4_ext_is_unwritten(ex)) status = EXTENT_STATUS_UNWRITTEN; ext4_es_cache_extent(inode, lblk, len, ext4_ext_pblock(ex), status); prev = lblk + len; } } static struct buffer_head * __read_extent_tree_block(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_idx *idx, int depth, int flags) { struct buffer_head *bh; int err; gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS; ext4_fsblk_t pblk; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; pblk = ext4_idx_pblock(idx); bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); if (!bh_uptodate_or_lock(bh)) { trace_ext4_ext_load_extent(inode, pblk, _RET_IP_); err = ext4_read_bh(bh, 0, NULL); if (err < 0) goto errout; } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; err = __ext4_ext_check(function, line, inode, ext_block_hdr(bh), depth, pblk, le32_to_cpu(idx->ei_block)); if (err) goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries */ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) { struct ext4_extent_header *eh = ext_block_hdr(bh); ext4_cache_extents(inode, eh); } return bh; errout: put_bh(bh); return ERR_PTR(err); } #define read_extent_tree_block(inode, idx, depth, flags) \ __read_extent_tree_block(__func__, __LINE__, (inode), (idx), \ (depth), (flags)) /* * This function is called to cache a file's extent information in the * extent status tree */ int ext4_ext_precache(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_ext_path *path = NULL; struct buffer_head *bh; int i = 0, depth, ret = 0; if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return 0; /* not an extent-mapped inode */ down_read(&ei->i_data_sem); depth = ext_depth(inode); /* Don't cache anything if there are no external extent blocks */ if (!depth) { up_read(&ei->i_data_sem); return ret; } path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), GFP_NOFS); if (path == NULL) { up_read(&ei->i_data_sem); return -ENOMEM; } path[0].p_hdr = ext_inode_hdr(inode); ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0); if (ret) goto out; path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr); while (i >= 0) { /* * If this is a leaf block or we've reached the end of * the index block, go up */ if ((i == depth) || path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) { brelse(path[i].p_bh); path[i].p_bh = NULL; i--; continue; } bh = read_extent_tree_block(inode, path[i].p_idx++, depth - i - 1, EXT4_EX_FORCE_CACHE); if (IS_ERR(bh)) { ret = PTR_ERR(bh); break; } i++; path[i].p_bh = bh; path[i].p_hdr = ext_block_hdr(bh); path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr); } ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED); out: up_read(&ei->i_data_sem); ext4_ext_drop_refs(path); kfree(path); return ret; } #ifdef EXT_DEBUG static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { int k, l = path->p_depth; ext_debug(inode, "path:"); for (k = 0; k <= l; k++, path++) { if (path->p_idx) { ext_debug(inode, " %d->%llu", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); } else if (path->p_ext) { ext_debug(inode, " %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext), ext4_ext_pblock(path->p_ext)); } else ext_debug(inode, " []"); } ext_debug(inode, "\n"); } static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) { int depth = ext_depth(inode); struct ext4_extent_header *eh; struct ext4_extent *ex; int i; if (!path) return; eh = path[depth].p_hdr; ex = EXT_FIRST_EXTENT(eh); ext_debug(inode, "Displaying leaf extents\n"); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { ext_debug(inode, "%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); } ext_debug(inode, "\n"); } static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, ext4_fsblk_t newblock, int level) { int depth = ext_depth(inode); struct ext4_extent *ex; if (depth != level) { struct ext4_extent_idx *idx; idx = path[level].p_idx; while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) { ext_debug(inode, "%d: move %d:%llu in new index %llu\n", level, le32_to_cpu(idx->ei_block), ext4_idx_pblock(idx), newblock); idx++; } return; } ex = path[depth].p_ext; while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) { ext_debug(inode, "move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), newblock); ex++; } } #else #define ext4_ext_show_path(inode, path) #define ext4_ext_show_leaf(inode, path) #define ext4_ext_show_move(inode, path, newblock, level) #endif void ext4_ext_drop_refs(struct ext4_ext_path *path) { int depth, i; if (!path) return; depth = path->p_depth; for (i = 0; i <= depth; i++, path++) { brelse(path->p_bh); path->p_bh = NULL; } } /* * ext4_ext_binsearch_idx: * binary search for the closest index of the given block * the header must be checked before calling this */ static void ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent_idx *r, *l, *m; ext_debug(inode, "binsearch for %u(idx): ", block); l = EXT_FIRST_INDEX(eh) + 1; r = EXT_LAST_INDEX(eh); while (l <= r) { m = l + (r - l) / 2; if (block < le32_to_cpu(m->ei_block)) r = m - 1; else l = m + 1; ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block), r, le32_to_cpu(r->ei_block)); } path->p_idx = l - 1; ext_debug(inode, " -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH { struct ext4_extent_idx *chix, *ix; int k; chix = ix = EXT_FIRST_INDEX(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) { if (k != 0 && le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) { printk(KERN_DEBUG "k=%d, ix=0x%p, " "first=0x%p\n", k, ix, EXT_FIRST_INDEX(eh)); printk(KERN_DEBUG "%u <= %u\n", le32_to_cpu(ix->ei_block), le32_to_cpu(ix[-1].ei_block)); } BUG_ON(k && le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)); if (block < le32_to_cpu(ix->ei_block)) break; chix = ix; } BUG_ON(chix != path->p_idx); } #endif } /* * ext4_ext_binsearch: * binary search for closest extent of the given block * the header must be checked before calling this */ static void ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent *r, *l, *m; if (eh->eh_entries == 0) { /* * this leaf is empty: * we get such a leaf in split/add case */ return; } ext_debug(inode, "binsearch for %u: ", block); l = EXT_FIRST_EXTENT(eh) + 1; r = EXT_LAST_EXTENT(eh); while (l <= r) { m = l + (r - l) / 2; if (block < le32_to_cpu(m->ee_block)) r = m - 1; else l = m + 1; ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block), r, le32_to_cpu(r->ee_block)); } path->p_ext = l - 1; ext_debug(inode, " -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_pblock(path->p_ext), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext)); #ifdef CHECK_BINSEARCH { struct ext4_extent *chex, *ex; int k; chex = ex = EXT_FIRST_EXTENT(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) { BUG_ON(k && le32_to_cpu(ex->ee_block) <= le32_to_cpu(ex[-1].ee_block)); if (block < le32_to_cpu(ex->ee_block)) break; chex = ex; } BUG_ON(chex != path->p_ext); } #endif } void ext4_ext_tree_init(handle_t *handle, struct inode *inode) { struct ext4_extent_header *eh; eh = ext_inode_hdr(inode); eh->eh_depth = 0; eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); eh->eh_generation = 0; ext4_mark_inode_dirty(handle, inode); } struct ext4_ext_path * ext4_find_extent(struct inode *inode, ext4_lblk_t block, struct ext4_ext_path **orig_path, int flags) { struct ext4_extent_header *eh; struct buffer_head *bh; struct ext4_ext_path *path = orig_path ? *orig_path : NULL; short int depth, i, ppos = 0; int ret; gfp_t gfp_flags = GFP_NOFS; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; eh = ext_inode_hdr(inode); depth = ext_depth(inode); if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) { EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d", depth); ret = -EFSCORRUPTED; goto err; } if (path) { ext4_ext_drop_refs(path); if (depth > path[0].p_maxdepth) { kfree(path); *orig_path = path = NULL; } } if (!path) { /* account possible depth increase */ path = kcalloc(depth + 2, sizeof(struct ext4_ext_path), gfp_flags); if (unlikely(!path)) return ERR_PTR(-ENOMEM); path[0].p_maxdepth = depth + 1; } path[0].p_hdr = eh; path[0].p_bh = NULL; i = depth; if (!(flags & EXT4_EX_NOCACHE) && depth == 0) ext4_cache_extents(inode, eh); /* walk through the tree */ while (i) { ext_debug(inode, "depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_ext_binsearch_idx(inode, path + ppos, block); path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx); path[ppos].p_depth = i; path[ppos].p_ext = NULL; bh = read_extent_tree_block(inode, path[ppos].p_idx, --i, flags); if (IS_ERR(bh)) { ret = PTR_ERR(bh); goto err; } eh = ext_block_hdr(bh); ppos++; path[ppos].p_bh = bh; path[ppos].p_hdr = eh; } path[ppos].p_depth = i; path[ppos].p_ext = NULL; path[ppos].p_idx = NULL; /* find extent */ ext4_ext_binsearch(inode, path + ppos, block); /* if not an empty leaf */ if (path[ppos].p_ext) path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext); ext4_ext_show_path(inode, path); if (orig_path) *orig_path = path; return path; err: ext4_ext_drop_refs(path); kfree(path); if (orig_path) *orig_path = NULL; return ERR_PTR(ret); } /* * ext4_ext_insert_index: * insert new index [@logical;@ptr] into the block at @curp; * check where to insert: before @curp or after @curp */ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, struct ext4_ext_path *curp, int logical, ext4_fsblk_t ptr) { struct ext4_extent_idx *ix; int len, err; err = ext4_ext_get_access(handle, inode, curp); if (err) return err; if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) { EXT4_ERROR_INODE(inode, "logical %d == ei_block %d!", logical, le32_to_cpu(curp->p_idx->ei_block)); return -EFSCORRUPTED; } if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries) >= le16_to_cpu(curp->p_hdr->eh_max))) { EXT4_ERROR_INODE(inode, "eh_entries %d >= eh_max %d!", le16_to_cpu(curp->p_hdr->eh_entries), le16_to_cpu(curp->p_hdr->eh_max)); return -EFSCORRUPTED; } if (logical > le32_to_cpu(curp->p_idx->ei_block)) { /* insert after */ ext_debug(inode, "insert new index %d after: %llu\n", logical, ptr); ix = curp->p_idx + 1; } else { /* insert before */ ext_debug(inode, "insert new index %d before: %llu\n", logical, ptr); ix = curp->p_idx; } if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); return -EFSCORRUPTED; } len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { ext_debug(inode, "insert new index %d: " "move %d indices from 0x%p to 0x%p\n", logical, len, ix, ix + 1); memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!"); return -EFSCORRUPTED; } err = ext4_ext_dirty(handle, inode, curp); ext4_std_error(inode->i_sb, err); return err; } /* * ext4_ext_split: * inserts new subtree into the path, using free index entry * at depth @at: * - allocates all needed blocks (new leaf and all intermediate index blocks) * - makes decision where to split * - moves remaining extents and index entries (right to the split point) * into the newly allocated blocks * - initializes subtree */ static int ext4_ext_split(handle_t *handle, struct inode *inode, unsigned int flags, struct ext4_ext_path *path, struct ext4_extent *newext, int at) { struct buffer_head *bh = NULL; int depth = ext_depth(inode); struct ext4_extent_header *neh; struct ext4_extent_idx *fidx; int i = at, k, m, a; ext4_fsblk_t newblock, oldblock; __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ gfp_t gfp_flags = GFP_NOFS; int err = 0; size_t ext_size = 0; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ /* if current leaf will be split, then we should use * border from split point */ if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!"); return -EFSCORRUPTED; } if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) { border = path[depth].p_ext[1].ee_block; ext_debug(inode, "leaf will be split." " next leaf starts at %d\n", le32_to_cpu(border)); } else { border = newext->ee_block; ext_debug(inode, "leaf will be added." " next leaf starts at %d\n", le32_to_cpu(border)); } /* * If error occurs, then we break processing * and mark filesystem read-only. index won't * be inserted and tree will be in consistent * state. Next mount will repair buffers too. */ /* * Get array to track all allocated blocks. * We need this to handle errors and free blocks * upon them. */ ablocks = kcalloc(depth, sizeof(ext4_fsblk_t), gfp_flags); if (!ablocks) return -ENOMEM; /* allocate all needed blocks */ ext_debug(inode, "allocate %d blocks for indexes/leaf\n", depth - at); for (a = 0; a < depth - at; a++) { newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err, flags); if (newblock == 0) goto cleanup; ablocks[a] = newblock; } /* initialize new leaf */ newblock = ablocks[--a]; if (unlikely(newblock == 0)) { EXT4_ERROR_INODE(inode, "newblock == 0!"); err = -EFSCORRUPTED; goto cleanup; } bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) { err = -ENOMEM; goto cleanup; } lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) goto cleanup; neh = ext_block_hdr(bh); neh->eh_entries = 0; neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; neh->eh_generation = 0; /* move remainder of path[depth] to the new leaf */ if (unlikely(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max)) { EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!", path[depth].p_hdr->eh_entries, path[depth].p_hdr->eh_max); err = -EFSCORRUPTED; goto cleanup; } /* start copy from next extent */ m = EXT_MAX_EXTENT(path[depth].p_hdr) - path[depth].p_ext++; ext4_ext_show_move(inode, path, newblock, depth); if (m) { struct ext4_extent *ex; ex = EXT_FIRST_EXTENT(neh); memmove(ex, path[depth].p_ext, sizeof(struct ext4_extent) * m); le16_add_cpu(&neh->eh_entries, m); } /* zero out unused area in the extent block */ ext_size = sizeof(struct ext4_extent_header) + sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries); memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto cleanup; brelse(bh); bh = NULL; /* correct old leaf */ if (m) { err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto cleanup; le16_add_cpu(&path[depth].p_hdr->eh_entries, -m); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto cleanup; } /* create intermediate indexes */ k = depth - at - 1; if (unlikely(k < 0)) { EXT4_ERROR_INODE(inode, "k %d < 0!", k); err = -EFSCORRUPTED; goto cleanup; } if (k) ext_debug(inode, "create %d intermediate indices\n", k); /* insert new index into current index block */ /* current depth stored in i var */ i = depth - 1; while (k--) { oldblock = newblock; newblock = ablocks[--a]; bh = sb_getblk(inode->i_sb, newblock); if (unlikely(!bh)) { err = -ENOMEM; goto cleanup; } lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) goto cleanup; neh = ext_block_hdr(bh); neh->eh_entries = cpu_to_le16(1); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); neh->eh_generation = 0; fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; ext4_idx_store_pblock(fidx, oldblock); ext_debug(inode, "int.index at %d (block %llu): %u -> %llu\n", i, newblock, le32_to_cpu(border), oldblock); /* move remainder of path[i] to the new index block */ if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) != EXT_LAST_INDEX(path[i].p_hdr))) { EXT4_ERROR_INODE(inode, "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!", le32_to_cpu(path[i].p_ext->ee_block)); err = -EFSCORRUPTED; goto cleanup; } /* start copy indexes */ m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++; ext_debug(inode, "cur 0x%p, last 0x%p\n", path[i].p_idx, EXT_MAX_INDEX(path[i].p_hdr)); ext4_ext_show_move(inode, path, newblock, i); if (m) { memmove(++fidx, path[i].p_idx, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } /* zero out unused area in the extent block */ ext_size = sizeof(struct ext4_extent_header) + (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries)); memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto cleanup; brelse(bh); bh = NULL; /* correct old index */ if (m) { err = ext4_ext_get_access(handle, inode, path + i); if (err) goto cleanup; le16_add_cpu(&path[i].p_hdr->eh_entries, -m); err = ext4_ext_dirty(handle, inode, path + i); if (err) goto cleanup; } i--; } /* insert new index */ err = ext4_ext_insert_index(handle, inode, path + at, le32_to_cpu(border), newblock); cleanup: if (bh) { if (buffer_locked(bh)) unlock_buffer(bh); brelse(bh); } if (err) { /* free all allocated blocks in error case */ for (i = 0; i < depth; i++) { if (!ablocks[i]) continue; ext4_free_blocks(handle, inode, NULL, ablocks[i], 1, EXT4_FREE_BLOCKS_METADATA); } } kfree(ablocks); return err; } /* * ext4_ext_grow_indepth: * implements tree growing procedure: * - allocates new block * - moves top-level data (index block or leaf) into the new block * - initializes new top-level, creating index that points to the * just created block */ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, unsigned int flags) { struct ext4_extent_header *neh; struct buffer_head *bh; ext4_fsblk_t newblock, goal = 0; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; int err = 0; size_t ext_size = 0; /* Try to prepend new index to old one */ if (ext_depth(inode)) goal = ext4_idx_pblock(EXT_FIRST_INDEX(ext_inode_hdr(inode))); if (goal > le32_to_cpu(es->s_first_data_block)) { flags |= EXT4_MB_HINT_TRY_GOAL; goal--; } else goal = ext4_inode_to_goal_block(inode); newblock = ext4_new_meta_blocks(handle, inode, goal, flags, NULL, &err); if (newblock == 0) return err; bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) return -ENOMEM; lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) { unlock_buffer(bh); goto out; } ext_size = sizeof(EXT4_I(inode)->i_data); /* move top-level index/leaf into new block */ memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size); /* zero out unused area in the extent block */ memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); /* set size of new block */ neh = ext_block_hdr(bh); /* old root could have indexes or leaves * so calculate e_max right way */ if (ext_depth(inode)) neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); else neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); set_buffer_verified(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto out; /* Update top-level index: num,max,pointer */ neh = ext_inode_hdr(inode); neh->eh_entries = cpu_to_le16(1); ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock); if (neh->eh_depth == 0) { /* Root extent block becomes index block */ neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0)); EXT_FIRST_INDEX(neh)->ei_block = EXT_FIRST_EXTENT(neh)->ee_block; } ext_debug(inode, "new root: num %d(%d), lblock %d, ptr %llu\n", le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max), le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), ext4_idx_pblock(EXT_FIRST_INDEX(neh))); le16_add_cpu(&neh->eh_depth, 1); err = ext4_mark_inode_dirty(handle, inode); out: brelse(bh); return err; } /* * ext4_ext_create_new_leaf: * finds empty index and adds new leaf. * if no free index is found, then it requests in-depth growing. */ static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode, unsigned int mb_flags, unsigned int gb_flags, struct ext4_ext_path **ppath, struct ext4_extent *newext) { struct ext4_ext_path *path = *ppath; struct ext4_ext_path *curp; int depth, i, err = 0; repeat: i = depth = ext_depth(inode); /* walk up to the tree and look for free index entry */ curp = path + depth; while (i > 0 && !EXT_HAS_FREE_INDEX(curp)) { i--; curp--; } /* we use already allocated block for index block, * so subsequent data blocks should be contiguous */ if (EXT_HAS_FREE_INDEX(curp)) { /* if we found index with free entry, then use that * entry: create all needed subtree and add new leaf */ err = ext4_ext_split(handle, inode, mb_flags, path, newext, i); if (err) goto out; /* refill path */ path = ext4_find_extent(inode, (ext4_lblk_t)le32_to_cpu(newext->ee_block), ppath, gb_flags); if (IS_ERR(path)) err = PTR_ERR(path); } else { /* tree is full, time to grow in depth */ err = ext4_ext_grow_indepth(handle, inode, mb_flags); if (err) goto out; /* refill path */ path = ext4_find_extent(inode, (ext4_lblk_t)le32_to_cpu(newext->ee_block), ppath, gb_flags); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; } /* * only first (depth 0 -> 1) produces free space; * in all other cases we have to split the grown tree */ depth = ext_depth(inode); if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) { /* now we need to split */ goto repeat; } } out: return err; } /* * search the closest allocated block to the left for *logical * and returns it at @logical + it's physical address at @phys * if *logical is the smallest allocated block, the function * returns 0 at @phys * return value contains 0 (success) or error code */ static int ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys) { struct ext4_extent_idx *ix; struct ext4_extent *ex; int depth, ee_len; if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; if (depth == 0 && path->p_ext == NULL) return 0; /* usually extent in the path covers blocks smaller * then *logical, but it can be that extent is the * first one in the file */ ex = path[depth].p_ext; ee_len = ext4_ext_get_actual_len(ex); if (*logical < le32_to_cpu(ex->ee_block)) { if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) { EXT4_ERROR_INODE(inode, "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!", *logical, le32_to_cpu(ex->ee_block)); return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!", ix != NULL ? le32_to_cpu(ix->ei_block) : 0, EXT_FIRST_INDEX(path[depth].p_hdr) != NULL ? le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block) : 0, depth); return -EFSCORRUPTED; } } return 0; } if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) { EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); return -EFSCORRUPTED; } *logical = le32_to_cpu(ex->ee_block) + ee_len - 1; *phys = ext4_ext_pblock(ex) + ee_len - 1; return 0; } /* * Search the closest allocated block to the right for *logical * and returns it at @logical + it's physical address at @phys. * If not exists, return 0 and @phys is set to 0. We will return * 1 which means we found an allocated block and ret_ex is valid. * Or return a (< 0) error code. */ static int ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys, struct ext4_extent *ret_ex) { struct buffer_head *bh = NULL; struct ext4_extent_header *eh; struct ext4_extent_idx *ix; struct ext4_extent *ex; int depth; /* Note, NOT eh_depth; depth from top of tree */ int ee_len; if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; if (depth == 0 && path->p_ext == NULL) return 0; /* usually extent in the path covers blocks smaller * then *logical, but it can be that extent is the * first one in the file */ ex = path[depth].p_ext; ee_len = ext4_ext_get_actual_len(ex); if (*logical < le32_to_cpu(ex->ee_block)) { if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) { EXT4_ERROR_INODE(inode, "first_extent(path[%d].p_hdr) != ex", depth); return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "ix != EXT_FIRST_INDEX *logical %d!", *logical); return -EFSCORRUPTED; } } goto found_extent; } if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) { EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); return -EFSCORRUPTED; } if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) { /* next allocated block in this leaf */ ex++; goto found_extent; } /* go up and search for index to the right */ while (--depth >= 0) { ix = path[depth].p_idx; if (ix != EXT_LAST_INDEX(path[depth].p_hdr)) goto got_index; } /* we've gone up to the root and found no index to the right */ return 0; got_index: /* we've found index to the right, let's * follow it and find the closest allocated * block to the right */ ix++; while (++depth < path->p_depth) { /* subtract from p_depth to get proper eh_depth */ bh = read_extent_tree_block(inode, ix, path->p_depth - depth, 0); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ix = EXT_FIRST_INDEX(eh); put_bh(bh); } bh = read_extent_tree_block(inode, ix, path->p_depth - depth, 0); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ex = EXT_FIRST_EXTENT(eh); found_extent: *logical = le32_to_cpu(ex->ee_block); *phys = ext4_ext_pblock(ex); if (ret_ex) *ret_ex = *ex; if (bh) put_bh(bh); return 1; } /* * ext4_ext_next_allocated_block: * returns allocated block in subsequent extent or EXT_MAX_BLOCKS. * NOTE: it considers block number from index entry as * allocated block. Thus, index entries have to be consistent * with leaves. */ ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path) { int depth; BUG_ON(path == NULL); depth = path->p_depth; if (depth == 0 && path->p_ext == NULL) return EXT_MAX_BLOCKS; while (depth >= 0) { struct ext4_ext_path *p = &path[depth]; if (depth == path->p_depth) { /* leaf */ if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr)) return le32_to_cpu(p->p_ext[1].ee_block); } else { /* index */ if (p->p_idx != EXT_LAST_INDEX(p->p_hdr)) return le32_to_cpu(p->p_idx[1].ei_block); } depth--; } return EXT_MAX_BLOCKS; } /* * ext4_ext_next_leaf_block: * returns first allocated block from next leaf or EXT_MAX_BLOCKS */ static ext4_lblk_t ext4_ext_next_leaf_block(struct ext4_ext_path *path) { int depth; BUG_ON(path == NULL); depth = path->p_depth; /* zero-tree has no leaf blocks at all */ if (depth == 0) return EXT_MAX_BLOCKS; /* go to index block */ depth--; while (depth >= 0) { if (path[depth].p_idx != EXT_LAST_INDEX(path[depth].p_hdr)) return (ext4_lblk_t) le32_to_cpu(path[depth].p_idx[1].ei_block); depth--; } return EXT_MAX_BLOCKS; } /* * ext4_ext_correct_indexes: * if leaf gets modified and modified extent is first in the leaf, * then we have to correct all indexes above. * TODO: do we need to correct tree in all cases? */ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { struct ext4_extent_header *eh; int depth = ext_depth(inode); struct ext4_extent *ex; __le32 border; int k, err = 0; eh = path[depth].p_hdr; ex = path[depth].p_ext; if (unlikely(ex == NULL || eh == NULL)) { EXT4_ERROR_INODE(inode, "ex %p == NULL or eh %p == NULL", ex, eh); return -EFSCORRUPTED; } if (depth == 0) { /* there is no tree at all */ return 0; } if (ex != EXT_FIRST_EXTENT(eh)) { /* we correct tree if first leaf got modified only */ return 0; } /* * TODO: we need correction if border is smaller than current one */ k = depth - 1; border = path[depth].p_ext->ee_block; err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) return err; while (k--) { /* change all left-side indexes */ if (path[k+1].p_idx != EXT_FIRST_INDEX(path[k+1].p_hdr)) break; err = ext4_ext_get_access(handle, inode, path + k); if (err) break; path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) break; } return err; } static int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2) { unsigned short ext1_ee_len, ext2_ee_len; if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2)) return 0; ext1_ee_len = ext4_ext_get_actual_len(ex1); ext2_ee_len = ext4_ext_get_actual_len(ex2); if (le32_to_cpu(ex1->ee_block) + ext1_ee_len != le32_to_cpu(ex2->ee_block)) return 0; if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN) return 0; if (ext4_ext_is_unwritten(ex1) && ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN) return 0; #ifdef AGGRESSIVE_TEST if (ext1_ee_len >= 4) return 0; #endif if (ext4_ext_pblock(ex1) + ext1_ee_len == ext4_ext_pblock(ex2)) return 1; return 0; } /* * This function tries to merge the "ex" extent to the next extent in the tree. * It always tries to merge towards right. If you want to merge towards * left, pass "ex - 1" as argument instead of "ex". * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns * 1 if they got merged. */ static int ext4_ext_try_to_merge_right(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth, len; int merge_done = 0, unwritten; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); eh = path[depth].p_hdr; while (ex < EXT_LAST_EXTENT(eh)) { if (!ext4_can_extents_be_merged(inode, ex, ex + 1)) break; /* merge with next extent! */ unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(ex + 1)); if (unwritten) ext4_ext_mark_unwritten(ex); if (ex + 1 < EXT_LAST_EXTENT(eh)) { len = (EXT_LAST_EXTENT(eh) - ex - 1) * sizeof(struct ext4_extent); memmove(ex + 1, ex + 2, len); } le16_add_cpu(&eh->eh_entries, -1); merge_done = 1; WARN_ON(eh->eh_entries == 0); if (!eh->eh_entries) EXT4_ERROR_INODE(inode, "eh->eh_entries = 0!"); } return merge_done; } /* * This function does a very simple check to see if we can collapse * an extent tree with a single extent tree leaf block into the inode. */ static void ext4_ext_try_to_merge_up(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { size_t s; unsigned max_root = ext4_ext_space_root(inode, 0); ext4_fsblk_t blk; if ((path[0].p_depth != 1) || (le16_to_cpu(path[0].p_hdr->eh_entries) != 1) || (le16_to_cpu(path[1].p_hdr->eh_entries) > max_root)) return; /* * We need to modify the block allocation bitmap and the block * group descriptor to release the extent tree block. If we * can't get the journal credits, give up. */ if (ext4_journal_extend(handle, 2, ext4_free_metadata_revoke_credits(inode->i_sb, 1))) return; /* * Copy the extent data up to the inode */ blk = ext4_idx_pblock(path[0].p_idx); s = le16_to_cpu(path[1].p_hdr->eh_entries) * sizeof(struct ext4_extent_idx); s += sizeof(struct ext4_extent_header); path[1].p_maxdepth = path[0].p_maxdepth; memcpy(path[0].p_hdr, path[1].p_hdr, s); path[0].p_depth = 0; path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) + (path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr)); path[0].p_hdr->eh_max = cpu_to_le16(max_root); brelse(path[1].p_bh); path[1].p_bh = NULL; ext4_free_blocks(handle, inode, NULL, blk, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } /* * This function tries to merge the @ex extent to neighbours in the tree, then * tries to collapse the extent tree into the inode. */ static void ext4_ext_try_to_merge(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth; int merge_done = 0; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); eh = path[depth].p_hdr; if (ex > EXT_FIRST_EXTENT(eh)) merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1); if (!merge_done) (void) ext4_ext_try_to_merge_right(inode, path, ex); ext4_ext_try_to_merge_up(handle, inode, path); } /* * check if a portion of the "newext" extent overlaps with an * existing extent. * * If there is an overlap discovered, it updates the length of the newext * such that there will be no overlap, and then returns 1. * If there is no overlap found, it returns 0. */ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi, struct inode *inode, struct ext4_extent *newext, struct ext4_ext_path *path) { ext4_lblk_t b1, b2; unsigned int depth, len1; unsigned int ret = 0; b1 = le32_to_cpu(newext->ee_block); len1 = ext4_ext_get_actual_len(newext); depth = ext_depth(inode); if (!path[depth].p_ext) goto out; b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block)); /* * get the next allocated block if the extent in the path * is before the requested block(s) */ if (b2 < b1) { b2 = ext4_ext_next_allocated_block(path); if (b2 == EXT_MAX_BLOCKS) goto out; b2 = EXT4_LBLK_CMASK(sbi, b2); } /* check for wrap through zero on extent logical start block*/ if (b1 + len1 < b1) { len1 = EXT_MAX_BLOCKS - b1; newext->ee_len = cpu_to_le16(len1); ret = 1; } /* check for overlap */ if (b1 + len1 > b2) { newext->ee_len = cpu_to_le16(b2 - b1); ret = 1; } out: return ret; } /* * ext4_ext_insert_extent: * tries to merge requested extent into the existing extent or * inserts requested extent as new one into the tree, * creating new leaf in the no-space case. */ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, struct ext4_extent *newext, int gb_flags) { struct ext4_ext_path *path = *ppath; struct ext4_extent_header *eh; struct ext4_extent *ex, *fex; struct ext4_extent *nearex; /* nearest extent */ struct ext4_ext_path *npath = NULL; int depth, len, err; ext4_lblk_t next; int mb_flags = 0, unwritten; if (gb_flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) mb_flags |= EXT4_MB_DELALLOC_RESERVED; if (unlikely(ext4_ext_get_actual_len(newext) == 0)) { EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0"); return -EFSCORRUPTED; } depth = ext_depth(inode); ex = path[depth].p_ext; eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); return -EFSCORRUPTED; } /* try to insert block into found extent and return */ if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) { /* * Try to see whether we should rather test the extent on * right from ex, or from the left of ex. This is because * ext4_find_extent() can return either extent on the * left, or on the right from the searched position. This * will make merging more effective. */ if (ex < EXT_LAST_EXTENT(eh) && (le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex) < le32_to_cpu(newext->ee_block))) { ex += 1; goto prepend; } else if ((ex > EXT_FIRST_EXTENT(eh)) && (le32_to_cpu(newext->ee_block) + ext4_ext_get_actual_len(newext) < le32_to_cpu(ex->ee_block))) ex -= 1; /* Try to append newex to the ex */ if (ext4_can_extents_be_merged(inode, ex, newext)) { ext_debug(inode, "append [%d]%d block to %u:[%d]%d" "(from %llu)\n", ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); eh = path[depth].p_hdr; nearex = ex; goto merge; } prepend: /* Try to prepend newex to the ex */ if (ext4_can_extents_be_merged(inode, newext, ex)) { ext_debug(inode, "prepend %u[%d]%d block to %u:[%d]%d" "(from %llu)\n", le32_to_cpu(newext->ee_block), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; unwritten = ext4_ext_is_unwritten(ex); ex->ee_block = newext->ee_block; ext4_ext_store_pblock(ex, ext4_ext_pblock(newext)); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); eh = path[depth].p_hdr; nearex = ex; goto merge; } } depth = ext_depth(inode); eh = path[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) goto has_space; /* probably next leaf has space for us? */ fex = EXT_LAST_EXTENT(eh); next = EXT_MAX_BLOCKS; if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)) next = ext4_ext_next_leaf_block(path); if (next != EXT_MAX_BLOCKS) { ext_debug(inode, "next leaf block - %u\n", next); BUG_ON(npath != NULL); npath = ext4_find_extent(inode, next, NULL, gb_flags); if (IS_ERR(npath)) return PTR_ERR(npath); BUG_ON(npath->p_depth != path->p_depth); eh = npath[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) { ext_debug(inode, "next leaf isn't full(%d)\n", le16_to_cpu(eh->eh_entries)); path = npath; goto has_space; } ext_debug(inode, "next leaf has no free space(%d,%d)\n", le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); } /* * There is no free space in the found leaf. * We're gonna add a new leaf in the tree. */ if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) mb_flags |= EXT4_MB_USE_RESERVED; err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags, ppath, newext); if (err) goto cleanup; path = *ppath; depth = ext_depth(inode); eh = path[depth].p_hdr; has_space: nearex = path[depth].p_ext; err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto cleanup; if (!nearex) { /* there is no extent in this leaf, create first one */ ext_debug(inode, "first extent in the leaf: %u:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext)); nearex = EXT_FIRST_EXTENT(eh); } else { if (le32_to_cpu(newext->ee_block) > le32_to_cpu(nearex->ee_block)) { /* Insert after */ ext_debug(inode, "insert %u:%llu:[%d]%d before: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), nearex); nearex++; } else { /* Insert before */ BUG_ON(newext->ee_block == nearex->ee_block); ext_debug(inode, "insert %u:%llu:[%d]%d after: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), nearex); } len = EXT_LAST_EXTENT(eh) - nearex + 1; if (len > 0) { ext_debug(inode, "insert %u:%llu:[%d]%d: " "move %d extents from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), len, nearex, nearex + 1); memmove(nearex + 1, nearex, len * sizeof(struct ext4_extent)); } } le16_add_cpu(&eh->eh_entries, 1); path[depth].p_ext = nearex; nearex->ee_block = newext->ee_block; ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext)); nearex->ee_len = newext->ee_len; merge: /* try to merge extents */ if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(handle, inode, path, nearex); /* time to correct all indexes above */ err = ext4_ext_correct_indexes(handle, inode, path); if (err) goto cleanup; err = ext4_ext_dirty(handle, inode, path + path->p_depth); cleanup: ext4_ext_drop_refs(npath); kfree(npath); return err; } static int ext4_fill_es_cache_info(struct inode *inode, ext4_lblk_t block, ext4_lblk_t num, struct fiemap_extent_info *fieinfo) { ext4_lblk_t next, end = block + num - 1; struct extent_status es; unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; unsigned int flags; int err; while (block <= end) { next = 0; flags = 0; if (!ext4_es_lookup_extent(inode, block, &next, &es)) break; if (ext4_es_is_unwritten(&es)) flags |= FIEMAP_EXTENT_UNWRITTEN; if (ext4_es_is_delayed(&es)) flags |= (FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); if (ext4_es_is_hole(&es)) flags |= EXT4_FIEMAP_EXTENT_HOLE; if (next == 0) flags |= FIEMAP_EXTENT_LAST; if (flags & (FIEMAP_EXTENT_DELALLOC| EXT4_FIEMAP_EXTENT_HOLE)) es.es_pblk = 0; else es.es_pblk = ext4_es_pblock(&es); err = fiemap_fill_next_extent(fieinfo, (__u64)es.es_lblk << blksize_bits, (__u64)es.es_pblk << blksize_bits, (__u64)es.es_len << blksize_bits, flags); if (next == 0) break; block = next; if (err < 0) return err; if (err == 1) return 0; } return 0; } /* * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole * * Determine hole length (and start if easily possible) around given logical * block. We don't try too hard to find the beginning of the hole but @path * actually points to extent before @lblk, we provide it. * * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; ext4_lblk_t len; ex = path[depth].p_ext; if (ex == NULL) { /* there is no extent yet, so gap is [0;-] */ *lblk = 0; len = EXT_MAX_BLOCKS; } else if (*lblk < le32_to_cpu(ex->ee_block)) { len = le32_to_cpu(ex->ee_block) - *lblk; } else if (*lblk >= le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)) { ext4_lblk_t next; *lblk = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); next = ext4_ext_next_allocated_block(path); BUG_ON(next == *lblk); len = next - *lblk; } else { BUG(); } return len; } /* * ext4_ext_rm_idx: * removes index from the index block. */ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, int depth) { int err; ext4_fsblk_t leaf; /* free index block */ depth--; path = path + depth; leaf = ext4_idx_pblock(path->p_idx); if (unlikely(path->p_hdr->eh_entries == 0)) { EXT4_ERROR_INODE(inode, "path->p_hdr->eh_entries == 0"); return -EFSCORRUPTED; } err = ext4_ext_get_access(handle, inode, path); if (err) return err; if (path->p_idx != EXT_LAST_INDEX(path->p_hdr)) { int len = EXT_LAST_INDEX(path->p_hdr) - path->p_idx; len *= sizeof(struct ext4_extent_idx); memmove(path->p_idx, path->p_idx + 1, len); } le16_add_cpu(&path->p_hdr->eh_entries, -1); err = ext4_ext_dirty(handle, inode, path); if (err) return err; ext_debug(inode, "index is empty, remove it, free block %llu\n", leaf); trace_ext4_ext_rm_idx(inode, leaf); ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); while (--depth >= 0) { if (path->p_idx != EXT_FIRST_INDEX(path->p_hdr)) break; path--; err = ext4_ext_get_access(handle, inode, path); if (err) break; path->p_idx->ei_block = (path+1)->p_idx->ei_block; err = ext4_ext_dirty(handle, inode, path); if (err) break; } return err; } /* * ext4_ext_calc_credits_for_single_extent: * This routine returns max. credits that needed to insert an extent * to the extent tree. * When pass the actual path, the caller should calculate credits * under i_data_sem. */ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, struct ext4_ext_path *path) { if (path) { int depth = ext_depth(inode); int ret = 0; /* probably there is space in leaf? */ if (le16_to_cpu(path[depth].p_hdr->eh_entries) < le16_to_cpu(path[depth].p_hdr->eh_max)) { /* * There are some space in the leaf tree, no * need to account for leaf block credit * * bitmaps and block group descriptor blocks * and other metadata blocks still need to be * accounted. */ /* 1 bitmap, 1 block group descriptor */ ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb); return ret; } } return ext4_chunk_trans_blocks(inode, nrblocks); } /* * How many index/leaf blocks need to change/allocate to add @extents extents? * * If we add a single extent, then in the worse case, each tree level * index/leaf need to be changed in case of the tree split. * * If more extents are inserted, they could cause the whole tree split more * than once, but this is really rare. */ int ext4_ext_index_trans_blocks(struct inode *inode, int extents) { int index; int depth; /* If we are converting the inline data, only one is needed here. */ if (ext4_has_inline_data(inode)) return 1; depth = ext_depth(inode); if (extents <= 1) index = depth * 2; else index = depth * 3; return index; } static inline int get_default_free_blocks_flags(struct inode *inode) { if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET; else if (ext4_should_journal_data(inode)) return EXT4_FREE_BLOCKS_FORGET; return 0; } /* * ext4_rereserve_cluster - increment the reserved cluster count when * freeing a cluster with a pending reservation * * @inode - file containing the cluster * @lblk - logical block in cluster to be reserved * * Increments the reserved cluster count and adjusts quota in a bigalloc * file system when freeing a partial cluster containing at least one * delayed and unwritten block. A partial cluster meeting that * requirement will have a pending reservation. If so, the * RERESERVE_CLUSTER flag is used when calling ext4_free_blocks() to * defer reserved and allocated space accounting to a subsequent call * to this function. */ static void ext4_rereserve_cluster(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); dquot_reclaim_block(inode, EXT4_C2B(sbi, 1)); spin_lock(&ei->i_block_reservation_lock); ei->i_reserved_data_blocks++; percpu_counter_add(&sbi->s_dirtyclusters_counter, 1); spin_unlock(&ei->i_block_reservation_lock); percpu_counter_add(&sbi->s_freeclusters_counter, 1); ext4_remove_pending(inode, lblk); } static int ext4_remove_blocks(handle_t *handle, struct inode *inode, struct ext4_extent *ex, struct partial_cluster *partial, ext4_lblk_t from, ext4_lblk_t to) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned short ee_len = ext4_ext_get_actual_len(ex); ext4_fsblk_t last_pblk, pblk; ext4_lblk_t num; int flags; /* only extent tail removal is allowed */ if (from < le32_to_cpu(ex->ee_block) || to != le32_to_cpu(ex->ee_block) + ee_len - 1) { ext4_error(sbi->s_sb, "strange request: removal(2) %u-%u from %u:%u", from, to, le32_to_cpu(ex->ee_block), ee_len); return 0; } #ifdef EXTENTS_STATS spin_lock(&sbi->s_ext_stats_lock); sbi->s_ext_blocks += ee_len; sbi->s_ext_extents++; if (ee_len < sbi->s_ext_min) sbi->s_ext_min = ee_len; if (ee_len > sbi->s_ext_max) sbi->s_ext_max = ee_len; if (ext_depth(inode) > sbi->s_depth_max) sbi->s_depth_max = ext_depth(inode); spin_unlock(&sbi->s_ext_stats_lock); #endif trace_ext4_remove_blocks(inode, ex, from, to, partial); /* * if we have a partial cluster, and it's different from the * cluster of the last block in the extent, we free it */ last_pblk = ext4_ext_pblock(ex) + ee_len - 1; if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, last_pblk)) { if (partial->state == tofree) { flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial->lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial->pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial->lblk); } partial->state = initial; } num = le32_to_cpu(ex->ee_block) + ee_len - from; pblk = ext4_ext_pblock(ex) + ee_len - num; /* * We free the partial cluster at the end of the extent (if any), * unless the cluster is used by another extent (partial_cluster * state is nofree). If a partial cluster exists here, it must be * shared with the last block in the extent. */ flags = get_default_free_blocks_flags(inode); /* partial, left end cluster aligned, right end unaligned */ if ((EXT4_LBLK_COFF(sbi, to) != sbi->s_cluster_ratio - 1) && (EXT4_LBLK_CMASK(sbi, to) >= from) && (partial->state != nofree)) { if (ext4_is_pending(inode, to)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_PBLK_CMASK(sbi, last_pblk), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, to); partial->state = initial; flags = get_default_free_blocks_flags(inode); } flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER; /* * For bigalloc file systems, we never free a partial cluster * at the beginning of the extent. Instead, we check to see if we * need to free it on a subsequent call to ext4_remove_blocks, * or at the end of ext4_ext_rm_leaf or ext4_ext_remove_space. */ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER; ext4_free_blocks(handle, inode, NULL, pblk, num, flags); /* reset the partial cluster if we've freed past it */ if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, pblk)) partial->state = initial; /* * If we've freed the entire extent but the beginning is not left * cluster aligned and is not marked as ineligible for freeing we * record the partial cluster at the beginning of the extent. It * wasn't freed by the preceding ext4_free_blocks() call, and we * need to look farther to the left to determine if it's to be freed * (not shared with another extent). Else, reset the partial * cluster - we're either done freeing or the beginning of the * extent is left cluster aligned. */ if (EXT4_LBLK_COFF(sbi, from) && num == ee_len) { if (partial->state == initial) { partial->pclu = EXT4_B2C(sbi, pblk); partial->lblk = from; partial->state = tofree; } } else { partial->state = initial; } return 0; } /* * ext4_ext_rm_leaf() Removes the extents associated with the * blocks appearing between "start" and "end". Both "start" * and "end" must appear in the same extent or EIO is returned. * * @handle: The journal handle * @inode: The files inode * @path: The path to the leaf * @partial_cluster: The cluster which we'll have to free if all extents * has been released from it. However, if this value is * negative, it's a cluster just to the right of the * punched region and it must not be freed. * @start: The first block to remove * @end: The last block to remove */ static int ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct partial_cluster *partial, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int err = 0, correct_index = 0; int depth = ext_depth(inode), credits, revoke_credits; struct ext4_extent_header *eh; ext4_lblk_t a, b; unsigned num; ext4_lblk_t ex_ee_block; unsigned short ex_ee_len; unsigned unwritten = 0; struct ext4_extent *ex; ext4_fsblk_t pblk; /* the header must be checked already in ext4_ext_remove_space() */ ext_debug(inode, "truncate since %u in leaf to %u\n", start, end); if (!path[depth].p_hdr) path[depth].p_hdr = ext_block_hdr(path[depth].p_bh); eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); return -EFSCORRUPTED; } /* find where to start removing */ ex = path[depth].p_ext; if (!ex) ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); trace_ext4_ext_rm_leaf(inode, start, ex, partial); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { if (ext4_ext_is_unwritten(ex)) unwritten = 1; else unwritten = 0; ext_debug(inode, "remove ext %u:[%d]%d\n", ex_ee_block, unwritten, ex_ee_len); path[depth].p_ext = ex; a = ex_ee_block > start ? ex_ee_block : start; b = ex_ee_block+ex_ee_len - 1 < end ? ex_ee_block+ex_ee_len - 1 : end; ext_debug(inode, " border %u:%u\n", a, b); /* If this extent is beyond the end of the hole, skip it */ if (end < ex_ee_block) { /* * We're going to skip this extent and move to another, * so note that its first cluster is in use to avoid * freeing it when removing blocks. Eventually, the * right edge of the truncated/punched region will * be just to the left. */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex); partial->pclu = EXT4_B2C(sbi, pblk); partial->state = nofree; } ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); continue; } else if (b != ex_ee_block + ex_ee_len - 1) { EXT4_ERROR_INODE(inode, "can not handle truncate %u:%u " "on extent %u:%u", start, end, ex_ee_block, ex_ee_block + ex_ee_len - 1); err = -EFSCORRUPTED; goto out; } else if (a != ex_ee_block) { /* remove tail of the extent */ num = a - ex_ee_block; } else { /* remove whole extent: excellent! */ num = 0; } /* * 3 for leaf, sb, and inode plus 2 (bmap and group * descriptor) for each block group; assume two block * groups plus ex_ee_len/blocks_per_block_group for * the worst case */ credits = 7 + 2*(ex_ee_len/EXT4_BLOCKS_PER_GROUP(inode->i_sb)); if (ex == EXT_FIRST_EXTENT(eh)) { correct_index = 1; credits += (ext_depth(inode)) + 1; } credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); /* * We may end up freeing some index blocks and data from the * punched range. Note that partial clusters are accounted for * by ext4_free_data_revoke_credits(). */ revoke_credits = ext4_free_metadata_revoke_credits(inode->i_sb, ext_depth(inode)) + ext4_free_data_revoke_credits(inode, b - a + 1); err = ext4_datasem_ensure_credits(handle, inode, credits, credits, revoke_credits); if (err) { if (err > 0) err = -EAGAIN; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; err = ext4_remove_blocks(handle, inode, ex, partial, a, b); if (err) goto out; if (num == 0) /* this extent is removed; mark slot entirely unused */ ext4_ext_store_pblock(ex, 0); ex->ee_len = cpu_to_le16(num); /* * Do not mark unwritten if all the blocks in the * extent have been removed. */ if (unwritten && num) ext4_ext_mark_unwritten(ex); /* * If the extent was completely released, * we need to remove it from the leaf */ if (num == 0) { if (end != EXT_MAX_BLOCKS - 1) { /* * For hole punching, we need to scoot all the * extents up when an extent is removed so that * we dont have blank extents in the middle */ memmove(ex, ex+1, (EXT_LAST_EXTENT(eh) - ex) * sizeof(struct ext4_extent)); /* Now get rid of the one at the end */ memset(EXT_LAST_EXTENT(eh), 0, sizeof(struct ext4_extent)); } le16_add_cpu(&eh->eh_entries, -1); } err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; ext_debug(inode, "new extent: %u:%u:%llu\n", ex_ee_block, num, ext4_ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); } if (correct_index && eh->eh_entries) err = ext4_ext_correct_indexes(handle, inode, path); /* * If there's a partial cluster and at least one extent remains in * the leaf, free the partial cluster if it isn't shared with the * current extent. If it is shared with the current extent * we reset the partial cluster because we've reached the start of the * truncated/punched region and we're done removing blocks. */ if (partial->state == tofree && ex >= EXT_FIRST_EXTENT(eh)) { pblk = ext4_ext_pblock(ex) + ex_ee_len - 1; if (partial->pclu != EXT4_B2C(sbi, pblk)) { int flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial->lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial->pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial->lblk); } partial->state = initial; } /* if this leaf is free, then we should * remove it from index block above */ if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL) err = ext4_ext_rm_idx(handle, inode, path, depth); out: return err; } /* * ext4_ext_more_to_rm: * returns 1 if current index has to be freed (even partial) */ static int ext4_ext_more_to_rm(struct ext4_ext_path *path) { BUG_ON(path->p_idx == NULL); if (path->p_idx < EXT_FIRST_INDEX(path->p_hdr)) return 0; /* * if truncate on deeper level happened, it wasn't partial, * so we have to consider current index for truncation */ if (le16_to_cpu(path->p_hdr->eh_entries) == path->p_block) return 0; return 1; } int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int depth = ext_depth(inode); struct ext4_ext_path *path = NULL; struct partial_cluster partial; handle_t *handle; int i = 0, err = 0; partial.pclu = 0; partial.lblk = 0; partial.state = initial; ext_debug(inode, "truncate since %u to %u\n", start, end); /* probably first extent we're gonna free will be last in block */ handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE, depth + 1, ext4_free_metadata_revoke_credits(inode->i_sb, depth)); if (IS_ERR(handle)) return PTR_ERR(handle); again: trace_ext4_ext_remove_space(inode, start, end, depth); /* * Check if we are removing extents inside the extent tree. If that * is the case, we are going to punch a hole inside the extent tree * so we have to check whether we need to split the extent covering * the last block to remove so we can easily remove the part of it * in ext4_ext_rm_leaf(). */ if (end < EXT_MAX_BLOCKS - 1) { struct ext4_extent *ex; ext4_lblk_t ee_block, ex_end, lblk; ext4_fsblk_t pblk; /* find extent for or closest extent to this block */ path = ext4_find_extent(inode, end, NULL, EXT4_EX_NOCACHE | EXT4_EX_NOFAIL); if (IS_ERR(path)) { ext4_journal_stop(handle); return PTR_ERR(path); } depth = ext_depth(inode); /* Leaf not may not exist only if inode has no blocks at all */ ex = path[depth].p_ext; if (!ex) { if (depth) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); err = -EFSCORRUPTED; } goto out; } ee_block = le32_to_cpu(ex->ee_block); ex_end = ee_block + ext4_ext_get_actual_len(ex) - 1; /* * See if the last block is inside the extent, if so split * the extent at 'end' block so we can easily remove the * tail of the first part of the split extent in * ext4_ext_rm_leaf(). */ if (end >= ee_block && end < ex_end) { /* * If we're going to split the extent, note that * the cluster containing the block after 'end' is * in use to avoid freeing it when removing blocks. */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex) + end - ee_block + 1; partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } /* * Split the extent in two so that 'end' is the last * block in the first new extent. Also we should not * fail removing space due to ENOSPC so try to use * reserved block if that happens. */ err = ext4_force_split_extent_at(handle, inode, &path, end + 1, 1); if (err < 0) goto out; } else if (sbi->s_cluster_ratio > 1 && end >= ex_end && partial.state == initial) { /* * If we're punching, there's an extent to the right. * If the partial cluster hasn't been set, set it to * that extent's first cluster and its state to nofree * so it won't be freed should it contain blocks to be * removed. If it's already set (tofree/nofree), we're * retrying and keep the original partial cluster info * so a cluster marked tofree as a result of earlier * extent removal is not lost. */ lblk = ex_end + 1; err = ext4_ext_search_right(inode, path, &lblk, &pblk, NULL); if (err < 0) goto out; if (pblk) { partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } } } /* * We start scanning from right side, freeing all the blocks * after i_size and walking into the tree depth-wise. */ depth = ext_depth(inode); if (path) { int k = i = depth; while (--k > 0) path[k].p_block = le16_to_cpu(path[k].p_hdr->eh_entries)+1; } else { path = kcalloc(depth + 1, sizeof(struct ext4_ext_path), GFP_NOFS | __GFP_NOFAIL); if (path == NULL) { ext4_journal_stop(handle); return -ENOMEM; } path[0].p_maxdepth = path[0].p_depth = depth; path[0].p_hdr = ext_inode_hdr(inode); i = 0; if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) { err = -EFSCORRUPTED; goto out; } } err = 0; while (i >= 0 && err == 0) { if (i == depth) { /* this is leaf block */ err = ext4_ext_rm_leaf(handle, inode, path, &partial, start, end); /* root level has p_bh == NULL, brelse() eats this */ brelse(path[i].p_bh); path[i].p_bh = NULL; i--; continue; } /* this is index block */ if (!path[i].p_hdr) { ext_debug(inode, "initialize header\n"); path[i].p_hdr = ext_block_hdr(path[i].p_bh); } if (!path[i].p_idx) { /* this level hasn't been touched yet */ path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr); path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1; ext_debug(inode, "init index ptr: hdr 0x%p, num %d\n", path[i].p_hdr, le16_to_cpu(path[i].p_hdr->eh_entries)); } else { /* we were already here, see at next index */ path[i].p_idx--; } ext_debug(inode, "level %d - index, first 0x%p, cur 0x%p\n", i, EXT_FIRST_INDEX(path[i].p_hdr), path[i].p_idx); if (ext4_ext_more_to_rm(path + i)) { struct buffer_head *bh; /* go to the next level */ ext_debug(inode, "move to level %d (block %llu)\n", i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); bh = read_extent_tree_block(inode, path[i].p_idx, depth - i - 1, EXT4_EX_NOCACHE); if (IS_ERR(bh)) { /* should we reset i_size? */ err = PTR_ERR(bh); break; } /* Yield here to deal with large extent trees. * Should be a no-op if we did IO above. */ cond_resched(); if (WARN_ON(i + 1 > depth)) { err = -EFSCORRUPTED; break; } path[i + 1].p_bh = bh; /* save actual number of indexes since this * number is changed at the next iteration */ path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries); i++; } else { /* we finished processing this index, go up */ if (path[i].p_hdr->eh_entries == 0 && i > 0) { /* index is empty, remove it; * handle must be already prepared by the * truncatei_leaf() */ err = ext4_ext_rm_idx(handle, inode, path, i); } /* root level has p_bh == NULL, brelse() eats this */ brelse(path[i].p_bh); path[i].p_bh = NULL; i--; ext_debug(inode, "return to level %d\n", i); } } trace_ext4_ext_remove_space_done(inode, start, end, depth, &partial, path->p_hdr->eh_entries); /* * if there's a partial cluster and we have removed the first extent * in the file, then we also free the partial cluster, if any */ if (partial.state == tofree && err == 0) { int flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial.lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial.pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial.lblk); partial.state = initial; } /* TODO: flexible tree reduction should be here */ if (path->p_hdr->eh_entries == 0) { /* * truncate to zero freed all the tree, * so we need to correct eh_depth */ err = ext4_ext_get_access(handle, inode, path); if (err == 0) { ext_inode_hdr(inode)->eh_depth = 0; ext_inode_hdr(inode)->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); err = ext4_ext_dirty(handle, inode, path); } } out: ext4_ext_drop_refs(path); kfree(path); path = NULL; if (err == -EAGAIN) goto again; ext4_journal_stop(handle); return err; } /* * called at mount time */ void ext4_ext_init(struct super_block *sb) { /* * possible initialization would be here */ if (ext4_has_feature_extents(sb)) { #if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS) printk(KERN_INFO "EXT4-fs: file extents enabled" #ifdef AGGRESSIVE_TEST ", aggressive tests" #endif #ifdef CHECK_BINSEARCH ", check binsearch" #endif #ifdef EXTENTS_STATS ", stats" #endif "\n"); #endif #ifdef EXTENTS_STATS spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock); EXT4_SB(sb)->s_ext_min = 1 << 30; EXT4_SB(sb)->s_ext_max = 0; #endif } } /* * called at umount time */ void ext4_ext_release(struct super_block *sb) { if (!ext4_has_feature_extents(sb)) return; #ifdef EXTENTS_STATS if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) { struct ext4_sb_info *sbi = EXT4_SB(sb); printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n", sbi->s_ext_blocks, sbi->s_ext_extents, sbi->s_ext_blocks / sbi->s_ext_extents); printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n", sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max); } #endif } static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) { ext4_lblk_t ee_block; ext4_fsblk_t ee_pblock; unsigned int ee_len; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); if (ee_len == 0) return 0; ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, EXTENT_STATUS_WRITTEN); return 0; } /* FIXME!! we need to try to merge to left or right after zero-out */ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { ext4_fsblk_t ee_pblock; unsigned int ee_len; ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); return ext4_issue_zeroout(inode, le32_to_cpu(ex->ee_block), ee_pblock, ee_len); } /* * ext4_split_extent_at() splits an extent at given block. * * @handle: the journal handle * @inode: the file inode * @path: the path to the extent * @split: the logical block where the extent is splitted. * @split_flags: indicates if the extent could be zeroout if split fails, and * the states(init or unwritten) of new extents. * @flags: flags used to insert new extent to extent tree. * * * Splits extent [a, b] into two extents [a, @split) and [@split, b], states * of which are determined by split_flag. * * There are two cases: * a> the extent are splitted into two extent. * b> split is not needed, and just mark the extent. * * return 0 on success. */ static int ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, ext4_lblk_t split, int split_flag, int flags) { struct ext4_ext_path *path = *ppath; ext4_fsblk_t newblock; ext4_lblk_t ee_block; struct ext4_extent *ex, newex, orig_ex, zero_ex; struct ext4_extent *ex2 = NULL; unsigned int ee_len, depth; int err = 0; BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); ext_debug(inode, "logical block %llu\n", (unsigned long long)split); ext4_ext_show_leaf(inode, path); depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); newblock = split - ee_block + ext4_ext_pblock(ex); BUG_ON(split < ee_block || split >= (ee_block + ee_len)); BUG_ON(!ext4_ext_is_unwritten(ex) && split_flag & (EXT4_EXT_MAY_ZEROOUT | EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; if (split == ee_block) { /* * case b: block @split is the block that the extent begins with * then we just change the state of the extent, and splitting * is not needed. */ if (split_flag & EXT4_EXT_MARK_UNWRIT2) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); if (!(flags & EXT4_GET_BLOCKS_PRE_IO)) ext4_ext_try_to_merge(handle, inode, path, ex); err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } /* case a */ memcpy(&orig_ex, ex, sizeof(orig_ex)); ex->ee_len = cpu_to_le16(split - ee_block); if (split_flag & EXT4_EXT_MARK_UNWRIT1) ext4_ext_mark_unwritten(ex); /* * path may lead to new leaf, not to original leaf any more * after ext4_ext_insert_extent() returns, */ err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto fix_extent_len; ex2 = &newex; ex2->ee_block = cpu_to_le32(split); ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block)); ext4_ext_store_pblock(ex2, newblock); if (split_flag & EXT4_EXT_MARK_UNWRIT2) ext4_ext_mark_unwritten(ex2); err = ext4_ext_insert_extent(handle, inode, ppath, &newex, flags); if (err != -ENOSPC && err != -EDQUOT && err != -ENOMEM) goto out; /* * Update path is required because previous ext4_ext_insert_extent() * may have freed or reallocated the path. Using EXT4_EX_NOFAIL * guarantees that ext4_find_extent() will not return -ENOMEM, * otherwise -ENOMEM will cause a retry in do_writepages(), and a * WARN_ON may be triggered in ext4_da_update_reserve_space() due to * an incorrect ee_len causing the i_reserved_data_blocks exception. */ path = ext4_find_extent(inode, ee_block, ppath, flags | EXT4_EX_NOFAIL); if (IS_ERR(path)) { EXT4_ERROR_INODE(inode, "Failed split extent on %u, err %ld", split, PTR_ERR(path)); return PTR_ERR(path); } depth = ext_depth(inode); ex = path[depth].p_ext; if (EXT4_EXT_MAY_ZEROOUT & split_flag) { if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { if (split_flag & EXT4_EXT_DATA_VALID1) { err = ext4_ext_zeroout(inode, ex2); zero_ex.ee_block = ex2->ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(ex2)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex2)); } else { err = ext4_ext_zeroout(inode, ex); zero_ex.ee_block = ex->ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex)); } } else { err = ext4_ext_zeroout(inode, &orig_ex); zero_ex.ee_block = orig_ex.ee_block; zero_ex.ee_len = cpu_to_le16( ext4_ext_get_actual_len(&orig_ex)); ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(&orig_ex)); } if (!err) { /* update the extent length and mark as initialized */ ex->ee_len = cpu_to_le16(ee_len); ext4_ext_try_to_merge(handle, inode, path, ex); err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (!err) /* update extent status tree */ err = ext4_zeroout_es(inode, &zero_ex); /* If we failed at this point, we don't know in which * state the extent tree exactly is so don't try to fix * length of the original extent as it may do even more * damage. */ goto out; } } fix_extent_len: ex->ee_len = orig_ex.ee_len; /* * Ignore ext4_ext_dirty return value since we are already in error path * and err is a non-zero error code. */ ext4_ext_dirty(handle, inode, path + path->p_depth); return err; out: ext4_ext_show_leaf(inode, *ppath); return err; } /* * ext4_split_extent() splits an extent and mark extent which is covered * by @map as split_flags indicates * * It may result in splitting the extent into multiple extents (up to three) * There are three possibilities: * a> There is no split required * b> Splits in two extents: Split is happening at either end of the extent * c> Splits in three extents: Somone is splitting in middle of the extent * */ static int ext4_split_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path **ppath, struct ext4_map_blocks *map, int split_flag, int flags) { struct ext4_ext_path *path = *ppath; ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len, depth; int err = 0; int unwritten; int split_flag1, flags1; int allocated = map->m_len; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); unwritten = ext4_ext_is_unwritten(ex); if (map->m_lblk + map->m_len < ee_block + ee_len) { split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT; flags1 = flags | EXT4_GET_BLOCKS_PRE_IO; if (unwritten) split_flag1 |= EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; if (split_flag & EXT4_EXT_DATA_VALID2) split_flag1 |= EXT4_EXT_DATA_VALID1; err = ext4_split_extent_at(handle, inode, ppath, map->m_lblk + map->m_len, split_flag1, flags1); if (err) goto out; } else { allocated = ee_len - (map->m_lblk - ee_block); } /* * Update path is required because previous ext4_split_extent_at() may * result in split of original leaf or extent zeroout. */ path = ext4_find_extent(inode, map->m_lblk, ppath, flags); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); return -EFSCORRUPTED; } unwritten = ext4_ext_is_unwritten(ex); split_flag1 = 0; if (map->m_lblk >= ee_block) { split_flag1 = split_flag & EXT4_EXT_DATA_VALID2; if (unwritten) { split_flag1 |= EXT4_EXT_MARK_UNWRIT1; split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT | EXT4_EXT_MARK_UNWRIT2); } err = ext4_split_extent_at(handle, inode, ppath, map->m_lblk, split_flag1, flags); if (err) goto out; } ext4_ext_show_leaf(inode, *ppath); out: return err ? err : allocated; } /* * This function is called by ext4_ext_map_blocks() if someone tries to write * to an unwritten extent. It may result in splitting the unwritten * extent into multiple extents (up to three - one initialized and two * unwritten). * There are three possibilities: * a> There is no split required: Entire extent should be initialized * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * * Pre-conditions: * - The extent pointed to by 'path' is unwritten. * - The extent pointed to by 'path' contains a superset * of the logical span [map->m_lblk, map->m_lblk + map->m_len). * * Post-conditions on success: * - the returned value is the number of blocks beyond map->l_lblk * that are allocated and initialized. * It is guaranteed to be >= map->m_len. */ static int ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, int flags) { struct ext4_ext_path *path = *ppath; struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; struct ext4_extent zero_ex1, zero_ex2; struct ext4_extent *ex, *abut_ex; ext4_lblk_t ee_block, eof_block; unsigned int ee_len, depth, map_len = map->m_len; int err = 0; int split_flag = EXT4_EXT_DATA_VALID2; int allocated = 0; unsigned int max_zeroout = 0; ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map_len) eof_block = map->m_lblk + map_len; depth = ext_depth(inode); eh = path[depth].p_hdr; ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); zero_ex1.ee_len = 0; zero_ex2.ee_len = 0; trace_ext4_ext_convert_to_initialized_enter(inode, map, ex); /* Pre-conditions */ BUG_ON(!ext4_ext_is_unwritten(ex)); BUG_ON(!in_range(map->m_lblk, ee_block, ee_len)); /* * Attempt to transfer newly initialized blocks from the currently * unwritten extent to its neighbor. This is much cheaper * than an insertion followed by a merge as those involve costly * memmove() calls. Transferring to the left is the common case in * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE) * followed by append writes. * * Limitations of the current logic: * - L1: we do not deal with writes covering the whole extent. * This would require removing the extent if the transfer * is possible. * - L2: we only attempt to merge with an extent stored in the * same extent tree node. */ if ((map->m_lblk == ee_block) && /* See if we can merge left */ (map_len < ee_len) && /*L1*/ (ex > EXT_FIRST_EXTENT(eh))) { /*L2*/ ext4_lblk_t prev_lblk; ext4_fsblk_t prev_pblk, ee_pblk; unsigned int prev_len; abut_ex = ex - 1; prev_lblk = le32_to_cpu(abut_ex->ee_block); prev_len = ext4_ext_get_actual_len(abut_ex); prev_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); /* * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: * - C1: abut_ex is initialized, * - C2: abut_ex is logically abutting ex, * - C3: abut_ex is physically abutting ex, * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/ ((prev_lblk + prev_len) == ee_block) && /*C2*/ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/ (prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); /* Shift the start of ex by 'map_len' blocks */ ex->ee_block = cpu_to_le32(ee_block + map_len); ext4_ext_store_pblock(ex, ee_pblk + map_len); ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_unwritten(ex); /* Restore the flag */ /* Extend abut_ex by 'map_len' blocks */ abut_ex->ee_len = cpu_to_le16(prev_len + map_len); /* Result: number of initialized blocks past m_lblk */ allocated = map_len; } } else if (((map->m_lblk + map_len) == (ee_block + ee_len)) && (map_len < ee_len) && /*L1*/ ex < EXT_LAST_EXTENT(eh)) { /*L2*/ /* See if we can merge right */ ext4_lblk_t next_lblk; ext4_fsblk_t next_pblk, ee_pblk; unsigned int next_len; abut_ex = ex + 1; next_lblk = le32_to_cpu(abut_ex->ee_block); next_len = ext4_ext_get_actual_len(abut_ex); next_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); /* * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: * - C1: abut_ex is initialized, * - C2: abut_ex is logically abutting ex, * - C3: abut_ex is physically abutting ex, * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/ ((map->m_lblk + map_len) == next_lblk) && /*C2*/ ((ee_pblk + ee_len) == next_pblk) && /*C3*/ (next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); /* Shift the start of abut_ex by 'map_len' blocks */ abut_ex->ee_block = cpu_to_le32(next_lblk - map_len); ext4_ext_store_pblock(abut_ex, next_pblk - map_len); ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_unwritten(ex); /* Restore the flag */ /* Extend abut_ex by 'map_len' blocks */ abut_ex->ee_len = cpu_to_le16(next_len + map_len); /* Result: number of initialized blocks past m_lblk */ allocated = map_len; } } if (allocated) { /* Mark the block containing both extents as dirty */ err = ext4_ext_dirty(handle, inode, path + depth); /* Update path to point to the right extent */ path[depth].p_ext = abut_ex; goto out; } else allocated = ee_len - (map->m_lblk - ee_block); WARN_ON(map->m_lblk < ee_block); /* * It is safe to convert extent to initialized via explicit * zeroout only if extent is fully inside i_size or new_size. */ split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; if (EXT4_EXT_MAY_ZEROOUT & split_flag) max_zeroout = sbi->s_extent_max_zeroout_kb >> (inode->i_sb->s_blocksize_bits - 10); /* * five cases: * 1. split the extent into three extents. * 2. split the extent into two extents, zeroout the head of the first * extent. * 3. split the extent into two extents, zeroout the tail of the second * extent. * 4. split the extent into two extents with out zeroout. * 5. no splitting needed, just possibly zeroout the head and / or the * tail of the extent. */ split_map.m_lblk = map->m_lblk; split_map.m_len = map->m_len; if (max_zeroout && (allocated > split_map.m_len)) { if (allocated <= max_zeroout) { /* case 3 or 5 */ zero_ex1.ee_block = cpu_to_le32(split_map.m_lblk + split_map.m_len); zero_ex1.ee_len = cpu_to_le16(allocated - split_map.m_len); ext4_ext_store_pblock(&zero_ex1, ext4_ext_pblock(ex) + split_map.m_lblk + split_map.m_len - ee_block); err = ext4_ext_zeroout(inode, &zero_ex1); if (err) goto fallback; split_map.m_len = allocated; } if (split_map.m_lblk - ee_block + split_map.m_len < max_zeroout) { /* case 2 or 5 */ if (split_map.m_lblk != ee_block) { zero_ex2.ee_block = ex->ee_block; zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk - ee_block); ext4_ext_store_pblock(&zero_ex2, ext4_ext_pblock(ex)); err = ext4_ext_zeroout(inode, &zero_ex2); if (err) goto fallback; } split_map.m_len += split_map.m_lblk - ee_block; split_map.m_lblk = ee_block; allocated = map->m_len; } } fallback: err = ext4_split_extent(handle, inode, ppath, &split_map, split_flag, flags); if (err > 0) err = 0; out: /* If we have gotten a failure, don't zero out status tree */ if (!err) { err = ext4_zeroout_es(inode, &zero_ex1); if (!err) err = ext4_zeroout_es(inode, &zero_ex2); } return err ? err : allocated; } /* * This function is called by ext4_ext_map_blocks() from * ext4_get_blocks_dio_write() when DIO to write * to an unwritten extent. * * Writing to an unwritten extent may result in splitting the unwritten * extent into multiple initialized/unwritten extents (up to three) * There are three possibilities: * a> There is no split required: Entire extent should be unwritten * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * * This works the same way in the case of initialized -> unwritten conversion. * * One of more index blocks maybe needed if the extent tree grow after * the unwritten extent split. To prevent ENOSPC occur at the IO * complete, we need to split the unwritten extent before DIO submit * the IO. The unwritten extent called at this time will be split * into three unwritten extent(at most). After IO complete, the part * being filled will be convert to initialized by the end_io callback function * via ext4_convert_unwritten_extents(). * * Returns the size of unwritten extent to be written on success. */ static int ext4_split_convert_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, int flags) { struct ext4_ext_path *path = *ppath; ext4_lblk_t eof_block; ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len; int split_flag = 0, depth; ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map->m_len); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) eof_block = map->m_lblk + map->m_len; /* * It is safe to convert extent to initialized via explicit * zeroout only if extent is fully inside i_size or new_size. */ depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); /* Convert to unwritten */ if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) { split_flag |= EXT4_EXT_DATA_VALID1; /* Convert to initialized */ } else if (flags & EXT4_GET_BLOCKS_CONVERT) { split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2); } flags |= EXT4_GET_BLOCKS_PRE_IO; return ext4_split_extent(handle, inode, ppath, map, split_flag, flags); } static int ext4_convert_unwritten_extents_endio(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath) { struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; int depth; int err = 0; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); /* If extent is larger than requested it is a clear sign that we still * have some extent state machine issues left. So extent_split is still * required. * TODO: Once all related issues will be fixed this situation should be * illegal. */ if (ee_block != map->m_lblk || ee_len > map->m_len) { #ifdef CONFIG_EXT4_DEBUG ext4_warning(inode->i_sb, "Inode (%ld) finished: extent logical block %llu," " len %u; IO logical block %llu, len %u", inode->i_ino, (unsigned long long)ee_block, ee_len, (unsigned long long)map->m_lblk, map->m_len); #endif err = ext4_split_convert_extents(handle, inode, map, ppath, EXT4_GET_BLOCKS_CONVERT); if (err < 0) return err; path = ext4_find_extent(inode, map->m_lblk, ppath, 0); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); ex = path[depth].p_ext; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; /* first mark the extent as initialized */ ext4_ext_mark_initialized(ex); /* note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ ext4_ext_try_to_merge(handle, inode, path, ex); /* Mark modified extent as dirty */ err = ext4_ext_dirty(handle, inode, path + path->p_depth); out: ext4_ext_show_leaf(inode, path); return err; } static int convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, unsigned int *allocated) { struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; int depth; int err = 0; /* * Make sure that the extent is no bigger than we support with * unwritten extent */ if (map->m_len > EXT_UNWRITTEN_MAX_LEN) map->m_len = EXT_UNWRITTEN_MAX_LEN / 2; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); if (ee_block != map->m_lblk || ee_len > map->m_len) { err = ext4_split_convert_extents(handle, inode, map, ppath, EXT4_GET_BLOCKS_CONVERT_UNWRITTEN); if (err < 0) return err; path = ext4_find_extent(inode, map->m_lblk, ppath, 0); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); return -EFSCORRUPTED; } } err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; /* first mark the extent as unwritten */ ext4_ext_mark_unwritten(ex); /* note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ ext4_ext_try_to_merge(handle, inode, path, ex); /* Mark modified extent as dirty */ err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (err) return err; ext4_ext_show_leaf(inode, path); ext4_update_inode_fsync_trans(handle, inode, 1); map->m_flags |= EXT4_MAP_UNWRITTEN; if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; return 0; } static int ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, int flags, unsigned int allocated, ext4_fsblk_t newblock) { int ret = 0; int err = 0; ext_debug(inode, "logical block %llu, max_blocks %u, flags 0x%x, allocated %u\n", (unsigned long long)map->m_lblk, map->m_len, flags, allocated); ext4_ext_show_leaf(inode, *ppath); /* * When writing into unwritten space, we should not fail to * allocate metadata blocks for the new extent block if needed. */ flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL; trace_ext4_ext_handle_unwritten_extents(inode, map, flags, allocated, newblock); /* get_block() before submitting IO, split the extent */ if (flags & EXT4_GET_BLOCKS_PRE_IO) { ret = ext4_split_convert_extents(handle, inode, map, ppath, flags | EXT4_GET_BLOCKS_CONVERT); if (ret < 0) { err = ret; goto out2; } /* * shouldn't get a 0 return when splitting an extent unless * m_len is 0 (bug) or extent has been corrupted */ if (unlikely(ret == 0)) { EXT4_ERROR_INODE(inode, "unexpected ret == 0, m_len = %u", map->m_len); err = -EFSCORRUPTED; goto out2; } map->m_flags |= EXT4_MAP_UNWRITTEN; goto out; } /* IO end_io complete, convert the filled extent to written */ if (flags & EXT4_GET_BLOCKS_CONVERT) { err = ext4_convert_unwritten_extents_endio(handle, inode, map, ppath); if (err < 0) goto out2; ext4_update_inode_fsync_trans(handle, inode, 1); goto map_out; } /* buffered IO cases */ /* * repeat fallocate creation request * we already have an unwritten extent */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { map->m_flags |= EXT4_MAP_UNWRITTEN; goto map_out; } /* buffered READ or buffered write_begin() lookup */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * We have blocks reserved already. We * return allocated blocks so that delalloc * won't do block reservation for us. But * the buffer head will be unmapped so that * a read from the block returns 0s. */ map->m_flags |= EXT4_MAP_UNWRITTEN; goto out1; } /* * Default case when (flags & EXT4_GET_BLOCKS_CREATE) == 1. * For buffered writes, at writepage time, etc. Convert a * discovered unwritten extent to written. */ ret = ext4_ext_convert_to_initialized(handle, inode, map, ppath, flags); if (ret < 0) { err = ret; goto out2; } ext4_update_inode_fsync_trans(handle, inode, 1); /* * shouldn't get a 0 return when converting an unwritten extent * unless m_len is 0 (bug) or extent has been corrupted */ if (unlikely(ret == 0)) { EXT4_ERROR_INODE(inode, "unexpected ret == 0, m_len = %u", map->m_len); err = -EFSCORRUPTED; goto out2; } out: allocated = ret; map->m_flags |= EXT4_MAP_NEW; map_out: map->m_flags |= EXT4_MAP_MAPPED; out1: map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; map->m_len = allocated; ext4_ext_show_leaf(inode, *ppath); out2: return err ? err : allocated; } /* * get_implied_cluster_alloc - check to see if the requested * allocation (in the map structure) overlaps with a cluster already * allocated in an extent. * @sb The filesystem superblock structure * @map The requested lblk->pblk mapping * @ex The extent structure which might contain an implied * cluster allocation * * This function is called by ext4_ext_map_blocks() after we failed to * find blocks that were already in the inode's extent tree. Hence, * we know that the beginning of the requested region cannot overlap * the extent from the inode's extent tree. There are three cases we * want to catch. The first is this case: * * |--- cluster # N--| * |--- extent ---| |---- requested region ---| * |==========| * * The second case that we need to test for is this one: * * |--------- cluster # N ----------------| * |--- requested region --| |------- extent ----| * |=======================| * * The third case is when the requested region lies between two extents * within the same cluster: * |------------- cluster # N-------------| * |----- ex -----| |---- ex_right ----| * |------ requested region ------| * |================| * * In each of the above cases, we need to set the map->m_pblk and * map->m_len so it corresponds to the return the extent labelled as * "|====|" from cluster #N, since it is already in use for data in * cluster EXT4_B2C(sbi, map->m_lblk). We will then return 1 to * signal to ext4_ext_map_blocks() that map->m_pblk should be treated * as a new "allocated" block region. Otherwise, we will return 0 and * ext4_ext_map_blocks() will then allocate one or more new clusters * by calling ext4_mb_new_blocks(). */ static int get_implied_cluster_alloc(struct super_block *sb, struct ext4_map_blocks *map, struct ext4_extent *ex, struct ext4_ext_path *path) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ext4_lblk_t ex_cluster_start, ex_cluster_end; ext4_lblk_t rr_cluster_start; ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len = ext4_ext_get_actual_len(ex); /* The extent passed in that we are trying to match */ ex_cluster_start = EXT4_B2C(sbi, ee_block); ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1); /* The requested region passed into ext4_map_blocks() */ rr_cluster_start = EXT4_B2C(sbi, map->m_lblk); if ((rr_cluster_start == ex_cluster_end) || (rr_cluster_start == ex_cluster_start)) { if (rr_cluster_start == ex_cluster_end) ee_start += ee_len - 1; map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset; map->m_len = min(map->m_len, (unsigned) sbi->s_cluster_ratio - c_offset); /* * Check for and handle this case: * * |--------- cluster # N-------------| * |------- extent ----| * |--- requested region ---| * |===========| */ if (map->m_lblk < ee_block) map->m_len = min(map->m_len, ee_block - map->m_lblk); /* * Check for the case where there is already another allocated * block to the right of 'ex' but before the end of the cluster. * * |------------- cluster # N-------------| * |----- ex -----| |---- ex_right ----| * |------ requested region ------| * |================| */ if (map->m_lblk > ee_block) { ext4_lblk_t next = ext4_ext_next_allocated_block(path); map->m_len = min(map->m_len, next - map->m_lblk); } trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1); return 1; } trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0); return 0; } /* * Determine hole length around the given logical block, first try to * locate and expand the hole from the given @path, and then adjust it * if it's partially or completely converted to delayed extents, insert * it into the extent cache tree if it's indeed a hole, finally return * the length of the determined extent. */ static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t lblk) { ext4_lblk_t hole_start, len; struct extent_status es; hole_start = lblk; len = ext4_ext_find_hole(inode, path, &hole_start); again: ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, hole_start + len - 1, &es); if (!es.es_len) goto insert_hole; /* * There's a delalloc extent in the hole, handle it if the delalloc * extent is in front of, behind and straddle the queried range. */ if (lblk >= es.es_lblk + es.es_len) { /* * The delalloc extent is in front of the queried range, * find again from the queried start block. */ len -= lblk - hole_start; hole_start = lblk; goto again; } else if (in_range(lblk, es.es_lblk, es.es_len)) { /* * The delalloc extent containing lblk, it must have been * added after ext4_map_blocks() checked the extent status * tree, adjust the length to the delalloc extent's after * lblk. */ len = es.es_lblk + es.es_len - lblk; return len; } else { /* * The delalloc extent is partially or completely behind * the queried range, update hole length until the * beginning of the delalloc extent. */ len = min(es.es_lblk - hole_start, len); } insert_hole: /* Put just found gap into cache to speed up subsequent requests */ ext_debug(inode, " -> %u:%u\n", hole_start, len); ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE); /* Update hole_len to reflect hole size after lblk */ if (hole_start != lblk) len -= lblk - hole_start; return len; } /* * Block allocation/map/preallocation routine for extents based files * * * Need to be called with * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) * * return > 0, number of blocks already mapped/allocated * if create == 0 and these are pre-allocated blocks * buffer head is unmapped * otherwise blocks are mapped * * return = 0, if plain look up failed (blocks have not been allocated) * buffer head is unmapped * * return < 0, error case. */ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct ext4_ext_path *path = NULL; struct ext4_extent newex, *ex, ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0, pblk; int err = 0, depth, ret; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; ext4_lblk_t cluster_offset; ext_debug(inode, "blocks %u/%u requested\n", map->m_lblk, map->m_len); trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* find extent for this block */ path = ext4_find_extent(inode, map->m_lblk, NULL, 0); if (IS_ERR(path)) { err = PTR_ERR(path); path = NULL; goto out; } depth = ext_depth(inode); /* * consistent leaf must not be empty; * this situation is possible, though, _during_ tree modification; * this is why assert can't be put in ext4_find_extent() */ if (unlikely(path[depth].p_ext == NULL && depth != 0)) { EXT4_ERROR_INODE(inode, "bad extent address " "lblock: %lu, depth: %d pblock %lld", (unsigned long) map->m_lblk, depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } ex = path[depth].p_ext; if (ex) { ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len; /* * unwritten extents are treated as holes, except that * we split out initialized portions during a write. */ ee_len = ext4_ext_get_actual_len(ex); trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len); /* if found extent covers block, simply return it */ if (in_range(map->m_lblk, ee_block, ee_len)) { newblock = map->m_lblk - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (map->m_lblk - ee_block); ext_debug(inode, "%u fit into %u:%d -> %llu\n", map->m_lblk, ee_block, ee_len, newblock); /* * If the extent is initialized check whether the * caller wants to convert it to unwritten. */ if ((!ext4_ext_is_unwritten(ex)) && (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { err = convert_initialized_extent(handle, inode, map, &path, &allocated); goto out; } else if (!ext4_ext_is_unwritten(ex)) { map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; map->m_len = allocated; ext4_ext_show_leaf(inode, path); goto out; } ret = ext4_ext_handle_unwritten_extents( handle, inode, map, &path, flags, allocated, newblock); if (ret < 0) err = ret; else allocated = ret; goto out; } } /* * requested block isn't allocated yet; * we couldn't try to create block if create flag is zero */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { ext4_lblk_t len; len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); map->m_pblk = 0; map->m_len = min_t(unsigned int, map->m_len, len); goto out; } /* * Okay, we need to do block allocation. */ newex.ee_block = cpu_to_le32(map->m_lblk); cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); /* * If we are doing bigalloc, check to see if the extent returned * by ext4_find_extent() implies a cluster we can use. */ if (cluster_offset && ex && get_implied_cluster_alloc(inode->i_sb, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; goto got_allocated_blocks; } /* find neighbour allocated blocks */ ar.lleft = map->m_lblk; err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft); if (err) goto out; ar.lright = map->m_lblk; err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2); if (err < 0) goto out; /* Check if the extent after searching to the right implies a * cluster we can use. */ if ((sbi->s_cluster_ratio > 1) && err && get_implied_cluster_alloc(inode->i_sb, map, &ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; goto got_allocated_blocks; } /* * See if request is beyond maximum number of blocks we can have in * a single extent. For an initialized extent this limit is * EXT_INIT_MAX_LEN and for an unwritten extent this limit is * EXT_UNWRITTEN_MAX_LEN. */ if (map->m_len > EXT_INIT_MAX_LEN && !(flags & EXT4_GET_BLOCKS_UNWRIT_EXT)) map->m_len = EXT_INIT_MAX_LEN; else if (map->m_len > EXT_UNWRITTEN_MAX_LEN && (flags & EXT4_GET_BLOCKS_UNWRIT_EXT)) map->m_len = EXT_UNWRITTEN_MAX_LEN; /* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */ newex.ee_len = cpu_to_le16(map->m_len); err = ext4_ext_check_overlap(sbi, inode, &newex, path); if (err) allocated = ext4_ext_get_actual_len(&newex); else allocated = map->m_len; /* allocate new block */ ar.inode = inode; ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk); ar.logical = map->m_lblk; /* * We calculate the offset from the beginning of the cluster * for the logical block number, since when we allocate a * physical cluster, the physical block should start at the * same offset from the beginning of the cluster. This is * needed so that future calls to get_implied_cluster_alloc() * work correctly. */ offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ar.len = EXT4_NUM_B2C(sbi, offset+allocated); ar.goal -= offset; ar.logical -= offset; if (S_ISREG(inode->i_mode)) ar.flags = EXT4_MB_HINT_DATA; else /* disable in-core preallocation for non-regular files */ ar.flags = 0; if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE) ar.flags |= EXT4_MB_HINT_NOPREALLOC; if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) ar.flags |= EXT4_MB_DELALLOC_RESERVED; if (flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) ar.flags |= EXT4_MB_USE_RESERVED; newblock = ext4_mb_new_blocks(handle, &ar, &err); if (!newblock) goto out; allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; ext_debug(inode, "allocate new block: goal %llu, found %llu/%u, requested %u\n", ar.goal, newblock, ar.len, allocated); if (ar.len > allocated) ar.len = allocated; got_allocated_blocks: /* try to insert new extent into found leaf and return */ pblk = newblock + offset; ext4_ext_store_pblock(&newex, pblk); newex.ee_len = cpu_to_le16(ar.len); /* Mark unwritten */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { ext4_ext_mark_unwritten(&newex); map->m_flags |= EXT4_MAP_UNWRITTEN; } err = ext4_ext_insert_extent(handle, inode, &path, &newex, flags); if (err) { if (allocated_clusters) { int fb_flags = 0; /* * free data blocks we just allocated. * not a good idea to call discard here directly, * but otherwise we'd need to call it every free(). */ ext4_discard_preallocations(inode, 0); if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; ext4_free_blocks(handle, inode, NULL, newblock, EXT4_C2B(sbi, allocated_clusters), fb_flags); } goto out; } /* * Reduce the reserved cluster count to reflect successful deferred * allocation of delayed allocated clusters or direct allocation of * clusters discovered to be delayed allocated. Once allocated, a * cluster is not included in the reserved count. */ if (test_opt(inode->i_sb, DELALLOC) && allocated_clusters) { if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { /* * When allocating delayed allocated clusters, simply * reduce the reserved cluster count and claim quota */ ext4_da_update_reserve_space(inode, allocated_clusters, 1); } else { ext4_lblk_t lblk, len; unsigned int n; /* * When allocating non-delayed allocated clusters * (from fallocate, filemap, DIO, or clusters * allocated when delalloc has been disabled by * ext4_nonda_switch), reduce the reserved cluster * count by the number of allocated clusters that * have previously been delayed allocated. Quota * has been claimed by ext4_mb_new_blocks() above, * so release the quota reservations made for any * previously delayed allocated clusters. */ lblk = EXT4_LBLK_CMASK(sbi, map->m_lblk); len = allocated_clusters << sbi->s_cluster_bits; n = ext4_es_delayed_clu(inode, lblk, len); if (n > 0) ext4_da_update_reserve_space(inode, (int) n, 0); } } /* * Cache the extent and update transaction to commit on fdatasync only * when it is _not_ an unwritten extent. */ if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0) ext4_update_inode_fsync_trans(handle, inode, 1); else ext4_update_inode_fsync_trans(handle, inode, 0); map->m_flags |= (EXT4_MAP_NEW | EXT4_MAP_MAPPED); map->m_pblk = pblk; map->m_len = ar.len; allocated = map->m_len; ext4_ext_show_leaf(inode, path); out: ext4_ext_drop_refs(path); kfree(path); trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); return err ? err : allocated; } int ext4_ext_truncate(handle_t *handle, struct inode *inode) { struct super_block *sb = inode->i_sb; ext4_lblk_t last_block; int err = 0; /* * TODO: optimization is possible here. * Probably we need not scan at all, * because page truncation is enough. */ /* we have to know where to truncate from in crash case */ EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_mark_inode_dirty(handle, inode); if (err) return err; last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); retry: err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); if (err == -ENOMEM) { cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } if (err) return err; retry_remove_space: err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); if (err == -ENOMEM) { cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry_remove_space; } return err; } static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, ext4_lblk_t len, loff_t new_size, int flags) { struct inode *inode = file_inode(file); handle_t *handle; int ret = 0, ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; struct ext4_map_blocks map; unsigned int credits; loff_t epos; BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)); map.m_lblk = offset; map.m_len = len; /* * Don't normalize the request if it can fit in one extent so * that it doesn't get unnecessarily split into multiple * extents. */ if (len <= EXT_UNWRITTEN_MAX_LEN) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, len); depth = ext_depth(inode); retry: while (len) { /* * Recalculate credits when extent tree depth changes. */ if (depth != ext_depth(inode)) { credits = ext4_chunk_trans_blocks(inode, len); depth = ext_depth(inode); } handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); break; } ret = ext4_map_blocks(handle, inode, &map, flags); if (ret <= 0) { ext4_debug("inode #%lu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); break; } /* * allow a full retry cycle for any remaining allocations */ retries = 0; map.m_lblk += ret; map.m_len = len = len - ret; epos = (loff_t)map.m_lblk << inode->i_blkbits; inode->i_ctime = current_time(inode); if (new_size) { if (epos > new_size) epos = new_size; if (ext4_update_inode_size(inode, epos) & 0x1) inode->i_mtime = inode->i_ctime; } ret2 = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); ret3 = ext4_journal_stop(handle); ret2 = ret3 ? ret3 : ret2; if (unlikely(ret2)) break; } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; return ret > 0 ? ret2 : ret; } static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) { struct inode *inode = file_inode(file); struct address_space *mapping = file->f_mapping; handle_t *handle = NULL; unsigned int max_blocks; loff_t new_size = 0; int ret = 0; int flags; int credits; int partial_begin, partial_end; loff_t start, end; ext4_lblk_t lblk; unsigned int blkbits = inode->i_blkbits; trace_ext4_zero_range(inode, offset, len, mode); /* Call ext4_force_commit to flush all data in case of data=journal. */ if (ext4_should_journal_data(inode)) { ret = ext4_force_commit(inode->i_sb); if (ret) return ret; } /* * Round up offset. This is not fallocate, we need to zero out * blocks, so convert interior block aligned part of the range to * unwritten and possibly manually zero out unaligned parts of the * range. */ start = round_up(offset, 1 << blkbits); end = round_down((offset + len), 1 << blkbits); if (start < offset || end > offset + len) return -EINVAL; partial_begin = offset & ((1 << blkbits) - 1); partial_end = (offset + len) & ((1 << blkbits) - 1); lblk = start >> blkbits; max_blocks = (end >> blkbits); if (max_blocks < lblk) max_blocks = 0; else max_blocks -= lblk; inode_lock(inode); /* * Indirect files do not support unwritten extents */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { ret = -EOPNOTSUPP; goto out_mutex; } if (!(mode & FALLOC_FL_KEEP_SIZE) && (offset + len > inode->i_size || offset + len > EXT4_I(inode)->i_disksize)) { new_size = offset + len; ret = inode_newsize_ok(inode, new_size); if (ret) goto out_mutex; } flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; /* Wait all existing dio workers, newcomers will block on i_mutex */ inode_dio_wait(inode); ret = file_modified(file); if (ret) goto out_mutex; /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, round_down(offset, 1 << blkbits) >> blkbits, (round_up((offset + len), 1 << blkbits) - round_down(offset, 1 << blkbits)) >> blkbits, new_size, flags); if (ret) goto out_mutex; } /* Zero range excluding the unaligned edges */ if (max_blocks > 0) { flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); /* * Prevent page faults from reinstantiating pages we have * released from page cache. */ filemap_invalidate_lock(mapping); ret = ext4_break_layouts(inode); if (ret) { filemap_invalidate_unlock(mapping); goto out_mutex; } ret = ext4_update_disksize_before_punch(inode, offset, len); if (ret) { filemap_invalidate_unlock(mapping); goto out_mutex; } /* Now release the pages and zero block aligned part of pages */ truncate_pagecache_range(inode, start, end - 1); inode->i_mtime = inode->i_ctime = current_time(inode); ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); filemap_invalidate_unlock(mapping); if (ret) goto out_mutex; } if (!partial_begin && !partial_end) goto out_mutex; /* * In worst case we have to writeout two nonadjacent unwritten * blocks and update the inode */ credits = (2 * ext4_ext_index_trans_blocks(inode, 2)) + 1; if (ext4_should_journal_data(inode)) credits += 2; handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(inode->i_sb, ret); goto out_mutex; } inode->i_mtime = inode->i_ctime = current_time(inode); if (new_size) ext4_update_inode_size(inode, new_size); ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); if (file->f_flags & O_SYNC) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); out_mutex: inode_unlock(inode); return ret; } /* * preallocate space for a file. This implements ext4's fallocate file * operation, which gets called from sys_fallocate system call. * For block-mapped files, posix_fallocate should fall back to the method * of writing zeroes to the required new blocks (the same behavior which is * expected for file systems which do not support fallocate() system call). */ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); loff_t new_size = 0; unsigned int max_blocks; int ret = 0; int flags; ext4_lblk_t lblk; unsigned int blkbits = inode->i_blkbits; /* * Encrypted inodes can't handle collapse range or insert * range since we would need to re-encrypt blocks with a * different IV or XTS tweak (which are based on the logical * block number). */ if (IS_ENCRYPTED(inode) && (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; inode_lock(inode); ret = ext4_convert_inline_data(inode); inode_unlock(inode); if (ret) goto exit; if (mode & FALLOC_FL_PUNCH_HOLE) { ret = ext4_punch_hole(file, offset, len); goto exit; } if (mode & FALLOC_FL_COLLAPSE_RANGE) { ret = ext4_collapse_range(file, offset, len); goto exit; } if (mode & FALLOC_FL_INSERT_RANGE) { ret = ext4_insert_range(file, offset, len); goto exit; } if (mode & FALLOC_FL_ZERO_RANGE) { ret = ext4_zero_range(file, offset, len, mode); goto exit; } trace_ext4_fallocate_enter(inode, offset, len, mode); lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; inode_lock(inode); /* * We only support preallocation for extent-based files only */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { ret = -EOPNOTSUPP; goto out; } if (!(mode & FALLOC_FL_KEEP_SIZE) && (offset + len > inode->i_size || offset + len > EXT4_I(inode)->i_disksize)) { new_size = offset + len; ret = inode_newsize_ok(inode, new_size); if (ret) goto out; } /* Wait all existing dio workers, newcomers will block on i_mutex */ inode_dio_wait(inode); ret = file_modified(file); if (ret) goto out; ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); if (ret) goto out; if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) { ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, EXT4_I(inode)->i_sync_tid); } out: inode_unlock(inode); trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); exit: return ret; } /* * This function convert a range of blocks to written extents * The caller of this function will pass the start offset and the size. * all unwritten extents within this range will be converted to * written extents. * * This function is called from the direct IO end io call back * function, to convert the fallocated extents after IO is completed. * Returns 0 on success. */ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len) { unsigned int max_blocks; int ret = 0, ret2 = 0, ret3 = 0; struct ext4_map_blocks map; unsigned int blkbits = inode->i_blkbits; unsigned int credits = 0; map.m_lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); if (!handle) { /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, max_blocks); } while (ret >= 0 && ret < max_blocks) { map.m_lblk += ret; map.m_len = (max_blocks -= ret); if (credits) { handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); break; } } ret = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_IO_CONVERT_EXT); if (ret <= 0) ext4_warning(inode->i_sb, "inode #%lu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); ret2 = ext4_mark_inode_dirty(handle, inode); if (credits) { ret3 = ext4_journal_stop(handle); if (unlikely(ret3)) ret2 = ret3; } if (ret <= 0 || ret2) break; } return ret > 0 ? ret2 : ret; } int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end) { int ret = 0, err = 0; struct ext4_io_end_vec *io_end_vec; /* * This is somewhat ugly but the idea is clear: When transaction is * reserved, everything goes into it. Otherwise we rather start several * smaller transactions for conversion of each extent separately. */ if (handle) { handle = ext4_journal_start_reserved(handle, EXT4_HT_EXT_CONVERT); if (IS_ERR(handle)) return PTR_ERR(handle); } list_for_each_entry(io_end_vec, &io_end->list_vec, list) { ret = ext4_convert_unwritten_extents(handle, io_end->inode, io_end_vec->offset, io_end_vec->size); if (ret) break; } if (handle) err = ext4_journal_stop(handle); return ret < 0 ? ret : err; } static int ext4_iomap_xattr_fiemap(struct inode *inode, struct iomap *iomap) { __u64 physical = 0; __u64 length = 0; int blockbits = inode->i_sb->s_blocksize_bits; int error = 0; u16 iomap_type; /* in-inode? */ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { struct ext4_iloc iloc; int offset; /* offset of xattr in inode */ error = ext4_get_inode_loc(inode, &iloc); if (error) return error; physical = (__u64)iloc.bh->b_blocknr << blockbits; offset = EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize; physical += offset; length = EXT4_SB(inode->i_sb)->s_inode_size - offset; brelse(iloc.bh); iomap_type = IOMAP_INLINE; } else if (EXT4_I(inode)->i_file_acl) { /* external block */ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits; length = inode->i_sb->s_blocksize; iomap_type = IOMAP_MAPPED; } else { /* no in-inode or external block for xattr, so return -ENOENT */ error = -ENOENT; goto out; } iomap->addr = physical; iomap->offset = 0; iomap->length = length; iomap->type = iomap_type; iomap->flags = 0; out: return error; } static int ext4_iomap_xattr_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { int error; error = ext4_iomap_xattr_fiemap(inode, iomap); if (error == 0 && (offset >= iomap->length)) error = -ENOENT; return error; } static const struct iomap_ops ext4_iomap_xattr_ops = { .iomap_begin = ext4_iomap_xattr_begin, }; static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len) { u64 maxbytes; if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) maxbytes = inode->i_sb->s_maxbytes; else maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes; if (*len == 0) return -EINVAL; if (start > maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; return 0; } int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { int error = 0; if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { error = ext4_ext_precache(inode); if (error) return error; fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } /* * For bitmap files the maximum size limit could be smaller than * s_maxbytes, so check len here manually instead of just relying on the * generic check. */ error = ext4_fiemap_check_ranges(inode, start, &len); if (error) return error; if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; return iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_xattr_ops); } return iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops); } int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { ext4_lblk_t start_blk, len_blks; __u64 last_blk; int error = 0; if (ext4_has_inline_data(inode)) { int has_inline; down_read(&EXT4_I(inode)->xattr_sem); has_inline = ext4_has_inline_data(inode); up_read(&EXT4_I(inode)->xattr_sem); if (has_inline) return 0; } if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { error = ext4_ext_precache(inode); if (error) return error; fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } error = fiemap_prep(inode, fieinfo, start, &len, 0); if (error) return error; error = ext4_fiemap_check_ranges(inode, start, &len); if (error) return error; start_blk = start >> inode->i_sb->s_blocksize_bits; last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; if (last_blk >= EXT_MAX_BLOCKS) last_blk = EXT_MAX_BLOCKS-1; len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; /* * Walk the extent tree gathering extent information * and pushing extents back to the user. */ return ext4_fill_es_cache_info(inode, start_blk, len_blks, fieinfo); } /* * ext4_ext_shift_path_extents: * Shift the extents of a path structure lying between path[depth].p_ext * and EXT_LAST_EXTENT(path[depth].p_hdr), by @shift blocks. @SHIFT tells * if it is right shift or left shift operation. */ static int ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, struct inode *inode, handle_t *handle, enum SHIFT_DIRECTION SHIFT) { int depth, err = 0; struct ext4_extent *ex_start, *ex_last; bool update = false; int credits, restart_credits; depth = path->p_depth; while (depth >= 0) { if (depth == path->p_depth) { ex_start = path[depth].p_ext; if (!ex_start) return -EFSCORRUPTED; ex_last = EXT_LAST_EXTENT(path[depth].p_hdr); /* leaf + sb + inode */ credits = 3; if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) { update = true; /* extent tree + sb + inode */ credits = depth + 2; } restart_credits = ext4_writepage_trans_blocks(inode); err = ext4_datasem_ensure_credits(handle, inode, credits, restart_credits, 0); if (err) { if (err > 0) err = -EAGAIN; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { le32_add_cpu(&ex_start->ee_block, -shift); /* Try to merge to the left. */ if ((ex_start > EXT_FIRST_EXTENT(path[depth].p_hdr)) && ext4_ext_try_to_merge_right(inode, path, ex_start - 1)) ex_last--; else ex_start++; } else { le32_add_cpu(&ex_last->ee_block, shift); ext4_ext_try_to_merge_right(inode, path, ex_last); ex_last--; } } err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; if (--depth < 0 || !update) break; } /* Update index too */ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; if (SHIFT == SHIFT_LEFT) le32_add_cpu(&path[depth].p_idx->ei_block, -shift); else le32_add_cpu(&path[depth].p_idx->ei_block, shift); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; /* we are done if current index is not a starting index */ if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr)) break; depth--; } out: return err; } /* * ext4_ext_shift_extents: * All the extents which lies in the range from @start to the last allocated * block for the @inode are shifted either towards left or right (depending * upon @SHIFT) by @shift blocks. * On success, 0 is returned, error otherwise. */ static int ext4_ext_shift_extents(struct inode *inode, handle_t *handle, ext4_lblk_t start, ext4_lblk_t shift, enum SHIFT_DIRECTION SHIFT) { struct ext4_ext_path *path; int ret = 0, depth; struct ext4_extent *extent; ext4_lblk_t stop, *iterator, ex_start, ex_end; ext4_lblk_t tmp = EXT_MAX_BLOCKS; /* Let path point to the last extent */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (!extent) goto out; stop = le32_to_cpu(extent->ee_block); /* * For left shifts, make sure the hole on the left is big enough to * accommodate the shift. For right shifts, make sure the last extent * won't be shifted beyond EXT_MAX_BLOCKS. */ if (SHIFT == SHIFT_LEFT) { path = ext4_find_extent(inode, start - 1, &path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (extent) { ex_start = le32_to_cpu(extent->ee_block); ex_end = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { ex_start = 0; ex_end = 0; } if ((start == ex_start && shift > ex_start) || (shift > start - ex_end)) { ret = -EINVAL; goto out; } } else { if (shift > EXT_MAX_BLOCKS - (stop + ext4_ext_get_actual_len(extent))) { ret = -EINVAL; goto out; } } /* * In case of left shift, iterator points to start and it is increased * till we reach stop. In case of right shift, iterator points to stop * and it is decreased till we reach start. */ again: ret = 0; if (SHIFT == SHIFT_LEFT) iterator = &start; else iterator = &stop; if (tmp != EXT_MAX_BLOCKS) *iterator = tmp; /* * Its safe to start updating extents. Start and stop are unsigned, so * in case of right shift if extent with 0 block is reached, iterator * becomes NULL to indicate the end of the loop. */ while (iterator && start <= stop) { path = ext4_find_extent(inode, *iterator, &path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (!extent) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) *iterator); return -EFSCORRUPTED; } if (SHIFT == SHIFT_LEFT && *iterator > le32_to_cpu(extent->ee_block)) { /* Hole, move to the next extent */ if (extent < EXT_LAST_EXTENT(path[depth].p_hdr)) { path[depth].p_ext++; } else { *iterator = ext4_ext_next_allocated_block(path); continue; } } tmp = *iterator; if (SHIFT == SHIFT_LEFT) { extent = EXT_LAST_EXTENT(path[depth].p_hdr); *iterator = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { extent = EXT_FIRST_EXTENT(path[depth].p_hdr); if (le32_to_cpu(extent->ee_block) > start) *iterator = le32_to_cpu(extent->ee_block) - 1; else if (le32_to_cpu(extent->ee_block) == start) iterator = NULL; else { extent = EXT_LAST_EXTENT(path[depth].p_hdr); while (le32_to_cpu(extent->ee_block) >= start) extent--; if (extent == EXT_LAST_EXTENT(path[depth].p_hdr)) break; extent++; iterator = NULL; } path[depth].p_ext = extent; } ret = ext4_ext_shift_path_extents(path, shift, inode, handle, SHIFT); /* iterator can be NULL which means we should break */ if (ret == -EAGAIN) goto again; if (ret) break; } out: ext4_ext_drop_refs(path); kfree(path); return ret; } /* * ext4_collapse_range: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; ext4_lblk_t punch_start, punch_stop; handle_t *handle; unsigned int credits; loff_t new_size, ioffset; int ret; /* * We need to test this early because xfstests assumes that a * collapse range of (0, 1) will return EOPNOTSUPP if the file * system does not support collapse range. */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; /* Collapse range works only on fs cluster size aligned regions. */ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; trace_ext4_collapse_range(inode, offset, len); punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb); punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb); /* Call ext4_force_commit to flush all data in case of data=journal. */ if (ext4_should_journal_data(inode)) { ret = ext4_force_commit(inode->i_sb); if (ret) return ret; } inode_lock(inode); /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation */ if (offset + len >= inode->i_size) { ret = -EINVAL; goto out_mutex; } /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ret = -EOPNOTSUPP; goto out_mutex; } /* Wait for existing dio to complete */ inode_dio_wait(inode); ret = file_modified(file); if (ret) goto out_mutex; /* * Prevent page faults from reinstantiating pages we have released from * page cache. */ filemap_invalidate_lock(mapping); ret = ext4_break_layouts(inode); if (ret) goto out_mmap; /* * Need to round down offset to be aligned with page size boundary * for page size > block size. */ ioffset = round_down(offset, PAGE_SIZE); /* * Write tail of the last page before removed range since it will get * removed from the page cache below. */ ret = filemap_write_and_wait_range(mapping, ioffset, offset); if (ret) goto out_mmap; /* * Write data that will be shifted to preserve them when discarding * page cache below. We are also protected from pages becoming dirty * by i_rwsem and invalidate_lock. */ ret = filemap_write_and_wait_range(mapping, offset + len, LLONG_MAX); if (ret) goto out_mmap; truncate_pagecache(inode, ioffset); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_mmap; } ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode, 0); ret = ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } ext4_discard_preallocations(inode, 0); ret = ext4_ext_shift_extents(inode, handle, punch_stop, punch_stop - punch_start, SHIFT_LEFT); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } new_size = inode->i_size - len; i_size_write(inode, new_size); EXT4_I(inode)->i_disksize = new_size; up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); inode->i_mtime = inode->i_ctime = current_time(inode); ret = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); out_mmap: filemap_invalidate_unlock(mapping); out_mutex: inode_unlock(inode); return ret; } /* * ext4_insert_range: * This function implements the FALLOC_FL_INSERT_RANGE flag of fallocate. * The data blocks starting from @offset to the EOF are shifted by @len * towards right to create a hole in the @inode. Inode size is increased * by len bytes. * Returns 0 on success, error otherwise. */ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; struct ext4_ext_path *path; struct ext4_extent *extent; ext4_lblk_t offset_lblk, len_lblk, ee_start_lblk = 0; unsigned int credits, ee_len; int ret = 0, depth, split_flag = 0; loff_t ioffset; /* * We need to test this early because xfstests assumes that an * insert range of (0, 1) will return EOPNOTSUPP if the file * system does not support insert range. */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; /* Insert range works only on fs cluster size aligned regions. */ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; trace_ext4_insert_range(inode, offset, len); offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb); len_lblk = len >> EXT4_BLOCK_SIZE_BITS(sb); /* Call ext4_force_commit to flush all data in case of data=journal */ if (ext4_should_journal_data(inode)) { ret = ext4_force_commit(inode->i_sb); if (ret) return ret; } inode_lock(inode); /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ret = -EOPNOTSUPP; goto out_mutex; } /* Check whether the maximum file size would be exceeded */ if (len > inode->i_sb->s_maxbytes - inode->i_size) { ret = -EFBIG; goto out_mutex; } /* Offset must be less than i_size */ if (offset >= inode->i_size) { ret = -EINVAL; goto out_mutex; } /* Wait for existing dio to complete */ inode_dio_wait(inode); ret = file_modified(file); if (ret) goto out_mutex; /* * Prevent page faults from reinstantiating pages we have released from * page cache. */ filemap_invalidate_lock(mapping); ret = ext4_break_layouts(inode); if (ret) goto out_mmap; /* * Need to round down to align start offset to page size boundary * for page size > block size. */ ioffset = round_down(offset, PAGE_SIZE); /* Write out all dirty pages */ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, LLONG_MAX); if (ret) goto out_mmap; truncate_pagecache(inode, ioffset); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_mmap; } ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; EXT4_I(inode)->i_disksize += len; inode->i_mtime = inode->i_ctime = current_time(inode); ret = ext4_mark_inode_dirty(handle, inode); if (ret) goto out_stop; down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode, 0); path = ext4_find_extent(inode, offset_lblk, NULL, 0); if (IS_ERR(path)) { up_write(&EXT4_I(inode)->i_data_sem); ret = PTR_ERR(path); goto out_stop; } depth = ext_depth(inode); extent = path[depth].p_ext; if (extent) { ee_start_lblk = le32_to_cpu(extent->ee_block); ee_len = ext4_ext_get_actual_len(extent); /* * If offset_lblk is not the starting block of extent, split * the extent @offset_lblk */ if ((offset_lblk > ee_start_lblk) && (offset_lblk < (ee_start_lblk + ee_len))) { if (ext4_ext_is_unwritten(extent)) split_flag = EXT4_EXT_MARK_UNWRIT1 | EXT4_EXT_MARK_UNWRIT2; ret = ext4_split_extent_at(handle, inode, &path, offset_lblk, split_flag, EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_METADATA_NOFAIL); } ext4_ext_drop_refs(path); kfree(path); if (ret < 0) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } } else { ext4_ext_drop_refs(path); kfree(path); } ret = ext4_es_remove_extent(inode, offset_lblk, EXT_MAX_BLOCKS - offset_lblk); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } /* * if offset_lblk lies in a hole which is at start of file, use * ee_start_lblk to shift extents */ ret = ext4_ext_shift_extents(inode, handle, ee_start_lblk > offset_lblk ? ee_start_lblk : offset_lblk, len_lblk, SHIFT_RIGHT); up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); out_mmap: filemap_invalidate_unlock(mapping); out_mutex: inode_unlock(inode); return ret; } /** * ext4_swap_extents() - Swap extents between two inodes * @handle: handle for this transaction * @inode1: First inode * @inode2: Second inode * @lblk1: Start block for first inode * @lblk2: Start block for second inode * @count: Number of blocks to swap * @unwritten: Mark second inode's extents as unwritten after swap * @erp: Pointer to save error value * * This helper routine does exactly what is promise "swap extents". All other * stuff such as page-cache locking consistency, bh mapping consistency or * extent's data copying must be performed by caller. * Locking: * i_mutex is held for both inodes * i_data_sem is locked for write for both inodes * Assumptions: * All pages from requested range are locked for both inodes */ int ext4_swap_extents(handle_t *handle, struct inode *inode1, struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2, ext4_lblk_t count, int unwritten, int *erp) { struct ext4_ext_path *path1 = NULL; struct ext4_ext_path *path2 = NULL; int replaced_count = 0; BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem)); BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem)); BUG_ON(!inode_is_locked(inode1)); BUG_ON(!inode_is_locked(inode2)); *erp = ext4_es_remove_extent(inode1, lblk1, count); if (unlikely(*erp)) return 0; *erp = ext4_es_remove_extent(inode2, lblk2, count); if (unlikely(*erp)) return 0; while (count) { struct ext4_extent *ex1, *ex2, tmp_ex; ext4_lblk_t e1_blk, e2_blk; int e1_len, e2_len, len; int split = 0; path1 = ext4_find_extent(inode1, lblk1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); path1 = NULL; finish: count = 0; goto repeat; } path2 = ext4_find_extent(inode2, lblk2, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); path2 = NULL; goto finish; } ex1 = path1[path1->p_depth].p_ext; ex2 = path2[path2->p_depth].p_ext; /* Do we have something to swap ? */ if (unlikely(!ex2 || !ex1)) goto finish; e1_blk = le32_to_cpu(ex1->ee_block); e2_blk = le32_to_cpu(ex2->ee_block); e1_len = ext4_ext_get_actual_len(ex1); e2_len = ext4_ext_get_actual_len(ex2); /* Hole handling */ if (!in_range(lblk1, e1_blk, e1_len) || !in_range(lblk2, e2_blk, e2_len)) { ext4_lblk_t next1, next2; /* if hole after extent, then go to next extent */ next1 = ext4_ext_next_allocated_block(path1); next2 = ext4_ext_next_allocated_block(path2); /* If hole before extent, then shift to that extent */ if (e1_blk > lblk1) next1 = e1_blk; if (e2_blk > lblk2) next2 = e2_blk; /* Do we have something to swap */ if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS) goto finish; /* Move to the rightest boundary */ len = next1 - lblk1; if (len < next2 - lblk2) len = next2 - lblk2; if (len > count) len = count; lblk1 += len; lblk2 += len; count -= len; goto repeat; } /* Prepare left boundary */ if (e1_blk < lblk1) { split = 1; *erp = ext4_force_split_extent_at(handle, inode1, &path1, lblk1, 0); if (unlikely(*erp)) goto finish; } if (e2_blk < lblk2) { split = 1; *erp = ext4_force_split_extent_at(handle, inode2, &path2, lblk2, 0); if (unlikely(*erp)) goto finish; } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) goto repeat; /* Prepare right boundary */ len = count; if (len > e1_blk + e1_len - lblk1) len = e1_blk + e1_len - lblk1; if (len > e2_blk + e2_len - lblk2) len = e2_blk + e2_len - lblk2; if (len != e1_len) { split = 1; *erp = ext4_force_split_extent_at(handle, inode1, &path1, lblk1 + len, 0); if (unlikely(*erp)) goto finish; } if (len != e2_len) { split = 1; *erp = ext4_force_split_extent_at(handle, inode2, &path2, lblk2 + len, 0); if (*erp) goto finish; } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) goto repeat; BUG_ON(e2_len != e1_len); *erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth); if (unlikely(*erp)) goto finish; *erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) goto finish; /* Both extents are fully inside boundaries. Swap it now */ tmp_ex = *ex1; ext4_ext_store_pblock(ex1, ext4_ext_pblock(ex2)); ext4_ext_store_pblock(ex2, ext4_ext_pblock(&tmp_ex)); ex1->ee_len = cpu_to_le16(e2_len); ex2->ee_len = cpu_to_le16(e1_len); if (unwritten) ext4_ext_mark_unwritten(ex2); if (ext4_ext_is_unwritten(&tmp_ex)) ext4_ext_mark_unwritten(ex1); ext4_ext_try_to_merge(handle, inode2, path2, ex2); ext4_ext_try_to_merge(handle, inode1, path1, ex1); *erp = ext4_ext_dirty(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) goto finish; *erp = ext4_ext_dirty(handle, inode1, path1 + path1->p_depth); /* * Looks scarry ah..? second inode already points to new blocks, * and it was successfully dirtied. But luckily error may happen * only due to journal error, so full transaction will be * aborted anyway. */ if (unlikely(*erp)) goto finish; lblk1 += len; lblk2 += len; replaced_count += len; count -= len; repeat: ext4_ext_drop_refs(path1); kfree(path1); ext4_ext_drop_refs(path2); kfree(path2); path1 = path2 = NULL; } return replaced_count; } /* * ext4_clu_mapped - determine whether any block in a logical cluster has * been mapped to a physical cluster * * @inode - file containing the logical cluster * @lclu - logical cluster of interest * * Returns 1 if any block in the logical cluster is mapped, signifying * that a physical cluster has been allocated for it. Otherwise, * returns 0. Can also return negative error codes. Derived from * ext4_ext_map_blocks(). */ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_ext_path *path; int depth, mapped = 0, err = 0; struct ext4_extent *extent; ext4_lblk_t first_lblk, first_lclu, last_lclu; /* * if data can be stored inline, the logical cluster isn't * mapped - no physical clusters have been allocated, and the * file has no extents */ if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) || ext4_has_inline_data(inode)) return 0; /* search for the extent closest to the first block in the cluster */ path = ext4_find_extent(inode, EXT4_C2B(sbi, lclu), NULL, 0); if (IS_ERR(path)) { err = PTR_ERR(path); path = NULL; goto out; } depth = ext_depth(inode); /* * A consistent leaf must not be empty. This situation is possible, * though, _during_ tree modification, and it's why an assert can't * be put in ext4_find_extent(). */ if (unlikely(path[depth].p_ext == NULL && depth != 0)) { EXT4_ERROR_INODE(inode, "bad extent address - lblock: %lu, depth: %d, pblock: %lld", (unsigned long) EXT4_C2B(sbi, lclu), depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } extent = path[depth].p_ext; /* can't be mapped if the extent tree is empty */ if (extent == NULL) goto out; first_lblk = le32_to_cpu(extent->ee_block); first_lclu = EXT4_B2C(sbi, first_lblk); /* * Three possible outcomes at this point - found extent spanning * the target cluster, to the left of the target cluster, or to the * right of the target cluster. The first two cases are handled here. * The last case indicates the target cluster is not mapped. */ if (lclu >= first_lclu) { last_lclu = EXT4_B2C(sbi, first_lblk + ext4_ext_get_actual_len(extent) - 1); if (lclu <= last_lclu) { mapped = 1; } else { first_lblk = ext4_ext_next_allocated_block(path); first_lclu = EXT4_B2C(sbi, first_lblk); if (lclu == first_lclu) mapped = 1; } } out: ext4_ext_drop_refs(path); kfree(path); return err ? err : mapped; } /* * Updates physical block address and unwritten status of extent * starting at lblk start and of len. If such an extent doesn't exist, * this function splits the extent tree appropriately to create an * extent like this. This function is called in the fast commit * replay path. Returns 0 on success and error on failure. */ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, int len, int unwritten, ext4_fsblk_t pblk) { struct ext4_ext_path *path; struct ext4_extent *ex; int ret; path = ext4_find_extent(inode, start, NULL, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ret = -EFSCORRUPTED; goto out; } if (le32_to_cpu(ex->ee_block) != start || ext4_ext_get_actual_len(ex) != len) { /* We need to split this extent to match our extent first */ down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_force_split_extent_at(NULL, inode, &path, start, 1); up_write(&EXT4_I(inode)->i_data_sem); if (ret) goto out; path = ext4_find_extent(inode, start, &path, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; WARN_ON(le32_to_cpu(ex->ee_block) != start); if (ext4_ext_get_actual_len(ex) != len) { down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_force_split_extent_at(NULL, inode, &path, start + len, 1); up_write(&EXT4_I(inode)->i_data_sem); if (ret) goto out; path = ext4_find_extent(inode, start, &path, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; } } if (unwritten) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); ext4_ext_store_pblock(ex, pblk); down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); out: ext4_ext_drop_refs(path); kfree(path); ext4_mark_inode_dirty(NULL, inode); return ret; } /* Try to shrink the extent tree */ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t old_cur, cur = 0; while (cur < end) { path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) return; ex = path[path->p_depth].p_ext; if (!ex) { ext4_ext_drop_refs(path); kfree(path); ext4_mark_inode_dirty(NULL, inode); return; } old_cur = cur; cur = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); if (cur <= old_cur) cur = old_cur + 1; ext4_ext_try_to_merge(NULL, inode, path, ex); down_write(&EXT4_I(inode)->i_data_sem); ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); ext4_mark_inode_dirty(NULL, inode); ext4_ext_drop_refs(path); kfree(path); } } /* Check if *cur is a hole and if it is, skip it */ static int skip_hole(struct inode *inode, ext4_lblk_t *cur) { int ret; struct ext4_map_blocks map; map.m_lblk = *cur; map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return ret; if (ret != 0) return 0; *cur = *cur + map.m_len; return 0; } /* Count number of blocks used by this inode and update i_blocks */ int ext4_ext_replay_set_iblocks(struct inode *inode) { struct ext4_ext_path *path = NULL, *path2 = NULL; struct ext4_extent *ex; ext4_lblk_t cur = 0, end; int numblks = 0, i, ret = 0; ext4_fsblk_t cmp1, cmp2; struct ext4_map_blocks map; /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ext4_ext_drop_refs(path); kfree(path); goto out; } end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); ext4_ext_drop_refs(path); kfree(path); /* Count the number of data blocks */ cur = 0; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) numblks += ret; cur = cur + map.m_len; } /* * Count the number of extent tree blocks. We do it by looking up * two successive extents and determining the difference between * their paths. When path is different for 2 successive extents * we compare the blocks in the path at each level and increment * iblocks by total number of differences found. */ cur = 0; ret = skip_hole(inode, &cur); if (ret < 0) goto out; path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) goto out; numblks += path->p_depth; ext4_ext_drop_refs(path); kfree(path); while (cur < end) { path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) break; ex = path[path->p_depth].p_ext; if (!ex) { ext4_ext_drop_refs(path); kfree(path); return 0; } cur = max(cur + 1, le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)); ret = skip_hole(inode, &cur); if (ret < 0) { ext4_ext_drop_refs(path); kfree(path); break; } path2 = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path2)) { ext4_ext_drop_refs(path); kfree(path); break; } for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) { cmp1 = cmp2 = 0; if (i <= path->p_depth) cmp1 = path[i].p_bh ? path[i].p_bh->b_blocknr : 0; if (i <= path2->p_depth) cmp2 = path2[i].p_bh ? path2[i].p_bh->b_blocknr : 0; if (cmp1 != cmp2 && cmp2 != 0) numblks++; } ext4_ext_drop_refs(path); ext4_ext_drop_refs(path2); kfree(path); kfree(path2); } out: inode->i_blocks = numblks << (inode->i_sb->s_blocksize_bits - 9); ext4_mark_inode_dirty(NULL, inode); return 0; } int ext4_ext_clear_bb(struct inode *inode) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t cur = 0, end; int j, ret = 0; struct ext4_map_blocks map; /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ext4_ext_drop_refs(path); kfree(path); return 0; } end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); ext4_ext_drop_refs(path); kfree(path); cur = 0; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, NULL, 0); if (!IS_ERR_OR_NULL(path)) { for (j = 0; j < path->p_depth; j++) { ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 0); ext4_fc_record_regions(inode->i_sb, inode->i_ino, 0, path[j].p_block, 1, 1); } ext4_ext_drop_refs(path); kfree(path); } ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); ext4_fc_record_regions(inode->i_sb, inode->i_ino, map.m_lblk, map.m_pblk, map.m_len, 1); } cur = cur + map.m_len; } return 0; } |
| 1515 1514 189 189 189 188 4 187 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/capability.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/cpu.h> #include <linux/acct.h> #include <linux/tsacct_kern.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/freezer.h> #include <linux/binfmts.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/profile.h> #include <linux/mount.h> #include <linux/proc_fs.h> #include <linux/kthread.h> #include <linux/mempolicy.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> #include <linux/cgroup.h> #include <linux/syscalls.h> #include <linux/signal.h> #include <linux/posix-timers.h> #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> #include <linux/tracehook.h> #include <linux/fs_struct.h> #include <linux/init_task.h> #include <linux/perf_event.h> #include <trace/events/sched.h> #include <linux/hw_breakpoint.h> #include <linux/oom.h> #include <linux/writeback.h> #include <linux/shm.h> #include <linux/kcov.h> #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <linux/sysfs.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/mmu_context.h> /* * The default value should be high enough to not crash a system that randomly * crashes its kernel from time to time, but low enough to at least not permit * overflowing 32-bit refcounts or the ldsem writer count. */ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL static struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, .maxlen = sizeof(oops_limit), .mode = 0644, .proc_handler = proc_douintvec, }, { } }; static __init int kernel_exit_sysctls_init(void) { register_sysctl_init("kernel", kern_exit_table); return 0; } late_initcall(kernel_exit_sysctls_init); #endif static atomic_t oops_count = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); } static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); static __init int kernel_exit_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); return 0; } late_initcall(kernel_exit_sysfs_init); #endif static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; detach_pid(p, PIDTYPE_PID); if (group_dead) { detach_pid(p, PIDTYPE_TGID); detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); list_del_rcu(&p->thread_node); } /* * This function expects the tasklist_lock write-locked. */ static void __exit_signal(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *tty; u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); #ifdef CONFIG_POSIX_TIMERS posix_cpu_timers_exit(tsk); if (group_dead) posix_cpu_timers_exit_group(tsk); #endif if (group_dead) { tty = sig->tty; sig->tty = NULL; } else { /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exit_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); } add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); /* * Accumulate here the counters for all threads as they die. We could * skip the group leader because it is the last user of signal_struct, * but we want to avoid the race with thread_group_cputime() which can * see the empty ->thread_head list. */ task_cputime(tsk, &utime, &stime); write_seqlock(&sig->stats_lock); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); /* * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); if (group_dead) { flush_sigqueue(&sig->shared_pending); tty_kref_put(tty); } } static void delayed_put_task_struct(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk); } void put_task_struct_rcu_user(struct task_struct *task) { if (refcount_dec_and_test(&task->rcu_users)) call_rcu(&task->rcu, delayed_put_task_struct); } void release_task(struct task_struct *p) { struct task_struct *leader; struct pid *thread_pid; int zap_leader; repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); rcu_read_unlock(); cgroup_release(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); thread_pid = get_pid(p->thread_pid); __exit_signal(p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); seccomp_filter_release(p); proc_flush_pid(thread_pid); put_pid(thread_pid); release_thread(p); put_task_struct_rcu_user(p); p = leader; if (unlikely(zap_leader)) goto repeat; } int rcuwait_wake_up(struct rcuwait *w) { int ret = 0; struct task_struct *task; rcu_read_lock(); /* * Order condition vs @task, such that everything prior to the load * of @task is visible. This is the condition as to why the user called * rcuwait_wake() in the first place. Pairs with set_current_state() * barrier (A) in rcuwait_wait_event(). * * WAIT WAKE * [S] tsk = current [S] cond = true * MB (A) MB (B) * [L] cond [L] tsk */ smp_mb(); /* (B) */ task = rcu_dereference(w->task); if (task) ret = wake_up_process(task); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rcuwait_wake_up); /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */ static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1; } int is_current_pgrp_orphaned(void) { int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval; } static bool has_stopped_jobs(struct pid *pgrp) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false; } /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) { struct pid *pgrp = task_pgrp(tsk); struct task_struct *ignored_task = tsk; if (!parent) /* exit: our father is in a different pgrp than * we are and we were the only connection outside. */ parent = tsk->real_parent; else /* reparent: our child is in a different pgrp than * we are, and it was the only connection outside. */ ignored_task = NULL; if (task_pgrp(parent) != pgrp && task_session(parent) == task_session(tsk) && will_become_orphaned_pgrp(pgrp, ignored_task) && has_stopped_jobs(pgrp)) { __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } #ifdef CONFIG_MEMCG /* * A task is exiting. If it owned this mm, find a new owner for the mm. */ void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *c, *g, *p = current; retry: /* * If the exiting or execing task is not the owner, it's * someone else's problem. */ if (mm->owner != p) return; /* * The current owner is exiting/execing and there are no other * candidates. Do not leave the mm pointing to a possibly * freed task structure. */ if (atomic_read(&mm->mm_users) <= 1) { WRITE_ONCE(mm->owner, NULL); return; } read_lock(&tasklist_lock); /* * Search in the children */ list_for_each_entry(c, &p->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search in the siblings */ list_for_each_entry(c, &p->real_parent->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search through everything else, we should not get here often. */ for_each_process(g) { if (atomic_read(&mm->mm_users) <= 1) break; if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { if (c->mm == mm) goto assign_new_owner; if (c->mm) break; } } read_unlock(&tasklist_lock); /* * We found no owner yet mm_users > 1: this implies that we are * most likely racing with swapoff (try_to_unuse()) or /proc or * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ WRITE_ONCE(mm->owner, NULL); return; assign_new_owner: BUG_ON(c == p); get_task_struct(c); /* * The task_lock protects c->mm from changing. * We always want mm->owner->mm == mm */ task_lock(c); /* * Delay read_unlock() till we have the task_lock() * to ensure that c does not slip away underneath us */ read_unlock(&tasklist_lock); if (c->mm != mm) { task_unlock(c); put_task_struct(c); goto retry; } WRITE_ONCE(mm->owner, c); task_unlock(c); put_task_struct(c); } #endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */ static void exit_mm(void) { struct mm_struct *mm = current->mm; struct core_state *core_state; exit_mm_release(current, mm); if (!mm) return; sync_mm_rss(mm); /* * Serialize with any possible pending coredump. * We must hold mmap_lock around checking core_state * and clearing tsk->mm. The core-inducing thread * will increment ->nr_threads for each thread in the * group with ->mm != NULL. */ mmap_read_lock(mm); core_state = mm->core_state; if (core_state) { struct core_thread self; mmap_read_unlock(mm); self.task = current; if (self.task->flags & PF_SIGNALED) self.next = xchg(&core_state->dumper.next, &self); else self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!self.task) /* see coredump_finish() */ break; freezable_schedule(); } __set_current_state(TASK_RUNNING); mmap_read_lock(mm); } mmgrab(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); /* * When a thread stops operating on an address space, the loop * in membarrier_private_expedited() may not observe that * tsk->mm, and the loop in membarrier_global_expedited() may * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED * rq->membarrier_state, so those would not issue an IPI. * Membarrier requires a memory barrier after accessing * user-space memory, before clearing tsk->mm or the * rq->membarrier_state. */ smp_mb__after_spinlock(); local_irq_disable(); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); local_irq_enable(); task_unlock(current); mmap_read_unlock(mm); mm_update_next_owner(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) exit_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) { struct task_struct *t; for_each_thread(p, t) { if (!(t->flags & PF_EXITING)) return t; } return NULL; } static struct task_struct *find_child_reaper(struct task_struct *father, struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; struct task_struct *p, *n; if (likely(reaper != father)) return reaper; reaper = find_alive_thread(father); if (reaper) { pid_ns->child_reaper = reaper; return reaper; } write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); return father; } /* * When we die, we re-parent all our children, and try to: * 1. give them to another thread in our thread group, if such a member exists * 2. give it to the first ancestor process which prctl'd itself as a * child_subreaper for its children (like a service manager) * 3. give it to the init process (PID 1) in our pid namespace */ static struct task_struct *find_new_reaper(struct task_struct *father, struct task_struct *child_reaper) { struct task_struct *thread, *reaper; thread = find_alive_thread(father); if (thread) return thread; if (father->signal->has_child_subreaper) { unsigned int ns_level = task_pid(father)->level; /* * Find the first ->is_child_subreaper ancestor in our pid_ns. * We can't check reaper != child_reaper to ensure we do not * cross the namespaces, the exiting parent could be injected * by setns() + fork(). * We check pid->level, this is slightly more efficient than * task_active_pid_ns(reaper) != task_active_pid_ns(father). */ for (reaper = father->real_parent; task_pid(reaper)->level == ns_level; reaper = reaper->real_parent) { if (reaper == &init_task) break; if (!reaper->signal->is_child_subreaper) continue; thread = find_alive_thread(reaper); if (thread) return thread; } } return child_reaper; } /* * Any that need to be release_task'd are put on the @dead list. */ static void reparent_leader(struct task_struct *father, struct task_struct *p, struct list_head *dead) { if (unlikely(p->exit_state == EXIT_DEAD)) return; /* We don't want people slaying init. */ p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ if (!p->ptrace && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { if (do_notify_parent(p, p->exit_signal)) { p->exit_state = EXIT_DEAD; list_add(&p->ptrace_entry, dead); } } kill_orphaned_pgrp(p, father); } /* * This does two things: * * A. Make init inherit all the child processes * B. Check to see if any process groups have become orphaned * as a result of our exiting, and if they have any stopped * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void forget_original_parent(struct task_struct *father, struct list_head *dead) { struct task_struct *p, *t, *reaper; if (unlikely(!list_empty(&father->ptraced))) exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; reaper = find_new_reaper(father, reaper); list_for_each_entry(p, &father->children, sibling) { for_each_thread(p, t) { RCU_INIT_POINTER(t->real_parent, reaper); BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father)); if (likely(!t->ptrace)) t->parent = t->real_parent; if (t->pdeath_signal) group_send_sig_info(t->pdeath_signal, SEND_SIG_NOINFO, t, PIDTYPE_TGID); } /* * If this is a threaded reparent there is no need to * notify anyone anything has happened. */ if (!same_thread_group(reaper, father)) reparent_leader(father, p, dead); } list_splice_tail_init(&father->children, &reaper->children); } /* * Send signals to all our closest relatives so that they know * to properly mourn us.. */ static void exit_notify(struct task_struct *tsk, int group_dead) { bool autoreap; struct task_struct *p, *n; LIST_HEAD(dead); write_lock_irq(&tasklist_lock); forget_original_parent(tsk, &dead); if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); tsk->exit_state = EXIT_ZOMBIE; if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && !ptrace_reparented(tsk) ? tsk->exit_signal : SIGCHLD; autoreap = do_notify_parent(tsk, sig); } else if (thread_group_leader(tsk)) { autoreap = thread_group_empty(tsk) && do_notify_parent(tsk, tsk->exit_signal); } else { autoreap = true; } if (autoreap) { tsk->exit_state = EXIT_DEAD; list_add(&tsk->ptrace_entry, &dead); } /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) wake_up_process(tsk->signal->group_exit_task); write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } } #ifdef CONFIG_DEBUG_STACK_USAGE static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); static int lowest_to_date = THREAD_SIZE; unsigned long free; free = stack_not_used(current); if (free >= lowest_to_date) return; spin_lock(&low_water_lock); if (free < lowest_to_date) { pr_info("%s (%d) used greatest stack depth: %lu bytes left\n", current->comm, task_pid_nr(current), free); lowest_to_date = free; } spin_unlock(&low_water_lock); } #else static inline void check_stack_usage(void) {} #endif void __noreturn do_exit(long code) { struct task_struct *tsk = current; int group_dead; /* * We can get here from a kernel oops, sometimes with preemption off. * Start by checking for critical errors. * Then fix up important state like USER_DS and preemption. * Then do everything else. */ WARN_ON(blk_needs_flush_plug(tsk)); if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); /* * If do_exit is called because this processes oopsed, it's possible * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before * continuing. Amongst other possible reasons, this is to prevent * mm_release()->clear_child_tid() from writing to a user-controlled * kernel address. */ force_uaccess_begin(); if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), preempt_count()); preempt_count_set(PREEMPT_ENABLED); } profile_task_exit(tsk); kcov_task_exit(tsk); ptrace_event(PTRACE_EVENT_EXIT, code); validate_creds_for_do_exit(tsk); /* * We're taking recursive faults here in do_exit. Safest is to just * leave this task alone and wait for reboot. */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); futex_exit_recursive(tsk); set_current_state(TASK_UNINTERRUPTIBLE); schedule(); } io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ /* sync mm's RSS info before statistics gathering */ if (tsk->mm) sync_mm_rss(tsk->mm); acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { /* * If the last thread of global init has exited, panic * immediately to get a useable coredump. */ if (unlikely(is_global_init(tsk))) panic("Attempted to kill init! exitcode=0x%08x\n", tsk->signal->group_exit_code ?: (int)code); #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); } acct_collect(code, group_dead); if (group_dead) tty_audit_exit(); audit_free(tsk); tsk->exit_code = code; taskstats_exit(tsk, group_dead); exit_mm(); if (group_dead) acct_process(); trace_sched_process_exit(tsk); exit_sem(tsk); exit_shm(tsk); exit_files(tsk); exit_fs(tsk); if (group_dead) disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); exit_thread(tsk); /* * Flush inherited counters to the parent - before the parent * gets woken up by child-exit notifications. * * because of cgroup mode, must be called before cgroup_exit() */ perf_event_exit_task(tsk); sched_autogroup_exit_task(tsk); cgroup_exit(tsk); /* * FIXME: do that only when needed, using sched_exit tracepoint */ flush_ptrace_hw_breakpoint(tsk); exit_tasks_rcu_start(); exit_notify(tsk, group_dead); proc_exit_connector(tsk); mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); #endif /* * Make sure we are holding no locks: */ debug_check_no_locks_held(); if (tsk->io_context) exit_io_context(tsk); if (tsk->splice_pipe) free_pipe_info(tsk->splice_pipe); if (tsk->task_frag.page) put_page(tsk->task_frag.page); validate_creds_for_do_exit(tsk); check_stack_usage(); preempt_disable(); if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); exit_tasks_rcu_finish(); lockdep_free_task(tsk); do_task_dead(); } EXPORT_SYMBOL_GPL(do_exit); void __noreturn make_task_dead(int signr) { /* * Take the task off the cpu after something catastrophic has * happened. */ unsigned int limit; /* * Every time the system oopses, if the oops happens while a reference * to an object was held, the reference leaks. * If the oops doesn't also leak memory, repeated oopsing can cause * reference counters to wrap around (if they're not using refcount_t). * This means that repeated oopsing can make unexploitable-looking bugs * exploitable through repeated oopsing. * To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ limit = READ_ONCE(oops_limit); if (atomic_inc_return(&oops_count) >= limit && limit) panic("Oopsed too often (kernel.oops_limit is %d)", limit); do_exit(signr); } void complete_and_exit(struct completion *comp, long code) { if (comp) complete(comp); do_exit(code); } EXPORT_SYMBOL(complete_and_exit); SYSCALL_DEFINE1(exit, int, error_code) { do_exit((error_code&0xff)<<8); } /* * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ void do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; BUG_ON(exit_code & 0x80); /* core dumps don't get here */ if (signal_group_exit(sig)) exit_code = sig->group_exit_code; else if (!thread_group_empty(current)) { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); if (signal_group_exit(sig)) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else { sig->group_exit_code = exit_code; sig->flags = SIGNAL_GROUP_EXIT; zap_other_threads(current); } spin_unlock_irq(&sighand->siglock); } do_exit(exit_code); /* NOTREACHED */ } /* * this kills every thread in the thread group. Note that any externally * wait4()-ing process will get the correct exit code - even if this * thread is not the thread group leader. */ SYSCALL_DEFINE1(exit_group, int, error_code) { do_group_exit((error_code & 0xff) << 8); /* NOTREACHED */ return 0; } struct waitid_info { pid_t pid; uid_t uid; int status; int cause; }; struct wait_opts { enum pid_type wo_type; int wo_flags; struct pid *wo_pid; struct waitid_info *wo_info; int wo_stat; struct rusage *wo_rusage; wait_queue_entry_t child_wait; int notask_error; }; static int eligible_pid(struct wait_opts *wo, struct task_struct *p) { return wo->wo_type == PIDTYPE_MAX || task_pid_type(p, wo->wo_type) == wo->wo_pid; } static int eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) { if (!eligible_pid(wo, p)) return 0; /* * Wait for all children (clone and not) if __WALL is set or * if it is traced by us. */ if (ptrace || (wo->wo_flags & __WALL)) return 1; /* * Otherwise, wait for clone children *only* if __WCLONE is set; * otherwise, wait for non-clone children *only*. * * Note: a "clone" child here is one that reports to its parent * using a signal other than SIGCHLD, or a non-leader thread which * we can only see if it is traced by us. */ if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) return 0; return 1; } /* * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { int state, status; pid_t pid = task_pid_vnr(p); uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); struct waitid_info *infop; if (!likely(wo->wo_flags & WEXITED)) return 0; if (unlikely(wo->wo_flags & WNOWAIT)) { status = p->exit_code; get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); goto out_info; } /* * Move the task's state to DEAD/TRACE, only one thread can do this. */ state = (ptrace_reparented(p) && thread_group_leader(p)) ? EXIT_TRACE : EXIT_DEAD; if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) return 0; /* * We own this thread, nobody else can reap it. */ read_unlock(&tasklist_lock); sched_annotate_sleep(); /* * Check thread_group_leader() to exclude the traced sub-threads. */ if (state == EXIT_DEAD && thread_group_leader(p)) { struct signal_struct *sig = p->signal; struct signal_struct *psig = current->signal; unsigned long maxrss; u64 tgutime, tgstime; /* * The resource counters for the group leader are in its * own task_struct. Those for dead threads in the group * are in its signal_struct, as are those for the child * processes it has previously reaped. All these * accumulate in the parent's signal_struct c* fields. * * We don't bother to take a lock here to protect these * p->signal fields because the whole thread group is dead * and nobody can change them. * * psig->stats_lock also protects us from our sub-theads * which can reap other children at the same time. Until * we change k_getrusage()-like users to rely on this lock * we have to take ->siglock as well. * * We use thread_group_cputime_adjusted() to get times for * the thread group, which consolidates times for all threads * in the group including the group leader. */ thread_group_cputime_adjusted(p, &tgutime, &tgstime); spin_lock_irq(¤t->sighand->siglock); write_seqlock(&psig->stats_lock); psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += p->maj_flt + sig->maj_flt + sig->cmaj_flt; psig->cnvcsw += p->nvcsw + sig->nvcsw + sig->cnvcsw; psig->cnivcsw += p->nivcsw + sig->nivcsw + sig->cnivcsw; psig->cinblock += task_io_get_inblock(p) + sig->inblock + sig->cinblock; psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; maxrss = max(sig->maxrss, sig->cmaxrss); if (psig->cmaxrss < maxrss) psig->cmaxrss = maxrss; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); write_sequnlock(&psig->stats_lock); spin_unlock_irq(¤t->sighand->siglock); } if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; wo->wo_stat = status; if (state == EXIT_TRACE) { write_lock_irq(&tasklist_lock); /* We dropped tasklist, ptracer could die and untrace */ ptrace_unlink(p); /* If parent wants a zombie, don't release it now */ state = EXIT_ZOMBIE; if (do_notify_parent(p, p->exit_signal)) state = EXIT_DEAD; p->exit_state = state; write_unlock_irq(&tasklist_lock); } if (state == EXIT_DEAD) release_task(p); out_info: infop = wo->wo_info; if (infop) { if ((status & 0x7f) == 0) { infop->cause = CLD_EXITED; infop->status = status >> 8; } else { infop->cause = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; infop->status = status & 0x7f; } infop->pid = pid; infop->uid = uid; } return pid; } static int *task_stopped_code(struct task_struct *p, bool ptrace) { if (ptrace) { if (task_is_traced(p) && !(p->jobctl & JOBCTL_LISTENING)) return &p->exit_code; } else { if (p->signal->flags & SIGNAL_STOP_STOPPED) return &p->signal->group_exit_code; } return NULL; } /** * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED * @wo: wait options * @ptrace: is the wait for ptrace * @p: task to wait for * * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED. * * CONTEXT: * read_lock(&tasklist_lock), which is released if return value is * non-zero. Also, grabs and releases @p->sighand->siglock. * * RETURNS: * 0 if wait condition didn't exist and search for other wait conditions * should continue. Non-zero return, -errno on failure and @p's pid on * success, implies that tasklist_lock is released and wait condition * search should terminate. */ static int wait_task_stopped(struct wait_opts *wo, int ptrace, struct task_struct *p) { struct waitid_info *infop; int exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; /* * Traditionally we see ptrace'd stopped tasks regardless of options. */ if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; if (!task_stopped_code(p, ptrace)) return 0; exit_code = 0; spin_lock_irq(&p->sighand->siglock); p_code = task_stopped_code(p, ptrace); if (unlikely(!p_code)) goto unlock_sig; exit_code = *p_code; if (!exit_code) goto unlock_sig; if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; uid = from_kuid_munged(current_user_ns(), task_uid(p)); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) return 0; /* * Now we are pretty sure this task is interesting. * Make sure it doesn't get reaped out from under us while we * give up the lock and then examine it below. We don't want to * keep holding onto the tasklist_lock while we call getrusage and * possibly take page faults for user memory. */ get_task_struct(p); pid = task_pid_vnr(p); why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); if (likely(!(wo->wo_flags & WNOWAIT))) wo->wo_stat = (exit_code << 8) | 0x7f; infop = wo->wo_info; if (infop) { infop->cause = why; infop->status = exit_code; infop->pid = pid; infop->uid = uid; } return pid; } /* * Handle do_wait work for one task in a live, non-stopped state. * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { struct waitid_info *infop; pid_t pid; uid_t uid; if (!unlikely(wo->wo_flags & WCONTINUED)) return 0; if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) return 0; spin_lock_irq(&p->sighand->siglock); /* Re-check with the lock held. */ if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) { spin_unlock_irq(&p->sighand->siglock); return 0; } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; uid = from_kuid_munged(current_user_ns(), task_uid(p)); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); infop = wo->wo_info; if (!infop) { wo->wo_stat = 0xffff; } else { infop->cause = CLD_CONTINUED; infop->pid = pid; infop->uid = uid; infop->status = SIGCONT; } return pid; } /* * Consider @p for a wait by @parent. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; * then ->notask_error is 0 if @p is an eligible child, * or still -ECHILD. */ static int wait_consider_task(struct wait_opts *wo, int ptrace, struct task_struct *p) { /* * We can race with wait_task_zombie() from another thread. * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition * can't confuse the checks below. */ int exit_state = READ_ONCE(p->exit_state); int ret; if (unlikely(exit_state == EXIT_DEAD)) return 0; ret = eligible_child(wo, ptrace, p); if (!ret) return ret; if (unlikely(exit_state == EXIT_TRACE)) { /* * ptrace == 0 means we are the natural parent. In this case * we should clear notask_error, debugger will notify us. */ if (likely(!ptrace)) wo->notask_error = 0; return 0; } if (likely(!ptrace) && unlikely(p->ptrace)) { /* * If it is traced by its real parent's group, just pretend * the caller is ptrace_do_wait() and reap this child if it * is zombie. * * This also hides group stop state from real parent; otherwise * a single stop can be reported twice as group and ptrace stop. * If a ptracer wants to distinguish these two events for its * own children it should create a separate process which takes * the role of real parent. */ if (!ptrace_reparented(p)) ptrace = 1; } /* slay zombie? */ if (exit_state == EXIT_ZOMBIE) { /* we don't reap group leaders with subthreads */ if (!delay_group_leader(p)) { /* * A zombie ptracee is only visible to its ptracer. * Notification and reaping will be cascaded to the * real parent when the ptracer detaches. */ if (unlikely(ptrace) || likely(!p->ptrace)) return wait_task_zombie(wo, p); } /* * Allow access to stopped/continued state via zombie by * falling through. Clearing of notask_error is complex. * * When !@ptrace: * * If WEXITED is set, notask_error should naturally be * cleared. If not, subset of WSTOPPED|WCONTINUED is set, * so, if there are live subthreads, there are events to * wait for. If all subthreads are dead, it's still safe * to clear - this function will be called again in finite * amount time once all the subthreads are released and * will then return without clearing. * * When @ptrace: * * Stopped state is per-task and thus can't change once the * target task dies. Only continued and exited can happen. * Clear notask_error if WCONTINUED | WEXITED. */ if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED))) wo->notask_error = 0; } else { /* * @p is alive and it's gonna stop, continue or exit, so * there always is something to wait for. */ wo->notask_error = 0; } /* * Wait for stopped. Depending on @ptrace, different stopped state * is used and the two don't interact with each other. */ ret = wait_task_stopped(wo, ptrace, p); if (ret) return ret; /* * Wait for continued. There's only one continued state and the * ptracer can consume it which can confuse the real parent. Don't * use WCONTINUED from ptracer. You don't need or want it. */ return wait_task_continued(wo, p); } /* * Do the work of do_wait() for one thread in the group, @tsk. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; then * ->notask_error is 0 if there were any eligible children, * or still -ECHILD. */ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->children, sibling) { int ret = wait_consider_task(wo, 0, p); if (ret) return ret; } return 0; } static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { int ret = wait_consider_task(wo, 1, p); if (ret) return ret; } return 0; } static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); struct task_struct *p = key; if (!eligible_pid(wo, p)) return 0; if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent) return 0; return default_wake_function(wait, mode, sync, key); } void __wake_up_parent(struct task_struct *p, struct task_struct *parent) { __wake_up_sync_key(&parent->signal->wait_chldexit, TASK_INTERRUPTIBLE, p); } static bool is_effectively_child(struct wait_opts *wo, bool ptrace, struct task_struct *target) { struct task_struct *parent = !ptrace ? target->real_parent : target->parent; return current == parent || (!(wo->wo_flags & __WNOTHREAD) && same_thread_group(current, parent)); } /* * Optimization for waiting on PIDTYPE_PID. No need to iterate through child * and tracee lists to find the target task. */ static int do_wait_pid(struct wait_opts *wo) { bool ptrace; struct task_struct *target; int retval; ptrace = false; target = pid_task(wo->wo_pid, PIDTYPE_TGID); if (target && is_effectively_child(wo, ptrace, target)) { retval = wait_consider_task(wo, ptrace, target); if (retval) return retval; } ptrace = true; target = pid_task(wo->wo_pid, PIDTYPE_PID); if (target && target->ptrace && is_effectively_child(wo, ptrace, target)) { retval = wait_consider_task(wo, ptrace, target); if (retval) return retval; } return 0; } static long do_wait(struct wait_opts *wo) { int retval; trace_sched_process_wait(wo->wo_pid); init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); wo->child_wait.private = current; add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); repeat: /* * If there is nothing that can match our criteria, just get out. * We will clear ->notask_error to zero if we see any child that * might later match our criteria, even if we are not able to reap * it yet. */ wo->notask_error = -ECHILD; if ((wo->wo_type < PIDTYPE_MAX) && (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type))) goto notask; set_current_state(TASK_INTERRUPTIBLE); read_lock(&tasklist_lock); if (wo->wo_type == PIDTYPE_PID) { retval = do_wait_pid(wo); if (retval) goto end; } else { struct task_struct *tsk = current; do { retval = do_wait_thread(wo, tsk); if (retval) goto end; retval = ptrace_do_wait(wo, tsk); if (retval) goto end; if (wo->wo_flags & __WNOTHREAD) break; } while_each_thread(current, tsk); } read_unlock(&tasklist_lock); notask: retval = wo->notask_error; if (!retval && !(wo->wo_flags & WNOHANG)) { retval = -ERESTARTSYS; if (!signal_pending(current)) { schedule(); goto repeat; } } end: __set_current_state(TASK_RUNNING); remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); return retval; } static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; unsigned int f_flags = 0; if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) return -EINVAL; switch (which) { case P_ALL: type = PIDTYPE_MAX; break; case P_PID: type = PIDTYPE_PID; if (upid <= 0) return -EINVAL; pid = find_get_pid(upid); break; case P_PGID: type = PIDTYPE_PGID; if (upid < 0) return -EINVAL; if (upid) pid = find_get_pid(upid); else pid = get_task_pid(current, PIDTYPE_PGID); break; case P_PIDFD: type = PIDTYPE_PID; if (upid < 0) return -EINVAL; pid = pidfd_get_pid(upid, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); break; default: return -EINVAL; } wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options; wo.wo_info = infop; wo.wo_rusage = ru; if (f_flags & O_NONBLOCK) wo.wo_flags |= WNOHANG; ret = do_wait(&wo); if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK)) ret = -EAGAIN; put_pid(pid); return ret; } SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, infop, int, options, struct rusage __user *, ru) { struct rusage r; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } long kernel_wait4(pid_t upid, int __user *stat_addr, int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; if (options & ~(WNOHANG|WUNTRACED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; /* -INT_MIN is not defined */ if (upid == INT_MIN) return -ESRCH; if (upid == -1) type = PIDTYPE_MAX; else if (upid < 0) { type = PIDTYPE_PGID; pid = find_get_pid(-upid); } else if (upid == 0) { type = PIDTYPE_PGID; pid = get_task_pid(current, PIDTYPE_PGID); } else /* upid > 0 */ { type = PIDTYPE_PID; pid = find_get_pid(upid); } wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options | WEXITED; wo.wo_info = NULL; wo.wo_stat = 0; wo.wo_rusage = ru; ret = do_wait(&wo); put_pid(pid); if (ret > 0 && stat_addr && put_user(wo.wo_stat, stat_addr)) ret = -EFAULT; return ret; } int kernel_wait(pid_t pid, int *stat) { struct wait_opts wo = { .wo_type = PIDTYPE_PID, .wo_pid = find_get_pid(pid), .wo_flags = WEXITED, }; int ret; ret = do_wait(&wo); if (ret > 0 && wo.wo_stat) *stat = wo.wo_stat; put_pid(wo.wo_pid); return ret; } SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, int, options, struct rusage __user *, ru) { struct rusage r; long err = kernel_wait4(upid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } return err; } #ifdef __ARCH_WANT_SYS_WAITPID /* * sys_waitpid() remains for compatibility. waitpid() should be * implemented by calling sys_wait4() from libc.a. */ SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options) { return kernel_wait4(pid, stat_addr, options, NULL); } #endif #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(wait4, compat_pid_t, pid, compat_uint_t __user *, stat_addr, int, options, struct compat_rusage __user *, ru) { struct rusage r; long err = kernel_wait4(pid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && put_compat_rusage(&r, ru)) return -EFAULT; } return err; } COMPAT_SYSCALL_DEFINE5(waitid, int, which, compat_pid_t, pid, struct compat_siginfo __user *, infop, int, options, struct compat_rusage __user *, uru) { struct rusage ru; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, pid, &info, options, uru ? &ru : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (uru) { /* kernel_waitid() overwrites everything in ru */ if (COMPAT_USE_64BIT_TIME) err = copy_to_user(uru, &ru, sizeof(ru)); else err = put_compat_rusage(&ru, uru); if (err) return -EFAULT; } } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } #endif /** * thread_group_exited - check that a thread group has exited * @pid: tgid of thread group to be checked. * * Test if the thread group represented by tgid has exited (all * threads are zombies, dead or completely gone). * * Return: true if the thread group has exited. false otherwise. */ bool thread_group_exited(struct pid *pid) { struct task_struct *task; bool exited; rcu_read_lock(); task = pid_task(pid, PIDTYPE_PID); exited = !task || (READ_ONCE(task->exit_state) && thread_group_empty(task)); rcu_read_unlock(); return exited; } EXPORT_SYMBOL(thread_group_exited); __weak void abort(void) { BUG(); /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } EXPORT_SYMBOL(abort); |
| 13 10 7 2 2 7 7 7 7 13 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Create default crypto algorithm instances. * * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> */ #include <crypto/internal/aead.h> #include <linux/completion.h> #include <linux/ctype.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/notifier.h> #include <linux/rtnetlink.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/string.h> #include "internal.h" struct cryptomgr_param { struct rtattr *tb[CRYPTO_MAX_ATTRS + 2]; struct { struct rtattr attr; struct crypto_attr_type data; } type; struct { struct rtattr attr; struct crypto_attr_alg data; } attrs[CRYPTO_MAX_ATTRS]; char template[CRYPTO_MAX_ALG_NAME]; struct crypto_larval *larval; u32 otype; u32 omask; }; struct crypto_test_param { char driver[CRYPTO_MAX_ALG_NAME]; char alg[CRYPTO_MAX_ALG_NAME]; u32 type; }; static int cryptomgr_probe(void *data) { struct cryptomgr_param *param = data; struct crypto_template *tmpl; int err; tmpl = crypto_lookup_template(param->template); if (!tmpl) goto out; do { err = tmpl->create(tmpl, param->tb); } while (err == -EAGAIN && !signal_pending(current)); crypto_tmpl_put(tmpl); out: complete_all(¶m->larval->completion); crypto_alg_put(¶m->larval->alg); kfree(param); module_put_and_kthread_exit(0); } static int cryptomgr_schedule_probe(struct crypto_larval *larval) { struct task_struct *thread; struct cryptomgr_param *param; const char *name = larval->alg.cra_name; const char *p; unsigned int len; int i; if (!try_module_get(THIS_MODULE)) goto err; param = kzalloc(sizeof(*param), GFP_KERNEL); if (!param) goto err_put_module; for (p = name; isalnum(*p) || *p == '-' || *p == '_'; p++) ; len = p - name; if (!len || *p != '(') goto err_free_param; memcpy(param->template, name, len); i = 0; for (;;) { name = ++p; for (; isalnum(*p) || *p == '-' || *p == '_'; p++) ; if (*p == '(') { int recursion = 0; for (;;) { if (!*++p) goto err_free_param; if (*p == '(') recursion++; else if (*p == ')' && !recursion--) break; } p++; } len = p - name; if (!len) goto err_free_param; param->attrs[i].attr.rta_len = sizeof(param->attrs[i]); param->attrs[i].attr.rta_type = CRYPTOA_ALG; memcpy(param->attrs[i].data.name, name, len); param->tb[i + 1] = ¶m->attrs[i].attr; i++; if (i >= CRYPTO_MAX_ATTRS) goto err_free_param; if (*p == ')') break; if (*p != ',') goto err_free_param; } if (!i) goto err_free_param; param->tb[i + 1] = NULL; param->type.attr.rta_len = sizeof(param->type); param->type.attr.rta_type = CRYPTOA_TYPE; param->type.data.type = larval->alg.cra_flags & ~CRYPTO_ALG_TESTED; param->type.data.mask = larval->mask & ~CRYPTO_ALG_TESTED; param->tb[0] = ¶m->type.attr; param->otype = larval->alg.cra_flags; param->omask = larval->mask; crypto_alg_get(&larval->alg); param->larval = larval; thread = kthread_run(cryptomgr_probe, param, "cryptomgr_probe"); if (IS_ERR(thread)) goto err_put_larval; return NOTIFY_STOP; err_put_larval: crypto_alg_put(&larval->alg); err_free_param: kfree(param); err_put_module: module_put(THIS_MODULE); err: return NOTIFY_OK; } static int cryptomgr_test(void *data) { struct crypto_test_param *param = data; u32 type = param->type; int err = 0; #ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS goto skiptest; #endif if (type & CRYPTO_ALG_TESTED) goto skiptest; err = alg_test(param->driver, param->alg, type, CRYPTO_ALG_TESTED); skiptest: crypto_alg_tested(param->driver, err); kfree(param); module_put_and_kthread_exit(0); } static int cryptomgr_schedule_test(struct crypto_alg *alg) { struct task_struct *thread; struct crypto_test_param *param; u32 type; if (!try_module_get(THIS_MODULE)) goto err; param = kzalloc(sizeof(*param), GFP_KERNEL); if (!param) goto err_put_module; memcpy(param->driver, alg->cra_driver_name, sizeof(param->driver)); memcpy(param->alg, alg->cra_name, sizeof(param->alg)); type = alg->cra_flags; /* Do not test internal algorithms. */ if (type & CRYPTO_ALG_INTERNAL) type |= CRYPTO_ALG_TESTED; param->type = type; thread = kthread_run(cryptomgr_test, param, "cryptomgr_test"); if (IS_ERR(thread)) goto err_free_param; return NOTIFY_STOP; err_free_param: kfree(param); err_put_module: module_put(THIS_MODULE); err: return NOTIFY_OK; } static int cryptomgr_notify(struct notifier_block *this, unsigned long msg, void *data) { switch (msg) { case CRYPTO_MSG_ALG_REQUEST: return cryptomgr_schedule_probe(data); case CRYPTO_MSG_ALG_REGISTER: return cryptomgr_schedule_test(data); case CRYPTO_MSG_ALG_LOADED: break; } return NOTIFY_DONE; } static struct notifier_block cryptomgr_notifier = { .notifier_call = cryptomgr_notify, }; static int __init cryptomgr_init(void) { return crypto_register_notifier(&cryptomgr_notifier); } static void __exit cryptomgr_exit(void) { int err = crypto_unregister_notifier(&cryptomgr_notifier); BUG_ON(err); } /* * This is arch_initcall() so that the crypto self-tests are run on algorithms * registered early by subsys_initcall(). subsys_initcall() is needed for * generic implementations so that they're available for comparison tests when * other implementations are registered later by module_init(). */ arch_initcall(cryptomgr_init); module_exit(cryptomgr_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Crypto Algorithm Manager"); |
| 9 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #ifndef _NET_BATMAN_ADV_ORIGINATOR_H_ #define _NET_BATMAN_ADV_ORIGINATOR_H_ #include "main.h" #include <linux/compiler.h> #include <linux/if_ether.h> #include <linux/jhash.h> #include <linux/kref.h> #include <linux/netlink.h> #include <linux/skbuff.h> #include <linux/types.h> bool batadv_compare_orig(const struct hlist_node *node, const void *data2); int batadv_originator_init(struct batadv_priv *bat_priv); void batadv_originator_free(struct batadv_priv *bat_priv); void batadv_purge_orig_ref(struct batadv_priv *bat_priv); void batadv_orig_node_release(struct kref *ref); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const u8 *addr); struct batadv_hardif_neigh_node * batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface, const u8 *neigh_addr); void batadv_hardif_neigh_release(struct kref *ref); struct batadv_neigh_node * batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node, struct batadv_hard_iface *hard_iface, const u8 *neigh_addr); void batadv_neigh_node_release(struct kref *ref); struct batadv_neigh_node * batadv_orig_router_get(struct batadv_orig_node *orig_node, const struct batadv_hard_iface *if_outgoing); struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_new(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); struct batadv_neigh_ifinfo * batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh, struct batadv_hard_iface *if_outgoing); void batadv_neigh_ifinfo_release(struct kref *ref); int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb); struct batadv_orig_ifinfo * batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing); struct batadv_orig_ifinfo * batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node, struct batadv_hard_iface *if_outgoing); void batadv_orig_ifinfo_release(struct kref *ref); int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb); struct batadv_orig_node_vlan * batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, unsigned short vid); struct batadv_orig_node_vlan * batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, unsigned short vid); void batadv_orig_node_vlan_release(struct kref *ref); /** * batadv_choose_orig() - Return the index of the orig entry in the hash table * @data: mac address of the originator node * @size: the size of the hash table * * Return: the hash index where the object represented by @data should be * stored at. */ static inline u32 batadv_choose_orig(const void *data, u32 size) { u32 hash = 0; hash = jhash(data, ETH_ALEN, hash); return hash % size; } struct batadv_orig_node * batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data); /** * batadv_orig_node_vlan_put() - decrement the refcounter and possibly release * the originator-vlan object * @orig_vlan: the originator-vlan object to release */ static inline void batadv_orig_node_vlan_put(struct batadv_orig_node_vlan *orig_vlan) { if (!orig_vlan) return; kref_put(&orig_vlan->refcount, batadv_orig_node_vlan_release); } /** * batadv_neigh_ifinfo_put() - decrement the refcounter and possibly release * the neigh_ifinfo * @neigh_ifinfo: the neigh_ifinfo object to release */ static inline void batadv_neigh_ifinfo_put(struct batadv_neigh_ifinfo *neigh_ifinfo) { if (!neigh_ifinfo) return; kref_put(&neigh_ifinfo->refcount, batadv_neigh_ifinfo_release); } /** * batadv_hardif_neigh_put() - decrement the hardif neighbors refcounter * and possibly release it * @hardif_neigh: hardif neigh neighbor to free */ static inline void batadv_hardif_neigh_put(struct batadv_hardif_neigh_node *hardif_neigh) { if (!hardif_neigh) return; kref_put(&hardif_neigh->refcount, batadv_hardif_neigh_release); } /** * batadv_neigh_node_put() - decrement the neighbors refcounter and possibly * release it * @neigh_node: neigh neighbor to free */ static inline void batadv_neigh_node_put(struct batadv_neigh_node *neigh_node) { if (!neigh_node) return; kref_put(&neigh_node->refcount, batadv_neigh_node_release); } /** * batadv_orig_ifinfo_put() - decrement the refcounter and possibly release * the orig_ifinfo * @orig_ifinfo: the orig_ifinfo object to release */ static inline void batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo) { if (!orig_ifinfo) return; kref_put(&orig_ifinfo->refcount, batadv_orig_ifinfo_release); } /** * batadv_orig_node_put() - decrement the orig node refcounter and possibly * release it * @orig_node: the orig node to free */ static inline void batadv_orig_node_put(struct batadv_orig_node *orig_node) { if (!orig_node) return; kref_put(&orig_node->refcount, batadv_orig_node_release); } #endif /* _NET_BATMAN_ADV_ORIGINATOR_H_ */ |
| 30 4 26 26 26 22 7 2 1 1 2 1 1 55 55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/ctype.h> #include <linux/kmod.h> #include <linux/sort.h> #include <linux/delay.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/delayacct.h> #include <linux/pid_namespace.h> #include <linux/cgroupstats.h> #include <linux/fs_parser.h> #include <trace/events/cgroup.h> /* * pidlists linger the following amount before being destroyed. The goal * is avoiding frequent destruction in the middle of consecutive read calls * Expiring in the middle is a performance problem not a correctness one. * 1 sec should be enough. */ #define CGROUP_PIDLIST_DESTROY_DELAY HZ /* Controllers blocked by the commandline in v1 */ static u16 cgroup_no_v1_mask; /* disable named v1 mounts */ static bool cgroup_no_v1_named; /* * pidlist destructions need to be flushed on cgroup destruction. Use a * separate workqueue as flush domain. */ static struct workqueue_struct *cgroup_pidlist_destroy_wq; /* protects cgroup_subsys->release_agent_path */ static DEFINE_SPINLOCK(release_agent_path_lock); bool cgroup1_ssid_disabled(int ssid) { return cgroup_no_v1_mask & (1 << ssid); } /** * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' * @from: attach to all cgroups of a given task * @tsk: the task to be attached * * Return: %0 on success or a negative errno code on failure */ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroup_root *root; int retval = 0; mutex_lock(&cgroup_mutex); cpus_read_lock(); percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; if (root == &cgrp_dfl_root) continue; spin_lock_irq(&css_set_lock); from_cgrp = task_cgroup_from_root(from, root); spin_unlock_irq(&css_set_lock); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) break; } percpu_up_write(&cgroup_threadgroup_rwsem); cpus_read_unlock(); mutex_unlock(&cgroup_mutex); return retval; } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /** * cgroup_transfer_tasks - move tasks from one cgroup to another * @to: cgroup to which the tasks will be moved * @from: cgroup in which the tasks currently reside * * Locking rules between cgroup_post_fork() and the migration path * guarantee that, if a task is forking while being migrated, the new child * is guaranteed to be either visible in the source cgroup after the * parent's migration is complete or put into the target cgroup. No task * can slip out of migration through forking. * * Return: %0 on success or a negative errno code on failure */ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { DEFINE_CGROUP_MGCTX(mgctx); struct cgrp_cset_link *link; struct css_task_iter it; struct task_struct *task; int ret; if (cgroup_on_dfl(to)) return -EINVAL; ret = cgroup_migrate_vet_dst(to); if (ret) return ret; mutex_lock(&cgroup_mutex); percpu_down_write(&cgroup_threadgroup_rwsem); /* all tasks in @from are being moved, all csets are source */ spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) cgroup_migrate_add_src(link->cset, to, &mgctx); spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_err; /* * Migrate tasks one-by-one until @from is empty. This fails iff * ->can_attach() fails. */ do { css_task_iter_start(&from->self, 0, &it); do { task = css_task_iter_next(&it); } while (task && (task->flags & PF_EXITING)); if (task) get_task_struct(task); css_task_iter_end(&it); if (task) { ret = cgroup_migrate(task, false, &mgctx); if (!ret) TRACE_CGROUP_PATH(transfer_tasks, to, task, false); put_task_struct(task); } } while (task && !ret); out_err: cgroup_migrate_finish(&mgctx); percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return ret; } /* * Stuff for reading the 'tasks'/'procs' files. * * Reading this file can return large amounts of data if a cgroup has * *lots* of attached tasks. So it may need several calls to read(), * but we cannot guarantee that the information we produce is correct * unless we produce it entirely atomically. * */ /* which pidlist file are we talking about? */ enum cgroup_filetype { CGROUP_FILE_PROCS, CGROUP_FILE_TASKS, }; /* * A pidlist is a list of pids that virtually represents the contents of one * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, * a pair (one each for procs, tasks) for each pid namespace that's relevant * to the cgroup. */ struct cgroup_pidlist { /* * used to find which pidlist is wanted. doesn't change as long as * this particular list stays in the list. */ struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; /* array of xids */ pid_t *list; /* how many elements the above list has */ int length; /* each of these stored in a list by its cgroup */ struct list_head links; /* pointer to the cgroup we belong to, for list removal purposes */ struct cgroup *owner; /* for delayed destruction */ struct delayed_work destroy_dwork; }; /* * Used to destroy all pidlists lingering waiting for destroy timer. None * should be left afterwards. */ void cgroup1_pidlist_destroy_all(struct cgroup *cgrp) { struct cgroup_pidlist *l, *tmp_l; mutex_lock(&cgrp->pidlist_mutex); list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); mutex_unlock(&cgrp->pidlist_mutex); flush_workqueue(cgroup_pidlist_destroy_wq); BUG_ON(!list_empty(&cgrp->pidlists)); } static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, destroy_dwork); struct cgroup_pidlist *tofree = NULL; mutex_lock(&l->owner->pidlist_mutex); /* * Destroy iff we didn't get queued again. The state won't change * as destroy_dwork can only be queued while locked. */ if (!delayed_work_pending(dwork)) { list_del(&l->links); kvfree(l->list); put_pid_ns(l->key.ns); tofree = l; } mutex_unlock(&l->owner->pidlist_mutex); kfree(tofree); } /* * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries * Returns the number of unique elements. */ static int pidlist_uniq(pid_t *list, int length) { int src, dest = 1; /* * we presume the 0th element is unique, so i starts at 1. trivial * edge cases first; no work needs to be done for either */ if (length == 0 || length == 1) return length; /* src and dest walk down the list; dest counts unique elements */ for (src = 1; src < length; src++) { /* find next unique element */ while (list[src] == list[src-1]) { src++; if (src == length) goto after; } /* dest always points to where the next unique element goes */ list[dest] = list[src]; dest++; } after: return dest; } /* * The two pid files - task and cgroup.procs - guaranteed that the result * is sorted, which forced this whole pidlist fiasco. As pid order is * different per namespace, each namespace needs differently sorted list, * making it impossible to use, for example, single rbtree of member tasks * sorted by task pointer. As pidlists can be fairly large, allocating one * per open file is dangerous, so cgroup had to implement shared pool of * pidlists keyed by cgroup and namespace. */ static int cmppid(const void *a, const void *b) { return *(pid_t *)a - *(pid_t *)b; } static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; /* don't need task_nsproxy() if we're looking at ourself */ struct pid_namespace *ns = task_active_pid_ns(current); lockdep_assert_held(&cgrp->pidlist_mutex); list_for_each_entry(l, &cgrp->pidlists, links) if (l->key.type == type && l->key.ns == ns) return l; return NULL; } /* * find the appropriate pidlist for our purpose (given procs vs tasks) * returns with the lock on that pidlist already held, and takes care * of the use count, or returns NULL with no locks held if we're out of * memory. */ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); l = cgroup_pidlist_find(cgrp, type); if (l) return l; /* entry not found; create a new one */ l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); if (!l) return l; INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); l->key.type = type; /* don't need task_nsproxy() if we're looking at ourself */ l->key.ns = get_pid_ns(task_active_pid_ns(current)); l->owner = cgrp; list_add(&l->links, &cgrp->pidlists); return l; } /* * Load a cgroup's pidarray with either procs' tgids or tasks' pids */ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, struct cgroup_pidlist **lp) { pid_t *array; int length; int pid, n = 0; /* used for populating the array */ struct css_task_iter it; struct task_struct *tsk; struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); /* * If cgroup gets more users after we read count, we won't have * enough space - tough. This race is indistinguishable to the * caller from the case that the additional cgroup users didn't * show up until sometime later on. */ length = cgroup_task_count(cgrp); array = kvmalloc_array(length, sizeof(pid_t), GFP_KERNEL); if (!array) return -ENOMEM; /* now, populate the array */ css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ if (type == CGROUP_FILE_PROCS) pid = task_tgid_vnr(tsk); else pid = task_pid_vnr(tsk); if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } css_task_iter_end(&it); length = n; /* now sort & strip out duplicates (tgids or recycled thread PIDs) */ sort(array, length, sizeof(pid_t), cmppid, NULL); length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { kvfree(array); return -ENOMEM; } /* store array, freeing old if necessary */ kvfree(l->list); l->list = array; l->length = length; *lp = l; return 0; } /* * seq_file methods for the tasks/procs files. The seq_file position is the * next pid to display; the seq_file iterator is a pointer to the pid * in the cgroup->l->list array. */ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) { /* * Initially we receive a position value that corresponds to * one more than the last pid shown (or 0 on the first call or * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; int index = 0, pid = *pos; int *iter, ret; mutex_lock(&cgrp->pidlist_mutex); /* * !NULL @ctx->procs1.pidlist indicates that this isn't the first * start() after open. If the matching pidlist is around, we can use * that. Look for it. Note that @ctx->procs1.pidlist can't be used * directly. It could already have been destroyed. */ if (ctx->procs1.pidlist) ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type); /* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ if (!ctx->procs1.pidlist) { ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); if (ret) return ERR_PTR(ret); } l = ctx->procs1.pidlist; if (pid) { int end = l->length; while (index < end) { int mid = (index + end) / 2; if (l->list[mid] == pid) { index = mid; break; } else if (l->list[mid] <= pid) index = mid + 1; else end = mid; } } /* If we're off the end of the array, we're done */ if (index >= l->length) return NULL; /* Update the abstract position to be the actual pid that we found */ iter = l->list + index; *pos = *iter; return iter; } static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, CGROUP_PIDLIST_DESTROY_DELAY); mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); } static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; pid_t *p = v; pid_t *end = l->list + l->length; /* * Advance to the next pid in the array. If this goes off the * end, we're done */ p++; if (p >= end) { (*pos)++; return NULL; } else { *pos = *p; return p; } } static int cgroup_pidlist_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *(int *)v); return 0; } static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct cgroup *cgrp; struct task_struct *task; const struct cred *cred, *tcred; ssize_t ret; bool locked; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* * Even if we're attaching all tasks in the thread group, we only need * to check permissions on one of them. Check permissions using the * credentials from file open to protect against inherited fd attacks. */ cred = of->file->f_cred; tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && !uid_eq(cred->euid, tcred->suid)) ret = -EACCES; put_cred(tcred); if (ret) goto out_finish; ret = cgroup_attach_task(cgrp, task, threadgroup); out_finish: cgroup_procs_write_finish(task, locked); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static ssize_t cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, true); } static ssize_t cgroup1_tasks_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, false); } static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; struct cgroup_file_ctx *ctx; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ ctx = of->priv; if ((ctx->ns->user_ns != &init_user_ns) || !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN)) return -EPERM; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; spin_lock(&release_agent_path_lock); strlcpy(cgrp->root->release_agent_path, strstrip(buf), sizeof(cgrp->root->release_agent_path)); spin_unlock(&release_agent_path_lock); cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_release_agent_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; spin_lock(&release_agent_path_lock); seq_puts(seq, cgrp->root->release_agent_path); spin_unlock(&release_agent_path_lock); seq_putc(seq, '\n'); return 0; } static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) { seq_puts(seq, "0\n"); return 0; } static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft) { return notify_on_release(css->cgroup); } static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); else clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); return 0; } static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, struct cftype *cft) { return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); } static int cgroup_clone_children_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); else clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); return 0; } /* cgroup core interface files for the legacy hierarchies */ struct cftype cgroup1_base_files[] = { { .name = "cgroup.procs", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_PROCS, .write = cgroup1_procs_write, }, { .name = "cgroup.clone_children", .read_u64 = cgroup_clone_children_read, .write_u64 = cgroup_clone_children_write, }, { .name = "cgroup.sane_behavior", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_sane_behavior_show, }, { .name = "tasks", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_TASKS, .write = cgroup1_tasks_write, }, { .name = "notify_on_release", .read_u64 = cgroup_read_notify_on_release, .write_u64 = cgroup_write_notify_on_release, }, { .name = "release_agent", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_release_agent_show, .write = cgroup_release_agent_write, .max_write_len = PATH_MAX - 1, }, { } /* terminate */ }; /* Display information about each subsystem and each hierarchy */ int proc_cgroupstats_show(struct seq_file *m, void *v) { struct cgroup_subsys *ss; int i; seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); /* * ideally we don't want subsystems moving around while we do this. * cgroup_mutex is also necessary to guarantee an atomic snapshot of * subsys/hierarchy state. */ mutex_lock(&cgroup_mutex); for_each_subsys(ss, i) seq_printf(m, "%s\t%d\t%d\t%d\n", ss->legacy_name, ss->root->hierarchy_id, atomic_read(&ss->root->nr_cgrps), cgroup_ssid_enabled(i)); mutex_unlock(&cgroup_mutex); return 0; } /** * cgroupstats_build - build and fill cgroupstats * @stats: cgroupstats to fill information into * @dentry: A dentry entry belonging to the cgroup for which stats have * been requested. * * Build and fill cgroupstats so that taskstats can export it to user * space. * * Return: %0 on success or a negative errno code on failure */ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct cgroup *cgrp; struct css_task_iter it; struct task_struct *tsk; /* it should be kernfs_node belonging to cgroupfs and is a directory */ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || kernfs_type(kn) != KERNFS_DIR) return -EINVAL; mutex_lock(&cgroup_mutex); /* * We aren't being called from kernfs and there's no guarantee on * @kn->priv's validity. For this and css_tryget_online_from_dir(), * @kn->priv is RCU safe. Let's do the RCU dancing. */ rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || cgroup_is_dead(cgrp)) { rcu_read_unlock(); mutex_unlock(&cgroup_mutex); return -ENOENT; } rcu_read_unlock(); css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { switch (READ_ONCE(tsk->__state)) { case TASK_RUNNING: stats->nr_running++; break; case TASK_INTERRUPTIBLE: stats->nr_sleeping++; break; case TASK_UNINTERRUPTIBLE: stats->nr_uninterruptible++; break; case TASK_STOPPED: stats->nr_stopped++; break; default: if (tsk->in_iowait) stats->nr_io_wait++; break; } } css_task_iter_end(&it); mutex_unlock(&cgroup_mutex); return 0; } void cgroup1_check_for_release(struct cgroup *cgrp) { if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) schedule_work(&cgrp->release_agent_work); } /* * Notify userspace when a cgroup is released, by running the * configured release agent with the name of the cgroup (path * relative to the root of cgroup file system) as the argument. * * Most likely, this user command will try to rmdir this cgroup. * * This races with the possibility that some other task will be * attached to this cgroup before it is removed, or that some other * user task will 'mkdir' a child cgroup of this cgroup. That's ok. * The presumed 'rmdir' will fail quietly if this cgroup is no longer * unused, and this cgroup will be reprieved from its death sentence, * to continue to serve a useful existence. Next time it's released, * we will get notified again, if it still has 'notify_on_release' set. * * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which * means only wait until the task is successfully execve()'d. The * separate release agent task is forked by call_usermodehelper(), * then control in this thread returns here, without waiting for the * release agent task. We don't bother to wait because the caller of * this routine has no use for the exit status of the release agent * task, so no sense holding our caller up for that. */ void cgroup1_release_agent(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, release_agent_work); char *pathbuf, *agentbuf; char *argv[3], *envp[3]; int ret; /* snoop agent path and exit early if empty */ if (!cgrp->root->release_agent_path[0]) return; /* prepare argument buffers */ pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf || !agentbuf) goto out_free; spin_lock(&release_agent_path_lock); strlcpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX); spin_unlock(&release_agent_path_lock); if (!agentbuf[0]) goto out_free; ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); if (ret < 0 || ret >= PATH_MAX) goto out_free; argv[0] = agentbuf; argv[1] = pathbuf; argv[2] = NULL; /* minimal command environment */ envp[0] = "HOME=/"; envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); out_free: kfree(agentbuf); kfree(pathbuf); } /* * cgroup_rename - Only allow simple rename of directories in place. */ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name_str) { struct cgroup *cgrp = kn->priv; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(new_name_str, '\n')) return -EINVAL; if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; if (kn->parent != new_parent) return -EIO; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. kernfs_rename() doesn't require active_ref * protection. Break them before grabbing cgroup_mutex. */ kernfs_break_active_protection(new_parent); kernfs_break_active_protection(kn); mutex_lock(&cgroup_mutex); ret = kernfs_rename(kn, new_parent, new_name_str); if (!ret) TRACE_CGROUP_PATH(rename, cgrp); mutex_unlock(&cgroup_mutex); kernfs_unbreak_active_protection(kn); kernfs_unbreak_active_protection(new_parent); return ret; } static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_subsys *ss; int ssid; for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_show_option(seq, ss->legacy_name, NULL); if (root->flags & CGRP_ROOT_NOPREFIX) seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); if (root->flags & CGRP_ROOT_CPUSET_V2_MODE) seq_puts(seq, ",cpuset_v2_mode"); spin_lock(&release_agent_path_lock); if (strlen(root->release_agent_path)) seq_show_option(seq, "release_agent", root->release_agent_path); spin_unlock(&release_agent_path_lock); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_show_option(seq, "name", root->name); return 0; } enum cgroup1_param { Opt_all, Opt_clone_children, Opt_cpuset_v2_mode, Opt_name, Opt_none, Opt_noprefix, Opt_release_agent, Opt_xattr, }; const struct fs_parameter_spec cgroup1_fs_parameters[] = { fsparam_flag ("all", Opt_all), fsparam_flag ("clone_children", Opt_clone_children), fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), fsparam_string("name", Opt_name), fsparam_flag ("none", Opt_none), fsparam_flag ("noprefix", Opt_noprefix), fsparam_string("release_agent", Opt_release_agent), fsparam_flag ("xattr", Opt_xattr), {} }; int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_subsys *ss; struct fs_parse_result result; int opt, i; opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { int ret; ret = vfs_parse_fs_param_source(fc, param); if (ret != -ENOPARAM) return ret; for_each_subsys(ss, i) { if (strcmp(param->key, ss->legacy_name)) continue; if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i)) return invalfc(fc, "Disabled controller '%s'", param->key); ctx->subsys_mask |= (1 << i); return 0; } return invalfc(fc, "Unknown subsys name '%s'", param->key); } if (opt < 0) return opt; switch (opt) { case Opt_none: /* Explicitly have no subsystems */ ctx->none = true; break; case Opt_all: ctx->all_ss = true; break; case Opt_noprefix: ctx->flags |= CGRP_ROOT_NOPREFIX; break; case Opt_clone_children: ctx->cpuset_clone_children = true; break; case Opt_cpuset_v2_mode: ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; break; case Opt_xattr: ctx->flags |= CGRP_ROOT_XATTR; break; case Opt_release_agent: /* Specifying two release agents is forbidden */ if (ctx->release_agent) return invalfc(fc, "release_agent respecified"); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) return invalfc(fc, "Setting release_agent not allowed"); ctx->release_agent = param->string; param->string = NULL; break; case Opt_name: /* blocked by boot param? */ if (cgroup_no_v1_named) return -ENOENT; /* Can't specify an empty name */ if (!param->size) return invalfc(fc, "Empty name"); if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1) return invalfc(fc, "Name too long"); /* Must match [\w.-]+ */ for (i = 0; i < param->size; i++) { char c = param->string[i]; if (isalnum(c)) continue; if ((c == '.') || (c == '-') || (c == '_')) continue; return invalfc(fc, "Invalid name"); } /* Specifying two names is forbidden */ if (ctx->name) return invalfc(fc, "name respecified"); ctx->name = param->string; param->string = NULL; break; } return 0; } static int check_cgroupfs_options(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); u16 mask = U16_MAX; u16 enabled = 0; struct cgroup_subsys *ss; int i; #ifdef CONFIG_CPUSETS mask = ~((u16)1 << cpuset_cgrp_id); #endif for_each_subsys(ss, i) if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i)) enabled |= 1 << i; ctx->subsys_mask &= enabled; /* * In absence of 'none', 'name=' and subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) ctx->all_ss = true; if (ctx->all_ss) { /* Mutually exclusive option 'all' + subsystem name */ if (ctx->subsys_mask) return invalfc(fc, "subsys name conflicts with all"); /* 'all' => select all the subsystems */ ctx->subsys_mask = enabled; } /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ if (!ctx->subsys_mask && !ctx->name) return invalfc(fc, "Need name or subsystem set"); /* * Option noprefix was introduced just for backward compatibility * with the old cpuset, so we allow noprefix only if mounting just * the cpuset subsystem. */ if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask)) return invalfc(fc, "noprefix used incorrectly"); /* Can't specify "none" and some subsystems */ if (ctx->subsys_mask && ctx->none) return invalfc(fc, "none used incorrectly"); return 0; } int cgroup1_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); int ret = 0; u16 added_mask, removed_mask; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* See what subsystems are wanted */ ret = check_cgroupfs_options(fc); if (ret) goto out_unlock; if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent) pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); added_mask = ctx->subsys_mask & ~root->subsys_mask; removed_mask = root->subsys_mask & ~ctx->subsys_mask; /* Don't allow flags or name to change at remount */ if ((ctx->flags ^ root->flags) || (ctx->name && strcmp(ctx->name, root->name))) { errorfc(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", ctx->flags, ctx->name ?: "", root->flags, root->name); ret = -EINVAL; goto out_unlock; } /* remounting is not allowed for populated hierarchies */ if (!list_empty(&root->cgrp.self.children)) { ret = -EBUSY; goto out_unlock; } ret = rebind_subsystems(root, added_mask); if (ret) goto out_unlock; WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); if (ctx->release_agent) { spin_lock(&release_agent_path_lock); strcpy(root->release_agent_path, ctx->release_agent); spin_unlock(&release_agent_path_lock); } trace_cgroup_remount(root); out_unlock: mutex_unlock(&cgroup_mutex); return ret; } struct kernfs_syscall_ops cgroup1_kf_syscall_ops = { .rename = cgroup1_rename, .show_options = cgroup1_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; /* * The guts of cgroup1 mount - find or create cgroup_root to use. * Called with cgroup_mutex held; returns 0 on success, -E... on * error and positive - in case when the candidate is busy dying. * On success it stashes a reference to cgroup_root into given * cgroup_fs_context; that reference is *NOT* counting towards the * cgroup_root refcount. */ static int cgroup1_root_to_use(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_root *root; struct cgroup_subsys *ss; int i, ret; /* First find the desired set of subsystems */ ret = check_cgroupfs_options(fc); if (ret) return ret; /* * Destruction of cgroup root is asynchronous, so subsystems may * still be dying after the previous unmount. Let's drain the * dying subsystems. We just need to ensure that the ones * unmounted previously finish dying and don't care about new ones * starting. Testing ref liveliness is good enough. */ for_each_subsys(ss, i) { if (!(ctx->subsys_mask & (1 << i)) || ss->root == &cgrp_dfl_root) continue; if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) return 1; /* restart */ cgroup_put(&ss->root->cgrp); } for_each_root(root) { bool name_match = false; if (root == &cgrp_dfl_root) continue; /* * If we asked for a name then it must match. Also, if * name matches but sybsys_mask doesn't, we should fail. * Remember whether name matched. */ if (ctx->name) { if (strcmp(ctx->name, root->name)) continue; name_match = true; } /* * If we asked for subsystems (or explicitly for no * subsystems) then they must match. */ if ((ctx->subsys_mask || ctx->none) && (ctx->subsys_mask != root->subsys_mask)) { if (!name_match) continue; return -EBUSY; } if (root->flags ^ ctx->flags) pr_warn("new mount options do not match the existing superblock, will be ignored\n"); ctx->root = root; return 0; } /* * No such thing, create a new one. name= matching without subsys * specification is allowed for already existing hierarchies but we * can't create new one without subsys specification. */ if (!ctx->subsys_mask && !ctx->none) return invalfc(fc, "No subsys list or none specified"); /* Hierarchies may only be created in the initial cgroup namespace. */ if (ctx->ns != &init_cgroup_ns) return -EPERM; root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) return -ENOMEM; ctx->root = root; init_cgroup_root(ctx); ret = cgroup_setup_root(root, ctx->subsys_mask); if (ret) cgroup_free_root(root); return ret; } int cgroup1_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; /* Check if the caller has permission to mount. */ if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); ret = cgroup1_root_to_use(fc); if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt)) ret = 1; /* restart */ mutex_unlock(&cgroup_mutex); if (!ret) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { fc_drop_locked(fc); ret = 1; } if (unlikely(ret > 0)) { msleep(10); return restart_syscall(); } return ret; } static int __init cgroup1_wq_init(void) { /* * Used to destroy pidlists and separate to serve as flush domain. * Cap @max_active to 1 too. */ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", 0, 1); BUG_ON(!cgroup_pidlist_destroy_wq); return 0; } core_initcall(cgroup1_wq_init); static int __init cgroup_no_v1(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; if (!strcmp(token, "all")) { cgroup_no_v1_mask = U16_MAX; continue; } if (!strcmp(token, "named")) { cgroup_no_v1_named = true; continue; } for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; cgroup_no_v1_mask |= 1 << i; } } return 1; } __setup("cgroup_no_v1=", cgroup_no_v1); |
| 19 2347 1 4 2 8 1 7 4 43 3 3 77 21 28 5 13 4 3 3 4 24 1 2 3 3 6 3 5 4 4 5 3 4 3 4 4 4 4 5 3 5 2 2 5 4 3 4 3 5 2 4 3 5 2 4 8 1 15 15 2 3 7 2 9 8 2498 1 2 16 34 3 1 1 1 4 8 14 57 1 2 10 2 9 2266 82 2510 64 193 2309 2489 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ioctl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/compat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> #include <linux/sched/signal.h> #include <linux/fiemap.h> #include <linux/mount.h> #include <linux/fscrypt.h> #include <linux/fileattr.h> #include "internal.h" #include <asm/ioctls.h> /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on * @cmd: ioctl command to execute * @arg: command-specific argument for ioctl * * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise * returns -ENOTTY. * * Returns 0 on success, -errno on error. */ long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; if (!filp->f_op->unlocked_ioctl) goto out; error = filp->f_op->unlocked_ioctl(filp, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; out: return error; } EXPORT_SYMBOL(vfs_ioctl); static int ioctl_fibmap(struct file *filp, int __user *p) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; int error, ur_block; sector_t block; if (!capable(CAP_SYS_RAWIO)) return -EPERM; error = get_user(ur_block, p); if (error) return error; if (ur_block < 0) return -EINVAL; block = ur_block; error = bmap(inode, &block); if (block > INT_MAX) { error = -ERANGE; pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n", current->comm, task_pid_nr(current), sb->s_id, filp); } if (error) ur_block = 0; else ur_block = block; if (put_user(ur_block, p)) error = -EFAULT; return error; } /** * fiemap_fill_next_extent - Fiemap helper function * @fieinfo: Fiemap context passed into ->fiemap * @logical: Extent logical start offset, in bytes * @phys: Extent physical start offset, in bytes * @len: Extent length, in bytes * @flags: FIEMAP_EXTENT flags that describe this extent * * Called from file system ->fiemap callback. Will populate extent * info as passed in via arguments and copy to user memory. On * success, extent count on fieinfo is incremented. * * Returns 0 on success, -errno on error, 1 if this was the last * extent that will fit in user array. */ #define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) #define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) #define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, u64 phys, u64 len, u32 flags) { struct fiemap_extent extent; struct fiemap_extent __user *dest = fieinfo->fi_extents_start; /* only count the extents */ if (fieinfo->fi_extents_max == 0) { fieinfo->fi_extents_mapped++; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) return 1; if (flags & SET_UNKNOWN_FLAGS) flags |= FIEMAP_EXTENT_UNKNOWN; if (flags & SET_NO_UNMOUNTED_IO_FLAGS) flags |= FIEMAP_EXTENT_ENCODED; if (flags & SET_NOT_ALIGNED_FLAGS) flags |= FIEMAP_EXTENT_NOT_ALIGNED; memset(&extent, 0, sizeof(extent)); extent.fe_logical = logical; extent.fe_physical = phys; extent.fe_length = len; extent.fe_flags = flags; dest += fieinfo->fi_extents_mapped; if (copy_to_user(dest, &extent, sizeof(extent))) return -EFAULT; fieinfo->fi_extents_mapped++; if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) return 1; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } EXPORT_SYMBOL(fiemap_fill_next_extent); /** * fiemap_prep - check validity of requested flags for fiemap * @inode: Inode to operate on * @fieinfo: Fiemap context passed into ->fiemap * @start: Start of the mapped range * @len: Length of the mapped range, can be truncated by this function. * @supported_flags: Set of fiemap flags that the file system understands * * This function must be called from each ->fiemap instance to validate the * fiemap request against the file system parameters. * * Returns 0 on success, or a negative error on failure. */ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 *len, u32 supported_flags) { u64 maxbytes = inode->i_sb->s_maxbytes; u32 incompat_flags; int ret = 0; if (*len == 0) return -EINVAL; if (start >= maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; supported_flags |= FIEMAP_FLAG_SYNC; supported_flags &= FIEMAP_FLAGS_COMPAT; incompat_flags = fieinfo->fi_flags & ~supported_flags; if (incompat_flags) { fieinfo->fi_flags = incompat_flags; return -EBADR; } if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) ret = filemap_write_and_wait(inode->i_mapping); return ret; } EXPORT_SYMBOL(fiemap_prep); static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) { struct fiemap fiemap; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (!inode->i_op->fiemap) return -EOPNOTSUPP; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { struct fd src_file = fdget(srcfd); loff_t cloned; int ret; if (!src_file.file) return -EBADF; ret = -EXDEV; if (src_file.file->f_path.mnt != dst_file->f_path.mnt) goto fdput; cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen, 0); if (cloned < 0) ret = cloned; else if (olen && cloned != olen) ret = -EINVAL; else ret = 0; fdput: fdput(src_file); return ret; } static long ioctl_file_clone_range(struct file *file, struct file_clone_range __user *argp) { struct file_clone_range args; if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; return ioctl_file_clone(file, args.src_fd, args.src_offset, args.src_length, args.dest_offset); } /* * This provides compatibility with legacy XFS pre-allocation ioctls * which predate the fallocate syscall. * * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ static int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += filp->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } /* on ia32 l_start is on a 32-bit boundary */ #if defined CONFIG_COMPAT && defined(CONFIG_X86_64) /* just account for different alignment */ static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *argp) { struct inode *inode = file_inode(file); struct space_resv_32 sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += file->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } #endif static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p) { switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: return ioctl_preallocate(filp, 0, p); case FS_IOC_UNRESVSP: case FS_IOC_UNRESVSP64: return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); case FS_IOC_ZERO_RANGE: return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return -ENOIOCTLCMD; } static int ioctl_fionbio(struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = O_NONBLOCK; #ifdef __sparc__ /* SunOS compatibility item. */ if (O_NONBLOCK != O_NDELAY) flag |= O_NDELAY; #endif spin_lock(&filp->f_lock); if (on) filp->f_flags |= flag; else filp->f_flags &= ~flag; spin_unlock(&filp->f_lock); return error; } static int ioctl_fioasync(unsigned int fd, struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = on ? FASYNC : 0; /* Did FASYNC state change ? */ if ((flag ^ filp->f_flags) & FASYNC) { if (filp->f_op->fasync) /* fasync() adjusts filp->f_flags */ error = filp->f_op->fasync(fd, filp, on); else error = -ENOTTY; } return error < 0 ? error : 0; } static int ioctl_fsfreeze(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* If filesystem doesn't support freeze feature, return. */ if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL) return -EOPNOTSUPP; /* Freeze */ if (sb->s_op->freeze_super) return sb->s_op->freeze_super(sb); return freeze_super(sb); } static int ioctl_fsthaw(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Thaw */ if (sb->s_op->thaw_super) return sb->s_op->thaw_super(sb); return thaw_super(sb); } static int ioctl_file_dedupe_range(struct file *file, struct file_dedupe_range __user *argp) { struct file_dedupe_range *same = NULL; int ret; unsigned long size; u16 count; if (get_user(count, &argp->dest_count)) { ret = -EFAULT; goto out; } size = offsetof(struct file_dedupe_range __user, info[count]); if (size > PAGE_SIZE) { ret = -ENOMEM; goto out; } same = memdup_user(argp, size); if (IS_ERR(same)) { ret = PTR_ERR(same); same = NULL; goto out; } same->dest_count = count; ret = vfs_dedupe_file_range(file, same); if (ret) goto out; ret = copy_to_user(argp, same, size); if (ret) ret = -EFAULT; out: kfree(same); return ret; } /** * fileattr_fill_xflags - initialize fileattr with xflags * @fa: fileattr pointer * @xflags: FS_XFLAG_* flags * * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags). All * other fields are zeroed. */ void fileattr_fill_xflags(struct fileattr *fa, u32 xflags) { memset(fa, 0, sizeof(*fa)); fa->fsx_valid = true; fa->fsx_xflags = xflags; if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE) fa->flags |= FS_IMMUTABLE_FL; if (fa->fsx_xflags & FS_XFLAG_APPEND) fa->flags |= FS_APPEND_FL; if (fa->fsx_xflags & FS_XFLAG_SYNC) fa->flags |= FS_SYNC_FL; if (fa->fsx_xflags & FS_XFLAG_NOATIME) fa->flags |= FS_NOATIME_FL; if (fa->fsx_xflags & FS_XFLAG_NODUMP) fa->flags |= FS_NODUMP_FL; if (fa->fsx_xflags & FS_XFLAG_DAX) fa->flags |= FS_DAX_FL; if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) fa->flags |= FS_PROJINHERIT_FL; } EXPORT_SYMBOL(fileattr_fill_xflags); /** * fileattr_fill_flags - initialize fileattr with flags * @fa: fileattr pointer * @flags: FS_*_FL flags * * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags). * All other fields are zeroed. */ void fileattr_fill_flags(struct fileattr *fa, u32 flags) { memset(fa, 0, sizeof(*fa)); fa->flags_valid = true; fa->flags = flags; if (fa->flags & FS_SYNC_FL) fa->fsx_xflags |= FS_XFLAG_SYNC; if (fa->flags & FS_IMMUTABLE_FL) fa->fsx_xflags |= FS_XFLAG_IMMUTABLE; if (fa->flags & FS_APPEND_FL) fa->fsx_xflags |= FS_XFLAG_APPEND; if (fa->flags & FS_NODUMP_FL) fa->fsx_xflags |= FS_XFLAG_NODUMP; if (fa->flags & FS_NOATIME_FL) fa->fsx_xflags |= FS_XFLAG_NOATIME; if (fa->flags & FS_DAX_FL) fa->fsx_xflags |= FS_XFLAG_DAX; if (fa->flags & FS_PROJINHERIT_FL) fa->fsx_xflags |= FS_XFLAG_PROJINHERIT; } EXPORT_SYMBOL(fileattr_fill_flags); /** * vfs_fileattr_get - retrieve miscellaneous file attributes * @dentry: the object to retrieve from * @fa: fileattr pointer * * Call i_op->fileattr_get() callback, if exists. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); if (!inode->i_op->fileattr_get) return -ENOIOCTLCMD; return inode->i_op->fileattr_get(dentry, fa); } EXPORT_SYMBOL(vfs_fileattr_get); /** * copy_fsxattr_to_user - copy fsxattr to userspace. * @fa: fileattr pointer * @ufa: fsxattr user pointer * * Return: 0 on success, or -EFAULT on failure. */ int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; if (copy_to_user(ufa, &xfa, sizeof(xfa))) return -EFAULT; return 0; } EXPORT_SYMBOL(copy_fsxattr_to_user); static int copy_fsxattr_from_user(struct fileattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; if (copy_from_user(&xfa, ufa, sizeof(xfa))) return -EFAULT; fileattr_fill_xflags(fa, xfa.fsx_xflags); fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; return 0; } /* * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject * any invalid configurations. * * Note: must be called with inode lock held. */ static int fileattr_set_prepare(struct inode *inode, const struct fileattr *old_ma, struct fileattr *fa) { int err; /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. */ if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags); if (err) return err; /* * Project Quota ID state is only allowed to change from within the init * namespace. Enforce that restriction only if we are trying to change * the quota ID state. Everything else is allowed in user namespaces. */ if (current_user_ns() != &init_user_ns) { if (old_ma->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_ma->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } else { /* * Caller is allowed to change the project ID. If it is being * changed, make sure that the new value is valid. */ if (old_ma->fsx_projid != fa->fsx_projid && !projid_valid(make_kprojid(&init_user_ns, fa->fsx_projid))) return -EINVAL; } /* Check extent size hints. */ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; /* * It is only valid to set the DAX flag on regular files and * directories on filesystems. */ if ((fa->fsx_xflags & FS_XFLAG_DAX) && !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; /* Extent size hints of zero turn off the flags. */ if (fa->fsx_extsize == 0) fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); if (fa->fsx_cowextsize == 0) fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; return 0; } /** * vfs_fileattr_set - change miscellaneous file attributes * @mnt_userns: user namespace of the mount * @dentry: the object to change * @fa: fileattr pointer * * After verifying permissions, call i_op->fileattr_set() callback, if * exists. * * Verifying attributes involves retrieving current attributes with * i_op->fileattr_get(), this also allows initializing attributes that have * not been set by the caller to current values. Inode lock is held * thoughout to prevent racing with another instance. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fileattr old_ma = {}; int err; if (!inode->i_op->fileattr_set) return -ENOIOCTLCMD; if (!inode_owner_or_capable(mnt_userns, inode)) return -EPERM; inode_lock(inode); err = vfs_fileattr_get(dentry, &old_ma); if (!err) { /* initialize missing bits from old_ma */ if (fa->flags_valid) { fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON; fa->fsx_extsize = old_ma.fsx_extsize; fa->fsx_nextents = old_ma.fsx_nextents; fa->fsx_projid = old_ma.fsx_projid; fa->fsx_cowextsize = old_ma.fsx_cowextsize; } else { fa->flags |= old_ma.flags & ~FS_COMMON_FL; } err = fileattr_set_prepare(inode, &old_ma, fa); if (!err) err = inode->i_op->fileattr_set(mnt_userns, dentry, fa); } inode_unlock(inode); return err; } EXPORT_SYMBOL(vfs_fileattr_set); static int ioctl_getflags(struct file *file, unsigned int __user *argp) { struct fileattr fa = { .flags_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = put_user(fa.flags, argp); return err; } static int ioctl_setflags(struct file *file, unsigned int __user *argp) { struct user_namespace *mnt_userns = file_mnt_user_ns(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; unsigned int flags; int err; err = get_user(flags, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { fileattr_fill_flags(&fa, flags); err = vfs_fileattr_set(mnt_userns, dentry, &fa); mnt_drop_write_file(file); } } return err; } static int ioctl_fsgetxattr(struct file *file, void __user *argp) { struct fileattr fa = { .fsx_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = copy_fsxattr_to_user(&fa, argp); return err; } static int ioctl_fssetxattr(struct file *file, void __user *argp) { struct user_namespace *mnt_userns = file_mnt_user_ns(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; int err; err = copy_fsxattr_from_user(&fa, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { err = vfs_fileattr_set(mnt_userns, dentry, &fa); mnt_drop_write_file(file); } } return err; } /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. * * When you add any new common ioctls to the switches above and below, * please ensure they have compatible arguments in compat mode. */ static int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct inode *inode = file_inode(filp); switch (cmd) { case FIOCLEX: set_close_on_exec(fd, 1); return 0; case FIONCLEX: set_close_on_exec(fd, 0); return 0; case FIONBIO: return ioctl_fionbio(filp, argp); case FIOASYNC: return ioctl_fioasync(fd, filp, argp); case FIOQSIZE: if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { loff_t res = inode_get_bytes(inode); return copy_to_user(argp, &res, sizeof(res)) ? -EFAULT : 0; } return -ENOTTY; case FIFREEZE: return ioctl_fsfreeze(filp); case FITHAW: return ioctl_fsthaw(filp); case FS_IOC_FIEMAP: return ioctl_fiemap(filp, argp); case FIGETBSZ: /* anon_bdev filesystems may not have a block size */ if (!inode->i_sb->s_blocksize) return -EINVAL; return put_user(inode->i_sb->s_blocksize, (int __user *)argp); case FICLONE: return ioctl_file_clone(filp, arg, 0, 0, 0); case FICLONERANGE: return ioctl_file_clone_range(filp, argp); case FIDEDUPERANGE: return ioctl_file_dedupe_range(filp, argp); case FIONREAD: if (!S_ISREG(inode->i_mode)) return vfs_ioctl(filp, cmd, arg); return put_user(i_size_read(inode) - filp->f_pos, (int __user *)argp); case FS_IOC_GETFLAGS: return ioctl_getflags(filp, argp); case FS_IOC_SETFLAGS: return ioctl_setflags(filp, argp); case FS_IOC_FSGETXATTR: return ioctl_fsgetxattr(filp, argp); case FS_IOC_FSSETXATTR: return ioctl_fssetxattr(filp, argp); default: if (S_ISREG(inode->i_mode)) return file_ioctl(filp, cmd, argp); break; } return -ENOIOCTLCMD; } SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl(f.file, cmd, arg); if (error) goto out; error = do_vfs_ioctl(f.file, fd, cmd, arg); if (error == -ENOIOCTLCMD) error = vfs_ioctl(f.file, cmd, arg); out: fdput(f); return error; } #ifdef CONFIG_COMPAT /** * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation * * This is not normally called as a function, but instead set in struct * file_operations as * * .compat_ioctl = compat_ptr_ioctl, * * On most architectures, the compat_ptr_ioctl() just passes all arguments * to the corresponding ->ioctl handler. The exception is arch/s390, where * compat_ptr() clears the top bit of a 32-bit pointer value, so user space * pointers to the second 2GB alias the first 2GB, as is the case for * native 32-bit s390 user space. * * The compat_ptr_ioctl() function must therefore be used only with ioctl * functions that either ignore the argument or pass a pointer to a * compatible data type. * * If any ioctl command handled by fops->unlocked_ioctl passes a plain * integer instead of a pointer, or any of the passed data types * is incompatible between 32-bit and 64-bit architectures, a proper * handler is required instead of compat_ptr_ioctl. */ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { if (!file->f_op->unlocked_ioctl) return -ENOIOCTLCMD; return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } EXPORT_SYMBOL(compat_ptr_ioctl); COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl_compat(f.file, cmd, arg); if (error) goto out; switch (cmd) { /* FICLONE takes an int argument, so don't use compat_ptr() */ case FICLONE: error = ioctl_file_clone(f.file, arg, 0, 0, 0); break; #if defined(CONFIG_X86_64) /* these get messy on amd64 due to alignment differences */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg)); break; case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, compat_ptr(arg)); break; case FS_IOC_ZERO_RANGE_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, compat_ptr(arg)); break; #endif /* * These access 32-bit values anyway so no further handling is * necessary. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: cmd = (cmd == FS_IOC32_GETFLAGS) ? FS_IOC_GETFLAGS : FS_IOC_SETFLAGS; fallthrough; /* * everything else in do_vfs_ioctl() takes either a compatible * pointer argument or no argument -- call it with a modified * argument. */ default: error = do_vfs_ioctl(f.file, fd, cmd, (unsigned long)compat_ptr(arg)); if (error != -ENOIOCTLCMD) break; if (f.file->f_op->compat_ioctl) error = f.file->f_op->compat_ioctl(f.file, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; break; } out: fdput(f); return error; } #endif |
| 621 621 621 621 621 619 227 227 227 227 621 620 619 618 621 621 484 485 620 618 620 620 486 602 618 619 621 621 621 620 621 619 621 621 621 603 619 619 621 620 619 621 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 | // SPDX-License-Identifier: GPL-2.0-or-later /* * x86 instruction analysis * * Copyright (C) IBM Corporation, 2002, 2004, 2009 */ #include <linux/kernel.h> #ifdef __KERNEL__ #include <linux/string.h> #else #include <string.h> #endif #include <asm/inat.h> /*__ignore_sync_check__ */ #include <asm/insn.h> /* __ignore_sync_check__ */ #include <asm/unaligned.h> /* __ignore_sync_check__ */ #include <linux/errno.h> #include <linux/kconfig.h> #include <asm/emulate_prefix.h> /* __ignore_sync_check__ */ #define leXX_to_cpu(t, r) \ ({ \ __typeof__(t) v; \ switch (sizeof(t)) { \ case 4: v = le32_to_cpu(r); break; \ case 2: v = le16_to_cpu(r); break; \ case 1: v = r; break; \ default: \ BUILD_BUG(); break; \ } \ v; \ }) /* Verify next sizeof(t) bytes can be on the same instruction */ #define validate_next(t, insn, n) \ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ ({ t r = get_unaligned((t *)(insn)->next_byte); (insn)->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ ({ t r = get_unaligned((t *)(insn)->next_byte + n); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) #define peek_nbyte_next(t, insn, n) \ ({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); }) #define peek_next(t, insn) peek_nbyte_next(t, insn, 0) /** * insn_init() - initialize struct insn * @insn: &struct insn to be initialized * @kaddr: address (in kernel memory) of instruction (or copy thereof) * @buf_len: length of the insn buffer at @kaddr * @x86_64: !0 for 64-bit kernel or 64-bit app */ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) { /* * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid * even if the input buffer is long enough to hold them. */ if (buf_len > MAX_INSN_SIZE) buf_len = MAX_INSN_SIZE; memset(insn, 0, sizeof(*insn)); insn->kaddr = kaddr; insn->end_kaddr = kaddr + buf_len; insn->next_byte = kaddr; insn->x86_64 = x86_64 ? 1 : 0; insn->opnd_bytes = 4; if (x86_64) insn->addr_bytes = 8; else insn->addr_bytes = 4; } static const insn_byte_t xen_prefix[] = { __XEN_EMULATE_PREFIX }; static const insn_byte_t kvm_prefix[] = { __KVM_EMULATE_PREFIX }; static int __insn_get_emulate_prefix(struct insn *insn, const insn_byte_t *prefix, size_t len) { size_t i; for (i = 0; i < len; i++) { if (peek_nbyte_next(insn_byte_t, insn, i) != prefix[i]) goto err_out; } insn->emulate_prefix_size = len; insn->next_byte += len; return 1; err_out: return 0; } static void insn_get_emulate_prefix(struct insn *insn) { if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix))) return; __insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix)); } /** * insn_get_prefixes - scan x86 instruction prefix bytes * @insn: &struct insn containing instruction * * Populates the @insn->prefixes bitmap, and updates @insn->next_byte * to point to the (first) opcode. No effect if @insn->prefixes.got * is already set. * * * Returns: * 0: on success * < 0: on error */ int insn_get_prefixes(struct insn *insn) { struct insn_field *prefixes = &insn->prefixes; insn_attr_t attr; insn_byte_t b, lb; int i, nb; if (prefixes->got) return 0; insn_get_emulate_prefix(insn); nb = 0; lb = 0; b = peek_next(insn_byte_t, insn); attr = inat_get_opcode_attribute(b); while (inat_is_legacy_prefix(attr)) { /* Skip if same prefix */ for (i = 0; i < nb; i++) if (prefixes->bytes[i] == b) goto found; if (nb == 4) /* Invalid instruction */ break; prefixes->bytes[nb++] = b; if (inat_is_address_size_prefix(attr)) { /* address size switches 2/4 or 4/8 */ if (insn->x86_64) insn->addr_bytes ^= 12; else insn->addr_bytes ^= 6; } else if (inat_is_operand_size_prefix(attr)) { /* oprand size switches 2/4 */ insn->opnd_bytes ^= 6; } found: prefixes->nbytes++; insn->next_byte++; lb = b; b = peek_next(insn_byte_t, insn); attr = inat_get_opcode_attribute(b); } /* Set the last prefix */ if (lb && lb != insn->prefixes.bytes[3]) { if (unlikely(insn->prefixes.bytes[3])) { /* Swap the last prefix */ b = insn->prefixes.bytes[3]; for (i = 0; i < nb; i++) if (prefixes->bytes[i] == lb) insn_set_byte(prefixes, i, b); } insn_set_byte(&insn->prefixes, 3, lb); } /* Decode REX prefix */ if (insn->x86_64) { b = peek_next(insn_byte_t, insn); attr = inat_get_opcode_attribute(b); if (inat_is_rex_prefix(attr)) { insn_field_set(&insn->rex_prefix, b, 1); insn->next_byte++; if (X86_REX_W(b)) /* REX.W overrides opnd_size */ insn->opnd_bytes = 8; } } insn->rex_prefix.got = 1; /* Decode VEX prefix */ b = peek_next(insn_byte_t, insn); attr = inat_get_opcode_attribute(b); if (inat_is_vex_prefix(attr)) { insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1); if (!insn->x86_64) { /* * In 32-bits mode, if the [7:6] bits (mod bits of * ModRM) on the second byte are not 11b, it is * LDS or LES or BOUND. */ if (X86_MODRM_MOD(b2) != 3) goto vex_end; } insn_set_byte(&insn->vex_prefix, 0, b); insn_set_byte(&insn->vex_prefix, 1, b2); if (inat_is_evex_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); insn_set_byte(&insn->vex_prefix, 2, b2); b2 = peek_nbyte_next(insn_byte_t, insn, 3); insn_set_byte(&insn->vex_prefix, 3, b2); insn->vex_prefix.nbytes = 4; insn->next_byte += 4; if (insn->x86_64 && X86_VEX_W(b2)) /* VEX.W overrides opnd_size */ insn->opnd_bytes = 8; } else if (inat_is_vex3_prefix(attr)) { b2 = peek_nbyte_next(insn_byte_t, insn, 2); insn_set_byte(&insn->vex_prefix, 2, b2); insn->vex_prefix.nbytes = 3; insn->next_byte += 3; if (insn->x86_64 && X86_VEX_W(b2)) /* VEX.W overrides opnd_size */ insn->opnd_bytes = 8; } else { /* * For VEX2, fake VEX3-like byte#2. * Makes it easier to decode vex.W, vex.vvvv, * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0. */ insn_set_byte(&insn->vex_prefix, 2, b2 & 0x7f); insn->vex_prefix.nbytes = 2; insn->next_byte += 2; } } vex_end: insn->vex_prefix.got = 1; prefixes->got = 1; return 0; err_out: return -ENODATA; } /** * insn_get_opcode - collect opcode(s) * @insn: &struct insn containing instruction * * Populates @insn->opcode, updates @insn->next_byte to point past the * opcode byte(s), and set @insn->attr (except for groups). * If necessary, first collects any preceding (prefix) bytes. * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got * is already 1. * * Returns: * 0: on success * < 0: on error */ int insn_get_opcode(struct insn *insn) { struct insn_field *opcode = &insn->opcode; int pfx_id, ret; insn_byte_t op; if (opcode->got) return 0; if (!insn->prefixes.got) { ret = insn_get_prefixes(insn); if (ret) return ret; } /* Get first opcode */ op = get_next(insn_byte_t, insn); insn_set_byte(opcode, 0, op); opcode->nbytes = 1; /* Check if there is VEX prefix or not */ if (insn_is_avx(insn)) { insn_byte_t m, p; m = insn_vex_m_bits(insn); p = insn_vex_p_bits(insn); insn->attr = inat_get_avx_attribute(op, m, p); if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))) { /* This instruction is bad */ insn->attr = 0; return -EINVAL; } /* VEX has only 1 byte for opcode */ goto end; } insn->attr = inat_get_opcode_attribute(op); while (inat_is_escape(insn->attr)) { /* Get escaped opcode */ op = get_next(insn_byte_t, insn); opcode->bytes[opcode->nbytes++] = op; pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); } if (inat_must_vex(insn->attr)) { /* This instruction is bad */ insn->attr = 0; return -EINVAL; } end: opcode->got = 1; return 0; err_out: return -ENODATA; } /** * insn_get_modrm - collect ModRM byte, if any * @insn: &struct insn containing instruction * * Populates @insn->modrm and updates @insn->next_byte to point past the * ModRM byte, if any. If necessary, first collects the preceding bytes * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. * * Returns: * 0: on success * < 0: on error */ int insn_get_modrm(struct insn *insn) { struct insn_field *modrm = &insn->modrm; insn_byte_t pfx_id, mod; int ret; if (modrm->got) return 0; if (!insn->opcode.got) { ret = insn_get_opcode(insn); if (ret) return ret; } if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); insn_field_set(modrm, mod, 1); if (inat_is_group(insn->attr)) { pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_group_attribute(mod, pfx_id, insn->attr); if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) { /* Bad insn */ insn->attr = 0; return -EINVAL; } } } if (insn->x86_64 && inat_is_force64(insn->attr)) insn->opnd_bytes = 8; modrm->got = 1; return 0; err_out: return -ENODATA; } /** * insn_rip_relative() - Does instruction use RIP-relative addressing mode? * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * ModRM byte. No effect if @insn->x86_64 is 0. */ int insn_rip_relative(struct insn *insn) { struct insn_field *modrm = &insn->modrm; int ret; if (!insn->x86_64) return 0; if (!modrm->got) { ret = insn_get_modrm(insn); if (ret) return 0; } /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. */ return (modrm->nbytes && (modrm->bytes[0] & 0xc7) == 0x5); } /** * insn_get_sib() - Get the SIB byte of instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * ModRM byte. * * Returns: * 0: if decoding succeeded * < 0: otherwise. */ int insn_get_sib(struct insn *insn) { insn_byte_t modrm; int ret; if (insn->sib.got) return 0; if (!insn->modrm.got) { ret = insn_get_modrm(insn); if (ret) return ret; } if (insn->modrm.nbytes) { modrm = insn->modrm.bytes[0]; if (insn->addr_bytes != 2 && X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) { insn_field_set(&insn->sib, get_next(insn_byte_t, insn), 1); } } insn->sib.got = 1; return 0; err_out: return -ENODATA; } /** * insn_get_displacement() - Get the displacement of instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * SIB byte. * Displacement value is sign-expanded. * * * Returns: * 0: if decoding succeeded * < 0: otherwise. */ int insn_get_displacement(struct insn *insn) { insn_byte_t mod, rm, base; int ret; if (insn->displacement.got) return 0; if (!insn->sib.got) { ret = insn_get_sib(insn); if (ret) return ret; } if (insn->modrm.nbytes) { /* * Interpreting the modrm byte: * mod = 00 - no displacement fields (exceptions below) * mod = 01 - 1-byte displacement field * mod = 10 - displacement field is 4 bytes, or 2 bytes if * address size = 2 (0x67 prefix in 32-bit mode) * mod = 11 - no memory operand * * If address size = 2... * mod = 00, r/m = 110 - displacement field is 2 bytes * * If address size != 2... * mod != 11, r/m = 100 - SIB byte exists * mod = 00, SIB base = 101 - displacement field is 4 bytes * mod = 00, r/m = 101 - rip-relative addressing, displacement * field is 4 bytes */ mod = X86_MODRM_MOD(insn->modrm.value); rm = X86_MODRM_RM(insn->modrm.value); base = X86_SIB_BASE(insn->sib.value); if (mod == 3) goto out; if (mod == 1) { insn_field_set(&insn->displacement, get_next(signed char, insn), 1); } else if (insn->addr_bytes == 2) { if ((mod == 0 && rm == 6) || mod == 2) { insn_field_set(&insn->displacement, get_next(short, insn), 2); } } else { if ((mod == 0 && rm == 5) || mod == 2 || (mod == 0 && base == 5)) { insn_field_set(&insn->displacement, get_next(int, insn), 4); } } } out: insn->displacement.got = 1; return 0; err_out: return -ENODATA; } /* Decode moffset16/32/64. Return 0 if failed */ static int __get_moffset(struct insn *insn) { switch (insn->addr_bytes) { case 2: insn_field_set(&insn->moffset1, get_next(short, insn), 2); break; case 4: insn_field_set(&insn->moffset1, get_next(int, insn), 4); break; case 8: insn_field_set(&insn->moffset1, get_next(int, insn), 4); insn_field_set(&insn->moffset2, get_next(int, insn), 4); break; default: /* opnd_bytes must be modified manually */ goto err_out; } insn->moffset1.got = insn->moffset2.got = 1; return 1; err_out: return 0; } /* Decode imm v32(Iz). Return 0 if failed */ static int __get_immv32(struct insn *insn) { switch (insn->opnd_bytes) { case 2: insn_field_set(&insn->immediate, get_next(short, insn), 2); break; case 4: case 8: insn_field_set(&insn->immediate, get_next(int, insn), 4); break; default: /* opnd_bytes must be modified manually */ goto err_out; } return 1; err_out: return 0; } /* Decode imm v64(Iv/Ov), Return 0 if failed */ static int __get_immv(struct insn *insn) { switch (insn->opnd_bytes) { case 2: insn_field_set(&insn->immediate1, get_next(short, insn), 2); break; case 4: insn_field_set(&insn->immediate1, get_next(int, insn), 4); insn->immediate1.nbytes = 4; break; case 8: insn_field_set(&insn->immediate1, get_next(int, insn), 4); insn_field_set(&insn->immediate2, get_next(int, insn), 4); break; default: /* opnd_bytes must be modified manually */ goto err_out; } insn->immediate1.got = insn->immediate2.got = 1; return 1; err_out: return 0; } /* Decode ptr16:16/32(Ap) */ static int __get_immptr(struct insn *insn) { switch (insn->opnd_bytes) { case 2: insn_field_set(&insn->immediate1, get_next(short, insn), 2); break; case 4: insn_field_set(&insn->immediate1, get_next(int, insn), 4); break; case 8: /* ptr16:64 is not exist (no segment) */ return 0; default: /* opnd_bytes must be modified manually */ goto err_out; } insn_field_set(&insn->immediate2, get_next(unsigned short, insn), 2); insn->immediate1.got = insn->immediate2.got = 1; return 1; err_out: return 0; } /** * insn_get_immediate() - Get the immediate in an instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * displacement bytes. * Basically, most of immediates are sign-expanded. Unsigned-value can be * computed by bit masking with ((1 << (nbytes * 8)) - 1) * * Returns: * 0: on success * < 0: on error */ int insn_get_immediate(struct insn *insn) { int ret; if (insn->immediate.got) return 0; if (!insn->displacement.got) { ret = insn_get_displacement(insn); if (ret) return ret; } if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) goto err_out; goto done; } if (!inat_has_immediate(insn->attr)) /* no immediates */ goto done; switch (inat_immediate_size(insn->attr)) { case INAT_IMM_BYTE: insn_field_set(&insn->immediate, get_next(signed char, insn), 1); break; case INAT_IMM_WORD: insn_field_set(&insn->immediate, get_next(short, insn), 2); break; case INAT_IMM_DWORD: insn_field_set(&insn->immediate, get_next(int, insn), 4); break; case INAT_IMM_QWORD: insn_field_set(&insn->immediate1, get_next(int, insn), 4); insn_field_set(&insn->immediate2, get_next(int, insn), 4); break; case INAT_IMM_PTR: if (!__get_immptr(insn)) goto err_out; break; case INAT_IMM_VWORD32: if (!__get_immv32(insn)) goto err_out; break; case INAT_IMM_VWORD: if (!__get_immv(insn)) goto err_out; break; default: /* Here, insn must have an immediate, but failed */ goto err_out; } if (inat_has_second_immediate(insn->attr)) { insn_field_set(&insn->immediate2, get_next(signed char, insn), 1); } done: insn->immediate.got = 1; return 0; err_out: return -ENODATA; } /** * insn_get_length() - Get the length of instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * immediates bytes. * * Returns: * - 0 on success * - < 0 on error */ int insn_get_length(struct insn *insn) { int ret; if (insn->length) return 0; if (!insn->immediate.got) { ret = insn_get_immediate(insn); if (ret) return ret; } insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); return 0; } /* Ensure this instruction is decoded completely */ static inline int insn_complete(struct insn *insn) { return insn->opcode.got && insn->modrm.got && insn->sib.got && insn->displacement.got && insn->immediate.got; } /** * insn_decode() - Decode an x86 instruction * @insn: &struct insn to be initialized * @kaddr: address (in kernel memory) of instruction (or copy thereof) * @buf_len: length of the insn buffer at @kaddr * @m: insn mode, see enum insn_mode * * Returns: * 0: if decoding succeeded * < 0: otherwise. */ int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m) { int ret; /* #define INSN_MODE_KERN -1 __ignore_sync_check__ mode is only valid in the kernel */ if (m == INSN_MODE_KERN) insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64)); else insn_init(insn, kaddr, buf_len, m == INSN_MODE_64); ret = insn_get_length(insn); if (ret) return ret; if (insn_complete(insn)) return 0; return -EINVAL; } |
| 469 24 24 219 277 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | #undef TRACE_SYSTEM #define TRACE_SYSTEM neigh #if !defined(_TRACE_NEIGH_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NEIGH_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <net/neighbour.h> #define neigh_state_str(state) \ __print_symbolic(state, \ { NUD_INCOMPLETE, "incomplete" }, \ { NUD_REACHABLE, "reachable" }, \ { NUD_STALE, "stale" }, \ { NUD_DELAY, "delay" }, \ { NUD_PROBE, "probe" }, \ { NUD_FAILED, "failed" }, \ { NUD_NOARP, "noarp" }, \ { NUD_PERMANENT, "permanent"}) TRACE_EVENT(neigh_create, TP_PROTO(struct neigh_table *tbl, struct net_device *dev, const void *pkey, const struct neighbour *n, bool exempt_from_gc), TP_ARGS(tbl, dev, pkey, n, exempt_from_gc), TP_STRUCT__entry( __field(u32, family) __dynamic_array(char, dev, IFNAMSIZ ) __field(int, entries) __field(u8, created) __field(u8, gc_exempt) __array(u8, primary_key4, 4) __array(u8, primary_key6, 16) ), TP_fast_assign( __be32 *p32; __entry->family = tbl->family; __assign_str(dev, (dev ? dev->name : "NULL")); __entry->entries = atomic_read(&tbl->gc_entries); __entry->created = n != NULL; __entry->gc_exempt = exempt_from_gc; p32 = (__be32 *)__entry->primary_key4; if (tbl->family == AF_INET) *p32 = *(__be32 *)pkey; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (tbl->family == AF_INET6) { struct in6_addr *pin6; pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)pkey; } #endif ), TP_printk("family %d dev %s entries %d primary_key4 %pI4 primary_key6 %pI6c created %d gc_exempt %d", __entry->family, __get_str(dev), __entry->entries, __entry->primary_key4, __entry->primary_key6, __entry->created, __entry->gc_exempt) ); TRACE_EVENT(neigh_update, TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid), TP_ARGS(n, lladdr, new, flags, nlmsg_pid), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __array(u8, new_lladdr, MAX_ADDR_LEN) __field(u8, new_state) __field(u32, update_flags) __field(u32, pid) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev, (n->dev ? n->dev->name : "NULL")); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; if (lladdr) memcpy(__entry->new_lladdr, lladdr, lladdr_len); __entry->new_state = new; __entry->update_flags = flags; __entry->pid = nlmsg_pid; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu new_lladdr %s " "new_state %s update_flags %02x pid %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __print_hex_str(__entry->new_lladdr, __entry->lladdr_len), neigh_state_str(__entry->new_state), __entry->update_flags, __entry->pid) ); DECLARE_EVENT_CLASS(neigh__update, TP_PROTO(struct neighbour *n, int err), TP_ARGS(n, err), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __field(u32, err) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev, (n->dev ? n->dev->name : "NULL")); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; __entry->err = err; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu err %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __entry->err) ); DEFINE_EVENT(neigh__update, neigh_update_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_timer_handler, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_dead, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_cleanup_and_release, TP_PROTO(struct neighbour *neigh, int rc), TP_ARGS(neigh, rc) ); #endif /* _TRACE_NEIGH_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016, Amir Vadai <amir@vadai.me> * Copyright (c) 2016, Mellanox Technologies. All rights reserved. */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/geneve.h> #include <net/vxlan.h> #include <net/erspan.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/dst.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_tunnel_key.h> #include <net/tc_act/tc_tunnel_key.h> static unsigned int tunnel_key_net_id; static struct tc_action_ops act_tunnel_key_ops; static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; int action; params = rcu_dereference_bh(t->params); tcf_lastuse_update(&t->tcf_tm); tcf_action_update_bstats(&t->common, skb); action = READ_ONCE(t->tcf_action); switch (params->tcft_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: skb_dst_drop(skb); break; case TCA_TUNNEL_KEY_ACT_SET: skb_dst_drop(skb); skb_dst_set(skb, dst_clone(¶ms->tcft_enc_metadata->dst)); break; default: WARN_ONCE(1, "Bad tunnel_key action %d.\n", params->tcft_action); break; } return action; } static const struct nla_policy enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC] = { .strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN }, [TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, [TCA_TUNNEL_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, [TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, }; static const struct nla_policy geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, }; static const struct nla_policy vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 }, }; static const struct nla_policy erspan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, }; static int tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1]; int err, data_len, opt_len; u8 *data; err = nla_parse_nested_deprecated(tb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX, nla, geneve_opt_policy, extack); if (err < 0) return err; if (!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] || !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] || !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]) { NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data"); return -EINVAL; } data = nla_data(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); data_len = nla_len(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); if (data_len < 4) { NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long"); return -ERANGE; } if (data_len % 4) { NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long"); return -ERANGE; } opt_len = sizeof(struct geneve_opt) + data_len; if (dst) { struct geneve_opt *opt = dst; WARN_ON(dst_len < opt_len); opt->opt_class = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]); opt->type = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]); opt->length = data_len / 4; /* length is in units of 4 bytes */ opt->r1 = 0; opt->r2 = 0; opt->r3 = 0; memcpy(opt + 1, data, data_len); } return opt_len; } static int tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1]; int err; err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX, nla, vxlan_opt_policy, extack); if (err < 0) return err; if (!tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]) { NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp"); return -EINVAL; } if (dst) { struct vxlan_metadata *md = dst; md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]); md->gbp &= VXLAN_GBP_MASK; } return sizeof(struct vxlan_metadata); } static int tunnel_key_copy_erspan_opt(const struct nlattr *nla, void *dst, int dst_len, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1]; int err; u8 ver; err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX, nla, erspan_opt_policy, extack); if (err < 0) return err; if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]) { NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver"); return -EINVAL; } ver = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]); if (ver == 1) { if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]) { NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index"); return -EINVAL; } } else if (ver == 2) { if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] || !tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]) { NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid"); return -EINVAL; } } else { NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect"); return -EINVAL; } if (dst) { struct erspan_metadata *md = dst; md->version = ver; if (ver == 1) { nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]; md->u.index = nla_get_be32(nla); } else { nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR]; md->u.md2.dir = nla_get_u8(nla); nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]; set_hwid(&md->u.md2, nla_get_u8(nla)); } } return sizeof(struct erspan_metadata); } static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, int dst_len, struct netlink_ext_ack *extack) { int err, rem, opt_len, len = nla_len(nla), opts_len = 0, type = 0; const struct nlattr *attr, *head = nla_data(nla); err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX, enc_opts_policy, extack); if (err) return err; nla_for_each_attr(attr, head, len, rem) { switch (nla_type(attr)) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: if (type && type != TUNNEL_GENEVE_OPT) { NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); return -EINVAL; } opt_len = tunnel_key_copy_geneve_opt(attr, dst, dst_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; if (opts_len > IP_TUNNEL_OPTS_MAX) { NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); return -EINVAL; } if (dst) { dst_len -= opt_len; dst += opt_len; } type = TUNNEL_GENEVE_OPT; break; case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: if (type) { NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options"); return -EINVAL; } opt_len = tunnel_key_copy_vxlan_opt(attr, dst, dst_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; type = TUNNEL_VXLAN_OPT; break; case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: if (type) { NL_SET_ERR_MSG(extack, "Duplicate type for erspan options"); return -EINVAL; } opt_len = tunnel_key_copy_erspan_opt(attr, dst, dst_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; type = TUNNEL_ERSPAN_OPT; break; } } if (!opts_len) { NL_SET_ERR_MSG(extack, "Empty list of tunnel options"); return -EINVAL; } if (rem > 0) { NL_SET_ERR_MSG(extack, "Trailing data after parsing tunnel key options attributes"); return -EINVAL; } return opts_len; } static int tunnel_key_get_opts_len(struct nlattr *nla, struct netlink_ext_ack *extack) { return tunnel_key_copy_opts(nla, NULL, 0, extack); } static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, int opts_len, struct netlink_ext_ack *extack) { info->options_len = opts_len; switch (nla_type(nla_data(nla))) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: #if IS_ENABLED(CONFIG_INET) info->key.tun_flags |= TUNNEL_GENEVE_OPT; return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else return -EAFNOSUPPORT; #endif case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: #if IS_ENABLED(CONFIG_INET) info->key.tun_flags |= TUNNEL_VXLAN_OPT; return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else return -EAFNOSUPPORT; #endif case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: #if IS_ENABLED(CONFIG_INET) info->key.tun_flags |= TUNNEL_ERSPAN_OPT; return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else return -EAFNOSUPPORT; #endif default: NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type"); return -EINVAL; } } static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_PARMS] = { .len = sizeof(struct tc_tunnel_key) }, [TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_IPV4_DST] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16}, [TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED }, [TCA_TUNNEL_KEY_ENC_TOS] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 }, }; static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) { if (!p) return; if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) dst_release(&p->tcft_enc_metadata->dst); kfree_rcu(p, rcu); } static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 act_flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; struct tcf_tunnel_key_params *params_new; struct metadata_dst *metadata = NULL; struct tcf_chain *goto_ch = NULL; struct tc_tunnel_key *parm; struct tcf_tunnel_key *t; bool exists = false; __be16 dst_port = 0; __be64 key_id = 0; int opts_len = 0; __be16 flags = 0; u8 tos, ttl; int ret = 0; u32 index; int err; if (!nla) { NL_SET_ERR_MSG(extack, "Tunnel requires attributes to be passed"); return -EINVAL; } err = nla_parse_nested_deprecated(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Failed to parse nested tunnel key attributes"); return err; } if (!tb[TCA_TUNNEL_KEY_PARMS]) { NL_SET_ERR_MSG(extack, "Missing tunnel key parameters"); return -EINVAL; } parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return 0; switch (parm->t_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: break; case TCA_TUNNEL_KEY_ACT_SET: if (tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { __be32 key32; key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]); key_id = key32_to_tunnel_id(key32); flags = TUNNEL_KEY; } flags |= TUNNEL_CSUM; if (tb[TCA_TUNNEL_KEY_NO_CSUM] && nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM])) flags &= ~TUNNEL_CSUM; if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); if (tb[TCA_TUNNEL_KEY_ENC_OPTS]) { opts_len = tunnel_key_get_opts_len(tb[TCA_TUNNEL_KEY_ENC_OPTS], extack); if (opts_len < 0) { ret = opts_len; goto err_out; } } tos = 0; if (tb[TCA_TUNNEL_KEY_ENC_TOS]) tos = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TOS]); ttl = 0; if (tb[TCA_TUNNEL_KEY_ENC_TTL]) ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]); if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { __be32 saddr; __be32 daddr; saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]); daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]); metadata = __ip_tun_set_dst(saddr, daddr, tos, ttl, dst_port, flags, key_id, opts_len); } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { struct in6_addr saddr; struct in6_addr daddr; saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]); daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]); metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port, 0, flags, key_id, opts_len); } else { NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst"); ret = -EINVAL; goto err_out; } if (!metadata) { NL_SET_ERR_MSG(extack, "Cannot allocate tunnel metadata dst"); ret = -ENOMEM; goto err_out; } #ifdef CONFIG_DST_CACHE ret = dst_cache_init(&metadata->u.tun_info.dst_cache, GFP_KERNEL); if (ret) goto release_tun_meta; #endif if (opts_len) { ret = tunnel_key_opts_set(tb[TCA_TUNNEL_KEY_ENC_OPTS], &metadata->u.tun_info, opts_len, extack); if (ret < 0) goto release_tun_meta; } metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: NL_SET_ERR_MSG(extack, "Unknown tunnel key action"); ret = -EINVAL; goto err_out; } if (!exists) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_tunnel_key_ops, bind, act_flags); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); goto release_tun_meta; } ret = ACT_P_CREATED; } else if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "TC IDR already exists"); ret = -EEXIST; goto release_tun_meta; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) { ret = err; exists = true; goto release_tun_meta; } t = to_tunnel_key(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); ret = -ENOMEM; exists = true; goto put_chain; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; spin_lock_bh(&t->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params_new = rcu_replace_pointer(t->params, params_new, lockdep_is_held(&t->tcf_lock)); spin_unlock_bh(&t->tcf_lock); tunnel_key_release_params(params_new); 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_tun_meta: if (metadata) dst_release(&metadata->dst); err_out: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return ret; } static void tunnel_key_release(struct tc_action *a) { struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); tunnel_key_release_params(params); } static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { int len = info->options_len; u8 *src = (u8 *)(info + 1); struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE); if (!start) return -EMSGSIZE; while (len > 0) { struct geneve_opt *opt = (struct geneve_opt *)src; if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, opt->opt_class) || nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, opt->type) || nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, opt->length * 4, opt + 1)) { nla_nest_cancel(skb, start); return -EMSGSIZE; } len -= sizeof(struct geneve_opt) + opt->length * 4; src += sizeof(struct geneve_opt) + opt->length * 4; } nla_nest_end(skb, start); return 0; } static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1); struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN); if (!start) return -EMSGSIZE; if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) { nla_nest_cancel(skb, start); return -EMSGSIZE; } nla_nest_end(skb, start); return 0; } static int tunnel_key_erspan_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { struct erspan_metadata *md = (struct erspan_metadata *)(info + 1); struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN); if (!start) return -EMSGSIZE; if (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, md->version)) goto err; if (md->version == 1 && nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index)) goto err; if (md->version == 2 && (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR, md->u.md2.dir) || nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID, get_hwid(&md->u.md2)))) goto err; nla_nest_end(skb, start); return 0; err: nla_nest_cancel(skb, start); return -EMSGSIZE; } static int tunnel_key_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { struct nlattr *start; int err = -EINVAL; if (!info->options_len) return 0; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS); if (!start) return -EMSGSIZE; if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) goto err_out; } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { err = tunnel_key_vxlan_opts_dump(skb, info); if (err) goto err_out; } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { err = tunnel_key_erspan_opts_dump(skb, info); if (err) goto err_out; } else { err_out: nla_nest_cancel(skb, start); return err; } nla_nest_end(skb, start); return 0; } static int tunnel_key_dump_addresses(struct sk_buff *skb, const struct ip_tunnel_info *info) { unsigned short family = ip_tunnel_info_af(info); if (family == AF_INET) { __be32 saddr = info->key.u.ipv4.src; __be32 daddr = info->key.u.ipv4.dst; if (!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_SRC, saddr) && !nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_DST, daddr)) return 0; } if (family == AF_INET6) { const struct in6_addr *saddr6 = &info->key.u.ipv6.src; const struct in6_addr *daddr6 = &info->key.u.ipv6.dst; if (!nla_put_in6_addr(skb, TCA_TUNNEL_KEY_ENC_IPV6_SRC, saddr6) && !nla_put_in6_addr(skb, TCA_TUNNEL_KEY_ENC_IPV6_DST, daddr6)) return 0; } return -EINVAL; } static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; struct tc_tunnel_key opt = { .index = t->tcf_index, .refcnt = refcount_read(&t->tcf_refcnt) - ref, .bindcnt = atomic_read(&t->tcf_bindcnt) - bind, }; struct tcf_t tm; spin_lock_bh(&t->tcf_lock); params = rcu_dereference_protected(t->params, lockdep_is_held(&t->tcf_lock)); opt.action = t->tcf_action; opt.t_action = params->tcft_action; if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { struct ip_tunnel_info *info = ¶ms->tcft_enc_metadata->u.tun_info; struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); if (((key->tun_flags & TUNNEL_KEY) && nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) || tunnel_key_dump_addresses(skb, ¶ms->tcft_enc_metadata->u.tun_info) || (key->tp_dst && nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst)) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, !(key->tun_flags & TUNNEL_CSUM)) || tunnel_key_opts_dump(skb, info)) goto nla_put_failure; if (key->tos && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TOS, key->tos)) goto nla_put_failure; if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl)) goto nla_put_failure; } tcf_tm_dump(&tm, &t->tcf_tm); if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm), &tm, TCA_TUNNEL_KEY_PAD)) goto nla_put_failure; spin_unlock_bh(&t->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&t->tcf_lock); nlmsg_trim(skb, b); return -1; } static int tunnel_key_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); return tcf_generic_walker(tn, skb, cb, type, ops, extack); } static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); return tcf_idr_search(tn, a, index); } static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", .id = TCA_ID_TUNNEL_KEY, .owner = THIS_MODULE, .act = tunnel_key_act, .dump = tunnel_key_dump, .init = tunnel_key_init, .cleanup = tunnel_key_release, .walk = tunnel_key_walker, .lookup = tunnel_key_search, .size = sizeof(struct tcf_tunnel_key), }; static __net_init int tunnel_key_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); return tc_action_net_init(net, tn, &act_tunnel_key_ops); } static void __net_exit tunnel_key_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, tunnel_key_net_id); } static struct pernet_operations tunnel_key_net_ops = { .init = tunnel_key_init_net, .exit_batch = tunnel_key_exit_net, .id = &tunnel_key_net_id, .size = sizeof(struct tc_action_net), }; static int __init tunnel_key_init_module(void) { return tcf_register_action(&act_tunnel_key_ops, &tunnel_key_net_ops); } static void __exit tunnel_key_cleanup_module(void) { tcf_unregister_action(&act_tunnel_key_ops, &tunnel_key_net_ops); } module_init(tunnel_key_init_module); module_exit(tunnel_key_cleanup_module); MODULE_AUTHOR("Amir Vadai <amir@vadai.me>"); MODULE_DESCRIPTION("ip tunnel manipulation actions"); MODULE_LICENSE("GPL v2"); |
| 54 54 2 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 | // SPDX-License-Identifier: GPL-2.0-or-later /****************************************************************************** * vlanproc.c VLAN Module. /proc filesystem interface. * * This module is completely hardware-independent and provides * access to the router using Linux /proc filesystem. * * Author: Ben Greear, <greearb@candelatech.com> coppied from wanproc.c * by: Gene Kozin <genek@compuserve.com> * * Copyright: (c) 1998 Ben Greear * * ============================================================================ * Jan 20, 1998 Ben Greear Initial Version *****************************************************************************/ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include "vlanproc.h" #include "vlan.h" /****** Function Prototypes *************************************************/ /* Methods for preparing data for reading proc entries */ static int vlan_seq_show(struct seq_file *seq, void *v); static void *vlan_seq_start(struct seq_file *seq, loff_t *pos); static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos); static void vlan_seq_stop(struct seq_file *seq, void *); static int vlandev_seq_show(struct seq_file *seq, void *v); /* * Global Data */ /* * Names of the proc directory entries */ static const char name_root[] = "vlan"; static const char name_conf[] = "config"; /* * Structures for interfacing with the /proc filesystem. * VLAN creates its own directory /proc/net/vlan with the following * entries: * config device status/configuration * <device> entry for each device */ /* * Generic /proc/net/vlan/<file> file and inode operations */ static const struct seq_operations vlan_seq_ops = { .start = vlan_seq_start, .next = vlan_seq_next, .stop = vlan_seq_stop, .show = vlan_seq_show, }; /* * Proc filesystem directory entries. */ /* Strings */ static const char *const vlan_name_type_str[VLAN_NAME_TYPE_HIGHEST] = { [VLAN_NAME_TYPE_RAW_PLUS_VID] = "VLAN_NAME_TYPE_RAW_PLUS_VID", [VLAN_NAME_TYPE_PLUS_VID_NO_PAD] = "VLAN_NAME_TYPE_PLUS_VID_NO_PAD", [VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD] = "VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD", [VLAN_NAME_TYPE_PLUS_VID] = "VLAN_NAME_TYPE_PLUS_VID", }; /* * Interface functions */ /* * Clean up /proc/net/vlan entries */ void vlan_proc_cleanup(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); if (vn->proc_vlan_conf) remove_proc_entry(name_conf, vn->proc_vlan_dir); if (vn->proc_vlan_dir) remove_proc_entry(name_root, net->proc_net); /* Dynamically added entries should be cleaned up as their vlan_device * is removed, so we should not have to take care of it here... */ } /* * Create /proc/net/vlan entries */ int __net_init vlan_proc_init(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); vn->proc_vlan_dir = proc_net_mkdir(net, name_root, net->proc_net); if (!vn->proc_vlan_dir) goto err; vn->proc_vlan_conf = proc_create_net(name_conf, S_IFREG | 0600, vn->proc_vlan_dir, &vlan_seq_ops, sizeof(struct seq_net_private)); if (!vn->proc_vlan_conf) goto err; return 0; err: pr_err("can't create entry in proc filesystem!\n"); vlan_proc_cleanup(net); return -ENOBUFS; } /* * Add directory entry for VLAN device. */ int vlan_proc_add_dev(struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); struct vlan_net *vn = net_generic(dev_net(vlandev), vlan_net_id); if (!strcmp(vlandev->name, name_conf)) return -EINVAL; vlan->dent = proc_create_single_data(vlandev->name, S_IFREG | 0600, vn->proc_vlan_dir, vlandev_seq_show, vlandev); if (!vlan->dent) return -ENOBUFS; return 0; } /* * Delete directory entry for VLAN device. */ void vlan_proc_rem_dev(struct net_device *vlandev) { /** NOTE: This will consume the memory pointed to by dent, it seems. */ proc_remove(vlan_dev_priv(vlandev)->dent); vlan_dev_priv(vlandev)->dent = NULL; } /****** Proc filesystem entry points ****************************************/ /* * The following few functions build the content of /proc/net/vlan/config */ /* start read of /proc/net/vlan/config */ static void *vlan_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { struct net_device *dev; struct net *net = seq_file_net(seq); loff_t i = 1; rcu_read_lock(); if (*pos == 0) return SEQ_START_TOKEN; for_each_netdev_rcu(net, dev) { if (!is_vlan_dev(dev)) continue; if (i++ == *pos) return dev; } return NULL; } static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net_device *dev; struct net *net = seq_file_net(seq); ++*pos; dev = v; if (v == SEQ_START_TOKEN) dev = net_device_entry(&net->dev_base_head); for_each_netdev_continue_rcu(net, dev) { if (!is_vlan_dev(dev)) continue; return dev; } return NULL; } static void vlan_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { rcu_read_unlock(); } static int vlan_seq_show(struct seq_file *seq, void *v) { struct net *net = seq_file_net(seq); struct vlan_net *vn = net_generic(net, vlan_net_id); if (v == SEQ_START_TOKEN) { const char *nmtype = NULL; seq_puts(seq, "VLAN Dev name | VLAN ID\n"); if (vn->name_type < ARRAY_SIZE(vlan_name_type_str)) nmtype = vlan_name_type_str[vn->name_type]; seq_printf(seq, "Name-Type: %s\n", nmtype ? nmtype : "UNKNOWN"); } else { const struct net_device *vlandev = v; const struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); seq_printf(seq, "%-15s| %d | %s\n", vlandev->name, vlan->vlan_id, vlan->real_dev->name); } return 0; } static int vlandev_seq_show(struct seq_file *seq, void *offset) { struct net_device *vlandev = (struct net_device *) seq->private; const struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats; static const char fmt64[] = "%30s %12llu\n"; int i; if (!is_vlan_dev(vlandev)) return 0; stats = dev_get_stats(vlandev, &temp); seq_printf(seq, "%s VID: %d REORDER_HDR: %i dev->priv_flags: %hx\n", vlandev->name, vlan->vlan_id, (int)(vlan->flags & 1), vlandev->priv_flags); seq_printf(seq, fmt64, "total frames received", stats->rx_packets); seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes); seq_printf(seq, fmt64, "Broadcast/Multicast Rcvd", stats->multicast); seq_puts(seq, "\n"); seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets); seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes); seq_printf(seq, "Device: %s", vlan->real_dev->name); /* now show all PRIORITY mappings relating to this VLAN */ seq_printf(seq, "\nINGRESS priority mappings: " "0:%u 1:%u 2:%u 3:%u 4:%u 5:%u 6:%u 7:%u\n", vlan->ingress_priority_map[0], vlan->ingress_priority_map[1], vlan->ingress_priority_map[2], vlan->ingress_priority_map[3], vlan->ingress_priority_map[4], vlan->ingress_priority_map[5], vlan->ingress_priority_map[6], vlan->ingress_priority_map[7]); seq_printf(seq, " EGRESS priority mappings: "); for (i = 0; i < 16; i++) { const struct vlan_priority_tci_mapping *mp = vlan->egress_priority_map[i]; while (mp) { seq_printf(seq, "%u:%hu ", mp->priority, ((mp->vlan_qos >> 13) & 0x7)); mp = mp->next; } } seq_puts(seq, "\n"); return 0; } |
| 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ieee80211.h> #include <linux/export.h> #include <net/cfg80211.h> #include "nl80211.h" #include "core.h" #include "rdev-ops.h" int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, bool notify) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; ASSERT_WDEV_LOCK(wdev); if (!rdev->ops->stop_ap) return -EOPNOTSUPP; if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; if (!wdev->beacon_interval) return -ENOENT; err = rdev_stop_ap(rdev, dev); if (!err) { wdev->conn_owner_nlportid = 0; wdev->beacon_interval = 0; memset(&wdev->chandef, 0, sizeof(wdev->chandef)); wdev->ssid_len = 0; rdev_set_qos_map(rdev, dev, NULL); if (notify) nl80211_send_ap_stopped(wdev); /* Should we apply the grace period during beaconing interface * shutdown also? */ cfg80211_sched_dfs_chan_update(rdev); } schedule_work(&cfg80211_disconnect_work); return err; } int cfg80211_stop_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, bool notify) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; wdev_lock(wdev); err = __cfg80211_stop_ap(rdev, dev, notify); wdev_unlock(wdev); return err; } |
| 9 9 9 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/mm_inline.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PAGE_RO, SCAN_LACK_REFERENCED_PAGE, SCAN_PAGE_NULL, SCAN_SCAN_ABORT, SCAN_PAGE_COUNT, SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, SCAN_ADDRESS_RANGE, SCAN_SWAP_CACHE_PAGE, SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, }; #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> static struct task_struct *khugepaged_thread __read_mostly; static DEFINE_MUTEX(khugepaged_mutex); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; static unsigned int khugepaged_full_scans; static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; /* during fragmentation poll the hugepage allocator once every minute */ static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; static unsigned long khugepaged_sleep_expire; static DEFINE_SPINLOCK(khugepaged_mm_lock); static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); /* * default collapse hugepages if there is at least one pte mapped like * it would have happened if the vma was large enough during page * fault. */ static unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static __read_mostly DEFINE_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __read_mostly; #define MAX_PTE_MAPPED_THP 8 /** * struct mm_slot - hash lookup from mm to mm_slot * @hash: hash collision list * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head * @mm: the mm that this information is valid for * @nr_pte_mapped_thp: number of pte mapped THP * @pte_mapped_thp: address array corresponding pte mapped THP */ struct mm_slot { struct hlist_node hash; struct list_head mm_node; struct mm_struct *mm; /* pte-mapped THP in this mm */ int nr_pte_mapped_thp; unsigned long pte_mapped_thp[MAX_PTE_MAPPED_THP]; }; /** * struct khugepaged_scan - cursor for scanning * @mm_head: the head of the mm list to scan * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * * There is only the one khugepaged_scan instance of this cursor structure. */ struct khugepaged_scan { struct list_head mm_head; struct mm_slot *mm_slot; unsigned long address; }; static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; #ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs); } static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_scan_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute scan_sleep_millisecs_attr = __ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show, scan_sleep_millisecs_store); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs); } static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_alloc_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = __ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show, alloc_sleep_millisecs_store); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int pages; int err; err = kstrtouint(buf, 10, &pages); if (err || !pages) return -EINVAL; khugepaged_pages_to_scan = pages; return count; } static struct kobj_attribute pages_to_scan_attr = __ATTR(pages_to_scan, 0644, pages_to_scan_show, pages_to_scan_store); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed); } static struct kobj_attribute pages_collapsed_attr = __ATTR_RO(pages_collapsed); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_full_scans); } static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); static ssize_t khugepaged_defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static ssize_t khugepaged_defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = __ATTR(defrag, 0644, khugepaged_defrag_show, khugepaged_defrag_store); /* * max_ptes_none controls if khugepaged should collapse hugepages over * any unmapped ptes in turn potentially increasing the memory * footprint of the vmas. When max_ptes_none is 0 khugepaged will not * reduce the available free memory in the system as it * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR-1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, khugepaged_max_ptes_none_store); static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); if (err || max_ptes_swap > HPAGE_PMD_NR-1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; return count; } static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show, khugepaged_max_ptes_swap_store); static ssize_t khugepaged_max_ptes_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } static ssize_t khugepaged_max_ptes_shared_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); if (err || max_ptes_shared > HPAGE_PMD_NR-1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; return count; } static struct kobj_attribute khugepaged_max_ptes_shared_attr = __ATTR(max_ptes_shared, 0644, khugepaged_max_ptes_shared_show, khugepaged_max_ptes_shared_store); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, &khugepaged_max_ptes_swap_attr.attr, &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, NULL, }; struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { switch (advice) { case MADV_HUGEPAGE: #ifdef CONFIG_S390 /* * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 * can't handle this properly after s390_enable_sie, so we simply * ignore the madvise to prevent qemu from causing a SIGSEGV. */ if (mm_has_pgste(vma->vm_mm)) return 0; #endif *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* * If the vma become good for khugepaged to scan, * register it here without waiting a page fault that * may not happen any time soon. */ if (!(*vm_flags & VM_NO_KHUGEPAGED) && khugepaged_enter_vma_merge(vma, *vm_flags)) return -ENOMEM; break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning * this vma even if we leave the mm registered in khugepaged if * it got registered before VM_NOHUGEPAGE was set. */ break; } return 0; } int __init khugepaged_init(void) { mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", sizeof(struct mm_slot), __alignof__(struct mm_slot), 0, NULL); if (!mm_slot_cache) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } void __init khugepaged_destroy(void) { kmem_cache_destroy(mm_slot_cache); } static inline struct mm_slot *alloc_mm_slot(void) { if (!mm_slot_cache) /* initialization failed */ return NULL; return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL); } static inline void free_mm_slot(struct mm_slot *mm_slot) { kmem_cache_free(mm_slot_cache, mm_slot); } static struct mm_slot *get_mm_slot(struct mm_struct *mm) { struct mm_slot *mm_slot; hash_for_each_possible(mm_slots_hash, mm_slot, hash, (unsigned long)mm) if (mm == mm_slot->mm) return mm_slot; return NULL; } static void insert_to_mm_slots_hash(struct mm_struct *mm, struct mm_slot *mm_slot) { mm_slot->mm = mm; hash_add(mm_slots_hash, &mm_slot->hash, (long)mm); } static inline int khugepaged_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags) { if (!transhuge_vma_enabled(vma, vm_flags)) return false; if (vma->vm_file && !IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR)) return false; /* Enabled via shmem mount options or sysfs settings. */ if (shmem_file(vma->vm_file)) return shmem_huge_enabled(vma); /* THP settings require madvise. */ if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always()) return false; /* Only regular file is valid */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && (vm_flags & VM_EXEC)) { struct inode *inode = vma->vm_file->f_inode; return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } if (!vma->anon_vma || vma->vm_ops) return false; if (vma_is_temporary_stack(vma)) return false; return !(vm_flags & VM_NO_KHUGEPAGED); } int __khugepaged_enter(struct mm_struct *mm) { struct mm_slot *mm_slot; int wakeup; mm_slot = alloc_mm_slot(); if (!mm_slot) return -ENOMEM; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(khugepaged_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { free_mm_slot(mm_slot); return 0; } spin_lock(&khugepaged_mm_lock); insert_to_mm_slots_hash(mm, mm_slot); /* * Insert just behind the scanning cursor, to let the area settle * down a little. */ wakeup = list_empty(&khugepaged_scan.mm_head); list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); return 0; } int khugepaged_enter_vma_merge(struct vm_area_struct *vma, unsigned long vm_flags) { unsigned long hstart, hend; /* * khugepaged only supports read-only files for non-shmem files. * khugepaged does not yet work on special mappings. And * file-private shmem THP is not supported. */ if (!hugepage_vma_check(vma, vm_flags)) return 0; hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) return khugepaged_enter(vma, vm_flags); return 0; } void __khugepaged_exit(struct mm_struct *mm) { struct mm_slot *mm_slot; int free = 0; spin_lock(&khugepaged_mm_lock); mm_slot = get_mm_slot(mm); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&mm_slot->hash); list_del(&mm_slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); free_mm_slot(mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * khugepaged_test_exit() (which is guaranteed to run * under mmap sem read mode). Stop here (after we * return all pagetables will be destroyed) until * khugepaged has finished working on the pagetables * under the mmap_lock. */ mmap_write_lock(mm); mmap_write_unlock(mm); } } static void release_pte_page(struct page *page) { mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page), -compound_nr(page)); unlock_page(page); putback_lru_page(page); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct page *page, *tmp; while (--_pte >= pte) { pte_t pteval = *_pte; page = pte_page(pteval); if (!pte_none(pteval) && !is_zero_pfn(pte_pfn(pteval)) && !PageCompound(page)) release_pte_page(page); } list_for_each_entry_safe(page, tmp, compound_pagelist, lru) { list_del(&page->lru); release_pte_page(page); } } static bool is_refcount_suitable(struct page *page) { int expected_refcount; expected_refcount = total_mapcount(page); if (PageSwapCache(page)) expected_refcount += compound_nr(page); return page_count(page) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct list_head *compound_pagelist) { struct page *page = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = 0, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = *_pte; if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { if (!userfaultfd_armed(vma) && ++none_or_zero <= khugepaged_max_ptes_none) { continue; } else { result = SCAN_EXCEED_NONE_PTE; goto out; } } if (!pte_present(pteval)) { result = SCAN_PTE_NON_PRESENT; goto out; } if (pte_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out; } page = vm_normal_page(vma, address, pteval); if (unlikely(!page)) { result = SCAN_PAGE_NULL; goto out; } VM_BUG_ON_PAGE(!PageAnon(page), page); if (page_mapcount(page) > 1 && ++shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; goto out; } if (PageCompound(page)) { struct page *p; page = compound_head(page); /* * Check if we have dealt with the compound page * already */ list_for_each_entry(p, compound_pagelist, lru) { if (page == p) goto next; } } /* * We can do it before isolate_lru_page because the * page can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!trylock_page(page)) { result = SCAN_PAGE_LOCK; goto out; } /* * Check if the page has any GUP (or other external) pins. * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ if (!is_refcount_suitable(page)) { unlock_page(page); result = SCAN_PAGE_COUNT; goto out; } if (!pte_write(pteval) && PageSwapCache(page) && !reuse_swap_page(page, NULL)) { /* * Page is in the swap cache and cannot be re-used. * It cannot be collapsed into a THP. */ unlock_page(page); result = SCAN_SWAP_CACHE_PAGE; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (isolate_lru_page(page)) { unlock_page(page); result = SCAN_DEL_PAGE_LRU; goto out; } mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_is_file_lru(page), compound_nr(page)); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); if (PageCompound(page)) list_add_tail(&page->lru, compound_pagelist); next: /* There should be enough young pte to collapse the page */ if (pte_young(pteval) || page_is_young(page) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address)) referenced++; if (pte_write(pteval)) writable = true; } if (unlikely(!writable)) { result = SCAN_PAGE_RO; } else if (unlikely(!referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(page, none_or_zero, referenced, writable, result); return 1; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(page, none_or_zero, referenced, writable, result); return 0; } static void __collapse_huge_page_copy(pte_t *pte, struct page *page, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct page *src_page, *tmp; pte_t *_pte; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, page++, address += PAGE_SIZE) { pte_t pteval = *_pte; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, address); add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); /* * paravirt calls inside pte_clear here are * superfluous. */ pte_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); } } else { src_page = pte_page(pteval); copy_user_highpage(page, src_page, address, vma); if (!PageCompound(src_page)) release_pte_page(src_page); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside page_remove_rmap(). */ spin_lock(ptl); /* * paravirt calls inside pte_clear here are * superfluous. */ pte_clear(vma->vm_mm, address, _pte); page_remove_rmap(src_page, false); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src_page, tmp, compound_pagelist, lru) { list_del(&src_page->lru); release_pte_page(src_page); } } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); freezable_schedule_timeout_interruptible( msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } static int khugepaged_node_load[MAX_NUMNODES]; static bool khugepaged_scan_abort(int nid) { int i; /* * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ if (khugepaged_node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!khugepaged_node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; } #ifdef CONFIG_NUMA static int khugepaged_find_target_node(void) { static int last_khugepaged_target_node = NUMA_NO_NODE; int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (khugepaged_node_load[nid] > max_value) { max_value = khugepaged_node_load[nid]; target_node = nid; } /* do some balance if several nodes have the same hit record */ if (target_node <= last_khugepaged_target_node) for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES; nid++) if (max_value == khugepaged_node_load[nid]) { target_node = nid; break; } last_khugepaged_target_node = target_node; return target_node; } static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { if (IS_ERR(*hpage)) { if (!*wait) return false; *wait = false; *hpage = NULL; khugepaged_alloc_sleep(); } else if (*hpage) { put_page(*hpage); *hpage = NULL; } return true; } static struct page * khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node) { VM_BUG_ON_PAGE(*hpage, *hpage); *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); if (unlikely(!*hpage)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); *hpage = ERR_PTR(-ENOMEM); return NULL; } prep_transhuge_page(*hpage); count_vm_event(THP_COLLAPSE_ALLOC); return *hpage; } #else static int khugepaged_find_target_node(void) { return 0; } static inline struct page *alloc_khugepaged_hugepage(void) { struct page *page; page = alloc_pages(alloc_hugepage_khugepaged_gfpmask(), HPAGE_PMD_ORDER); if (page) prep_transhuge_page(page); return page; } static struct page *khugepaged_alloc_hugepage(bool *wait) { struct page *hpage; do { hpage = alloc_khugepaged_hugepage(); if (!hpage) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); if (!*wait) return NULL; *wait = false; khugepaged_alloc_sleep(); } else count_vm_event(THP_COLLAPSE_ALLOC); } while (unlikely(!hpage) && likely(khugepaged_enabled())); return hpage; } static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { /* * If the hpage allocated earlier was briefly exposed in page cache * before collapse_file() failed, it is possible that racing lookups * have not yet completed, and would then be unpleasantly surprised by * finding the hpage reused for the same mapping at a different offset. * Just release the previous allocation if there is any danger of that. */ if (*hpage && page_count(*hpage) > 1) { put_page(*hpage); *hpage = NULL; } if (!*hpage) *hpage = khugepaged_alloc_hugepage(wait); if (unlikely(!*hpage)) return false; return true; } static struct page * khugepaged_alloc_page(struct page **hpage, gfp_t gfp, int node) { VM_BUG_ON(!*hpage); return *hpage; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Return 0 if succeeds, otherwise return none-zero * value (scan code). */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, struct vm_area_struct **vmap) { struct vm_area_struct *vma; unsigned long hstart, hend; if (unlikely(khugepaged_test_exit(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (address < hstart || address + HPAGE_PMD_SIZE > hend) return SCAN_ADDRESS_RANGE; if (!hugepage_vma_check(vma, vma->vm_flags)) return SCAN_VMA_CHECK; /* Anon VMA expected */ if (!vma->anon_vma || vma->vm_ops) return SCAN_VMA_CHECK; return 0; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if khugepaged_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held, * but with mmap_lock held to protect against vma changes. */ static bool __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, int referenced) { int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, haddr), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; vmf.pte = pte_offset_map(pmd, address); vmf.orig_pte = *vmf.pte; if (!is_swap_pte(vmf.orig_pte)) { pte_unmap(vmf.pte); continue; } swapped_in++; ret = do_swap_page(&vmf); /* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */ if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); if (hugepage_vma_revalidate(mm, haddr, &vma)) { /* vma is no longer available, don't continue to swapin */ trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); return false; } /* check if the pmd is still valid */ if (mm_find_pmd(mm, haddr) != pmd) { trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); return false; } } if (ret & VM_FAULT_ERROR) { trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0); return false; } } /* Drain LRU add pagevec to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 1); return true; } static void collapse_huge_page(struct mm_struct *mm, unsigned long address, struct page **hpage, int node, int referenced, int unmapped) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct page *new_page; spinlock_t *pmd_ptl, *pte_ptl; int isolated = 0, result = 0; struct vm_area_struct *vma; struct mmu_notifier_range range; gfp_t gfp; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* Only allocate from the target node */ gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; /* * Before allocating the hugepage, release the mmap_lock read lock. * The allocation can take potentially a long time if it involves * sync compaction, and we do not need to hold the mmap_lock during * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); new_page = khugepaged_alloc_page(hpage, gfp, node); if (!new_page) { result = SCAN_ALLOC_HUGE_PAGE_FAIL; goto out_nolock; } if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, &vma); if (result) { mmap_read_unlock(mm); goto out_nolock; } pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; mmap_read_unlock(mm); goto out_nolock; } /* * __collapse_huge_page_swapin always returns with mmap_lock locked. * If it fails, we release mmap_lock and jump out_nolock. * Continuing to collapse causes inconsistency. */ if (unmapped && !__collapse_huge_page_swapin(mm, vma, address, pmd, referenced)) { mmap_read_unlock(mm); goto out_nolock; } mmap_read_unlock(mm); /* * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, &vma); if (result) goto out_up_write; /* check if the pmd is still valid */ if (mm_find_pmd(mm, address) != pmd) goto out_up_write; anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pte = pte_offset_map(pmd, address); pte_ptl = pte_lockptr(mm, pmd); pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * * Parallel fast GUP is fine since fast GUP will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); spin_lock(pte_ptl); isolated = __collapse_huge_page_isolate(vma, address, pte, &compound_pagelist); spin_unlock(pte_ptl); if (unlikely(!isolated)) { pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing * hugepmds and never for establishing regular pmds that * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); result = SCAN_FAIL; goto out_up_write; } /* * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ anon_vma_unlock_write(vma->anon_vma); __collapse_huge_page_copy(pte, new_page, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); /* * spin_lock() below is not the equivalent of smp_wmb(), but * the smp_wmb() inside __SetPageUptodate() can be reused to * avoid the copy_huge_page writes to become visible after * the set_pmd_at() write. */ __SetPageUptodate(new_page); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(new_page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); page_add_new_anon_rmap(new_page, vma, address, true); lru_cache_add_inactive_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); spin_unlock(pmd_ptl); *hpage = NULL; khugepaged_pages_collapsed++; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (!IS_ERR_OR_NULL(*hpage)) mem_cgroup_uncharge(*hpage); trace_mm_collapse_huge_page(mm, isolated, result); return; } static int khugepaged_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, struct page **hpage) { pmd_t *pmd; pte_t *pte, *_pte; int ret = 0, result = 0, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); pmd = mm_find_pmd(mm, address); if (!pmd) { result = SCAN_PMD_NULL; goto out; } memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = *_pte; if (is_swap_pte(pteval)) { if (++unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { if (!userfaultfd_armed(vma) && ++none_or_zero <= khugepaged_max_ptes_none) { continue; } else { result = SCAN_EXCEED_NONE_PTE; goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page)) { result = SCAN_PAGE_NULL; goto out_unmap; } if (page_mapcount(page) > 1 && ++shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; goto out_unmap; } page = compound_head(page); /* * Record which node the original page is from and save this * information to khugepaged_node_load[]. * Khupaged will allocate hugepage from the node has the max * hit record. */ node = page_to_nid(page); if (khugepaged_scan_abort(node)) { result = SCAN_SCAN_ABORT; goto out_unmap; } khugepaged_node_load[node]++; if (!PageLRU(page)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (PageLocked(page)) { result = SCAN_PAGE_LOCK; goto out_unmap; } if (!PageAnon(page)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check is racy it may see totmal_mapcount > refcount * in some cases. * For example, one process with one forked child process. * The parent has the PMD split due to MADV_DONTNEED, then * the child is trying unmap the whole PMD, but khugepaged * may be scanning the parent between the child has * PageDoubleMap flag cleared and dec the mapcount. So * khugepaged may see total_mapcount > refcount. * * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(page)) { result = SCAN_PAGE_COUNT; goto out_unmap; } if (pte_young(pteval) || page_is_young(page) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address)) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (!referenced || (unmapped && referenced < HPAGE_PMD_NR/2)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; ret = 1; } out_unmap: pte_unmap_unlock(pte, ptl); if (ret) { node = khugepaged_find_target_node(); /* collapse_huge_page will return with the mmap_lock released */ collapse_huge_page(mm, address, hpage, node, referenced, unmapped); } out: trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, none_or_zero, result, unmapped); return ret; } static void collect_mm_slot(struct mm_slot *mm_slot) { struct mm_struct *mm = mm_slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (khugepaged_test_exit(mm)) { /* free mm_slot */ hash_del(&mm_slot->hash); list_del(&mm_slot->mm_node); /* * Not strictly needed because the mm exited already. * * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); */ /* khugepaged_mm_lock actually not necessary for the below */ free_mm_slot(mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* * Notify khugepaged that given addr of the mm is pte-mapped THP. Then * khugepaged should try to collapse the page table. */ static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) { struct mm_slot *mm_slot; VM_BUG_ON(addr & ~HPAGE_PMD_MASK); spin_lock(&khugepaged_mm_lock); mm_slot = get_mm_slot(mm); if (likely(mm_slot && mm_slot->nr_pte_mapped_thp < MAX_PTE_MAPPED_THP)) mm_slot->pte_mapped_thp[mm_slot->nr_pte_mapped_thp++] = addr; spin_unlock(&khugepaged_mm_lock); return 0; } /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. * * @mm: process address space where collapse happens * @addr: THP collapse address * * This function checks whether all the PTEs in the PMD are pointing to the * right THP. If so, retract the page table so the THP can refault in with * as pmd-mapped. */ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) { unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = find_vma(mm, haddr); struct page *hpage; pte_t *start_pte, *pte; pmd_t *pmd, _pmd; spinlock_t *ptl; int count = 0; int i; struct mmu_notifier_range range; if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return; /* * This vm_flags may not have VM_HUGEPAGE if the page was not * collapsed by this mm. But we can still collapse if the page is * the valid THP. Add extra VM_HUGEPAGE so hugepage_vma_check() * will not fail the vma for missing VM_HUGEPAGE */ if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE)) return; hpage = find_lock_page(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (!hpage) return; if (!PageHead(hpage)) goto drop_hpage; pmd = mm_find_pmd(mm, haddr); if (!pmd) goto drop_hpage; /* * We need to lock the mapping so that from here on, only GUP-fast and * hardware page walks can access the parts of the page tables that * we're operating on. */ i_mmap_lock_write(vma->vm_file->f_mapping); /* * This spinlock should be unnecessary: Nobody else should be accessing * the page tables under spinlock protection here, only * lockless_pages_from_mm() and the hardware page walker can access page * tables while all the high-level locks are held in write mode. */ start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; /* empty pte, skip */ if (pte_none(*pte)) continue; /* page swapped out, abort */ if (!pte_present(*pte)) goto abort; page = vm_normal_page(vma, addr, *pte); /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (hpage + i != page) goto abort; count++; } /* step 2: adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; if (pte_none(*pte)) continue; page = vm_normal_page(vma, addr, *pte); page_remove_rmap(page, false); } pte_unmap_unlock(start_pte, ptl); /* step 3: set proper refcount and mm_counters. */ if (count) { page_ref_sub(hpage, count); add_mm_counter(vma->vm_mm, mm_counter_file(hpage), -count); } /* step 4: collapse pmd */ /* we make no change to anon, but protect concurrent anon page lookup */ if (vma->anon_vma) anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); _pmd = pmdp_collapse_flush(vma, haddr, pmd); mm_dec_nr_ptes(mm); tlb_remove_table_sync_one(); mmu_notifier_invalidate_range_end(&range); pte_free(mm, pmd_pgtable(_pmd)); if (vma->anon_vma) anon_vma_unlock_write(vma->anon_vma); i_mmap_unlock_write(vma->vm_file->f_mapping); drop_hpage: unlock_page(hpage); put_page(hpage); return; abort: pte_unmap_unlock(start_pte, ptl); i_mmap_unlock_write(vma->vm_file->f_mapping); goto drop_hpage; } static void khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) { struct mm_struct *mm = mm_slot->mm; int i; if (likely(mm_slot->nr_pte_mapped_thp == 0)) return; if (!mmap_write_trylock(mm)) return; if (unlikely(khugepaged_test_exit(mm))) goto out; for (i = 0; i < mm_slot->nr_pte_mapped_thp; i++) collapse_pte_mapped_thp(mm, mm_slot->pte_mapped_thp[i]); out: mm_slot->nr_pte_mapped_thp = 0; mmap_write_unlock(mm); } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, _pmd; i_mmap_lock_write(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth investing * mmap_write_lock(mm) as PMD-mapping is likely to be split * later. * * Not that vma->anon_vma check is racy: it can be set up after * the check but before we took mmap_lock by the fault path. * But page lock would prevent establishing any new ptes of the * page, so we are safe. * * An alternative would be drop the check, but check that page * table is clear before calling pmdp_collapse_flush() under * ptl. It has higher chance to recover THP for the VMA, but * has higher cost too. It would also probably require locking * the anon_vma. */ if (vma->anon_vma) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK) continue; if (vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; pmd = mm_find_pmd(mm, addr); if (!pmd) continue; /* * We need exclusive mmap_lock to retract page table. * * We use trylock due to lock inversion: we need to acquire * mmap_lock while holding page lock. Fault path does it in * reverse order. Trylock is a way to avoid deadlock. */ if (mmap_write_trylock(mm)) { if (!khugepaged_test_exit(mm)) { struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); /* assume page table is clear */ _pmd = pmdp_collapse_flush(vma, addr, pmd); mm_dec_nr_ptes(mm); tlb_remove_table_sync_one(); pte_free(mm, pmd_pgtable(_pmd)); mmu_notifier_invalidate_range_end(&range); } mmap_write_unlock(mm); } else { /* Try again later */ khugepaged_add_pte_mapped_thp(mm, addr); } } i_mmap_unlock_write(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @file: file that collapse on * @start: collapse start address * @hpage: new allocated huge page for collapse * @node: appointed node the new huge page allocate from * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache replacing old pages with the new one * + swap/gup in pages if necessary; * + fill in gaps; * + keep old pages around in case rollback is required; * - if replacing succeeds: * + copy data over; * + free old pages; * + unlock huge page; * - if replacing failed; * + put all pages back and unfreeze them; * + restore gaps in the page cache; * + unlock and free huge page; */ static void collapse_file(struct mm_struct *mm, struct file *file, pgoff_t start, struct page **hpage, int node) { struct address_space *mapping = file->f_mapping; gfp_t gfp; struct page *new_page; pgoff_t index, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); int nr; VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); /* Only allocate from the target node */ gfp = alloc_hugepage_khugepaged_gfpmask() | __GFP_THISNODE; new_page = khugepaged_alloc_page(hpage, gfp, node); if (!new_page) { result = SCAN_ALLOC_HUGE_PAGE_FAIL; goto out; } if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); /* This will be less messy when we use multi-index entries */ do { xas_lock_irq(&xas); xas_create_range(&xas); if (!xas_error(&xas)) break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; goto out; } } while (1); __SetPageLocked(new_page); if (is_shmem) __SetPageSwapBacked(new_page); new_page->index = start; new_page->mapping = mapping; /* * At this point the new_page is locked and not up-to-date. * It's safe to insert it into the page cache, because nobody would * be able to map it or use it in another way until we unlock it. */ xas_set(&xas, start); for (index = start; index < end; index++) { struct page *page = xas_next(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!page) { /* * Stop if extent has been truncated or * hole-punched, and is now completely * empty. */ if (index == start) { if (!xas_next_entry(&xas, end - 1)) { result = SCAN_TRUNCATED; goto xa_locked; } xas_set(&xas, index); } if (!shmem_charge(mapping->host, 1)) { result = SCAN_FAIL; goto xa_locked; } xas_store(&xas, new_page); nr_none++; continue; } if (xa_is_value(page) || !PageUptodate(page)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_getpage(mapping->host, index, &page, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!page || xa_is_value(page)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain pagevecs to help isolate_lru_page() */ lru_add_drain(); page = find_lock_page(mapping, index); if (unlikely(page == NULL)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (PageDirty(page)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * * Trigger async flush here and hope the * writeback is done when khugepaged * revisits this page. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; } else if (PageWriteback(page)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The page must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_PAGE(!PageLocked(page), page); /* make sure the page is up to date */ if (unlikely(!PageUptodate(page))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first page, then a THP might be there already. */ if (PageTransCompound(page)) { result = SCAN_PAGE_COMPOUND; goto out_unlock; } if (page_mapping(page) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (PageDirty(page) || PageWriteback(page))) { /* * khugepaged only works on read-only fd, so this * page is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; putback_lru_page(page); goto out_unlock; } if (page_mapped(page)) unmap_mapping_pages(mapping, index, 1, false); xas_lock_irq(&xas); xas_set(&xas, index); VM_BUG_ON_PAGE(page != xas_load(&xas), page); VM_BUG_ON_PAGE(page_mapped(page), page); /* * The page is expected to have page_count() == 3: * - we hold a pin on it; * - one reference from page cache; * - one from isolate_lru_page; */ if (!page_ref_freeze(page, 3)) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); putback_lru_page(page); goto out_unlock; } /* * Add the page to the list to be able to undo the collapse if * something go wrong. */ list_add_tail(&page->lru, &pagelist); /* Finally, replace with the new page. */ xas_store(&xas, new_page); continue; out_unlock: unlock_page(page); put_page(page); goto xa_unlocked; } nr = thp_nr_pages(new_page); if (is_shmem) __mod_lruvec_page_state(new_page, NR_SHMEM_THPS, nr); else { __mod_lruvec_page_state(new_page, NR_FILE_THPS, nr); filemap_nr_thps_inc(mapping); /* * Paired with smp_mb() in do_dentry_open() to ensure * i_writecount is up to date and the update to nr_thps is * visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; __mod_lruvec_page_state(new_page, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); goto xa_locked; } } if (nr_none) { __mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none); if (is_shmem) __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); } xa_locked: xas_unlock_irq(&xas); xa_unlocked: if (result == SCAN_SUCCEED) { struct page *page, *tmp; /* * Replacing old pages with new one has succeeded, now we * need to copy the content and free the old pages. */ index = start; list_for_each_entry_safe(page, tmp, &pagelist, lru) { while (index < page->index) { clear_highpage(new_page + (index % HPAGE_PMD_NR)); index++; } copy_highpage(new_page + (page->index % HPAGE_PMD_NR), page); list_del(&page->lru); page->mapping = NULL; page_ref_unfreeze(page, 1); ClearPageActive(page); ClearPageUnevictable(page); unlock_page(page); put_page(page); index++; } while (index < end) { clear_highpage(new_page + (index % HPAGE_PMD_NR)); index++; } SetPageUptodate(new_page); page_ref_add(new_page, HPAGE_PMD_NR - 1); if (is_shmem) set_page_dirty(new_page); lru_cache_add(new_page); /* * Remove pte page tables, so we can re-fault the page as huge. */ retract_page_tables(mapping, start); *hpage = NULL; khugepaged_pages_collapsed++; } else { struct page *page; /* Something went wrong: roll back page cache changes */ xas_lock_irq(&xas); mapping->nrpages -= nr_none; if (is_shmem) shmem_uncharge(mapping->host, nr_none); xas_set(&xas, start); xas_for_each(&xas, page, end - 1) { page = list_first_entry_or_null(&pagelist, struct page, lru); if (!page || xas.xa_index < page->index) { if (!nr_none) break; nr_none--; /* Put holes back where they were */ xas_store(&xas, NULL); continue; } VM_BUG_ON_PAGE(page->index != xas.xa_index, page); /* Unfreeze the page. */ list_del(&page->lru); page_ref_unfreeze(page, 2); xas_store(&xas, page); xas_pause(&xas); xas_unlock_irq(&xas); unlock_page(page); putback_lru_page(page); xas_lock_irq(&xas); } VM_BUG_ON(nr_none); xas_unlock_irq(&xas); new_page->mapping = NULL; } unlock_page(new_page); out: VM_BUG_ON(!list_empty(&pagelist)); if (!IS_ERR_OR_NULL(*hpage)) mem_cgroup_uncharge(*hpage); /* TODO: tracepoints */ } static void khugepaged_scan_file(struct mm_struct *mm, struct file *file, pgoff_t start, struct page **hpage) { struct page *page = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; present = 0; swap = 0; memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); rcu_read_lock(); xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) { if (++swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; break; } continue; } if (PageTransCompound(page)) { result = SCAN_PAGE_COMPOUND; break; } node = page_to_nid(page); if (khugepaged_scan_abort(node)) { result = SCAN_SCAN_ABORT; break; } khugepaged_node_load[node]++; if (!PageLRU(page)) { result = SCAN_PAGE_LRU; break; } if (page_count(page) != 1 + page_mapcount(page) + page_has_private(page)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the page is referenced here, but * nobody would transfer pte_young() to PageReferenced() for us. * And rmap walk here is just too costly... */ present++; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; } else { node = khugepaged_find_target_node(); collapse_file(mm, file, start, hpage, node); } } /* TODO: tracepoints */ } #else static void khugepaged_scan_file(struct mm_struct *mm, struct file *file, pgoff_t start, struct page **hpage) { BUILD_BUG(); } static void khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot) { } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, struct page **hpage) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct mm_slot *mm_slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); if (khugepaged_scan.mm_slot) mm_slot = khugepaged_scan.mm_slot; else { mm_slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); khugepaged_collapse_pte_mapped_thps(mm_slot); mm = mm_slot->mm; /* * Don't wait for semaphore (to avoid long wait times). Just move to * the next mm on the list. */ vma = NULL; if (unlikely(!mmap_read_trylock(mm))) goto breakouterloop_mmap_lock; if (likely(!khugepaged_test_exit(mm))) vma = find_vma(mm, khugepaged_scan.address); progress++; for (; vma; vma = vma->vm_next) { unsigned long hstart, hend; cond_resched(); if (unlikely(khugepaged_test_exit(mm))) { progress++; break; } if (!hugepage_vma_check(vma, vma->vm_flags)) { skip: progress++; continue; } hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart >= hend) goto skip; if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); if (shmem_file(vma->vm_file) && !shmem_huge_enabled(vma)) goto skip; while (khugepaged_scan.address < hend) { int ret; cond_resched(); if (unlikely(khugepaged_test_exit(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); mmap_read_unlock(mm); ret = 1; khugepaged_scan_file(mm, file, pgoff, hpage); fput(file); } else { ret = khugepaged_scan_pmd(mm, vma, khugepaged_scan.address, hpage); } /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (ret) /* we released mmap_lock so break loop */ goto breakouterloop_mmap_lock; if (progress >= pages) goto breakouterloop; } } breakouterloop: mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ breakouterloop_mmap_lock: spin_lock(&khugepaged_mm_lock); VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ if (khugepaged_test_exit(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find * mm_slot not pointing to the exiting mm. */ if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) { khugepaged_scan.mm_slot = list_entry( mm_slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.address = 0; } else { khugepaged_scan.mm_slot = NULL; khugepaged_full_scans++; } collect_mm_slot(mm_slot); } return progress; } static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && khugepaged_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(void) { struct page *hpage = NULL; unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; lru_add_drain_all(); while (progress < pages) { if (!khugepaged_prealloc_page(&hpage, &wait)) break; cond_resched(); if (unlikely(kthread_should_stop() || try_to_freeze())) break; spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) progress += khugepaged_scan_mm_slot(pages - progress, &hpage); else progress = pages; spin_unlock(&khugepaged_mm_lock); } if (!IS_ERR_OR_NULL(hpage)) put_page(hpage); } static bool khugepaged_should_wakeup(void) { return kthread_should_stop() || time_after_eq(jiffies, khugepaged_sleep_expire); } static void khugepaged_wait_work(void) { if (khugepaged_has_work()) { const unsigned long scan_sleep_jiffies = msecs_to_jiffies(khugepaged_scan_sleep_millisecs); if (!scan_sleep_jiffies) return; khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; wait_event_freezable_timeout(khugepaged_wait, khugepaged_should_wakeup(), scan_sleep_jiffies); return; } if (khugepaged_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(); khugepaged_wait_work(); } spin_lock(&khugepaged_mm_lock); mm_slot = khugepaged_scan.mm_slot; khugepaged_scan.mm_slot = NULL; if (mm_slot) collect_mm_slot(mm_slot); spin_unlock(&khugepaged_mm_lock); return 0; } static void set_recommended_min_free_kbytes(void) { struct zone *zone; int nr_zones = 0; unsigned long recommended_min; for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of * ZONE_MOVABLE since it only has movable pages. */ if (zone_idx(zone) > gfp_zone(GFP_USER)) continue; nr_zones++; } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; /* * Make sure that on average at least two pageblocks are almost free * of another type, one for a migratetype to fall back to and a * second to avoid subsequent fallbacks of other types There are 3 * MIGRATE_TYPES we care about. */ recommended_min += pageblock_nr_pages * nr_zones * MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; /* don't ever allow to reserve more than 5% of the lowmem */ recommended_min = min(recommended_min, (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); if (recommended_min > min_free_kbytes) { if (user_min_free_kbytes >= 0) pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", min_free_kbytes, recommended_min); min_free_kbytes = recommended_min; } setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (khugepaged_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (IS_ERR(khugepaged_thread)) { pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); set_recommended_min_free_kbytes(); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (khugepaged_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } |
| 14 418 420 419 91 16 404 265 403 403 288 401 2 403 403 403 400 404 404 16 1 403 403 17 64 356 400 401 53 53 53 53 59 58 3 6 50 50 56 56 3 59 359 358 360 149 149 149 149 61 85 18 18 3 15 87 148 148 147 148 148 148 148 3 90 56 55 56 56 56 65 56 9 24 24 22 16 32 32 32 23 9 32 32 56 56 56 23 33 33 24 28 4 24 19 24 21 6 19 4 32 32 1 165 29 5 141 225 224 226 226 226 3 104 45 114 224 223 217 36 197 36 27 201 204 17 185 3 82 136 201 3 201 200 192 16 133 80 26 8 6 1 26 26 24 24 25 131 92 8 8 197 198 119 81 81 198 138 5 41 106 134 212 1 211 209 160 34 35 136 77 2 79 131 211 211 135 77 211 194 35 208 209 203 5 110 1 110 23 20 20 111 3 3 105 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * The Internet Protocol (IP) output module. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <Alan.Cox@linux.org> * Richard Underwood * Stefan Becker, <stefanb@yello.ping.de> * Jorge Cwik, <jorge@laser.satlink.net> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Hirokazu Takahashi, <taka@valinux.co.jp> * * See ip_input.c for original log * * Fixes: * Alan Cox : Missing nonblock feature in ip_build_xmit. * Mike Kilburn : htons() missing in ip_build_xmit. * Bradford Johnson: Fix faulty handling of some frames when * no route is found. * Alexander Demenshin: Missing sk/skb free in ip_queue_xmit * (in case if packet not accepted by * output firewall rules) * Mike McLagan : Routing by source * Alexey Kuznetsov: use new route cache * Andi Kleen: Fix broken PMTU recovery and remove * some redundant tests. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Andi Kleen : Replace ip_reply with ip_send_reply. * Andi Kleen : Split fast and slow ip_build_xmit path * for decreased register pressure on x86 * and more readability. * Marc Boucher : When call_out_firewall returns FW_QUEUE, * silently drop skb instead of failing with -EPERM. * Detlev Wengorz : Copy protocol for fragments. * Hirokazu Takahashi: HW checksumming for outgoing UDP * datagrams. * Hirokazu Takahashi: sendfile() on UDP works now. */ #include <linux/uaccess.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/init.h> #include <net/snmp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/xfrm.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/arp.h> #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> #include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> #include <linux/netlink.h> #include <linux/tcp.h> static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)); /* Generate a checksum for an outgoing IP datagram. */ void ip_send_check(struct iphdr *iph) { iph->check = 0; iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } EXPORT_SYMBOL(ip_send_check); int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = htons(skb->len); ip_send_check(iph); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip_out(sk, skb); if (unlikely(!skb)) return 0; skb->protocol = htons(ETH_P_IP); return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); } int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { int err; err = __ip_local_out(net, sk, skb); if (likely(err == 1)) err = dst_output(net, sk, skb); return err; } EXPORT_SYMBOL_GPL(ip_local_out); static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) { int ttl = inet->uc_ttl; if (ttl < 0) ttl = ip4_dst_hoplimit(dst); return ttl; } /* * Add an ip header to a skbuff and send it out. * */ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt, u8 tos) { struct inet_sock *inet = inet_sk(sk); struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct iphdr *iph; /* Build the IP header. */ skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = tos; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; /* Do not bother generating IPID for small packets (eg SYNACK) */ if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; /* TCP packets here are SYNACK with fat IPv4/TCP options. * Avoid using the hashed IP ident generator. */ if (sk->sk_protocol == IPPROTO_TCP) iph->id = (__force __be16)prandom_u32(); else __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; ip_options_build(skb, &opt->opt, daddr, rt, 0); } skb->priority = sk->sk_priority; if (!skb->mark) skb->mark = sk->sk_mark; /* Send it out. */ return ip_local_out(net, skb->sk, skb); } EXPORT_SYMBOL_GPL(ip_build_and_send_pkt); static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); if (res != LWTUNNEL_XMIT_CONTINUE) return res; } rcu_read_lock_bh(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { int res; sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ res = neigh_output(neigh, skb, is_v6gw); rcu_read_unlock_bh(); return res; } rcu_read_unlock_bh(); net_dbg_ratelimited("%s: No header cache and no neighbour!\n", __func__); kfree_skb(skb); return -EINVAL; } static int ip_finish_output_gso(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; /* common case: seglen is <= mtu */ if (skb_gso_validate_network_len(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length exceeds the egress MTU. * * This can happen in several cases: * - Forwarding of a TCP GRO skb, when DF flag is not set. * - Forwarding of an skb that arrived on a virtualization interface * (virtio-net/vhost/tap) with TSO/GSO size set by other network * stack. * - Local GSO skb transmitted on an NETIF_F_TSO tunnel stacked over an * interface with a smaller MTU. * - Arriving GRO skb (or GSO skb in a virtualized environment) that is * bridged to a NETIF_F_TSO tunnel stacked over an interface with an * insufficient MTU. */ features = netif_skb_features(skb); BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET); 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); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) ret = err; } return ret; } static int __ip_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) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(net, sk, skb); } #endif mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); } static int ip_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: return __ip_finish_output(net, sk, skb); case NET_XMIT_CN: return __ip_finish_output(net, sk, skb) ? : ret; default: kfree_skb(skb); return ret; } } static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *new_rt; bool do_cn = false; int ret, err; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); switch (ret) { case NET_XMIT_CN: do_cn = true; fallthrough; case NET_XMIT_SUCCESS: break; default: kfree_skb(skb); return ret; } /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten, * see ipv4_pktinfo_prepare(). */ new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb)); if (new_rt) { new_rt->rt_iif = 0; skb_dst_drop(skb); skb_dst_set(skb, &new_rt->dst); } err = dev_loopback_xmit(net, sk, skb); return (do_cn && err) ? ret : err; } int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; /* * If the indicated interface is up and running, send the packet. */ IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); /* * Multicasts are looped back for other local users */ if (rt->rt_flags&RTCF_MULTICAST) { if (sk_mc_loop(sk) #ifdef CONFIG_IP_MROUTE /* Small optimization: do not loopback not local frames, which returned after forwarding; they will be dropped by ip_mr_input in any case. Note, that local frames are looped back to be delivered to local recipients. This check is duplicated in ip_mr_input at the moment. */ && ((rt->rt_flags & RTCF_LOCAL) || !(IPCB(skb)->flags & IPSKB_FORWARDED)) #endif ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } /* Multicasts with ttl 0 must not go beyond the host */ if (ip_hdr(skb)->ttl == 0) { kfree_skb(skb); return 0; } } if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, newskb, NULL, newskb->dev, ip_mc_finish_output); } return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, skb->dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev, *indev = 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, indev, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } EXPORT_SYMBOL(ip_output); /* * copy saddr and daddr, possibly using 64bit load/stores * Equivalent to : * iph->saddr = fl4->saddr; * iph->daddr = fl4->daddr; */ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); iph->saddr = fl4->saddr; iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, __u8 tos) { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options_rcu *inet_opt; struct flowi4 *fl4; struct rtable *rt; struct iphdr *iph; int res; /* Skip all of this if the packet is already routed, * f.e. by something like SCTP. */ rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); fl4 = &fl->u.ip4; rt = skb_rtable(skb); if (rt) goto packet_routed; /* Make sure we can route this packet. */ rt = (struct rtable *)__sk_dst_check(sk, 0); if (!rt) { __be32 daddr; /* Use correct destination address if we have options. */ daddr = inet->inet_daddr; if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. */ rt = ip_route_output_ports(net, fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, RT_CONN_FLAGS_TOS(sk, tos), sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; sk_setup_caps(sk, &rt->dst); } skb_dst_set_noref(skb, &rt->dst); packet_routed: if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0)); skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff)); if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); /* Transport layer set skb->h.foo itself. */ if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } ip_select_ident_segs(net, skb, sk, skb_shinfo(skb)->gso_segs ?: 1); /* TODO : should we use skb->sk here instead of sk ? */ skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; res = ip_local_out(net, sk, skb); rcu_read_unlock(); return res; no_route: rcu_read_unlock(); IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EHOSTUNREACH; } EXPORT_SYMBOL(__ip_queue_xmit); int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) { return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos); } EXPORT_SYMBOL(ip_queue_xmit); static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) { to->pkt_type = from->pkt_type; to->priority = from->priority; to->protocol = from->protocol; to->skb_iif = from->skb_iif; skb_dst_drop(to); skb_dst_copy(to, 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); #if IS_ENABLED(CONFIG_IP_VS) to->ipvs_property = from->ipvs_property; #endif skb_copy_secmark(to, from); } static int ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph = ip_hdr(skb); if ((iph->frag_off & htons(IP_DF)) == 0) return ip_do_fragment(net, sk, skb, output); if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); kfree_skb(skb); return -EMSGSIZE; } return ip_do_fragment(net, sk, skb, output); } void ip_fraglist_init(struct sk_buff *skb, struct iphdr *iph, unsigned int hlen, struct ip_fraglist_iter *iter) { unsigned int first_len = skb_pagelen(skb); iter->frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); iter->offset = 0; iter->iph = iph; iter->hlen = hlen; skb->data_len = first_len - skb_headlen(skb); skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_init); void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) { unsigned int hlen = iter->hlen; struct iphdr *iph = iter->iph; struct sk_buff *frag; frag = iter->frag; frag->ip_summed = CHECKSUM_NONE; skb_reset_transport_header(frag); __skb_push(frag, hlen); skb_reset_network_header(frag); memcpy(skb_network_header(frag), iph, hlen); iter->iph = ip_hdr(frag); iph = iter->iph; iph->tot_len = htons(frag->len); ip_copy_metadata(frag, skb); iter->offset += skb->len - hlen; iph->frag_off = htons(iter->offset >> 3); if (frag->next) iph->frag_off |= htons(IP_MF); /* Ready, complete checksum */ ip_send_check(iph); } EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; state->left = skb->len - hlen; /* Space per frame */ state->ptr = hlen; /* Where to start from */ state->offset = (ntohs(iph->frag_off) & IP_OFFSET) << 3; state->not_last_frag = iph->frag_off & htons(IP_MF); } EXPORT_SYMBOL(ip_frag_init); static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, bool first_frag) { /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE * on the initial skb, so that all the following fragments * will inherit fixed options. */ if (first_frag) ip_options_fragment(from); } struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) { unsigned int len = state->left; struct sk_buff *skb2; struct iphdr *iph; 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 */ skb2 = alloc_skb(len + state->hlen + state->ll_rs, GFP_ATOMIC); if (!skb2) return ERR_PTR(-ENOMEM); /* * Set up data on packet */ ip_copy_metadata(skb2, skb); skb_reserve(skb2, state->ll_rs); skb_put(skb2, len + state->hlen); skb_reset_network_header(skb2); skb2->transport_header = skb2->network_header + state->hlen; /* * Charge the memory for the fragment to any owner * it might possess */ if (skb->sk) skb_set_owner_w(skb2, skb->sk); /* * Copy the packet header into the new buffer. */ skb_copy_from_linear_data(skb, skb_network_header(skb2), state->hlen); /* * Copy a block of the IP datagram. */ if (skb_copy_bits(skb, state->ptr, skb_transport_header(skb2), len)) BUG(); state->left -= len; /* * Fill in the new header fields. */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); if (state->DF) iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the * last fragment then keep MF on each bit */ if (state->left > 0 || state->not_last_frag) iph->frag_off |= htons(IP_MF); state->ptr += len; state->offset += len; iph->tot_len = htons(len + state->hlen); ip_send_check(iph); return skb2; } EXPORT_SYMBOL(ip_frag_next); /* * This IP datagram is too large to be sent in one piece. Break it up into * smaller pieces (each of size equal to IP header plus * a block of the data of the original IP data part) that will yet fit in a * single device frame, and queue such a frame for sending. */ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { struct iphdr *iph; struct sk_buff *skb2; struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ if (skb->ip_summed == CHECKSUM_PARTIAL && (err = skb_checksum_help(skb))) goto fail; /* * Point into the IP datagram header. */ iph = ip_hdr(skb); mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; /* * Setup starting values. */ hlen = iph->ihl * 4; mtu = mtu - hlen; /* Size of data space */ IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE; ll_rs = LL_RESERVED_SPACE(rt->dst.dev); /* When frag_list is given, use it. First, check its validity: * some transformers could create wrong frag_list or break existing * one, it is not prohibited. In this case fall back to copying. * * LATER: this step can be merged to real generation of fragments, * we can switch to copy when see the first bad fragment. */ if (skb_has_frag_list(skb)) { struct sk_buff *frag, *frag2; unsigned int first_len = skb_pagelen(skb); if (first_len - hlen > mtu || ((first_len - hlen) & 7) || ip_is_fragment(iph) || skb_cloned(skb) || skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { /* Correct geometry. */ if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen + ll_rs) 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; } /* Everything is OK. Generate! */ ip_fraglist_init(skb, iph, hlen, &iter); for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { bool first_frag = (iter.offset == 0); IPCB(iter.frag)->flags = IPCB(skb)->flags; ip_fraglist_prepare(skb, &iter); if (first_frag && IPCB(skb)->opt.optlen) { /* ipcb->opt is not populated for frags * coming from __ip_make_skb(), * ip_options_fragment() needs optlen */ IPCB(iter.frag)->opt.optlen = IPCB(skb)->opt.optlen; ip_options_fragment(iter.frag); ip_send_check(iter.iph); } } skb->tstamp = tstamp; err = output(net, sk, skb); if (!err) IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); if (err || !iter.frag) break; skb = ip_fraglist_next(&iter); } if (err == 0) { IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return 0; } kfree_skb_list(iter.frag); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); 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. */ ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, &state); /* * Keep copying data until we run out. */ while (state.left > 0) { bool first_frag = (state.offset == 0); skb2 = ip_frag_next(skb, &state); if (IS_ERR(skb2)) { err = PTR_ERR(skb2); goto fail; } ip_frag_ipcb(skb, skb2, first_frag); /* * Put this fragment into the sending queue. */ skb2->tstamp = tstamp; err = output(net, sk, skb2); if (err) goto fail; IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); } consume_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return err; fail: kfree_skb(skb); IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; } EXPORT_SYMBOL(ip_do_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct msghdr *msg = from; if (skb->ip_summed == CHECKSUM_PARTIAL) { if (!copy_from_iter_full(to, len, &msg->msg_iter)) return -EFAULT; } else { __wsum csum = 0; if (!csum_and_copy_from_iter_full(to, len, &csum, &msg->msg_iter)) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, odd); } return 0; } EXPORT_SYMBOL(ip_generic_getfrag); static inline __wsum csum_page(struct page *page, int offset, int copy) { char *kaddr; __wsum csum; kaddr = kmap(page); csum = csum_partial(kaddr + offset, copy, 0); kunmap(page); return csum; } static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; int mtu; int copy; int err; int offset = 0; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; unsigned int wmem_alloc_delta = 0; bool paged, extra_uref = false; u32 tskey = 0; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; if (cork->tx_flags & SKBTX_ANY_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } /* * transhdrlen > 0 means that this is the first fragment and we wish * it won't be fragmented in the future. */ if (transhdrlen && length + fragheaderlen <= mtu && rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && (!(flags & MSG_MORE) || cork->gso_size) && (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; if (flags & MSG_ZEROCOPY && length && 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; } else { uarg->zerocopy = 0; skb_zcopy_set(skb, uarg, &extra_uref); } } cork->length += length; /* So, what's going on in the loop below? * * We use calculated fragment length to generate chained skb, * each of segments is IP fragment ready for sending to network after * adding appropriate IP header. */ if (!skb) goto alloc_new_skb; while (length > 0) { /* Check if the remaining data fits into current packet. */ copy = mtu - 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; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; if (skb_prev) fraggap = skb_prev->len - maxfraglen; else fraggap = 0; /* * If remaining data exceeds the mtu, * we know we need more fragment(s). */ datalen = length + fraggap; if (datalen > mtu - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; pagedlen = 0; alloc_extra = hh_len + 15; alloc_extra += exthdrlen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ if (datalen == length + fraggap) alloc_extra += rt->dst.trailer_len; 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 = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; } alloclen += alloc_extra; 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->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ data = skb_put(skb, fraglen + exthdrlen - pagedlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); data += fragheaderlen + exthdrlen; 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); } copy = datalen - transhdrlen - fraggap - pagedlen; if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); goto error; } offset += copy; length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; csummode = CHECKSUM_NONE; /* 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 (!uarg || !uarg->zerocopy) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; 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; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return err; } static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, struct ipcm_cookie *ipc, struct rtable **rtp) { struct ip_options_rcu *opt; struct rtable *rt; rt = *rtp; if (unlikely(!rt)) return -EFAULT; cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); if (!inetdev_valid_mtu(cork->fragsize)) return -ENETUNREACH; /* * setup for corking. */ opt = ipc->opt; if (opt) { if (!cork->opt) { cork->opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation); if (unlikely(!cork->opt)) return -ENOBUFS; } memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); cork->flags |= IPCORK_OPT; cork->addr = ipc->addr; } cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; /* We stole this route, caller should not release it. */ *rtp = NULL; cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; cork->mark = ipc->sockc.mark; cork->priority = ipc->priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags); return 0; } /* * ip_append_data() and ip_append_page() can make one large IP datagram * from many pieces of data. Each pieces will be holded on the socket * until ip_push_pending_frames() is called. Each piece can be a page * or non-page data. * * Not only UDP, other transport protocols - e.g. raw sockets - can use * this interface potentially. * * LATER: length must be adjusted by pad at tail, when it is required. */ int ip_append_data(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); int err; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) { err = ip_setup_cork(sk, &inet->cork.base, ipc, rtp); if (err) return err; } else { transhdrlen = 0; } return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags); } ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, int offset, size_t size, int flags) { struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; struct rtable *rt; struct ip_options *opt = NULL; struct inet_cork *cork; int hh_len; int mtu; int len; int err; unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize; if (inet->hdrincl) return -EPERM; if (flags&MSG_PROBE) return 0; if (skb_queue_empty(&sk->sk_write_queue)) return -EINVAL; cork = &inet->cork.base; rt = (struct rtable *)cork->dst; if (cork->flags & IPCORK_OPT) opt = cork->opt; if (!(rt->dst.dev->features & NETIF_F_SG)) return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu; if (cork->length + size > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu - (opt ? opt->optlen : 0)); return -EMSGSIZE; } skb = skb_peek_tail(&sk->sk_write_queue); if (!skb) return -EINVAL; cork->length += size; while (size > 0) { /* Check if the remaining data fits into current packet. */ len = mtu - skb->len; if (len < size) len = maxfraglen - skb->len; if (len <= 0) { struct sk_buff *skb_prev; int alloclen; skb_prev = skb; fraggap = skb_prev->len - maxfraglen; alloclen = fragheaderlen + hh_len + fraggap + 15; skb = sock_wmalloc(sk, alloclen, 1, sk->sk_allocation); if (unlikely(!skb)) { err = -ENOBUFS; goto error; } /* * Fill in the control structures */ skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; skb_reserve(skb, hh_len); /* * Find where to start putting bytes. */ skb_put(skb, fragheaderlen + fraggap); skb_reset_network_header(skb); skb->transport_header = (skb->network_header + fragheaderlen); if (fraggap) { skb->csum = skb_copy_and_csum_bits(skb_prev, maxfraglen, skb_transport_header(skb), fraggap); skb_prev->csum = csum_sub(skb_prev->csum, skb->csum); pskb_trim_unique(skb_prev, maxfraglen); } /* * Put the packet on the pending queue. */ __skb_queue_tail(&sk->sk_write_queue, skb); continue; } if (len > size) len = size; if (skb_append_pagefrags(skb, page, offset, len)) { err = -EMSGSIZE; goto error; } if (skb->ip_summed == CHECKSUM_NONE) { __wsum csum; csum = csum_page(page, offset, len); skb->csum = csum_block_add(skb->csum, csum, skb->len); } skb->len += len; skb->data_len += len; skb->truesize += len; refcount_add(len, &sk->sk_wmem_alloc); offset += len; size -= len; } return 0; error: cork->length -= size; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); return err; } static void ip_cork_release(struct inet_cork *cork) { cork->flags &= ~IPCORK_OPT; kfree(cork->opt); cork->opt = NULL; dst_release(cork->dst); cork->dst = NULL; } /* * Combined all pending IP fragments on the socket as one IP datagram * and push them out. */ struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); struct ip_options *opt = NULL; struct rtable *rt = (struct rtable *)cork->dst; struct iphdr *iph; __be16 df = 0; __u8 ttl; 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; } /* Unless user demanded real pmtu discovery (IP_PMTUDISC_DO), we allow * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ skb->ignore_df = ip_sk_ignore_df(sk); /* DF bit is set when we want to see DF on outgoing frames. * If ignore_df is set too, we still allow to fragment this frame * locally. */ if (inet->pmtudisc == IP_PMTUDISC_DO || inet->pmtudisc == IP_PMTUDISC_PROBE || (skb->len <= dst_mtu(&rt->dst) && ip_dont_fragment(sk, &rt->dst))) df = htons(IP_DF); if (cork->flags & IPCORK_OPT) opt = cork->opt; if (cork->ttl != 0) ttl = cork->ttl; else if (rt->rt_type == RTN_MULTICAST) ttl = inet->mc_ttl; else ttl = ip_select_ttl(inet, &rt->dst); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 5; iph->tos = (cork->tos != -1) ? cork->tos : inet->tos; iph->frag_off = df; iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); ip_select_ident(net, skb, sk); if (opt) { iph->ihl += opt->optlen >> 2; ip_options_build(skb, opt, cork->addr, rt, 0); } skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; skb->mark = cork->mark; skb->tstamp = cork->transmit_time; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount */ cork->dst = NULL; skb_dst_set(skb, &rt->dst); if (iph->protocol == IPPROTO_ICMP) { u8 icmp_type; /* For such sockets, transhdrlen is zero when do ip_append_data(), * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; icmp_out_count(net, icmp_type); } ip_cork_release(cork); out: return skb; } int ip_send_skb(struct net *net, struct sk_buff *skb) { int err; err = ip_local_out(net, skb->sk, skb); if (err) { if (err > 0) err = net_xmit_errno(err); if (err) IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS); } return err; } int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4) { struct sk_buff *skb; skb = ip_finish_skb(sk, fl4); if (!skb) return 0; /* Netfilter gets whole the not fragmented skb. */ return ip_send_skb(sock_net(sk), skb); } /* * Throw away all pending data on the socket. */ static void __ip_flush_pending_frames(struct sock *sk, struct sk_buff_head *queue, struct inet_cork *cork) { struct sk_buff *skb; while ((skb = __skb_dequeue_tail(queue)) != NULL) kfree_skb(skb); ip_cork_release(cork); } void ip_flush_pending_frames(struct sock *sk) { __ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base); } struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, struct inet_cork *cork, unsigned int flags) { struct sk_buff_head queue; int err; if (flags & MSG_PROBE) return NULL; __skb_queue_head_init(&queue); cork->flags = 0; cork->addr = 0; cork->opt = NULL; err = ip_setup_cork(sk, cork, ipc, rtp); if (err) return ERR_PTR(err); err = __ip_append_data(sk, fl4, &queue, cork, ¤t->task_frag, getfrag, from, length, transhdrlen, flags); if (err) { __ip_flush_pending_frames(sk, &queue, cork); return ERR_PTR(err); } return __ip_make_skb(sk, fl4, &queue, cork); } /* * Fetch data from kernel space and fill in checksum if needed. */ static int ip_reply_glue_bits(void *dptr, char *to, int offset, int len, int odd, struct sk_buff *skb) { __wsum csum; csum = csum_partial_copy_nocheck(dptr+offset, to, len); skb->csum = csum_block_add(skb->csum, csum, odd); return 0; } /* * Generic function to send a packet as reply to another packet. * Used to send some TCP resets/acks so far. */ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, const struct ip_options *sopt, __be32 daddr, __be32 saddr, const struct ip_reply_arg *arg, unsigned int len, u64 transmit_time) { struct ip_options_data replyopts; struct ipcm_cookie ipc; struct flowi4 fl4; struct rtable *rt = skb_rtable(skb); struct net *net = sock_net(sk); struct sk_buff *nskb; int err; int oif; if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt)) return; ipcm_init(&ipc); ipc.addr = daddr; ipc.sockc.transmit_time = transmit_time; if (replyopts.opt.opt.optlen) { ipc.opt = &replyopts.opt; if (replyopts.opt.opt.srr) daddr = replyopts.opt.opt.faddr; } oif = arg->bound_dev_if; if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), daddr, saddr, tcp_hdr(skb)->source, tcp_hdr(skb)->dest, arg->uid); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) return; inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default); ipc.sockc.mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { ip_flush_pending_frames(sk); goto out; } nskb = skb_peek(&sk->sk_write_queue); if (nskb) { if (arg->csumoffset >= 0) *((__sum16 *)skb_transport_header(nskb) + arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; ip_push_pending_frames(sk, &fl4); } out: ip_rt_put(rt); } void __init ip_init(void) { ip_rt_init(); inet_initpeers(); #if defined(CONFIG_IP_MULTICAST) igmp_mc_init(); #endif } |
| 40 1012 2 1041 8 8 1011 1012 1013 1014 1011 1016 1012 3 1015 1013 1015 1016 1014 1013 1014 1014 1011 1013 1011 1014 3 1012 1916 1918 30 31 31 31 30 31 31 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/fs_struct.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/prefetch.h> #include "mount.h" struct prepend_buffer { char *buf; int len; }; #define DECLARE_BUFFER(__name, __buf, __len) \ struct prepend_buffer __name = {.buf = __buf + __len, .len = __len} static char *extract_string(struct prepend_buffer *p) { if (likely(p->len >= 0)) return p->buf; return ERR_PTR(-ENAMETOOLONG); } static bool prepend_char(struct prepend_buffer *p, unsigned char c) { if (likely(p->len > 0)) { p->len--; *--p->buf = c; return true; } p->len = -1; return false; } /* * The source of the prepend data can be an optimistoc load * of a dentry name and length. And because we don't hold any * locks, the length and the pointer to the name may not be * in sync if a concurrent rename happens, and the kernel * copy might fault as a result. * * The end result will correct itself when we check the * rename sequence count, but we need to be able to handle * the fault gracefully. */ static bool prepend_copy(void *dst, const void *src, int len) { if (unlikely(copy_from_kernel_nofault(dst, src, len))) { memset(dst, 'x', len); return false; } return true; } static bool prepend(struct prepend_buffer *p, const char *str, int namelen) { // Already overflowed? if (p->len < 0) return false; // Will overflow? if (p->len < namelen) { // Fill as much as possible from the end of the name str += namelen - p->len; p->buf -= p->len; prepend_copy(p->buf, str, p->len); p->len = -1; return false; } // Fits fully p->len -= namelen; p->buf -= namelen; return prepend_copy(p->buf, str, namelen); } /** * prepend_name - prepend a pathname in front of current buffer pointer * @buffer: buffer pointer * @buflen: allocated length of the buffer * @name: name string and length qstr structure * * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to * make sure that either the old or the new name pointer and length are * fetched. However, there may be mismatch between length and pointer. * But since the length cannot be trusted, we need to copy the name very * carefully when doing the prepend_copy(). It also prepends "/" at * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. * * Load acquire is needed to make sure that we see the new name data even * if we might get the length wrong. */ static bool prepend_name(struct prepend_buffer *p, const struct qstr *name) { const char *dname = smp_load_acquire(&name->name); /* ^^^ */ u32 dlen = READ_ONCE(name->len); return prepend(p, dname, dlen) && prepend_char(p, '/'); } static int __prepend_path(const struct dentry *dentry, const struct mount *mnt, const struct path *root, struct prepend_buffer *p) { while (dentry != root->dentry || &mnt->mnt != root->mnt) { const struct dentry *parent = READ_ONCE(dentry->d_parent); if (dentry == mnt->mnt.mnt_root) { struct mount *m = READ_ONCE(mnt->mnt_parent); struct mnt_namespace *mnt_ns; if (likely(mnt != m)) { dentry = READ_ONCE(mnt->mnt_mountpoint); mnt = m; continue; } /* Global root */ mnt_ns = READ_ONCE(mnt->mnt_ns); /* open-coded is_mounted() to use local mnt_ns */ if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns)) return 1; // absolute root else return 2; // detached or not attached yet } if (unlikely(dentry == parent)) /* Escaped? */ return 3; prefetch(parent); if (!prepend_name(p, &dentry->d_name)) break; dentry = parent; } return 0; } /** * prepend_path - Prepend path string to a buffer * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @buffer: pointer to the end of the buffer * @buflen: pointer to buffer length * * The function will first try to write out the pathname without taking any * lock other than the RCU read lock to make sure that dentries won't go away. * It only checks the sequence number of the global rename_lock as any change * in the dentry's d_seq will be preceded by changes in the rename_lock * sequence number. If the sequence number had been changed, it will restart * the whole pathname back-tracing sequence again by taking the rename_lock. * In this case, there is no need to take the RCU read lock as the recursive * parent pointer references will keep the dentry chain alive as long as no * rename operation is performed. */ static int prepend_path(const struct path *path, const struct path *root, struct prepend_buffer *p) { unsigned seq, m_seq = 0; struct prepend_buffer b; int error; rcu_read_lock(); restart_mnt: read_seqbegin_or_lock(&mount_lock, &m_seq); seq = 0; rcu_read_lock(); restart: b = *p; read_seqbegin_or_lock(&rename_lock, &seq); error = __prepend_path(path->dentry, real_mount(path->mnt), root, &b); if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (!(m_seq & 1)) rcu_read_unlock(); if (need_seqretry(&mount_lock, m_seq)) { m_seq = 1; goto restart_mnt; } done_seqretry(&mount_lock, m_seq); if (unlikely(error == 3)) b = *p; if (b.len == p->len) prepend_char(&b, '/'); *p = b; return error; } /** * __d_path - return the path of a dentry * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. * * Returns a pointer into the buffer or an error code if the * path was too long. * * "buflen" should be positive. * * If the path is not reachable from the supplied root, return %NULL. */ char *__d_path(const struct path *path, const struct path *root, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, root, &b) > 0)) return NULL; return extract_string(&b); } char *d_absolute_path(const struct path *path, char *buf, int buflen) { struct path root = {}; DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, &root, &b) > 1)) return ERR_PTR(-EINVAL); return extract_string(&b); } static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); *root = fs->root; } while (read_seqcount_retry(&fs->seq, seq)); } /** * d_path - return the path of a dentry * @path: path to report * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. If the entry has been deleted * the string " (deleted)" is appended. Note that this is ambiguous. * * Returns a pointer into the buffer or an error code if the path was * too long. Note: Callers should use the returned pointer, not the passed * in buffer, to use the name! The implementation often starts at an offset * into the buffer, and may leave 0 bytes at the start. * * "buflen" should be positive. */ char *d_path(const struct path *path, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); struct path root; /* * We have various synthetic filesystems that never get mounted. On * these filesystems dentries are never used for lookup purposes, and * thus don't need to be hashed. They also don't need a name until a * user wants to identify the object in /proc/pid/fd/. The little hack * below allows us to generate a name for these objects on demand: * * Some pseudo inodes are mountable. When they are mounted * path->dentry == path->mnt->mnt_root. In that case don't call d_dname * and instead have d_path return the mounted path. */ if (path->dentry->d_op && path->dentry->d_op->d_dname && (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) return path->dentry->d_op->d_dname(path->dentry, buf, buflen); rcu_read_lock(); get_fs_root_rcu(current->fs, &root); if (unlikely(d_unlinked(path->dentry))) prepend(&b, " (deleted)", 11); else prepend_char(&b, 0); prepend_path(path, &root, &b); rcu_read_unlock(); return extract_string(&b); } EXPORT_SYMBOL(d_path); /* * Helper function for dentry_operations.d_dname() members */ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen, const char *fmt, ...) { va_list args; char temp[64]; int sz; va_start(args, fmt); sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1; va_end(args); if (sz > sizeof(temp) || sz > buflen) return ERR_PTR(-ENAMETOOLONG); buffer += buflen - sz; return memcpy(buffer, temp, sz); } char *simple_dname(struct dentry *dentry, char *buffer, int buflen) { DECLARE_BUFFER(b, buffer, buflen); /* these dentries are never renamed, so d_lock is not needed */ prepend(&b, " (deleted)", 11); prepend(&b, dentry->d_name.name, dentry->d_name.len); prepend_char(&b, '/'); return extract_string(&b); } /* * Write full pathname from the root of the filesystem into the buffer. */ static char *__dentry_path(const struct dentry *d, struct prepend_buffer *p) { const struct dentry *dentry; struct prepend_buffer b; int seq = 0; rcu_read_lock(); restart: dentry = d; b = *p; read_seqbegin_or_lock(&rename_lock, &seq); while (!IS_ROOT(dentry)) { const struct dentry *parent = dentry->d_parent; prefetch(parent); if (!prepend_name(&b, &dentry->d_name)) break; dentry = parent; } if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (b.len == p->len) prepend_char(&b, '/'); return extract_string(&b); } char *dentry_path_raw(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); return __dentry_path(dentry, &b); } EXPORT_SYMBOL(dentry_path_raw); char *dentry_path(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); if (unlikely(d_unlinked(dentry))) prepend(&b, "//deleted", 10); else prepend_char(&b, 0); return __dentry_path(dentry, &b); } static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, struct path *pwd) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); *root = fs->root; *pwd = fs->pwd; } while (read_seqcount_retry(&fs->seq, seq)); } /* * NOTE! The user-level library version returns a * character pointer. The kernel system call just * returns the length of the buffer filled (which * includes the ending '\0' character), or a negative * error value. So libc would do something like * * char *getcwd(char * buf, size_t size) * { * int retval; * * retval = sys_getcwd(buf, size); * if (retval >= 0) * return buf; * errno = -retval; * return NULL; * } */ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) { int error; struct path pwd, root; char *page = __getname(); if (!page) return -ENOMEM; rcu_read_lock(); get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); if (unlikely(d_unlinked(pwd.dentry))) { rcu_read_unlock(); error = -ENOENT; } else { unsigned len; DECLARE_BUFFER(b, page, PATH_MAX); prepend_char(&b, 0); if (unlikely(prepend_path(&pwd, &root, &b) > 0)) prepend(&b, "(unreachable)", 13); rcu_read_unlock(); len = PATH_MAX - b.len; if (unlikely(len > PATH_MAX)) error = -ENAMETOOLONG; else if (unlikely(len > size)) error = -ERANGE; else if (copy_to_user(buf, b.buf, len)) error = -EFAULT; else error = len; } __putname(page); return error; } |
| 21 1 20 7 42 2 1 20 15 48 48 34 15 15 11 11 4 4 4 1 1 1 1 174 9 11 2 7 2 6 5 60 108 162 162 141 140 3 1 1 1 9 8 2 25 4 4 1 1 5 1 1 1 2 2 2 3 9 9 3 17 2 7 4 1 10 14 10 4 25 25 22 22 24 24 25 25 4 4 955 940 304 100 100 142 143 25 25 25 25 142 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io */ /* Devmaps primary use is as a backend map for XDP BPF helper call * bpf_redirect_map(). Because XDP is mostly concerned with performance we * spent some effort to ensure the datapath with redirect maps does not use * any locking. This is a quick note on the details. * * We have three possible paths to get into the devmap control plane bpf * syscalls, bpf programs, and driver side xmit/flush operations. A bpf syscall * will invoke an update, delete, or lookup operation. To ensure updates and * deletes appear atomic from the datapath side xchg() is used to modify the * netdev_map array. Then because the datapath does a lookup into the netdev_map * array (read-only) from an RCU critical section we use call_rcu() to wait for * an rcu grace period before free'ing the old data structures. This ensures the * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the * netdev_map consistent in this case. From the devmap side BPF programs * calling into these operations are the same as multiple user space threads * making system calls. * * Finally, any of the above may race with a netdev_unregister notifier. The * unregister notifier must search for net devices in the map structure that * contain a reference to the net device and remove them. This is a two step * process (a) dereference the bpf_dtab_netdev object in netdev_map and (b) * check to see if the ifindex is the same as the net_device being removed. * When removing the dev a cmpxchg() is used to ensure the correct dev is * removed, in the case of a concurrent update or delete operation it is * possible that the initially referenced dev is no longer in the map. As the * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. * * The devmap_hash type is a map type which interprets keys as ifindexes and * indexes these using a hashmap. This allows maps that use ifindex as key to be * densely packed instead of having holes in the lookup array for unused * ifindexes. The setup and packet enqueue/send code is shared between the two * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_dtab *dtab; struct bpf_prog *xdp_prog; struct rcu_head rcu; unsigned int idx; struct bpf_devmap_val val; }; struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ struct hlist_head *dev_index_head; spinlock_t index_lock; unsigned int items; u32 n_buckets; }; static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); static struct hlist_head *dev_map_create_hash(unsigned int entries, int numa_node) { int i; struct hlist_head *hash; hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, int idx) { return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; } static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { u32 valsize = attr->value_size; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex * 8 bytes: ifindex + prog fd */ if (attr->max_entries == 0 || attr->key_size != 4 || (valsize != offsetofend(struct bpf_devmap_val, ifindex) && valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return -EINVAL; /* Lookup returns a pointer straight to dev->ifindex, so make sure the * verifier prevents writes from the BPF side */ attr->map_flags |= BPF_F_RDONLY_PROG; bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { /* hash table size must be power of 2; roundup_pow_of_two() can * overflow into UB on 32-bit arches, so check that first */ if (dtab->map.max_entries > 1UL << 31) return -EINVAL; dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) return -ENOMEM; } return 0; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; int err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); dtab = kzalloc(sizeof(*dtab), GFP_USER | __GFP_ACCOUNT); if (!dtab) return ERR_PTR(-ENOMEM); err = dev_map_init_map(dtab, attr); if (err) { kfree(dtab); return ERR_PTR(err); } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were * disconnected from events. The following synchronize_rcu() guarantees * both rcu read critical sections complete and waits for * preempt-disable regions (NAPI being the relevant context here) so we * are certain there will be no further reads against the netdev_map and * all flush operations are complete. Flush operations can only be done * from NAPI context for this reason. */ spin_lock(&dev_map_lock); list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); bpf_clear_redirect_map(map); synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } } bpf_map_area_free(dtab->dev_index_head); } else { for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } bpf_map_area_free(dtab->netdev_map); } kfree(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = next_key; if (index >= dtab->map.max_entries) { *next = 0; return 0; } if (index == dtab->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; hlist_for_each_entry_rcu(dev, head, index_hlist, lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; return NULL; } static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); u32 idx, *next = next_key; struct bpf_dtab_netdev *dev, *next_dev; struct hlist_head *head; int i = 0; if (!key) goto find_first; idx = *(u32 *)key; dev = __dev_map_hash_lookup_elem(map, idx); if (!dev) goto find_first; next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } i = idx & (dtab->n_buckets - 1); i++; find_first: for (; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), struct bpf_dtab_netdev, index_hlist); if (next_dev) { *next = next_dev->idx; return 0; } } return -ENOENT; } static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, struct net_device *tx_dev, struct net_device *rx_dev) { struct xdp_txq_info txq = { .dev = tx_dev }; struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0; for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; u32 act; int err; xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; xdp.rxq = &rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { case XDP_PASS: err = xdp_update_frame_from_buff(&xdp, xdpf); if (unlikely(err < 0)) xdp_return_frame_rx_napi(xdpf); else frames[nframes++] = xdpf; break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); break; } } return nframes; /* sent frames count */ } static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; unsigned int cnt = bq->count; int sent = 0, err = 0; int to_send = cnt; int i; if (unlikely(!cnt)) return; for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } if (bq->xdp_prog) { to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; } sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { /* If ndo_xdp_xmit fails with an errno, no frames have * been xmit'ed. */ err = sent; sent = 0; } /* If not all frames have been transmitted, it is our * responsibility to free them */ for (i = sent; unlikely(i < to_send); i++) xdp_return_frame_rx_napi(bq->q[i]); out: bq->count = 0; trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } /* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the * driver before returning from its napi->poll() routine. See the comment above * xdp_do_flush() in filter.c. */ void __dev_flush(void) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); } } /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; if (key >= map->max_entries) return NULL; obj = rcu_dereference_check(dtab->netdev_map[key], rcu_read_lock_bh_held()); return obj; } /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. * * Do the same with xdp_prog and flush_list since these fields * are only ever modified together. */ if (!bq->dev_rx) { bq->dev_rx = dev_rx; bq->xdp_prog = xdp_prog; list_add(&bq->flush_node, flush_list); } bq->q[bq->count++] = xdpf; } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdpf->len); if (unlikely(err)) return err; bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) { struct xdp_txq_info txq = { .dev = dst->dev }; struct xdp_buff xdp; u32 act; if (!dst->xdp_prog) return XDP_PASS; __skb_pull(skb, skb->mac_len); xdp.txq = &txq; act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); switch (act) { case XDP_PASS: __skb_push(skb, skb->mac_len); break; default: bpf_warn_invalid_xdp_action(act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); fallthrough; case XDP_DROP: kfree_skb(skb); break; } return act; } int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj || !obj->dev->netdev_ops->ndo_xdp_xmit) return false; if (xdp_ok_fwd_dev(obj->dev, xdpf->len)) return false; return true; } static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, struct net_device *dev_rx, struct xdp_frame *xdpf) { struct xdp_frame *nxdpf; nxdpf = xdpf_clone(xdpf); if (!nxdpf) return -ENOMEM; bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); return 0; } static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) { while (num_excluded--) { if (ifindex == excluded[num_excluded]) return true; } return false; } /* Get ifindex of each upper device. 'indexes' must be able to hold at * least MAX_NEST_DEV elements. * Returns the number of ifindexes added. */ static int get_upper_ifindexes(struct net_device *dev, int *indexes) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { indexes[n++] = upper->ifindex; } return n; } int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); excluded_devices[num_excluded++] = dev_rx->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); if (err) return err; last_dst = dst; } } } /* consume the last copy of the frame */ if (last_dst) bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); else xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { int err; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; /* Redirect has already succeeded semantically at this point, so we just * return 0 even if packet is dropped. Helper below takes care of * freeing skb. */ if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) return 0; skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { struct sk_buff *nskb; int err; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; err = dev_map_generic_redirect(dst, nskb, xdp_prog); if (unlikely(err)) { consume_skb(nskb); return err; } return 0; } int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; struct hlist_node *next; int num_excluded = 0; unsigned int i; int err; if (exclude_ingress) { num_excluded = get_upper_ifindexes(dev, excluded_devices); excluded_devices[num_excluded++] = dev->ifindex; } if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ for (i = 0; i < dtab->n_buckets; i++) { head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dst, next, head, index_hlist) { if (!dst) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) continue; /* we only need n-1 clones; last_dst enqueued below */ if (!last_dst) { last_dst = dst; continue; } err = dev_map_redirect_clone(last_dst, skb, xdp_prog); if (err) return err; last_dst = dst; } } } /* consume the first skb and return */ if (last_dst) return dev_map_generic_redirect(last_dst, skb, xdp_prog); /* dtab is empty */ consume_skb(skb); return 0; } static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, *(u32 *)key); return obj ? &obj->val : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) { struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); if (dev->xdp_prog) bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } static int dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; } static int dev_map_hash_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; u32 k = *(u32 *)key; unsigned long flags; int ret = -ENOENT; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, k); if (old_dev) { dtab->items--; hlist_del_init_rcu(&old_dev->index_hlist); call_rcu(&old_dev->rcu, __dev_map_entry_free); ret = 0; } spin_unlock_irqrestore(&dtab->index_lock, flags); return ret; } static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_dtab *dtab, struct bpf_devmap_val *val, unsigned int idx) { struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); dev->dev = dev_get_by_index(net, val->ifindex); if (!dev->dev) goto err_out; if (val->bpf_prog.fd > 0) { prog = bpf_prog_get_type_dev(val->bpf_prog.fd, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; if (prog->expected_attach_type != BPF_XDP_DEVMAP) goto err_put_prog; } dev->idx = idx; dev->dtab = dtab; if (prog) { dev->xdp_prog = prog; dev->val.bpf_prog.id = prog->aux->id; } else { dev->xdp_prog = NULL; dev->val.bpf_prog.id = 0; } dev->val.ifindex = val->ifindex; return dev; err_put_prog: bpf_prog_put(prog); err_put_dev: dev_put(dev->dev); err_out: kfree(dev); return ERR_PTR(-EINVAL); } static int __dev_map_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; if (unlikely(i >= dtab->map.max_entries)) return -E2BIG; if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (!val.ifindex) { dev = NULL; /* can not specify fd if ifindex is 0 */ if (val.bpf_prog.fd > 0) return -EINVAL; } else { dev = __dev_map_alloc_node(net, dtab, &val, i); if (IS_ERR(dev)) return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed * Remembering the driver side flush operation will happen before the * net device is removed. */ old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; } static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static int __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dev, *old_dev; struct bpf_devmap_val val = {}; u32 idx = *(u32 *)key; unsigned long flags; int err = -EEXIST; /* already verified value_size <= sizeof val */ memcpy(&val, value, map->value_size); if (unlikely(map_flags > BPF_EXIST || !val.ifindex)) return -EINVAL; spin_lock_irqsave(&dtab->index_lock, flags); old_dev = __dev_map_hash_lookup_elem(map, idx); if (old_dev && (map_flags & BPF_NOEXIST)) goto out_err; dev = __dev_map_alloc_node(net, dtab, &val, idx); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out_err; } if (old_dev) { hlist_del_rcu(&old_dev->index_hlist); } else { if (dtab->items >= dtab->map.max_entries) { spin_unlock_irqrestore(&dtab->index_lock, flags); call_rcu(&dev->rcu, __dev_map_entry_free); return -E2BIG; } dtab->items++; } hlist_add_head_rcu(&dev->index_hlist, dev_map_index_hash(dtab, idx)); spin_unlock_irqrestore(&dtab->index_lock, flags); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; out_err: spin_unlock_irqrestore(&dtab->index_lock, flags); return err; } static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __dev_map_hash_update_elem(current->nsproxy->net_ns, map, key, value, map_flags); } static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_hash_lookup_elem); } static int dev_map_btf_id; const struct bpf_map_ops dev_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, .map_lookup_elem = dev_map_lookup_elem, .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, .map_btf_name = "bpf_dtab", .map_btf_id = &dev_map_btf_id, .map_redirect = dev_map_redirect, }; static int dev_map_hash_map_btf_id; const struct bpf_map_ops dev_map_hash_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_hash_get_next_key, .map_lookup_elem = dev_map_hash_lookup_elem, .map_update_elem = dev_map_hash_update_elem, .map_delete_elem = dev_map_hash_delete_elem, .map_check_btf = map_check_no_btf, .map_btf_name = "bpf_dtab", .map_btf_id = &dev_map_hash_map_btf_id, .map_redirect = dev_hash_map_redirect, }; static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, struct net_device *netdev) { unsigned long flags; u32 i; spin_lock_irqsave(&dtab->index_lock, flags); for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; struct hlist_head *head; struct hlist_node *next; head = dev_map_index_hash(dtab, i); hlist_for_each_entry_safe(dev, next, head, index_hlist) { if (netdev != dev->dev) continue; dtab->items--; hlist_del_rcu(&dev->index_hlist); call_rcu(&dev->rcu, __dev_map_entry_free); } } spin_unlock_irqrestore(&dtab->index_lock, flags); } static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; int i, cpu; switch (event) { case NETDEV_REGISTER: if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) break; /* will be freed in free_netdev() */ netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); if (!netdev->xdp_bulkq) return NOTIFY_BAD; for_each_possible_cpu(cpu) per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete * operation does not free a netdev_map entry while we * are comparing it against the netdev being unregistered. */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dev_map_hash_remove_netdev(dtab, netdev); continue; } for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) call_rcu(&dev->rcu, __dev_map_entry_free); } } rcu_read_unlock(); break; default: break; } return NOTIFY_OK; } static struct notifier_block dev_map_notifier = { .notifier_call = dev_map_notification, }; static int __init dev_map_init(void) { int cpu; /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); for_each_possible_cpu(cpu) INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu)); return 0; } subsys_initcall(dev_map_init); |
| 289 290 291 291 290 291 291 830 826 830 315 316 315 316 314 316 42 291 290 291 290 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_irq(&wb->work_lock); } static void finish_writeback_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(wb, work); spin_unlock_irq(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ /* * Maximum inodes per isw. A specific value has been chosen to make * struct inode_switch_wbs_context fit into 1024 bytes kmalloc. */ #define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \ / sizeof(struct inode *)) static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (page) { memcg_css = mem_cgroup_css_from_page(page); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } EXPORT_SYMBOL_GPL(__inode_attach_wb); /** * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list * @inode: inode of interest with i_lock held * @wb: target bdi_writeback * * Remove the inode from wb's io lists and if necessarily put onto b_attached * list. Only inodes attached to cgwb's are kept on this list. */ static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; if (wb != &wb->bdi->wb) list_move(&inode->i_io_list, &wb->b_attached); else list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct rcu_work work; /* * Multiple inodes can be switched at once. The switching procedure * consists of two parts, separated by a RCU grace period. To make * sure that the second part is executed for each inode gone through * the first part, all inode pointers are placed into a NULL-terminated * array embedded into struct inode_switch_wbs_context. Otherwise * an inode could be left in a non-consistent state. */ struct bdi_writeback *new_wb; struct inode *inodes[]; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static bool inode_do_switch_wbs(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb) { struct address_space *mapping = inode->i_mapping; XA_STATE(xas, &mapping->i_pages, 0); struct page *page; bool switched = false; spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction * path owns the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to * pages actually under writeback. */ xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (PageDirty(page)) { dec_wb_stat(old_wb, WB_RECLAIMABLE); inc_wb_stat(new_wb, WB_RECLAIMABLE); } } xas_set(&xas, 0); xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { WARN_ON_ONCE(!PageWriteback(page)); dec_wb_stat(old_wb, WB_WRITEBACK); inc_wb_stat(new_wb, WB_WRITEBACK); } if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { atomic_dec(&old_wb->writeback_inodes); atomic_inc(&new_wb->writeback_inodes); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. If the @inode is dirty, * the specific list @inode was on is ignored and the @inode is put on * ->b_dirty which is always correct including from ->b_dirty_time. * The transfer preserves @inode->dirtied_when ordering. If the @inode * was clean, it means it was on the b_attached list, so move it onto * the b_attached list of @new_wb. */ if (!list_empty(&inode->i_io_list)) { inode->i_wb = new_wb; if (inode->i_state & I_DIRTY_ALL) { struct inode *pos; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode_cgwb_move_to_attached(inode, new_wb); } } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); return switched; } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(to_rcu_work(work), struct inode_switch_wbs_context, work); struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; struct bdi_writeback *new_wb = isw->new_wb; unsigned long nr_switched = 0; struct inode **inodep; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } for (inodep = isw->inodes; *inodep; inodep++) { WARN_ON_ONCE((*inodep)->i_wb != old_wb); if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) nr_switched++; } spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (nr_switched) { wb_wakeup(new_wb); wb_put_many(old_wb, nr_switched); } for (inodep = isw->inodes; *inodep; inodep++) iput(*inodep); wb_put(new_wb); kfree(isw); atomic_dec(&isw_nr_in_flight); } static bool inode_prepare_wbs_switch(struct inode *inode, struct bdi_writeback *new_wb) { /* * Paired with smp_mb() in cgroup_writeback_umount(). * isw_nr_in_flight must be increased before checking SB_ACTIVE and * grabbing an inode, otherwise isw_nr_in_flight can be observed as 0 * in cgroup_writeback_umount() and the isw_wq will be not flushed. */ smp_mb(); if (IS_DAX(inode)) return false; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || inode_to_wb(inode) == new_wb) { spin_unlock(&inode->i_lock); return false; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); return true; } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(sizeof(*isw) + 2 * sizeof(struct inode *), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; if (!inode_prepare_wbs_switch(inode, isw->new_wb)) goto out_free; isw->inodes[0] = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *isw, struct list_head *list, int *nr) { struct inode *inode; list_for_each_entry(inode, list, i_io_list) { if (!inode_prepare_wbs_switch(inode, isw->new_wb)) continue; isw->inodes[*nr] = inode; (*nr)++; if (*nr >= WB_MAX_INODES_PER_ISW - 1) return true; } return false; } /** * cleanup_offline_cgwb - detach associated inodes * @wb: target wb * * Switch all inodes attached to @wb to a nearest living ancestor's wb in order * to eventually release the dying @wb. Returns %true if not all inodes were * switched and the function has to be restarted. */ bool cleanup_offline_cgwb(struct bdi_writeback *wb) { struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; int nr; bool restart = false; isw = kzalloc(sizeof(*isw) + WB_MAX_INODES_PER_ISW * sizeof(struct inode *), GFP_KERNEL); if (!isw) return restart; atomic_inc(&isw_nr_in_flight); for (memcg_css = wb->memcg_css->parent; memcg_css; memcg_css = memcg_css->parent) { isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); if (isw->new_wb) break; } if (unlikely(!isw->new_wb)) isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ nr = 0; spin_lock(&wb->list_lock); /* * In addition to the inodes that have completed writeback, also switch * cgwbs for those inodes only with dirty timestamps. Otherwise, those * inodes won't be written back for a long time when lazytime is * enabled, and thus pinning the dying cgwbs. It won't break the * bandwidth restrictions, as writeback of inode metadata is not * accounted for. */ restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr); if (!restart) restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr); spin_unlock(&wb->list_lock); /* no attached inodes? bail out */ if (nr == 0) { atomic_dec(&isw_nr_in_flight); wb_put(isw->new_wb); kfree(isw); return restart; } /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return restart; } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @page: page being written out * @bytes: number of bytes being written out * * @bytes from @page are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_page(page); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * inode_congested - test whether an inode is congested * @inode: inode to test for congestion (may be NULL) * @cong_bits: mask of WB_[a]sync_congested bits to test * * Tests whether @inode is congested. @cong_bits is the mask of congestion * bits to test and the return value is the mask of set bits. * * If cgroup writeback is enabled for @inode, the congestion state is * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg * associated with @inode is congested; otherwise, the root wb's congestion * state is used. * * @inode is allowed to be NULL as this function is often called on * mapping->host which is NULL for the swapper space. */ int inode_congested(struct inode *inode, int cong_bits) { /* * Once set, ->i_wb never becomes NULL while the inode is alive. * Start transaction iff ->i_wb is visible. */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; struct wb_lock_cookie lock_cookie = {}; bool congested; wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } EXPORT_SYMBOL_GPL(inode_congested); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* * If wb_tryget fails, the wb has been shutdown, skip it. * * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ if (!wb_tryget(wb)) continue; /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; unsigned long dirty; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * The caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. * * BTW the memcg stats are flushed periodically and this is best-effort * estimation, so some potential error is ok. */ dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY); dirty = dirty * 10 / 8; /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = dirty; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(void) { /* * SB_ACTIVE should be reliably cleared before checking * isw_nr_in_flight, see generic_shutdown_super(). */ smp_mb(); if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); inode->i_state &= ~I_SYNC_QUEUED; } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } #define EXPIRE_DIRTY_ATIME 0x0001 /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; spin_lock(&inode->i_lock); list_move(&inode->i_io_list, &tmp); moved++; inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* * Although inode's i_io_list is moved from 'tmp' to 'dispatch_queue', * we don't take inode->i_lock here because it is just a pointless overhead. * Inode is already marked as I_SYNC_QUEUED so writeback list handling is * fully under our control. */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ static void __inode_wait_for_writeback(struct inode *inode) __releases(inode->i_lock) __acquires(inode->i_lock) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); } } /* * Wait for writeback on an inode to complete. Caller must have inode pinned. */ void inode_wait_for_writeback(struct inode *inode) { spin_lock(&inode->i_lock); __inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { DEFINE_WAIT(wait); wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); int sleep; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); sleep = inode->i_state & I_SYNC; spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wqh, &wait); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * Writeback is not making progress due to locked buffers. * Skip this inode for now. Although having skipped pages * is odd for clean inodes, it can happen for some * filesystems so handle that gracefully. */ if (inode->i_state & I_DIRTY_ALL) redirty_tail_locked(inode, wb); else inode_cgwb_move_to_attached(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_cgwb_move_to_attached(inode, wb); } } /* * Write out an inode and its dirty pages (or some of its dirty pages, depending * on @wbc->nr_to_write), and clear the relevant dirty flags from i_state. * * This doesn't remove the inode from the writeback list it is on, except * potentially to move it from b_dirty_time to b_dirty due to timestamp * expiration. The caller is otherwise responsible for writeback list handling. * * The caller is also responsible for setting the I_SYNC flag beforehand and * calling inode_sync_complete() to clear it afterwards. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Get and clear the dirty flags from i_state. This needs to be done * after calling writepages because some filesystems may redirty the * inode during writepages due to delalloc. It also needs to be done * after handling timestamp expiration, as that may dirty the inode too. */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty data and metadata on-demand, i.e. separately from * the regular batched writeback done by the flusher threads in * writeback_sb_inodes(). @wbc controls various aspects of the write, such as * whether it is a data-integrity sync (%WB_SYNC_ALL) or not (%WB_SYNC_NONE). * * To prevent the inode from going away, either the caller must have a reference * to the inode, or the inode must have I_WILL_FREE or I_FREEING set. */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { /* * Writeback is already running on the inode. For WB_SYNC_NONE, * that's enough and we can just return. For WB_SYNC_ALL, we * must wait for the existing writeback to complete, then do * writeback again if there's anything left. */ if (wbc->sync_mode != WB_SYNC_ALL) goto out; __inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * If the inode is already fully clean, then there's nothing to do. * * For data-integrity syncs we also need to check whether any pages are * still under writeback, e.g. due to prior WB_SYNC_NONE writeback. If * there are any such pages, we'll need to wait for them. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If the inode is freeing, its i_io_list shoudn't be updated * as it can be finally deleted at this moment. */ if (!(inode->i_state & I_FREEING)) { /* * If the inode is now fully clean, then it can be safely * removed from its writeback list (if any). Otherwise the * flusher threads are responsible for the writeback lists. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); else if (!(inode->i_state & I_SYNC_QUEUED)) { if ((inode->i_state & I_DIRTY)) redirty_tail_locked(inode, wb); else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); } } } spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; long wrote; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ requeue_io(inode, wb); spin_unlock(&inode->i_lock); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; wrote = wrote < 0 ? 0 : wrote; total_wrote += wrote; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!trylock_super(sb)) { /* * trylock_super() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; /* * Kupdate and background works are special and we want to * include all inodes that need writing. Livelock avoidance is * handled by these works yielding to any other work so we are * safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress) continue; /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) break; /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); spin_lock(&wb->list_lock); } spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_irq(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_irq(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(wb, work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); current->flags &= ~PF_SWAPWRITE; } /* * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero, * write back the whole world. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ if (blk_needs_flush_plug(current)) blk_schedule_flush_plug(current); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } /** * __mark_inode_dirty - internal function to mark an inode dirty * * @inode: inode to mark * @flags: what kind of dirty, e.g. I_DIRTY_SYNC. This can be a combination of * multiple I_DIRTY_* flags, except that I_DIRTY_TIME can't be combined * with I_DIRTY_PAGES. * * Mark an inode as dirty. We notify the filesystem, then update the inode's * dirty flags. Then, if needed we add the inode to the appropriate dirty list. * * Most callers should use mark_inode_dirty() or mark_inode_dirty_sync() * instead of calling this directly. * * CAREFUL! We only add the inode to the dirty list if it is hashed or if it * refers to a blockdev. Unhashed inodes will never be added to the dirty list * even if they are later hashed, as they will have been marked dirty already. * * In short, ensure you hash any inodes _before_ you start marking them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime = 0; struct bdi_writeback *wb = NULL; trace_writeback_mark_inode_dirty(inode, flags); if (flags & I_DIRTY_INODE) { /* * Inode timestamp update will piggback on this dirtying. * We tell ->dirty_inode callback that timestamps need to * be updated by setting I_DIRTY_TIME in flags. */ if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); if (inode->i_state & I_DIRTY_TIME) { inode->i_state &= ~I_DIRTY_TIME; flags |= I_DIRTY_TIME; } spin_unlock(&inode->i_lock); } /* * Notify the filesystem about the inode being dirtied, so that * (if needed) it can update on-disk fields and journal the * inode. This is only needed when the inode itself is being * dirtied now. I.e. it's only needed for I_DIRTY_INODE, not * for just I_DIRTY_PAGES or I_DIRTY_TIME. */ trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags & (I_DIRTY_INODE | I_DIRTY_TIME)); trace_writeback_dirty_inode(inode, flags); /* I_DIRTY_INODE supersedes I_DIRTY_TIME. */ flags &= ~I_DIRTY_TIME; } else { /* * Else it's either I_DIRTY_PAGES, I_DIRTY_TIME, or nothing. * (We don't support setting both I_DIRTY_PAGES and I_DIRTY_TIME * in one call to __mark_inode_dirty().) */ dirtytime = flags & I_DIRTY_TIME; WARN_ON_ONCE(dirtytime && flags != I_DIRTY_TIME); } /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if ((inode->i_state & flags) == flags) return; spin_lock(&inode->i_lock); if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); inode->i_state |= flags; /* * Grab inode's wb early because it requires dropping i_lock and we * need to make sure following checks happen atomically with dirty * list handling so that we don't move inodes under flush worker's * hands. */ if (!was_dirty) { wb = locked_inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); } /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock; } if (inode->i_state & I_FREEING) goto out_unlock; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct list_head *dirty_list; bool wakeup_bdi = false; inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } } out_unlock: if (wb) spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |
| 71 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UNWIND_H #define _ASM_X86_UNWIND_H #include <linux/sched.h> #include <linux/ftrace.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> #define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) #define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) struct unwind_state { struct stack_info stack_info; unsigned long stack_mask; struct task_struct *task; int graph_idx; bool error; #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; /* * If non-NULL: The current frame is incomplete and doesn't contain a * valid BP. When looking for the next frame, use this instead of the * non-existent saved BP. */ unsigned long *next_bp; struct pt_regs *regs; #else unsigned long *sp; #endif }; void __unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame); bool unwind_next_frame(struct unwind_state *state); unsigned long unwind_get_return_address(struct unwind_state *state); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state); static inline bool unwind_done(struct unwind_state *state) { return state->stack_info.type == STACK_TYPE_UNKNOWN; } static inline bool unwind_error(struct unwind_state *state) { return state->error; } static inline void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs, unsigned long *first_frame) { first_frame = first_frame ? : get_stack_pointer(task, regs); __unwind_start(state, task, regs, first_frame); } #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) /* * If 'partial' returns true, only the iret frame registers are valid. */ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, bool *partial) { if (unwind_done(state)) return NULL; if (partial) { #ifdef CONFIG_UNWINDER_ORC *partial = !state->full_regs; #else *partial = false; #endif } return state->regs; } #else static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, bool *partial) { return NULL; } #endif #ifdef CONFIG_UNWINDER_ORC void unwind_init(void); void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size); #else static inline void unwind_init(void) {} static inline void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, void *orc, size_t orc_size) {} #endif /* * This disables KASAN checking when reading a value from another task's stack, * since the other task could be running on another CPU and could have poisoned * the stack in the meantime. */ #define READ_ONCE_TASK_STACK(task, x) \ ({ \ unsigned long val; \ if (task == current) \ val = READ_ONCE(x); \ else \ val = READ_ONCE_NOCHECK(x); \ val; \ }) static inline bool task_on_another_cpu(struct task_struct *task) { #ifdef CONFIG_SMP return task != current && task->on_cpu; #else return false; #endif } #endif /* _ASM_X86_UNWIND_H */ |
| 6 124 131 1 128 130 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/bitops.h> #include <asm/word-at-a-time.h> /* * Do a strnlen, return length of string *with* final '\0'. * 'count' is the user-supplied count, while 'max' is the * address space maximum. * * Return 0 for exceptions (which includes hitting the address * space maximum), or 'count+1' if hitting the user-supplied * maximum count. * * NOTE! We can sometimes overshoot the user-supplied maximum * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; unsigned long c; /* * Do everything aligned. But that means that we * need to also expand the maximum.. */ align = (sizeof(unsigned long) - 1) & (unsigned long)src; src -= align; max += align; unsafe_get_user(c, (unsigned long __user *)src, efault); c |= aligned_byte_mask(align); for (;;) { unsigned long data; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); return res + find_zero(data) + 1 - align; } res += sizeof(unsigned long); /* We already handled 'unsigned long' bytes. Did we do it all ? */ if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); unsafe_get_user(c, (unsigned long __user *)(src+res), efault); } res -= align; /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, return the marker for "too long". */ if (res >= count) return count+1; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's 0. */ efault: return 0; } /** * strnlen_user: - Get the size of a user string INCLUDING final NUL. * @str: The string to measure. * @count: Maximum count (including NUL character) * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Get the size of a NUL-terminated string in user space. * * Returns the size of the string INCLUDING the terminating NUL. * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * NOTE! You should basically never use this function. There is * almost never any valid case for using the length of a user space * string, since the string can be changed at any time by other * threads. Use "strncpy_from_user()" instead to get a stable copy * of the string. */ long strnlen_user(const char __user *str, long count) { unsigned long max_addr, src_addr; if (unlikely(count <= 0)) return 0; max_addr = user_addr_max(); src_addr = (unsigned long)untagged_addr(str); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(str, max)) { retval = do_strnlen_user(str, count, max); user_read_access_end(); return retval; } } return 0; } EXPORT_SYMBOL(strnlen_user); |
| 7558 3081 7540 23 23 4788 4784 1633 1636 79 79 78 79 79 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/capability.c * * Copyright (C) 1997 Andrew Main <zefram@fysh.org> * * Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org> * 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/audit.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> /* * Leveraged for setting/resetting capabilities */ const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; EXPORT_SYMBOL(__cap_empty_set); int file_caps_enabled = 1; static int __init file_caps_disable(char *str) { file_caps_enabled = 0; return 1; } __setup("no_file_caps", file_caps_disable); #ifdef CONFIG_MULTIUSER /* * More recent versions of libcap are available from: * * http://www.kernel.org/pub/linux/libs/security/linux-privs/ */ static void warn_legacy_capability_use(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n", get_task_comm(name, current)); } /* * Version 2 capabilities worked fine, but the linux/capability.h file * that accompanied their introduction encouraged their use without * the necessary user-space source code changes. As such, we have * created a version 3 with equivalent functionality to version 2, but * with a header change to protect legacy source code from using * version 2 when it wanted to use version 1. If your system has code * that trips the following warning, it is using version 2 specific * capabilities and may be doing so insecurely. * * The remedy is to either upgrade your version of libcap (to 2.10+, * if the application is linked against it), or recompile your * application with modern kernel headers and this warning will go * away. */ static void warn_deprecated_v2(void) { char name[sizeof(current->comm)]; pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n", get_task_comm(name, current)); } /* * Version check. Return the number of u32s in each capability flag * array, or a negative value on error. */ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) { __u32 version; if (get_user(version, &header->version)) return -EFAULT; switch (version) { case _LINUX_CAPABILITY_VERSION_1: warn_legacy_capability_use(); *tocopy = _LINUX_CAPABILITY_U32S_1; break; case _LINUX_CAPABILITY_VERSION_2: warn_deprecated_v2(); fallthrough; /* v3 is otherwise equivalent to v2 */ case _LINUX_CAPABILITY_VERSION_3: *tocopy = _LINUX_CAPABILITY_U32S_3; break; default: if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version)) return -EFAULT; return -EINVAL; } return 0; } /* * The only thing that can change the capabilities of the current * process is the current process. As such, we can't be in this code * at the same time as we are in the process of setting capabilities * in this process. The net result is that we can limit our use of * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) { int ret; if (pid && (pid != task_pid_vnr(current))) { struct task_struct *target; rcu_read_lock(); target = find_task_by_vpid(pid); if (!target) ret = -ESRCH; else ret = security_capget(target, pEp, pIp, pPp); rcu_read_unlock(); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and * target pid data * @dataptr: pointer to struct that contains the effective, permitted, * and inheritable capabilities that are returned * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) { int ret = 0; pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret; if (get_user(pid, &header->pid)) return -EFAULT; if (pid < 0) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); if (!ret) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i; for (i = 0; i < tocopy; i++) { kdata[i].effective = pE.cap[i]; kdata[i].permitted = pP.cap[i]; kdata[i].inheritable = pI.cap[i]; } /* * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, * we silently drop the upper capabilities here. This * has the effect of making older libcap * implementations implicitly drop upper capability * bits when they perform a: capget/modify/capset * sequence. * * This behavior is considered fail-safe * behavior. Upgrading the application to a newer * version of libcap will enable access to the newer * capabilities. * * An alternative would be to return an error here * (-ERANGE), but that causes legacy applications to * unexpectedly fail; the capget/modify/capset aborts * before modification is attempted and the application * fails. */ if (copy_to_user(dataptr, kdata, tocopy * sizeof(struct __user_cap_data_struct))) { return -EFAULT; } } return ret; } /** * sys_capset - set capabilities for a process or (*) a group of processes * @header: pointer to struct that contains capability version and * target pid data * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * * Set capabilities for the current process only. The ability to any other * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * * I: any raised capabilities must be a subset of the old permitted * P: any raised capabilities must be a subset of the old permitted * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i, tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; pid_t pid; ret = cap_validate_magic(header, &tocopy); if (ret != 0) return ret; if (get_user(pid, &header->pid)) return -EFAULT; /* may only affect current now */ if (pid != 0 && pid != task_pid_vnr(current)) return -EPERM; copybytes = tocopy * sizeof(struct __user_cap_data_struct); if (copybytes > sizeof(kdata)) return -EFAULT; if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; for (i = 0; i < tocopy; i++) { effective.cap[i] = kdata[i].effective; permitted.cap[i] = kdata[i].permitted; inheritable.cap[i] = kdata[i].inheritable; } while (i < _KERNEL_CAPABILITY_U32S) { effective.cap[i] = 0; permitted.cap[i] = 0; inheritable.cap[i] = 0; i++; } effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; new = prepare_creds(); if (!new) return -ENOMEM; ret = security_capset(new, current_cred(), &effective, &inheritable, &permitted); if (ret < 0) goto error; audit_log_capset(new, current_cred()); return commit_creds(new); error: abort_creds(new); return ret; } /** * has_ns_capability - Does a task have a capability in a specific user ns * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE); rcu_read_unlock(); return (ret == 0); } /** * has_capability - Does a task have a capability in init_user_ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the initial user namespace, false if not. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability(struct task_struct *t, int cap) { return has_ns_capability(t, &init_user_ns, cap); } EXPORT_SYMBOL(has_capability); /** * has_ns_capability_noaudit - Does a task have a capability (unaudited) * in a specific user ns. * @t: The task in question * @ns: target user namespace * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to the specified user namespace, false if not. * Do not write an audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_ns_capability_noaudit(struct task_struct *t, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } /** * has_capability_noaudit - Does a task have a capability (unaudited) in the * initial user ns * @t: The task in question * @cap: The capability to be tested for * * Return true if the specified task has the given superior capability * currently in effect to init_user_ns, false if not. Don't write an * audit message for the check. * * Note that this does not set PF_SUPERPRIV on the task. */ bool has_capability_noaudit(struct task_struct *t, int cap) { return has_ns_capability_noaudit(t, &init_user_ns, cap); } static bool ns_capable_common(struct user_namespace *ns, int cap, unsigned int opts) { int capable; if (unlikely(!cap_valid(cap))) { pr_crit("capable() called with invalid cap=%u\n", cap); BUG(); } capable = security_capable(current_cred(), ns, cap, opts); if (capable == 0) { current->flags |= PF_SUPERPRIV; return true; } return false; } /** * ns_capable - Determine if the current task has a superior capability in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NONE); } EXPORT_SYMBOL(ns_capable); /** * ns_capable_noaudit - Determine if the current task has a superior capability * (unaudited) in effect * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_noaudit(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT); } EXPORT_SYMBOL(ns_capable_noaudit); /** * ns_capable_setid - Determine if the current task has a superior capability * in effect, while signalling that this check is being done from within a * setid or setgroups syscall. * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool ns_capable_setid(struct user_namespace *ns, int cap) { return ns_capable_common(ns, cap, CAP_OPT_INSETID); } EXPORT_SYMBOL(ns_capable_setid); /** * capable - Determine if the current task has a superior capability in effect * @cap: The capability to be tested for * * Return true if the current task has the given superior capability currently * available for use, false if not. * * This sets PF_SUPERPRIV on the task if the capability is available on the * assumption that it's about to be used. */ bool capable(int cap) { return ns_capable(&init_user_ns, cap); } EXPORT_SYMBOL(capable); #endif /* CONFIG_MULTIUSER */ /** * file_ns_capable - Determine if the file's opener had a capability in effect * @file: The file we want to check * @ns: The usernamespace we want the capability in * @cap: The capability to be tested for * * Return true if task that opened the file had a capability in effect * when the file was opened. * * This does not set PF_SUPERPRIV because the caller may not * actually be privileged. */ bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap) { if (WARN_ON_ONCE(!cap_valid(cap))) return false; if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0) return true; return false; } EXPORT_SYMBOL(file_ns_capable); /** * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode? * @ns: The user namespace in question * @inode: The inode in question * * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, struct user_namespace *mnt_userns, const struct inode *inode) { return kuid_has_mapping(ns, i_uid_into_mnt(mnt_userns, inode)) && kgid_has_mapping(ns, i_gid_into_mnt(mnt_userns, inode)); } /** * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @inode: The inode in question * @cap: The capability in question * * Return true if the current task has the given capability targeted at * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns, const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, mnt_userns, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); /** * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace * @tsk: The task that may be ptraced * @ns: The user namespace to search for CAP_SYS_PTRACE in * * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE * in the specified user namespace. */ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) { int ret = 0; /* An absent tracer adds no restrictions */ const struct cred *cred; rcu_read_lock(); cred = rcu_dereference(tsk->ptracer_cred); if (cred) ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); rcu_read_unlock(); return (ret == 0); } |
| 7 1238 1239 1243 1238 7 7 7 7 7 7 7 7 22 7 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BLK_CGROUP_H #define _BLK_CGROUP_H /* * Common Block IO controller cgroup interface * * Based on ideas and code from CFQ, CFS and BFQ: * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk> * * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it> * Paolo Valente <paolo.valente@unimore.it> * * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com> * Nauman Rafique <nauman@google.com> */ #include <linux/cgroup.h> #include <linux/percpu.h> #include <linux/percpu_counter.h> #include <linux/u64_stats_sync.h> #include <linux/seq_file.h> #include <linux/radix-tree.h> #include <linux/blkdev.h> #include <linux/atomic.h> #include <linux/kthread.h> #include <linux/fs.h> #include <linux/blk-mq.h> /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) /* Max limits for throttle policy */ #define THROTL_IOPS_MAX UINT_MAX #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP enum blkg_iostat_type { BLKG_IOSTAT_READ, BLKG_IOSTAT_WRITE, BLKG_IOSTAT_DISCARD, BLKG_IOSTAT_NR, }; struct blkcg_gq; struct blkcg { struct cgroup_subsys_state css; spinlock_t lock; refcount_t online_pin; struct radix_tree_root blkg_tree; struct blkcg_gq __rcu *blkg_hint; struct hlist_head blkg_list; struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; struct list_head all_blkcgs_node; #ifdef CONFIG_BLK_CGROUP_FC_APPID char fc_app_id[FC_APPID_LEN]; #endif #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; #endif }; struct blkg_iostat { u64 bytes[BLKG_IOSTAT_NR]; u64 ios[BLKG_IOSTAT_NR]; }; struct blkg_iostat_set { struct u64_stats_sync sync; struct blkg_iostat cur; struct blkg_iostat last; }; /* * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a * request_queue (q). This is used by blkcg policies which need to track * information per blkcg - q pair. * * There can be multiple active blkcg policies and each blkg:policy pair is * represented by a blkg_policy_data which is allocated and freed by each * policy's pd_alloc/free_fn() methods. A policy can allocate private data * area by allocating larger data structure which embeds blkg_policy_data * at the beginning. */ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; }; /* * Policies that need to keep per-blkcg data which is independent from any * request_queue associated to it should implement cpd_alloc/free_fn() * methods. A policy can allocate private data area by allocating larger * data structure which embeds blkcg_policy_data at the beginning. * cpd_init() is invoked to let each policy handle per-blkcg data. */ struct blkcg_policy_data { /* the blkcg and policy id this per-policy data belongs to */ struct blkcg *blkcg; int plid; }; /* association between a blk cgroup and a request queue */ struct blkcg_gq { /* Pointer to the associated request_queue */ struct request_queue *q; struct list_head q_node; struct hlist_node blkcg_node; struct blkcg *blkcg; /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; /* reference count */ struct percpu_ref refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; struct blkg_iostat_set __percpu *iostat_cpu; struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; spinlock_t async_bio_lock; struct bio_list async_bios; struct work_struct async_bio_work; atomic_t use_delay; atomic64_t delay_nsec; atomic64_t delay_start; u64 last_delay; int last_use; struct rcu_head rcu_head; }; typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg); typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, struct seq_file *s); struct blkcg_policy { int plid; /* cgroup files for the policy */ struct cftype *dfl_cftypes; struct cftype *legacy_cftypes; /* operations */ blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; blkcg_pol_init_cpd_fn *cpd_init_fn; blkcg_pol_free_cpd_fn *cpd_free_fn; blkcg_pol_bind_cpd_fn *cpd_bind_fn; blkcg_pol_alloc_pd_fn *pd_alloc_fn; blkcg_pol_init_pd_fn *pd_init_fn; blkcg_pol_online_pd_fn *pd_online_fn; blkcg_pol_offline_pd_fn *pd_offline_fn; blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; blkcg_pol_stat_pd_fn *pd_stat_fn; }; extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); int blkcg_init_queue(struct request_queue *q); void blkcg_exit_queue(struct request_queue *q); /* Blkio controller policy registration */ int blkcg_policy_register(struct blkcg_policy *pol); void blkcg_policy_unregister(struct blkcg_policy *pol); int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol); void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol); const char *blkg_dev_name(struct blkcg_gq *blkg); void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), const struct blkcg_policy *pol, int data, bool show_total); u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); struct blkg_conf_ctx { struct block_device *bdev; struct blkcg_gq *blkg; char *body; }; struct block_device *blkcg_conf_open_bdev(char **inputp); int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); /** * blkcg_css - find the current css * * Find the css associated with either the kthread or the current task. * This may return a dying css, so it is up to the caller to use tryget logic * to confirm it is alive and well. */ static inline struct cgroup_subsys_state *blkcg_css(void) { struct cgroup_subsys_state *css; css = kthread_blkcg(); if (css) return css; return task_css(current, io_cgrp_id); } static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } /** * __bio_blkcg - internal, inconsistent version to get blkcg * * DO NOT USE. * This function is inconsistent and consequently is dangerous to use. The * first part of the function returns a blkcg where a reference is owned by the * bio. This means it does not need to be rcu protected as it cannot go away * with the bio owning a reference to it. However, the latter potentially gets * it from task_css(). This can race against task migration and the cgroup * dying. It is also semantically different as it must be called rcu protected * and is susceptible to failure when trying to get a reference to it. * Therefore, it is not ok to assume that *_get() will always succeed on the * blkcg returned here. */ static inline struct blkcg *__bio_blkcg(struct bio *bio) { if (bio && bio->bi_blkg) return bio->bi_blkg->blkcg; return css_to_blkcg(blkcg_css()); } /** * bio_blkcg - grab the blkcg associated with a bio * @bio: target bio * * This returns the blkcg associated with a bio, %NULL if not associated. * Callers are expected to either handle %NULL or know association has been * done prior to calling this. */ static inline struct blkcg *bio_blkcg(struct bio *bio) { if (bio && bio->bi_blkg) return bio->bi_blkg->blkcg; return NULL; } static inline bool blk_cgroup_congested(void) { struct cgroup_subsys_state *css; bool ret = false; rcu_read_lock(); css = kthread_blkcg(); if (!css) css = task_css(current, io_cgrp_id); while (css) { if (atomic_read(&css->cgroup->congestion_count)) { ret = true; break; } css = css->parent; } rcu_read_unlock(); return ret; } /** * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg * @return: true if this bio needs to be submitted with the root blkg context. * * In order to avoid priority inversions we sometimes need to issue a bio as if * it were attached to the root blkg, and then backcharge to the actual owning * blkg. The idea is we do bio_blkcg() to look up the actual context for the * bio and attach the appropriate blkg to the bio. Then we call this helper and * if it is true run with the root blkg for that queue and then do any * backcharging to the originating cgroup once the io is complete. */ static inline bool bio_issue_as_root_blkg(struct bio *bio) { return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; } /** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * * Return the parent blkcg of @blkcg. Can be called anytime. */ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) { return css_to_blkcg(blkcg->css.parent); } /** * __blkg_lookup - internal version of blkg_lookup() * @blkcg: blkcg of interest * @q: request_queue of interest * @update_hint: whether to update lookup hint with the result or not * * This is internal version and shouldn't be used by policy * implementations. Looks up blkgs for the @blkcg - @q pair regardless of * @q's bypass state. If @update_hint is %true, the caller should be * holding @q->queue_lock and lookup hint is updated on success. */ static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, bool update_hint) { struct blkcg_gq *blkg; if (blkcg == &blkcg_root) return q->root_blkg; blkg = rcu_dereference(blkcg->blkg_hint); if (blkg && blkg->q == q) return blkg; return blkg_lookup_slowpath(blkcg, q, update_hint); } /** * blkg_lookup - lookup blkg for the specified blkcg - q pair * @blkcg: blkcg of interest * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. This function should be called * under RCU read lock. */ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q) { WARN_ON_ONCE(!rcu_read_lock_held()); return __blkg_lookup(blkcg, q, false); } /** * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair * @q: request_queue of interest * * Lookup blkg for @q at the root level. See also blkg_lookup(). */ static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) { return q->root_blkg; } /** * blkg_to_pdata - get policy private data * @blkg: blkg of interest * @pol: policy of interest * * Return pointer to private data associated with the @blkg-@pol pair. */ static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return blkg ? blkg->pd[pol->plid] : NULL; } static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, struct blkcg_policy *pol) { return blkcg ? blkcg->cpd[pol->plid] : NULL; } /** * pdata_to_blkg - get blkg associated with policy private data * @pd: policy private data of interest * * @pd is policy private data. Determine the blkg it's associated with. */ static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return pd ? pd->blkg : NULL; } static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) { return cpd ? cpd->blkcg : NULL; } extern void blkcg_destroy_blkgs(struct blkcg *blkcg); /** * blkcg_pin_online - pin online state * @blkcg: blkcg of interest * * While pinned, a blkcg is kept online. This is primarily used to * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline * while an associated cgwb is still active. */ static inline void blkcg_pin_online(struct blkcg *blkcg) { refcount_inc(&blkcg->online_pin); } /** * blkcg_unpin_online - unpin online state * @blkcg: blkcg of interest * * This is primarily used to impedance-match blkg and cgwb lifetimes so * that blkg doesn't go offline while an associated cgwb is still active. * When this count goes to zero, all active cgwbs have finished so the * blkcg can continue destruction by calling blkcg_destroy_blkgs(). */ static inline void blkcg_unpin_online(struct blkcg *blkcg) { do { if (!refcount_dec_and_test(&blkcg->online_pin)) break; blkcg_destroy_blkgs(blkcg); blkcg = blkcg_parent(blkcg); } while (blkcg); } /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest * @buf: target buffer * @buflen: target buffer length * * Format the path of the cgroup of @blkg into @buf. */ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) { return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); } /** * blkg_get - get a blkg reference * @blkg: blkg to get * * The caller should be holding an existing reference. */ static inline void blkg_get(struct blkcg_gq *blkg) { percpu_ref_get(&blkg->refcnt); } /** * blkg_tryget - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ static inline bool blkg_tryget(struct blkcg_gq *blkg) { return blkg && percpu_ref_tryget(&blkg->refcnt); } /** * blkg_put - put a blkg reference * @blkg: blkg to put */ static inline void blkg_put(struct blkcg_gq *blkg) { percpu_ref_put(&blkg->refcnt); } /** * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU * read locked. If called under either blkcg or queue lock, the iteration * is guaranteed to include all and only online blkgs. The caller may * update @pos_css by calling css_rightmost_descendant() to skip subtree. * @p_blkg is included in the iteration and the first node to be visited. */ #define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) /** * blkg_for_each_descendant_post - post-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant * @pos_css: used for iteration * @p_blkg: target blkg to walk descendants of * * Similar to blkg_for_each_descendant_pre() but performs post-order * traversal instead. Synchronization rules are the same. @p_blkg is * included in the iteration and the last node to be visited. */ #define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) bool __blkcg_punt_bio_submit(struct bio *bio); static inline bool blkcg_punt_bio_submit(struct bio *bio) { if (bio->bi_opf & REQ_CGROUP_PUNT) return __blkcg_punt_bio_submit(bio); else return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { bio_issue_init(&bio->bi_issue, bio_sectors(bio)); } static inline void blkcg_use_delay(struct blkcg_gq *blkg) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) return; if (atomic_add_return(1, &blkg->use_delay) == 1) atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); } static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); if (WARN_ON_ONCE(old < 0)) return 0; if (old == 0) return 0; /* * We do this song and dance because we can race with somebody else * adding or removing delay. If we just did an atomic_dec we'd end up * negative and we'd already be in trouble. We need to subtract 1 and * then check to see if we were the last delay so we can drop the * congestion count on the cgroup. */ while (old) { int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1); if (cur == old) break; old = cur; } if (old == 0) return 0; if (old == 1) atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); return 1; } /** * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount * @blkg: target blkg * @delay: delay duration in nsecs * * When enabled with this function, the delay is not decayed and must be * explicitly cleared with blkcg_clear_delay(). Must not be mixed with * blkcg_[un]use_delay() and blkcg_add_delay() usages. */ static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) { int old = atomic_read(&blkg->use_delay); /* We only want 1 person setting the congestion count for this blkg. */ if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old) atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); atomic64_set(&blkg->delay_nsec, delay); } /** * blkcg_clear_delay - Disable allocator delay mechanism * @blkg: target blkg * * Disable use_delay mechanism. See blkcg_set_delay(). */ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) { int old = atomic_read(&blkg->use_delay); /* We only want 1 person clearing the congestion count for this blkg. */ if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old) atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); } /** * blk_cgroup_mergeable - Determine whether to allow or disallow merges * @rq: request to merge into * @bio: bio to merge * * @bio and @rq should belong to the same cgroup and their issue_as_root should * match. The latter is necessary as we don't want to throttle e.g. a metadata * update because it happens to be next to a regular IO. */ static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return rq->bio->bi_blkg == bio->bi_blkg && bio_issue_as_root_blkg(rq->bio) == bio_issue_as_root_blkg(bio); } void blk_cgroup_bio_start(struct bio *bio); void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); #else /* CONFIG_BLK_CGROUP */ struct blkcg { }; struct blkg_policy_data { }; struct blkcg_policy_data { }; struct blkcg_gq { }; struct blkcg_policy { }; #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } #ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) { return NULL; } static inline int blkcg_init_queue(struct request_queue *q) { return 0; } static inline void blkcg_exit_queue(struct request_queue *q) { } static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } static inline int blkcg_activate_policy(struct request_queue *q, const struct blkcg_policy *pol) { return 0; } static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, struct blkcg_policy *pol) { return NULL; } static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline void blk_cgroup_bio_start(struct bio *bio) { } static inline bool blk_cgroup_mergeable(struct request *rq, struct bio *bio) { return true; } #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) #endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_BLK_CGROUP_FC_APPID /* * Sets the fc_app_id field associted to blkcg * @app_id: application identifier * @cgrp_id: cgroup id * @app_id_len: size of application identifier */ static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) { struct cgroup *cgrp; struct cgroup_subsys_state *css; struct blkcg *blkcg; int ret = 0; if (app_id_len > FC_APPID_LEN) return -EINVAL; cgrp = cgroup_get_from_id(cgrp_id); if (!cgrp) return -ENOENT; css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); if (!css) { ret = -ENOENT; goto out_cgrp_put; } blkcg = css_to_blkcg(css); /* * There is a slight race condition on setting the appid. * Worst case an I/O may not find the right id. * This is no different from the I/O we let pass while obtaining * the vmid from the fabric. * Adding the overhead of a lock is not necessary. */ strlcpy(blkcg->fc_app_id, app_id, app_id_len); css_put(css); out_cgrp_put: cgroup_put(cgrp); return ret; } /** * blkcg_get_fc_appid - get the fc app identifier associated with a bio * @bio: target bio * * On success return the fc_app_id, on failure return NULL */ static inline char *blkcg_get_fc_appid(struct bio *bio) { if (bio && bio->bi_blkg && (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) return bio->bi_blkg->blkcg->fc_app_id; return NULL; } #else static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } #endif /*CONFIG_BLK_CGROUP_FC_APPID*/ #endif /* _BLK_CGROUP_H */ |
| 2 2 2 2 2 2 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 | // SPDX-License-Identifier: GPL-2.0-only /* * IEEE 802.1Q Multiple Registration Protocol (MRP) * * Copyright (c) 2012 Massachusetts Institute of Technology * * Adapted from code in net/802/garp.c * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/timer.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/module.h> #include <net/mrp.h> #include <asm/unaligned.h> static unsigned int mrp_join_time __read_mostly = 200; module_param(mrp_join_time, uint, 0644); MODULE_PARM_DESC(mrp_join_time, "Join time in ms (default 200ms)"); static unsigned int mrp_periodic_time __read_mostly = 1000; module_param(mrp_periodic_time, uint, 0644); MODULE_PARM_DESC(mrp_periodic_time, "Periodic time in ms (default 1s)"); MODULE_LICENSE("GPL"); static const u8 mrp_applicant_state_table[MRP_APPLICANT_MAX + 1][MRP_EVENT_MAX + 1] = { [MRP_APPLICANT_VO] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_VP, [MRP_EVENT_LV] = MRP_APPLICANT_VO, [MRP_EVENT_TX] = MRP_APPLICANT_VO, [MRP_EVENT_R_NEW] = MRP_APPLICANT_VO, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_AO, [MRP_EVENT_R_IN] = MRP_APPLICANT_VO, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_VO, [MRP_EVENT_R_MT] = MRP_APPLICANT_VO, [MRP_EVENT_R_LV] = MRP_APPLICANT_VO, [MRP_EVENT_R_LA] = MRP_APPLICANT_VO, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VO, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_VO, }, [MRP_APPLICANT_VP] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_VP, [MRP_EVENT_LV] = MRP_APPLICANT_VO, [MRP_EVENT_TX] = MRP_APPLICANT_AA, [MRP_EVENT_R_NEW] = MRP_APPLICANT_VP, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_AP, [MRP_EVENT_R_IN] = MRP_APPLICANT_VP, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_VP, [MRP_EVENT_R_MT] = MRP_APPLICANT_VP, [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_VP, }, [MRP_APPLICANT_VN] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_VN, [MRP_EVENT_LV] = MRP_APPLICANT_LA, [MRP_EVENT_TX] = MRP_APPLICANT_AN, [MRP_EVENT_R_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_VN, [MRP_EVENT_R_IN] = MRP_APPLICANT_VN, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_VN, [MRP_EVENT_R_MT] = MRP_APPLICANT_VN, [MRP_EVENT_R_LV] = MRP_APPLICANT_VN, [MRP_EVENT_R_LA] = MRP_APPLICANT_VN, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VN, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_VN, }, [MRP_APPLICANT_AN] = { [MRP_EVENT_NEW] = MRP_APPLICANT_AN, [MRP_EVENT_JOIN] = MRP_APPLICANT_AN, [MRP_EVENT_LV] = MRP_APPLICANT_LA, [MRP_EVENT_TX] = MRP_APPLICANT_QA, [MRP_EVENT_R_NEW] = MRP_APPLICANT_AN, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_AN, [MRP_EVENT_R_IN] = MRP_APPLICANT_AN, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AN, [MRP_EVENT_R_MT] = MRP_APPLICANT_AN, [MRP_EVENT_R_LV] = MRP_APPLICANT_VN, [MRP_EVENT_R_LA] = MRP_APPLICANT_VN, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VN, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AN, }, [MRP_APPLICANT_AA] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_AA, [MRP_EVENT_LV] = MRP_APPLICANT_LA, [MRP_EVENT_TX] = MRP_APPLICANT_QA, [MRP_EVENT_R_NEW] = MRP_APPLICANT_AA, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QA, [MRP_EVENT_R_IN] = MRP_APPLICANT_AA, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AA, [MRP_EVENT_R_MT] = MRP_APPLICANT_AA, [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AA, }, [MRP_APPLICANT_QA] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_QA, [MRP_EVENT_LV] = MRP_APPLICANT_LA, [MRP_EVENT_TX] = MRP_APPLICANT_QA, [MRP_EVENT_R_NEW] = MRP_APPLICANT_QA, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QA, [MRP_EVENT_R_IN] = MRP_APPLICANT_QA, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AA, [MRP_EVENT_R_MT] = MRP_APPLICANT_AA, [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AA, }, [MRP_APPLICANT_LA] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_AA, [MRP_EVENT_LV] = MRP_APPLICANT_LA, [MRP_EVENT_TX] = MRP_APPLICANT_VO, [MRP_EVENT_R_NEW] = MRP_APPLICANT_LA, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_LA, [MRP_EVENT_R_IN] = MRP_APPLICANT_LA, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_LA, [MRP_EVENT_R_MT] = MRP_APPLICANT_LA, [MRP_EVENT_R_LV] = MRP_APPLICANT_LA, [MRP_EVENT_R_LA] = MRP_APPLICANT_LA, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_LA, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_LA, }, [MRP_APPLICANT_AO] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_AP, [MRP_EVENT_LV] = MRP_APPLICANT_AO, [MRP_EVENT_TX] = MRP_APPLICANT_AO, [MRP_EVENT_R_NEW] = MRP_APPLICANT_AO, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QO, [MRP_EVENT_R_IN] = MRP_APPLICANT_AO, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AO, [MRP_EVENT_R_MT] = MRP_APPLICANT_AO, [MRP_EVENT_R_LV] = MRP_APPLICANT_VO, [MRP_EVENT_R_LA] = MRP_APPLICANT_VO, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VO, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AO, }, [MRP_APPLICANT_QO] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_QP, [MRP_EVENT_LV] = MRP_APPLICANT_QO, [MRP_EVENT_TX] = MRP_APPLICANT_QO, [MRP_EVENT_R_NEW] = MRP_APPLICANT_QO, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QO, [MRP_EVENT_R_IN] = MRP_APPLICANT_QO, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AO, [MRP_EVENT_R_MT] = MRP_APPLICANT_AO, [MRP_EVENT_R_LV] = MRP_APPLICANT_VO, [MRP_EVENT_R_LA] = MRP_APPLICANT_VO, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VO, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_QO, }, [MRP_APPLICANT_AP] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_AP, [MRP_EVENT_LV] = MRP_APPLICANT_AO, [MRP_EVENT_TX] = MRP_APPLICANT_QA, [MRP_EVENT_R_NEW] = MRP_APPLICANT_AP, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QP, [MRP_EVENT_R_IN] = MRP_APPLICANT_AP, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AP, [MRP_EVENT_R_MT] = MRP_APPLICANT_AP, [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AP, }, [MRP_APPLICANT_QP] = { [MRP_EVENT_NEW] = MRP_APPLICANT_VN, [MRP_EVENT_JOIN] = MRP_APPLICANT_QP, [MRP_EVENT_LV] = MRP_APPLICANT_QO, [MRP_EVENT_TX] = MRP_APPLICANT_QP, [MRP_EVENT_R_NEW] = MRP_APPLICANT_QP, [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QP, [MRP_EVENT_R_IN] = MRP_APPLICANT_QP, [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AP, [MRP_EVENT_R_MT] = MRP_APPLICANT_AP, [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AP, }, }; static const u8 mrp_tx_action_table[MRP_APPLICANT_MAX + 1] = { [MRP_APPLICANT_VO] = MRP_TX_ACTION_S_IN_OPTIONAL, [MRP_APPLICANT_VP] = MRP_TX_ACTION_S_JOIN_IN, [MRP_APPLICANT_VN] = MRP_TX_ACTION_S_NEW, [MRP_APPLICANT_AN] = MRP_TX_ACTION_S_NEW, [MRP_APPLICANT_AA] = MRP_TX_ACTION_S_JOIN_IN, [MRP_APPLICANT_QA] = MRP_TX_ACTION_S_JOIN_IN_OPTIONAL, [MRP_APPLICANT_LA] = MRP_TX_ACTION_S_LV, [MRP_APPLICANT_AO] = MRP_TX_ACTION_S_IN_OPTIONAL, [MRP_APPLICANT_QO] = MRP_TX_ACTION_S_IN_OPTIONAL, [MRP_APPLICANT_AP] = MRP_TX_ACTION_S_JOIN_IN, [MRP_APPLICANT_QP] = MRP_TX_ACTION_S_IN_OPTIONAL, }; static void mrp_attrvalue_inc(void *value, u8 len) { u8 *v = (u8 *)value; /* Add 1 to the last byte. If it becomes zero, * go to the previous byte and repeat. */ while (len > 0 && !++v[--len]) ; } static int mrp_attr_cmp(const struct mrp_attr *attr, const void *value, u8 len, u8 type) { if (attr->type != type) return attr->type - type; if (attr->len != len) return attr->len - len; return memcmp(attr->value, value, len); } static struct mrp_attr *mrp_attr_lookup(const struct mrp_applicant *app, const void *value, u8 len, u8 type) { struct rb_node *parent = app->mad.rb_node; struct mrp_attr *attr; int d; while (parent) { attr = rb_entry(parent, struct mrp_attr, node); d = mrp_attr_cmp(attr, value, len, type); if (d > 0) parent = parent->rb_left; else if (d < 0) parent = parent->rb_right; else return attr; } return NULL; } static struct mrp_attr *mrp_attr_create(struct mrp_applicant *app, const void *value, u8 len, u8 type) { struct rb_node *parent = NULL, **p = &app->mad.rb_node; struct mrp_attr *attr; int d; while (*p) { parent = *p; attr = rb_entry(parent, struct mrp_attr, node); d = mrp_attr_cmp(attr, value, len, type); if (d > 0) p = &parent->rb_left; else if (d < 0) p = &parent->rb_right; else { /* The attribute already exists; re-use it. */ return attr; } } attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC); if (!attr) return attr; attr->state = MRP_APPLICANT_VO; attr->type = type; attr->len = len; memcpy(attr->value, value, len); rb_link_node(&attr->node, parent, p); rb_insert_color(&attr->node, &app->mad); return attr; } static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr) { rb_erase(&attr->node, &app->mad); kfree(attr); } static void mrp_attr_destroy_all(struct mrp_applicant *app) { struct rb_node *node, *next; struct mrp_attr *attr; for (node = rb_first(&app->mad); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct mrp_attr, node); mrp_attr_destroy(app, attr); } } static int mrp_pdu_init(struct mrp_applicant *app) { struct sk_buff *skb; struct mrp_pdu_hdr *ph; skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev), GFP_ATOMIC); if (!skb) return -ENOMEM; skb->dev = app->dev; skb->protocol = app->app->pkttype.type; skb_reserve(skb, LL_RESERVED_SPACE(app->dev)); skb_reset_network_header(skb); skb_reset_transport_header(skb); ph = __skb_put(skb, sizeof(*ph)); ph->version = app->app->version; app->pdu = skb; return 0; } static int mrp_pdu_append_end_mark(struct mrp_applicant *app) { __be16 *endmark; if (skb_tailroom(app->pdu) < sizeof(*endmark)) return -1; endmark = __skb_put(app->pdu, sizeof(*endmark)); put_unaligned(MRP_END_MARK, endmark); return 0; } static void mrp_pdu_queue(struct mrp_applicant *app) { if (!app->pdu) return; if (mrp_cb(app->pdu)->mh) mrp_pdu_append_end_mark(app); mrp_pdu_append_end_mark(app); dev_hard_header(app->pdu, app->dev, ntohs(app->app->pkttype.type), app->app->group_address, app->dev->dev_addr, app->pdu->len); skb_queue_tail(&app->queue, app->pdu); app->pdu = NULL; } static void mrp_queue_xmit(struct mrp_applicant *app) { struct sk_buff *skb; while ((skb = skb_dequeue(&app->queue))) dev_queue_xmit(skb); } static int mrp_pdu_append_msg_hdr(struct mrp_applicant *app, u8 attrtype, u8 attrlen) { struct mrp_msg_hdr *mh; if (mrp_cb(app->pdu)->mh) { if (mrp_pdu_append_end_mark(app) < 0) return -1; mrp_cb(app->pdu)->mh = NULL; mrp_cb(app->pdu)->vah = NULL; } if (skb_tailroom(app->pdu) < sizeof(*mh)) return -1; mh = __skb_put(app->pdu, sizeof(*mh)); mh->attrtype = attrtype; mh->attrlen = attrlen; mrp_cb(app->pdu)->mh = mh; return 0; } static int mrp_pdu_append_vecattr_hdr(struct mrp_applicant *app, const void *firstattrvalue, u8 attrlen) { struct mrp_vecattr_hdr *vah; if (skb_tailroom(app->pdu) < sizeof(*vah) + attrlen) return -1; vah = __skb_put(app->pdu, sizeof(*vah) + attrlen); put_unaligned(0, &vah->lenflags); memcpy(vah->firstattrvalue, firstattrvalue, attrlen); mrp_cb(app->pdu)->vah = vah; memcpy(mrp_cb(app->pdu)->attrvalue, firstattrvalue, attrlen); return 0; } static int mrp_pdu_append_vecattr_event(struct mrp_applicant *app, const struct mrp_attr *attr, enum mrp_vecattr_event vaevent) { u16 len, pos; u8 *vaevents; int err; again: if (!app->pdu) { err = mrp_pdu_init(app); if (err < 0) return err; } /* If there is no Message header in the PDU, or the Message header is * for a different attribute type, add an EndMark (if necessary) and a * new Message header to the PDU. */ if (!mrp_cb(app->pdu)->mh || mrp_cb(app->pdu)->mh->attrtype != attr->type || mrp_cb(app->pdu)->mh->attrlen != attr->len) { if (mrp_pdu_append_msg_hdr(app, attr->type, attr->len) < 0) goto queue; } /* If there is no VectorAttribute header for this Message in the PDU, * or this attribute's value does not sequentially follow the previous * attribute's value, add a new VectorAttribute header to the PDU. */ if (!mrp_cb(app->pdu)->vah || memcmp(mrp_cb(app->pdu)->attrvalue, attr->value, attr->len)) { if (mrp_pdu_append_vecattr_hdr(app, attr->value, attr->len) < 0) goto queue; } len = be16_to_cpu(get_unaligned(&mrp_cb(app->pdu)->vah->lenflags)); pos = len % 3; /* Events are packed into Vectors in the PDU, three to a byte. Add a * byte to the end of the Vector if necessary. */ if (!pos) { if (skb_tailroom(app->pdu) < sizeof(u8)) goto queue; vaevents = __skb_put(app->pdu, sizeof(u8)); } else { vaevents = (u8 *)(skb_tail_pointer(app->pdu) - sizeof(u8)); } switch (pos) { case 0: *vaevents = vaevent * (__MRP_VECATTR_EVENT_MAX * __MRP_VECATTR_EVENT_MAX); break; case 1: *vaevents += vaevent * __MRP_VECATTR_EVENT_MAX; break; case 2: *vaevents += vaevent; break; default: WARN_ON(1); } /* Increment the length of the VectorAttribute in the PDU, as well as * the value of the next attribute that would continue its Vector. */ put_unaligned(cpu_to_be16(++len), &mrp_cb(app->pdu)->vah->lenflags); mrp_attrvalue_inc(mrp_cb(app->pdu)->attrvalue, attr->len); return 0; queue: mrp_pdu_queue(app); goto again; } static void mrp_attr_event(struct mrp_applicant *app, struct mrp_attr *attr, enum mrp_event event) { enum mrp_applicant_state state; state = mrp_applicant_state_table[attr->state][event]; if (state == MRP_APPLICANT_INVALID) { WARN_ON(1); return; } if (event == MRP_EVENT_TX) { /* When appending the attribute fails, don't update its state * in order to retry at the next TX event. */ switch (mrp_tx_action_table[attr->state]) { case MRP_TX_ACTION_NONE: case MRP_TX_ACTION_S_JOIN_IN_OPTIONAL: case MRP_TX_ACTION_S_IN_OPTIONAL: break; case MRP_TX_ACTION_S_NEW: if (mrp_pdu_append_vecattr_event( app, attr, MRP_VECATTR_EVENT_NEW) < 0) return; break; case MRP_TX_ACTION_S_JOIN_IN: if (mrp_pdu_append_vecattr_event( app, attr, MRP_VECATTR_EVENT_JOIN_IN) < 0) return; break; case MRP_TX_ACTION_S_LV: if (mrp_pdu_append_vecattr_event( app, attr, MRP_VECATTR_EVENT_LV) < 0) return; /* As a pure applicant, sending a leave message * implies that the attribute was unregistered and * can be destroyed. */ mrp_attr_destroy(app, attr); return; default: WARN_ON(1); } } attr->state = state; } int mrp_request_join(const struct net_device *dev, const struct mrp_application *appl, const void *value, u8 len, u8 type) { struct mrp_port *port = rtnl_dereference(dev->mrp_port); struct mrp_applicant *app = rtnl_dereference( port->applicants[appl->type]); struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > sizeof_field(struct sk_buff, cb)) return -ENOMEM; spin_lock_bh(&app->lock); attr = mrp_attr_create(app, value, len, type); if (!attr) { spin_unlock_bh(&app->lock); return -ENOMEM; } mrp_attr_event(app, attr, MRP_EVENT_JOIN); spin_unlock_bh(&app->lock); return 0; } EXPORT_SYMBOL_GPL(mrp_request_join); void mrp_request_leave(const struct net_device *dev, const struct mrp_application *appl, const void *value, u8 len, u8 type) { struct mrp_port *port = rtnl_dereference(dev->mrp_port); struct mrp_applicant *app = rtnl_dereference( port->applicants[appl->type]); struct mrp_attr *attr; if (sizeof(struct mrp_skb_cb) + len > sizeof_field(struct sk_buff, cb)) return; spin_lock_bh(&app->lock); attr = mrp_attr_lookup(app, value, len, type); if (!attr) { spin_unlock_bh(&app->lock); return; } mrp_attr_event(app, attr, MRP_EVENT_LV); spin_unlock_bh(&app->lock); } EXPORT_SYMBOL_GPL(mrp_request_leave); static void mrp_mad_event(struct mrp_applicant *app, enum mrp_event event) { struct rb_node *node, *next; struct mrp_attr *attr; for (node = rb_first(&app->mad); next = node ? rb_next(node) : NULL, node != NULL; node = next) { attr = rb_entry(node, struct mrp_attr, node); mrp_attr_event(app, attr, event); } } static void mrp_join_timer_arm(struct mrp_applicant *app) { unsigned long delay; delay = (u64)msecs_to_jiffies(mrp_join_time) * prandom_u32() >> 32; mod_timer(&app->join_timer, jiffies + delay); } static void mrp_join_timer(struct timer_list *t) { struct mrp_applicant *app = from_timer(app, t, join_timer); spin_lock(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); mrp_pdu_queue(app); spin_unlock(&app->lock); mrp_queue_xmit(app); spin_lock(&app->lock); if (likely(app->active)) mrp_join_timer_arm(app); spin_unlock(&app->lock); } static void mrp_periodic_timer_arm(struct mrp_applicant *app) { mod_timer(&app->periodic_timer, jiffies + msecs_to_jiffies(mrp_periodic_time)); } static void mrp_periodic_timer(struct timer_list *t) { struct mrp_applicant *app = from_timer(app, t, periodic_timer); spin_lock(&app->lock); if (likely(app->active)) { mrp_mad_event(app, MRP_EVENT_PERIODIC); mrp_pdu_queue(app); mrp_periodic_timer_arm(app); } spin_unlock(&app->lock); } static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) { __be16 endmark; if (skb_copy_bits(skb, *offset, &endmark, sizeof(endmark)) < 0) return -1; if (endmark == MRP_END_MARK) { *offset += sizeof(endmark); return -1; } return 0; } static void mrp_pdu_parse_vecattr_event(struct mrp_applicant *app, struct sk_buff *skb, enum mrp_vecattr_event vaevent) { struct mrp_attr *attr; enum mrp_event event; attr = mrp_attr_lookup(app, mrp_cb(skb)->attrvalue, mrp_cb(skb)->mh->attrlen, mrp_cb(skb)->mh->attrtype); if (attr == NULL) return; switch (vaevent) { case MRP_VECATTR_EVENT_NEW: event = MRP_EVENT_R_NEW; break; case MRP_VECATTR_EVENT_JOIN_IN: event = MRP_EVENT_R_JOIN_IN; break; case MRP_VECATTR_EVENT_IN: event = MRP_EVENT_R_IN; break; case MRP_VECATTR_EVENT_JOIN_MT: event = MRP_EVENT_R_JOIN_MT; break; case MRP_VECATTR_EVENT_MT: event = MRP_EVENT_R_MT; break; case MRP_VECATTR_EVENT_LV: event = MRP_EVENT_R_LV; break; default: return; } mrp_attr_event(app, attr, event); } static int mrp_pdu_parse_vecattr(struct mrp_applicant *app, struct sk_buff *skb, int *offset) { struct mrp_vecattr_hdr _vah; u16 valen; u8 vaevents, vaevent; mrp_cb(skb)->vah = skb_header_pointer(skb, *offset, sizeof(_vah), &_vah); if (!mrp_cb(skb)->vah) return -1; *offset += sizeof(_vah); if (get_unaligned(&mrp_cb(skb)->vah->lenflags) & MRP_VECATTR_HDR_FLAG_LA) mrp_mad_event(app, MRP_EVENT_R_LA); valen = be16_to_cpu(get_unaligned(&mrp_cb(skb)->vah->lenflags) & MRP_VECATTR_HDR_LEN_MASK); /* The VectorAttribute structure in a PDU carries event information * about one or more attributes having consecutive values. Only the * value for the first attribute is contained in the structure. So * we make a copy of that value, and then increment it each time we * advance to the next event in its Vector. */ if (sizeof(struct mrp_skb_cb) + mrp_cb(skb)->mh->attrlen > sizeof_field(struct sk_buff, cb)) return -1; if (skb_copy_bits(skb, *offset, mrp_cb(skb)->attrvalue, mrp_cb(skb)->mh->attrlen) < 0) return -1; *offset += mrp_cb(skb)->mh->attrlen; /* In a VectorAttribute, the Vector contains events which are packed * three to a byte. We process one byte of the Vector at a time. */ while (valen > 0) { if (skb_copy_bits(skb, *offset, &vaevents, sizeof(vaevents)) < 0) return -1; *offset += sizeof(vaevents); /* Extract and process the first event. */ vaevent = vaevents / (__MRP_VECATTR_EVENT_MAX * __MRP_VECATTR_EVENT_MAX); if (vaevent >= __MRP_VECATTR_EVENT_MAX) { /* The byte is malformed; stop processing. */ return -1; } mrp_pdu_parse_vecattr_event(app, skb, vaevent); /* If present, extract and process the second event. */ if (!--valen) break; mrp_attrvalue_inc(mrp_cb(skb)->attrvalue, mrp_cb(skb)->mh->attrlen); vaevents %= (__MRP_VECATTR_EVENT_MAX * __MRP_VECATTR_EVENT_MAX); vaevent = vaevents / __MRP_VECATTR_EVENT_MAX; mrp_pdu_parse_vecattr_event(app, skb, vaevent); /* If present, extract and process the third event. */ if (!--valen) break; mrp_attrvalue_inc(mrp_cb(skb)->attrvalue, mrp_cb(skb)->mh->attrlen); vaevents %= __MRP_VECATTR_EVENT_MAX; vaevent = vaevents; mrp_pdu_parse_vecattr_event(app, skb, vaevent); } return 0; } static int mrp_pdu_parse_msg(struct mrp_applicant *app, struct sk_buff *skb, int *offset) { struct mrp_msg_hdr _mh; mrp_cb(skb)->mh = skb_header_pointer(skb, *offset, sizeof(_mh), &_mh); if (!mrp_cb(skb)->mh) return -1; *offset += sizeof(_mh); if (mrp_cb(skb)->mh->attrtype == 0 || mrp_cb(skb)->mh->attrtype > app->app->maxattr || mrp_cb(skb)->mh->attrlen == 0) return -1; while (skb->len > *offset) { if (mrp_pdu_parse_end_mark(skb, offset) < 0) break; if (mrp_pdu_parse_vecattr(app, skb, offset) < 0) return -1; } return 0; } static int mrp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct mrp_application *appl = container_of(pt, struct mrp_application, pkttype); struct mrp_port *port; struct mrp_applicant *app; struct mrp_pdu_hdr _ph; const struct mrp_pdu_hdr *ph; int offset = skb_network_offset(skb); /* If the interface is in promiscuous mode, drop the packet if * it was unicast to another host. */ if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) goto out; skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto out; port = rcu_dereference(dev->mrp_port); if (unlikely(!port)) goto out; app = rcu_dereference(port->applicants[appl->type]); if (unlikely(!app)) goto out; ph = skb_header_pointer(skb, offset, sizeof(_ph), &_ph); if (!ph) goto out; offset += sizeof(_ph); if (ph->version != app->app->version) goto out; spin_lock(&app->lock); while (skb->len > offset) { if (mrp_pdu_parse_end_mark(skb, &offset) < 0) break; if (mrp_pdu_parse_msg(app, skb, &offset) < 0) break; } spin_unlock(&app->lock); out: kfree_skb(skb); return 0; } static int mrp_init_port(struct net_device *dev) { struct mrp_port *port; port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; rcu_assign_pointer(dev->mrp_port, port); return 0; } static void mrp_release_port(struct net_device *dev) { struct mrp_port *port = rtnl_dereference(dev->mrp_port); unsigned int i; for (i = 0; i <= MRP_APPLICATION_MAX; i++) { if (rtnl_dereference(port->applicants[i])) return; } RCU_INIT_POINTER(dev->mrp_port, NULL); kfree_rcu(port, rcu); } int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) { struct mrp_applicant *app; int err; ASSERT_RTNL(); if (!rtnl_dereference(dev->mrp_port)) { err = mrp_init_port(dev); if (err < 0) goto err1; } err = -ENOMEM; app = kzalloc(sizeof(*app), GFP_KERNEL); if (!app) goto err2; err = dev_mc_add(dev, appl->group_address); if (err < 0) goto err3; app->dev = dev; app->app = appl; app->mad = RB_ROOT; app->active = true; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); timer_setup(&app->join_timer, mrp_join_timer, 0); mrp_join_timer_arm(app); timer_setup(&app->periodic_timer, mrp_periodic_timer, 0); mrp_periodic_timer_arm(app); return 0; err3: kfree(app); err2: mrp_release_port(dev); err1: return err; } EXPORT_SYMBOL_GPL(mrp_init_applicant); void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) { struct mrp_port *port = rtnl_dereference(dev->mrp_port); struct mrp_applicant *app = rtnl_dereference( port->applicants[appl->type]); ASSERT_RTNL(); RCU_INIT_POINTER(port->applicants[appl->type], NULL); spin_lock_bh(&app->lock); app->active = false; spin_unlock_bh(&app->lock); /* Delete timer and generate a final TX event to flush out * all pending messages before the applicant is gone. */ del_timer_sync(&app->join_timer); del_timer_sync(&app->periodic_timer); spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); mrp_attr_destroy_all(app); mrp_pdu_queue(app); spin_unlock_bh(&app->lock); mrp_queue_xmit(app); dev_mc_del(dev, appl->group_address); kfree_rcu(app, rcu); mrp_release_port(dev); } EXPORT_SYMBOL_GPL(mrp_uninit_applicant); int mrp_register_application(struct mrp_application *appl) { appl->pkttype.func = mrp_rcv; dev_add_pack(&appl->pkttype); return 0; } EXPORT_SYMBOL_GPL(mrp_register_application); void mrp_unregister_application(struct mrp_application *appl) { dev_remove_pack(&appl->pkttype); } EXPORT_SYMBOL_GPL(mrp_unregister_application); |
| 21 15 21 21 21 21 21 21 25 22 5 19 8 15 37 1 2 1 35 37 37 37 7 34 34 32 1 34 1 32 12 11 30 37 15 3 15 15 15 2 1 15 15 15 15 15 15 15 15 2 15 15 15 15 15 15 15 15 15 15 14 14 5 14 14 14 14 14 14 14 14 14 14 14 14 2 12 14 14 2 12 3 20 17 9 2 14 14 14 2 1 1 62 21 21 21 5 5 5 1 5 5 5 5 5 5 5 3 19 8 2 3 5 1 1 1 2 7 15 13 2 4 11 10 1 6 7 21 21 21 5 21 21 21 21 21 21 21 21 21 2 16 21 21 15 15 2 2 1 1 1 5 3 5 5 1 4 68 69 39 30 30 30 30 28 2 28 2 30 30 30 30 30 179 178 179 4053 560 3883 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * kernel/cpuset.c * * Processor and Memory placement constraints for sets of tasks. * * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2007 Silicon Graphics, Inc. * Copyright (C) 2006 Google, Inc * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #include "cgroup-internal.h" #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/kthread.h> #include <linux/list.h> #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/memory.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/deadline.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/seq_file.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/time.h> #include <linux/time64.h> #include <linux/backing-dev.h> #include <linux/sort.h> #include <linux/oom.h> #include <linux/sched/isolation.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h> #include <linux/cgroup.h> #include <linux/wait.h> DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* See "Frequency meter" comments, below. */ struct fmeter { int cnt; /* unprocessed events count */ int val; /* most recent output value */ time64_t time; /* clock (secs) when val computed */ spinlock_t lock; /* guards read or write of above */ }; struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ /* * On default hierarchy: * * The user-configured masks can only be changed by writing to * cpuset.cpus and cpuset.mems, and won't be limited by the * parent masks. * * The effective masks is the real masks that apply to the tasks * in the cpuset. They may be changed if the configured masks are * changed or hotplug happens. * * effective_mask == configured_mask & parent's effective_mask, * and if it ends up empty, it will inherit the parent's mask. * * * On legacy hierarchy: * * The user-configured masks are always the same with effective masks. */ /* user-configured CPUs and Memory Nodes allow to tasks */ cpumask_var_t cpus_allowed; nodemask_t mems_allowed; /* effective CPUs and Memory Nodes allow to tasks */ cpumask_var_t effective_cpus; nodemask_t effective_mems; /* * CPUs allocated to child sub-partitions (default hierarchy only) * - CPUs granted by the parent = effective_cpus U subparts_cpus * - effective_cpus and subparts_cpus are mutually exclusive. * * effective_cpus contains only onlined CPUs, but subparts_cpus * may have offlined ones. */ cpumask_var_t subparts_cpus; /* * This is old Memory Nodes tasks took on. * * - top_cpuset.old_mems_allowed is initialized to mems_allowed. * - A new cpuset's old_mems_allowed is initialized when some * task is moved into it. * - old_mems_allowed is used in cpuset_migrate_mm() when we change * cpuset.mems_allowed and have tasks' nodemask updated, and * then old_mems_allowed is updated to mems_allowed. */ nodemask_t old_mems_allowed; struct fmeter fmeter; /* memory_pressure filter */ /* * Tasks are being attached to this cpuset. Used to prevent * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). */ int attach_in_progress; /* partition number for rebuild_sched_domains() */ int pn; /* for custom sched domain */ int relax_domain_level; /* number of CPUs in subparts_cpus */ int nr_subparts_cpus; /* partition root state */ int partition_root_state; /* * Default hierarchy only: * use_parent_ecpus - set if using parent's effective_cpus * child_ecpus_count - # of children with use_parent_ecpus set */ int use_parent_ecpus; int child_ecpus_count; /* * number of SCHED_DEADLINE tasks attached to this cpuset, so that we * know when to rebuild associated root domain bandwidth information. */ int nr_deadline_tasks; int nr_migrate_dl_tasks; u64 sum_migrate_dl_bw; /* Handle for cpuset.cpus.partition */ struct cgroup_file partition_file; }; /* * Partition root states: * * 0 - not a partition root * * 1 - partition root * * -1 - invalid partition root * None of the cpus in cpus_allowed can be put into the parent's * subparts_cpus. In this case, the cpuset is not a real partition * root anymore. However, the CPU_EXCLUSIVE bit will still be set * and the cpuset can be restored back to a partition root if the * parent cpuset can give more CPUs back to this child cpuset. */ #define PRS_DISABLED 0 #define PRS_ENABLED 1 #define PRS_ERROR -1 /* * Temporary cpumasks for working with partitions that are passed among * functions to avoid memory allocation in inner functions. */ struct tmpmasks { cpumask_var_t addmask, delmask; /* For partition root */ cpumask_var_t new_cpus; /* For update_cpumasks_hier() */ }; static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) { return css ? container_of(css, struct cpuset, css) : NULL; } /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { return css_cs(task_css(task, cpuset_cgrp_id)); } static inline struct cpuset *parent_cs(struct cpuset *cs) { return css_cs(cs->css.parent); } void inc_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks++; } void dec_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks--; } /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, CS_MEM_HARDWALL, CS_MEMORY_MIGRATE, CS_SCHED_LOAD_BALANCE, CS_SPREAD_PAGE, CS_SPREAD_SLAB, } cpuset_flagbits_t; /* convenient tests for these bits */ static inline bool is_cpuset_online(struct cpuset *cs) { return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) { return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); } static inline int is_mem_exclusive(const struct cpuset *cs) { return test_bit(CS_MEM_EXCLUSIVE, &cs->flags); } static inline int is_mem_hardwall(const struct cpuset *cs) { return test_bit(CS_MEM_HARDWALL, &cs->flags); } static inline int is_sched_load_balance(const struct cpuset *cs) { return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } static inline int is_memory_migrate(const struct cpuset *cs) { return test_bit(CS_MEMORY_MIGRATE, &cs->flags); } static inline int is_spread_page(const struct cpuset *cs) { return test_bit(CS_SPREAD_PAGE, &cs->flags); } static inline int is_spread_slab(const struct cpuset *cs) { return test_bit(CS_SPREAD_SLAB, &cs->flags); } static inline int is_partition_root(const struct cpuset *cs) { return cs->partition_root_state > 0; } /* * Send notification event of whenever partition_root_state changes. */ static inline void notify_partition_change(struct cpuset *cs, int old_prs, int new_prs) { if (old_prs != new_prs) cgroup_file_notify(&cs->partition_file); } static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), .partition_root_state = PRS_ENABLED, }; /** * cpuset_for_each_child - traverse online children of a cpuset * @child_cs: loop cursor pointing to the current child * @pos_css: used for iteration * @parent_cs: target cpuset to walk children of * * Walk @child_cs through the online children of @parent_cs. Must be used * with RCU read locked. */ #define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ css_for_each_child((pos_css), &(parent_cs)->css) \ if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) /** * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants * @des_cs: loop cursor pointing to the current descendant * @pos_css: used for iteration * @root_cs: target cpuset to walk ancestor of * * Walk @des_cs through the online descendants of @root_cs. Must be used * with RCU read locked. The caller may modify @pos_css by calling * css_rightmost_descendant() to skip subtree. @root_cs is included in the * iteration and the first node to be visited. */ #define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset * structures. Note that cpuset_mutex needs to be a mutex as it is used in * paths that rely on priority inheritance (e.g. scheduler - on RT) for * correctness. * * A task must hold both locks to modify cpusets. If a task holds * cpuset_mutex, it blocks others, ensuring that it is the only task able to * also acquire callback_lock and be able to modify cpusets. It can perform * various checks on the cpuset structure first, knowing nothing will change. * It can also allocate memory while just holding cpuset_mutex. While it is * performing these checks, various callback routines can briefly acquire * callback_lock to query cpusets. Once it is ready to make the changes, it * takes callback_lock, blocking everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock * from one of the callbacks into the cpuset code from within * __alloc_pages(). * * If a task is only holding callback_lock, then it has read-only * access to cpusets. * * Now, the task_struct fields mems_allowed and mempolicy may be changed * by other task, we use alloc_lock in the task_struct fields to protect * them. * * The cpuset_common_file_read() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. * * Accessing a task's cpuset should be done in accordance with the * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(cpuset_mutex); void cpuset_lock(void) { mutex_lock(&cpuset_mutex); } void cpuset_unlock(void) { mutex_unlock(&cpuset_mutex); } static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; /* * CPU / memory hotplug is handled asynchronously. */ static void cpuset_hotplug_workfn(struct work_struct *work); static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option. * With v2 behavior, "cpus" and "mems" are always what the users have * requested and won't be changed by hotplug events. Only the effective * cpus or mems will be affected. */ static inline bool is_in_v2_mode(void) { return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); } /* * Return in pmask the portion of a task's cpusets's cpus_allowed that * are online and are capable of running the task. If none are found, * walk up the cpuset hierarchy until we find one that does have some * appropriate cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct task_struct *tsk, struct cpumask *pmask) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); struct cpuset *cs; if (WARN_ON(!cpumask_and(pmask, possible_mask, cpu_online_mask))) cpumask_copy(pmask, cpu_online_mask); rcu_read_lock(); cs = task_cs(tsk); while (!cpumask_intersects(cs->effective_cpus, pmask)) { cs = parent_cs(cs); if (unlikely(!cs)) { /* * The top cpuset doesn't have any online cpu as a * consequence of a race between cpuset_hotplug_work * and cpu hotplug notifier. But we know the top * cpuset's effective_cpus is on its way to be * identical to cpu_online_mask. */ goto out_unlock; } } cpumask_and(pmask, pmask, cs->effective_cpus); out_unlock: rcu_read_unlock(); } /* * Return in *pmask the portion of a cpusets's mems_allowed that * are online, with memory. If none are online with memory, walk * up the cpuset hierarchy until we find one that does have some * online mems. The top cpuset always has some mems online. * * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY])) cs = parent_cs(cs); nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]); } /* * update task's spread flag if cpuset's page/slab spread flag is set * * Call with callback_lock or cpuset_mutex held. */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) task_set_spread_page(tsk); else task_clear_spread_page(tsk); if (is_spread_slab(cs)) task_set_spread_slab(tsk); else task_clear_spread_slab(tsk); } /* * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); } /** * alloc_cpumasks - allocate three cpumasks for cpuset * @cs: the cpuset that have cpumasks to be allocated. * @tmp: the tmpmasks structure pointer * Return: 0 if successful, -ENOMEM otherwise. * * Only one of the two input arguments should be non-NULL. */ static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { cpumask_var_t *pmask1, *pmask2, *pmask3; if (cs) { pmask1 = &cs->cpus_allowed; pmask2 = &cs->effective_cpus; pmask3 = &cs->subparts_cpus; } else { pmask1 = &tmp->new_cpus; pmask2 = &tmp->addmask; pmask3 = &tmp->delmask; } if (!zalloc_cpumask_var(pmask1, GFP_KERNEL)) return -ENOMEM; if (!zalloc_cpumask_var(pmask2, GFP_KERNEL)) goto free_one; if (!zalloc_cpumask_var(pmask3, GFP_KERNEL)) goto free_two; return 0; free_two: free_cpumask_var(*pmask2); free_one: free_cpumask_var(*pmask1); return -ENOMEM; } /** * free_cpumasks - free cpumasks in a tmpmasks structure * @cs: the cpuset that have cpumasks to be free. * @tmp: the tmpmasks structure pointer */ static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { if (cs) { free_cpumask_var(cs->cpus_allowed); free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->subparts_cpus); } if (tmp) { free_cpumask_var(tmp->new_cpus); free_cpumask_var(tmp->addmask); free_cpumask_var(tmp->delmask); } } /** * alloc_trial_cpuset - allocate a trial cpuset * @cs: the cpuset that the trial cpuset duplicates */ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) { struct cpuset *trial; trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); if (!trial) return NULL; if (alloc_cpumasks(trial, NULL)) { kfree(trial); return NULL; } cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); cpumask_copy(trial->effective_cpus, cs->effective_cpus); return trial; } /** * free_cpuset - free the cpuset * @cs: the cpuset to be freed */ static inline void free_cpuset(struct cpuset *cs) { free_cpumasks(cs, NULL); kfree(cs); } /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the * cpuset in the list must use cur below, not trial. * * 'trial' is the address of bulk structure copy of cur, with * perhaps one or more of the fields cpus_allowed, mems_allowed, * or flags changed to new, trial values. * * Return 0 if valid, -errno if not. */ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; int ret; rcu_read_lock(); /* Each of our child cpusets must be a subset of us */ ret = -EBUSY; cpuset_for_each_child(c, css, cur) if (!is_cpuset_subset(c, trial)) goto out; /* Remaining checks don't apply to root cpuset */ ret = 0; if (cur == &top_cpuset) goto out; par = parent_cs(cur); /* On legacy hierarchy, we must be a subset of our parent cpuset. */ ret = -EACCES; if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) goto out; /* * If either I or some sibling (!= me) is exclusive, we can't * overlap */ ret = -EINVAL; cpuset_for_each_child(c, css, par) { if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) goto out; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && nodes_intersects(trial->mems_allowed, c->mems_allowed)) goto out; } /* * Cpusets with tasks - existing or newly being attached - can't * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) { if (!cpumask_empty(cur->cpus_allowed) && cpumask_empty(trial->cpus_allowed)) goto out; if (!nodes_empty(cur->mems_allowed) && nodes_empty(trial->mems_allowed)) goto out; } /* * We can't shrink if we won't have enough room for SCHED_DEADLINE * tasks. */ ret = -EBUSY; if (is_cpu_exclusive(cur) && !cpuset_cpumask_can_shrink(cur->cpus_allowed, trial->cpus_allowed)) goto out; ret = 0; out: rcu_read_unlock(); return ret; } #ifdef CONFIG_SMP /* * Helper routine for generate_sched_domains(). * Do cpusets a, b have overlapping effective cpus_allowed masks? */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { return cpumask_intersects(a->effective_cpus, b->effective_cpus); } static void update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) { if (dattr->relax_domain_level < c->relax_domain_level) dattr->relax_domain_level = c->relax_domain_level; return; } static void update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *root_cs) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (is_sched_load_balance(cp)) update_domain_attr(dattr, cp); } rcu_read_unlock(); } /* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ return static_key_count(&cpusets_enabled_key.key) + 1; } /* * generate_sched_domains() * * This function builds a partial partition of the systems CPUs * A 'partial partition' is a set of non-overlapping subsets whose * union is a subset of that set. * The output of this function needs to be passed to kernel/sched/core.c * partition_sched_domains() routine, which will rebuild the scheduler's * load balancing domains (sched domains) as specified by that partial * partition. * * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this * routine would rather not worry about failures to rebuild sched * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a * top-down scan of all cpusets. For our purposes, rebuilding * the schedulers sched domains, we can ignore !is_sched_load_ * balance cpusets. * csa - (for CpuSet Array) Array of pointers to all the cpusets * that need to be load balanced, for convenient iterative * access by the subsequent code that finds the best partition, * i.e the set of domains (subsets) of CPUs such that the * cpus_allowed of every cpuset marked is_sched_load_balance * is a subset of one of these domains, while there are as * many such domains as possible, each as small as possible. * doms - Conversion of 'csa' to an array of cpumasks, for passing to * the kernel/sched/core.c routine partition_sched_domains() in a * convenient format, that can be easily compared to the prior * value to determine what partition elements (sched domains) * were changed (added or removed.) * * Finding the best partition (set of domains): * The triple nested loops below over i, j, k scan over the * load balanced cpusets (using the array of cpuset pointers in * csa[]) looking for pairs of cpusets that have overlapping * cpus_allowed, but which don't have the same 'pn' partition * number and gives them in the same partition number. It keeps * looping on the 'restart' label until it can no longer find * any such pairs. * * The union of the cpus_allowed masks from the set of * all cpusets having the same 'pn' value then form the one * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { struct cpuset *cp; /* top-down scan of cpusets */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ struct cgroup_subsys_state *pos_css; bool root_load_balance = is_sched_load_balance(&top_cpuset); doms = NULL; dattr = NULL; csa = NULL; /* Special case for the 99% of systems with one, full, sched domain */ if (root_load_balance && !top_cpuset.nr_subparts_cpus) { ndoms = 1; doms = alloc_sched_domains(ndoms); if (!doms) goto done; dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); if (dattr) { *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, housekeeping_cpumask(HK_FLAG_DOMAIN)); goto done; } csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; rcu_read_lock(); if (root_load_balance) csa[csn++] = &top_cpuset; cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { if (cp == &top_cpuset) continue; /* * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The * latter: All child cpusets contain a subset of the * parent's cpus, so just skip them, and then we call * update_domain_attr_tree() to calc relax_domain_level of * the corresponding sched domain. * * If root is load-balancing, we can skip @cp if it * is a subset of the root's effective_cpus. */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && cpumask_intersects(cp->cpus_allowed, housekeeping_cpumask(HK_FLAG_DOMAIN)))) continue; if (root_load_balance && cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) continue; if (is_sched_load_balance(cp) && !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* skip @cp's subtree if not a partition root */ if (!is_partition_root(cp)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); for (i = 0; i < csn; i++) csa[i]->pn = i; ndoms = csn; restart: /* Find the best partition (set of sched domains) */ for (i = 0; i < csn; i++) { struct cpuset *a = csa[i]; int apn = a->pn; for (j = 0; j < csn; j++) { struct cpuset *b = csa[j]; int bpn = b->pn; if (apn != bpn && cpusets_overlap(a, b)) { for (k = 0; k < csn; k++) { struct cpuset *c = csa[k]; if (c->pn == bpn) c->pn = apn; } ndoms--; /* one less element */ goto restart; } } } /* * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = alloc_sched_domains(ndoms); if (!doms) goto done; /* * The rest of the code, including the scheduler, can deal with * dattr==NULL case. No need to abort if alloc fails. */ dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), GFP_KERNEL); for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; struct cpumask *dp; int apn = a->pn; if (apn < 0) { /* Skip completed partitions */ continue; } dp = doms[nslot]; if (nslot == ndoms) { static int warnings = 10; if (warnings) { pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n", nslot, ndoms, csn, i, apn); warnings--; } continue; } cpumask_clear(dp); if (dattr) *(dattr + nslot) = SD_ATTR_INIT; for (j = i; j < csn; j++) { struct cpuset *b = csa[j]; if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); /* Done with this partition */ b->pn = -1; } } nslot++; } BUG_ON(nslot != ndoms); done: kfree(csa); /* * Fallback to the default domain if kmalloc() failed. * See comments in partition_sched_domains(). */ if (doms == NULL) ndoms = 1; *domains = doms; *attributes = dattr; return ndoms; } static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; if (cs->nr_deadline_tasks == 0) return; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) dl_add_task_root_domain(task); css_task_iter_end(&it); } static void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); rcu_read_lock(); /* * Clear default root domain DL accounting, it will be computed again * if a task belongs to it. */ dl_clear_root_domain(&def_root_domain); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cpumask_empty(cs->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } css_get(&cs->css); rcu_read_unlock(); dl_update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } static void partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); dl_rebuild_rd_accounting(); mutex_unlock(&sched_domains_mutex); } /* * Rebuild scheduler domains. * * If the flag 'sched_load_balance' of any cpuset with non-empty * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset * which has that flag enabled, or if any cpuset with a non-empty * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * * Call with cpuset_mutex held. Takes cpus_read_lock(). */ static void rebuild_sched_domains_locked(void) { struct cgroup_subsys_state *pos_css; struct sched_domain_attr *attr; cpumask_var_t *doms; struct cpuset *cs; int ndoms; lockdep_assert_cpus_held(); lockdep_assert_held(&cpuset_mutex); /* * If we have raced with CPU hotplug, return early to avoid * passing doms with offlined cpu to partition_sched_domains(). * Anyways, cpuset_hotplug_workfn() will rebuild sched domains. * * With no CPUs in any subpartitions, top_cpuset's effective CPUs * should be the same as the active CPUs, so checking only top_cpuset * is enough to detect racing CPU offlines. */ if (!top_cpuset.nr_subparts_cpus && !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) return; /* * With subpartition CPUs, however, the effective CPUs of a partition * root should be only a subset of the active CPUs. Since a CPU in any * partition root could be offlined, all must be checked. */ if (top_cpuset.nr_subparts_cpus) { rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (!is_partition_root(cs)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!cpumask_subset(cs->effective_cpus, cpu_active_mask)) { rcu_read_unlock(); return; } } rcu_read_unlock(); } /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_and_rebuild_sched_domains(ndoms, doms, attr); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) { } #endif /* CONFIG_SMP */ void rebuild_sched_domains(void) { cpus_read_lock(); mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; bool top_cs = cs == &top_cpuset; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { /* * Percpu kthreads in top_cpuset are ignored */ if (top_cs && (task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) continue; set_cpus_allowed_ptr(task, cs->effective_cpus); } css_task_iter_end(&it); } /** * compute_effective_cpumask - Compute the effective cpumask of the cpuset * @new_cpus: the temp variable for the new effective_cpus mask * @cs: the cpuset the need to recompute the new effective_cpus mask * @parent: the parent cpuset * * If the parent has subpartition CPUs, include them in the list of * allowable CPUs in computing the new effective_cpus mask. Since offlined * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask * to mask those out. */ static void compute_effective_cpumask(struct cpumask *new_cpus, struct cpuset *cs, struct cpuset *parent) { if (parent->nr_subparts_cpus) { cpumask_or(new_cpus, parent->effective_cpus, parent->subparts_cpus); cpumask_and(new_cpus, new_cpus, cs->cpus_allowed); cpumask_and(new_cpus, new_cpus, cpu_active_mask); } else { cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus); } } /* * Commands for update_parent_subparts_cpumask */ enum subparts_cmd { partcmd_enable, /* Enable partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's subparts_cpus */ }; /** * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset * @cpuset: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask * Return: 0, 1 or an error code * * For partcmd_enable, the cpuset is being transformed from a non-partition * root to a partition root. The cpus_allowed mask of the given cpuset will * be put into parent's subparts_cpus and taken away from parent's * effective_cpus. The function will return 0 if all the CPUs listed in * cpus_allowed can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transofrmed from a partition * root back to a non-partition root. Any CPUs in cpus_allowed that are in * parent's subparts_cpus will be taken away from that cpumask and put back * into parent's effective_cpus. 0 should always be returned. * * For partcmd_update, if the optional newmask is specified, the cpu * list is to be changed from cpus_allowed to newmask. Otherwise, * cpus_allowed is assumed to remain the same. The cpuset should either * be a partition root or an invalid partition root. The partition root * state may change if newmask is NULL and none of the requested CPUs can * be granted by the parent. The function will return 1 if changes to * parent's subparts_cpus and effective_cpus happen or 0 otherwise. * Error code should only be returned when newmask is non-NULL. * * The partcmd_enable and partcmd_disable commands are used by * update_prstate(). The partcmd_update command is used by * update_cpumasks_hier() with newmask NULL and update_cpumask() with * newmask set. * * The checking is more strict when enabling partition root than the * other two commands. * * Because of the implicit cpu exclusive nature of a partition root, * cpumask changes that violates the cpu exclusivity rule will not be * permitted when checked by validate_change(). The validate_change() * function will also prevent any changes to the cpu list if it is not * a superset of children's cpu lists. */ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpumask *newmask, struct tmpmasks *tmp) { struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ int old_prs, new_prs; bool part_error = false; /* Partition error? */ lockdep_assert_held(&cpuset_mutex); /* * The parent must be a partition root. * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ if (!is_partition_root(parent) || (newmask && cpumask_empty(newmask)) || (!newmask && cpumask_empty(cpuset->cpus_allowed))) return -EINVAL; /* * Enabling/disabling partition root is not allowed if there are * online children. */ if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css)) return -EBUSY; /* * Enabling partition root is not allowed if not all the CPUs * can be granted from parent's effective_cpus or at least one * CPU will be left after that. */ if ((cmd == partcmd_enable) && (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) return -EINVAL; /* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; old_prs = new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } else if (newmask) { /* * partcmd_update with newmask: * * delmask = cpus_allowed & ~newmask & parent->subparts_cpus * addmask = newmask & parent->effective_cpus * & ~parent->subparts_cpus */ cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->subparts_cpus); cpumask_and(tmp->addmask, newmask, parent->effective_cpus); adding = cpumask_andnot(tmp->addmask, tmp->addmask, parent->subparts_cpus); /* * Return error if the new effective_cpus could become empty. */ if (adding && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) return -EINVAL; /* * As some of the CPUs in subparts_cpus might have * been offlined, we need to compute the real delmask * to confirm that. */ if (!cpumask_and(tmp->addmask, tmp->delmask, cpu_active_mask)) return -EINVAL; cpumask_copy(tmp->addmask, parent->effective_cpus); } } else { /* * partcmd_update w/o newmask: * * addmask = cpus_allowed & parent->effective_cpus * * Note that parent's subparts_cpus may have been * pre-shrunk in case there is a change in the cpu list. * So no deletion is needed. */ adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed, parent->effective_cpus); part_error = cpumask_equal(tmp->addmask, parent->effective_cpus); } if (cmd == partcmd_update) { int prev_prs = cpuset->partition_root_state; /* * Check for possible transition between PRS_ENABLED * and PRS_ERROR. */ switch (cpuset->partition_root_state) { case PRS_ENABLED: if (part_error) new_prs = PRS_ERROR; break; case PRS_ERROR: if (!part_error) new_prs = PRS_ENABLED; break; } /* * Set part_error if previously in invalid state. */ part_error = (prev_prs == PRS_ERROR); } if (!part_error && (new_prs == PRS_ERROR)) return 0; /* Nothing need to be done */ if (new_prs == PRS_ERROR) { /* * Remove all its cpus from parent's subparts_cpus. */ adding = false; deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } if (!adding && !deleting && (new_prs == old_prs)) return 0; /* * Change the parent's subparts_cpus. * Newly added CPUs will be removed from effective_cpus and * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); if (adding) { cpumask_or(parent->subparts_cpus, parent->subparts_cpus, tmp->addmask); cpumask_andnot(parent->effective_cpus, parent->effective_cpus, tmp->addmask); } if (deleting) { cpumask_andnot(parent->subparts_cpus, parent->subparts_cpus, tmp->delmask); /* * Some of the CPUs in subparts_cpus might have been offlined. */ cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, tmp->delmask); } parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); if (old_prs != new_prs) cpuset->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cpuset, old_prs, new_prs); return cmd == partcmd_update; } /* * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree * @cs: the cpuset to consider * @tmp: temp variables for calculating effective_cpus & partition setup * * When configured cpumask is changed, the effective cpumasks of this cpuset * and all its descendants need to be updated. * * On legacy hierarchy, effective_cpus will be the same with cpu_allowed. * * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; int old_prs, new_prs; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); compute_effective_cpumask(tmp->new_cpus, cp, parent); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; parent->child_ecpus_count++; } } else if (cp->use_parent_ecpus) { cp->use_parent_ecpus = false; WARN_ON_ONCE(!parent->child_ecpus_count); parent->child_ecpus_count--; } /* * Skip the whole subtree if the cpumask remains the same * and has no partition root state. */ if (!cp->partition_root_state && cpumask_equal(tmp->new_cpus, cp->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ old_prs = new_prs = cp->partition_root_state; if ((cp != cs) && old_prs) { switch (parent->partition_root_state) { case PRS_DISABLED: /* * If parent is not a partition root or an * invalid partition root, clear its state * and its CS_CPU_EXCLUSIVE flag. */ WARN_ON_ONCE(cp->partition_root_state != PRS_ERROR); new_prs = PRS_DISABLED; /* * clear_bit() is an atomic operation and * readers aren't interested in the state * of CS_CPU_EXCLUSIVE anyway. So we can * just update the flag without holding * the callback_lock. */ clear_bit(CS_CPU_EXCLUSIVE, &cp->flags); break; case PRS_ENABLED: if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp)) update_tasks_cpumask(parent); break; case PRS_ERROR: /* * When parent is invalid, it has to be too. */ new_prs = PRS_ERROR; break; } } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { /* * Make sure that effective_cpus & subparts_cpus * are mutually exclusive. * * In the unlikely event that effective_cpus * becomes empty. we clear cp->nr_subparts_cpus and * let its child partition roots to compete for * CPUs again. */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); if (cpumask_empty(cp->effective_cpus)) { cpumask_copy(cp->effective_cpus, tmp->new_cpus); cpumask_clear(cp->subparts_cpus); cp->nr_subparts_cpus = 0; } else if (!cpumask_subset(cp->subparts_cpus, tmp->new_cpus)) { cpumask_andnot(cp->subparts_cpus, cp->subparts_cpus, tmp->new_cpus); cp->nr_subparts_cpus = cpumask_weight(cp->subparts_cpus); } } if (new_prs != old_prs) cp->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cp, old_prs, new_prs); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); update_tasks_cpumask(cp); /* * On legacy hierarchy, if the effective cpumask of any non- * empty cpuset is changed, we need to rebuild sched domains. * On default hierarchy, the cpuset needs to be a partition * root as well. */ if (!cpumask_empty(cp->cpus_allowed) && is_sched_load_balance(cp) && (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || is_partition_root(cp))) need_rebuild_sched_domains = true; rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); if (need_rebuild_sched_domains) rebuild_sched_domains_locked(); } /** * update_sibling_cpumasks - Update siblings cpumasks * @parent: Parent cpuset * @cs: Current cpuset * @tmp: Temp variables */ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *sibling; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); /* * Check all its siblings and call update_cpumasks_hier() * if their use_parent_ecpus flag is set in order for them * to use the right effective_cpus value. * * The update_cpumasks_hier() function may sleep. So we have to * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { if (sibling == cs) continue; if (!sibling->use_parent_ecpus) continue; if (!css_tryget_online(&sibling->css)) continue; rcu_read_unlock(); update_cpumasks_hier(sibling, tmp); rcu_read_lock(); css_put(&sibling->css); } rcu_read_unlock(); } /** * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset */ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ if (cs == &top_cpuset) return -EACCES; /* * An empty cpus_allowed is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have cpus. */ if (!*buf) { cpumask_clear(trialcs->cpus_allowed); } else { retval = cpulist_parse(buf, trialcs->cpus_allowed); if (retval < 0) return retval; if (!cpumask_subset(trialcs->cpus_allowed, top_cpuset.cpus_allowed)) return -EINVAL; } /* Nothing to do if the cpus didn't change */ if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) return 0; retval = validate_change(cs, trialcs); if (retval < 0) return retval; #ifdef CONFIG_CPUMASK_OFFSTACK /* * Use the cpumasks in trialcs for tmpmasks when they are pointers * to allocated cpumasks. */ tmp.addmask = trialcs->subparts_cpus; tmp.delmask = trialcs->effective_cpus; tmp.new_cpus = trialcs->cpus_allowed; #endif if (cs->partition_root_state) { /* Cpumask of a partition root cannot be empty */ if (cpumask_empty(trialcs->cpus_allowed)) return -EINVAL; if (update_parent_subparts_cpumask(cs, partcmd_update, trialcs->cpus_allowed, &tmp) < 0) return -EINVAL; } spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); /* * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } spin_unlock_irq(&callback_lock); update_cpumasks_hier(cs, &tmp); if (cs->partition_root_state) { struct cpuset *parent = parent_cs(cs); /* * For partition root, update the cpumasks of sibling * cpusets if they use parent's effective_cpus. */ if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmp); } return 0; } /* * Migrate memory region from one set of nodes to another. This is * performed asynchronously as it can be called from process migration path * holding locks involved in process management. All mm migrations are * performed in the queued order and can be waited for by flushing * cpuset_migrate_mm_wq. */ struct cpuset_migrate_mm_work { struct work_struct work; struct mm_struct *mm; nodemask_t from; nodemask_t to; }; static void cpuset_migrate_mm_workfn(struct work_struct *work) { struct cpuset_migrate_mm_work *mwork = container_of(work, struct cpuset_migrate_mm_work, work); /* on a wq worker, no need to worry about %current's mems_allowed */ do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); mmput(mwork->mm); kfree(mwork); } static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { struct cpuset_migrate_mm_work *mwork; if (nodes_equal(*from, *to)) { mmput(mm); return; } mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); if (mwork) { mwork->mm = mm; mwork->from = *from; mwork->to = *to; INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); queue_work(cpuset_migrate_mm_wq, &mwork->work); } else { mmput(mm); } } static void cpuset_post_attach(void) { flush_workqueue(cpuset_migrate_mm_wq); } /* * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy * @tsk: the task to change * @newmems: new nodes that the task will be set * * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed * and rebind an eventual tasks' mempolicy. If the task is allocating in * parallel, it might temporarily see an empty intersection, which results in * a seqlock check and retry before OOM or allocation failure. */ static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { task_lock(tsk); local_irq_disable(); write_seqcount_begin(&tsk->mems_allowed_seq); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems); tsk->mems_allowed = *newmems; write_seqcount_end(&tsk->mems_allowed_seq); local_irq_enable(); task_unlock(tsk); } static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ guarantee_online_mems(cs, &newmems); /* * The mpol_rebind_mm() call takes mmap_lock, which we couldn't * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { struct mm_struct *mm; bool migrate; cpuset_change_task_nodemask(task, &newmems); mm = get_task_mm(task); if (!mm) continue; migrate = is_memory_migrate(cs); mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else mmput(mm); } css_task_iter_end(&it); /* * All the tasks' nodemasks have been updated, update * cs->old_mems_allowed. */ cs->old_mems_allowed = newmems; /* We're done rebinding vmas to this cpuset's new mems_allowed. */ cpuset_being_rebound = NULL; } /* * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree * @cs: the cpuset to consider * @new_mems: a temp variable for calculating new effective_mems * * When configured nodemask is changed, the effective nodemasks of this cpuset * and all its descendants need to be updated. * * On legacy hierarchy, effective_mems will be the same with mems_allowed. * * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some MEMs. */ if (is_in_v2_mode() && nodes_empty(*new_mems)) *new_mems = parent->effective_mems; /* Skip the whole subtree if the nodemask remains the same. */ if (nodes_equal(*new_mems, cp->effective_mems)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); update_tasks_nodemask(cp); rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); } /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the * cpusets mems_allowed, and for each task in the cpuset, * update mems_allowed and rebind task's mempolicy and any vma * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; /* * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; * it's read-only */ if (cs == &top_cpuset) { retval = -EACCES; goto done; } /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * Since nodelist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have memory. */ if (!*buf) { nodes_clear(trialcs->mems_allowed); } else { retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) goto done; if (!nodes_subset(trialcs->mems_allowed, top_cpuset.mems_allowed)) { retval = -EINVAL; goto done; } } if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } retval = validate_change(cs, trialcs); if (retval < 0) goto done; spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); done: return retval; } bool current_cpuset_is_being_rebound(void) { bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; rcu_read_unlock(); return ret; } static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP if (val < -1 || val > sched_domain_level_max + 1) return -EINVAL; #endif if (val != cs->relax_domain_level) { cs->relax_domain_level = val; if (!cpumask_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) rebuild_sched_domains_locked(); } return 0; } /** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) cpuset_update_task_spread_flag(cs, task); css_task_iter_end(&it); } /* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; int balance_flag_changed; int spread_flag_changed; int err; trialcs = alloc_trial_cpuset(cs); if (!trialcs) return -ENOMEM; if (turning_on) set_bit(bit, &trialcs->flags); else clear_bit(bit, &trialcs->flags); err = validate_change(cs, trialcs); if (err < 0) goto out; balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) || (is_spread_page(cs) != is_spread_page(trialcs))); spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) rebuild_sched_domains_locked(); if (spread_flag_changed) update_tasks_flags(cs); out: free_cpuset(trialcs); return err; } /* * update_prstate - update partititon_root_state * cs: the cpuset to update * new_prs: new partition root state * * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { int err, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; if (old_prs == new_prs) return 0; /* * Cannot force a partial or invalid partition root to a full * partition root. */ if (new_prs && (old_prs == PRS_ERROR)) return -EINVAL; if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM; err = -EINVAL; if (!old_prs) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed * cannot be NULL. */ if (cpumask_empty(cs->cpus_allowed)) goto out; err = update_flag(CS_CPU_EXCLUSIVE, cs, 1); if (err) goto out; err = update_parent_subparts_cpumask(cs, partcmd_enable, NULL, &tmpmask); if (err) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } } else { /* * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ if (old_prs == PRS_ERROR) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; } err = update_parent_subparts_cpumask(cs, partcmd_disable, NULL, &tmpmask); if (err) goto out; /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } update_tasks_cpumask(parent); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask); rebuild_sched_domains_locked(); out: if (!err) { spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); notify_partition_change(cs, old_prs, new_prs); } free_cpumasks(NULL, &tmpmask); return err; } /* * Frequency meter - How fast is some event occurring? * * These routines manage a digitally filtered, constant time based, * event frequency meter. There are four routines: * fmeter_init() - initialize a frequency meter. * fmeter_markevent() - called each time the event happens. * fmeter_getrate() - returns the recent rate of such events. * fmeter_update() - internal routine used to update fmeter. * * A common data structure is passed to each of these routines, * which is used to keep track of the state required to manage the * frequency meter and its digital filter. * * The filter works on the number of events marked per unit time. * The filter is single-pole low-pass recursive (IIR). The time unit * is 1 second. Arithmetic is done using 32-bit integers scaled to * simulate 3 decimal digits of precision (multiplied by 1000). * * With an FM_COEF of 933, and a time base of 1 second, the filter * has a half-life of 10 seconds, meaning that if the events quit * happening, then the rate returned from the fmeter_getrate() * will be cut in half each 10 seconds, until it converges to zero. * * It is not worth doing a real infinitely recursive filter. If more * than FM_MAXTICKS ticks have elapsed since the last filter event, * just compute FM_MAXTICKS ticks worth, by which point the level * will be stable. * * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid * arithmetic overflow in the fmeter_update() routine. * * Given the simple 32 bit integer arithmetic used, this meter works * best for reporting rates between one per millisecond (msec) and * one per 32 (approx) seconds. At constant rates faster than one * per msec it maxes out at values just under 1,000,000. At constant * rates between one per msec, and one per second it will stabilize * to a value N*1000, where N is the rate of events per second. * At constant rates between one per second and one per 32 seconds, * it will be choppy, moving up on the seconds that have an event, * and then decaying until the next event. At rates slower than * about one in 32 seconds, it decays all the way back to zero between * each event. */ #define FM_COEF 933 /* coefficient for half-life of 10 secs */ #define FM_MAXTICKS ((u32)99) /* useless computing more ticks than this */ #define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ #define FM_SCALE 1000 /* faux fixed point scale */ /* Initialize a frequency meter */ static void fmeter_init(struct fmeter *fmp) { fmp->cnt = 0; fmp->val = 0; fmp->time = 0; spin_lock_init(&fmp->lock); } /* Internal meter update - process cnt events and update value */ static void fmeter_update(struct fmeter *fmp) { time64_t now; u32 ticks; now = ktime_get_seconds(); ticks = now - fmp->time; if (ticks == 0) return; ticks = min(FM_MAXTICKS, ticks); while (ticks-- > 0) fmp->val = (FM_COEF * fmp->val) / FM_SCALE; fmp->time = now; fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; fmp->cnt = 0; } /* Process any previous ticks, then bump cnt by one (times scale). */ static void fmeter_markevent(struct fmeter *fmp) { spin_lock(&fmp->lock); fmeter_update(fmp); fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); spin_unlock(&fmp->lock); } /* Process any previous ticks, then return current value. */ static int fmeter_getrate(struct fmeter *fmp) { int val; spin_lock(&fmp->lock); fmeter_update(fmp); val = fmp->val; spin_unlock(&fmp->lock); return val; } static struct cpuset *cpuset_attach_old_cs; static void reset_migrate_dl_data(struct cpuset *cs) { cs->nr_migrate_dl_tasks = 0; cs->sum_migrate_dl_bw = 0; } /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs, *oldcs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); oldcs = cpuset_attach_old_cs; cs = css_cs(css); mutex_lock(&cpuset_mutex); /* allow moving tasks into an empty cpuset if on default hierarchy */ ret = -ENOSPC; if (!is_in_v2_mode() && (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; if (dl_task(task)) { cs->nr_migrate_dl_tasks++; cs->sum_migrate_dl_bw += task->dl.dl_bw; } } if (!cs->nr_migrate_dl_tasks) goto out_success; if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); if (unlikely(cpu >= nr_cpu_ids)) { reset_migrate_dl_data(cs); ret = -EINVAL; goto out_unlock; } ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); if (ret) { reset_migrate_dl_data(cs); goto out_unlock; } } out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; ret = 0; out_unlock: mutex_unlock(&cpuset_mutex); return ret; } static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); if (cs->nr_migrate_dl_tasks) { int cpu = cpumask_any(cs->effective_cpus); dl_bw_free(cpu, cs->sum_migrate_dl_bw); reset_migrate_dl_data(cs); } mutex_unlock(&cpuset_mutex); } /* * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ static cpumask_var_t cpus_attach; static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; struct cgroup_subsys_state *css; struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ mutex_lock(&cpuset_mutex); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) { if (cs != &top_cpuset) guarantee_online_cpus(task, cpus_attach); else cpumask_copy(cpus_attach, task_cpu_possible_mask(task)); /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here */ WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flag(cs, task); } /* * Change mm for all threadgroup leaders. This is expensive and may * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); /* * old_mems_allowed is the same with mems_allowed * here, except if this task is being moved * automatically due to hotplug. In that case * @mems_allowed has been updated and is empty, so * @old_mems_allowed is the right nodesets that we * migrate mm from. */ if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); else mmput(mm); } } cs->old_mems_allowed = cpuset_attach_nodemask_to; if (cs->nr_migrate_dl_tasks) { cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; reset_migrate_dl_data(cs); } cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ typedef enum { FILE_MEMORY_MIGRATE, FILE_CPULIST, FILE_MEMLIST, FILE_EFFECTIVE_CPULIST, FILE_EFFECTIVE_MEMLIST, FILE_SUBPARTS_CPULIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, FILE_SCHED_LOAD_BALANCE, FILE_PARTITION_ROOT, FILE_SCHED_RELAX_DOMAIN_LEVEL, FILE_MEMORY_PRESSURE_ENABLED, FILE_MEMORY_PRESSURE, FILE_SPREAD_PAGE, FILE_SPREAD_SLAB, } cpuset_filetype_t; static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = 0; cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; } switch (type) { case FILE_CPU_EXCLUSIVE: retval = update_flag(CS_CPU_EXCLUSIVE, cs, val); break; case FILE_MEM_EXCLUSIVE: retval = update_flag(CS_MEM_EXCLUSIVE, cs, val); break; case FILE_MEM_HARDWALL: retval = update_flag(CS_MEM_HARDWALL, cs, val); break; case FILE_SCHED_LOAD_BALANCE: retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val); break; case FILE_MEMORY_MIGRATE: retval = update_flag(CS_MEMORY_MIGRATE, cs, val); break; case FILE_MEMORY_PRESSURE_ENABLED: cpuset_memory_pressure_enabled = !!val; break; case FILE_SPREAD_PAGE: retval = update_flag(CS_SPREAD_PAGE, cs, val); break; case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = -ENODEV; cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: retval = update_relax_domain_level(cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return retval; } /* * Common handling for a write to a "cpus" or "mems" file. */ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); struct cpuset *trialcs; int retval = -ENODEV; buf = strstrip(buf); /* * CPU or memory hotunplug may leave @cs w/o any execution * resources, in which case the hotplug code asynchronously updates * configuration and transfers all tasks to the nearest ancestor * which can execute. * * As writes to "cpus" or "mems" may restore @cs's execution * resources, wait for the previously scheduled operations before * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. * * cpuset_hotplug_work calls back into cgroup core via * cgroup_transfer_tasks() and waiting for it from a cgroupfs * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; trialcs = alloc_trial_cpuset(cs); if (!trialcs) { retval = -ENOMEM; goto out_unlock; } switch (of_cft(of)->private) { case FILE_CPULIST: retval = update_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } free_cpuset(trialcs); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } /* * These ascii lists should be read in a single call, by using a user * buffer large enough to hold the entire map. If read in smaller * chunks, there is no guarantee of atomicity. Since the display format * used, list of ranges of sequential numbers, is variable length, * and since these maps can change value dynamically, one could read * gibberish by doing partial reads while a list was changing. */ static int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); break; case FILE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus)); break; default: ret = -EINVAL; } spin_unlock_irq(&callback_lock); return ret; } static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_CPU_EXCLUSIVE: return is_cpu_exclusive(cs); case FILE_MEM_EXCLUSIVE: return is_mem_exclusive(cs); case FILE_MEM_HARDWALL: return is_mem_hardwall(cs); case FILE_SCHED_LOAD_BALANCE: return is_sched_load_balance(cs); case FILE_MEMORY_MIGRATE: return is_memory_migrate(cs); case FILE_MEMORY_PRESSURE_ENABLED: return cpuset_memory_pressure_enabled; case FILE_MEMORY_PRESSURE: return fmeter_getrate(&cs->fmeter); case FILE_SPREAD_PAGE: return is_spread_page(cs); case FILE_SPREAD_SLAB: return is_spread_slab(cs); default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: return cs->relax_domain_level; default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static int sched_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); switch (cs->partition_root_state) { case PRS_ENABLED: seq_puts(seq, "root\n"); break; case PRS_DISABLED: seq_puts(seq, "member\n"); break; case PRS_ERROR: seq_puts(seq, "root invalid\n"); break; } return 0; } static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); int val; int retval = -ENODEV; buf = strstrip(buf); /* * Convert "root" to ENABLED, and convert "member" to DISABLED. */ if (!strcmp(buf, "root")) val = PRS_ENABLED; else if (!strcmp(buf, "member")) val = PRS_DISABLED; else return -EINVAL; css_get(&cs->css); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); css_put(&cs->css); return retval ?: nbytes; } /* * for the common functions, 'private' gives the type of file */ static struct cftype legacy_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, }, { .name = "effective_cpus", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "effective_mems", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpu_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_CPU_EXCLUSIVE, }, { .name = "mem_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_EXCLUSIVE, }, { .name = "mem_hardwall", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_HARDWALL, }, { .name = "sched_load_balance", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SCHED_LOAD_BALANCE, }, { .name = "sched_relax_domain_level", .read_s64 = cpuset_read_s64, .write_s64 = cpuset_write_s64, .private = FILE_SCHED_RELAX_DOMAIN_LEVEL, }, { .name = "memory_migrate", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_MIGRATE, }, { .name = "memory_pressure", .read_u64 = cpuset_read_u64, .private = FILE_MEMORY_PRESSURE, }, { .name = "memory_spread_page", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_PAGE, }, { .name = "memory_spread_slab", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_SLAB, }, { .name = "memory_pressure_enabled", .flags = CFTYPE_ONLY_ON_ROOT, .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_PRESSURE_ENABLED, }, { } /* terminate */ }; /* * This is currently a minimal set for the default hierarchy. It can be * expanded later on by migrating more features and control files from v1. */ static struct cftype dfl_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "mems.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpus.partition", .seq_show = sched_partition_show, .write = sched_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cpuset, partition_file), }, { .name = "cpus.subpartitions", .seq_show = cpuset_common_seq_show, .private = FILE_SUBPARTS_CPULIST, .flags = CFTYPE_DEBUG, }, { } /* terminate */ }; /* * cpuset_css_alloc - allocate a cpuset css * cgrp: control group that the new cpuset will be part of */ static struct cgroup_subsys_state * cpuset_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuset *cs; if (!parent_css) return &top_cpuset.css; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); if (alloc_cpumasks(cs, NULL)) { kfree(cs); return ERR_PTR(-ENOMEM); } __set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); nodes_clear(cs->mems_allowed); nodes_clear(cs->effective_mems); fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; /* Set CS_MEMORY_MIGRATE for default hierarchy */ if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) __set_bit(CS_MEMORY_MIGRATE, &cs->flags); return &cs->css; } static int cpuset_css_online(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; struct cgroup_subsys_state *pos_css; if (!parent) return 0; cpus_read_lock(); mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) set_bit(CS_SPREAD_PAGE, &cs->flags); if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); cpuset_inc(); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; cs->use_parent_ecpus = true; parent->child_ecpus_count++; } spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; /* * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is * set. This flag handling is implemented in cgroup core for * histrical reasons - the flag may be specified during mount. * * Currently, if any sibling cpusets have exclusive cpus or mem, we * refuse to clone the configuration - thereby refusing the task to * be entered, and as a result refusing the sys_unshare() or * clone() which initiated it. If this becomes a problem for some * users who wish to allow that scenario, then this could be * changed to grant parent->cpus_allowed-sibling_cpus_exclusive * (and likewise for mems) to the new cgroup. */ rcu_read_lock(); cpuset_for_each_child(tmp_cs, pos_css, parent) { if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); spin_lock_irq(&callback_lock); cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); return 0; } /* * If the cpuset being removed has its flag 'sched_load_balance' * enabled, then simulate turning sched_load_balance off, which * will call rebuild_sched_domains_locked(). That is not needed * in the default hierarchy where only changes in partition * will cause repartitioning. * * If the cpuset has the 'sched.partition' flag enabled, simulate * turning 'sched.partition" off. */ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); cpus_read_lock(); mutex_lock(&cpuset_mutex); if (is_partition_root(cs)) update_prstate(cs, 0); if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); cpus_read_unlock(); } static void cpuset_css_free(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); free_cpuset(cs); } static void cpuset_bind(struct cgroup_subsys_state *root_css) { mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); top_cpuset.mems_allowed = node_possible_map; } else { cpumask_copy(top_cpuset.cpus_allowed, top_cpuset.effective_cpus); top_cpuset.mems_allowed = top_cpuset.effective_mems; } spin_unlock_irq(&callback_lock); mutex_unlock(&cpuset_mutex); } /* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ static void cpuset_fork(struct task_struct *task) { if (task_css_is_root(task, cpuset_cgrp_id)) return; set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; } struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, .css_offline = cpuset_css_offline, .css_free = cpuset_css_free, .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, .fork = cpuset_fork, .legacy_cftypes = legacy_files, .dfl_cftypes = dfl_files, .early_init = true, .threaded = true, }; /** * cpuset_init - initialize cpusets at system boot * * Description: Initialize top_cpuset **/ int __init cpuset_init(void) { BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); cpumask_setall(top_cpuset.effective_cpus); nodes_setall(top_cpuset.effective_mems); fmeter_init(&top_cpuset.fmeter); set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); top_cpuset.relax_domain_level = -1; BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); return 0; } /* * If CPU and/or memory hotplug handlers, below, unplug any CPUs * or memory nodes, we need to walk over the cpuset hierarchy, * removing that CPU or node from all cpusets. If this removes the * last CPU or node from a cpuset, then move the tasks in the empty * cpuset to its next-highest non-empty parent. */ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) { struct cpuset *parent; /* * Find its next-highest non-empty parent, (top cpuset * has online cpus, so can't be empty). */ parent = parent_cs(cs); while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) parent = parent_cs(parent); if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { pr_err("cpuset: failed to transfer tasks out of empty cpuset "); pr_cont_cgroup_name(cs->css.cgroup); pr_cont("\n"); } } static void hotplug_update_tasks_legacy(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { bool is_empty; spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, new_cpus); cpumask_copy(cs->effective_cpus, new_cpus); cs->mems_allowed = *new_mems; cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); /* * Don't call update_tasks_cpumask() if the cpuset becomes empty, * as the tasks will be migratecd to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) update_tasks_cpumask(cs); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); mutex_unlock(&cpuset_mutex); /* * Move tasks to the nearest ancestor with execution resources, * This is full cgroup operation which will also call back into * cpuset. Should be done outside any lock. */ if (is_empty) remove_tasks_in_empty_cpuset(cs); mutex_lock(&cpuset_mutex); } static void hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { if (cpumask_empty(new_cpus)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); if (cpus_updated) update_tasks_cpumask(cs); if (mems_updated) update_tasks_nodemask(cs); } static bool force_rebuild; void cpuset_force_rebuild(void) { force_rebuild = true; } /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest * @tmp: the tmpmasks structure pointer * * Compare @cs's cpu and mem masks against top_cpuset and if some have gone * offline, update @cs accordingly. If @cs ends up with no CPU or memory, * all its tasks are moved to the nearest ancestor with both resources. */ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated; bool mems_updated; struct cpuset *parent; retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); mutex_lock(&cpuset_mutex); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { mutex_unlock(&cpuset_mutex); goto retry; } parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); if (cs->nr_subparts_cpus) /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. */ cpumask_andnot(&new_cpus, &new_cpus, cs->subparts_cpus); if (!tmp || !cs->partition_root_state) goto update_tasks; /* * In the unlikely event that a partition root has empty * effective_cpus or its parent becomes erroneous, we have to * transition it to the erroneous state. */ if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || (parent->partition_root_state == PRS_ERROR))) { if (cs->nr_subparts_cpus) { spin_lock_irq(&callback_lock); cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); spin_unlock_irq(&callback_lock); compute_effective_cpumask(&new_cpus, cs, parent); } /* * If the effective_cpus is empty because the child * partitions take away all the CPUs, we can keep * the current partition and let the child partitions * fight for available CPUs. */ if ((parent->partition_root_state == PRS_ERROR) || cpumask_empty(&new_cpus)) { int old_prs; update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); old_prs = cs->partition_root_state; if (old_prs != PRS_ERROR) { spin_lock_irq(&callback_lock); cs->partition_root_state = PRS_ERROR; spin_unlock_irq(&callback_lock); notify_partition_change(cs, old_prs, PRS_ERROR); } } cpuset_force_rebuild(); } /* * On the other hand, an erroneous partition root may be transitioned * back to a regular one or a partition root with no CPU allocated * from the parent may change to erroneous. */ if (is_partition_root(parent) && ((cs->partition_root_state == PRS_ERROR) || !cpumask_intersects(&new_cpus, parent->subparts_cpus)) && update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) cpuset_force_rebuild(); update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); else hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); mutex_unlock(&cpuset_mutex); } /** * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always * synchronized to cpu_active_mask and N_MEMORY, which is necessary in * order to make cpusets transparent (of no affect) on systems that are * actively using CPU hotplug but making no active use of cpusets. * * Non-root cpusets are only affected by offlining. If any CPUs or memory * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on * all descendants. * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. */ static void cpuset_hotplug_workfn(struct work_struct *work) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; bool on_dfl = is_in_v2_mode(); struct tmpmasks tmp, *ptmp = NULL; if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY]; /* * If subparts_cpus is populated, it is likely that the check below * will produce a false positive on cpus_updated when the cpu list * isn't changed. It is extra work, but it is better to be safe. */ cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); /* * In the rare case that hotplug removes all the cpus in subparts_cpus, * we assumed that cpus are updated. */ if (!cpus_updated && top_cpuset.nr_subparts_cpus) cpus_updated = true; /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. If no CPU is left, * we clear the subparts_cpus & let the child partitions * fight for the CPUs again. */ if (top_cpuset.nr_subparts_cpus) { if (cpumask_subset(&new_cpus, top_cpuset.subparts_cpus)) { top_cpuset.nr_subparts_cpus = 0; cpumask_clear(top_cpuset.subparts_cpus); } else { cpumask_andnot(&new_cpus, &new_cpus, top_cpuset.subparts_cpus); } } cpumask_copy(top_cpuset.effective_cpus, &new_cpus); spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; spin_unlock_irq(&callback_lock); update_tasks_nodemask(&top_cpuset); } mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { struct cpuset *cs; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cs == &top_cpuset || !css_tryget_online(&cs->css)) continue; rcu_read_unlock(); cpuset_hotplug_update_tasks(cs, ptmp); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } /* rebuild sched domains if cpus_allowed has changed */ if (cpus_updated || force_rebuild) { force_rebuild = false; rebuild_sched_domains(); } free_cpumasks(NULL, ptmp); } void cpuset_update_active_cpus(void) { /* * We're inside cpu hotplug critical region which usually nests * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ schedule_work(&cpuset_hotplug_work); } void cpuset_wait_for_hotplug(void) { flush_work(&cpuset_hotplug_work); } /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. * See cpuset_update_active_cpus() for CPU hotplug handling. */ static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { schedule_work(&cpuset_hotplug_work); return NOTIFY_OK; } static struct notifier_block cpuset_track_online_nodes_nb = { .notifier_call = cpuset_track_online_nodes, .priority = 10, /* ??! */ }; /** * cpuset_init_smp - initialize cpus_allowed * * Description: Finish top cpuset after cpu, node maps are initialized */ void __init cpuset_init_smp(void) { /* * cpus_allowd/mems_allowed set to v2 values in the initial * cpuset_bind() call will be reset to v1 values in another * cpuset_bind() call when v1 cpuset is mounted. */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); BUG_ON(!cpuset_migrate_mm_wq); } /** * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the * tasks cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; spin_lock_irqsave(&callback_lock, flags); guarantee_online_cpus(tsk, pmask); spin_unlock_irqrestore(&callback_lock, flags); } /** * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe. * @tsk: pointer to task_struct with which the scheduler is struggling * * Description: In the case that the scheduler cannot find an allowed cpu in * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy * mode however, this value is the same as task_cs(tsk)->effective_cpus, * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. * * Returns true if the affinity of @tsk was changed, false otherwise. **/ bool cpuset_cpus_allowed_fallback(struct task_struct *tsk) { const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); const struct cpumask *cs_mask; bool changed = false; rcu_read_lock(); cs_mask = task_cs(tsk)->cpus_allowed; if (is_in_v2_mode() && cpumask_subset(cs_mask, possible_mask)) { do_set_cpus_allowed(tsk, cs_mask); changed = true; } rcu_read_unlock(); /* * We own tsk->cpus_allowed, nobody can change it under us. * * But we used cs && cs->cpus_allowed lockless and thus can * race with cgroup_attach_task() or update_cpumask() and get * the wrong tsk->cpus_allowed. However, both cases imply the * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() * which takes task_rq_lock(). * * If we are called after it dropped the lock we must see all * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. * * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ return changed; } void __init cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); } /** * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. * * Description: Returns the nodemask_t mems_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of node_states[N_MEMORY], even if this means going outside the * tasks cpuset. **/ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { nodemask_t mask; unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_mems(task_cs(tsk), &mask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return mask; } /** * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? */ int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return nodes_intersects(*nodemask, current->mems_allowed); } /* * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or * mem_hardwall ancestor to the specified cpuset. Call holding * callback_lock. If no ancestor is mem_exclusive or mem_hardwall * (an unusual configuration), then returns the root cpuset. */ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) { while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) cs = parent_cs(cs); return cs; } /** * cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. * Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset * unless the task has been OOM killed. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * * Scanning up parent cpusets requires callback_lock. The * __alloc_pages() routine only calls here with __GFP_HARDWALL bit * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the * current tasks mems_allowed came up empty on the first pass over * the zonelist. So only GFP_KERNEL allocations, if all nodes in the * cpuset are short of memory, might require taking the callback_lock. * * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless * in interrupt, of course). * * The second pass through get_page_from_freelist() doesn't even call * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set * in alloc_flags. That logic and the checks below have the combined * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ int allowed; /* is allocation in zone z allowed? */ unsigned long flags; if (in_interrupt()) return true; if (node_isset(node, current->mems_allowed)) return true; /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ if (unlikely(tsk_is_oom_victim(current))) return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return allowed; } /** * cpuset_mem_spread_node() - On which node to begin search for a file page * cpuset_slab_spread_node() - On which node to begin search for a slab page * * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for * tasks in a cpuset with is_spread_page or is_spread_slab set), * and if the memory allocation used cpuset_mem_spread_node() * to determine on which node to start looking, as it will for * certain page cache or slab cache pages such as used for file * system buffers and inode caches, then instead of starting on the * local node to look for a free page, rather spread the starting * node around the tasks mems_allowed nodes. * * We don't have to worry about the returned node being offline * because "it can't happen", and even if it did, it would be ok. * * The routines calling guarantee_online_mems() are careful to * only set nodes in task->mems_allowed that are online. So it * should not be possible for the following code to return an * offline node. But if it did, that would be ok, as this routine * is not returning the node where the allocation must be, only * the node where the search should start. The zonelist passed to * __alloc_pages() will include all nodes. If the slab allocator * is passed an offline node, it will fall back to the local node. * See kmem_cache_alloc_node(). */ static int cpuset_spread_node(int *rotor) { return *rotor = next_node_in(*rotor, current->mems_allowed); } int cpuset_mem_spread_node(void) { if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) current->cpuset_mem_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) current->cpuset_slab_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); /** * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? * @tsk1: pointer to task_struct of some task. * @tsk2: pointer to task_struct of some other task. * * Description: Return true if @tsk1's mems_allowed intersects the * mems_allowed of @tsk2. Used by the OOM killer to determine if * one of the task's memory usage might impact the memory available * to the other. **/ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } /** * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed * * Description: Prints current's name, cpuset name, and cached copy of its * mems_allowed to the kernel log. */ void cpuset_print_current_mems_allowed(void) { struct cgroup *cgrp; rcu_read_lock(); cgrp = task_cs(current)->css.cgroup; pr_cont(",cpuset="); pr_cont_cgroup_name(cgrp); pr_cont(",mems_allowed=%*pbl", nodemask_pr_args(¤t->mems_allowed)); rcu_read_unlock(); } /* * Collection of memory_pressure is suppressed unless * this flag is enabled by writing "1" to the special * cpuset file 'memory_pressure_enabled' in the root cpuset. */ int cpuset_memory_pressure_enabled __read_mostly; /** * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. * * Keep a running average of the rate of synchronous (direct) * page reclaim efforts initiated by tasks in each cpuset. * * This represents the rate at which some task in the cpuset * ran low on memory on all nodes it was allowed to use, and * had to enter the kernels page reclaim code in an effort to * create more free memory by tossing clean pages or swapping * or writing dirty pages. * * Display to user space in the per-cpuset read-only file * "memory_pressure". Value displayed is an integer * representing the recent rate of entry into the synchronous * (direct) page reclaim by any task attached to the cpuset. **/ void __cpuset_memory_pressure_bump(void) { rcu_read_lock(); fmeter_markevent(&task_cs(current)->fmeter); rcu_read_unlock(); } #ifdef CONFIG_PROC_PID_CPUSET /* * proc_cpuset_show() * - Print tasks cpuset path into seq_file. * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; struct cgroup_subsys_state *css; int retval; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; rcu_read_lock(); spin_lock_irq(&css_set_lock); css = task_css(tsk, cpuset_cgrp_id); retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX, current->nsproxy->cgroup_ns); spin_unlock_irq(&css_set_lock); rcu_read_unlock(); if (retval >= PATH_MAX) retval = -ENAMETOOLONG; if (retval < 0) goto out_free; seq_puts(m, buf); seq_putc(m, '\n'); retval = 0; out_free: kfree(buf); out: return retval; } #endif /* CONFIG_PROC_PID_CPUSET */ /* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Mems_allowed:\t%*pb\n", nodemask_pr_args(&task->mems_allowed)); seq_printf(m, "Mems_allowed_list:\t%*pbl\n", nodemask_pr_args(&task->mems_allowed)); } |
| 955 933 143 54 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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/netns/generic.h> #include <net/netfilter/nf_conntrack.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; }; struct pcpu_dstats { u64 tx_pkts; u64 tx_bytes; u64 tx_drps; u64 rx_pkts; u64 rx_bytes; u64 rx_drps; struct u64_stats_sync syncp; }; 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); dstats->rx_pkts++; 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 void vrf_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { int i; for_each_possible_cpu(i) { const struct pcpu_dstats *dstats; u64 tbytes, tpkts, tdrops, rbytes, rpkts; unsigned int start; dstats = per_cpu_ptr(dev->dstats, i); do { start = u64_stats_fetch_begin_irq(&dstats->syncp); tbytes = dstats->tx_bytes; tpkts = dstats->tx_pkts; tdrops = dstats->tx_drps; rbytes = dstats->rx_bytes; rpkts = dstats->rx_pkts; } while (u64_stats_fetch_retry_irq(&dstats->syncp, start)); stats->tx_bytes += tbytes; stats->tx_packets += tpkts; stats->tx_dropped += tdrops; stats->rx_bytes += rbytes; stats->rx_packets += rpkts; } } 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 this_cpu_inc(dev->dstats->rx_drps); 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 = RT_TOS(ip4h->tos); 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) { int len = skb->len; netdev_tx_t ret = is_ip_tx_frame(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); dstats->tx_pkts++; dstats->tx_bytes += len; u64_stats_update_end(&dstats->syncp); } else { this_cpu_inc(dev->dstats->tx_drps); } 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_bh(); nexthop = rt6_nexthop((struct 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_bh(); return ret; } rcu_read_unlock_bh(); 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; dev_put(dst->dev); dst->dev = net->loopback_dev; dev_hold(dst->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 = (struct 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_bh(); 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_bh(); return ret; } rcu_read_unlock_bh(); 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; dev_put(dst->dev); dst->dev = net->loopback_dev; dev_hold(dst->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, 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); free_percpu(dev->dstats); dev->dstats = NULL; } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); if (!dev->dstats) goto out_nomem; /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) goto out_stats; 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_stats: free_percpu(dev->dstats); dev->dstats = NULL; 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_get_stats64 = vrf_get_stats64, .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) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); strlcpy(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->features |= NETIF_F_LLTX; /* don't allow vrf devices to change network namespaces. */ dev->features |= NETIF_F_NETNS_LOCAL; /* 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; } 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(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(net, "net/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); 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); |
| 953 924 53 11 954 39 3 9 12 11 3 5 3 3 70 90 90 25 54 54 44 72 51 51 29 28 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic parts * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/init.h> #include <linux/llc.h> #include <net/llc.h> #include <net/stp.h> #include <net/switchdev.h> #include "br_private.h" /* * Handle changes in state of network devices enslaved to a bridge. * * Note: don't care about up/down if bridge itself is down, because * port state is checked when bridge is brought up. */ static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct netdev_notifier_pre_changeaddr_info *prechaddr_info; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; bool notified = false; bool changed_addr; int err; if (dev->priv_flags & IFF_EBRIDGE) { err = br_vlan_bridge_event(dev, event, ptr); if (err) return notifier_from_errno(err); if (event == NETDEV_REGISTER) { /* register of bridge completed, add sysfs entries */ err = br_sysfs_addbr(dev); if (err) return notifier_from_errno(err); return NOTIFY_DONE; } } /* not a port of a bridge */ p = br_port_get_rtnl(dev); if (!p) return NOTIFY_DONE; br = p->br; switch (event) { case NETDEV_CHANGEMTU: br_mtu_auto_adjust(br); break; case NETDEV_PRE_CHANGEADDR: if (br->dev->addr_assign_type == NET_ADDR_SET) break; prechaddr_info = ptr; err = dev_pre_changeaddr_notify(br->dev, prechaddr_info->dev_addr, extack); if (err) return notifier_from_errno(err); break; case NETDEV_CHANGEADDR: spin_lock_bh(&br->lock); br_fdb_changeaddr(p, dev->dev_addr); changed_addr = br_stp_recalculate_bridge_id(br); spin_unlock_bh(&br->lock); if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); break; case NETDEV_CHANGE: br_port_carrier_check(p, ¬ified); break; case NETDEV_FEAT_CHANGE: netdev_update_features(br->dev); break; case NETDEV_DOWN: spin_lock_bh(&br->lock); if (br->dev->flags & IFF_UP) { br_stp_disable_port(p); notified = true; } spin_unlock_bh(&br->lock); break; case NETDEV_UP: if (netif_running(br->dev) && netif_oper_up(dev)) { spin_lock_bh(&br->lock); br_stp_enable_port(p); notified = true; spin_unlock_bh(&br->lock); } break; case NETDEV_UNREGISTER: br_del_if(br, dev); break; case NETDEV_CHANGENAME: err = br_sysfs_renameif(p); if (err) return notifier_from_errno(err); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_RESEND_IGMP: /* Propagate to master device */ call_netdevice_notifiers(event, br->dev); break; } if (event != NETDEV_UNREGISTER) br_vlan_port_event(p, event); /* Events that may cause spanning tree to refresh */ if (!notified && (event == NETDEV_CHANGEADDR || event == NETDEV_UP || event == NETDEV_CHANGE || event == NETDEV_DOWN)) br_ifinfo_notify(RTM_NEWLINK, NULL, p); return NOTIFY_DONE; } static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; /* called with RTNL or RCU */ static int br_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; struct switchdev_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; p = br_port_get_rtnl_rcu(dev); if (!p) goto out; br = p->br; switch (event) { case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, fdb_info->vid, false); if (err) { err = notifier_from_errno(err); break; } br_fdb_offloaded_set(br, p, fdb_info->addr, fdb_info->vid, true); break; case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, fdb_info->vid, false); if (err) err = notifier_from_errno(err); break; case SWITCHDEV_FDB_OFFLOADED: fdb_info = ptr; br_fdb_offloaded_set(br, p, fdb_info->addr, fdb_info->vid, fdb_info->offloaded); break; case SWITCHDEV_FDB_FLUSH_TO_BRIDGE: fdb_info = ptr; /* Don't delete static entries */ br_fdb_delete_by_port(br, p, fdb_info->vid, 0); break; } out: return err; } static struct notifier_block br_switchdev_notifier = { .notifier_call = br_switchdev_event, }; /* called under rtnl_mutex */ static int br_switchdev_blocking_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_brport_info *brport_info; const struct switchdev_brport *b; struct net_bridge_port *p; int err = NOTIFY_DONE; p = br_port_get_rtnl(dev); if (!p) goto out; switch (event) { case SWITCHDEV_BRPORT_OFFLOADED: brport_info = ptr; b = &brport_info->brport; err = br_switchdev_port_offload(p, b->dev, b->ctx, b->atomic_nb, b->blocking_nb, b->tx_fwd_offload, extack); err = notifier_from_errno(err); break; case SWITCHDEV_BRPORT_UNOFFLOADED: brport_info = ptr; b = &brport_info->brport; br_switchdev_port_unoffload(p, b->ctx, b->atomic_nb, b->blocking_nb); break; } out: return err; } static struct notifier_block br_switchdev_blocking_notifier = { .notifier_call = br_switchdev_blocking_event, }; /* br_boolopt_toggle - change user-controlled boolean option * * @br: bridge device * @opt: id of the option to change * @on: new option value * @extack: extack for error messages * * Changes the value of the respective boolean option to @on taking care of * any internal option value mapping and configuration. */ int br_boolopt_toggle(struct net_bridge *br, enum br_boolopt_id opt, bool on, struct netlink_ext_ack *extack) { int err = 0; switch (opt) { case BR_BOOLOPT_NO_LL_LEARN: br_opt_toggle(br, BROPT_NO_LL_LEARN, on); break; case BR_BOOLOPT_MCAST_VLAN_SNOOPING: err = br_multicast_toggle_vlan_snooping(br, on, extack); break; default: /* shouldn't be called with unsupported options */ WARN_ON(1); break; } return err; } int br_boolopt_get(const struct net_bridge *br, enum br_boolopt_id opt) { switch (opt) { case BR_BOOLOPT_NO_LL_LEARN: return br_opt_get(br, BROPT_NO_LL_LEARN); case BR_BOOLOPT_MCAST_VLAN_SNOOPING: return br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED); default: /* shouldn't be called with unsupported options */ WARN_ON(1); break; } return 0; } int br_boolopt_multi_toggle(struct net_bridge *br, struct br_boolopt_multi *bm, struct netlink_ext_ack *extack) { unsigned long bitmap = bm->optmask; int err = 0; int opt_id; for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) { bool on = !!(bm->optval & BIT(opt_id)); err = br_boolopt_toggle(br, opt_id, on, extack); if (err) { br_debug(br, "boolopt multi-toggle error: option: %d current: %d new: %d error: %d\n", opt_id, br_boolopt_get(br, opt_id), on, err); break; } } return err; } void br_boolopt_multi_get(const struct net_bridge *br, struct br_boolopt_multi *bm) { u32 optval = 0; int opt_id; for (opt_id = 0; opt_id < BR_BOOLOPT_MAX; opt_id++) optval |= (br_boolopt_get(br, opt_id) << opt_id); bm->optval = optval; bm->optmask = GENMASK((BR_BOOLOPT_MAX - 1), 0); } /* private bridge options, controlled by the kernel */ void br_opt_toggle(struct net_bridge *br, enum net_bridge_opts opt, bool on) { bool cur = !!br_opt_get(br, opt); br_debug(br, "toggle option: %d state: %d -> %d\n", opt, cur, on); if (cur == on) return; if (on) set_bit(opt, &br->options); else clear_bit(opt, &br->options); } static void __net_exit br_net_exit(struct net *net) { struct net_device *dev; LIST_HEAD(list); rtnl_lock(); for_each_netdev(net, dev) if (dev->priv_flags & IFF_EBRIDGE) br_dev_delete(dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations br_net_ops = { .exit = br_net_exit, }; static const struct stp_proto br_stp_proto = { .rcv = br_stp_rcv, }; static int __init br_init(void) { int err; BUILD_BUG_ON(sizeof(struct br_input_skb_cb) > sizeof_field(struct sk_buff, cb)); err = stp_proto_register(&br_stp_proto); if (err < 0) { pr_err("bridge: can't register sap for STP\n"); return err; } err = br_fdb_init(); if (err) goto err_out; err = register_pernet_subsys(&br_net_ops); if (err) goto err_out1; err = br_nf_core_init(); if (err) goto err_out2; err = register_netdevice_notifier(&br_device_notifier); if (err) goto err_out3; err = register_switchdev_notifier(&br_switchdev_notifier); if (err) goto err_out4; err = register_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); if (err) goto err_out5; err = br_netlink_init(); if (err) goto err_out6; brioctl_set(br_ioctl_stub); #if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = br_fdb_test_addr; #endif #if IS_MODULE(CONFIG_BRIDGE_NETFILTER) pr_info("bridge: filtering via arp/ip/ip6tables is no longer available " "by default. Update your scripts to load br_netfilter if you " "need this.\n"); #endif return 0; err_out6: unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); err_out5: unregister_switchdev_notifier(&br_switchdev_notifier); err_out4: unregister_netdevice_notifier(&br_device_notifier); err_out3: br_nf_core_fini(); err_out2: unregister_pernet_subsys(&br_net_ops); err_out1: br_fdb_fini(); err_out: stp_proto_unregister(&br_stp_proto); return err; } static void __exit br_deinit(void) { stp_proto_unregister(&br_stp_proto); br_netlink_fini(); unregister_switchdev_blocking_notifier(&br_switchdev_blocking_notifier); unregister_switchdev_notifier(&br_switchdev_notifier); unregister_netdevice_notifier(&br_device_notifier); brioctl_set(NULL); unregister_pernet_subsys(&br_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ br_nf_core_fini(); #if IS_ENABLED(CONFIG_ATM_LANE) br_fdb_test_addr_hook = NULL; #endif br_fdb_fini(); } module_init(br_init) module_exit(br_deinit) MODULE_LICENSE("GPL"); MODULE_VERSION(BR_VERSION); MODULE_ALIAS_RTNL_LINK("bridge"); |
| 7 11 4 4 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ #include "netlink.h" #include "main.h" #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/genetlink.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/minmax.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/printk.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/stddef.h> #include <linux/types.h> #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/sock.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" #include "gateway_client.h" #include "gateway_common.h" #include "hard-interface.h" #include "log.h" #include "multicast.h" #include "network-coding.h" #include "originator.h" #include "soft-interface.h" #include "tp_meter.h" #include "translation-table.h" struct genl_family batadv_netlink_family; /* multicast groups */ enum batadv_netlink_multicast_groups { BATADV_NL_MCGRP_CONFIG, BATADV_NL_MCGRP_TPMETER, }; /** * enum batadv_genl_ops_flags - flags for genl_ops's internal_flags */ enum batadv_genl_ops_flags { /** * @BATADV_FLAG_NEED_MESH: request requires valid soft interface in * attribute BATADV_ATTR_MESH_IFINDEX and expects a pointer to it to be * saved in info->user_ptr[0] */ BATADV_FLAG_NEED_MESH = BIT(0), /** * @BATADV_FLAG_NEED_HARDIF: request requires valid hard interface in * attribute BATADV_ATTR_HARD_IFINDEX and expects a pointer to it to be * saved in info->user_ptr[1] */ BATADV_FLAG_NEED_HARDIF = BIT(1), /** * @BATADV_FLAG_NEED_VLAN: request requires valid vlan in * attribute BATADV_ATTR_VLANID and expects a pointer to it to be * saved in info->user_ptr[1] */ BATADV_FLAG_NEED_VLAN = BIT(2), }; static const struct genl_multicast_group batadv_netlink_mcgrps[] = { [BATADV_NL_MCGRP_CONFIG] = { .name = BATADV_NL_MCAST_GROUP_CONFIG }, [BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER }, }; static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_VERSION] = { .type = NLA_STRING }, [BATADV_ATTR_ALGO_NAME] = { .type = NLA_STRING }, [BATADV_ATTR_MESH_IFINDEX] = { .type = NLA_U32 }, [BATADV_ATTR_MESH_IFNAME] = { .type = NLA_STRING }, [BATADV_ATTR_MESH_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_HARD_IFINDEX] = { .type = NLA_U32 }, [BATADV_ATTR_HARD_IFNAME] = { .type = NLA_STRING }, [BATADV_ATTR_HARD_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_ORIG_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TPMETER_RESULT] = { .type = NLA_U8 }, [BATADV_ATTR_TPMETER_TEST_TIME] = { .type = NLA_U32 }, [BATADV_ATTR_TPMETER_BYTES] = { .type = NLA_U64 }, [BATADV_ATTR_TPMETER_COOKIE] = { .type = NLA_U32 }, [BATADV_ATTR_ACTIVE] = { .type = NLA_FLAG }, [BATADV_ATTR_TT_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TT_TTVN] = { .type = NLA_U8 }, [BATADV_ATTR_TT_LAST_TTVN] = { .type = NLA_U8 }, [BATADV_ATTR_TT_CRC32] = { .type = NLA_U32 }, [BATADV_ATTR_TT_VID] = { .type = NLA_U16 }, [BATADV_ATTR_TT_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_FLAG_BEST] = { .type = NLA_FLAG }, [BATADV_ATTR_LAST_SEEN_MSECS] = { .type = NLA_U32 }, [BATADV_ATTR_NEIGH_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_TQ] = { .type = NLA_U8 }, [BATADV_ATTR_THROUGHPUT] = { .type = NLA_U32 }, [BATADV_ATTR_BANDWIDTH_UP] = { .type = NLA_U32 }, [BATADV_ATTR_BANDWIDTH_DOWN] = { .type = NLA_U32 }, [BATADV_ATTR_ROUTER] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_OWN] = { .type = NLA_FLAG }, [BATADV_ATTR_BLA_ADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_VID] = { .type = NLA_U16 }, [BATADV_ATTR_BLA_BACKBONE] = { .len = ETH_ALEN }, [BATADV_ATTR_BLA_CRC] = { .type = NLA_U16 }, [BATADV_ATTR_DAT_CACHE_IP4ADDRESS] = { .type = NLA_U32 }, [BATADV_ATTR_DAT_CACHE_HWADDRESS] = { .len = ETH_ALEN }, [BATADV_ATTR_DAT_CACHE_VID] = { .type = NLA_U16 }, [BATADV_ATTR_MCAST_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_MCAST_FLAGS_PRIV] = { .type = NLA_U32 }, [BATADV_ATTR_VLANID] = { .type = NLA_U16 }, [BATADV_ATTR_AGGREGATED_OGMS_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_AP_ISOLATION_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_ISOLATION_MARK] = { .type = NLA_U32 }, [BATADV_ATTR_ISOLATION_MASK] = { .type = NLA_U32 }, [BATADV_ATTR_BONDING_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_FRAGMENTATION_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_GW_BANDWIDTH_DOWN] = { .type = NLA_U32 }, [BATADV_ATTR_GW_BANDWIDTH_UP] = { .type = NLA_U32 }, [BATADV_ATTR_GW_MODE] = { .type = NLA_U8 }, [BATADV_ATTR_GW_SEL_CLASS] = { .type = NLA_U32 }, [BATADV_ATTR_HOP_PENALTY] = { .type = NLA_U8 }, [BATADV_ATTR_LOG_LEVEL] = { .type = NLA_U32 }, [BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_MULTICAST_FANOUT] = { .type = NLA_U32 }, [BATADV_ATTR_NETWORK_CODING_ENABLED] = { .type = NLA_U8 }, [BATADV_ATTR_ORIG_INTERVAL] = { .type = NLA_U32 }, [BATADV_ATTR_ELP_INTERVAL] = { .type = NLA_U32 }, [BATADV_ATTR_THROUGHPUT_OVERRIDE] = { .type = NLA_U32 }, }; /** * batadv_netlink_get_ifindex() - Extract an interface index from a message * @nlh: Message header * @attrtype: Attribute which holds an interface index * * Return: interface index, or 0. */ int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) { struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype); return (attr && nla_len(attr) == sizeof(u32)) ? nla_get_u32(attr) : 0; } /** * batadv_netlink_mesh_fill_ap_isolation() - Add ap_isolation softif attribute * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_mesh_fill_ap_isolation(struct sk_buff *msg, struct batadv_priv *bat_priv) { struct batadv_softif_vlan *vlan; u8 ap_isolation; vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); if (!vlan) return 0; ap_isolation = atomic_read(&vlan->ap_isolation); batadv_softif_vlan_put(vlan); return nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, !!ap_isolation); } /** * batadv_netlink_set_mesh_ap_isolation() - Set ap_isolation from genl msg * @attr: parsed BATADV_ATTR_AP_ISOLATION_ENABLED attribute * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_mesh_ap_isolation(struct nlattr *attr, struct batadv_priv *bat_priv) { struct batadv_softif_vlan *vlan; vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); if (!vlan) return -ENOENT; atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); batadv_softif_vlan_put(vlan); return 0; } /** * batadv_netlink_mesh_fill() - Fill message with mesh attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the soft interface information * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_mesh_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags) { struct net_device *soft_iface = bat_priv->soft_iface; struct batadv_hard_iface *primary_if = NULL; struct net_device *hard_iface; void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) || nla_put_string(msg, BATADV_ATTR_ALGO_NAME, bat_priv->algo_ops->name) || nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, soft_iface->ifindex) || nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, soft_iface->name) || nla_put(msg, BATADV_ATTR_MESH_ADDRESS, ETH_ALEN, soft_iface->dev_addr) || nla_put_u8(msg, BATADV_ATTR_TT_TTVN, (u8)atomic_read(&bat_priv->tt.vn))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BLA if (nla_put_u16(msg, BATADV_ATTR_BLA_CRC, ntohs(bat_priv->bla.claim_dest.group))) goto nla_put_failure; #endif if (batadv_mcast_mesh_info_put(msg, bat_priv)) goto nla_put_failure; primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) { hard_iface = primary_if->net_dev; if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, hard_iface->ifindex) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, hard_iface->name) || nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, hard_iface->dev_addr)) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_AGGREGATED_OGMS_ENABLED, !!atomic_read(&bat_priv->aggregated_ogms))) goto nla_put_failure; if (batadv_netlink_mesh_fill_ap_isolation(msg, bat_priv)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MARK, bat_priv->isolation_mark)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MASK, bat_priv->isolation_mark_mask)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_BONDING_ENABLED, !!atomic_read(&bat_priv->bonding))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BLA if (nla_put_u8(msg, BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED, !!atomic_read(&bat_priv->bridge_loop_avoidance))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_BLA */ #ifdef CONFIG_BATMAN_ADV_DAT if (nla_put_u8(msg, BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED, !!atomic_read(&bat_priv->distributed_arp_table))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_DAT */ if (nla_put_u8(msg, BATADV_ATTR_FRAGMENTATION_ENABLED, !!atomic_read(&bat_priv->fragmentation))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_DOWN, atomic_read(&bat_priv->gw.bandwidth_down))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_UP, atomic_read(&bat_priv->gw.bandwidth_up))) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_GW_MODE, atomic_read(&bat_priv->gw.mode))) goto nla_put_failure; if (bat_priv->algo_ops->gw.get_best_gw_node && bat_priv->algo_ops->gw.is_eligible) { /* GW selection class is not available if the routing algorithm * in use does not implement the GW API */ if (nla_put_u32(msg, BATADV_ATTR_GW_SEL_CLASS, atomic_read(&bat_priv->gw.sel_class))) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY, atomic_read(&bat_priv->hop_penalty))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_DEBUG if (nla_put_u32(msg, BATADV_ATTR_LOG_LEVEL, atomic_read(&bat_priv->log_level))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_DEBUG */ #ifdef CONFIG_BATMAN_ADV_MCAST if (nla_put_u8(msg, BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED, !atomic_read(&bat_priv->multicast_mode))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_MULTICAST_FANOUT, atomic_read(&bat_priv->multicast_fanout))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_MCAST */ #ifdef CONFIG_BATMAN_ADV_NC if (nla_put_u8(msg, BATADV_ATTR_NETWORK_CODING_ENABLED, !!atomic_read(&bat_priv->network_coding))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_NC */ if (nla_put_u32(msg, BATADV_ATTR_ORIG_INTERVAL, atomic_read(&bat_priv->orig_interval))) goto nla_put_failure; batadv_hardif_put(primary_if); genlmsg_end(msg, hdr); return 0; nla_put_failure: batadv_hardif_put(primary_if); genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_mesh() - send softif attributes to listener * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success, < 0 on error */ int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_SET_MESH, 0, 0, 0); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->soft_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_get_mesh() - Get softif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_get_mesh(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_GET_MESH, info->snd_portid, info->snd_seq, 0); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_mesh() - Set softif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]) { attr = info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]; atomic_set(&bat_priv->aggregated_ogms, !!nla_get_u8(attr)); } if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; batadv_netlink_set_mesh_ap_isolation(attr, bat_priv); } if (info->attrs[BATADV_ATTR_ISOLATION_MARK]) { attr = info->attrs[BATADV_ATTR_ISOLATION_MARK]; bat_priv->isolation_mark = nla_get_u32(attr); } if (info->attrs[BATADV_ATTR_ISOLATION_MASK]) { attr = info->attrs[BATADV_ATTR_ISOLATION_MASK]; bat_priv->isolation_mark_mask = nla_get_u32(attr); } if (info->attrs[BATADV_ATTR_BONDING_ENABLED]) { attr = info->attrs[BATADV_ATTR_BONDING_ENABLED]; atomic_set(&bat_priv->bonding, !!nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_BLA if (info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]) { attr = info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]; atomic_set(&bat_priv->bridge_loop_avoidance, !!nla_get_u8(attr)); batadv_bla_status_update(bat_priv->soft_iface); } #endif /* CONFIG_BATMAN_ADV_BLA */ #ifdef CONFIG_BATMAN_ADV_DAT if (info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]) { attr = info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]; atomic_set(&bat_priv->distributed_arp_table, !!nla_get_u8(attr)); batadv_dat_status_update(bat_priv->soft_iface); } #endif /* CONFIG_BATMAN_ADV_DAT */ if (info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); rtnl_lock(); batadv_update_min_mtu(bat_priv->soft_iface); rtnl_unlock(); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]; atomic_set(&bat_priv->gw.bandwidth_down, nla_get_u32(attr)); batadv_gw_tvlv_container_update(bat_priv); } if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]) { attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]; atomic_set(&bat_priv->gw.bandwidth_up, nla_get_u32(attr)); batadv_gw_tvlv_container_update(bat_priv); } if (info->attrs[BATADV_ATTR_GW_MODE]) { u8 gw_mode; attr = info->attrs[BATADV_ATTR_GW_MODE]; gw_mode = nla_get_u8(attr); if (gw_mode <= BATADV_GW_MODE_SERVER) { /* Invoking batadv_gw_reselect() is not enough to really * de-select the current GW. It will only instruct the * gateway client code to perform a re-election the next * time that this is needed. * * When gw client mode is being switched off the current * GW must be de-selected explicitly otherwise no GW_ADD * uevent is thrown on client mode re-activation. This * is operation is performed in * batadv_gw_check_client_stop(). */ batadv_gw_reselect(bat_priv); /* always call batadv_gw_check_client_stop() before * changing the gateway state */ batadv_gw_check_client_stop(bat_priv); atomic_set(&bat_priv->gw.mode, gw_mode); batadv_gw_tvlv_container_update(bat_priv); } } if (info->attrs[BATADV_ATTR_GW_SEL_CLASS] && bat_priv->algo_ops->gw.get_best_gw_node && bat_priv->algo_ops->gw.is_eligible) { /* setting the GW selection class is allowed only if the routing * algorithm in use implements the GW API */ u32 sel_class_max = 0xffffffffu; u32 sel_class; attr = info->attrs[BATADV_ATTR_GW_SEL_CLASS]; sel_class = nla_get_u32(attr); if (!bat_priv->algo_ops->gw.store_sel_class) sel_class_max = BATADV_TQ_MAX_VALUE; if (sel_class >= 1 && sel_class <= sel_class_max) { atomic_set(&bat_priv->gw.sel_class, sel_class); batadv_gw_reselect(bat_priv); } } if (info->attrs[BATADV_ATTR_HOP_PENALTY]) { attr = info->attrs[BATADV_ATTR_HOP_PENALTY]; atomic_set(&bat_priv->hop_penalty, nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_DEBUG if (info->attrs[BATADV_ATTR_LOG_LEVEL]) { attr = info->attrs[BATADV_ATTR_LOG_LEVEL]; atomic_set(&bat_priv->log_level, nla_get_u32(attr) & BATADV_DBG_ALL); } #endif /* CONFIG_BATMAN_ADV_DEBUG */ #ifdef CONFIG_BATMAN_ADV_MCAST if (info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]) { attr = info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]; atomic_set(&bat_priv->multicast_mode, !nla_get_u8(attr)); } if (info->attrs[BATADV_ATTR_MULTICAST_FANOUT]) { attr = info->attrs[BATADV_ATTR_MULTICAST_FANOUT]; atomic_set(&bat_priv->multicast_fanout, nla_get_u32(attr)); } #endif /* CONFIG_BATMAN_ADV_MCAST */ #ifdef CONFIG_BATMAN_ADV_NC if (info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]) { attr = info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]; atomic_set(&bat_priv->network_coding, !!nla_get_u8(attr)); batadv_nc_status_update(bat_priv->soft_iface); } #endif /* CONFIG_BATMAN_ADV_NC */ if (info->attrs[BATADV_ATTR_ORIG_INTERVAL]) { u32 orig_interval; attr = info->attrs[BATADV_ATTR_ORIG_INTERVAL]; orig_interval = nla_get_u32(attr); orig_interval = min_t(u32, orig_interval, INT_MAX); orig_interval = max_t(u32, orig_interval, 2 * BATADV_JITTER); atomic_set(&bat_priv->orig_interval, orig_interval); } batadv_netlink_notify_mesh(bat_priv); return 0; } /** * batadv_netlink_tp_meter_put() - Fill information of started tp_meter session * @msg: netlink message to be sent back * @cookie: tp meter session cookie * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_put(struct sk_buff *msg, u32 cookie) { if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie)) return -ENOBUFS; return 0; } /** * batadv_netlink_tpmeter_notify() - send tp_meter result via netlink to client * @bat_priv: the bat priv with all the soft interface information * @dst: destination of tp_meter session * @result: reason for tp meter session stop * @test_time: total time of the tp_meter session * @total_bytes: bytes acked to the receiver * @cookie: cookie of tp_meter session * * Return: 0 on success, < 0 on error */ int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst, u8 result, u32 test_time, u64 total_bytes, u32 cookie) { struct sk_buff *msg; void *hdr; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, 0, 0, &batadv_netlink_family, 0, BATADV_CMD_TP_METER); if (!hdr) { ret = -ENOBUFS; goto err_genlmsg; } if (nla_put_u32(msg, BATADV_ATTR_TPMETER_COOKIE, cookie)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_TPMETER_TEST_TIME, test_time)) goto nla_put_failure; if (nla_put_u64_64bit(msg, BATADV_ATTR_TPMETER_BYTES, total_bytes, BATADV_ATTR_PAD)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_TPMETER_RESULT, result)) goto nla_put_failure; if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, dst)) goto nla_put_failure; genlmsg_end(msg, hdr); genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->soft_iface), msg, 0, BATADV_NL_MCGRP_TPMETER, GFP_KERNEL); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); ret = -EMSGSIZE; err_genlmsg: nlmsg_free(msg); return ret; } /** * batadv_netlink_tp_meter_start() - Start a new tp_meter session * @skb: received netlink message * @info: receiver information * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg = NULL; u32 test_length; void *msg_head; u32 cookie; u8 *dst; int ret; if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; if (!info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]) return -EINVAL; dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); test_length = nla_get_u32(info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto out; } msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq, &batadv_netlink_family, 0, BATADV_CMD_TP_METER); if (!msg_head) { ret = -ENOBUFS; goto out; } batadv_tp_start(bat_priv, dst, test_length, &cookie); ret = batadv_netlink_tp_meter_put(msg, cookie); out: if (ret) { if (msg) nlmsg_free(msg); return ret; } genlmsg_end(msg, msg_head); return genlmsg_reply(msg, info); } /** * batadv_netlink_tp_meter_cancel() - Cancel a running tp_meter session * @skb: received netlink message * @info: receiver information * * Return: 0 on success, < 0 on error */ static int batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info) { struct batadv_priv *bat_priv = info->user_ptr[0]; u8 *dst; int ret = 0; if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); batadv_tp_stop(bat_priv, dst, BATADV_TP_REASON_CANCEL); return ret; } /** * batadv_netlink_hardif_fill() - Fill message with hardif attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the soft interface information * @hard_iface: hard interface which was modified * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * @cb: Control block containing additional options * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_hardif_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, struct batadv_hard_iface *hard_iface, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags, struct netlink_callback *cb) { struct net_device *net_dev = hard_iface->net_dev; void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (cb) genl_dump_check_consistent(cb, hdr); if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, bat_priv->soft_iface->ifindex)) goto nla_put_failure; if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, bat_priv->soft_iface->name)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, net_dev->ifindex) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, net_dev->name) || nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, net_dev->dev_addr)) goto nla_put_failure; if (hard_iface->if_status == BATADV_IF_ACTIVE) { if (nla_put_flag(msg, BATADV_ATTR_ACTIVE)) goto nla_put_failure; } if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY, atomic_read(&hard_iface->hop_penalty))) goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BATMAN_V if (nla_put_u32(msg, BATADV_ATTR_ELP_INTERVAL, atomic_read(&hard_iface->bat_v.elp_interval))) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_THROUGHPUT_OVERRIDE, atomic_read(&hard_iface->bat_v.throughput_override))) goto nla_put_failure; #endif /* CONFIG_BATMAN_ADV_BATMAN_V */ genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_hardif() - send hardif attributes to listener * @bat_priv: the bat priv with all the soft interface information * @hard_iface: hard interface which was modified * * Return: 0 on success, < 0 on error */ int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv, struct batadv_hard_iface *hard_iface) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_SET_HARDIF, 0, 0, 0, NULL); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->soft_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_get_hardif() - Get hardif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_get_hardif(struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_GET_HARDIF, info->snd_portid, info->snd_seq, 0, NULL); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_hardif() - Set hardif attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_hardif(struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_HOP_PENALTY]) { attr = info->attrs[BATADV_ATTR_HOP_PENALTY]; atomic_set(&hard_iface->hop_penalty, nla_get_u8(attr)); } #ifdef CONFIG_BATMAN_ADV_BATMAN_V if (info->attrs[BATADV_ATTR_ELP_INTERVAL]) { attr = info->attrs[BATADV_ATTR_ELP_INTERVAL]; atomic_set(&hard_iface->bat_v.elp_interval, nla_get_u32(attr)); } if (info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]) { attr = info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]; atomic_set(&hard_iface->bat_v.throughput_override, nla_get_u32(attr)); } #endif /* CONFIG_BATMAN_ADV_BATMAN_V */ batadv_netlink_notify_hardif(bat_priv, hard_iface); return 0; } /** * batadv_netlink_dump_hardif() - Dump all hard interface into a messages * @msg: Netlink message to dump into * @cb: Parameters from query * * Return: error code, or length of reply message on success */ static int batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hard_iface *hard_iface; struct batadv_priv *bat_priv; int ifindex; int portid = NETLINK_CB(cb->skb).portid; int skip = cb->args[0]; int i = 0; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface) return -ENODEV; if (!batadv_softif_is_valid(soft_iface)) { dev_put(soft_iface); return -ENODEV; } bat_priv = netdev_priv(soft_iface); rtnl_lock(); cb->seq = batadv_hardif_generation << 1 | 1; list_for_each_entry(hard_iface, &batadv_hardif_list, list) { if (hard_iface->soft_iface != soft_iface) continue; if (i++ < skip) continue; if (batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, BATADV_CMD_GET_HARDIF, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb)) { i--; break; } } rtnl_unlock(); dev_put(soft_iface); cb->args[0] = i; return msg->len; } /** * batadv_netlink_vlan_fill() - Fill message with vlan attributes * @msg: Netlink message to dump into * @bat_priv: the bat priv with all the soft interface information * @vlan: vlan which was modified * @cmd: type of message to generate * @portid: Port making netlink request * @seq: sequence number for message * @flags: Additional flags for message * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_vlan_fill(struct sk_buff *msg, struct batadv_priv *bat_priv, struct batadv_softif_vlan *vlan, enum batadv_nl_commands cmd, u32 portid, u32 seq, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) return -ENOBUFS; if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, bat_priv->soft_iface->ifindex)) goto nla_put_failure; if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, bat_priv->soft_iface->name)) goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK)) goto nla_put_failure; if (nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, !!atomic_read(&vlan->ap_isolation))) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** * batadv_netlink_notify_vlan() - send vlan attributes to listener * @bat_priv: the bat priv with all the soft interface information * @vlan: vlan which was modified * * Return: 0 on success, < 0 on error */ int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv, struct batadv_softif_vlan *vlan) { struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_SET_VLAN, 0, 0, 0); if (ret < 0) { nlmsg_free(msg); return ret; } genlmsg_multicast_netns(&batadv_netlink_family, dev_net(bat_priv->soft_iface), msg, 0, BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); return 0; } /** * batadv_netlink_get_vlan() - Get vlan attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_get_vlan(struct sk_buff *skb, struct genl_info *info) { struct batadv_softif_vlan *vlan = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg; int ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_GET_VLAN, info->snd_portid, info->snd_seq, 0); if (ret < 0) { nlmsg_free(msg); return ret; } ret = genlmsg_reply(msg, info); return ret; } /** * batadv_netlink_set_vlan() - Get vlan attributes * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info) { struct batadv_softif_vlan *vlan = info->user_ptr[1]; struct batadv_priv *bat_priv = info->user_ptr[0]; struct nlattr *attr; if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); } batadv_netlink_notify_vlan(bat_priv, vlan); return 0; } /** * batadv_get_softif_from_info() - Retrieve soft interface from genl attributes * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to soft interface (with increased refcnt) on success, error * pointer on error */ static struct net_device * batadv_get_softif_from_info(struct net *net, struct genl_info *info) { struct net_device *soft_iface; int ifindex; if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) return ERR_PTR(-EINVAL); ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface) return ERR_PTR(-ENODEV); if (!batadv_softif_is_valid(soft_iface)) goto err_put_softif; return soft_iface; err_put_softif: dev_put(soft_iface); return ERR_PTR(-EINVAL); } /** * batadv_get_hardif_from_info() - Retrieve hardif from genl attributes * @bat_priv: the bat priv with all the soft interface information * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to hard interface (with increased refcnt) on success, error * pointer on error */ static struct batadv_hard_iface * batadv_get_hardif_from_info(struct batadv_priv *bat_priv, struct net *net, struct genl_info *info) { struct batadv_hard_iface *hard_iface; struct net_device *hard_dev; unsigned int hardif_index; if (!info->attrs[BATADV_ATTR_HARD_IFINDEX]) return ERR_PTR(-EINVAL); hardif_index = nla_get_u32(info->attrs[BATADV_ATTR_HARD_IFINDEX]); hard_dev = dev_get_by_index(net, hardif_index); if (!hard_dev) return ERR_PTR(-ENODEV); hard_iface = batadv_hardif_get_by_netdev(hard_dev); if (!hard_iface) goto err_put_harddev; if (hard_iface->soft_iface != bat_priv->soft_iface) goto err_put_hardif; /* hard_dev is referenced by hard_iface and not needed here */ dev_put(hard_dev); return hard_iface; err_put_hardif: batadv_hardif_put(hard_iface); err_put_harddev: dev_put(hard_dev); return ERR_PTR(-EINVAL); } /** * batadv_get_vlan_from_info() - Retrieve vlan from genl attributes * @bat_priv: the bat priv with all the soft interface information * @net: the applicable net namespace * @info: receiver information * * Return: Pointer to vlan on success (with increased refcnt), error pointer * on error */ static struct batadv_softif_vlan * batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net, struct genl_info *info) { struct batadv_softif_vlan *vlan; u16 vid; if (!info->attrs[BATADV_ATTR_VLANID]) return ERR_PTR(-EINVAL); vid = nla_get_u16(info->attrs[BATADV_ATTR_VLANID]); vlan = batadv_softif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG); if (!vlan) return ERR_PTR(-ENOENT); return vlan; } /** * batadv_pre_doit() - Prepare batman-adv genl doit request * @ops: requested netlink operation * @skb: Netlink message with request data * @info: receiver information * * Return: 0 on success or negative error number in case of failure */ static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct batadv_hard_iface *hard_iface; struct batadv_priv *bat_priv = NULL; struct batadv_softif_vlan *vlan; struct net_device *soft_iface; u8 user_ptr1_flags; u8 mesh_dep_flags; int ret; user_ptr1_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; if (WARN_ON(hweight8(ops->internal_flags & user_ptr1_flags) > 1)) return -EINVAL; mesh_dep_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; if (WARN_ON((ops->internal_flags & mesh_dep_flags) && (~ops->internal_flags & BATADV_FLAG_NEED_MESH))) return -EINVAL; if (ops->internal_flags & BATADV_FLAG_NEED_MESH) { soft_iface = batadv_get_softif_from_info(net, info); if (IS_ERR(soft_iface)) return PTR_ERR(soft_iface); bat_priv = netdev_priv(soft_iface); info->user_ptr[0] = bat_priv; } if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF) { hard_iface = batadv_get_hardif_from_info(bat_priv, net, info); if (IS_ERR(hard_iface)) { ret = PTR_ERR(hard_iface); goto err_put_softif; } info->user_ptr[1] = hard_iface; } if (ops->internal_flags & BATADV_FLAG_NEED_VLAN) { vlan = batadv_get_vlan_from_info(bat_priv, net, info); if (IS_ERR(vlan)) { ret = PTR_ERR(vlan); goto err_put_softif; } info->user_ptr[1] = vlan; } return 0; err_put_softif: if (bat_priv) dev_put(bat_priv->soft_iface); return ret; } /** * batadv_post_doit() - End batman-adv genl doit request * @ops: requested netlink operation * @skb: Netlink message with request data * @info: receiver information */ static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface; struct batadv_softif_vlan *vlan; struct batadv_priv *bat_priv; if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF && info->user_ptr[1]) { hard_iface = info->user_ptr[1]; batadv_hardif_put(hard_iface); } if (ops->internal_flags & BATADV_FLAG_NEED_VLAN && info->user_ptr[1]) { vlan = info->user_ptr[1]; batadv_softif_vlan_put(vlan); } if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) { bat_priv = info->user_ptr[0]; dev_put(bat_priv->soft_iface); } } static const struct genl_small_ops batadv_netlink_ops[] = { { .cmd = BATADV_CMD_GET_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = batadv_netlink_get_mesh, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_tp_meter_start, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER_CANCEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_tp_meter_cancel, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_GET_ROUTING_ALGOS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_algo_dump, }, { .cmd = BATADV_CMD_GET_HARDIF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .dumpit = batadv_netlink_dump_hardif, .doit = batadv_netlink_get_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_HARDIF, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_tt_local_dump, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_GLOBAL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_tt_global_dump, }, { .cmd = BATADV_CMD_GET_ORIGINATORS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_orig_dump, }, { .cmd = BATADV_CMD_GET_NEIGHBORS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_hardif_neigh_dump, }, { .cmd = BATADV_CMD_GET_GATEWAYS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_gw_dump, }, { .cmd = BATADV_CMD_GET_BLA_CLAIM, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_bla_claim_dump, }, { .cmd = BATADV_CMD_GET_BLA_BACKBONE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_bla_backbone_dump, }, { .cmd = BATADV_CMD_GET_DAT_CACHE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_dat_cache_dump, }, { .cmd = BATADV_CMD_GET_MCAST_FLAGS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .dumpit = batadv_mcast_flags_dump, }, { .cmd = BATADV_CMD_SET_MESH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_mesh, .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_SET_HARDIF, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_hardif, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_HARDIF, }, { .cmd = BATADV_CMD_GET_VLAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = batadv_netlink_get_vlan, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_VLAN, }, { .cmd = BATADV_CMD_SET_VLAN, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_UNS_ADMIN_PERM, .doit = batadv_netlink_set_vlan, .internal_flags = BATADV_FLAG_NEED_MESH | BATADV_FLAG_NEED_VLAN, }, }; struct genl_family batadv_netlink_family __ro_after_init = { .hdrsize = 0, .name = BATADV_NL_NAME, .version = 1, .maxattr = BATADV_ATTR_MAX, .policy = batadv_netlink_policy, .netnsok = true, .pre_doit = batadv_pre_doit, .post_doit = batadv_post_doit, .module = THIS_MODULE, .small_ops = batadv_netlink_ops, .n_small_ops = ARRAY_SIZE(batadv_netlink_ops), .mcgrps = batadv_netlink_mcgrps, .n_mcgrps = ARRAY_SIZE(batadv_netlink_mcgrps), }; /** * batadv_netlink_register() - register batadv genl netlink family */ void __init batadv_netlink_register(void) { int ret; ret = genl_register_family(&batadv_netlink_family); if (ret) pr_warn("unable to register netlink family"); } /** * batadv_netlink_unregister() - unregister batadv genl netlink family */ void batadv_netlink_unregister(void) { genl_unregister_family(&batadv_netlink_family); } |
| 67 2 65 240 241 252 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; fs->root = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); do_each_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); write_seqcount_end(&fs->seq); while (hits--) { count++; path_get(new_root); } spin_unlock(&fs->lock); } task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); spin_lock(&fs->lock); tsk->fs = NULL; kill = !--fs->users; spin_unlock(&fs->lock); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; spin_lock_init(&fs->lock); seqcount_spinlock_init(&fs->seq, &fs->lock); fs->umask = old->umask; spin_lock(&old->lock); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); spin_lock(&fs->lock); kill = !--fs->users; current->fs = new_fs; spin_unlock(&fs->lock); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); int current_umask(void) { return current->fs->umask; } EXPORT_SYMBOL(current_umask); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock), .umask = 0022, }; |
| 39 39 39 39 39 39 39 39 39 39 39 39 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 | // SPDX-License-Identifier: GPL-2.0-or-later /* Provide a way to create a superblock configuration context within the kernel * that allows a superblock to be set up prior to mounting. * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/magic.h> #include <linux/security.h> #include <linux/mnt_namespace.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <asm/sections.h> #include "mount.h" #include "internal.h" enum legacy_fs_param { LEGACY_FS_UNSET_PARAMS, LEGACY_FS_MONOLITHIC_PARAMS, LEGACY_FS_INDIVIDUAL_PARAMS, }; struct legacy_fs_context { char *legacy_data; /* Data page for legacy filesystems */ size_t data_size; enum legacy_fs_param param_type; }; static int legacy_init_fs_context(struct fs_context *fc); static const struct constant_table common_set_sb_flag[] = { { "dirsync", SB_DIRSYNC }, { "lazytime", SB_LAZYTIME }, { "mand", SB_MANDLOCK }, { "ro", SB_RDONLY }, { "sync", SB_SYNCHRONOUS }, { }, }; static const struct constant_table common_clear_sb_flag[] = { { "async", SB_SYNCHRONOUS }, { "nolazytime", SB_LAZYTIME }, { "nomand", SB_MANDLOCK }, { "rw", SB_RDONLY }, { }, }; /* * Check for a common mount option that manipulates s_flags. */ static int vfs_parse_sb_flag(struct fs_context *fc, const char *key) { unsigned int token; token = lookup_constant(common_set_sb_flag, key, 0); if (token) { fc->sb_flags |= token; fc->sb_flags_mask |= token; return 0; } token = lookup_constant(common_clear_sb_flag, key, 0); if (token) { fc->sb_flags &= ~token; fc->sb_flags_mask |= token; return 0; } return -ENOPARAM; } /** * vfs_parse_fs_param_source - Handle setting "source" via parameter * @fc: The filesystem context to modify * @param: The parameter * * This is a simple helper for filesystems to verify that the "source" they * accept is sane. * * Returns 0 on success, -ENOPARAM if this is not "source" parameter, and * -EINVAL otherwise. In the event of failure, supplementary error information * is logged. */ int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param) { if (strcmp(param->key, "source") != 0) return -ENOPARAM; if (param->type != fs_value_is_string) return invalf(fc, "Non-string source"); if (fc->source) return invalf(fc, "Multiple sources"); fc->source = param->string; param->string = NULL; return 0; } EXPORT_SYMBOL(vfs_parse_fs_param_source); /** * vfs_parse_fs_param - Add a single parameter to a superblock config * @fc: The filesystem context to modify * @param: The parameter * * A single mount option in string form is applied to the filesystem context * being set up. Certain standard options (for example "ro") are translated * into flag bits without going to the filesystem. The active security module * is allowed to observe and poach options. Any other options are passed over * to the filesystem to parse. * * This may be called multiple times for a context. * * Returns 0 on success and a negative error code on failure. In the event of * failure, supplementary error information may have been set. */ int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param) { int ret; if (!param->key) return invalf(fc, "Unnamed parameter\n"); ret = vfs_parse_sb_flag(fc, param->key); if (ret != -ENOPARAM) return ret; ret = security_fs_context_parse_param(fc, param); if (ret != -ENOPARAM) /* Param belongs to the LSM or is disallowed by the LSM; so * don't pass to the FS. */ return ret; if (fc->ops->parse_param) { ret = fc->ops->parse_param(fc, param); if (ret != -ENOPARAM) return ret; } /* If the filesystem doesn't take any arguments, give it the * default handling of source. */ ret = vfs_parse_fs_param_source(fc, param); if (ret != -ENOPARAM) return ret; return invalf(fc, "%s: Unknown parameter '%s'", fc->fs_type->name, param->key); } EXPORT_SYMBOL(vfs_parse_fs_param); /** * vfs_parse_fs_string - Convenience function to just parse a string. */ int vfs_parse_fs_string(struct fs_context *fc, const char *key, const char *value, size_t v_size) { int ret; struct fs_parameter param = { .key = key, .type = fs_value_is_flag, .size = v_size, }; if (value) { param.string = kmemdup_nul(value, v_size, GFP_KERNEL); if (!param.string) return -ENOMEM; param.type = fs_value_is_string; } ret = vfs_parse_fs_param(fc, ¶m); kfree(param.string); return ret; } EXPORT_SYMBOL(vfs_parse_fs_string); /** * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data * @ctx: The superblock configuration to fill in. * @data: The data to parse * * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be * called from the ->monolithic_mount_data() fs_context operation. * * Returns 0 on success or the error returned by the ->parse_option() fs_context * operation on failure. */ int generic_parse_monolithic(struct fs_context *fc, void *data) { char *options = data, *key; int ret = 0; if (!options) return 0; ret = security_sb_eat_lsm_opts(options, &fc->security); if (ret) return ret; while ((key = strsep(&options, ",")) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); if (value) { if (value == key) continue; *value++ = 0; v_len = strlen(value); } ret = vfs_parse_fs_string(fc, key, value, v_len); if (ret < 0) break; } } return ret; } EXPORT_SYMBOL(generic_parse_monolithic); /** * alloc_fs_context - Create a filesystem context. * @fs_type: The filesystem type. * @reference: The dentry from which this one derives (or NULL) * @sb_flags: Filesystem/superblock flags (SB_*) * @sb_flags_mask: Applicable members of @sb_flags * @purpose: The purpose that this configuration shall be used for. * * Open a filesystem and create a mount context. The mount context is * initialised with the supplied flags and, if a submount/automount from * another superblock (referred to by @reference) is supplied, may have * parameters such as namespaces copied across from that superblock. */ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, struct dentry *reference, unsigned int sb_flags, unsigned int sb_flags_mask, enum fs_context_purpose purpose) { int (*init_fs_context)(struct fs_context *); struct fs_context *fc; int ret = -ENOMEM; fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL_ACCOUNT); if (!fc) return ERR_PTR(-ENOMEM); fc->purpose = purpose; fc->sb_flags = sb_flags; fc->sb_flags_mask = sb_flags_mask; fc->fs_type = get_filesystem(fs_type); fc->cred = get_current_cred(); fc->net_ns = get_net(current->nsproxy->net_ns); fc->log.prefix = fs_type->name; mutex_init(&fc->uapi_mutex); switch (purpose) { case FS_CONTEXT_FOR_MOUNT: fc->user_ns = get_user_ns(fc->cred->user_ns); break; case FS_CONTEXT_FOR_SUBMOUNT: fc->user_ns = get_user_ns(reference->d_sb->s_user_ns); break; case FS_CONTEXT_FOR_RECONFIGURE: atomic_inc(&reference->d_sb->s_active); fc->user_ns = get_user_ns(reference->d_sb->s_user_ns); fc->root = dget(reference); break; } /* TODO: Make all filesystems support this unconditionally */ init_fs_context = fc->fs_type->init_fs_context; if (!init_fs_context) init_fs_context = legacy_init_fs_context; ret = init_fs_context(fc); if (ret < 0) goto err_fc; fc->need_free = true; return fc; err_fc: put_fs_context(fc); return ERR_PTR(ret); } struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, unsigned int sb_flags) { return alloc_fs_context(fs_type, NULL, sb_flags, 0, FS_CONTEXT_FOR_MOUNT); } EXPORT_SYMBOL(fs_context_for_mount); struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, unsigned int sb_flags, unsigned int sb_flags_mask) { return alloc_fs_context(dentry->d_sb->s_type, dentry, sb_flags, sb_flags_mask, FS_CONTEXT_FOR_RECONFIGURE); } EXPORT_SYMBOL(fs_context_for_reconfigure); struct fs_context *fs_context_for_submount(struct file_system_type *type, struct dentry *reference) { return alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT); } EXPORT_SYMBOL(fs_context_for_submount); void fc_drop_locked(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; dput(fc->root); fc->root = NULL; deactivate_locked_super(sb); } static void legacy_fs_context_free(struct fs_context *fc); /** * vfs_dup_fc_config: Duplicate a filesystem context. * @src_fc: The context to copy. */ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc) { struct fs_context *fc; int ret; if (!src_fc->ops->dup) return ERR_PTR(-EOPNOTSUPP); fc = kmemdup(src_fc, sizeof(struct fs_context), GFP_KERNEL); if (!fc) return ERR_PTR(-ENOMEM); mutex_init(&fc->uapi_mutex); fc->fs_private = NULL; fc->s_fs_info = NULL; fc->source = NULL; fc->security = NULL; get_filesystem(fc->fs_type); get_net(fc->net_ns); get_user_ns(fc->user_ns); get_cred(fc->cred); if (fc->log.log) refcount_inc(&fc->log.log->usage); /* Can't call put until we've called ->dup */ ret = fc->ops->dup(fc, src_fc); if (ret < 0) goto err_fc; ret = security_fs_context_dup(fc, src_fc); if (ret < 0) goto err_fc; return fc; err_fc: put_fs_context(fc); return ERR_PTR(ret); } EXPORT_SYMBOL(vfs_dup_fs_context); /** * logfc - Log a message to a filesystem context * @fc: The filesystem context to log to. * @fmt: The format of the buffer. */ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...) { va_list va; struct va_format vaf = {.fmt = fmt, .va = &va}; va_start(va, fmt); if (!log) { switch (level) { case 'w': printk(KERN_WARNING "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; case 'e': printk(KERN_ERR "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; default: printk(KERN_NOTICE "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; } } else { unsigned int logsize = ARRAY_SIZE(log->buffer); u8 index; char *q = kasprintf(GFP_KERNEL, "%c %s%s%pV\n", level, prefix ? prefix : "", prefix ? ": " : "", &vaf); index = log->head & (logsize - 1); BUILD_BUG_ON(sizeof(log->head) != sizeof(u8) || sizeof(log->tail) != sizeof(u8)); if ((u8)(log->head - log->tail) == logsize) { /* The buffer is full, discard the oldest message */ if (log->need_free & (1 << index)) kfree(log->buffer[index]); log->tail++; } log->buffer[index] = q ? q : "OOM: Can't store error string"; if (q) log->need_free |= 1 << index; else log->need_free &= ~(1 << index); log->head++; } va_end(va); } EXPORT_SYMBOL(logfc); /* * Free a logging structure. */ static void put_fc_log(struct fs_context *fc) { struct fc_log *log = fc->log.log; int i; if (log) { if (refcount_dec_and_test(&log->usage)) { fc->log.log = NULL; for (i = 0; i <= 7; i++) if (log->need_free & (1 << i)) kfree(log->buffer[i]); kfree(log); } } } /** * put_fs_context - Dispose of a superblock configuration context. * @fc: The context to dispose of. */ void put_fs_context(struct fs_context *fc) { struct super_block *sb; if (fc->root) { sb = fc->root->d_sb; dput(fc->root); fc->root = NULL; deactivate_super(sb); } if (fc->need_free && fc->ops && fc->ops->free) fc->ops->free(fc); security_free_mnt_opts(&fc->security); put_net(fc->net_ns); put_user_ns(fc->user_ns); put_cred(fc->cred); put_fc_log(fc); put_filesystem(fc->fs_type); kfree(fc->source); kfree(fc); } EXPORT_SYMBOL(put_fs_context); /* * Free the config for a filesystem that doesn't support fs_context. */ static void legacy_fs_context_free(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; if (ctx) { if (ctx->param_type == LEGACY_FS_INDIVIDUAL_PARAMS) kfree(ctx->legacy_data); kfree(ctx); } } /* * Duplicate a legacy config. */ static int legacy_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { struct legacy_fs_context *ctx; struct legacy_fs_context *src_ctx = src_fc->fs_private; ctx = kmemdup(src_ctx, sizeof(*src_ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; if (ctx->param_type == LEGACY_FS_INDIVIDUAL_PARAMS) { ctx->legacy_data = kmemdup(src_ctx->legacy_data, src_ctx->data_size, GFP_KERNEL); if (!ctx->legacy_data) { kfree(ctx); return -ENOMEM; } } fc->fs_private = ctx; return 0; } /* * Add a parameter to a legacy config. We build up a comma-separated list of * options. */ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct legacy_fs_context *ctx = fc->fs_private; unsigned int size = ctx->data_size; size_t len = 0; int ret; ret = vfs_parse_fs_param_source(fc, param); if (ret != -ENOPARAM) return ret; if (ctx->param_type == LEGACY_FS_MONOLITHIC_PARAMS) return invalf(fc, "VFS: Legacy: Can't mix monolithic and individual options"); switch (param->type) { case fs_value_is_string: len = 1 + param->size; fallthrough; case fs_value_is_flag: len += strlen(param->key); break; default: return invalf(fc, "VFS: Legacy: Parameter type for '%s' not supported", param->key); } if (size + len + 2 > PAGE_SIZE) return invalf(fc, "VFS: Legacy: Cumulative options too large"); if (strchr(param->key, ',') || (param->type == fs_value_is_string && memchr(param->string, ',', param->size))) return invalf(fc, "VFS: Legacy: Option '%s' contained comma", param->key); if (!ctx->legacy_data) { ctx->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!ctx->legacy_data) return -ENOMEM; } if (size) ctx->legacy_data[size++] = ','; len = strlen(param->key); memcpy(ctx->legacy_data + size, param->key, len); size += len; if (param->type == fs_value_is_string) { ctx->legacy_data[size++] = '='; memcpy(ctx->legacy_data + size, param->string, param->size); size += param->size; } ctx->legacy_data[size] = '\0'; ctx->data_size = size; ctx->param_type = LEGACY_FS_INDIVIDUAL_PARAMS; return 0; } /* * Add monolithic mount data. */ static int legacy_parse_monolithic(struct fs_context *fc, void *data) { struct legacy_fs_context *ctx = fc->fs_private; if (ctx->param_type != LEGACY_FS_UNSET_PARAMS) { pr_warn("VFS: Can't mix monolithic and individual options\n"); return -EINVAL; } ctx->legacy_data = data; ctx->param_type = LEGACY_FS_MONOLITHIC_PARAMS; if (!ctx->legacy_data) return 0; if (fc->fs_type->fs_flags & FS_BINARY_MOUNTDATA) return 0; return security_sb_eat_lsm_opts(ctx->legacy_data, &fc->security); } /* * Get a mountable root with the legacy mount command. */ static int legacy_get_tree(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; struct super_block *sb; struct dentry *root; root = fc->fs_type->mount(fc->fs_type, fc->sb_flags, fc->source, ctx->legacy_data); if (IS_ERR(root)) return PTR_ERR(root); sb = root->d_sb; BUG_ON(!sb); fc->root = root; return 0; } /* * Handle remount. */ static int legacy_reconfigure(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; struct super_block *sb = fc->root->d_sb; if (!sb->s_op->remount_fs) return 0; return sb->s_op->remount_fs(sb, &fc->sb_flags, ctx ? ctx->legacy_data : NULL); } const struct fs_context_operations legacy_fs_context_ops = { .free = legacy_fs_context_free, .dup = legacy_fs_context_dup, .parse_param = legacy_parse_param, .parse_monolithic = legacy_parse_monolithic, .get_tree = legacy_get_tree, .reconfigure = legacy_reconfigure, }; /* * Initialise a legacy context for a filesystem that doesn't support * fs_context. */ static int legacy_init_fs_context(struct fs_context *fc) { fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL_ACCOUNT); if (!fc->fs_private) return -ENOMEM; fc->ops = &legacy_fs_context_ops; return 0; } int parse_monolithic_mount_data(struct fs_context *fc, void *data) { int (*monolithic_mount_data)(struct fs_context *, void *); monolithic_mount_data = fc->ops->parse_monolithic; if (!monolithic_mount_data) monolithic_mount_data = generic_parse_monolithic; return monolithic_mount_data(fc, data); } /* * Clean up a context after performing an action on it and put it into a state * from where it can be used to reconfigure a superblock. * * Note that here we do only the parts that can't fail; the rest is in * finish_clean_context() below and in between those fs_context is marked * FS_CONTEXT_AWAITING_RECONF. The reason for splitup is that after * successful mount or remount we need to report success to userland. * Trying to do full reinit (for the sake of possible subsequent remount) * and failing to allocate memory would've put us into a nasty situation. * So here we only discard the old state and reinitialization is left * until we actually try to reconfigure. */ void vfs_clean_context(struct fs_context *fc) { if (fc->need_free && fc->ops && fc->ops->free) fc->ops->free(fc); fc->need_free = false; fc->fs_private = NULL; fc->s_fs_info = NULL; fc->sb_flags = 0; security_free_mnt_opts(&fc->security); kfree(fc->source); fc->source = NULL; fc->purpose = FS_CONTEXT_FOR_RECONFIGURE; fc->phase = FS_CONTEXT_AWAITING_RECONF; } int finish_clean_context(struct fs_context *fc) { int error; if (fc->phase != FS_CONTEXT_AWAITING_RECONF) return 0; if (fc->fs_type->init_fs_context) error = fc->fs_type->init_fs_context(fc); else error = legacy_init_fs_context(fc); if (unlikely(error)) { fc->phase = FS_CONTEXT_FAILED; return error; } fc->need_free = true; fc->phase = FS_CONTEXT_RECONF_PARAMS; return 0; } |
| 7 7 7 7 7 7 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 | // SPDX-License-Identifier: GPL-2.0 #include "blk-rq-qos.h" /* * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded, * false if 'v' + 1 would be bigger than 'below'. */ static bool atomic_inc_below(atomic_t *v, unsigned int below) { unsigned int cur = atomic_read(v); for (;;) { unsigned int old; if (cur >= below) return false; old = atomic_cmpxchg(v, cur, cur + 1); if (old == cur) break; cur = old; } return true; } bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit) { return atomic_inc_below(&rq_wait->inflight, limit); } void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio) { do { if (rqos->ops->cleanup) rqos->ops->cleanup(rqos, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_done(struct rq_qos *rqos, struct request *rq) { do { if (rqos->ops->done) rqos->ops->done(rqos, rq); rqos = rqos->next; } while (rqos); } void __rq_qos_issue(struct rq_qos *rqos, struct request *rq) { do { if (rqos->ops->issue) rqos->ops->issue(rqos, rq); rqos = rqos->next; } while (rqos); } void __rq_qos_requeue(struct rq_qos *rqos, struct request *rq) { do { if (rqos->ops->requeue) rqos->ops->requeue(rqos, rq); rqos = rqos->next; } while (rqos); } void __rq_qos_throttle(struct rq_qos *rqos, struct bio *bio) { do { if (rqos->ops->throttle) rqos->ops->throttle(rqos, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_track(struct rq_qos *rqos, struct request *rq, struct bio *bio) { do { if (rqos->ops->track) rqos->ops->track(rqos, rq, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_merge(struct rq_qos *rqos, struct request *rq, struct bio *bio) { do { if (rqos->ops->merge) rqos->ops->merge(rqos, rq, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_done_bio(struct rq_qos *rqos, struct bio *bio) { do { if (rqos->ops->done_bio) rqos->ops->done_bio(rqos, bio); rqos = rqos->next; } while (rqos); } void __rq_qos_queue_depth_changed(struct rq_qos *rqos) { do { if (rqos->ops->queue_depth_changed) rqos->ops->queue_depth_changed(rqos); rqos = rqos->next; } while (rqos); } /* * Return true, if we can't increase the depth further by scaling */ bool rq_depth_calc_max_depth(struct rq_depth *rqd) { unsigned int depth; bool ret = false; /* * For QD=1 devices, this is a special case. It's important for those * to have one request ready when one completes, so force a depth of * 2 for those devices. On the backend, it'll be a depth of 1 anyway, * since the device can't have more than that in flight. If we're * scaling down, then keep a setting of 1/1/1. */ if (rqd->queue_depth == 1) { if (rqd->scale_step > 0) rqd->max_depth = 1; else { rqd->max_depth = 2; ret = true; } } else { /* * scale_step == 0 is our default state. If we have suffered * latency spikes, step will be > 0, and we shrink the * allowed write depths. If step is < 0, we're only doing * writes, and we allow a temporarily higher depth to * increase performance. */ depth = min_t(unsigned int, rqd->default_depth, rqd->queue_depth); if (rqd->scale_step > 0) depth = 1 + ((depth - 1) >> min(31, rqd->scale_step)); else if (rqd->scale_step < 0) { unsigned int maxd = 3 * rqd->queue_depth / 4; depth = 1 + ((depth - 1) << -rqd->scale_step); if (depth > maxd) { depth = maxd; ret = true; } } rqd->max_depth = depth; } return ret; } /* Returns true on success and false if scaling up wasn't possible */ bool rq_depth_scale_up(struct rq_depth *rqd) { /* * Hit max in previous round, stop here */ if (rqd->scaled_max) return false; rqd->scale_step--; rqd->scaled_max = rq_depth_calc_max_depth(rqd); return true; } /* * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we * had a latency violation. Returns true on success and returns false if * scaling down wasn't possible. */ bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle) { /* * Stop scaling down when we've hit the limit. This also prevents * ->scale_step from going to crazy values, if the device can't * keep up. */ if (rqd->max_depth == 1) return false; if (rqd->scale_step < 0 && hard_throttle) rqd->scale_step = 0; else rqd->scale_step++; rqd->scaled_max = false; rq_depth_calc_max_depth(rqd); return true; } struct rq_qos_wait_data { struct wait_queue_entry wq; struct task_struct *task; struct rq_wait *rqw; acquire_inflight_cb_t *cb; void *private_data; bool got_token; }; static int rq_qos_wake_function(struct wait_queue_entry *curr, unsigned int mode, int wake_flags, void *key) { struct rq_qos_wait_data *data = container_of(curr, struct rq_qos_wait_data, wq); /* * If we fail to get a budget, return -1 to interrupt the wake up loop * in __wake_up_common. */ if (!data->cb(data->rqw, data->private_data)) return -1; data->got_token = true; smp_wmb(); wake_up_process(data->task); list_del_init_careful(&curr->entry); return 1; } /** * rq_qos_wait - throttle on a rqw if we need to * @rqw: rqw to throttle on * @private_data: caller provided specific data * @acquire_inflight_cb: inc the rqw->inflight counter if we can * @cleanup_cb: the callback to cleanup in case we race with a waker * * This provides a uniform place for the rq_qos users to do their throttling. * Since you can end up with a lot of things sleeping at once, this manages the * waking up based on the resources available. The acquire_inflight_cb should * inc the rqw->inflight if we have the ability to do so, or return false if not * and then we will sleep until the room becomes available. * * cleanup_cb is in case that we race with a waker and need to cleanup the * inflight count accordingly. */ void rq_qos_wait(struct rq_wait *rqw, void *private_data, acquire_inflight_cb_t *acquire_inflight_cb, cleanup_cb_t *cleanup_cb) { struct rq_qos_wait_data data = { .wq = { .func = rq_qos_wake_function, .entry = LIST_HEAD_INIT(data.wq.entry), }, .task = current, .rqw = rqw, .cb = acquire_inflight_cb, .private_data = private_data, }; bool has_sleeper; has_sleeper = wq_has_sleeper(&rqw->wait); if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) return; has_sleeper = !prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); do { /* The memory barrier in set_task_state saves us here. */ if (data.got_token) break; if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) { finish_wait(&rqw->wait, &data.wq); /* * We raced with wbt_wake_function() getting a token, * which means we now have two. Put our local token * and wake anyone else potentially waiting for one. */ smp_rmb(); if (data.got_token) cleanup_cb(rqw, private_data); break; } io_schedule(); has_sleeper = true; set_current_state(TASK_UNINTERRUPTIBLE); } while (1); finish_wait(&rqw->wait, &data.wq); } void rq_qos_exit(struct request_queue *q) { blk_mq_debugfs_unregister_queue_rqos(q); while (q->rq_qos) { struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; rqos->ops->exit(rqos); } } |
| 8126 891 8122 5883 5891 5876 7810 7788 7789 7814 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 | // SPDX-License-Identifier: GPL-2.0 #include <linux/debugfs.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/memblock.h> #include <linux/stacktrace.h> #include <linux/page_owner.h> #include <linux/jump_label.h> #include <linux/migrate.h> #include <linux/stackdepot.h> #include <linux/seq_file.h> #include <linux/sched/clock.h> #include "internal.h" /* * TODO: teach PAGE_OWNER_STACK_DEPTH (__dump_page_owner and save_stack) * to use off stack temporal storage */ #define PAGE_OWNER_STACK_DEPTH (16) struct page_owner { unsigned short order; short last_migrate_reason; gfp_t gfp_mask; depot_stack_handle_t handle; depot_stack_handle_t free_handle; u64 ts_nsec; u64 free_ts_nsec; pid_t pid; }; static bool page_owner_enabled = false; DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; static depot_stack_handle_t failure_handle; static depot_stack_handle_t early_handle; static void init_early_allocated_pages(void); static int __init early_page_owner_param(char *buf) { return kstrtobool(buf, &page_owner_enabled); } early_param("page_owner", early_page_owner_param); static bool need_page_owner(void) { return page_owner_enabled; } static __always_inline depot_stack_handle_t create_dummy_stack(void) { unsigned long entries[4]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); return stack_depot_save(entries, nr_entries, GFP_KERNEL); } static noinline void register_dummy_stack(void) { dummy_handle = create_dummy_stack(); } static noinline void register_failure_stack(void) { failure_handle = create_dummy_stack(); } static noinline void register_early_stack(void) { early_handle = create_dummy_stack(); } static void init_page_owner(void) { if (!page_owner_enabled) return; register_dummy_stack(); register_failure_stack(); register_early_stack(); static_branch_enable(&page_owner_inited); init_early_allocated_pages(); } struct page_ext_operations page_owner_ops = { .size = sizeof(struct page_owner), .need = need_page_owner, .init = init_page_owner, }; static inline struct page_owner *get_page_owner(struct page_ext *page_ext) { return (void *)page_ext + page_owner_ops.offset; } static noinline depot_stack_handle_t save_stack(gfp_t flags) { unsigned long entries[PAGE_OWNER_STACK_DEPTH]; depot_stack_handle_t handle; unsigned int nr_entries; /* * Avoid recursion. * * Sometimes page metadata allocation tracking requires more * memory to be allocated: * - when new stack trace is saved to stack depot * - when backtrace itself is calculated (ia64) */ if (current->in_page_owner) return dummy_handle; current->in_page_owner = 1; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2); handle = stack_depot_save(entries, nr_entries, flags); if (!handle) handle = failure_handle; current->in_page_owner = 0; return handle; } void __reset_page_owner(struct page *page, unsigned int order) { int i; struct page_ext *page_ext; depot_stack_handle_t handle; struct page_owner *page_owner; u64 free_ts_nsec = local_clock(); page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) return; handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); for (i = 0; i < (1 << order); i++) { __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_owner = get_page_owner(page_ext); page_owner->free_handle = handle; page_owner->free_ts_nsec = free_ts_nsec; page_ext = page_ext_next(page_ext); } } static inline void __set_page_owner_handle(struct page_ext *page_ext, depot_stack_handle_t handle, unsigned int order, gfp_t gfp_mask) { struct page_owner *page_owner; int i; for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); page_owner->handle = handle; page_owner->order = order; page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = -1; page_owner->pid = current->pid; page_owner->ts_nsec = local_clock(); __set_bit(PAGE_EXT_OWNER, &page_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); page_ext = page_ext_next(page_ext); } } noinline void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { struct page_ext *page_ext = lookup_page_ext(page); depot_stack_handle_t handle; if (unlikely(!page_ext)) return; handle = save_stack(gfp_mask); __set_page_owner_handle(page_ext, handle, order, gfp_mask); } void __set_page_owner_migrate_reason(struct page *page, int reason) { struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; if (unlikely(!page_ext)) return; page_owner = get_page_owner(page_ext); page_owner->last_migrate_reason = reason; } void __split_page_owner(struct page *page, unsigned int nr) { int i; struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; if (unlikely(!page_ext)) return; for (i = 0; i < nr; i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; page_ext = page_ext_next(page_ext); } } void __copy_page_owner(struct page *oldpage, struct page *newpage) { struct page_ext *old_ext = lookup_page_ext(oldpage); struct page_ext *new_ext = lookup_page_ext(newpage); struct page_owner *old_page_owner, *new_page_owner; if (unlikely(!old_ext || !new_ext)) return; old_page_owner = get_page_owner(old_ext); new_page_owner = get_page_owner(new_ext); new_page_owner->order = old_page_owner->order; new_page_owner->gfp_mask = old_page_owner->gfp_mask; new_page_owner->last_migrate_reason = old_page_owner->last_migrate_reason; new_page_owner->handle = old_page_owner->handle; new_page_owner->pid = old_page_owner->pid; new_page_owner->ts_nsec = old_page_owner->ts_nsec; new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; /* * We don't clear the bit on the oldpage as it's going to be freed * after migration. Until then, the info can be useful in case of * a bug, and the overall stats will be off a bit only temporarily. * Also, migrate_misplaced_transhuge_page() can still fail the * migration and then we want the oldpage to retain the info. But * in that case we also don't need to explicitly clear the info from * the new page, which will be freed. */ __set_bit(PAGE_EXT_OWNER, &new_ext->flags); __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); } void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { struct page *page; struct page_ext *page_ext; struct page_owner *page_owner; unsigned long pfn, block_end_pfn; unsigned long end_pfn = zone_end_pfn(zone); unsigned long count[MIGRATE_TYPES] = { 0, }; int pageblock_mt, page_mt; int i; /* Scan block by block. First and last block may be incomplete */ pfn = zone->zone_start_pfn; /* * Walk the zone in pageblock_nr_pages steps. If a page block spans * a zone boundary, it will be double counted between zones. This does * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { page = pfn_to_online_page(pfn); if (!page) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); if (page_zone(page) != zone) continue; if (PageBuddy(page)) { unsigned long freepage_order; freepage_order = buddy_order_unsafe(page); if (freepage_order < MAX_ORDER) pfn += (1UL << freepage_order) - 1; continue; } if (PageReserved(page)) continue; page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) continue; if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); page_mt = gfp_migratetype(page_owner->gfp_mask); if (pageblock_mt != page_mt) { if (is_migrate_cma(pageblock_mt)) count[MIGRATE_MOVABLE]++; else count[pageblock_mt]++; pfn = block_end_pfn; break; } pfn += (1UL << page_owner->order) - 1; } } /* Print counts */ seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); for (i = 0; i < MIGRATE_TYPES; i++) seq_printf(m, "%12lu ", count[i]); seq_putc(m, '\n'); } static ssize_t print_page_owner(char __user *buf, size_t count, unsigned long pfn, struct page *page, struct page_owner *page_owner, depot_stack_handle_t handle) { int ret, pageblock_mt, page_mt; unsigned long *entries; unsigned int nr_entries; char *kbuf; count = min_t(size_t, count, PAGE_SIZE); kbuf = kmalloc(count, GFP_KERNEL); if (!kbuf) return -ENOMEM; ret = snprintf(kbuf, count, "Page allocated via order %u, mask %#x(%pGg), pid %d, ts %llu ns, free_ts %llu ns\n", page_owner->order, page_owner->gfp_mask, &page_owner->gfp_mask, page_owner->pid, page_owner->ts_nsec, page_owner->free_ts_nsec); if (ret >= count) goto err; /* Print information relevant to grouping pages by mobility */ pageblock_mt = get_pageblock_migratetype(page); page_mt = gfp_migratetype(page_owner->gfp_mask); ret += snprintf(kbuf + ret, count - ret, "PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n", pfn, migratetype_names[page_mt], pfn >> pageblock_order, migratetype_names[pageblock_mt], page->flags, &page->flags); if (ret >= count) goto err; nr_entries = stack_depot_fetch(handle, &entries); ret += stack_trace_snprint(kbuf + ret, count - ret, entries, nr_entries, 0); if (ret >= count) goto err; if (page_owner->last_migrate_reason != -1) { ret += snprintf(kbuf + ret, count - ret, "Page has been migrated, last migrate reason: %s\n", migrate_reason_names[page_owner->last_migrate_reason]); if (ret >= count) goto err; } ret += snprintf(kbuf + ret, count - ret, "\n"); if (ret >= count) goto err; if (copy_to_user(buf, kbuf, ret)) ret = -EFAULT; kfree(kbuf); return ret; err: kfree(kbuf); return -ENOMEM; } void __dump_page_owner(const struct page *page) { struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; depot_stack_handle_t handle; unsigned long *entries; unsigned int nr_entries; gfp_t gfp_mask; int mt; if (unlikely(!page_ext)) { pr_alert("There is not page extension available.\n"); return; } page_owner = get_page_owner(page_ext); gfp_mask = page_owner->gfp_mask; mt = gfp_migratetype(gfp_mask); if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { pr_alert("page_owner info is not present (never set?)\n"); return; } if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) pr_alert("page_owner tracks the page as allocated\n"); else pr_alert("page_owner tracks the page as freed\n"); pr_alert("page last allocated via order %u, migratetype %s, gfp_mask %#x(%pGg), pid %d, ts %llu, free_ts %llu\n", page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask, page_owner->pid, page_owner->ts_nsec, page_owner->free_ts_nsec); handle = READ_ONCE(page_owner->handle); if (!handle) { pr_alert("page_owner allocation stack trace missing\n"); } else { nr_entries = stack_depot_fetch(handle, &entries); stack_trace_print(entries, nr_entries, 0); } handle = READ_ONCE(page_owner->free_handle); if (!handle) { pr_alert("page_owner free stack trace missing\n"); } else { nr_entries = stack_depot_fetch(handle, &entries); pr_alert("page last free stack trace:\n"); stack_trace_print(entries, nr_entries, 0); } if (page_owner->last_migrate_reason != -1) pr_alert("page has been migrated, last migrate reason: %s\n", migrate_reason_names[page_owner->last_migrate_reason]); } static ssize_t read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long pfn; struct page *page; struct page_ext *page_ext; struct page_owner *page_owner; depot_stack_handle_t handle; if (!static_branch_unlikely(&page_owner_inited)) return -EINVAL; page = NULL; pfn = min_low_pfn + *ppos; /* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */ while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0) pfn++; drain_all_pages(NULL); /* Find an allocated page */ for (; pfn < max_pfn; pfn++) { /* * If the new page is in a new MAX_ORDER_NR_PAGES area, * validate the area as existing, skip it if not */ if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) { pfn += MAX_ORDER_NR_PAGES - 1; continue; } page = pfn_to_page(pfn); if (PageBuddy(page)) { unsigned long freepage_order = buddy_order_unsafe(page); if (freepage_order < MAX_ORDER) pfn += (1UL << freepage_order) - 1; continue; } page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) continue; /* * Some pages could be missed by concurrent allocation or free, * because we don't hold the zone lock. */ if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; /* * Although we do have the info about past allocation of free * pages, it's not relevant for current memory usage. */ if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); /* * Don't print "tail" pages of high-order allocations as that * would inflate the stats. */ if (!IS_ALIGNED(pfn, 1 << page_owner->order)) continue; /* * Access to page_ext->handle isn't synchronous so we should * be careful to access it. */ handle = READ_ONCE(page_owner->handle); if (!handle) continue; /* Record the next PFN to read in the file offset */ *ppos = (pfn - min_low_pfn) + 1; return print_page_owner(buf, count, pfn, page, page_owner, handle); } return 0; } static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) { unsigned long pfn = zone->zone_start_pfn; unsigned long end_pfn = zone_end_pfn(zone); unsigned long count = 0; /* * Walk the zone in pageblock_nr_pages steps. If a page block spans * a zone boundary, it will be double counted between zones. This does * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { unsigned long block_end_pfn; if (!pfn_valid(pfn)) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); for (; pfn < block_end_pfn; pfn++) { struct page *page = pfn_to_page(pfn); struct page_ext *page_ext; if (page_zone(page) != zone) continue; /* * To avoid having to grab zone->lock, be a little * careful when reading buddy page order. The only * danger is that we skip too much and potentially miss * some early allocated pages, which is better than * heavy lock contention. */ if (PageBuddy(page)) { unsigned long order = buddy_order_unsafe(page); if (order > 0 && order < MAX_ORDER) pfn += (1UL << order) - 1; continue; } if (PageReserved(page)) continue; page_ext = lookup_page_ext(page); if (unlikely(!page_ext)) continue; /* Maybe overlapping zone */ if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; /* Found early allocated page */ __set_page_owner_handle(page_ext, early_handle, 0, 0); count++; } cond_resched(); } pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n", pgdat->node_id, zone->name, count); } static void init_zones_in_node(pg_data_t *pgdat) { struct zone *zone; struct zone *node_zones = pgdat->node_zones; for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { if (!populated_zone(zone)) continue; init_pages_in_zone(pgdat, zone); } } static void init_early_allocated_pages(void) { pg_data_t *pgdat; for_each_online_pgdat(pgdat) init_zones_in_node(pgdat); } static const struct file_operations proc_page_owner_operations = { .read = read_page_owner, }; static int __init pageowner_init(void) { if (!static_branch_unlikely(&page_owner_inited)) { pr_info("page_owner is disabled\n"); return 0; } debugfs_create_file("page_owner", 0400, NULL, NULL, &proc_page_owner_operations); return 0; } late_initcall(pageowner_init) |
| 249 2478 1826 2475 768 771 1838 10 1830 1828 1839 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> static struct vfsmount *anon_inode_mnt __read_mostly; static struct inode *anon_inode_inode; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; static struct inode *anon_inode_make_secure_inode( const char *name, const struct inode *context_inode) { struct inode *inode; const struct qstr qname = QSTR_INIT(name, strlen(name)); int error; inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; error = security_inode_init_security_anon(inode, &qname, context_inode); if (error) { iput(inode); return ERR_PTR(error); } return inode; } static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool secure) { struct inode *inode; struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); if (secure) { inode = anon_inode_make_secure_inode(name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; } } else { inode = anon_inode_inode; if (IS_ERR(inode)) { file = ERR_PTR(-ENODEV); goto err; } /* * We know the anon_inode inode count is always * greater than zero, so ihold() is safe. */ ihold(inode); } file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_iput; file->f_mapping = inode->i_mapping; file->private_data = priv; return file; err_iput: iput(inode); err: module_put(fops->owner); return file; } /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfile(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool secure) { int error, fd; struct file *file; error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; file = __anon_inode_getfile(name, fops, priv, flags, context_inode, secure); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; } fd_install(fd, file); return fd; err_put_unused_fd: put_unused_fd(fd); return error; } /** * anon_inode_getfd - creates a new file instance by hooking it up to * an anonymous inode and a dentry that describe * the "class" of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is * useful for files that do not need to have a full-fledged inode in * order to operate correctly. All the files created with * anon_inode_getfd() will use the same singleton inode, reducing * memory use and avoiding code duplication for the file/inode/dentry * setup. Returns a newly created file descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfd(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfd); /** * anon_inode_getfd_secure - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls * the inode_init_security_anon() LSM hook. This allows the inode to have its * own security context and for a LSM to reject creation of the inode. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. */ int anon_inode_getfd_secure(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } EXPORT_SYMBOL_GPL(anon_inode_getfd_secure); static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); return 0; } fs_initcall(anon_inode_init); |
| 18 19 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001 Intel Corp. * * This file is part of the SCTP kernel implementation * * These are definitions needed by the state machine. * * Please send any bug reports or fixes you make to the * email addresses: * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Xingang Guo <xingang.guo@intel.com> * Jon Grimm <jgrimm@us.ibm.com> * Dajiang Zhang <dajiang.zhang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Kevin Gao <kevin.gao@intel.com> */ #include <linux/types.h> #include <linux/compiler.h> #include <linux/slab.h> #include <linux/in.h> #include <net/sctp/command.h> #include <net/sctp/sctp.h> #ifndef __sctp_sm_h__ #define __sctp_sm_h__ /* * Possible values for the disposition are: */ enum sctp_disposition { SCTP_DISPOSITION_DISCARD, /* No further processing. */ SCTP_DISPOSITION_CONSUME, /* Process return values normally. */ SCTP_DISPOSITION_NOMEM, /* We ran out of memory--recover. */ SCTP_DISPOSITION_DELETE_TCB, /* Close the association. */ SCTP_DISPOSITION_ABORT, /* Close the association NOW. */ SCTP_DISPOSITION_VIOLATION, /* The peer is misbehaving. */ SCTP_DISPOSITION_NOT_IMPL, /* This entry is not implemented. */ SCTP_DISPOSITION_ERROR, /* This is plain old user error. */ SCTP_DISPOSITION_BUG, /* This is a bug. */ }; typedef enum sctp_disposition (sctp_state_fn_t) ( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); typedef void (sctp_timer_event_t) (struct timer_list *); struct sctp_sm_table_entry { sctp_state_fn_t *fn; const char *name; }; /* A naming convention of "sctp_sf_xxx" applies to all the state functions * currently in use. */ /* Prototypes for generic state functions. */ sctp_state_fn_t sctp_sf_not_impl; sctp_state_fn_t sctp_sf_bug; /* Prototypes for gener timer state functions. */ sctp_state_fn_t sctp_sf_timer_ignore; /* Prototypes for chunk state functions. */ sctp_state_fn_t sctp_sf_do_9_1_abort; sctp_state_fn_t sctp_sf_cookie_wait_abort; sctp_state_fn_t sctp_sf_cookie_echoed_abort; sctp_state_fn_t sctp_sf_shutdown_pending_abort; sctp_state_fn_t sctp_sf_shutdown_sent_abort; sctp_state_fn_t sctp_sf_shutdown_ack_sent_abort; sctp_state_fn_t sctp_sf_do_5_1B_init; sctp_state_fn_t sctp_sf_do_5_1C_ack; sctp_state_fn_t sctp_sf_do_5_1D_ce; sctp_state_fn_t sctp_sf_do_5_1E_ca; sctp_state_fn_t sctp_sf_do_4_C; sctp_state_fn_t sctp_sf_eat_data_6_2; sctp_state_fn_t sctp_sf_eat_data_fast_4_4; sctp_state_fn_t sctp_sf_eat_sack_6_2; sctp_state_fn_t sctp_sf_operr_notify; sctp_state_fn_t sctp_sf_t1_init_timer_expire; sctp_state_fn_t sctp_sf_t1_cookie_timer_expire; sctp_state_fn_t sctp_sf_t2_timer_expire; sctp_state_fn_t sctp_sf_t4_timer_expire; sctp_state_fn_t sctp_sf_t5_timer_expire; sctp_state_fn_t sctp_sf_sendbeat_8_3; sctp_state_fn_t sctp_sf_beat_8_3; sctp_state_fn_t sctp_sf_backbeat_8_3; sctp_state_fn_t sctp_sf_do_9_2_final; sctp_state_fn_t sctp_sf_do_9_2_shutdown; sctp_state_fn_t sctp_sf_do_9_2_shut_ctsn; sctp_state_fn_t sctp_sf_do_ecn_cwr; sctp_state_fn_t sctp_sf_do_ecne; sctp_state_fn_t sctp_sf_ootb; sctp_state_fn_t sctp_sf_pdiscard; sctp_state_fn_t sctp_sf_violation; sctp_state_fn_t sctp_sf_discard_chunk; sctp_state_fn_t sctp_sf_do_5_2_1_siminit; sctp_state_fn_t sctp_sf_do_5_2_2_dupinit; sctp_state_fn_t sctp_sf_do_5_2_3_initack; sctp_state_fn_t sctp_sf_do_5_2_4_dupcook; sctp_state_fn_t sctp_sf_unk_chunk; sctp_state_fn_t sctp_sf_do_8_5_1_E_sa; sctp_state_fn_t sctp_sf_cookie_echoed_err; sctp_state_fn_t sctp_sf_do_asconf; sctp_state_fn_t sctp_sf_do_asconf_ack; sctp_state_fn_t sctp_sf_do_reconf; sctp_state_fn_t sctp_sf_do_9_2_reshutack; sctp_state_fn_t sctp_sf_eat_fwd_tsn; sctp_state_fn_t sctp_sf_eat_fwd_tsn_fast; sctp_state_fn_t sctp_sf_eat_auth; /* Prototypes for primitive event state functions. */ sctp_state_fn_t sctp_sf_do_prm_asoc; sctp_state_fn_t sctp_sf_do_prm_send; sctp_state_fn_t sctp_sf_do_9_2_prm_shutdown; sctp_state_fn_t sctp_sf_cookie_wait_prm_shutdown; sctp_state_fn_t sctp_sf_cookie_echoed_prm_shutdown; sctp_state_fn_t sctp_sf_do_9_1_prm_abort; sctp_state_fn_t sctp_sf_cookie_wait_prm_abort; sctp_state_fn_t sctp_sf_cookie_echoed_prm_abort; sctp_state_fn_t sctp_sf_shutdown_pending_prm_abort; sctp_state_fn_t sctp_sf_shutdown_sent_prm_abort; sctp_state_fn_t sctp_sf_shutdown_ack_sent_prm_abort; sctp_state_fn_t sctp_sf_error_closed; sctp_state_fn_t sctp_sf_error_shutdown; sctp_state_fn_t sctp_sf_ignore_primitive; sctp_state_fn_t sctp_sf_do_prm_requestheartbeat; sctp_state_fn_t sctp_sf_do_prm_asconf; sctp_state_fn_t sctp_sf_do_prm_reconf; /* Prototypes for other event state functions. */ sctp_state_fn_t sctp_sf_do_no_pending_tsn; sctp_state_fn_t sctp_sf_do_9_2_start_shutdown; sctp_state_fn_t sctp_sf_do_9_2_shutdown_ack; sctp_state_fn_t sctp_sf_ignore_other; sctp_state_fn_t sctp_sf_cookie_wait_icmp_abort; /* Prototypes for timeout event state functions. */ sctp_state_fn_t sctp_sf_do_6_3_3_rtx; sctp_state_fn_t sctp_sf_send_reconf; sctp_state_fn_t sctp_sf_send_probe; sctp_state_fn_t sctp_sf_do_6_2_sack; sctp_state_fn_t sctp_sf_autoclose_timer_expire; /* Prototypes for utility support functions. */ __u8 sctp_get_chunk_type(struct sctp_chunk *chunk); const struct sctp_sm_table_entry *sctp_sm_lookup_event( struct net *net, enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype); int sctp_chunk_iif(const struct sctp_chunk *); struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *, struct sctp_chunk *, gfp_t gfp); __u32 sctp_generate_verification_tag(void); void sctp_populate_tie_tags(__u8 *cookie, __u32 curTag, __u32 hisTag); /* Prototypes for chunk-building functions. */ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, const struct sctp_bind_addr *bp, gfp_t gfp, int vparam_len); struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const gfp_t gfp, const int unkparam_len); struct sctp_chunk *sctp_make_cookie_echo(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_cwr(const struct sctp_association *asoc, const __u32 lowest_tsn, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_idata(const struct sctp_association *asoc, __u8 flags, int paylen, gfp_t gfp); struct sctp_chunk *sctp_make_ifwdtsn(const struct sctp_association *asoc, __u32 new_cum_tsn, size_t nstreams, struct sctp_ifwdtsn_skip *skiplist); struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, const struct sctp_sndrcvinfo *sinfo, int len, __u8 flags, gfp_t gfp); struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, const __u32 lowest_tsn); struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc); struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_shutdown_complete( const struct sctp_association *asoc, const struct sctp_chunk *chunk); int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause, size_t paylen); struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const size_t hint); struct sctp_chunk *sctp_make_abort_no_data(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __u32 tsn); struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc, struct msghdr *msg, size_t msg_len); struct sctp_chunk *sctp_make_abort_violation( const struct sctp_association *asoc, const struct sctp_chunk *chunk, const __u8 *payload, const size_t paylen); struct sctp_chunk *sctp_make_violation_paramlen( const struct sctp_association *asoc, const struct sctp_chunk *chunk, struct sctp_paramhdr *param); struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_new_encap_port( const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport, __u32 probe_size); struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const void *payload, const size_t paylen); struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len); struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, size_t paylen, size_t reserve_tail); struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, union sctp_addr *laddr, struct sockaddr *addrs, int addrcnt, __be16 flags); struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, union sctp_addr *addr); bool sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *chunk, bool addr_param_needed, struct sctp_paramhdr **errp); struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf); int sctp_process_asconf_ack(struct sctp_association *asoc, struct sctp_chunk *asconf_ack); struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc, __u32 new_cum_tsn, size_t nstreams, struct sctp_fwdtsn_skip *skiplist); struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc, __u16 key_id); struct sctp_chunk *sctp_make_strreset_req(const struct sctp_association *asoc, __u16 stream_num, __be16 *stream_list, bool out, bool in); struct sctp_chunk *sctp_make_strreset_tsnreq( const struct sctp_association *asoc); struct sctp_chunk *sctp_make_strreset_addstrm( const struct sctp_association *asoc, __u16 out, __u16 in); struct sctp_chunk *sctp_make_strreset_resp(const struct sctp_association *asoc, __u32 result, __u32 sn); struct sctp_chunk *sctp_make_strreset_tsnresp(struct sctp_association *asoc, __u32 result, __u32 sn, __u32 sender_tsn, __u32 receiver_tsn); bool sctp_verify_reconf(const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_paramhdr **errp); void sctp_chunk_assign_tsn(struct sctp_chunk *chunk); void sctp_chunk_assign_ssn(struct sctp_chunk *chunk); /* Prototypes for stream-processing functions. */ struct sctp_chunk *sctp_process_strreset_outreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_inreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_tsnreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_addstrm_in( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_resp( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); /* Prototypes for statetable processing. */ int sctp_do_sm(struct net *net, enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, gfp_t gfp); /* 2nd level prototypes */ void sctp_generate_t3_rtx_event(struct timer_list *t); void sctp_generate_heartbeat_event(struct timer_list *t); void sctp_generate_reconf_event(struct timer_list *t); void sctp_generate_probe_event(struct timer_list *t); void sctp_generate_proto_unreach_event(struct timer_list *t); void sctp_ootb_pkt_free(struct sctp_packet *packet); struct sctp_association *sctp_unpack_cookie( const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, gfp_t gfp, int *err, struct sctp_chunk **err_chk_p); /* 3rd level prototypes */ __u32 sctp_generate_tag(const struct sctp_endpoint *ep); __u32 sctp_generate_tsn(const struct sctp_endpoint *ep); /* Extern declarations for major data structures. */ extern sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES]; /* Get the size of a DATA chunk payload. */ static inline __u16 sctp_data_size(struct sctp_chunk *chunk) { __u16 size; size = ntohs(chunk->chunk_hdr->length); size -= sctp_datachk_len(&chunk->asoc->stream); return size; } /* Compare two TSNs */ #define TSN_lt(a,b) \ (typecheck(__u32, a) && \ typecheck(__u32, b) && \ ((__s32)((a) - (b)) < 0)) #define TSN_lte(a,b) \ (typecheck(__u32, a) && \ typecheck(__u32, b) && \ ((__s32)((a) - (b)) <= 0)) /* Compare two MIDs */ #define MID_lt(a, b) \ (typecheck(__u32, a) && \ typecheck(__u32, b) && \ ((__s32)((a) - (b)) < 0)) /* Compare two SSNs */ #define SSN_lt(a,b) \ (typecheck(__u16, a) && \ typecheck(__u16, b) && \ ((__s16)((a) - (b)) < 0)) /* ADDIP 3.1.1 */ #define ADDIP_SERIAL_gte(a,b) \ (typecheck(__u32, a) && \ typecheck(__u32, b) && \ ((__s32)((b) - (a)) <= 0)) /* Check VTAG of the packet matches the sender's own tag. */ static inline int sctp_vtag_verify(const struct sctp_chunk *chunk, const struct sctp_association *asoc) { /* RFC 2960 Sec 8.5 When receiving an SCTP packet, the endpoint * MUST ensure that the value in the Verification Tag field of * the received SCTP packet matches its own Tag. If the received * Verification Tag value does not match the receiver's own * tag value, the receiver shall silently discard the packet... */ if (ntohl(chunk->sctp_hdr->vtag) != asoc->c.my_vtag) return 0; chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; return 1; } /* Check VTAG of the packet matches the sender's own tag and the T bit is * not set, OR its peer's tag and the T bit is set in the Chunk Flags. */ static inline int sctp_vtag_verify_either(const struct sctp_chunk *chunk, const struct sctp_association *asoc) { /* RFC 2960 Section 8.5.1, sctpimpguide Section 2.41 * * B) The receiver of a ABORT MUST accept the packet * if the Verification Tag field of the packet matches its own tag * and the T bit is not set * OR * it is set to its peer's tag and the T bit is set in the Chunk * Flags. * Otherwise, the receiver MUST silently discard the packet * and take no further action. * * C) The receiver of a SHUTDOWN COMPLETE shall accept the packet * if the Verification Tag field of the packet matches its own tag * and the T bit is not set * OR * it is set to its peer's tag and the T bit is set in the Chunk * Flags. * Otherwise, the receiver MUST silently discard the packet * and take no further action. An endpoint MUST ignore the * SHUTDOWN COMPLETE if it is not in the SHUTDOWN-ACK-SENT state. */ if ((!sctp_test_T_bit(chunk) && (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag)) || (sctp_test_T_bit(chunk) && asoc->c.peer_vtag && (ntohl(chunk->sctp_hdr->vtag) == asoc->c.peer_vtag))) { return 1; } return 0; } #endif /* __sctp_sm_h__ */ |
| 956 955 950 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 | // SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause /* Authors: Bernard Metzler <bmt@zurich.ibm.com> */ /* Copyright (c) 2008-2019, IBM Corporation */ #include <linux/init.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/dma-mapping.h> #include <net/addrconf.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> #include <rdma/rdma_netlink.h> #include <linux/kthread.h> #include "siw.h" #include "siw_verbs.h" MODULE_AUTHOR("Bernard Metzler"); MODULE_DESCRIPTION("Software iWARP Driver"); MODULE_LICENSE("Dual BSD/GPL"); /* transmit from user buffer, if possible */ const bool zcopy_tx = true; /* Restrict usage of GSO, if hardware peer iwarp is unable to process * large packets. try_gso = true lets siw try to use local GSO, * if peer agrees. Not using GSO severly limits siw maximum tx bandwidth. */ const bool try_gso; /* Attach siw also with loopback devices */ const bool loopback_enabled = true; /* We try to negotiate CRC on, if true */ const bool mpa_crc_required; /* MPA CRC on/off enforced */ const bool mpa_crc_strict; /* Control TCP_NODELAY socket option */ const bool siw_tcp_nagle; /* Select MPA version to be used during connection setup */ u_char mpa_version = MPA_REVISION_2; /* Selects MPA P2P mode (additional handshake during connection * setup, if true. */ const bool peer_to_peer; struct task_struct *siw_tx_thread[NR_CPUS]; struct crypto_shash *siw_crypto_shash; static int siw_device_register(struct siw_device *sdev, const char *name) { struct ib_device *base_dev = &sdev->base_dev; static int dev_id = 1; int rv; sdev->vendor_part_id = dev_id++; rv = ib_register_device(base_dev, name, NULL); if (rv) { pr_warn("siw: device registration error %d\n", rv); return rv; } siw_dbg(base_dev, "HWaddr=%pM\n", sdev->netdev->dev_addr); return 0; } static void siw_device_cleanup(struct ib_device *base_dev) { struct siw_device *sdev = to_siw_dev(base_dev); xa_destroy(&sdev->qp_xa); xa_destroy(&sdev->mem_xa); } static int siw_create_tx_threads(void) { int cpu, assigned = 0; for_each_online_cpu(cpu) { /* Skip HT cores */ if (cpu % cpumask_weight(topology_sibling_cpumask(cpu))) continue; siw_tx_thread[cpu] = kthread_create(siw_run_sq, (unsigned long *)(long)cpu, "siw_tx/%d", cpu); if (IS_ERR(siw_tx_thread[cpu])) { siw_tx_thread[cpu] = NULL; continue; } kthread_bind(siw_tx_thread[cpu], cpu); wake_up_process(siw_tx_thread[cpu]); assigned++; } return assigned; } static int siw_dev_qualified(struct net_device *netdev) { /* * Additional hardware support can be added here * (e.g. ARPHRD_FDDI, ARPHRD_ATM, ...) - see * <linux/if_arp.h> for type identifiers. */ if (netdev->type == ARPHRD_ETHER || netdev->type == ARPHRD_IEEE802 || (netdev->type == ARPHRD_LOOPBACK && loopback_enabled)) return 1; return 0; } static DEFINE_PER_CPU(atomic_t, siw_use_cnt); static struct { struct cpumask **tx_valid_cpus; int num_nodes; } siw_cpu_info; static int siw_init_cpulist(void) { int i, num_nodes = nr_node_ids; memset(siw_tx_thread, 0, sizeof(siw_tx_thread)); siw_cpu_info.num_nodes = num_nodes; siw_cpu_info.tx_valid_cpus = kcalloc(num_nodes, sizeof(struct cpumask *), GFP_KERNEL); if (!siw_cpu_info.tx_valid_cpus) { siw_cpu_info.num_nodes = 0; return -ENOMEM; } for (i = 0; i < siw_cpu_info.num_nodes; i++) { siw_cpu_info.tx_valid_cpus[i] = kzalloc(sizeof(struct cpumask), GFP_KERNEL); if (!siw_cpu_info.tx_valid_cpus[i]) goto out_err; cpumask_clear(siw_cpu_info.tx_valid_cpus[i]); } for_each_possible_cpu(i) cpumask_set_cpu(i, siw_cpu_info.tx_valid_cpus[cpu_to_node(i)]); return 0; out_err: siw_cpu_info.num_nodes = 0; while (--i >= 0) kfree(siw_cpu_info.tx_valid_cpus[i]); kfree(siw_cpu_info.tx_valid_cpus); siw_cpu_info.tx_valid_cpus = NULL; return -ENOMEM; } static void siw_destroy_cpulist(void) { int i = 0; while (i < siw_cpu_info.num_nodes) kfree(siw_cpu_info.tx_valid_cpus[i++]); kfree(siw_cpu_info.tx_valid_cpus); } /* * Choose CPU with least number of active QP's from NUMA node of * TX interface. */ int siw_get_tx_cpu(struct siw_device *sdev) { const struct cpumask *tx_cpumask; int i, num_cpus, cpu, min_use, node = sdev->numa_node, tx_cpu = -1; if (node < 0) tx_cpumask = cpu_online_mask; else tx_cpumask = siw_cpu_info.tx_valid_cpus[node]; num_cpus = cpumask_weight(tx_cpumask); if (!num_cpus) { /* no CPU on this NUMA node */ tx_cpumask = cpu_online_mask; num_cpus = cpumask_weight(tx_cpumask); } if (!num_cpus) goto out; cpu = cpumask_first(tx_cpumask); for (i = 0, min_use = SIW_MAX_QP; i < num_cpus; i++, cpu = cpumask_next(cpu, tx_cpumask)) { int usage; /* Skip any cores which have no TX thread */ if (!siw_tx_thread[cpu]) continue; usage = atomic_read(&per_cpu(siw_use_cnt, cpu)); if (usage <= min_use) { tx_cpu = cpu; min_use = usage; } } siw_dbg(&sdev->base_dev, "tx cpu %d, node %d, %d qp's\n", tx_cpu, node, min_use); out: if (tx_cpu >= 0) atomic_inc(&per_cpu(siw_use_cnt, tx_cpu)); else pr_warn("siw: no tx cpu found\n"); return tx_cpu; } void siw_put_tx_cpu(int cpu) { atomic_dec(&per_cpu(siw_use_cnt, cpu)); } static struct ib_qp *siw_get_base_qp(struct ib_device *base_dev, int id) { struct siw_qp *qp = siw_qp_id2obj(to_siw_dev(base_dev), id); if (qp) { /* * siw_qp_id2obj() increments object reference count */ siw_qp_put(qp); return &qp->base_qp; } return NULL; } static const struct ib_device_ops siw_device_ops = { .owner = THIS_MODULE, .uverbs_abi_ver = SIW_ABI_VERSION, .driver_id = RDMA_DRIVER_SIW, .alloc_mr = siw_alloc_mr, .alloc_pd = siw_alloc_pd, .alloc_ucontext = siw_alloc_ucontext, .create_cq = siw_create_cq, .create_qp = siw_create_qp, .create_srq = siw_create_srq, .dealloc_driver = siw_device_cleanup, .dealloc_pd = siw_dealloc_pd, .dealloc_ucontext = siw_dealloc_ucontext, .dereg_mr = siw_dereg_mr, .destroy_cq = siw_destroy_cq, .destroy_qp = siw_destroy_qp, .destroy_srq = siw_destroy_srq, .get_dma_mr = siw_get_dma_mr, .get_port_immutable = siw_get_port_immutable, .iw_accept = siw_accept, .iw_add_ref = siw_qp_get_ref, .iw_connect = siw_connect, .iw_create_listen = siw_create_listen, .iw_destroy_listen = siw_destroy_listen, .iw_get_qp = siw_get_base_qp, .iw_reject = siw_reject, .iw_rem_ref = siw_qp_put_ref, .map_mr_sg = siw_map_mr_sg, .mmap = siw_mmap, .mmap_free = siw_mmap_free, .modify_qp = siw_verbs_modify_qp, .modify_srq = siw_modify_srq, .poll_cq = siw_poll_cq, .post_recv = siw_post_receive, .post_send = siw_post_send, .post_srq_recv = siw_post_srq_recv, .query_device = siw_query_device, .query_gid = siw_query_gid, .query_port = siw_query_port, .query_qp = siw_query_qp, .query_srq = siw_query_srq, .req_notify_cq = siw_req_notify_cq, .reg_user_mr = siw_reg_user_mr, INIT_RDMA_OBJ_SIZE(ib_cq, siw_cq, base_cq), INIT_RDMA_OBJ_SIZE(ib_pd, siw_pd, base_pd), INIT_RDMA_OBJ_SIZE(ib_qp, siw_qp, base_qp), INIT_RDMA_OBJ_SIZE(ib_srq, siw_srq, base_srq), INIT_RDMA_OBJ_SIZE(ib_ucontext, siw_ucontext, base_ucontext), }; static struct siw_device *siw_device_create(struct net_device *netdev) { struct siw_device *sdev = NULL; struct ib_device *base_dev; int rv; sdev = ib_alloc_device(siw_device, base_dev); if (!sdev) return NULL; base_dev = &sdev->base_dev; sdev->netdev = netdev; if (netdev->type != ARPHRD_LOOPBACK) { addrconf_addr_eui48((unsigned char *)&base_dev->node_guid, netdev->dev_addr); } else { /* * The loopback device does not have a HW address, * but connection mangagement lib expects gid != 0 */ size_t len = min_t(size_t, strlen(base_dev->name), 6); char addr[6] = { }; memcpy(addr, base_dev->name, len); addrconf_addr_eui48((unsigned char *)&base_dev->node_guid, addr); } base_dev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POST_SEND); base_dev->node_type = RDMA_NODE_RNIC; memcpy(base_dev->node_desc, SIW_NODE_DESC_COMMON, sizeof(SIW_NODE_DESC_COMMON)); /* * Current model (one-to-one device association): * One Softiwarp device per net_device or, equivalently, * per physical port. */ base_dev->phys_port_cnt = 1; base_dev->num_comp_vectors = num_possible_cpus(); xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1); xa_init_flags(&sdev->mem_xa, XA_FLAGS_ALLOC1); ib_set_device_ops(base_dev, &siw_device_ops); rv = ib_device_set_netdev(base_dev, netdev, 1); if (rv) goto error; memcpy(base_dev->iw_ifname, netdev->name, sizeof(base_dev->iw_ifname)); /* Disable TCP port mapping */ base_dev->iw_driver_flags = IW_F_NO_PORT_MAP; sdev->attrs.max_qp = SIW_MAX_QP; sdev->attrs.max_qp_wr = SIW_MAX_QP_WR; sdev->attrs.max_ord = SIW_MAX_ORD_QP; sdev->attrs.max_ird = SIW_MAX_IRD_QP; sdev->attrs.max_sge = SIW_MAX_SGE; sdev->attrs.max_sge_rd = SIW_MAX_SGE_RD; sdev->attrs.max_cq = SIW_MAX_CQ; sdev->attrs.max_cqe = SIW_MAX_CQE; sdev->attrs.max_mr = SIW_MAX_MR; sdev->attrs.max_pd = SIW_MAX_PD; sdev->attrs.max_mw = SIW_MAX_MW; sdev->attrs.max_srq = SIW_MAX_SRQ; sdev->attrs.max_srq_wr = SIW_MAX_SRQ_WR; sdev->attrs.max_srq_sge = SIW_MAX_SGE; INIT_LIST_HEAD(&sdev->cep_list); INIT_LIST_HEAD(&sdev->qp_list); atomic_set(&sdev->num_ctx, 0); atomic_set(&sdev->num_srq, 0); atomic_set(&sdev->num_qp, 0); atomic_set(&sdev->num_cq, 0); atomic_set(&sdev->num_mr, 0); atomic_set(&sdev->num_pd, 0); sdev->numa_node = dev_to_node(&netdev->dev); spin_lock_init(&sdev->lock); return sdev; error: ib_dealloc_device(base_dev); return NULL; } /* * Network link becomes unavailable. Mark all * affected QP's accordingly. */ static void siw_netdev_down(struct work_struct *work) { struct siw_device *sdev = container_of(work, struct siw_device, netdev_down); struct siw_qp_attrs qp_attrs; struct list_head *pos, *tmp; memset(&qp_attrs, 0, sizeof(qp_attrs)); qp_attrs.state = SIW_QP_STATE_ERROR; list_for_each_safe(pos, tmp, &sdev->qp_list) { struct siw_qp *qp = list_entry(pos, struct siw_qp, devq); down_write(&qp->state_lock); WARN_ON(siw_qp_modify(qp, &qp_attrs, SIW_QP_ATTR_STATE)); up_write(&qp->state_lock); } ib_device_put(&sdev->base_dev); } static void siw_device_goes_down(struct siw_device *sdev) { if (ib_device_try_get(&sdev->base_dev)) { INIT_WORK(&sdev->netdev_down, siw_netdev_down); schedule_work(&sdev->netdev_down); } } static int siw_netdev_event(struct notifier_block *nb, unsigned long event, void *arg) { struct net_device *netdev = netdev_notifier_info_to_dev(arg); struct ib_device *base_dev; struct siw_device *sdev; dev_dbg(&netdev->dev, "siw: event %lu\n", event); base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (!base_dev) return NOTIFY_OK; sdev = to_siw_dev(base_dev); switch (event) { case NETDEV_UP: sdev->state = IB_PORT_ACTIVE; siw_port_event(sdev, 1, IB_EVENT_PORT_ACTIVE); break; case NETDEV_GOING_DOWN: siw_device_goes_down(sdev); break; case NETDEV_DOWN: sdev->state = IB_PORT_DOWN; siw_port_event(sdev, 1, IB_EVENT_PORT_ERR); break; case NETDEV_REGISTER: /* * Device registration now handled only by * rdma netlink commands. So it shall be impossible * to end up here with a valid siw device. */ siw_dbg(base_dev, "unexpected NETDEV_REGISTER event\n"); break; case NETDEV_UNREGISTER: ib_unregister_device_queued(&sdev->base_dev); break; case NETDEV_CHANGEADDR: siw_port_event(sdev, 1, IB_EVENT_LID_CHANGE); break; /* * Todo: Below netdev events are currently not handled. */ case NETDEV_CHANGEMTU: case NETDEV_CHANGE: break; default: break; } ib_device_put(&sdev->base_dev); return NOTIFY_OK; } static struct notifier_block siw_netdev_nb = { .notifier_call = siw_netdev_event, }; static int siw_newlink(const char *basedev_name, struct net_device *netdev) { struct ib_device *base_dev; struct siw_device *sdev = NULL; int rv = -ENOMEM; if (!siw_dev_qualified(netdev)) return -EINVAL; base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (base_dev) { ib_device_put(base_dev); return -EEXIST; } sdev = siw_device_create(netdev); if (sdev) { dev_dbg(&netdev->dev, "siw: new device\n"); if (netif_running(netdev) && netif_carrier_ok(netdev)) sdev->state = IB_PORT_ACTIVE; else sdev->state = IB_PORT_DOWN; rv = siw_device_register(sdev, basedev_name); if (rv) ib_dealloc_device(&sdev->base_dev); } return rv; } static struct rdma_link_ops siw_link_ops = { .type = "siw", .newlink = siw_newlink, }; /* * siw_init_module - Initialize Softiwarp module and register with netdev * subsystem. */ static __init int siw_init_module(void) { int rv; int nr_cpu; if (SENDPAGE_THRESH < SIW_MAX_INLINE) { pr_info("siw: sendpage threshold too small: %u\n", (int)SENDPAGE_THRESH); rv = -EINVAL; goto out_error; } rv = siw_init_cpulist(); if (rv) goto out_error; rv = siw_cm_init(); if (rv) goto out_error; if (!siw_create_tx_threads()) { pr_info("siw: Could not start any TX thread\n"); rv = -ENOMEM; goto out_error; } /* * Locate CRC32 algorithm. If unsuccessful, fail * loading siw only, if CRC is required. */ siw_crypto_shash = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(siw_crypto_shash)) { pr_info("siw: Loading CRC32c failed: %ld\n", PTR_ERR(siw_crypto_shash)); siw_crypto_shash = NULL; if (mpa_crc_required) { rv = -EOPNOTSUPP; goto out_error; } } rv = register_netdevice_notifier(&siw_netdev_nb); if (rv) goto out_error; rdma_link_register(&siw_link_ops); pr_info("SoftiWARP attached\n"); return 0; out_error: for (nr_cpu = 0; nr_cpu < nr_cpu_ids; nr_cpu++) { if (siw_tx_thread[nr_cpu]) { siw_stop_tx_thread(nr_cpu); siw_tx_thread[nr_cpu] = NULL; } } if (siw_crypto_shash) crypto_free_shash(siw_crypto_shash); pr_info("SoftIWARP attach failed. Error: %d\n", rv); siw_cm_exit(); siw_destroy_cpulist(); return rv; } static void __exit siw_exit_module(void) { int cpu; for_each_possible_cpu(cpu) { if (siw_tx_thread[cpu]) { siw_stop_tx_thread(cpu); siw_tx_thread[cpu] = NULL; } } unregister_netdevice_notifier(&siw_netdev_nb); rdma_link_unregister(&siw_link_ops); ib_unregister_driver(RDMA_DRIVER_SIW); siw_cm_exit(); siw_destroy_cpulist(); if (siw_crypto_shash) crypto_free_shash(siw_crypto_shash); pr_info("SoftiWARP detached\n"); } module_init(siw_init_module); module_exit(siw_exit_module); MODULE_ALIAS_RDMA_LINK("siw"); |
| 54 54 53 53 54 54 53 53 10 10 10 10 10 10 54 54 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/proc/net.c * * Copyright (C) 2007 * * Author: Eric Biederman <ebiederm@xmission.com> * * proc net directory handling functions */ #include <linux/uaccess.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/module.h> #include <linux/bitops.h> #include <linux/mount.h> #include <linux/nsproxy.h> #include <linux/uidgid.h> #include <net/net_namespace.h> #include <linux/seq_file.h> #include "internal.h" static inline struct net *PDE_NET(struct proc_dir_entry *pde) { return pde->parent->data; } static struct net *get_proc_net(const struct inode *inode) { return maybe_get_net(PDE_NET(PDE(inode))); } static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; struct seq_net_private *p; struct net *net; WARN_ON_ONCE(state_size < sizeof(*p)); if (file->f_mode & FMODE_WRITE && !PDE(inode)->write) return -EACCES; net = get_proc_net(inode); if (!net) return -ENXIO; p = __seq_open_private(file, PDE(inode)->seq_ops, state_size); if (!p) { put_net(net); return -ENOMEM; } #ifdef CONFIG_NET_NS p->net = net; #endif return 0; } static int seq_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; put_net(seq_file_net(seq)); seq_release_private(ino, f); return 0; } static const struct proc_ops proc_net_seq_ops = { .proc_open = seq_open_net, .proc_read = seq_read, .proc_write = proc_simple_write, .proc_lseek = seq_lseek, .proc_release = seq_release_net, }; int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux) { #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; p->net = get_net(current->nsproxy->net_ns); #endif return 0; } void bpf_iter_fini_seq_net(void *priv_data) { #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; put_net(p->net); #endif } struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_data); /** * proc_create_net_data_write - Create a writable net_ns-specific proc file * @name: The name of the file. * @mode: The file's access mode. * @parent: The parent directory in which to create. * @ops: The seq_file ops with which to read the file. * @write: The write method with which to 'modify' the file. * @data: Data for retrieval by PDE_DATA(). * * Create a network namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a * series of elements and also provides for the file accepting writes that have * some arbitrary effect. * * The functions in the @ops table are used to iterate over items to be * presented and extract the readable content using the seq_file interface. * * The @write function is called with the data copied into a kernel space * scratch buffer and has a NUL appended for convenience. The buffer may be * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling * PDE_DATA() on the file inode. The network namespace must be accessed by * calling seq_file_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, proc_write_t write, unsigned int state_size, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_seq_ops; p->seq_ops = ops; p->state_size = state_size; p->write = write; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_data_write); static int single_open_net(struct inode *inode, struct file *file) { struct proc_dir_entry *de = PDE(inode); struct net *net; int err; net = get_proc_net(inode); if (!net) return -ENXIO; err = single_open(file, de->single_show, net); if (err) put_net(net); return err; } static int single_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; put_net(seq->private); return single_release(ino, f); } static const struct proc_ops proc_net_single_ops = { .proc_open = single_open_net, .proc_read = seq_read, .proc_write = proc_simple_write, .proc_lseek = seq_lseek, .proc_release = single_release_net, }; struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_single_ops; p->single_show = show; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_single); /** * proc_create_net_single_write - Create a writable net_ns-specific proc file * @name: The name of the file. * @mode: The file's access mode. * @parent: The parent directory in which to create. * @show: The seqfile show method with which to read the file. * @write: The write method with which to 'modify' the file. * @data: Data for retrieval by PDE_DATA(). * * Create a network-namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a * single element rather than a series and also provides for the file accepting * writes that have some arbitrary effect. * * The @show function is called to extract the readable content via the * seq_file interface. * * The @write function is called with the data copied into a kernel space * scratch buffer and has a NUL appended for convenience. The buffer may be * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling * PDE_DATA() on the file inode. The network namespace must be accessed by * calling seq_file_single_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), proc_write_t write, void *data) { struct proc_dir_entry *p; p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; pde_force_lookup(p); p->proc_ops = &proc_net_single_ops; p->single_show = show; p->write = write; return proc_register(parent, p); } EXPORT_SYMBOL_GPL(proc_create_net_single_write); static struct net *get_proc_task_net(struct inode *dir) { struct task_struct *task; struct nsproxy *ns; struct net *net = NULL; rcu_read_lock(); task = pid_task(proc_pid(dir), PIDTYPE_PID); if (task != NULL) { task_lock(task); ns = task->nsproxy; if (ns != NULL) net = get_net(ns->net_ns); task_unlock(task); } rcu_read_unlock(); return net; } static struct dentry *proc_tgid_net_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct dentry *de; struct net *net; de = ERR_PTR(-ENOENT); net = get_proc_task_net(dir); if (net != NULL) { de = proc_lookup_de(dir, dentry, net->proc_net); put_net(net); } return de; } static int proc_tgid_net_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct net *net; net = get_proc_task_net(inode); generic_fillattr(&init_user_ns, inode, stat); if (net != NULL) { stat->nlink = net->proc_net->nlink; put_net(net); } return 0; } const struct inode_operations proc_net_inode_operations = { .lookup = proc_tgid_net_lookup, .getattr = proc_tgid_net_getattr, }; static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx) { int ret; struct net *net; ret = -EINVAL; net = get_proc_task_net(file_inode(file)); if (net != NULL) { ret = proc_readdir_de(file, ctx, net->proc_net); put_net(net); } return ret; } const struct file_operations proc_net_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = proc_tgid_net_readdir, }; static __net_init int proc_net_ns_init(struct net *net) { struct proc_dir_entry *netd, *net_statd; kuid_t uid; kgid_t gid; int err; err = -ENOMEM; netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) goto out; netd->subdir = RB_ROOT; netd->data = net; netd->nlink = 2; netd->namelen = 3; netd->parent = &proc_root; netd->name = netd->inline_name; memcpy(netd->name, "net", 4); uid = make_kuid(net->user_ns, 0); if (!uid_valid(uid)) uid = netd->uid; gid = make_kgid(net->user_ns, 0); if (!gid_valid(gid)) gid = netd->gid; proc_set_user(netd, uid, gid); /* Seed dentry revalidation for /proc/${pid}/net */ pde_force_lookup(netd); err = -EEXIST; net_statd = proc_net_mkdir(net, "stat", netd); if (!net_statd) goto free_net; net->proc_net = netd; net->proc_net_stat = net_statd; return 0; free_net: pde_free(netd); out: return err; } static __net_exit void proc_net_ns_exit(struct net *net) { remove_proc_entry("stat", net->proc_net); pde_free(net->proc_net); } static struct pernet_operations __net_initdata proc_net_ns_ops = { .init = proc_net_ns_init, .exit = proc_net_ns_exit, }; int __init proc_net_init(void) { proc_symlink("net", NULL, "self/net"); return register_pernet_subsys(&proc_net_ns_ops); } |
| 300 297 299 300 296 296 294 296 297 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 | // SPDX-License-Identifier: GPL-2.0-only /* * Common framework for low-level network console, dump, and debugger code * * Sep 8 2003 Matt Mackall <mpm@selenic.com> * * based on the netconsole code from: * * Copyright (C) 2001 Ingo Molnar <mingo@redhat.com> * Copyright (C) 2002 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> #include <linux/inet.h> #include <linux/interrupt.h> #include <linux/netpoll.h> #include <linux/sched.h> #include <linux/delay.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/if_vlan.h> #include <net/tcp.h> #include <net/udp.h> #include <net/addrconf.h> #include <net/ndisc.h> #include <net/ip6_checksum.h> #include <asm/unaligned.h> #include <trace/events/napi.h> #include <linux/kconfig.h> /* * We maintain a small pool of fully-sized skbs, to make sure the * message gets out even in extreme OOM situations. */ #define MAX_UDP_CHUNK 1460 #define MAX_SKBS 32 static struct sk_buff_head skb_pool; DEFINE_STATIC_SRCU(netpoll_srcu); #define USEC_PER_POLL 50 #define MAX_SKB_SIZE \ (sizeof(struct ethhdr) + \ sizeof(struct iphdr) + \ sizeof(struct udphdr) + \ MAX_UDP_CHUNK) static void zap_completion_queue(void); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); #define np_info(np, fmt, ...) \ pr_info("%s: " fmt, np->name, ##__VA_ARGS__) #define np_err(np, fmt, ...) \ pr_err("%s: " fmt, np->name, ##__VA_ARGS__) #define np_notice(np, fmt, ...) \ pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) static netdev_tx_t netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { netdev_tx_t status = NETDEV_TX_OK; netdev_features_t features; features = netif_skb_features(skb); if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) { skb = __vlan_hwaccel_push_inside(skb); if (unlikely(!skb)) { /* This is actually a packet drop, but we * don't want the code that calls this * function to try and operate on a NULL skb. */ goto out; } } status = netdev_start_xmit(skb, dev, txq, false); out: return status; } static void queue_process(struct work_struct *work) { struct netpoll_info *npinfo = container_of(work, struct netpoll_info, tx_work.work); struct sk_buff *skb; unsigned long flags; while ((skb = skb_dequeue(&npinfo->txq))) { struct net_device *dev = skb->dev; struct netdev_queue *txq; unsigned int q_index; if (!netif_device_present(dev) || !netif_running(dev)) { kfree_skb(skb); continue; } local_irq_save(flags); /* check if skb->queue_mapping is still valid */ q_index = skb_get_queue_mapping(skb); if (unlikely(q_index >= dev->real_num_tx_queues)) { q_index = q_index % dev->real_num_tx_queues; skb_set_queue_mapping(skb, q_index); } txq = netdev_get_tx_queue(dev, q_index); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (netif_xmit_frozen_or_stopped(txq) || !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) { skb_queue_head(&npinfo->txq, skb); HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); schedule_delayed_work(&npinfo->tx_work, HZ/10); return; } HARD_TX_UNLOCK(dev, txq); local_irq_restore(flags); } } static int netif_local_xmit_active(struct net_device *dev) { int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) return 1; } return 0; } static void poll_one_napi(struct napi_struct *napi) { int work; /* If we set this bit but see that it has already been set, * that indicates that napi has been disabled and we need * to abort this operation */ if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) return; /* We explicilty pass the polling call a budget of 0 to * indicate that we are clearing the Tx path only. */ work = napi->poll(napi, 0); WARN_ONCE(work, "%pS exceeded budget in poll\n", napi->poll); trace_napi_poll(napi, work, 0); clear_bit(NAPI_STATE_NPSVC, &napi->state); } static void poll_napi(struct net_device *dev) { struct napi_struct *napi; int cpu = smp_processor_id(); list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) { poll_one_napi(napi); smp_store_release(&napi->poll_owner, -1); } } } void netpoll_poll_dev(struct net_device *dev) { struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); const struct net_device_ops *ops; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity * while changing device state */ if (!ni || down_trylock(&ni->dev_lock)) return; /* Some drivers will take the same locks in poll and xmit, * we can't poll if local CPU is already in xmit. */ if (!netif_running(dev) || netif_local_xmit_active(dev)) { up(&ni->dev_lock); return; } ops = dev->netdev_ops; if (ops->ndo_poll_controller) ops->ndo_poll_controller(dev); poll_napi(dev); up(&ni->dev_lock); zap_completion_queue(); } EXPORT_SYMBOL(netpoll_poll_dev); void netpoll_poll_disable(struct net_device *dev) { struct netpoll_info *ni; int idx; might_sleep(); idx = srcu_read_lock(&netpoll_srcu); ni = srcu_dereference(dev->npinfo, &netpoll_srcu); if (ni) down(&ni->dev_lock); srcu_read_unlock(&netpoll_srcu, idx); } EXPORT_SYMBOL(netpoll_poll_disable); void netpoll_poll_enable(struct net_device *dev) { struct netpoll_info *ni; rcu_read_lock(); ni = rcu_dereference(dev->npinfo); if (ni) up(&ni->dev_lock); rcu_read_unlock(); } EXPORT_SYMBOL(netpoll_poll_enable); static void refill_skbs(void) { struct sk_buff *skb; unsigned long flags; spin_lock_irqsave(&skb_pool.lock, flags); while (skb_pool.qlen < MAX_SKBS) { skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC); if (!skb) break; __skb_queue_tail(&skb_pool, skb); } spin_unlock_irqrestore(&skb_pool.lock, flags); } static void zap_completion_queue(void) { unsigned long flags; struct softnet_data *sd = &get_cpu_var(softnet_data); if (sd->completion_queue) { struct sk_buff *clist; local_irq_save(flags); clist = sd->completion_queue; sd->completion_queue = NULL; local_irq_restore(flags); while (clist != NULL) { struct sk_buff *skb = clist; clist = clist->next; if (!skb_irq_freeable(skb)) { refcount_set(&skb->users, 1); dev_kfree_skb_any(skb); /* put this one back */ } else { __kfree_skb(skb); } } } put_cpu_var(softnet_data); } static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve) { int count = 0; struct sk_buff *skb; zap_completion_queue(); refill_skbs(); repeat: skb = alloc_skb(len, GFP_ATOMIC); if (!skb) skb = skb_dequeue(&skb_pool); if (!skb) { if (++count < 10) { netpoll_poll_dev(np->dev); goto repeat; } return NULL; } refcount_set(&skb->users, 1); skb_reserve(skb, reserve); return skb; } static int netpoll_owner_active(struct net_device *dev) { struct napi_struct *napi; list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (READ_ONCE(napi->poll_owner) == smp_processor_id()) return 1; } return 0; } /* call with IRQ disabled */ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { netdev_tx_t status = NETDEV_TX_BUSY; struct net_device *dev; unsigned long tries; /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo; lockdep_assert_irqs_disabled(); dev = np->dev; npinfo = rcu_dereference_bh(dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { dev_kfree_skb_irq(skb); return NET_XMIT_DROP; } /* don't get messages out of order, and no recursion */ if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) { struct netdev_queue *txq; txq = netdev_core_pick_tx(dev, skb, NULL); /* try until next clock tick */ for (tries = jiffies_to_usecs(1)/USEC_PER_POLL; tries > 0; --tries) { if (HARD_TX_TRYLOCK(dev, txq)) { if (!netif_xmit_stopped(txq)) status = netpoll_start_xmit(skb, dev, txq); HARD_TX_UNLOCK(dev, txq); if (dev_xmit_complete(status)) break; } /* tickle device maybe there is some cleanup */ netpoll_poll_dev(np->dev); udelay(USEC_PER_POLL); } WARN_ONCE(!irqs_disabled(), "netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pS)\n", dev->name, dev->netdev_ops->ndo_start_xmit); } if (!dev_xmit_complete(status)) { skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } return NETDEV_TX_OK; } netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { unsigned long flags; netdev_tx_t ret; if (unlikely(!np)) { dev_kfree_skb_irq(skb); ret = NET_XMIT_DROP; } else { local_irq_save(flags); ret = __netpoll_send_skb(np, skb); local_irq_restore(flags); } return ret; } EXPORT_SYMBOL(netpoll_send_skb); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { int total_len, ip_len, udp_len; struct sk_buff *skb; struct udphdr *udph; struct iphdr *iph; struct ethhdr *eth; static atomic_t ip_ident; struct ipv6hdr *ip6h; if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!irqs_disabled()); udp_len = len + sizeof(*udph); if (np->ipv6) ip_len = udp_len + sizeof(*ip6h); else ip_len = udp_len + sizeof(*iph); total_len = ip_len + LL_RESERVED_SPACE(np->dev); skb = find_skb(np, total_len + np->dev->needed_tailroom, total_len - len); if (!skb) return; skb_copy_to_linear_data(skb, msg, len); skb_put(skb, len); skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); udph = udp_hdr(skb); udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); if (np->ipv6) { udph->check = 0; udph->check = csum_ipv6_magic(&np->local_ip.in6, &np->remote_ip.in6, udp_len, IPPROTO_UDP, csum_partial(udph, udp_len, 0)); if (udph->check == 0) udph->check = CSUM_MANGLED_0; skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); /* ip6h->version = 6; ip6h->priority = 0; */ *(unsigned char *)ip6h = 0x60; ip6h->flow_lbl[0] = 0; ip6h->flow_lbl[1] = 0; ip6h->flow_lbl[2] = 0; ip6h->payload_len = htons(sizeof(struct udphdr) + len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = 32; ip6h->saddr = np->local_ip.in6; ip6h->daddr = np->remote_ip.in6; eth = skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); skb->protocol = eth->h_proto = htons(ETH_P_IPV6); } else { udph->check = 0; udph->check = csum_tcpudp_magic(np->local_ip.ip, np->remote_ip.ip, udp_len, IPPROTO_UDP, csum_partial(udph, udp_len, 0)); if (udph->check == 0) udph->check = CSUM_MANGLED_0; skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); iph = ip_hdr(skb); /* iph->version = 4; iph->ihl = 5; */ *(unsigned char *)iph = 0x45; iph->tos = 0; put_unaligned(htons(ip_len), &(iph->tot_len)); iph->id = htons(atomic_inc_return(&ip_ident)); iph->frag_off = 0; iph->ttl = 64; iph->protocol = IPPROTO_UDP; iph->check = 0; put_unaligned(np->local_ip.ip, &(iph->saddr)); put_unaligned(np->remote_ip.ip, &(iph->daddr)); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); eth = skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); skb->protocol = eth->h_proto = htons(ETH_P_IP); } ether_addr_copy(eth->h_source, np->dev->dev_addr); ether_addr_copy(eth->h_dest, np->remote_mac); skb->dev = np->dev; netpoll_send_skb(np, skb); } EXPORT_SYMBOL(netpoll_send_udp); void netpoll_print_options(struct netpoll *np) { np_info(np, "local port %d\n", np->local_port); if (np->ipv6) np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); else np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); np_info(np, "interface '%s'\n", np->dev_name); np_info(np, "remote port %d\n", np->remote_port); if (np->ipv6) np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); else np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); np_info(np, "remote ethernet address %pM\n", np->remote_mac); } EXPORT_SYMBOL(netpoll_print_options); static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) { const char *end; if (!strchr(str, ':') && in4_pton(str, -1, (void *)addr, -1, &end) > 0) { if (!*end) return 0; } if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { #if IS_ENABLED(CONFIG_IPV6) if (!*end) return 1; #else return -1; #endif } return -1; } int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; int ipv6; bool ipversion_set = false; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; *delim = 0; if (kstrtou16(cur, 10, &np->local_port)) goto parse_failed; cur = delim; } cur++; if (*cur != '/') { ipversion_set = true; if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); if (ipv6 < 0) goto parse_failed; else np->ipv6 = (bool)ipv6; cur = delim; } cur++; if (*cur != ',') { /* parse out dev name */ if ((delim = strchr(cur, ',')) == NULL) goto parse_failed; *delim = 0; strscpy(np->dev_name, cur, sizeof(np->dev_name)); cur = delim; } cur++; if (*cur != '@') { /* dst port */ if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; *delim = 0; if (*cur == ' ' || *cur == '\t') np_info(np, "warning: whitespace is not allowed\n"); if (kstrtou16(cur, 10, &np->remote_port)) goto parse_failed; cur = delim; } cur++; /* dst ip */ if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); if (ipv6 < 0) goto parse_failed; else if (ipversion_set && np->ipv6 != (bool)ipv6) goto parse_failed; else np->ipv6 = (bool)ipv6; cur = delim + 1; if (*cur != 0) { /* MAC address */ if (!mac_pton(cur, np->remote_mac)) goto parse_failed; } netpoll_print_options(np); return 0; parse_failed: np_info(np, "couldn't parse config at '%s'!\n", cur); return -1; } EXPORT_SYMBOL(netpoll_parse_options); int __netpoll_setup(struct netpoll *np, struct net_device *ndev) { struct netpoll_info *npinfo; const struct net_device_ops *ops; int err; np->dev = ndev; strscpy(np->dev_name, ndev->name, IFNAMSIZ); if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", np->dev_name); err = -ENOTSUPP; goto out; } if (!rcu_access_pointer(ndev->npinfo)) { npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); if (!npinfo) { err = -ENOMEM; goto out; } sema_init(&npinfo->dev_lock, 1); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); refcount_set(&npinfo->refcnt, 1); ops = np->dev->netdev_ops; if (ops->ndo_netpoll_setup) { err = ops->ndo_netpoll_setup(ndev, npinfo); if (err) goto free_npinfo; } } else { npinfo = rtnl_dereference(ndev->npinfo); refcount_inc(&npinfo->refcnt); } npinfo->netpoll = np; /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); return 0; free_npinfo: kfree(npinfo); out: return err; } EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { struct net_device *ndev = NULL; struct in_device *in_dev; int err; rtnl_lock(); if (np->dev_name[0]) { struct net *net = current->nsproxy->net_ns; ndev = __dev_get_by_name(net, np->dev_name); } if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; goto unlock; } dev_hold(ndev); if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; goto put; } if (!netif_running(ndev)) { unsigned long atmost, atleast; np_info(np, "device %s not up yet, forcing it\n", np->dev_name); err = dev_open(ndev, NULL); if (err) { np_err(np, "failed to open %s\n", ndev->name); goto put; } rtnl_unlock(); atleast = jiffies + HZ/10; atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { if (time_after(jiffies, atmost)) { np_notice(np, "timeout waiting for carrier\n"); break; } msleep(1); } /* If carrier appears to come up instantly, we don't * trust it and pause so that we don't pump all our * queued console messages into the bitbucket. */ if (time_before(jiffies, atleast)) { np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n"); msleep(4000); } rtnl_lock(); } if (!np->local_ip.ip) { if (!np->ipv6) { const struct in_ifaddr *ifa; in_dev = __in_dev_get_rtnl(ndev); if (!in_dev) goto put_noaddr; ifa = rtnl_dereference(in_dev->ifa_list); if (!ifa) { put_noaddr: np_err(np, "no IP address for %s, aborting\n", np->dev_name); err = -EDESTADDRREQ; goto put; } np->local_ip.ip = ifa->ifa_local; np_info(np, "local IP %pI4\n", &np->local_ip.ip); } else { #if IS_ENABLED(CONFIG_IPV6) struct inet6_dev *idev; err = -EDESTADDRREQ; idev = __in6_dev_get(ndev); if (idev) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) != !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; err = 0; break; } read_unlock_bh(&idev->lock); } if (err) { np_err(np, "no IPv6 address for %s, aborting\n", np->dev_name); goto put; } else np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); #else np_err(np, "IPv6 is not supported %s, aborting\n", np->dev_name); err = -EINVAL; goto put; #endif } } /* fill up the skb queue */ refill_skbs(); err = __netpoll_setup(np, ndev); if (err) goto put; rtnl_unlock(); return 0; put: dev_put(ndev); unlock: rtnl_unlock(); return err; } EXPORT_SYMBOL(netpoll_setup); static int __init netpoll_init(void) { skb_queue_head_init(&skb_pool); return 0; } core_initcall(netpoll_init); static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) { struct netpoll_info *npinfo = container_of(rcu_head, struct netpoll_info, rcu); skb_queue_purge(&npinfo->txq); /* we can't call cancel_delayed_work_sync here, as we are in softirq */ cancel_delayed_work(&npinfo->tx_work); /* clean after last, unfinished work */ __skb_queue_purge(&npinfo->txq); /* now cancel it again */ cancel_delayed_work(&npinfo->tx_work); kfree(npinfo); } void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; npinfo = rtnl_dereference(np->dev->npinfo); if (!npinfo) return; synchronize_srcu(&netpoll_srcu); if (refcount_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; ops = np->dev->netdev_ops; if (ops->ndo_netpoll_cleanup) ops->ndo_netpoll_cleanup(np->dev); RCU_INIT_POINTER(np->dev->npinfo, NULL); call_rcu(&npinfo->rcu, rcu_cleanup_netpoll_info); } else RCU_INIT_POINTER(np->dev->npinfo, NULL); } EXPORT_SYMBOL_GPL(__netpoll_cleanup); void __netpoll_free(struct netpoll *np) { ASSERT_RTNL(); /* Wait for transmitting packets to finish before freeing. */ synchronize_rcu(); __netpoll_cleanup(np); kfree(np); } EXPORT_SYMBOL_GPL(__netpoll_free); void netpoll_cleanup(struct netpoll *np) { rtnl_lock(); if (!np->dev) goto out; __netpoll_cleanup(np); dev_put(np->dev); np->dev = NULL; out: rtnl_unlock(); } EXPORT_SYMBOL(netpoll_cleanup); |
| 178 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H /* * Define 'struct task_struct' and provide the main scheduler * APIs (schedule(), wakeup variants, etc.) */ #include <uapi/linux/sched.h> #include <asm/current.h> #include <linux/pid.h> #include <linux/sem.h> #include <linux/shm.h> #include <linux/mutex.h> #include <linux/plist.h> #include <linux/hrtimer.h> #include <linux/irqflags.h> #include <linux/seccomp.h> #include <linux/nodemask.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> #include <linux/syscall_user_dispatch.h> #include <linux/mm_types_task.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers.h> #include <linux/rseq.h> #include <linux/seqlock.h> #include <linux/kcsan.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; struct backing_dev_info; struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; struct io_context; struct io_uring_task; struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; struct robust_list_head; struct root_domain; struct rq; struct sched_attr; struct sched_param; struct seq_file; struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). * * We have two separate sets of flags: task->state * is about runnability, while task->exit_state are * about the task exiting. Confusing, but this way * modifying one set can't modify the other one by * mistake. */ /* Used in tsk->state: */ #define TASK_RUNNING 0x0000 #define TASK_INTERRUPTIBLE 0x0001 #define TASK_UNINTERRUPTIBLE 0x0002 #define __TASK_STOPPED 0x0004 #define __TASK_TRACED 0x0008 /* Used in tsk->exit_state: */ #define EXIT_DEAD 0x0010 #define EXIT_ZOMBIE 0x0020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->state again: */ #define TASK_PARKED 0x0040 #define TASK_DEAD 0x0080 #define TASK_WAKEKILL 0x0100 #define TASK_WAKING 0x0200 #define TASK_NOLOAD 0x0400 #define TASK_NEW 0x0800 /* RT specific auxilliary flag to mark RT lock waiters */ #define TASK_RTLOCK_WAIT 0x1000 #define TASK_STATE_MAX 0x2000 /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED (TASK_WAKEKILL | __TASK_TRACED) #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) #define task_is_traced(task) ((READ_ONCE(task->__state) & __TASK_TRACED) != 0) #define task_is_stopped(task) ((READ_ONCE(task->__state) & __TASK_STOPPED) != 0) #define task_is_stopped_or_traced(task) ((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ do { \ WARN_ON_ONCE(is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_special_state_change(state_value) \ do { \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_set_state() \ do { \ current->saved_state_change = current->task_state_change;\ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_restore_state() \ do { \ current->task_state_change = current->saved_state_change;\ } while (0) #else # define debug_normal_state_change(cond) do { } while (0) # define debug_special_state_change(cond) do { } while (0) # define debug_rtlock_wait_set_state() do { } while (0) # define debug_rtlock_wait_restore_state() do { } while (0) #endif /* * set_current_state() includes a barrier so that the write of current->state * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); * if (CONDITION) * break; * * schedule(); * } * __set_current_state(TASK_RUNNING); * * If the caller does not need such serialisation (because, for instance, the * CONDITION test and condition change and wakeup are under the same lock) then * use __set_current_state(). * * The above is typically ordered against the wakeup, which does: * * CONDITION = 1; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * * where wake_up_state()/try_to_wake_up() executes a full memory barrier before * accessing p->state. * * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ smp_store_mb(current->__state, (state_value)); \ } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must * serialize against wakeups such that any possible in-flight TASK_RUNNING * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ debug_special_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) /* * PREEMPT_RT specific variants for "sleeping" spin/rwlocks * * RT's spin/rwlock substitutions are state preserving. The state of the * task when blocking on the lock is saved in task_struct::saved_state and * restored after the lock has been acquired. These operations are * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT * lock related wakeups while the task is blocked on the lock are * redirected to operate on task_struct::saved_state to ensure that these * are not dropped. On restore task_struct::saved_state is set to * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. * * The lock operation looks like this: * * current_save_and_set_rtlock_wait_state(); * for (;;) { * if (try_lock()) * break; * raw_spin_unlock_irq(&lock->wait_lock); * schedule_rtlock(); * raw_spin_lock_irq(&lock->wait_lock); * set_current_state(TASK_RTLOCK_WAIT); * } * current_restore_rtlock_saved_state(); */ #define current_save_and_set_rtlock_wait_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ current->saved_state = current->__state; \ debug_rtlock_wait_set_state(); \ WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define current_restore_rtlock_saved_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ debug_rtlock_wait_restore_state(); \ WRITE_ONCE(current->__state, current->saved_state); \ current->saved_state = TASK_RUNNING; \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define get_current_state() READ_ONCE(current->__state) /* Task command name length: */ #define TASK_COMM_LEN 16 extern void scheduler_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern long schedule_timeout(long timeout); extern long schedule_timeout_interruptible(long timeout); extern long schedule_timeout_killable(long timeout); extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); #ifdef CONFIG_PREEMPT_RT extern void schedule_rtlock(void); #endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); /** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode * @lock: protects the above two fields * * Stores previous user/system time values such that we can guarantee * monotonicity. */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE u64 utime; u64 stime; raw_spinlock_t lock; #endif }; enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, /* Task is idle */ VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, /* Task runs in userspace in a CPU with VTIME active: */ VTIME_USER, /* Task runs as guests in a CPU with VTIME active: */ VTIME_GUEST, }; struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; unsigned int cpu; u64 utime; u64 stime; u64 gtime; }; /* * Utilization clamp constraints. * @UCLAMP_MIN: Minimum utilization * @UCLAMP_MAX: Maximum utilization * @UCLAMP_CNT: Utilization clamp constraints count */ enum uclamp_id { UCLAMP_MIN = 0, UCLAMP_MAX, UCLAMP_CNT }; #ifdef CONFIG_SMP extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; #endif struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ /* # of times we have run on this CPU: */ unsigned long pcount; /* Time spent waiting on a runqueue: */ unsigned long long run_delay; /* Timestamps: */ /* When did we last run on a CPU? */ unsigned long long last_arrival; /* When were we last queued to run? */ unsigned long long last_queued; #endif /* CONFIG_SCHED_INFO */ }; /* * Integer metrics need fixed point arithmetic, e.g., sched/fair * has a few: load, load_avg, util_avg, freq, and capacity. * * We define a basic fixed point arithmetic range, and then formalize * all these metrics based on that basic range. */ # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) /* Increase resolution of cpu_capacity calculations */ # define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT # define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) struct load_weight { unsigned long weight; u32 inv_weight; }; /** * struct util_est - Estimation utilization of FAIR tasks * @enqueued: instantaneous estimated utilization of a task/cpu * @ewma: the Exponential Weighted Moving Average (EWMA) * utilization of a task * * Support data structure to track an Exponential Weighted Moving Average * (EWMA) of a FAIR task's utilization. New samples are added to the moving * average each time a task completes an activation. Sample's weight is chosen * so that the EWMA will be relatively insensitive to transient changes to the * task's workload. * * The enqueued attribute has a slightly different meaning for tasks and cpus: * - task: the task's util_avg at last task dequeue time * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU * Thus, the util_est.enqueued of a task represents the contribution on the * estimated utilization of the CPU where that task is currently enqueued. * * Only for tasks we track a moving average of the past instantaneous * estimated utilization. This allows to absorb sporadic drops in utilization * of an otherwise almost periodic task. * * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg * updates. When a task is dequeued, its util_est should not be updated if its * util_avg has not been updated in the meantime. * This information is mapped into the MSB bit of util_est.enqueued at dequeue * time. Since max value of util_est.enqueued for a task is 1024 (PELT util_avg * for a task) it is safe to use MSB. */ struct util_est { unsigned int enqueued; unsigned int ewma; #define UTIL_EST_WEIGHT_SHIFT 2 #define UTIL_AVG_UNCHANGED 0x80000000 } __attribute__((__aligned__(sizeof(u64)))); /* * The load/runnable/util_avg accumulates an infinite geometric series * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c). * * [load_avg definition] * * load_avg = runnable% * scale_load_down(load) * * [runnable_avg definition] * * runnable_avg = runnable% * SCHED_CAPACITY_SCALE * * [util_avg definition] * * util_avg = running% * SCHED_CAPACITY_SCALE * * where runnable% is the time ratio that a sched_entity is runnable and * running% the time ratio that a sched_entity is running. * * For cfs_rq, they are the aggregated values of all runnable and blocked * sched_entities. * * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU * capacity scaling. The scaling is done through the rq_clock_pelt that is used * for computing those signals (see update_rq_clock_pelt()) * * N.B., the above ratios (runnable% and running%) themselves are in the * range of [0, 1]. To do fixed point arithmetics, we therefore scale them * to as large a range as necessary. This is for example reflected by * util_avg's SCHED_CAPACITY_SCALE. * * [Overflow issue] * * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities * with the highest load (=88761), always runnable on a single cfs_rq, * and should not overflow as the number already hits PID_MAX_LIMIT. * * For all other cases (including 32-bit kernels), struct load_weight's * weight will overflow first before we do, because: * * Max(load_avg) <= Max(load.weight) * * Then it is the load_weight's responsibility to consider overflow * issues. */ struct sched_avg { u64 last_update_time; u64 load_sum; u64 runnable_sum; u32 util_sum; u32 period_contrib; unsigned long load_avg; unsigned long runnable_avg; unsigned long util_avg; struct util_est util_est; } ____cacheline_aligned; struct sched_statistics { #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; u64 wait_count; u64 wait_sum; u64 iowait_count; u64 iowait_sum; u64 sleep_start; u64 sleep_max; s64 sum_sleep_runtime; u64 block_start; u64 block_max; u64 exec_max; u64 slice_max; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; u64 nr_wakeups; u64 nr_wakeups_sync; u64 nr_wakeups_migrate; u64 nr_wakeups_local; u64 nr_wakeups_remote; u64 nr_wakeups_affine; u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; #endif } ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ struct load_weight load; struct rb_node run_node; struct list_head group_node; unsigned int on_rq; u64 exec_start; u64 sum_exec_runtime; u64 vruntime; u64 prev_sum_exec_runtime; u64 nr_migrations; #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; /* rq "owned" by this entity/group: */ struct cfs_rq *my_q; /* cached value of my_q->h_nr_running */ unsigned long runnable_weight; #endif #ifdef CONFIG_SMP /* * Per entity load average tracking. * * Put into separate cache line so it does not * collide with read-mostly values above. */ struct sched_avg avg; #endif }; struct sched_rt_entity { struct list_head run_list; unsigned long timeout; unsigned long watchdog_stamp; unsigned int time_slice; unsigned short on_rq; unsigned short on_list; struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity *parent; /* rq on which this entity is (to be) queued: */ struct rt_rq *rt_rq; /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif } __randomize_layout; struct sched_dl_entity { struct rb_node rb_node; /* * Original scheduling parameters. Copied here from sched_attr * during sched_setattr(), they will remain the same until * the next sched_setattr(). */ u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ u64 dl_bw; /* dl_runtime / dl_period */ u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ u64 deadline; /* Absolute deadline for this instance */ unsigned int flags; /* Specifying the scheduler behaviour */ /* * Some bool flags: * * @dl_throttled tells if we exhausted the runtime. If so, the * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * * @dl_non_contending tells if the task is inactive while still * contributing to the active utilization. In other words, it * indicates if the inactive timer has been armed and its handler * has not been executed yet. This flag is useful to avoid race * conditions between the inactive timer handler and the wakeup * code. * * @dl_overrun tells if the task asked to be informed about runtime * overruns. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; /* * Inactive timer, responsible for decreasing the active utilization * at the "0-lag time". When a -deadline task blocks, it contributes * to GRUB's active utilization until the "0-lag time", hence a * timer is needed to decrease the active utilization at the correct * time. */ struct hrtimer inactive_timer; #ifdef CONFIG_RT_MUTEXES /* * Priority Inheritance. When a DEADLINE scheduling entity is boosted * pi_se points to the donor, otherwise points to the dl_se it belongs * to (the original one/itself). */ struct sched_dl_entity *pi_se; #endif }; #ifdef CONFIG_UCLAMP_TASK /* Number of utilization clamp buckets (shorter alias) */ #define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT /* * Utilization clamp for a scheduling entity * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value * @active: the se is currently refcounted in a rq's bucket * @user_defined: the requested clamp value comes from user-space * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from * the fast path. * * The active bit is set whenever a task has got an "effective" value assigned, * which can be different from the clamp value "requested" from user-space. * This allows to know a task is refcounted in the rq's bucket corresponding * to the "effective" bucket_id. * * The user_defined bit is set whenever a task has got a task-specific clamp * value requested from userspace, i.e. the system defaults apply to this task * just as a restriction. This allows to relax default clamps when a less * restrictive task-specific value has been requested, thus allowing to * implement a "nice" semantic. For example, a task running with a 20% * default boost can still drop its own boosting to 0%. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); unsigned int active : 1; unsigned int user_defined : 1; }; #endif /* CONFIG_UCLAMP_TASK */ union rcu_special { struct { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; enum perf_event_task_context { perf_invalid_context = -1, perf_hw_context = 0, perf_sw_context, perf_nr_task_contexts, }; struct wake_q_node { struct wake_q_node *next; }; struct kmap_ctrl { #ifdef CONFIG_KMAP_LOCAL int idx; pte_t pteval[KM_MAX_IDX]; #endif }; struct task_struct { #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For reasons of header soup (see current_thread_info()), this * must be the first element of task_struct. */ struct thread_info thread_info; #endif unsigned int __state; #ifdef CONFIG_PREEMPT_RT /* saved state for "spinlock sleepers" */ unsigned int saved_state; #endif /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. */ randomized_struct_fields_start void *stack; refcount_t usage; /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; #ifdef CONFIG_THREAD_INFO_IN_TASK /* Current CPU: */ unsigned int cpu; #endif unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; /* * recent_used_cpu is initially set as the last CPU used by a task * that wakes affine another task. Waker/wakee relationships can * push tasks around a CPU where each wakeup moves to the next one. * Tracking a recently used CPU allows a quick search for a recently * used CPU that may be idle. */ int recent_used_cpu; int wake_cpu; #endif int on_rq; int prio; int static_prio; int normal_prio; unsigned int rt_priority; const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; unsigned long core_cookie; unsigned int core_occupation; #endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp_req[UCLAMP_CNT]; /* * Effective clamp values used for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif struct sched_statistics stats; #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; #endif #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif unsigned int policy; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; #ifdef CONFIG_SMP unsigned short migration_disabled; #endif unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; u8 rcu_tasks_holdout; u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; int trc_ipi_to_cpu; union rcu_special trc_reader_special; bool trc_reader_checked; struct list_head trc_holdout_list; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; struct list_head tasks; #ifdef CONFIG_SMP struct plist_node pushable_tasks; struct rb_node pushable_dl_tasks; #endif struct mm_struct *mm; struct mm_struct *active_mm; /* Per-thread vma caching: */ struct vmacache vmacache; #ifdef SPLIT_RSS_COUNTING struct task_rss_stat rss_stat; #endif int exit_state; int exit_code; int exit_signal; /* The signal sent when the parent dies: */ int pdeath_signal; /* JOBCTL_*, siglock protected: */ unsigned long jobctl; /* Used for emulating ABI behavior of previous Linux versions: */ unsigned int personality; /* Scheduler bits, serialized by scheduler locks: */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; #ifdef CONFIG_PSI unsigned sched_psi_wake_requeue:1; #endif /* Force alignment to the next boundary: */ unsigned :0; /* Unserialized, strictly 'current' */ /* * This field must not be in the scheduler word above due to wakelist * queueing no longer being serialized by p->on_cpu. However: * * p->XXX = X; ttwu() * schedule() if (p->on_rq && ..) // false * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true * deactivate_task() ttwu_queue_wakelist()) * p->on_rq = 0; p->sched_remote_wakeup = Y; * * guarantees all stores of 'current' are visible before * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; /* Bit to tell LSMs we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG unsigned in_user_fault:1; #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif #ifdef CONFIG_CGROUPS /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; /* task is frozen/stopped (used by the cgroup freezer) */ unsigned frozen:1; #endif #ifdef CONFIG_BLK_CGROUP unsigned use_memdelay:1; #endif #ifdef CONFIG_PSI /* Stalled due to lack of memory */ unsigned in_memstall:1; #endif #ifdef CONFIG_PAGE_OWNER /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; pid_t pid; pid_t tgid; #ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif /* * Pointers to the (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->real_parent->pid) */ /* Real parent process: */ struct task_struct __rcu *real_parent; /* Recipient of SIGCHLD, wait4() reports: */ struct task_struct __rcu *parent; /* * Children/sibling form the list of natural children: */ struct list_head children; struct list_head sibling; struct task_struct *group_leader; /* * 'ptraced' is the list of tasks this task is using ptrace() on. * * This includes both natural children and PTRACE_ATTACH targets. * 'ptrace_entry' is this task's link on the p->parent->ptraced list. */ struct list_head ptraced; struct list_head ptrace_entry; /* PID/PID hash table linkage. */ struct pid *thread_pid; struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_group; struct list_head thread_node; struct completion *vfork_done; /* CLONE_CHILD_SETTID: */ int __user *set_child_tid; /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; /* PF_IO_WORKER */ void *pf_io_worker; u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME u64 utimescaled; u64 stimescaled; #endif u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif /* Context switch counts: */ unsigned long nvcsw; unsigned long nivcsw; /* Monotonic time in nsecs: */ u64 start_time; /* Boot based time in nsecs: */ u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; unsigned long maj_flt; /* Empty if CONFIG_POSIX_CPUTIMERS=n */ struct posix_cputimers posix_cputimers; #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK struct posix_cputimers_work posix_cputimers_work; #endif /* Process credentials: */ /* Tracer's credentials at attach: */ const struct cred __rcu *ptracer_cred; /* Objective and real subjective task credentials (COW): */ const struct cred __rcu *real_cred; /* Effective (overridable) subjective task credentials (COW): */ const struct cred __rcu *cred; #ifdef CONFIG_KEYS /* Cached requested key. */ struct key *cached_requested_key; #endif /* * executable name, excluding path. * * - normally initialized setup_new_exec() * - access it with [gs]et_task_comm() * - lock it with task_lock() */ char comm[TASK_COMM_LEN]; struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC struct sysv_sem sysvsem; struct sysv_shm sysvshm; #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; /* Open file information: */ struct files_struct *files; #ifdef CONFIG_IO_URING struct io_uring_task *io_uring; #endif /* Namespaces: */ struct nsproxy *nsproxy; /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; struct callback_head *task_works; #ifdef CONFIG_AUDIT #ifdef CONFIG_AUDITSYSCALL struct audit_context *audit_context; #endif kuid_t loginuid; unsigned int sessionid; #endif struct seccomp seccomp; struct syscall_user_dispatch syscall_dispatch; /* Thread group tracking: */ u64 parent_exec_id; u64 self_exec_id; /* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */ spinlock_t alloc_lock; /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; struct wake_q_node wake_q; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ struct rt_mutex_waiter *pi_blocked_on; #endif #ifdef CONFIG_DEBUG_MUTEXES /* Mutex deadlock detection: */ struct mutex_waiter *blocked_on; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP int non_block_count; #endif #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events irqtrace; unsigned int hardirq_threaded; u64 hardirq_chain_key; int softirqs_enabled; int softirq_context; int irq_config; #endif #ifdef CONFIG_PREEMPT_RT int softirq_disable_cnt; #endif #ifdef CONFIG_LOCKDEP # define MAX_LOCK_DEPTH 48UL u64 curr_chain_key; int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif #if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP) unsigned int in_ubsan; #endif /* Journalling filesystem info: */ void *journal_info; /* Stacked block device info: */ struct bio_list *bio_list; #ifdef CONFIG_BLOCK /* Stack plugging: */ struct blk_plug *plug; #endif /* VM state: */ struct reclaim_state *reclaim_state; struct backing_dev_info *backing_dev_info; struct io_context *io_context; #ifdef CONFIG_COMPACTION struct capture_control *capture_control; #endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_PSI /* Pressure stall state */ unsigned int psi_flags; #endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; /* Accumulated virtual memory usage: */ u64 acct_vm_mem1; /* stime + utime since last update: */ u64 acct_timexpd; #endif #ifdef CONFIG_CPUSETS /* Protected by ->alloc_lock: */ nodemask_t mems_allowed; /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; int cpuset_slab_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif #ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; struct mutex futex_exit_mutex; unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts]; struct mutex perf_event_mutex; struct list_head perf_event_list; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; #endif #ifdef CONFIG_NUMA /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING int numa_scan_seq; unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; unsigned long numa_migrate_retry; /* Migration stamp: */ u64 node_stamp; u64 last_task_numa_placement; u64 last_sum_exec_runtime; struct callback_head numa_work; /* * This pointer is only modified for current in syscall and * pagefault context (and for tasks being destroyed), so it can be read * from any of the following contexts: * - RCU read-side critical section * - current->numa_group from everywhere * - task's runqueue locked, task not running */ struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer * in this precise order. * * faults_memory: Exponential decaying average of faults on a per-node * basis. Scheduling placement decisions are made based on these * counts. The values remain static for the duration of a PTE scan. * faults_cpu: Track the nodes the process was running on when a NUMA * hinting fault was incurred. * faults_memory_buffer and faults_cpu_buffer: Record faults per node * during the current scan window. When the scan completes, the counts * in faults_memory and faults_cpu decay and these values are copied. */ unsigned long *numa_faults; unsigned long total_numa_faults; /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local or failed to migrate. The task scan * period is adapted based on the locality of the faults with different * weights depending on whether they were shared or private faults */ unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_RSEQ struct rseq __user *rseq; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically * with respect to preemption. */ unsigned long rseq_event_mask; #endif struct tlbflush_unmap_batch tlb_ubc; union { refcount_t rcu_users; struct rcu_head rcu; }; /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; struct page_frag task_frag; #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif #ifdef CONFIG_FAULT_INJECTION int make_it_fail; unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call * balance_dirty_pages() for a dirty throttling pause: */ int nr_dirtied; int nr_dirtied_pause; /* Start of a write-and-pause period: */ unsigned long dirty_paused_when; #ifdef CONFIG_LATENCYTOP int latency_record_count; struct latency_record latency_record[LT_SAVECOUNT]; #endif /* * Time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ u64 timer_slack_ns; u64 default_timer_slack_ns; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) unsigned int kasan_depth; #endif #ifdef CONFIG_KCSAN struct kcsan_ctx kcsan_ctx; #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif #endif #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; int curr_ret_depth; /* Stack of return addresses for return function tracing: */ struct ftrace_ret_stack *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; /* * Number of functions that haven't been traced * because of depth overrun: */ atomic_t trace_overrun; /* Pause tracing: */ atomic_t tracing_graph_pause; #endif #ifdef CONFIG_TRACING /* State flags for use by tracers: */ unsigned long trace; /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV /* See kernel/kcov.c for more details. */ /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; /* Buffer for coverage collection: */ void *kcov_area; /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; /* KCOV common handle for remote coverage collection: */ u64 kcov_handle; /* KCOV sequence number: */ int kcov_sequence; /* Collect coverage from softirq context: */ unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG struct mem_cgroup *memcg_in_oom; gfp_t memcg_oom_gfp_mask; int memcg_oom_order; /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; #endif #ifdef CONFIG_BLK_CGROUP struct request_queue *throttle_queue; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) unsigned int sequential_io; unsigned int sequential_io_avg; #endif struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; # ifdef CONFIG_PREEMPT_RT unsigned long saved_state_change; # endif #endif int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK /* A live task holds one reference: */ refcount_t stack_refcount; #endif #ifdef CONFIG_LIVEPATCH int patch_state; #endif #ifdef CONFIG_SECURITY /* Used by LSM modules for access restriction: */ void *security; #endif #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; unsigned long prev_lowest_stack; #endif #ifdef CONFIG_X86_MCE void __user *mce_vaddr; __u64 mce_kflags; u64 mce_addr; __u64 mce_ripv : 1, mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; int mce_count; #endif #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* * If L1D flush is supported on mm context switch * then we use this callback head to queue kill work * to kill tasks that are not running on SMT disabled * cores */ struct callback_head l1d_flush_kill; #endif /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. */ randomized_struct_fields_end /* CPU-specific state of this task: */ struct thread_struct thread; /* * WARNING: on x86, 'thread_struct' contains a variable-sized * structure. It *MUST* be at the end of 'task_struct'. * * Do not put anything below here! */ }; static inline struct pid *task_pid(struct task_struct *task) { return task->thread_pid; } /* * the helpers to get the task's different pids as they are seen * from various namespaces * * task_xid_nr() : global id, i.e. the id seen from the init namespace; * task_xid_vnr() : virtual id, i.e. the id seen from the pid namespace of * current. * task_xid_nr_ns() : id seen from the ns specified; * * see also pid_nr() etc in include/linux/pid.h */ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns); static inline pid_t task_pid_nr(struct task_struct *tsk) { return tsk->pid; } static inline pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns); } static inline pid_t task_pid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL); } static inline pid_t task_tgid_nr(struct task_struct *tsk) { return tsk->tgid; } /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. * * Test if a process is not yet dead (at most zombie state) * If pid_alive fails, then pointers within the task structure * can be stale and must not be dereferenced. * * Return: 1 if the process is alive. 0 otherwise. */ static inline int pid_alive(const struct task_struct *p) { return p->thread_pid != NULL; } static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); } static inline pid_t task_pgrp_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL); } static inline pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns); } static inline pid_t task_session_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, ns); } static inline pid_t task_tgid_vnr(struct task_struct *tsk) { return __task_pid_nr_ns(tsk, PIDTYPE_TGID, NULL); } static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) { pid_t pid = 0; rcu_read_lock(); if (pid_alive(tsk)) pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); rcu_read_unlock(); return pid; } static inline pid_t task_ppid_nr(const struct task_struct *tsk) { return task_ppid_nr_ns(tsk, &init_pid_ns); } /* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { return task_pgrp_nr_ns(tsk, &init_pid_ns); } #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) static inline unsigned int task_state_index(struct task_struct *tsk) { unsigned int tsk_state = READ_ONCE(tsk->__state); unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if (tsk_state == TASK_IDLE) state = TASK_REPORT_IDLE; /* * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. */ if (tsk_state == TASK_RTLOCK_WAIT) state = TASK_UNINTERRUPTIBLE; return fls(state); } static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); return state_char[state]; } static inline char task_state_to_char(struct task_struct *tsk) { return task_index_to_char(task_state_index(tsk)); } /** * is_global_init - check if a task structure is init. Since init * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. * * Return: 1 if the task structure is init. 0 otherwise. */ static inline int is_global_init(struct task_struct *tsk) { return task_tgid_nr(tsk) == 1; } extern struct pid *cad_pid; /* * Per process flags */ #define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ #define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF_FROZEN 0x00010000 /* Frozen for system suspend */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocation requests will inherit GFP_NOFS */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocation requests will inherit GFP_NOIO */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example * with tsk_used_math (like during threaded core dumping). * There is however an exception to this rule during ptrace * or during fork: the ptracer task is allowed to write to the * child->flags of its traced child (same goes for fork, the parent * can write to the child->flags), because we're guaranteed the * child is not running and in turn not changing child->flags * at the same time the parent does it. */ #define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) #define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) #define clear_used_math() clear_stopped_child_used_math(current) #define set_used_math() set_stopped_child_used_math(current) #define conditional_stopped_child_used_math(condition, child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0) #define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current) #define copy_to_stopped_child_used_math(child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0) /* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && (current->nr_cpus_allowed == 1); #else return true; #endif } /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ { return test_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_SET(name, func) \ static inline void task_set_##func(struct task_struct *p) \ { set_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_CLEAR(name, func) \ static inline void task_clear_##func(struct task_struct *p) \ { clear_bit(PFA_##name, &p->atomic_flags); } TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) TASK_PFA_TEST(SPREAD_PAGE, spread_page) TASK_PFA_SET(SPREAD_PAGE, spread_page) TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { current->flags &= ~flags; current->flags |= orig_flags & flags; } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { if (!cpumask_test_cpu(0, new_mask)) return -EINVAL; return 0; } static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { if (src->user_cpus_ptr) return -EINVAL; return 0; } static inline void release_user_cpus_ptr(struct task_struct *p) { WARN_ON(p->user_cpus_ptr); } static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) { return 0; } #endif extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); /** * task_nice - return the nice value of a given task. * @p: the task in question. * * Return: The nice value [ -20 ... 0 ... 19 ]. */ static inline int task_nice(const struct task_struct *p) { return PRIO_TO_NICE((p)->static_prio); } extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. * * Return: 1 if @p is an idle task. 0 otherwise. */ static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { #ifndef CONFIG_ARCH_TASK_STRUCT_ON_STACK struct task_struct task; #endif #ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; #endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; #ifndef CONFIG_THREAD_INFO_IN_TASK extern struct thread_info init_thread_info; #endif extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK static inline struct thread_info *task_thread_info(struct task_struct *task) { return &task->thread_info; } #elif !defined(__HAVE_THREAD_FUNCTIONS) # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif /* * find a task by one of its numerical ids * * find_task_by_pid_ns(): * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid * * see also find_vpid() etc in include/linux/pid.h */ extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); /* * find a task by its virtual pid and get the task struct */ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); #else static inline void kick_process(struct task_struct *tsk) { } #endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); static inline void set_task_comm(struct task_struct *tsk, const char *from) { __set_task_comm(tsk, from, false); } extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk); #define get_task_comm(buf, tsk) ({ \ BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN); \ __get_task_comm(buf, sizeof(buf), tsk); \ }) #ifdef CONFIG_SMP static __always_inline void scheduler_ipi(void) { /* * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting * TIF_NEED_RESCHED remotely (for the first time) will also send * this IPI. */ preempt_fold_need_resched(); } extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); #else static inline void scheduler_ipi(void) { } static inline unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) { return 1; } #endif /* * Set thread flags in other task's structures. * See asm/thread_info.h for TIF_xxxx flags available: */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { set_ti_thread_flag(task_thread_info(tsk), flag); } static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) { clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, bool value) { update_ti_thread_flag(task_thread_info(tsk), flag, value); } static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_ti_thread_flag(task_thread_info(tsk), flag); } static inline void set_tsk_need_resched(struct task_struct *tsk) { set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline int test_tsk_need_resched(struct task_struct *tsk) { return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); #ifdef CONFIG_PREEMPT_DYNAMIC DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) { return static_call_mod(cond_resched)(); } #else static inline int _cond_resched(void) { return __cond_resched(); } #endif /* CONFIG_PREEMPT_DYNAMIC */ #else static inline int _cond_resched(void) { return 0; } #endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */ #define cond_resched() ({ \ ___might_sleep(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); #define cond_resched_lock(lock) ({ \ ___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\ __cond_resched_lock(lock); \ }) #define cond_resched_rwlock_read(lock) ({ \ __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ __cond_resched_rwlock_read(lock); \ }) #define cond_resched_rwlock_write(lock) ({ \ __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ __cond_resched_rwlock_write(lock); \ }) static inline void cond_resched_rcu(void) { #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) rcu_read_unlock(); cond_resched(); rcu_read_lock(); #endif } /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, * but a general need for low latency) */ static inline int spin_needbreak(spinlock_t *lock) { #ifdef CONFIG_PREEMPTION return spin_is_contended(lock); #else return 0; #endif } /* * Check if a rwlock is contended. * Returns non-zero if there is another task waiting on the rwlock. * Returns zero if the lock is not contended or the system / underlying * rwlock implementation does not support contention detection. * Technically does not depend on CONFIG_PREEMPTION, but a general need * for low latency. */ static inline int rwlock_needbreak(rwlock_t *lock) { #ifdef CONFIG_PREEMPTION return rwlock_is_contended(lock); #else return 0; #endif } static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); } /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP static inline unsigned int task_cpu(const struct task_struct *p) { #ifdef CONFIG_THREAD_INFO_IN_TASK return READ_ONCE(p->cpu); #else return READ_ONCE(task_thread_info(p)->cpu); #endif } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); #else static inline unsigned int task_cpu(const struct task_struct *p) { return 0; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_SMP */ extern bool sched_task_on_rq(struct task_struct *p); /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. * * This allows us to terminate optimistic spin loops and block, analogous to * the native optimistic spin heuristic of testing if the lock owner task is * running or not. */ #ifndef vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { return false; } #endif extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif #ifdef CONFIG_SMP /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu, unsigned long max); #endif /* CONFIG_SMP */ #ifdef CONFIG_RSEQ /* * Map the event mask on the user-space ABI enum rseq_cs_flags * for direct mask checks. */ enum rseq_event_mask_bits { RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, }; enum rseq_event_mask { RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), }; static inline void rseq_set_notify_resume(struct task_struct *t) { if (t->rseq) set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { if (current->rseq) __rseq_handle_notify_resume(ksig, regs); } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { preempt_disable(); __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); preempt_enable(); rseq_handle_notify_resume(ksig, regs); } /* rseq_preempt() requires preemption to be disabled. */ static inline void rseq_preempt(struct task_struct *t) { __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* rseq_migrate() requires preemption to be disabled. */ static inline void rseq_migrate(struct task_struct *t) { __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* * If parent process has a registered restartable sequences area, the * child inherits. Unregister rseq for a clone with CLONE_VM set. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { if (clone_flags & CLONE_VM) { t->rseq = NULL; t->rseq_sig = 0; t->rseq_event_mask = 0; } else { t->rseq = current->rseq; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; } } static inline void rseq_execve(struct task_struct *t) { t->rseq = NULL; t->rseq_sig = 0; t->rseq_event_mask = 0; } #else static inline void rseq_set_notify_resume(struct task_struct *t) { } static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_preempt(struct task_struct *t) { } static inline void rseq_migrate(struct task_struct *t) { } static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { } static inline void rseq_execve(struct task_struct *t) { } #endif #ifdef CONFIG_DEBUG_RSEQ void rseq_syscall(struct pt_regs *regs); #else static inline void rseq_syscall(struct pt_regs *regs) { } #endif const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq); char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len); int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq); const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq); const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); int sched_trace_rq_cpu(struct rq *rq); int sched_trace_rq_cpu_capacity(struct rq *rq); int sched_trace_rq_nr_running(struct rq *rq); const struct cpumask *sched_trace_rd_span(struct root_domain *rd); #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, unsigned long uaddr); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } #endif #endif |
| 37 37 37 37 37 37 36 37 37 4 4 3 1 1 1 8 8 2 6 8 8 4 4 4 20 20 7 19 37 1 4 1 2 8 8 1 1 2 2 3 1 4 4 2 2 4 4 4 7 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * "Ping" sockets * * Based on ipv4/udp.c code. * * Authors: Vasiliy Kulikov / Openwall (for Linux 2.6), * Pavel Kankovsky (for Linux 2.4.32) * * Pavel gave all rights to bugs to Vasiliy, * none of the bugs are Pavel's now. */ #include <linux/uaccess.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/mm.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <net/snmp.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/export.h> #include <net/sock.h> #include <net/ping.h> #include <net/udp.h> #include <net/route.h> #include <net/inet_common.h> #include <net/checksum.h> #if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #include <linux/icmpv6.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/transp_v6.h> #endif struct ping_table { struct hlist_nulls_head hash[PING_HTABLE_SIZE]; rwlock_t lock; }; static struct ping_table ping_table; struct pingv6_ops pingv6_ops; EXPORT_SYMBOL_GPL(pingv6_ops); static u16 ping_port_rover; static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask) { u32 res = (num + net_hash_mix(net)) & mask; pr_debug("hash(%u) = %u\n", num, res); return res; } EXPORT_SYMBOL_GPL(ping_hash); static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table, struct net *net, unsigned int num) { return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)]; } int ping_get_port(struct sock *sk, unsigned short ident) { struct hlist_nulls_node *node; struct hlist_nulls_head *hlist; struct inet_sock *isk, *isk2; struct sock *sk2 = NULL; isk = inet_sk(sk); write_lock_bh(&ping_table.lock); if (ident == 0) { u32 i; u16 result = ping_port_rover + 1; for (i = 0; i < (1L << 16); i++, result++) { if (!result) result++; /* avoid zero */ hlist = ping_hashslot(&ping_table, sock_net(sk), result); ping_portaddr_for_each_entry(sk2, node, hlist) { isk2 = inet_sk(sk2); if (isk2->inet_num == result) goto next_port; } /* found */ ping_port_rover = ident = result; break; next_port: ; } if (i >= (1L << 16)) goto fail; } else { hlist = ping_hashslot(&ping_table, sock_net(sk), ident); ping_portaddr_for_each_entry(sk2, node, hlist) { isk2 = inet_sk(sk2); /* BUG? Why is this reuse and not reuseaddr? ping.c * doesn't turn off SO_REUSEADDR, and it doesn't expect * that other ping processes can steal its packets. */ if ((isk2->inet_num == ident) && (sk2 != sk) && (!sk2->sk_reuse || !sk->sk_reuse)) goto fail; } } pr_debug("found port/ident = %d\n", ident); isk->inet_num = ident; if (sk_unhashed(sk)) { pr_debug("was not hashed\n"); sock_hold(sk); hlist_nulls_add_head(&sk->sk_nulls_node, hlist); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } write_unlock_bh(&ping_table.lock); return 0; fail: write_unlock_bh(&ping_table.lock); return 1; } EXPORT_SYMBOL_GPL(ping_get_port); int ping_hash(struct sock *sk) { pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num); BUG(); /* "Please do not press this button again." */ return 0; } void ping_unhash(struct sock *sk) { struct inet_sock *isk = inet_sk(sk); pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); write_lock_bh(&ping_table.lock); if (sk_hashed(sk)) { hlist_nulls_del(&sk->sk_nulls_node); sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); } write_unlock_bh(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_unhash); static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) { struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident); struct sock *sk = NULL; struct inet_sock *isk; struct hlist_nulls_node *hnode; int dif, sdif; if (skb->protocol == htons(ETH_P_IP)) { dif = inet_iif(skb); sdif = inet_sdif(skb); pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", (int)ident, &ip_hdr(skb)->daddr, dif); #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { dif = inet6_iif(skb); sdif = inet6_sdif(skb); pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n", (int)ident, &ipv6_hdr(skb)->daddr, dif); #endif } else { return NULL; } read_lock_bh(&ping_table.lock); ping_portaddr_for_each_entry(sk, hnode, hslot) { isk = inet_sk(sk); pr_debug("iterate\n"); if (isk->inet_num != ident) continue; if (skb->protocol == htons(ETH_P_IP) && sk->sk_family == AF_INET) { pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk, (int) isk->inet_num, &isk->inet_rcv_saddr, sk->sk_bound_dev_if); if (isk->inet_rcv_saddr && isk->inet_rcv_saddr != ip_hdr(skb)->daddr) continue; #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6) && sk->sk_family == AF_INET6) { pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk, (int) isk->inet_num, &sk->sk_v6_rcv_saddr, sk->sk_bound_dev_if); if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, &ipv6_hdr(skb)->daddr)) continue; #endif } else { continue; } if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && sk->sk_bound_dev_if != sdif) continue; sock_hold(sk); goto exit; } sk = NULL; exit: read_unlock_bh(&ping_table.lock); return sk; } static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, kgid_t *high) { kgid_t *data = net->ipv4.ping_group_range.range; unsigned int seq; do { seq = read_seqbegin(&net->ipv4.ping_group_range.lock); *low = data[0]; *high = data[1]; } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); } int ping_init_sock(struct sock *sk) { struct net *net = sock_net(sk); kgid_t group = current_egid(); struct group_info *group_info; int i; kgid_t low, high; int ret = 0; if (sk->sk_family == AF_INET6) sk->sk_ipv6only = 1; inet_get_ping_group_range_net(net, &low, &high); if (gid_lte(low, group) && gid_lte(group, high)) return 0; group_info = get_current_groups(); for (i = 0; i < group_info->ngroups; i++) { kgid_t gid = group_info->gid[i]; if (gid_lte(low, gid) && gid_lte(gid, high)) goto out_release_group; } ret = -EACCES; out_release_group: put_group_info(group_info); return ret; } EXPORT_SYMBOL_GPL(ping_init_sock); void ping_close(struct sock *sk, long timeout) { pr_debug("ping_close(sk=%p,sk->num=%u)\n", inet_sk(sk), inet_sk(sk)->inet_num); pr_debug("isk->refcnt = %d\n", refcount_read(&sk->sk_refcnt)); sk_common_release(sk); } EXPORT_SYMBOL_GPL(ping_close); /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, struct sockaddr *uaddr, int addr_len) { struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; u32 tb_id = RT_TABLE_LOCAL; int chk_addr_ret; if (addr_len < sizeof(*addr)) return -EINVAL; if (addr->sin_family != AF_INET && !(addr->sin_family == AF_UNSPEC && addr->sin_addr.s_addr == htonl(INADDR_ANY))) return -EAFNOSUPPORT; pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) chk_addr_ret = RTN_LOCAL; else { tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); } if ((!inet_can_nonlocal_bind(net, isk) && chk_addr_ret != RTN_LOCAL) || chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) return -EADDRNOTAVAIL; #if IS_ENABLED(CONFIG_IPV6) } else if (sk->sk_family == AF_INET6) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; int addr_type, scoped, has_addr; struct net_device *dev = NULL; if (addr_len < sizeof(*addr)) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EAFNOSUPPORT; pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n", sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port)); addr_type = ipv6_addr_type(&addr->sin6_addr); scoped = __ipv6_addr_needs_scope_id(addr_type); if ((addr_type != IPV6_ADDR_ANY && !(addr_type & IPV6_ADDR_UNICAST)) || (scoped && !addr->sin6_scope_id)) return -EINVAL; rcu_read_lock(); if (addr->sin6_scope_id) { dev = dev_get_by_index_rcu(net, addr->sin6_scope_id); if (!dev) { rcu_read_unlock(); return -ENODEV; } } if (!dev && sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { rcu_read_unlock(); return -ENODEV; } } has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev, scoped); rcu_read_unlock(); if (!(ipv6_can_nonlocal_bind(net, isk) || has_addr || addr_type == IPV6_ADDR_ANY)) return -EADDRNOTAVAIL; if (scoped) sk->sk_bound_dev_if = addr->sin6_scope_id; #endif } else { return -EAFNOSUPPORT; } return 0; } static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) { if (saddr->sa_family == AF_INET) { struct inet_sock *isk = inet_sk(sk); struct sockaddr_in *addr = (struct sockaddr_in *) saddr; isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr; #if IS_ENABLED(CONFIG_IPV6) } else if (saddr->sa_family == AF_INET6) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr; struct ipv6_pinfo *np = inet6_sk(sk); sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr; #endif } } /* * We need our own bind because there are no privileged id's == local ports. * Moreover, we don't allow binding to multi- and broadcast addresses. */ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *isk = inet_sk(sk); unsigned short snum; int err; int dif = sk->sk_bound_dev_if; err = ping_check_bind_addr(sk, isk, uaddr, addr_len); if (err) return err; lock_sock(sk); err = -EINVAL; if (isk->inet_num != 0) goto out; err = -EADDRINUSE; snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port); if (ping_get_port(sk, snum) != 0) { /* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */ sk->sk_bound_dev_if = dif; goto out; } ping_set_saddr(sk, uaddr); pr_debug("after bind(): num = %hu, dif = %d\n", isk->inet_num, sk->sk_bound_dev_if); err = 0; if (sk->sk_family == AF_INET && isk->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; #endif if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; isk->inet_sport = htons(isk->inet_num); isk->inet_daddr = 0; isk->inet_dport = 0; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); #endif sk_dst_reset(sk); out: release_sock(sk); pr_debug("ping_v4_bind -> %d\n", err); return err; } EXPORT_SYMBOL_GPL(ping_bind); /* * Is this a supported type of ICMP message? */ static inline int ping_supported(int family, int type, int code) { return (family == AF_INET && type == ICMP_ECHO && code == 0) || (family == AF_INET && type == ICMP_EXT_ECHO && code == 0) || (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0) || (family == AF_INET6 && type == ICMPV6_EXT_ECHO_REQUEST && code == 0); } /* * This routine is called by the ICMP module when it gets some * sort of error condition. */ void ping_err(struct sk_buff *skb, int offset, u32 info) { int family; struct icmphdr *icmph; struct inet_sock *inet_sock; int type; int code; struct net *net = dev_net(skb->dev); struct sock *sk; int harderr; int err; if (skb->protocol == htons(ETH_P_IP)) { family = AF_INET; type = icmp_hdr(skb)->type; code = icmp_hdr(skb)->code; icmph = (struct icmphdr *)(skb->data + offset); } else if (skb->protocol == htons(ETH_P_IPV6)) { family = AF_INET6; type = icmp6_hdr(skb)->icmp6_type; code = icmp6_hdr(skb)->icmp6_code; icmph = (struct icmphdr *) (skb->data + offset); } else { BUG(); } /* We assume the packet has already been checked by icmp_unreach */ if (!ping_supported(family, icmph->type, icmph->code)) return; pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n", skb->protocol, type, code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); if (!sk) { pr_debug("no socket, dropping\n"); return; /* No socket for error */ } pr_debug("err on socket %p\n", sk); err = 0; harderr = 0; inet_sock = inet_sk(sk); if (skb->protocol == htons(ETH_P_IP)) { switch (type) { default: case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; case ICMP_SOURCE_QUENCH: /* This is not a real error but ping wants to see it. * Report it with some fake errno. */ err = EREMOTEIO; break; case ICMP_PARAMETERPROB: err = EPROTO; harderr = 1; break; case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ ipv4_sk_update_pmtu(skb, sk, info); if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; break; } goto out; } err = EHOSTUNREACH; if (code <= NR_ICMP_UNREACH) { harderr = icmp_err_convert[code].fatal; err = icmp_err_convert[code].errno; } break; case ICMP_REDIRECT: /* See ICMP_SOURCE_QUENCH */ ipv4_sk_redirect(skb, sk); err = EREMOTEIO; break; } #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { harderr = pingv6_ops.icmpv6_err_convert(type, code, &err); #endif } /* * RFC1122: OK. Passes ICMP errors back to application, as per * 4.1.3.3. */ if ((family == AF_INET && !inet_sock->recverr) || (family == AF_INET6 && !inet6_sk(sk)->recverr)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else { if (family == AF_INET) { ip_icmp_error(sk, skb, err, 0 /* no remote port */, info, (u8 *)icmph); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { pingv6_ops.ipv6_icmp_error(sk, skb, err, 0, info, (u8 *)icmph); #endif } } sk->sk_err = err; sk_error_report(sk); out: sock_put(sk); } EXPORT_SYMBOL_GPL(ping_err); /* * Copy and checksum an ICMP Echo packet from user space into a buffer * starting from the payload. */ int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *skb) { struct pingfakehdr *pfh = (struct pingfakehdr *)from; if (offset == 0) { fraglen -= sizeof(struct icmphdr); if (fraglen < 0) BUG(); if (!csum_and_copy_from_iter_full(to + sizeof(struct icmphdr), fraglen, &pfh->wcheck, &pfh->msg->msg_iter)) return -EFAULT; } else if (offset < sizeof(struct icmphdr)) { BUG(); } else { if (!csum_and_copy_from_iter_full(to, fraglen, &pfh->wcheck, &pfh->msg->msg_iter)) return -EFAULT; } #if IS_ENABLED(CONFIG_IPV6) /* For IPv6, checksum each skb as we go along, as expected by * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in * wcheck, it will be finalized in ping_v4_push_pending_frames. */ if (pfh->family == AF_INET6) { skb->csum = pfh->wcheck; skb->ip_summed = CHECKSUM_NONE; pfh->wcheck = 0; } #endif return 0; } EXPORT_SYMBOL_GPL(ping_getfrag); static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, struct flowi4 *fl4) { struct sk_buff *skb = skb_peek(&sk->sk_write_queue); if (!skb) return 0; pfh->wcheck = csum_partial((char *)&pfh->icmph, sizeof(struct icmphdr), pfh->wcheck); pfh->icmph.checksum = csum_fold(pfh->wcheck); memcpy(icmp_hdr(skb), &pfh->icmph, sizeof(struct icmphdr)); skb->ip_summed = CHECKSUM_NONE; return ip_push_pending_frames(sk, fl4); } int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len) { u8 type, code; if (len > 0xFFFF) return -EMSGSIZE; /* Must have at least a full ICMP header. */ if (len < icmph_len) return -EINVAL; /* * Check the flags. */ /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* * Fetch the ICMP header provided by the userland. * iovec is modified! The ICMP header is consumed. */ if (memcpy_from_msg(user_icmph, msg, icmph_len)) return -EFAULT; if (family == AF_INET) { type = ((struct icmphdr *) user_icmph)->type; code = ((struct icmphdr *) user_icmph)->code; #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { type = ((struct icmp6hdr *) user_icmph)->icmp6_type; code = ((struct icmp6hdr *) user_icmph)->icmp6_code; #endif } else { BUG(); } if (!ping_supported(family, type, code)) return -EINVAL; return 0; } EXPORT_SYMBOL_GPL(ping_common_sendmsg); static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct net *net = sock_net(sk); struct flowi4 fl4; struct inet_sock *inet = inet_sk(sk); struct ipcm_cookie ipc; struct icmphdr user_icmph; struct pingfakehdr pfh; struct rtable *rt = NULL; struct ip_options_data opt_copy; int free = 0; __be32 saddr, daddr, faddr; u8 tos; int err; pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph, sizeof(user_icmph)); if (err) return err; /* * Get and verify the address. */ if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) return -EAFNOSUPPORT; daddr = usin->sin_addr.s_addr; /* no remote port */ } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = inet->inet_daddr; /* no remote port */ } ipcm_init_sk(&ipc, inet); if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); if (unlikely(err)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { memcpy(&opt_copy, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen); ipc.opt = &opt_copy.opt; } rcu_read_unlock(); } saddr = ipc.addr; ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) { err = -EINVAL; goto out_free; } faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); if (sock_flag(sk, SOCK_LOCALROUTE) || (msg->msg_flags & MSG_DONTROUTE) || (ipc.opt && ipc.opt->opt.is_strictroute)) { tos |= RTO_ONLINK; } if (ipv4_is_multicast(daddr)) { if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) ipc.oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; } else if (!ipc.oif) ipc.oif = inet->uc_index; flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); fl4.fl4_icmp_type = user_icmph.type; fl4.fl4_icmp_code = user_icmph.code; security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; if (err == -ENETUNREACH) IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } err = -EACCES; if ((rt->rt_flags & RTCF_BROADCAST) && !sock_flag(sk, SOCK_BROADCAST)) goto out; if (msg->msg_flags & MSG_CONFIRM) goto do_confirm; back_from_confirm: if (!ipc.addr) ipc.addr = fl4.daddr; lock_sock(sk); pfh.icmph.type = user_icmph.type; /* already checked */ pfh.icmph.code = user_icmph.code; /* ditto */ pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence; pfh.msg = msg; pfh.wcheck = 0; pfh.family = AF_INET; err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len, 0, &ipc, &rt, msg->msg_flags); if (err) ip_flush_pending_frames(sk); else err = ping_v4_push_pending_frames(sk, &pfh, &fl4); release_sock(sk); out: ip_rt_put(rt); out_free: if (free) kfree(ipc.opt); if (!err) { icmp_out_count(sock_net(sk), user_icmph.type); return len; } return err; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(&rt->dst, &fl4.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto out; } int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *isk = inet_sk(sk); int family = sk->sk_family; struct sk_buff *skb; int copied, err; pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); err = -EOPNOTSUPP; if (flags & MSG_OOB) goto out; if (flags & MSG_ERRQUEUE) return inet_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } /* Don't bother checking the checksum */ err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto done; sock_recv_timestamp(msg, sk, skb); /* Copy the address and add cmsg data. */ if (family == AF_INET) { DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); if (sin) { sin->sin_family = AF_INET; sin->sin_port = 0 /* skb->h.uh->source */; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); } if (isk->cmsg_flags) ip_cmsg_recv(msg, skb); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *ip6 = ipv6_hdr(skb); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ip6->saddr; sin6->sin6_flowinfo = 0; if (np->sndflow) sin6->sin6_flowinfo = ip6_flowinfo(ip6); sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); *addr_len = sizeof(*sin6); } if (inet6_sk(sk)->rxopt.all) pingv6_ops.ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6) && inet6_sk(sk)->rxopt.all) pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb); else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags) ip_cmsg_recv(msg, skb); #endif } else { BUG(); } err = copied; done: skb_free_datagram(sk, skb); out: pr_debug("ping_recvmsg -> %d\n", err); return err; } EXPORT_SYMBOL_GPL(ping_recvmsg); int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); pr_debug("ping_queue_rcv_skb -> failed\n"); return -1; } return 0; } EXPORT_SYMBOL_GPL(ping_queue_rcv_skb); /* * All we need to do is get the socket. */ bool ping_rcv(struct sk_buff *skb) { struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); bool rc = false; /* We assume the packet has already been checked by icmp_rcv */ pr_debug("ping_rcv(skb=%p,id=%04x,seq=%04x)\n", skb, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); /* Push ICMP header back */ skb_push(skb, skb->data - (u8 *)icmph); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); if (sk) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); if (skb2 && !ping_queue_rcv_skb(sk, skb2)) rc = true; sock_put(sk); } if (!rc) pr_debug("no socket, dropping\n"); return rc; } EXPORT_SYMBOL_GPL(ping_rcv); struct proto ping_prot = { .name = "PING", .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, .connect = ip4_datagram_connect, .disconnect = __udp_disconnect, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .sendmsg = ping_v4_sendmsg, .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, .release_cb = ip4_datagram_release_cb, .hash = ping_hash, .unhash = ping_unhash, .get_port = ping_get_port, .obj_size = sizeof(struct inet_sock), }; EXPORT_SYMBOL(ping_prot); #ifdef CONFIG_PROC_FS static struct sock *ping_get_first(struct seq_file *seq, int start) { struct sock *sk; struct ping_iter_state *state = seq->private; struct net *net = seq_file_net(seq); for (state->bucket = start; state->bucket < PING_HTABLE_SIZE; ++state->bucket) { struct hlist_nulls_node *node; struct hlist_nulls_head *hslot; hslot = &ping_table.hash[state->bucket]; if (hlist_nulls_empty(hslot)) continue; sk_nulls_for_each(sk, node, hslot) { if (net_eq(sock_net(sk), net) && sk->sk_family == state->family) goto found; } } sk = NULL; found: return sk; } static struct sock *ping_get_next(struct seq_file *seq, struct sock *sk) { struct ping_iter_state *state = seq->private; struct net *net = seq_file_net(seq); do { sk = sk_nulls_next(sk); } while (sk && (!net_eq(sock_net(sk), net))); if (!sk) return ping_get_first(seq, state->bucket + 1); return sk; } static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) { struct sock *sk = ping_get_first(seq, 0); if (sk) while (pos && (sk = ping_get_next(seq, sk)) != NULL) --pos; return pos ? NULL : sk; } void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) __acquires(ping_table.lock) { struct ping_iter_state *state = seq->private; state->bucket = 0; state->family = family; read_lock_bh(&ping_table.lock); return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } EXPORT_SYMBOL_GPL(ping_seq_start); static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos) { return ping_seq_start(seq, pos, AF_INET); } void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; if (v == SEQ_START_TOKEN) sk = ping_get_idx(seq, 0); else sk = ping_get_next(seq, v); ++*pos; return sk; } EXPORT_SYMBOL_GPL(ping_seq_next); void ping_seq_stop(struct seq_file *seq, void *v) __releases(ping_table.lock) { read_unlock_bh(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_seq_stop); static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, int bucket) { struct inet_sock *inet = inet_sk(sp); __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); seq_printf(f, "%5d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), sk_rmem_alloc_get(sp), 0, 0L, 0, from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } static int ping_v4_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 127); if (v == SEQ_START_TOKEN) seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode ref pointer drops"); else { struct ping_iter_state *state = seq->private; ping_v4_format_sock(v, seq, state->bucket); } seq_pad(seq, '\n'); return 0; } static const struct seq_operations ping_v4_seq_ops = { .start = ping_v4_seq_start, .show = ping_v4_seq_show, .next = ping_seq_next, .stop = ping_seq_stop, }; static int __net_init ping_v4_proc_init_net(struct net *net) { if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops, sizeof(struct ping_iter_state))) return -ENOMEM; return 0; } static void __net_exit ping_v4_proc_exit_net(struct net *net) { remove_proc_entry("icmp", net->proc_net); } static struct pernet_operations ping_v4_net_ops = { .init = ping_v4_proc_init_net, .exit = ping_v4_proc_exit_net, }; int __init ping_proc_init(void) { return register_pernet_subsys(&ping_v4_net_ops); } void ping_proc_exit(void) { unregister_pernet_subsys(&ping_v4_net_ops); } #endif void __init ping_init(void) { int i; for (i = 0; i < PING_HTABLE_SIZE; i++) INIT_HLIST_NULLS_HEAD(&ping_table.hash[i], i); rwlock_init(&ping_table.lock); } |
| 54 54 54 169 169 169 161 159 169 16 168 166 20 20 105 13 14 14 133 171 65 11 161 77 143 143 142 7 134 3 107 177 96 153 1 173 108 127 127 126 127 127 127 65 39 65 65 3 77 77 14 71 3 3 127 74 65 74 127 65 74 16 59 59 362 82 39 196 376 378 11 90 90 360 360 360 123 47 92 94 98 98 54 54 277 254 199 1 4 139 15 11 4 105 104 110 88 59 59 59 59 95 21 76 54 54 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001 Intel Corp. * Copyright (c) 2001 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * Initialization/cleanup for SCTP protocol support. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/init.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/seq_file.h> #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/swap.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/route.h> #include <net/sctp/sctp.h> #include <net/addrconf.h> #include <net/inet_common.h> #include <net/inet_ecn.h> #include <net/udp_tunnel.h> #define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; struct idr sctp_assocs_id; DEFINE_SPINLOCK(sctp_assocs_id_lock); static struct sctp_pf *sctp_pf_inet6_specific; static struct sctp_pf *sctp_pf_inet_specific; static struct sctp_af *sctp_af_v4_specific; static struct sctp_af *sctp_af_v6_specific; struct kmem_cache *sctp_chunk_cachep __read_mostly; struct kmem_cache *sctp_bucket_cachep __read_mostly; long sysctl_sctp_mem[3]; int sysctl_sctp_rmem[3]; int sysctl_sctp_wmem[3]; /* Private helper to extract ipv4 address and stash them in * the protocol structure. */ static void sctp_v4_copy_addrlist(struct list_head *addrlist, struct net_device *dev) { struct in_device *in_dev; struct in_ifaddr *ifa; struct sctp_sockaddr_entry *addr; rcu_read_lock(); if ((in_dev = __in_dev_get_rcu(dev)) == NULL) { rcu_read_unlock(); return; } in_dev_for_each_ifa_rcu(ifa, in_dev) { /* Add the address to the local list. */ addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; addr->valid = 1; INIT_LIST_HEAD(&addr->list); list_add_tail(&addr->list, addrlist); } } rcu_read_unlock(); } /* Extract our IP addresses from the system and stash them in the * protocol structure. */ static void sctp_get_local_addr_list(struct net *net) { struct net_device *dev; struct list_head *pos; struct sctp_af *af; rcu_read_lock(); for_each_netdev_rcu(net, dev) { list_for_each(pos, &sctp_address_families) { af = list_entry(pos, struct sctp_af, list); af->copy_addrlist(&net->sctp.local_addr_list, dev); } } rcu_read_unlock(); } /* Free the existing local addresses. */ static void sctp_free_local_addr_list(struct net *net) { struct sctp_sockaddr_entry *addr; struct list_head *pos, *temp; list_for_each_safe(pos, temp, &net->sctp.local_addr_list) { addr = list_entry(pos, struct sctp_sockaddr_entry, list); list_del(pos); kfree(addr); } } /* Copy the local addresses which are valid for 'scope' into 'bp'. */ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, enum sctp_scope scope, gfp_t gfp, int copy_flags) { struct sctp_sockaddr_entry *addr; union sctp_addr laddr; int error = 0; rcu_read_lock(); list_for_each_entry_rcu(addr, &net->sctp.local_addr_list, list) { if (!addr->valid) continue; if (!sctp_in_scope(net, &addr->a, scope)) continue; /* Now that the address is in scope, check to see if * the address type is really supported by the local * sock as well as the remote peer. */ if (addr->a.sa.sa_family == AF_INET && (!(copy_flags & SCTP_ADDR4_ALLOWED) || !(copy_flags & SCTP_ADDR4_PEERSUPP))) continue; if (addr->a.sa.sa_family == AF_INET6 && (!(copy_flags & SCTP_ADDR6_ALLOWED) || !(copy_flags & SCTP_ADDR6_PEERSUPP))) continue; laddr = addr->a; /* also works for setting ipv6 address port */ laddr.v4.sin_port = htons(bp->port); if (sctp_bind_addr_state(bp, &laddr) != -1) continue; error = sctp_add_bind_addr(bp, &addr->a, sizeof(addr->a), SCTP_ADDR_SRC, GFP_ATOMIC); if (error) break; } rcu_read_unlock(); return error; } /* Copy over any ip options */ static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk) { struct inet_sock *newinet, *inet = inet_sk(sk); struct ip_options_rcu *inet_opt, *newopt = NULL; newinet = inet_sk(newsk); rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + inet_opt->opt.optlen, GFP_ATOMIC); if (newopt) memcpy(newopt, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen); else pr_err("%s: Failed to copy ip options\n", __func__); } RCU_INIT_POINTER(newinet->inet_opt, newopt); rcu_read_unlock(); } /* Account for the IP options */ static int sctp_v4_ip_options_len(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_options_rcu *inet_opt; int len = 0; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) len = inet_opt->opt.optlen; rcu_read_unlock(); return len; } /* Initialize a sctp_addr from in incoming skb. */ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, int is_saddr) { /* Always called on head skb, so this is safe */ struct sctphdr *sh = sctp_hdr(skb); struct sockaddr_in *sa = &addr->v4; addr->v4.sin_family = AF_INET; if (is_saddr) { sa->sin_port = sh->source; sa->sin_addr.s_addr = ip_hdr(skb)->saddr; } else { sa->sin_port = sh->dest; sa->sin_addr.s_addr = ip_hdr(skb)->daddr; } memset(sa->sin_zero, 0, sizeof(sa->sin_zero)); } /* Initialize an sctp_addr from a socket. */ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) { addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ static void sctp_v4_to_sk_saddr(union sctp_addr *addr, struct sock *sk) { inet_sk(sk)->inet_rcv_saddr = addr->v4.sin_addr.s_addr; } /* Initialize sk->sk_daddr from sctp_addr. */ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk) { inet_sk(sk)->inet_daddr = addr->v4.sin_addr.s_addr; } /* Initialize a sctp_addr from an address parameter. */ static bool sctp_v4_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param)) return false; addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); return true; } /* Initialize an address parameter from a sctp_addr and return the length * of the address parameter. */ static int sctp_v4_to_addr_param(const union sctp_addr *addr, union sctp_addr_param *param) { int length = sizeof(struct sctp_ipv4addr_param); param->v4.param_hdr.type = SCTP_PARAM_IPV4_ADDRESS; param->v4.param_hdr.length = htons(length); param->v4.addr.s_addr = addr->v4.sin_addr.s_addr; return length; } /* Initialize a sctp_addr from a dst_entry. */ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, __be16 port) { saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; saddr->v4.sin_addr.s_addr = fl4->saddr; memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero)); } /* Compare two addresses exactly. */ static int sctp_v4_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2) { if (addr1->sa.sa_family != addr2->sa.sa_family) return 0; if (addr1->v4.sin_port != addr2->v4.sin_port) return 0; if (addr1->v4.sin_addr.s_addr != addr2->v4.sin_addr.s_addr) return 0; return 1; } /* Initialize addr struct to INADDR_ANY. */ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) { addr->v4.sin_family = AF_INET; addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Is this a wildcard address? */ static int sctp_v4_is_any(const union sctp_addr *addr) { return htonl(INADDR_ANY) == addr->v4.sin_addr.s_addr; } /* This function checks if the address is a valid address to be used for * SCTP binding. * * Output: * Return 0 - If the address is a non-unicast or an illegal address. * Return 1 - If the address is a unicast. */ static int sctp_v4_addr_valid(union sctp_addr *addr, struct sctp_sock *sp, const struct sk_buff *skb) { /* IPv4 addresses not allowed */ if (sp && ipv6_only_sock(sctp_opt2sk(sp))) return 0; /* Is this a non-unicast address or a unusable SCTP address? */ if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) return 0; /* Is this a broadcast address? */ if (skb && skb_rtable(skb)->rt_flags & RTCF_BROADCAST) return 0; return 1; } /* Should this be available for binding? */ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) { struct net *net = sock_net(&sp->inet.sk); int ret = inet_addr_type(net, addr->v4.sin_addr.s_addr); if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind)) return 0; if (ipv6_only_sock(sctp_opt2sk(sp))) return 0; return 1; } /* Checking the loopback, private and other address scopes as defined in * RFC 1918. The IPv4 scoping is based on the draft for SCTP IPv4 * scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>. * * Level 0 - unusable SCTP addresses * Level 1 - loopback address * Level 2 - link-local addresses * Level 3 - private addresses. * Level 4 - global addresses * For INIT and INIT-ACK address list, let L be the level of * requested destination address, sender and receiver * SHOULD include all of its addresses with level greater * than or equal to L. * * IPv4 scoping can be controlled through sysctl option * net.sctp.addr_scope_policy */ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr) { enum sctp_scope retval; /* Check for unusable SCTP addresses. */ if (IS_IPV4_UNUSABLE_ADDRESS(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_UNUSABLE; } else if (ipv4_is_loopback(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_LOOPBACK; } else if (ipv4_is_linklocal_169(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_LINK; } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) || ipv4_is_private_172(addr->v4.sin_addr.s_addr) || ipv4_is_private_192(addr->v4.sin_addr.s_addr) || ipv4_is_test_198(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_PRIVATE; } else { retval = SCTP_SCOPE_GLOBAL; } return retval; } /* Returns a valid dst cache entry for the given source and destination ip * addresses. If an association is passed, trys to get a dst entry with a * source address that matches an address in the bind address list. */ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, struct flowi *fl, struct sock *sk) { struct sctp_association *asoc = t->asoc; struct rtable *rt; struct flowi _fl; struct flowi4 *fl4 = &_fl.u.ip4; struct sctp_bind_addr *bp; struct sctp_sockaddr_entry *laddr; struct dst_entry *dst = NULL; union sctp_addr *daddr = &t->ipaddr; union sctp_addr dst_saddr; __u8 tos = inet_sk(sk)->tos; if (t->dscp & SCTP_DSCP_SET_MASK) tos = t->dscp & SCTP_DSCP_VAL_MASK; memset(&_fl, 0x0, sizeof(_fl)); fl4->daddr = daddr->v4.sin_addr.s_addr; fl4->fl4_dport = daddr->v4.sin_port; fl4->flowi4_proto = IPPROTO_SCTP; if (asoc) { fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos); fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if; fl4->fl4_sport = htons(asoc->base.bind_addr.port); } if (saddr) { fl4->saddr = saddr->v4.sin_addr.s_addr; if (!fl4->fl4_sport) fl4->fl4_sport = saddr->v4.sin_port; } pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr, &fl4->saddr); rt = ip_route_output_key(sock_net(sk), fl4); if (!IS_ERR(rt)) { dst = &rt->dst; t->dst = dst; memcpy(fl, &_fl, sizeof(_fl)); } /* If there is no association or if a source address is passed, no * more validation is required. */ if (!asoc || saddr) goto out; bp = &asoc->base.bind_addr; if (dst) { /* Walk through the bind address list and look for a bind * address that matches the source address of the returned dst. */ sctp_v4_dst_saddr(&dst_saddr, fl4, htons(bp->port)); rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { if (!laddr->valid || (laddr->state == SCTP_ADDR_DEL) || (laddr->state != SCTP_ADDR_SRC && !asoc->src_out_of_asoc_ok)) continue; if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a)) goto out_unlock; } rcu_read_unlock(); /* None of the bound addresses match the source address of the * dst. So release it. */ dst_release(dst); dst = NULL; } /* Walk through the bind address list and try to get a dst that * matches a bind address as the source address. */ rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { struct net_device *odev; if (!laddr->valid) continue; if (laddr->state != SCTP_ADDR_SRC || AF_INET != laddr->a.sa.sa_family) continue; fl4->fl4_sport = laddr->a.v4.sin_port; flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if, RT_CONN_FLAGS_TOS(asoc->base.sk, tos), daddr->v4.sin_addr.s_addr, laddr->a.v4.sin_addr.s_addr); rt = ip_route_output_key(sock_net(sk), fl4); if (IS_ERR(rt)) continue; /* Ensure the src address belongs to the output * interface. */ odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, false); if (!odev || odev->ifindex != fl4->flowi4_oif) { if (!dst) { dst = &rt->dst; t->dst = dst; memcpy(fl, &_fl, sizeof(_fl)); } else { dst_release(&rt->dst); } continue; } dst_release(dst); dst = &rt->dst; t->dst = dst; memcpy(fl, &_fl, sizeof(_fl)); break; } out_unlock: rcu_read_unlock(); out: if (dst) { pr_debug("rt_dst:%pI4, rt_src:%pI4\n", &fl->u.ip4.daddr, &fl->u.ip4.saddr); } else { t->dst = NULL; pr_debug("no route\n"); } } /* For v4, the source address is cached in the route entry(dst). So no need * to cache it separately and hence this is an empty routine. */ static void sctp_v4_get_saddr(struct sctp_sock *sk, struct sctp_transport *t, struct flowi *fl) { union sctp_addr *saddr = &t->saddr; struct rtable *rt = (struct rtable *)t->dst; if (rt) { saddr->v4.sin_family = AF_INET; saddr->v4.sin_addr.s_addr = fl->u.ip4.saddr; } } /* What interface did this skb arrive on? */ static int sctp_v4_skb_iif(const struct sk_buff *skb) { return inet_iif(skb); } /* Was this packet marked by Explicit Congestion Notification? */ static int sctp_v4_is_ce(const struct sk_buff *skb) { return INET_ECN_is_ce(ip_hdr(skb)->tos); } /* Create and initialize a new sk for the socket returned by accept(). */ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, struct sctp_association *asoc, bool kern) { struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, sk->sk_prot, kern); struct inet_sock *newinet; if (!newsk) goto out; sock_init_data(NULL, newsk); sctp_copy_sock(newsk, sk, asoc); sock_reset_flag(newsk, SOCK_ZAPPED); sctp_v4_copy_ip_options(sk, newsk); newinet = inet_sk(newsk); newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; sk_refcnt_debug_inc(newsk); if (newsk->sk_prot->init(newsk)) { sk_common_release(newsk); newsk = NULL; } out: return newsk; } static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { /* No address mapping for V4 sockets */ memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); return sizeof(struct sockaddr_in); } /* Dump the v4 addr to the seq file. */ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) { seq_printf(seq, "%pI4 ", &addr->v4.sin_addr); } static void sctp_v4_ecn_capable(struct sock *sk) { INET_ECN_xmit(sk); } static void sctp_addr_wq_timeout_handler(struct timer_list *t) { struct net *net = from_timer(net, t, sctp.addr_wq_timer); struct sctp_sockaddr_entry *addrw, *temp; struct sctp_sock *sp; spin_lock_bh(&net->sctp.addr_wq_lock); list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) { pr_debug("%s: the first ent in wq:%p is addr:%pISc for cmd:%d at " "entry:%p\n", __func__, &net->sctp.addr_waitq, &addrw->a.sa, addrw->state, addrw); #if IS_ENABLED(CONFIG_IPV6) /* Now we send an ASCONF for each association */ /* Note. we currently don't handle link local IPv6 addressees */ if (addrw->a.sa.sa_family == AF_INET6) { struct in6_addr *in6; if (ipv6_addr_type(&addrw->a.v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) goto free_next; in6 = (struct in6_addr *)&addrw->a.v6.sin6_addr; if (ipv6_chk_addr(net, in6, NULL, 0) == 0 && addrw->state == SCTP_ADDR_NEW) { unsigned long timeo_val; pr_debug("%s: this is on DAD, trying %d sec " "later\n", __func__, SCTP_ADDRESS_TICK_DELAY); timeo_val = jiffies; timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY); mod_timer(&net->sctp.addr_wq_timer, timeo_val); break; } } #endif list_for_each_entry(sp, &net->sctp.auto_asconf_splist, auto_asconf_list) { struct sock *sk; sk = sctp_opt2sk(sp); /* ignore bound-specific endpoints */ if (!sctp_is_ep_boundall(sk)) continue; bh_lock_sock(sk); if (sctp_asconf_mgmt(sp, addrw) < 0) pr_debug("%s: sctp_asconf_mgmt failed\n", __func__); bh_unlock_sock(sk); } #if IS_ENABLED(CONFIG_IPV6) free_next: #endif list_del(&addrw->list); kfree(addrw); } spin_unlock_bh(&net->sctp.addr_wq_lock); } static void sctp_free_addr_wq(struct net *net) { struct sctp_sockaddr_entry *addrw; struct sctp_sockaddr_entry *temp; spin_lock_bh(&net->sctp.addr_wq_lock); del_timer(&net->sctp.addr_wq_timer); list_for_each_entry_safe(addrw, temp, &net->sctp.addr_waitq, list) { list_del(&addrw->list); kfree(addrw); } spin_unlock_bh(&net->sctp.addr_wq_lock); } /* lookup the entry for the same address in the addr_waitq * sctp_addr_wq MUST be locked */ static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct net *net, struct sctp_sockaddr_entry *addr) { struct sctp_sockaddr_entry *addrw; list_for_each_entry(addrw, &net->sctp.addr_waitq, list) { if (addrw->a.sa.sa_family != addr->a.sa.sa_family) continue; if (addrw->a.sa.sa_family == AF_INET) { if (addrw->a.v4.sin_addr.s_addr == addr->a.v4.sin_addr.s_addr) return addrw; } else if (addrw->a.sa.sa_family == AF_INET6) { if (ipv6_addr_equal(&addrw->a.v6.sin6_addr, &addr->a.v6.sin6_addr)) return addrw; } } return NULL; } void sctp_addr_wq_mgmt(struct net *net, struct sctp_sockaddr_entry *addr, int cmd) { struct sctp_sockaddr_entry *addrw; unsigned long timeo_val; /* first, we check if an opposite message already exist in the queue. * If we found such message, it is removed. * This operation is a bit stupid, but the DHCP client attaches the * new address after a couple of addition and deletion of that address */ spin_lock_bh(&net->sctp.addr_wq_lock); /* Offsets existing events in addr_wq */ addrw = sctp_addr_wq_lookup(net, addr); if (addrw) { if (addrw->state != cmd) { pr_debug("%s: offsets existing entry for %d, addr:%pISc " "in wq:%p\n", __func__, addrw->state, &addrw->a.sa, &net->sctp.addr_waitq); list_del(&addrw->list); kfree(addrw); } spin_unlock_bh(&net->sctp.addr_wq_lock); return; } /* OK, we have to add the new address to the wait queue */ addrw = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); if (addrw == NULL) { spin_unlock_bh(&net->sctp.addr_wq_lock); return; } addrw->state = cmd; list_add_tail(&addrw->list, &net->sctp.addr_waitq); pr_debug("%s: add new entry for cmd:%d, addr:%pISc in wq:%p\n", __func__, addrw->state, &addrw->a.sa, &net->sctp.addr_waitq); if (!timer_pending(&net->sctp.addr_wq_timer)) { timeo_val = jiffies; timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY); mod_timer(&net->sctp.addr_wq_timer, timeo_val); } spin_unlock_bh(&net->sctp.addr_wq_lock); } /* Event handler for inet address addition/deletion events. * The sctp_local_addr_list needs to be protocted by a spin lock since * multiple notifiers (say IPv4 and IPv6) may be running at the same * time and thus corrupt the list. * The reader side is protected with RCU. */ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, void *ptr) { struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct sctp_sockaddr_entry *addr = NULL; struct sctp_sockaddr_entry *temp; struct net *net = dev_net(ifa->ifa_dev->dev); int found = 0; switch (ev) { case NETDEV_UP: addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; addr->valid = 1; spin_lock_bh(&net->sctp.local_addr_lock); list_add_tail_rcu(&addr->list, &net->sctp.local_addr_list); sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_NEW); spin_unlock_bh(&net->sctp.local_addr_lock); } break; case NETDEV_DOWN: spin_lock_bh(&net->sctp.local_addr_lock); list_for_each_entry_safe(addr, temp, &net->sctp.local_addr_list, list) { if (addr->a.sa.sa_family == AF_INET && addr->a.v4.sin_addr.s_addr == ifa->ifa_local) { sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; list_del_rcu(&addr->list); break; } } spin_unlock_bh(&net->sctp.local_addr_lock); if (found) kfree_rcu(addr, rcu); break; } return NOTIFY_DONE; } /* * Initialize the control inode/socket with a control endpoint data * structure. This endpoint is reserved exclusively for the OOTB processing. */ static int sctp_ctl_sock_init(struct net *net) { int err; sa_family_t family = PF_INET; if (sctp_get_pf_specific(PF_INET6)) family = PF_INET6; err = inet_ctl_sock_create(&net->sctp.ctl_sock, family, SOCK_SEQPACKET, IPPROTO_SCTP, net); /* If IPv6 socket could not be created, try the IPv4 socket */ if (err < 0 && family == PF_INET6) err = inet_ctl_sock_create(&net->sctp.ctl_sock, AF_INET, SOCK_SEQPACKET, IPPROTO_SCTP, net); if (err < 0) { pr_err("Failed to create the SCTP control socket\n"); return err; } return 0; } static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb) { SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source; skb_set_transport_header(skb, sizeof(struct udphdr)); sctp_rcv(skb); return 0; } int sctp_udp_sock_start(struct net *net) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; struct udp_port_cfg udp_conf = {0}; struct socket *sock; int err; udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = htonl(INADDR_ANY); udp_conf.local_udp_port = htons(net->sctp.udp_port); err = udp_sock_create(net, &udp_conf, &sock); if (err) { pr_err("Failed to create the SCTP UDP tunneling v4 sock\n"); return err; } tuncfg.encap_type = 1; tuncfg.encap_rcv = sctp_udp_rcv; tuncfg.encap_err_lookup = sctp_udp_v4_err; setup_udp_tunnel_sock(net, sock, &tuncfg); net->sctp.udp4_sock = sock->sk; #if IS_ENABLED(CONFIG_IPV6) memset(&udp_conf, 0, sizeof(udp_conf)); udp_conf.family = AF_INET6; udp_conf.local_ip6 = in6addr_any; udp_conf.local_udp_port = htons(net->sctp.udp_port); udp_conf.use_udp6_rx_checksums = true; udp_conf.ipv6_v6only = true; err = udp_sock_create(net, &udp_conf, &sock); if (err) { pr_err("Failed to create the SCTP UDP tunneling v6 sock\n"); udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket); net->sctp.udp4_sock = NULL; return err; } tuncfg.encap_type = 1; tuncfg.encap_rcv = sctp_udp_rcv; tuncfg.encap_err_lookup = sctp_udp_v6_err; setup_udp_tunnel_sock(net, sock, &tuncfg); net->sctp.udp6_sock = sock->sk; #endif return 0; } void sctp_udp_sock_stop(struct net *net) { if (net->sctp.udp4_sock) { udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket); net->sctp.udp4_sock = NULL; } if (net->sctp.udp6_sock) { udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket); net->sctp.udp6_sock = NULL; } } /* Register address family specific functions. */ int sctp_register_af(struct sctp_af *af) { switch (af->sa_family) { case AF_INET: if (sctp_af_v4_specific) return 0; sctp_af_v4_specific = af; break; case AF_INET6: if (sctp_af_v6_specific) return 0; sctp_af_v6_specific = af; break; default: return 0; } INIT_LIST_HEAD(&af->list); list_add_tail(&af->list, &sctp_address_families); return 1; } /* Get the table of functions for manipulating a particular address * family. */ struct sctp_af *sctp_get_af_specific(sa_family_t family) { switch (family) { case AF_INET: return sctp_af_v4_specific; case AF_INET6: return sctp_af_v6_specific; default: return NULL; } } /* Common code to initialize a AF_INET msg_name. */ static void sctp_inet_msgname(char *msgname, int *addr_len) { struct sockaddr_in *sin; sin = (struct sockaddr_in *)msgname; *addr_len = sizeof(struct sockaddr_in); sin->sin_family = AF_INET; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); } /* Copy the primary address of the peer primary address as the msg_name. */ static void sctp_inet_event_msgname(struct sctp_ulpevent *event, char *msgname, int *addr_len) { struct sockaddr_in *sin, *sinfrom; if (msgname) { struct sctp_association *asoc; asoc = event->asoc; sctp_inet_msgname(msgname, addr_len); sin = (struct sockaddr_in *)msgname; sinfrom = &asoc->peer.primary_addr.v4; sin->sin_port = htons(asoc->peer.port); sin->sin_addr.s_addr = sinfrom->sin_addr.s_addr; } } /* Initialize and copy out a msgname from an inbound skb. */ static void sctp_inet_skb_msgname(struct sk_buff *skb, char *msgname, int *len) { if (msgname) { struct sctphdr *sh = sctp_hdr(skb); struct sockaddr_in *sin = (struct sockaddr_in *)msgname; sctp_inet_msgname(msgname, len); sin->sin_port = sh->source; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; } } /* Do we support this AF? */ static int sctp_inet_af_supported(sa_family_t family, struct sctp_sock *sp) { /* PF_INET only supports AF_INET addresses. */ return AF_INET == family; } /* Address matching with wildcards allowed. */ static int sctp_inet_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2, struct sctp_sock *opt) { /* PF_INET only supports AF_INET addresses. */ if (addr1->sa.sa_family != addr2->sa.sa_family) return 0; if (htonl(INADDR_ANY) == addr1->v4.sin_addr.s_addr || htonl(INADDR_ANY) == addr2->v4.sin_addr.s_addr) return 1; if (addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr) return 1; return 0; } /* Verify that provided sockaddr looks bindable. Common verification has * already been taken care of. */ static int sctp_inet_bind_verify(struct sctp_sock *opt, union sctp_addr *addr) { return sctp_v4_available(addr, opt); } /* Verify that sockaddr looks sendable. Common verification has already * been taken care of. */ static int sctp_inet_send_verify(struct sctp_sock *opt, union sctp_addr *addr) { return 1; } /* Fill in Supported Address Type information for INIT and INIT-ACK * chunks. Returns number of addresses supported. */ static int sctp_inet_supported_addrs(const struct sctp_sock *opt, __be16 *types) { types[0] = SCTP_PARAM_IPV4_ADDRESS; return 1; } /* Wrapper routine that calls the ip transmit routine. */ static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t) { struct dst_entry *dst = dst_clone(t->dst); struct flowi4 *fl4 = &t->fl.u.ip4; struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); __u8 dscp = inet->tos; __be16 df = 0; pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, skb->len, &fl4->saddr, &fl4->daddr); if (t->dscp & SCTP_DSCP_SET_MASK) dscp = t->dscp & SCTP_DSCP_VAL_MASK; inet->pmtudisc = t->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO : IP_PMTUDISC_DONT; SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); if (!t->encap_port || !sctp_sk(sk)->udp_port) { skb_dst_set(skb, dst); return __ip_queue_xmit(sk, skb, &t->fl, dscp); } if (skb_is_gso(skb)) skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; if (ip_dont_fragment(sk, dst) && !skb->ignore_df) df = htons(IP_DF); skb->encapsulation = 1; skb_reset_inner_mac_header(skb); skb_reset_inner_transport_header(skb); skb_set_inner_ipproto(skb, IPPROTO_SCTP); udp_tunnel_xmit_skb((struct rtable *)dst, sk, skb, fl4->saddr, fl4->daddr, dscp, ip4_dst_hoplimit(dst), df, sctp_sk(sk)->udp_port, t->encap_port, false, false); return 0; } static struct sctp_af sctp_af_inet; static struct sctp_pf sctp_pf_inet = { .event_msgname = sctp_inet_event_msgname, .skb_msgname = sctp_inet_skb_msgname, .af_supported = sctp_inet_af_supported, .cmp_addr = sctp_inet_cmp_addr, .bind_verify = sctp_inet_bind_verify, .send_verify = sctp_inet_send_verify, .supported_addrs = sctp_inet_supported_addrs, .create_accept_sk = sctp_v4_create_accept_sk, .addr_to_user = sctp_v4_addr_to_user, .to_sk_saddr = sctp_v4_to_sk_saddr, .to_sk_daddr = sctp_v4_to_sk_daddr, .copy_ip_options = sctp_v4_copy_ip_options, .af = &sctp_af_inet }; /* Notifier for inetaddr addition/deletion events. */ static struct notifier_block sctp_inetaddr_notifier = { .notifier_call = sctp_inetaddr_event, }; /* Socket operations. */ static const struct proto_ops inet_seqpacket_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, /* Needs to be wrapped... */ .bind = inet_bind, .connect = sctp_inet_connect, .socketpair = sock_no_socketpair, .accept = inet_accept, .getname = inet_getname, /* Semantics are different. */ .poll = sctp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = sctp_inet_listen, .shutdown = inet_shutdown, /* Looks harmless. */ .setsockopt = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */ .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; /* Registration with AF_INET family. */ static struct inet_protosw sctp_seqpacket_protosw = { .type = SOCK_SEQPACKET, .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, .flags = SCTP_PROTOSW_FLAG }; static struct inet_protosw sctp_stream_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_SCTP, .prot = &sctp_prot, .ops = &inet_seqpacket_ops, .flags = SCTP_PROTOSW_FLAG }; static int sctp4_rcv(struct sk_buff *skb) { SCTP_INPUT_CB(skb)->encap_port = 0; return sctp_rcv(skb); } /* Register with IP layer. */ static const struct net_protocol sctp_protocol = { .handler = sctp4_rcv, .err_handler = sctp_v4_err, .no_policy = 1, .icmp_strict_tag_validation = 1, }; /* IPv4 address related functions. */ static struct sctp_af sctp_af_inet = { .sa_family = AF_INET, .sctp_xmit = sctp_v4_xmit, .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .get_dst = sctp_v4_get_dst, .get_saddr = sctp_v4_get_saddr, .copy_addrlist = sctp_v4_copy_addrlist, .from_skb = sctp_v4_from_skb, .from_sk = sctp_v4_from_sk, .from_addr_param = sctp_v4_from_addr_param, .to_addr_param = sctp_v4_to_addr_param, .cmp_addr = sctp_v4_cmp_addr, .addr_valid = sctp_v4_addr_valid, .inaddr_any = sctp_v4_inaddr_any, .is_any = sctp_v4_is_any, .available = sctp_v4_available, .scope = sctp_v4_scope, .skb_iif = sctp_v4_skb_iif, .is_ce = sctp_v4_is_ce, .seq_dump_addr = sctp_v4_seq_dump_addr, .ecn_capable = sctp_v4_ecn_capable, .net_header_len = sizeof(struct iphdr), .sockaddr_len = sizeof(struct sockaddr_in), .ip_options_len = sctp_v4_ip_options_len, }; struct sctp_pf *sctp_get_pf_specific(sa_family_t family) { switch (family) { case PF_INET: return sctp_pf_inet_specific; case PF_INET6: return sctp_pf_inet6_specific; default: return NULL; } } /* Register the PF specific function table. */ int sctp_register_pf(struct sctp_pf *pf, sa_family_t family) { switch (family) { case PF_INET: if (sctp_pf_inet_specific) return 0; sctp_pf_inet_specific = pf; break; case PF_INET6: if (sctp_pf_inet6_specific) return 0; sctp_pf_inet6_specific = pf; break; default: return 0; } return 1; } static inline int init_sctp_mibs(struct net *net) { net->sctp.sctp_statistics = alloc_percpu(struct sctp_mib); if (!net->sctp.sctp_statistics) return -ENOMEM; return 0; } static inline void cleanup_sctp_mibs(struct net *net) { free_percpu(net->sctp.sctp_statistics); } static void sctp_v4_pf_init(void) { /* Initialize the SCTP specific PF functions. */ sctp_register_pf(&sctp_pf_inet, PF_INET); sctp_register_af(&sctp_af_inet); } static void sctp_v4_pf_exit(void) { list_del(&sctp_af_inet.list); } static int sctp_v4_protosw_init(void) { int rc; rc = proto_register(&sctp_prot, 1); if (rc) return rc; /* Register SCTP(UDP and TCP style) with socket layer. */ inet_register_protosw(&sctp_seqpacket_protosw); inet_register_protosw(&sctp_stream_protosw); return 0; } static void sctp_v4_protosw_exit(void) { inet_unregister_protosw(&sctp_stream_protosw); inet_unregister_protosw(&sctp_seqpacket_protosw); proto_unregister(&sctp_prot); } static int sctp_v4_add_protocol(void) { /* Register notifier for inet address additions/deletions. */ register_inetaddr_notifier(&sctp_inetaddr_notifier); /* Register SCTP with inet layer. */ if (inet_add_protocol(&sctp_protocol, IPPROTO_SCTP) < 0) return -EAGAIN; return 0; } static void sctp_v4_del_protocol(void) { inet_del_protocol(&sctp_protocol, IPPROTO_SCTP); unregister_inetaddr_notifier(&sctp_inetaddr_notifier); } static int __net_init sctp_defaults_init(struct net *net) { int status; /* * 14. Suggested SCTP Protocol Parameter Values */ /* The following protocol parameters are RECOMMENDED: */ /* RTO.Initial - 3 seconds */ net->sctp.rto_initial = SCTP_RTO_INITIAL; /* RTO.Min - 1 second */ net->sctp.rto_min = SCTP_RTO_MIN; /* RTO.Max - 60 seconds */ net->sctp.rto_max = SCTP_RTO_MAX; /* RTO.Alpha - 1/8 */ net->sctp.rto_alpha = SCTP_RTO_ALPHA; /* RTO.Beta - 1/4 */ net->sctp.rto_beta = SCTP_RTO_BETA; /* Valid.Cookie.Life - 60 seconds */ net->sctp.valid_cookie_life = SCTP_DEFAULT_COOKIE_LIFE; /* Whether Cookie Preservative is enabled(1) or not(0) */ net->sctp.cookie_preserve_enable = 1; /* Default sctp sockets to use md5 as their hmac alg */ #if defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_MD5) net->sctp.sctp_hmac_alg = "md5"; #elif defined (CONFIG_SCTP_DEFAULT_COOKIE_HMAC_SHA1) net->sctp.sctp_hmac_alg = "sha1"; #else net->sctp.sctp_hmac_alg = NULL; #endif /* Max.Burst - 4 */ net->sctp.max_burst = SCTP_DEFAULT_MAX_BURST; /* Disable of Primary Path Switchover by default */ net->sctp.ps_retrans = SCTP_PS_RETRANS_MAX; /* Enable pf state by default */ net->sctp.pf_enable = 1; /* Ignore pf exposure feature by default */ net->sctp.pf_expose = SCTP_PF_EXPOSE_UNSET; /* Association.Max.Retrans - 10 attempts * Path.Max.Retrans - 5 attempts (per destination address) * Max.Init.Retransmits - 8 attempts */ net->sctp.max_retrans_association = 10; net->sctp.max_retrans_path = 5; net->sctp.max_retrans_init = 8; /* Sendbuffer growth - do per-socket accounting */ net->sctp.sndbuf_policy = 0; /* Rcvbuffer growth - do per-socket accounting */ net->sctp.rcvbuf_policy = 0; /* HB.interval - 30 seconds */ net->sctp.hb_interval = SCTP_DEFAULT_TIMEOUT_HEARTBEAT; /* delayed SACK timeout */ net->sctp.sack_timeout = SCTP_DEFAULT_TIMEOUT_SACK; /* Disable ADDIP by default. */ net->sctp.addip_enable = 0; net->sctp.addip_noauth = 0; net->sctp.default_auto_asconf = 0; /* Enable PR-SCTP by default. */ net->sctp.prsctp_enable = 1; /* Disable RECONF by default. */ net->sctp.reconf_enable = 0; /* Disable AUTH by default. */ net->sctp.auth_enable = 0; /* Enable ECN by default. */ net->sctp.ecn_enable = 1; /* Set UDP tunneling listening port to 0 by default */ net->sctp.udp_port = 0; /* Set remote encap port to 0 by default */ net->sctp.encap_port = 0; /* Set SCOPE policy to enabled */ net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE; /* Set the default rwnd update threshold */ net->sctp.rwnd_upd_shift = SCTP_DEFAULT_RWND_SHIFT; /* Initialize maximum autoclose timeout. */ net->sctp.max_autoclose = INT_MAX / HZ; status = sctp_sysctl_net_register(net); if (status) goto err_sysctl_register; /* Allocate and initialise sctp mibs. */ status = init_sctp_mibs(net); if (status) goto err_init_mibs; #ifdef CONFIG_PROC_FS /* Initialize proc fs directory. */ status = sctp_proc_init(net); if (status) goto err_init_proc; #endif sctp_dbg_objcnt_init(net); /* Initialize the local address list. */ INIT_LIST_HEAD(&net->sctp.local_addr_list); spin_lock_init(&net->sctp.local_addr_lock); sctp_get_local_addr_list(net); /* Initialize the address event list */ INIT_LIST_HEAD(&net->sctp.addr_waitq); INIT_LIST_HEAD(&net->sctp.auto_asconf_splist); spin_lock_init(&net->sctp.addr_wq_lock); net->sctp.addr_wq_timer.expires = 0; timer_setup(&net->sctp.addr_wq_timer, sctp_addr_wq_timeout_handler, 0); return 0; #ifdef CONFIG_PROC_FS err_init_proc: cleanup_sctp_mibs(net); #endif err_init_mibs: sctp_sysctl_net_unregister(net); err_sysctl_register: return status; } static void __net_exit sctp_defaults_exit(struct net *net) { /* Free the local address list */ sctp_free_addr_wq(net); sctp_free_local_addr_list(net); #ifdef CONFIG_PROC_FS remove_proc_subtree("sctp", net->proc_net); net->sctp.proc_net_sctp = NULL; #endif cleanup_sctp_mibs(net); sctp_sysctl_net_unregister(net); } static struct pernet_operations sctp_defaults_ops = { .init = sctp_defaults_init, .exit = sctp_defaults_exit, }; static int __net_init sctp_ctrlsock_init(struct net *net) { int status; /* Initialize the control inode/socket for handling OOTB packets. */ status = sctp_ctl_sock_init(net); if (status) pr_err("Failed to initialize the SCTP control sock\n"); return status; } static void __net_exit sctp_ctrlsock_exit(struct net *net) { /* Free the control endpoint. */ inet_ctl_sock_destroy(net->sctp.ctl_sock); } static struct pernet_operations sctp_ctrlsock_ops = { .init = sctp_ctrlsock_init, .exit = sctp_ctrlsock_exit, }; /* Initialize the universe into something sensible. */ static __init int sctp_init(void) { unsigned long nr_pages = totalram_pages(); unsigned long limit; unsigned long goal; int max_entry_order; int num_entries; int max_share; int status; int order; int i; sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); /* Allocate bind_bucket and chunk caches. */ status = -ENOBUFS; sctp_bucket_cachep = kmem_cache_create("sctp_bind_bucket", sizeof(struct sctp_bind_bucket), 0, SLAB_HWCACHE_ALIGN, NULL); if (!sctp_bucket_cachep) goto out; sctp_chunk_cachep = kmem_cache_create("sctp_chunk", sizeof(struct sctp_chunk), 0, SLAB_HWCACHE_ALIGN, NULL); if (!sctp_chunk_cachep) goto err_chunk_cachep; status = percpu_counter_init(&sctp_sockets_allocated, 0, GFP_KERNEL); if (status) goto err_percpu_counter_init; /* Implementation specific variables. */ /* Initialize default stream count setup information. */ sctp_max_instreams = SCTP_DEFAULT_INSTREAMS; sctp_max_outstreams = SCTP_DEFAULT_OUTSTREAMS; /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_sctp_mem[0] = limit / 4 * 3; sysctl_sctp_mem[1] = limit; sysctl_sctp_mem[2] = sysctl_sctp_mem[0] * 2; /* Set per-socket limits to no more than 1/128 the pressure threshold*/ limit = (sysctl_sctp_mem[1]) << (PAGE_SHIFT - 7); max_share = min(4UL*1024*1024, limit); sysctl_sctp_rmem[0] = SK_MEM_QUANTUM; /* give each asoc 1 page min */ sysctl_sctp_rmem[1] = 1500 * SKB_TRUESIZE(1); sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share); sysctl_sctp_wmem[0] = SK_MEM_QUANTUM; sysctl_sctp_wmem[1] = 16*1024; sysctl_sctp_wmem[2] = max(64*1024, max_share); /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. * Though not identical. Start by getting a goal size */ if (nr_pages >= (128 * 1024)) goal = nr_pages >> (22 - PAGE_SHIFT); else goal = nr_pages >> (24 - PAGE_SHIFT); /* Then compute the page order for said goal */ order = get_order(goal); /* Now compute the required page order for the maximum sized table we * want to create */ max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES * sizeof(struct sctp_bind_hashbucket)); /* Limit the page order by that maximum hash table size */ order = min(order, max_entry_order); /* Allocate and initialize the endpoint hash table. */ sctp_ep_hashsize = 64; sctp_ep_hashtable = kmalloc_array(64, sizeof(struct sctp_hashbucket), GFP_KERNEL); if (!sctp_ep_hashtable) { pr_err("Failed endpoint_hash alloc\n"); status = -ENOMEM; goto err_ehash_alloc; } for (i = 0; i < sctp_ep_hashsize; i++) { rwlock_init(&sctp_ep_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } /* Allocate and initialize the SCTP port hash table. * Note that order is initalized to start at the max sized * table we want to support. If we can't get that many pages * reduce the order and try again */ do { sctp_port_hashtable = (struct sctp_bind_hashbucket *) __get_free_pages(GFP_KERNEL | __GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); status = -ENOMEM; goto err_bhash_alloc; } /* Now compute the number of entries that will fit in the * port hash space we allocated */ num_entries = (1UL << order) * PAGE_SIZE / sizeof(struct sctp_bind_hashbucket); /* And finish by rounding it down to the nearest power of two. * This wastes some memory of course, but it's needed because * the hash function operates based on the assumption that * the number of entries is a power of two. */ sctp_port_hashsize = rounddown_pow_of_two(num_entries); for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } status = sctp_transport_hashtable_init(); if (status) goto err_thash_alloc; pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize, num_entries); sctp_sysctl_register(); INIT_LIST_HEAD(&sctp_address_families); sctp_v4_pf_init(); sctp_v6_pf_init(); sctp_sched_ops_init(); status = register_pernet_subsys(&sctp_defaults_ops); if (status) goto err_register_defaults; status = sctp_v4_protosw_init(); if (status) goto err_protosw_init; status = sctp_v6_protosw_init(); if (status) goto err_v6_protosw_init; status = register_pernet_subsys(&sctp_ctrlsock_ops); if (status) goto err_register_ctrlsock; status = sctp_v4_add_protocol(); if (status) goto err_add_protocol; /* Register SCTP with inet6 layer. */ status = sctp_v6_add_protocol(); if (status) goto err_v6_add_protocol; if (sctp_offload_init() < 0) pr_crit("%s: Cannot add SCTP protocol offload\n", __func__); out: return status; err_v6_add_protocol: sctp_v4_del_protocol(); err_add_protocol: unregister_pernet_subsys(&sctp_ctrlsock_ops); err_register_ctrlsock: sctp_v6_protosw_exit(); err_v6_protosw_init: sctp_v4_protosw_exit(); err_protosw_init: unregister_pernet_subsys(&sctp_defaults_ops); err_register_defaults: sctp_v4_pf_exit(); sctp_v6_pf_exit(); sctp_sysctl_unregister(); free_pages((unsigned long)sctp_port_hashtable, get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); err_bhash_alloc: sctp_transport_hashtable_destroy(); err_thash_alloc: kfree(sctp_ep_hashtable); err_ehash_alloc: percpu_counter_destroy(&sctp_sockets_allocated); err_percpu_counter_init: kmem_cache_destroy(sctp_chunk_cachep); err_chunk_cachep: kmem_cache_destroy(sctp_bucket_cachep); goto out; } /* Exit handler for the SCTP protocol. */ static __exit void sctp_exit(void) { /* BUG. This should probably do something useful like clean * up all the remaining associations and all that memory. */ /* Unregister with inet6/inet layers. */ sctp_v6_del_protocol(); sctp_v4_del_protocol(); unregister_pernet_subsys(&sctp_ctrlsock_ops); /* Free protosw registrations */ sctp_v6_protosw_exit(); sctp_v4_protosw_exit(); unregister_pernet_subsys(&sctp_defaults_ops); /* Unregister with socket layer. */ sctp_v6_pf_exit(); sctp_v4_pf_exit(); sctp_sysctl_unregister(); free_pages((unsigned long)sctp_port_hashtable, get_order(sctp_port_hashsize * sizeof(struct sctp_bind_hashbucket))); kfree(sctp_ep_hashtable); sctp_transport_hashtable_destroy(); percpu_counter_destroy(&sctp_sockets_allocated); rcu_barrier(); /* Wait for completion of call_rcu()'s */ kmem_cache_destroy(sctp_chunk_cachep); kmem_cache_destroy(sctp_bucket_cachep); } module_init(sctp_init); module_exit(sctp_exit); /* * __stringify doesn't likes enums, so use IPPROTO_SCTP value (132) directly. */ MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-132"); MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132"); MODULE_AUTHOR("Linux Kernel SCTP developers <linux-sctp@vger.kernel.org>"); MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)"); module_param_named(no_checksums, sctp_checksum_disable, bool, 0644); MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification"); MODULE_LICENSE("GPL"); |
| 202 3 236 243 1551 1558 1316 65 1648 1651 1653 259 1554 1553 1554 3 3 3 1 2 252 253 253 252 254 252 254 252 252 252 252 253 254 250 252 253 254 251 253 217 215 215 217 216 217 217 217 70 70 70 3 3 3 3 3 3 3 3 3 257 258 259 234 259 258 78 253 254 253 253 78 78 78 67 67 67 67 106 29 78 67 254 254 253 253 253 18 18 5 5 25 25 25 254 250 251 254 253 13 239 252 51 202 246 245 254 254 66 67 252 253 179 177 179 40 178 178 262 1 1 1 256 257 260 1 258 258 258 259 259 257 7 254 252 252 9 16 230 169 2 61 179 181 181 2 18 160 178 178 178 153 25 178 178 178 168 10 2 54 70 78 67 66 66 66 67 74 263 263 23 40 203 78 178 153 26 154 26 179 153 25 25 264 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/random.h> #include <linux/tty.h> #include <linux/blkdev.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/stackleak.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> #include <linux/tick.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } #endif #ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) #ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_stack = cached_vm_stacks[i]; if (!vm_stack) continue; vfree(vm_stack->addr); cached_vm_stacks[i] = NULL; } return 0; } #endif static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { #ifdef CONFIG_VMAP_STACK void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *s; s = this_cpu_xchg(cached_stacks[i], NULL); if (!s) continue; /* Mark stack accessible for KASAN. */ kasan_unpoison_range(s->addr, THREAD_SIZE); /* Clear stale pointers from reused stack. */ memset(s->addr, 0, THREAD_SIZE); tsk->stack_vm_area = s; tsk->stack = s->addr; return s->addr; } /* * Allocated stacks are cached and later reused by new threads, * so memcg accounting is performed manually on assigning/releasing * stacks to tasks. Drop __GFP_ACCOUNT. */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ if (stack) { tsk->stack_vm_area = find_vm_area(stack); tsk->stack = stack; } return stack; #else struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return tsk->stack; } return NULL; #endif } static inline void free_thread_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK struct vm_struct *vm = task_stack_vm_area(tsk); if (vm) { int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm->pages[i], 0); for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, tsk->stack_vm_area) != NULL) continue; return; } vfree_atomic(tsk->stack); return; } #endif __free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_stack_cache; static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack; } static void free_thread_stack(struct task_struct *tsk) { kmem_cache_free(thread_stack_cache, tsk->stack); } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } # endif #endif /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma; vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (vma) vma_init(vma, mm); return vma; } struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) { struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (new) { ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); /* * orig->shared.rb may be modified concurrently, but the clone * will be reinitialized. */ *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; } return new; } void vm_area_free(struct vm_area_struct *vma) { kmem_cache_free(vm_area_cachep, vma); } static void account_kernel_stack(struct task_struct *tsk, int account) { void *stack = task_stack_page(tsk); struct vm_struct *vm = task_stack_vm_area(tsk); if (vm) { int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } static int memcg_charge_kernel_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK struct vm_struct *vm = task_stack_vm_area(tsk); int ret; BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0); if (vm) { int i; BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { /* * If memcg_kmem_charge_page() fails, page's * memory cgroup pointer is NULL, and * memcg_kmem_uncharge_page() in free_thread_stack() * will ignore this page. */ ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); if (ret) return ret; } } #endif return 0; } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ account_kernel_stack(tsk, -1); free_thread_stack(tsk); tsk->stack = NULL; #ifdef CONFIG_VMAP_STACK tsk->stack_vm_area = NULL; #endif } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && deny_write_access(exe_file)) pr_warn_once("deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { struct vm_area_struct *mpnt, *tmp, *prev, **pprev; struct rb_node **rb_link, *rb_parent; int retval; unsigned long charge; LIST_HEAD(uf); uprobe_start_dup_mmap(); if (mmap_write_lock_killable(oldmm)) { retval = -EINTR; goto fail_uprobe_end; } flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ mmap_write_lock_nested(mm, SINGLE_DEPTH_NESTING); /* No ordering required: file already has been exposed. */ dup_mm_exe_file(mm, oldmm); mm->total_vm = oldmm->total_vm; mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; rb_link = &mm->mm_rb.rb_node; rb_parent = NULL; pprev = &mm->mmap; retval = ksm_fork(mm, oldmm); if (retval) goto out; retval = khugepaged_fork(mm, oldmm); if (retval) goto out; prev = NULL; for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; /* * Don't duplicate many vmas if we've been oom-killed (for * example) */ if (fatal_signal_pending(current)) { retval = -EINTR; goto out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); if (security_vm_enough_memory_mm(oldmm, len)) /* sic */ goto fail_nomem; charge = len; } tmp = vm_area_dup(mpnt); if (!tmp) goto fail_nomem; retval = vma_dup_policy(mpnt, tmp); if (retval) goto fail_nomem_policy; tmp->vm_mm = mm; retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; if (tmp->vm_flags & VM_WIPEONFORK) { /* * VM_WIPEONFORK gets a clean slate in the child. * Don't prepare anon_vma until fault since we don't * copy page for current vma. */ tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; get_file(file); i_mmap_lock_write(mapping); if (tmp->vm_flags & VM_SHARED) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ vma_interval_tree_insert_after(tmp, mpnt, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); i_mmap_unlock_write(mapping); } /* * Clear hugetlb-related page reserves for children. This only * affects MAP_PRIVATE mappings. Faults generated by the child * are not guaranteed to succeed, even if read-only */ if (is_vm_hugetlb_page(tmp)) reset_vma_resv_huge_pages(tmp); /* * Link in the new vma and copy the page table entries. */ *pprev = tmp; pprev = &tmp->vm_next; tmp->vm_prev = prev; prev = tmp; __vma_link_rb(mm, tmp, rb_link, rb_parent); rb_link = &tmp->vm_rb.rb_right; rb_parent = &tmp->vm_rb; mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); if (retval) goto out; } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); mmap_write_unlock(oldmm); dup_userfaultfd_complete(&uf); fail_uprobe_end: uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); fail_nomem_policy: vm_area_free(tmp); fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); goto out; } static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { mmap_write_lock(oldmm); dup_mm_exe_file(mm, oldmm); mmap_write_unlock(oldmm); return 0; } #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = atomic_long_read(&mm->rss_stat.count[i]); if (unlikely(x)) pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n", mm, resident_page_types[i], x); } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); if (!profile_handoff_task(tsk)) free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = totalram_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR static void task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } #endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */ void __init fork_init(void) { int i; #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); #endif /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; unsigned long *stack; struct vm_struct *stack_vm_area __maybe_unused; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; stack = alloc_thread_stack_node(tsk, node); if (!stack) goto free_tsk; if (memcg_charge_kernel_stack(tsk)) goto free_stack; stack_vm_area = task_stack_vm_area(tsk); err = arch_dup_task_struct(tsk, orig); /* * arch_dup_task_struct() clobbers the stack-related fields. Make * sure they're properly initialized before using any stack-related * functions again. */ tsk->stack = stack; #ifdef CONFIG_VMAP_STACK tsk->stack_vm_area = stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif if (err) goto free_stack; err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->pf_io_worker = NULL; account_kernel_stack(tsk, 1); kcov_task_init(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_queue = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif return tsk; free_stack: free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_pasid(struct mm_struct *mm) { #ifdef CONFIG_IOMMU_SUPPORT mm->pasid = INIT_PASID; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mm->mmap = NULL; mm->mm_rb = RB_ROOT; mm->vmacache_seqnum = 0; atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); mm->core_state = NULL; mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_init_pasid(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; mm->def_flags = 0; } if (mm_alloc_pgd(mm)) goto fail_nopgd; if (init_new_context(p, mm)) goto fail_nocontext; mm->user_ns = get_user_ns(user_ns); return mm; fail_nocontext: mm_free_pgd(mm); fail_nopgd: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_page(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #ifdef CONFIG_MMU static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve task is single * threaded. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * * This changes mm's executable file (shown as symlink /proc/[pid]/exe), * dealing with concurrent invocation and without grabbing the mmap lock in * write mode. * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { mmap_read_lock(mm); for (vma = mm->mmap; vma && !ret; vma = vma->vm_next) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) ret = -EBUSY; } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } /* set the new file, lockless */ ret = deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); old_exe_file = xchg(&mm->exe_file, new_exe_file); if (old_exe_file) { /* * Don't race with dup_mmap() getting the file and disallowing * write access while someone might open the file writable. */ mmap_read_lock(mm); allow_write_access(old_exe_file); fput(old_exe_file); mmap_read_unlock(mm); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = rcu_dereference(mm->exe_file); if (exe_file && !get_file_rcu(exe_file)) exe_file = NULL; rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (!(task->flags & PF_KTHREAD)) exe_file = get_mm_exe_file(mm); } task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; task_lock(task); mm = task->mm; if (mm) { if (task->flags & PF_KTHREAD) mm = NULL; else mmget(mm); } task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (mm && mm != current->mm && !ptrace_may_access(task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { int killed; freezer_do_not_count(); cgroup_enter_frozen(); killed = wait_for_completion_killable(vfork); cgroup_leave_frozen(false); freezer_count(); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) && atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; err = dup_mmap(mm, oldmm); if (err) goto free_pt; mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); fail_nomem: return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; /* initialize the new vmacache entries */ vmacache_flush(tsk); if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; return 0; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ spin_lock(&fs->lock); if (fs->in_exec) { spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(unsigned long clone_flags, struct task_struct *tsk) { struct files_struct *oldf, *newf; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) return 0; if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); return 0; } newf = dup_fd(oldf, NULL); if (IS_ERR(newf)) return PTR_ERR(newf); tsk->files = newf; return 0; } static int copy_io(unsigned long clone_flags, struct task_struct *tsk) { #ifdef CONFIG_BLOCK struct io_context *ioc = current->io_context; struct io_context *new_ioc; if (!ioc) return 0; /* * Share io context with parent, if CLONE_IO is set */ if (clone_flags & CLONE_IO) { ioc_task_link(ioc); tsk->io_context = ioc; } else if (ioprio_valid(ioc->ioprio)) { new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE); if (unlikely(!new_ioc)) return -ENOMEM; new_ioc->ioprio = ioc->ioprio; put_io_context(new_ioc); } #endif return 0; } static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_LIST_HEAD(&sig->posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } struct pid *pidfd_pid(const struct file *file) { if (file->f_op == &pidfd_fops) return file->private_data; return ERR_PTR(-EBADF); } static int pidfd_release(struct inode *inode, struct file *file) { struct pid *pid = file->private_data; file->private_data = NULL; put_pid(pid); return 0; } #ifdef CONFIG_PROC_FS /** * pidfd_show_fdinfo - print information about a pidfd * @m: proc fdinfo file * @f: file referencing a pidfd * * Pid: * This function will print the pid that a given pidfd refers to in the * pid namespace of the procfs instance. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its pid. This is * similar to calling getppid() on a process whose parent is outside of * its pid namespace. * * NSpid: * If pid namespaces are supported then this function will also print * the pid of a given pidfd refers to for all descendant pid namespaces * starting from the current pid namespace of the instance, i.e. the * Pid field and the first entry in the NSpid field will be identical. * If the pid namespace of the process is not a descendant of the pid * namespace of the procfs instance 0 will be shown as its first NSpid * entry and no others will be shown. * Note that this differs from the Pid and NSpid fields in * /proc/<pid>/status where Pid and NSpid are always shown relative to * the pid namespace of the procfs instance. The difference becomes * obvious when sending around a pidfd between pid namespaces from a * different branch of the tree, i.e. where no ancestral relation is * present between the pid namespaces: * - create two new pid namespaces ns1 and ns2 in the initial pid * namespace (also take care to create new mount namespaces in the * new pid namespace and mount procfs) * - create a process with a pidfd in ns1 * - send pidfd from ns1 to ns2 * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid * have exactly one entry, which is 0 */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { struct pid *pid = f->private_data; struct pid_namespace *ns; pid_t nr = -1; if (likely(pid_has_task(pid, PIDTYPE_PID))) { ns = proc_pid_ns(file_inode(m->file)->i_sb); nr = pid_nr_ns(pid, ns); } seq_put_decimal_ll(m, "Pid:\t", nr); #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { int i; /* If nr is non-zero it means that 'pid' is valid and that * ns, i.e. the pid namespace associated with the procfs * instance, is in the pid namespace hierarchy of pid. * Start at one below the already printed level. */ for (i = ns->level + 1; i <= pid->level; i++) seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); } #endif seq_putc(m, '\n'); } #endif /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = file->private_data; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); /* * Inform pollers only when the whole thread group exits. * If the thread group leader exits before all other threads in the * group, then poll(2) should block, similar to the wait(2) family. */ if (thread_group_exited(pid)) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; } const struct file_operations pidfd_fops = { .release = pidfd_release, .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif }; static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ static __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } /* * If the new process will be in a different time namespace * do not allow it to share VM or a thread group with the forking task. */ if (clone_flags & (CLONE_THREAD | CLONE_VM)) { if (nsp->time_ns != nsp->time_ns_for_children) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. * - CLONE_THREAD is blocked until someone really needs it. */ if (clone_flags & (CLONE_DETACHED | CLONE_THREAD)) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; if (args->io_thread) { /* * Mark us an IO worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_IO_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } /* * This _must_ happen before we call free_task(), i.e. before we jump * to any of the bad_fork_* labels. This is to avoid freeing * p->set_child_tid which is (ab)used as a kthread's data pointer for * kernel threads (PF_KTHREAD). */ p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif #if defined(SPLIT_RSS_COUNTING) memset(&p->rss_stat, 0, sizeof(p->rss_stat)); #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_threadgroup_lock; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; p->cpuset_slab_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; #ifdef CONFIG_LOCKDEP lockdep_init_task(p); #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_cleanup_policy; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(clone_flags, args->stack, args->stack_size, p, args->tls); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, O_RDWR | O_CLOEXEC); if (IS_ERR(pidfile)) { put_unused_fd(pidfd); retval = PTR_ERR(pidfile); goto bad_fork_free_pid; } get_pid(pid); /* held by pidfile now */ retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ sched_cgroup_fork(p, args); /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_cancel_cgroup; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_cancel_cgroup; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_cancel_cgroup: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); bad_fork_cleanup_threadgroup_lock: #endif delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO; struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .stack = (unsigned long)fn, .stack_size = (unsigned long)arg, .io_thread = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((args->flags & CLONE_PIDFD) && (args->flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .stack = (unsigned long)fn, .stack_size = (unsigned long)arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE3 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } #endif void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { fd = dup_fd(fd, NULL); if (IS_ERR(fd)) return PTR_ERR(fd); *new_fdp = fd; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *fd, *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; spin_unlock(&fs->lock); } if (new_fd) { fd = current->files; current->files = new_fd; new_fd = fd; } task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } |
| 9 3678 822 3172 823 829 821 4386 4322 81 390 384 4432 4432 82 3059 2072 471 384 383 1 4290 160 613 29 23 4315 4316 93 92 15 80 66 15 23 10 18 23 23 79 72 16 3 81 81 623 626 127 567 82 1 69 21 81 81 80 1 1 1 4318 4322 4314 4332 902 4290 830 4320 4316 4316 4306 830 10 3959 4285 588 56 4315 4334 4317 1132 4283 257 4310 4289 4290 340 4283 4308 1187 1191 1188 1187 1187 352 1095 1034 1038 157 1039 1040 350 1 352 52 52 6 6 4 2 2 2 4 172 171 172 172 173 172 172 171 171 172 172 15 15 15 15 454 454 447 2 89 6 6 6 90 456 454 6 116 383 385 385 385 383 384 381 127 4 4 4 389 390 390 386 314 66 66 65 66 66 65 66 66 66 66 66 66 65 66 66 66 66 66 65 65 66 66 65 66 66 66 66 66 66 66 66 66 66 66 66 65 66 66 66 66 66 66 66 66 66 66 66 66 66 65 66 66 15 15 15 11 15 15 15 8 15 2 2 15 1715 1721 1716 69 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include "workqueue_internal.h" enum { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. */ POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 24, }; /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * X: During normal operation, modification requires pool->lock and should * be done only from local cpu. Either disabling preemption on local * cpu or grabbing pool->lock is enough for read access. If * POOL_DISASSOCIATED is set, it's identical to L. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * MD: wq_mayday_lock protected. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* X: flags */ unsigned long watchdog_ts; /* L: watchdog timestamp */ struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* X: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct completion *detach_completion; /* all workers detached */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ /* * The current concurrency level. As it's likely to be accessed * from other CPUs during try_to_wake_up(), put it in a separate * cacheline. */ atomic_t nr_running ____cacheline_aligned_in_smp; /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; } ____cacheline_aligned_in_smp; /* * The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ /* * nr_active management and WORK_STRUCT_INACTIVE: * * When pwq->nr_active >= max_active, new work item is queued to * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * * All work items marked with WORK_STRUCT_INACTIVE do not participate * in pwq->nr_active and all work items in pwq->inactive_works are * marked with WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE * work items are in pwq->inactive_works. Some of them are ready to * run in pool->worklist or worker->scheduled. Those work itmes are * only struct wq_barrier which is used for flush_work() and should * not participate in pwq->nr_active. For non-barrier work item, it * is marked with WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ int max_active; /* L: max active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ /* * Release of unbound pwq is punted to system_wq. See put_pwq() * and pwq_unbound_release_workfn() for details. pool_workqueue * itself is also RCU protected so that the first pwq can be * determined without grabbing wq->mutex. */ struct work_struct unbound_release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_FLAG_BITS); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ int saved_max_active; /* WQ: saved pwq max_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */ struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */ }; static struct kmem_cache *pwq_cache; static cpumask_var_t *wq_numa_possible_cpumask; /* possible CPUs of each node */ static bool wq_disable_numa; module_param_named(disable_numa, wq_disable_numa, bool, 0444); /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_numa_enabled; /* unbound NUMA affinity enabled */ /* buf for wq_update_unbound_numa_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; struct workqueue_struct *system_wq __read_mostly; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __read_mostly; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __read_mostly; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __read_mostly; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __read_mostly; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { destroy_timer_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } /** * unbound_pwq_by_node - return the unbound pool_workqueue for the given node * @wq: the target workqueue * @node: the node ID * * This must be called with any of wq_pool_mutex, wq->mutex or RCU * read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * Return: The unbound pool_workqueue for @node. */ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, int node) { assert_rcu_or_wq_mutex_or_pool_mutex(wq); /* * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a * delayed item is pending. The plan is to keep CPU -> NODE * mapping valid and stable across CPU on/offlines. Once that * happens, this workaround can be removed. */ if (unlikely(node == NUMA_NO_NODE)) return wq->dfl_pwq; return rcu_dereference_raw(wq->numa_pwq_tbl[node]); } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(unsigned long work_data) { return (work_data >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling() * and clear_work_data() can be used to set the pwq, pool or clear * work->data. These functions should only be called while the work is * owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. * * %WORK_OFFQ_CANCELING is used to mark a work item which is being * canceled. While being canceled, a work item may have its PENDING set * but stay off timer and worklist for arbitrarily long and nobody should * try to steal the PENDING bit. */ static inline void set_work_data(struct work_struct *work, unsigned long data, unsigned long flags) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | flags | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long extra_flags) { set_work_data(work, (unsigned long)pwq, WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id) { set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, WORK_STRUCT_PENDING); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static void clear_work_data(struct work_struct *work) { smp_wmb(); /* see set_work_pool_and_clear_pending() */ set_work_data(work, WORK_STRUCT_NO_POOL, 0); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } /** * get_work_pool_id - return the worker pool ID a given work is associated with * @work: the work item of interest * * Return: The worker_pool ID @work was last associated with. * %WORK_OFFQ_POOL_NONE if none. */ static int get_work_pool_id(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool->id; return data >> WORK_OFFQ_POOL_SHIFT; } static void mark_work_canceling(struct work_struct *work) { unsigned long pool_id = get_work_pool_id(work); pool_id <<= WORK_OFFQ_POOL_SHIFT; set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING); } static bool work_is_canceling(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); return !(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_CANCELING); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ static bool __need_more_worker(struct worker_pool *pool) { return !atomic_read(&pool->nr_running); } /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && __need_more_worker(pool); } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && atomic_read(&pool->nr_running) <= 1; } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /* * Wake up functions. */ /* Return the first idle worker. Safe with preemption disabled */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * wake_up_worker - wake up an idle worker * @pool: worker pool to wake worker from * * Wake up the first idle worker of @pool. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void wake_up_worker(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); if (likely(worker)) wake_up_process(worker->task); } /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!worker->sleeping) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&worker->pool->nr_running); preempt_enable(); worker->sleeping = 0; } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. Preemption needs to be disabled to protect ->sleeping * assignment. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *next, *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (worker->sleeping) return; worker->sleeping = 1; raw_spin_lock_irq(&pool->lock); /* * The counterpart of the following dec_and_test, implied mb, * worklist not empty test sequence is in insert_work(). * Please read comment there. * * NOT_RUNNING is clear. This means that we're bound to and * running on the local cpu w/ rq lock held and preemption * disabled, which in turn means that none else could be * manipulating idle_list, so dereferencing idle_list without pool * lock is safe. */ if (atomic_dec_and_test(&pool->nr_running) && !list_empty(&pool->worklist)) { next = first_idle_worker(pool); if (next) wake_up_process(next->task); } raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: * raw_spin_lock_irq(pool->lock) */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; WARN_ON_ONCE(worker->task != current); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { atomic_dec(&pool->nr_running); } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. * * CONTEXT: * raw_spin_lock_irq(pool->lock) */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; WARN_ON_ONCE(worker->task != current); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) atomic_inc(&pool->nr_running); } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to * be scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. * * If @nextp is not NULL, it's updated to point to the next work of * the last scheduled work. This allows move_linked_works() to be * nested inside outer list_for_each_entry_safe(). * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; if (WARN_ON_ONCE(!(pwq->wq->flags & WQ_UNBOUND))) return; /* * @pwq can't be released under pool->lock, bounce to * pwq_unbound_release_workfn(). This never recurses on the same * pool->lock as this path is taken only for unbound workqueues and * the release work item is scheduled on a per-cpu workqueue. To * avoid lockdep warning, unbound pool->locks are given lockdep * subclass of 1 in get_unbound_pool(). */ schedule_work(&pwq->unbound_release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static void pwq_activate_inactive_work(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work)); pwq->nr_active++; } static void pwq_activate_first_inactive(struct pool_workqueue *pwq) { struct work_struct *work = list_first_entry(&pwq->inactive_works, struct work_struct, entry); pwq_activate_inactive_work(work); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @work_data: work_data of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data) { int color = get_work_color(work_data); if (!(work_data & WORK_STRUCT_INACTIVE)) { pwq->nr_active--; if (!list_empty(&pwq->inactive_works)) { /* one down, submit an inactive one */ if (pwq->nr_active < pwq->max_active) pwq_activate_first_inactive(pwq); } } pwq->nr_in_flight[color]--; /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @is_dwork: @work is a delayed_work * @flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * -ENOENT if someone else is canceling @work, this state may persist * for arbitrarily long * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, unsigned long *flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*flags); /* try to steal the timer if it exists */ if (is_dwork) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If del_timer() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(del_timer(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { debug_work_deactivate(work); /* * A cancelable inactive work item must be in the * pwq->inactive_works since a queued barrier can't be * canceled (see the comments in insert_wq_barrier()). * * An inactive work item cannot be grabbed directly because * it might have linked barrier work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Make sure the work * item is activated before grabbing. */ if (*work_data_bits(work) & WORK_STRUCT_INACTIVE) pwq_activate_inactive_work(work); list_del_init(&work->entry); pwq_dec_nr_in_flight(pwq, *work_data_bits(work)); /* work->data points to pwq iff queued, point to pool */ set_work_pool_and_keep_pending(work, pool->id); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*flags); if (work_is_canceling(work)) return -ENOENT; cpu_relax(); return -EAGAIN; } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { struct worker_pool *pool = pwq->pool; /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); /* * Ensure either wq_worker_sleeping() sees the above * list_add_tail() or we see zero nr_running to avoid workers lying * around lazily while there are works to be processed. */ smp_mb(); if (__need_more_worker(pool)) wake_up_worker(pool); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { static bool printed_dbg_warning; int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else if (!printed_dbg_warning) { pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n"); printed_dbg_warning = true; } if (cpumask_empty(wq_unbound_cpumask)) return cpu; new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) { new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; } __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool; struct list_head *worklist; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* if draining, only works from the same workqueue are allowed */ if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (wq->flags & WQ_UNBOUND) { if (req_cpu == WORK_CPU_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); } else { if (req_cpu == WORK_CPU_UNBOUND) cpu = raw_smp_processor_id(); pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); } /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. */ last_pool = get_work_pool(work); if (last_pool && last_pool != pwq->pool) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pwq->pool->lock); } } else { raw_spin_lock(&pwq->pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have * raced with pwq release and it could already be dead. If its * refcnt is zero, repeat pwq selection. Note that pwqs never die * without another pwq replacing it in the numa_pwq_tbl or while * work items are executing on it, so the retrying is guaranteed to * make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pwq->pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); if (likely(pwq->nr_active < pwq->max_active)) { trace_workqueue_activate_work(work); pwq->nr_active++; worklist = &pwq->pool->worklist; if (list_empty(worklist)) pwq->pool->watchdog_ts = jiffies; } else { work_flags |= WORK_STRUCT_INACTIVE; worklist = &pwq->inactive_works; } debug_work_activate(work); insert_work(pwq, work, worklist, work_flags); out: raw_spin_unlock(&pwq->pool->lock); rcu_read_unlock(); } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long flags; local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * workqueue_select_cpu_near - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int workqueue_select_cpu_near(int node) { int cpu; /* No point in doing this if NUMA isn't enabled for workqueues */ if (!wq_numa_enabled) return WORK_CPU_UNBOUND; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { int cpu = workqueue_select_cpu_near(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); WARN_ON_FUNCTION_MISMATCH(timer->function, delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (unlikely(cpu != WORK_CPU_UNBOUND)) add_timer_on(timer, cpu); else add_timer(timer); } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long flags; /* read the comment in __queue_work() */ local_irq_save(flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long flags; int ret; do { ret = try_to_grab_pending(&dwork->work, true, &flags); } while (unlikely(ret == -EAGAIN)); if (likely(ret >= 0)) { __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(flags); } /* -ENOENT from try_to_grab_pending() becomes %true */ return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { rwork->wq = wq; call_rcu(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* * Sanity check nr_running. Because unbind_workers() releases * pool->lock between setting %WORKER_UNBOUND and zapping * nr_running, the warning may trigger spuriously. Check iff * unbind is not in progress. */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && pool->nr_workers == pool->nr_idle && atomic_read(&pool->nr_running)); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains * stable across this function. See the comments above the flag * definition for details. */ if (pool->flags & POOL_DISASSOCIATED) worker->flags |= WORKER_UNBOUND; else kthread_set_per_cpu(worker->task, pool->cpu); if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; struct completion *detach_completion = NULL; mutex_lock(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); list_del(&worker->node); worker->pool = NULL; if (list_empty(&pool->workers)) detach_completion = pool->detach_completion; mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); if (detach_completion) complete(detach_completion); } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; char id_buf[16]; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); if (id < 0) return NULL; worker = alloc_worker(pool->node); if (!worker) goto fail; worker->id = id; if (pool->cpu >= 0) snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, pool->attrs->nice < 0 ? "H" : ""); else snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "kworker/%s", id_buf); if (IS_ERR(worker->task)) goto fail; set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool->attrs->cpumask); /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: ida_free(&pool->worker_ida, id); kfree(worker); return NULL; } /** * destroy_worker - destroy a workqueue worker * @worker: worker to be destroyed * * Destroy @worker and adjust @pool stats accordingly. The worker should * be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void destroy_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; list_del_init(&worker->entry); worker->flags |= WORKER_DIE; wake_up_process(worker->task); } static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, idle_timer); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_entry(pool->idle_list.prev, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } destroy_worker(worker); } raw_spin_unlock_irq(&pool->lock); } static void send_mayday(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(work); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } del_timer_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; bool cpu_intensive = pwq->wq->flags & WQ_CPU_INTENSIVE; unsigned long work_data; struct worker *collision; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* * A single work shouldn't be executed concurrently by * multiple workers on a single cpu. Check whether anyone is * already processing the work. If so, defer the work to the * currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, NULL); return; } /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(cpu_intensive)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Wake up another worker if necessary. The condition is always * false for normal per-cpu workers since nr_running would always * be >= 1 at this point. This is used to chain execution of the * pending work items for WORKER_NOT_RUNNING workers such as the * UNBOUND and CPU_INTENSIVE ones. */ if (need_more_worker(pool)) wake_up_worker(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id); raw_spin_unlock_irq(&pool->lock); lock_map_acquire(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); lock_map_release(&lockdep_map); lock_map_release(&pwq->wq->lockdep_map); if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" " last function: %ps\n", current->comm, preempt_count(), task_pid_nr(current), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ cond_resched(); raw_spin_lock_irq(&pool->lock); /* clear cpu intensive status */ if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; pwq_dec_nr_in_flight(pwq, work_data); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { while (!list_empty(&worker->scheduled)) { struct work_struct *work = list_first_entry(&worker->scheduled, struct work_struct, entry); process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); WARN_ON_ONCE(!list_empty(&worker->entry)); set_pf_worker(false); set_task_comm(worker->task, "kworker/dying"); ida_free(&pool->worker_ida, worker->id); worker_detach_from_pool(worker); kfree(worker); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); pool->watchdog_ts = jiffies; if (likely(!(*work_data_bits(work) & WORK_STRUCT_LINKED))) { /* optimization path, not strictly necessary */ process_one_work(worker, work); if (unlikely(!list_empty(&worker->scheduled))) process_scheduled_works(worker); } else { move_linked_works(work, &worker->scheduled, NULL); process_scheduled_works(worker); } } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; struct list_head *scheduled = &rescuer->scheduled; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; bool first = true; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); /* * Slurp in all works issued via this workqueue and * process'em. */ WARN_ON_ONCE(!list_empty(scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { if (first) pool->watchdog_ts = jiffies; move_linked_works(work, scheduled, &n); } first = false; } if (!list_empty(scheduled)) { process_scheduled_works(rescuer); /* * The above execution of rescued work items could * have created more to rescue through * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't * incur MAYDAY_INTERVAL delay inbetween. */ if (pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); /* * Queue iff we aren't racing destruction * and somebody else hasn't queued it already. */ if (wq->rescuer && list_empty(&pwq->mayday_node)) { get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); } raw_spin_unlock(&wq_mayday_lock); } } /* * Put the reference grabbed by send_mayday(). @pool won't * go away while we're still attached to it. */ put_pwq(pwq); /* * Leave this pool. If need_more_worker() is %true, notify a * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. */ if (need_more_worker(pool)) wake_up_worker(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * * %current is trying to flush the whole @target_wq or @target_work on it. * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not * reclaiming memory or running on a workqueue which doesn't have * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to * a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work) { work_func_t target_func = target_work ? target_work->func : NULL; struct worker *worker; if (target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. */ INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* The barrier work item does not participate in pwq->nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) { head = worker->scheduled.next; work_color = worker->current_color; } else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ work_flags |= *bits & WORK_STRUCT_LINKED; work_color = get_work_color(*bits); __set_bit(WORK_STRUCT_LINKED_BIT, bits); } pwq->nr_in_flight[work_color]++; work_flags |= work_color_to_flags(work_color); debug_work_activate(&barr->work); insert_work(pwq, &barr->work, head, work_flags); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } for_each_pwq(pwq, wq) { struct worker_pool *pool = pwq->pool; raw_spin_lock_irq(&pool->lock); if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } raw_spin_unlock_irq(&pool->lock); } if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } /** * flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, wq->lockdep_map), }; int next_color; if (WARN_ON(!wq_online)) return; lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = !pwq->nr_active && list_empty(&pwq->inactive_works); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: %s() isn't complete after %u tries\n", wq->name, __func__, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; might_sleep(); rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } check_flush_dependency(pwq->wq, work); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)) { lock_map_acquire(&pwq->wq->lockdep_map); lock_map_release(&pwq->wq->lockdep_map); } rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (start_flush_work(work, &barr, from_cancel)) { wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); return true; } else { return false; } } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); struct cwt_wait { wait_queue_entry_t wait; struct work_struct *work; }; static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); if (cwait->work != key) return 0; return autoremove_wake_function(wait, mode, sync, key); } static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) { static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq); unsigned long flags; int ret; do { ret = try_to_grab_pending(work, is_dwork, &flags); /* * If someone else is already canceling, wait for it to * finish. flush_work() doesn't work for PREEMPT_NONE * because we may get scheduled between @work's completion * and the other canceling task resuming and clearing * CANCELING - flush_work() will return false immediately * as @work is no longer busy, try_to_grab_pending() will * return -ENOENT as @work is still being canceled and the * other canceling task won't be able to clear CANCELING as * we're hogging the CPU. * * Let's wait for completion using a waitqueue. As this * may lead to the thundering herd problem, use a custom * wake function which matches @work along with exclusive * wait and wakeup. */ if (unlikely(ret == -ENOENT)) { struct cwt_wait cwait; init_wait(&cwait.wait); cwait.wait.func = cwt_wakefn; cwait.work = work; prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait, TASK_UNINTERRUPTIBLE); if (work_is_canceling(work)) schedule(); finish_wait(&cancel_waitq, &cwait.wait); } } while (unlikely(ret < 0)); /* tell other tasks trying to grab @work to back off */ mark_work_canceling(work); local_irq_restore(flags); /* * This allows canceling during early boot. We know that @work * isn't executing. */ if (wq_online) __flush_work(work, true); clear_work_data(work); /* * Paired with prepare_to_wait() above so that either * waitqueue_active() is visible here or !work_is_canceling() is * visible there. */ smp_mb(); if (waitqueue_active(&cancel_waitq)) __wake_up(&cancel_waitq, TASK_NORMAL, 1, work); return ret; } /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function * can be used even if the work re-queues itself or migrates to * another workqueue. On return from this function, @work is * guaranteed to be not pending or executing on any CPU. * * cancel_work_sync(&delayed_work->work) must not be used for * delayed_work's. Use cancel_delayed_work_sync() instead. * * The caller must ensure that the workqueue on which @work was last * queued can't be destroyed before this function returns. * * Return: * %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_timer(work, false); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static bool __cancel_work(struct work_struct *work, bool is_dwork) { unsigned long flags; int ret; do { ret = try_to_grab_pending(work, is_dwork, &flags); } while (unlikely(ret == -EAGAIN)); if (unlikely(ret < 0)) return false; set_work_pool_and_clear_pending(work, get_work_pool_id(work)); local_irq_restore(flags); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, false); } EXPORT_SYMBOL(cancel_work); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, true); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_timer(&dwork->work, true); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; cpus_read_lock(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); cpus_read_unlock(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs(void) { struct workqueue_attrs *attrs; attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); /* * Unlike hash and equality test, this function doesn't ignore * ->no_numa as it is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears ->no_numa after copying. */ to->no_numa = from->no_numa; } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (!cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->watchdog_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; lockdep_init_map(&wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); wq_free_lockdep(wq); if (!(wq->flags & WQ_UNBOUND)) free_percpu(wq->cpu_pwqs); else free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /* This returns with the lock held on success (pool manager is inactive). */ static bool wq_manager_inactive(struct worker_pool *pool) { raw_spin_lock_irq(&pool->lock); if (pool->flags & POOL_MANAGER_ACTIVE) { raw_spin_unlock_irq(&pool->lock); return false; } return true; } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { DECLARE_COMPLETION_ONSTACK(detach_completion); struct worker *worker; lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * Because of how wq_manager_inactive() works, we will hold the * spinlock after a successful wait. */ rcuwait_wait_event(&manager_wait, wq_manager_inactive(pool), TASK_UNINTERRUPTIBLE); pool->flags |= POOL_MANAGER_ACTIVE; while ((worker = first_idle_worker(pool))) destroy_worker(worker); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); mutex_lock(&wq_pool_attach_mutex); if (!list_empty(&pool->workers)) pool->detach_completion = &detach_completion; mutex_unlock(&wq_pool_attach_mutex); if (pool->detach_completion) wait_for_completion(pool->detach_completion); /* shut down the timers */ del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int node; int target_node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* if cpumask is contained inside a NUMA node, we belong to that node */ if (wq_numa_enabled) { for_each_node(node) { if (cpumask_subset(attrs->cpumask, wq_numa_possible_cpumask[node])) { target_node = node; break; } } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, target_node); if (!pool || init_worker_pool(pool) < 0) goto fail; lockdep_set_subclass(&pool->lock, 1); /* see put_pwq() */ copy_workqueue_attrs(pool->attrs, attrs); pool->node = target_node; /* * no_numa isn't a worker_pool attribute, always clear it. See * 'struct workqueue_attrs' comments for detail. */ pool->attrs->no_numa = false; if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } static void rcu_free_pwq(struct rcu_head *rcu) { kmem_cache_free(pwq_cache, container_of(rcu, struct pool_workqueue, rcu)); } /* * Scheduled on system_wq by put_pwq() when an unbound pwq hits zero refcnt * and needs to be destroyed. */ static void pwq_unbound_release_workfn(struct work_struct *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, unbound_release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * when @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND))) return; mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); mutex_unlock(&wq->mutex); } mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); call_rcu(&pwq->rcu, rcu_free_pwq); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /** * pwq_adjust_max_active - update a pwq's max_active to the current setting * @pwq: target pool_workqueue * * If @pwq isn't freezing, set @pwq->max_active to the associated * workqueue's saved_max_active and activate inactive work items * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. */ static void pwq_adjust_max_active(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; bool freezable = wq->flags & WQ_FREEZABLE; unsigned long flags; /* for @wq->saved_max_active */ lockdep_assert_held(&wq->mutex); /* fast exit for non-freezable wqs */ if (!freezable && pwq->max_active == wq->saved_max_active) return; /* this function can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, flags); /* * During [un]freezing, the caller is responsible for ensuring that * this function is called at least once after @workqueue_freezing * is updated and visible. */ if (!freezable || !workqueue_freezing) { bool kick = false; pwq->max_active = wq->saved_max_active; while (!list_empty(&pwq->inactive_works) && pwq->nr_active < pwq->max_active) { pwq_activate_first_inactive(pwq); kick = true; } /* * Need to kick a worker after thawed or an unbound wq's * max_active is bumped. In realtime scenarios, always kicking a * worker will cause interference on the isolated cpu cores, so * let's kick iff work items were activated. */ if (kick) wake_up_worker(pwq->pool); } else { pwq->max_active = 0; } raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); } /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); INIT_WORK(&pwq->unbound_release_work, pwq_unbound_release_workfn); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* sync max_active to the current setting */ pwq_adjust_max_active(pwq); /* link in @pwq */ list_add_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } /** * wq_calc_node_cpumask - calculate a wq_attrs' cpumask for the specified node * @attrs: the wq_attrs of the default pwq of the target workqueue * @node: the target NUMA node * @cpu_going_down: if >= 0, the CPU to consider as offline * @cpumask: outarg, the resulting cpumask * * Calculate the cpumask a workqueue with @attrs should use on @node. If * @cpu_going_down is >= 0, that cpu is considered offline during * calculation. The result is stored in @cpumask. * * If NUMA affinity is not enabled, @attrs->cpumask is always used. If * enabled and @node has online CPUs requested by @attrs, the returned * cpumask is the intersection of the possible CPUs of @node and * @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @node stays * stable. * * Return: %true if the resulting @cpumask is different from @attrs->cpumask, * %false if equal. */ static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node, int cpu_going_down, cpumask_t *cpumask) { if (!wq_numa_enabled || attrs->no_numa) goto use_dfl; /* does @node have any online CPUs @attrs wants? */ cpumask_and(cpumask, cpumask_of_node(node), attrs->cpumask); if (cpu_going_down >= 0) cpumask_clear_cpu(cpu_going_down, cpumask); if (cpumask_empty(cpumask)) goto use_dfl; /* yeap, return possible CPUs in @node that @attrs wants */ cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]); if (cpumask_empty(cpumask)) { pr_warn_once("WARNING: workqueue cpumask: online intersect > " "possible intersect\n"); return false; } return !cpumask_equal(cpumask, attrs->cpumask); use_dfl: cpumask_copy(cpumask, attrs->cpumask); return false; } /* install @pwq into @wq's numa_pwq_tbl[] for @node and return the old pwq */ static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, int node, struct pool_workqueue *pwq) { struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); rcu_assign_pointer(wq->numa_pwq_tbl[node], pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int node; for_each_node(node) put_pwq_unlocked(ctx->pwq_tbl[node]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs, *tmp_attrs; int node; lockdep_assert_held(&wq_pool_mutex); ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_node_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); tmp_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs || !tmp_attrs) goto out_free; /* * Calculate the attrs of the default pwq. * If the user configured cpumask doesn't overlap with the * wq_unbound_cpumask, we fallback to the wq_unbound_cpumask. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, wq_unbound_cpumask); if (unlikely(cpumask_empty(new_attrs->cpumask))) cpumask_copy(new_attrs->cpumask, wq_unbound_cpumask); /* * We may create multiple pwqs with differing cpumasks. Make a * copy of @new_attrs which will be modified and used to obtain * pools. */ copy_workqueue_attrs(tmp_attrs, new_attrs); /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_node(node) { if (wq_calc_node_cpumask(new_attrs, node, -1, tmp_attrs->cpumask)) { ctx->pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); if (!ctx->pwq_tbl[node]) goto out_free; } else { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[node] = ctx->dfl_pwq; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); ctx->attrs = new_attrs; ctx->wq = wq; free_workqueue_attrs(tmp_attrs); return ctx; out_free: free_workqueue_attrs(tmp_attrs); free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return NULL; } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int node; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwq and install the new one */ for_each_node(node) ctx->pwq_tbl[node] = numa_pwq_tbl_install(ctx->wq, node, ctx->pwq_tbl[node]); /* @dfl_pwq might not have been used, ensure it's linked */ link_pwq(ctx->dfl_pwq); swap(ctx->wq->dfl_pwq, ctx->dfl_pwq); mutex_unlock(&ctx->wq->mutex); } static void apply_wqattrs_lock(void) { /* CPUs should stay stable across pwq creations and installations */ cpus_read_lock(); mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; /* creating multiple pwqs breaks ordering guarantee */ if (!list_empty(&wq->pwqs)) { if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return -EINVAL; wq->flags &= ~__WQ_ORDERED; } ctx = apply_wqattrs_prepare(wq, attrs); if (!ctx) return -ENOMEM; /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, on NUMA * machines, this function maps a separate pwq to each NUMA node with * possibles CPUs in @attrs->cpumask so that work items are affine to the * NUMA node it was issued on. Older pwqs are released as in-flight work * items finish. Note that a work item which repeatedly requeues itself * back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Assumes caller has CPU hotplug read exclusion, i.e. cpus_read_lock(). * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; lockdep_assert_cpus_held(); mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * wq_update_unbound_numa - update NUMA affinity of a wq for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU coming up or going down * @online: whether @cpu is coming up or going down * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update NUMA affinity of * @wq accordingly. * * If NUMA affinity can't be adjusted due to memory allocation failure, it * falls back to @wq->dfl_pwq which may not be optimal but is always * correct. * * Note that when the last allowed CPU of a NUMA node goes offline for a * workqueue with a cpumask spanning multiple nodes, the workers which were * already executing the work items for the workqueue will lose their CPU * affinity and may execute on any CPU. This is similar to how per-cpu * workqueues behave on CPU_DOWN. If a workqueue user wants strict * affinity, it's the user's responsibility to flush the work item from * CPU_DOWN_PREPARE. */ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, bool online) { int node = cpu_to_node(cpu); int cpu_off = online ? -1 : cpu; struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; cpumask_t *cpumask; lockdep_assert_held(&wq_pool_mutex); if (!wq_numa_enabled || !(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->no_numa) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = wq_update_unbound_numa_attrs_buf; cpumask = target_attrs->cpumask; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); pwq = unbound_pwq_by_node(wq, node); /* * Let's determine what needs to be done. If the target cpumask is * different from the default pwq's, we need to compare it to @pwq's * and create a new one if they don't match. If the target cpumask * equals the default pwq's, the default pwq should be used. */ if (wq_calc_node_cpumask(wq->dfl_pwq->pool->attrs, node, cpu_off, cpumask)) { if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask)) return; } else { goto use_dfl_pwq; } /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = numa_pwq_tbl_install(wq, node, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); raw_spin_lock_irq(&wq->dfl_pwq->pool->lock); get_pwq(wq->dfl_pwq); raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock); old_pwq = numa_pwq_tbl_install(wq, node, wq->dfl_pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; if (!(wq->flags & WQ_UNBOUND)) { wq->cpu_pwqs = alloc_percpu(struct pool_workqueue); if (!wq->cpu_pwqs) return -ENOMEM; for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); struct worker_pool *cpu_pools = per_cpu(cpu_worker_pools, cpu); init_pwq(pwq, wq, &cpu_pools[highpri]); mutex_lock(&wq->mutex); link_pwq(pwq); mutex_unlock(&wq->mutex); } return 0; } cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } cpus_read_unlock(); return ret; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE; if (max_active < 1 || max_active > lim) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, lim); return clamp_val(max_active, 1, lim); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; int ret; if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) return -ENOMEM; rescuer->rescue_wq = wq; rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", wq->name); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); kfree(rescuer); return ret; } wq->rescuer = rescuer; kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } __printf(1, 4) struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...) { size_t tbl_size = 0; va_list args; struct workqueue_struct *wq; struct pool_workqueue *pwq; /* * Unbound && max_active == 1 used to imply ordered, which is no * longer the case on NUMA machines due to per-node pools. While * alloc_ordered_workqueue() is the right way to create an ordered * workqueue, keep the previous behavior to avoid subtle breakages * on NUMA. */ if ((flags & WQ_UNBOUND) && max_active == 1) flags |= __WQ_ORDERED; /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]); wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs(); if (!wq->unbound_attrs) goto err_free_wq; } va_start(args, max_active); vsnprintf(wq->name, sizeof(wq->name), fmt, args); va_end(args); max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); /* init wq */ wq->flags = flags; wq->saved_max_active = max_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); wq_init_lockdep(wq); INIT_LIST_HEAD(&wq->list); if (alloc_and_link_pwqs(wq) < 0) goto err_unreg_lockdep; if (wq_online && init_rescuer(wq) < 0) goto err_destroy; if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; /* * wq_pool_mutex protects global freeze state and workqueues list. * Grab it, adjust max_active and add the new @wq to workqueues * list. */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); mutex_unlock(&wq_pool_mutex); return wq; err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_destroy: destroy_workqueue(wq); return NULL; } EXPORT_SYMBOL_GPL(alloc_workqueue); static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1)) return true; if (pwq->nr_active || !list_empty(&pwq->inactive_works)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int node; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { struct worker *rescuer = wq->rescuer; /* this prevents new queueing */ raw_spin_lock_irq(&wq_mayday_lock); wq->rescuer = NULL; raw_spin_unlock_irq(&wq_mayday_lock); /* rescuer will empty maydays list before exiting */ kthread_stop(rescuer->task); kfree(rescuer); } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND)) { wq_unregister_lockdep(wq); /* * The base ref is never dropped on per-cpu pwqs. Directly * schedule RCU free. */ call_rcu(&wq->rcu, rcu_free_wq); } else { /* * We're the sole accessor of @wq at this point. Directly * access numa_pwq_tbl[] and dfl_pwq to put the base refs. * @wq will be freed when the last pwq is released. */ for_each_node(node) { pwq = rcu_access_pointer(wq->numa_pwq_tbl[node]); RCU_INIT_POINTER(wq->numa_pwq_tbl[node], NULL); put_pwq_unlocked(pwq); } /* * Put dfl_pwq. @wq may be freed any time after dfl_pwq is * put. Don't access it afterwards. */ pwq = wq->dfl_pwq; wq->dfl_pwq = NULL; put_pwq_unlocked(pwq); } } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { struct pool_workqueue *pwq; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->flags &= ~__WQ_ORDERED; wq->saved_max_active = max_active; for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * Note that both per-cpu and unbound workqueues may be associated with * multiple pool_workqueues which have separate congested states. A * workqueue being congested on one CPU doesn't mean the workqueue is also * contested on other CPUs / NUMA nodes. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; rcu_read_lock(); preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); if (!(wq->flags & WQ_UNBOUND)) pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); else pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); ret = !list_empty(&pwq->inactive_works); preempt_enable(); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); } static void pr_cont_work(bool comma, struct work_struct *work) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { pr_cont("%s %ps", comma ? "," : "", work->func); } } static void show_pwq(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d/%d refcnt=%d%s\n", pwq->nr_active, pwq->max_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont("%s %d%s:%ps", comma ? "," : "", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : "", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont("\n"); } } /** * show_one_workqueue - dump state of specified workqueue * @wq: workqueue whose state will be printed */ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; unsigned long flags; for_each_pwq(pwq, wq) { if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { idle = false; break; } } if (idle) /* Nothing to print for idle workqueue */ return; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, flags); if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); show_pwq(pwq); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } /** * show_one_worker_pool - dump state of specified worker pool * @pool: worker pool whose state will be printed */ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; unsigned long flags; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write * paths. */ printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s%d", first ? "idle: " : "", task_pid_nr(worker->task)); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } /** * show_all_workqueues - dump workqueue state * * Called from a sysrq handler or try_to_freeze_tasks() and prints out * all busy workqueues and pools. */ void show_all_workqueues(void) { struct workqueue_struct *wq; struct worker_pool *pool; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) show_one_workqueue(wq); for_each_pool(pool, pi) show_one_worker_pool(pool); rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { int off; /* always show the actual comm */ off = strscpy(buf, task->comm, size); if (off < 0) return; /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } mutex_unlock(&wq_pool_attach_mutex); } #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * except for the ones which are still executing works from * before the last CPU down must be on the cpu. After * this, they may become diasporas. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; raw_spin_unlock_irq(&pool->lock); for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, -1); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } mutex_unlock(&wq_pool_attach_mutex); /* * Call schedule() so that we cross rq->lock and thus can * guarantee sched callbacks see the %WORKER_UNBOUND flag. * This is necessary as scheduler callbacks may be invoked * from other cpus. */ schedule(); /* * Sched callbacks are disabled now. Zap nr_running. * After this, nr_running stays zero and need_more_worker() * and keep_working() are always true as long as the * worklist is not empty. This pool now behaves as an * unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ atomic_set(&pool->nr_running, 0); /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ raw_spin_lock_irq(&pool->lock); wake_up_worker(pool); raw_spin_unlock_irq(&pool->lock); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask) < 0); } raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * A bound idle worker should actually be on the runqueue * of the associated CPU for local wake-ups targeting it to * work. Kick all idle workers so that they migrate to the * associated CPU. Doing this in the same loop as * replacing UNBOUND with REBOUND is safe as no worker will * be bound before @pool->lock is released. */ if (worker_flags & WORKER_IDLE) wake_up_process(worker->task); /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); for_each_pool(pool, pi) { mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update NUMA affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) wq_update_unbound_numa(wq, cpu, true); mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update NUMA affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) wq_update_unbound_numa(wq, cpu, false); mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * @key: The lock class key for lock debugging purposes * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu_key); /** * work_on_cpu_safe_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function argument * @key: The lock class key for lock debugging purposes * * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold * any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_safe_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { long ret = -ENODEV; cpus_read_lock(); if (cpu_online(cpu)) ret = work_on_cpu_key(cpu, fn, arg, key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_on_cpu_safe_key); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) pwq_adjust_max_active(pwq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(void) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND)) continue; /* creating multiple pwqs breaks ordering guarantee */ if (!list_empty(&wq->pwqs)) { if (wq->flags & __WQ_ORDERED_EXPLICIT) continue; wq->flags &= ~__WQ_ORDERED; } ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs); if (!ctx) { ret = -ENOMEM; break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } return ret; } /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; cpumask_var_t saved_cpumask; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { apply_wqattrs_lock(); if (cpumask_equal(cpumask, wq_unbound_cpumask)) { ret = 0; goto out_unlock; } if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL)) { ret = -ENOMEM; goto out_unlock; } /* save the old wq_unbound_cpumask. */ cpumask_copy(saved_cpumask, wq_unbound_cpumask); /* update wq_unbound_cpumask at first and apply it to wqs. */ cpumask_copy(wq_unbound_cpumask, cpumask); ret = workqueue_apply_unbound_cpumask(); /* restore the wq_unbound_cpumask when failed. */ if (ret < 0) cpumask_copy(wq_unbound_cpumask, saved_cpumask); free_cpumask_var(saved_cpumask); out_unlock: apply_wqattrs_unlock(); } return ret; } #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * pool_ids RO int : the associated pool IDs for each node * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * numa RW bool : whether enable NUMA affinity */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_pool_ids_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); const char *delim = ""; int node, written = 0; cpus_read_lock(); rcu_read_lock(); for_each_node(node) { written += scnprintf(buf + written, PAGE_SIZE - written, "%s%d:%d", delim, node, unbound_pwq_by_node(wq, node)->pool->id); delim = " "; } written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); rcu_read_unlock(); cpus_read_unlock(); return written; } static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_numa_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", !wq->unbound_attrs->no_numa); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_numa_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = -EINVAL; if (sscanf(buf, "%d", &v) == 1) { attrs->no_numa = !v; ret = apply_workqueue_attrs_locked(wq, attrs); } out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(pool_ids, 0444, wq_pool_ids_show, NULL), __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(numa, 0644, wq_numa_show, wq_numa_store), __ATTR_NULL, }; static struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; static ssize_t wq_unbound_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq_unbound_cpumask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t wq_unbound_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static struct device_attribute wq_sysfs_cpumask_attr = __ATTR(cpumask, 0644, wq_unbound_cpumask_show, wq_unbound_cpumask_store); static int __init wq_sysfs_init(void) { int err; err = subsys_virtual_register(&wq_subsys, NULL); if (err) return err; return device_create_file(wq_subsys.dev_root, &wq_sysfs_cpumask_attr); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; /* * Adjusting max_active or creating new pwqs by applying * attributes breaks ordering guarantee. Disallow exposing ordered * workqueues. */ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; unsigned long now = jiffies; struct worker_pool *pool; int pi; if (!thresh) return; rcu_read_lock(); for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->watchdog_ts); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(now - pool_ts) / 1000); } } rcu_read_unlock(); if (lockup_detected) show_all_workqueues(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned long touch_ts = READ_ONCE(wq_watchdog_touched); unsigned long now = jiffies; if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = now; else WARN_ONCE(1, "%s should be called with valid CPU", __func__); /* Don't unnecessarily store to global cacheline */ if (time_after(now, touch_ts + thresh / 4)) WRITE_ONCE(wq_watchdog_touched, jiffies); } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; del_timer_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void __init wq_numa_init(void) { cpumask_var_t *tbl; int node, cpu; if (num_possible_nodes() <= 1) return; if (wq_disable_numa) { pr_info("workqueue: NUMA affinity support disabled\n"); return; } for_each_possible_cpu(cpu) { if (WARN_ON(cpu_to_node(cpu) == NUMA_NO_NODE)) { pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu); return; } } wq_update_unbound_numa_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!wq_update_unbound_numa_attrs_buf); /* * We want masks of possible CPUs of each node which isn't readily * available. Build one from cpu_to_node() which should have been * fully initialized by now. */ tbl = kcalloc(nr_node_ids, sizeof(tbl[0]), GFP_KERNEL); BUG_ON(!tbl); for_each_node(node) BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { node = cpu_to_node(cpu); cpumask_set_cpu(cpu, tbl[node]); } wq_numa_possible_cpumask = tbl; wq_numa_enabled = true; } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first half of two-staged workqueue subsystem initialization * and invoked as soon as the bare basics - memory allocation, cpumasks and * idr are up. It sets up all the data structures and system workqueues * and allows early boot code to create workqueues and queue/cancel work * items. Actual work item execution starts only after kthreads can be * created and scheduled right before early initcalls. */ void __init workqueue_init_early(void) { int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(hk_flags)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); /* initialize CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_cpu_worker_pool(pool, cpu) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); pool->attrs->nice = std_nice[i++]; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. * Turn off NUMA so that dfl_pwq is used for all nodes. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->no_numa = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq); } /** * workqueue_init - bring workqueue subsystem fully online * * This is the latter half of two-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. * Workqueues have been created and work items queued on them, but there * are no kworkers executing the work items yet. Populate the worker pools * with the initial workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; /* * It'd be simpler to initialize NUMA in workqueue_init_early() but * CPU to node mapping may not be available that early on some * archs such as power and arm64. As per-cpu pools created * previously could be missing node hint and unbound pools NUMA * affinity, fix them up. * * Also, while iterating workqueues, create rescuers if requested. */ wq_numa_init(); mutex_lock(&wq_pool_mutex); for_each_possible_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->node = cpu_to_node(cpu); } } list_for_each_entry(wq, &workqueues, list) { wq_update_unbound_numa(wq, smp_processor_id(), true); WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* create the initial workers */ for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } |
| 827 832 830 832 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2019 Facebook * Copyright 2020 Google LLC. */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/bpf_local_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/bpf_lsm.h> #include <linux/btf_ids.h> #include <linux/fdtable.h> DEFINE_BPF_STORAGE_CACHE(inode_cache); static struct bpf_local_storage __rcu ** inode_storage_ptr(void *owner) { struct inode *inode = owner; struct bpf_storage_blob *bsb; bsb = bpf_inode(inode); if (!bsb) return NULL; return &bsb->storage; } static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *inode_storage; struct bpf_local_storage_map *smap; struct bpf_storage_blob *bsb; bsb = bpf_inode(inode); if (!bsb) return NULL; inode_storage = rcu_dereference(bsb->storage); if (!inode_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(inode_storage, smap, cacheit_lockit); } void bpf_inode_storage_free(struct inode *inode) { struct bpf_local_storage_elem *selem; struct bpf_local_storage *local_storage; bool free_inode_storage = false; struct bpf_storage_blob *bsb; struct hlist_node *n; bsb = bpf_inode(inode); if (!bsb) return; rcu_read_lock(); local_storage = rcu_dereference(bsb->storage); if (!local_storage) { rcu_read_unlock(); return; } /* Neither the bpf_prog nor the bpf-map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added-to or deleted-from the * local_storage->list by the bpf_prog or by the bpf-map's syscall. * * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the local_storage->list and * the map's bucket->list. */ raw_spin_lock_bh(&local_storage->lock); hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { /* Always unlink from map before unlinking from * local_storage. */ bpf_selem_unlink_map(selem); free_inode_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, false); } raw_spin_unlock_bh(&local_storage->lock); rcu_read_unlock(); /* free_inoode_storage should always be true as long as * local_storage->list was non-empty. */ if (free_inode_storage) kfree_rcu(local_storage, rcu); } static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct file *f; int fd; fd = *(int *)key; f = fget_raw(fd); if (!f) return ERR_PTR(-EBADF); sdata = inode_storage_lookup(f->f_inode, map, true); fput(f); return sdata ? sdata->data : NULL; } static int bpf_fd_inode_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct file *f; int fd; fd = *(int *)key; f = fget_raw(fd); if (!f) return -EBADF; if (!inode_storage_ptr(f->f_inode)) { fput(f); return -EBADF; } sdata = bpf_local_storage_update(f->f_inode, (struct bpf_local_storage_map *)map, value, map_flags); fput(f); return PTR_ERR_OR_ZERO(sdata); } static int inode_storage_delete(struct inode *inode, struct bpf_map *map) { struct bpf_local_storage_data *sdata; sdata = inode_storage_lookup(inode, map, false); if (!sdata) return -ENOENT; bpf_selem_unlink(SELEM(sdata)); return 0; } static int bpf_fd_inode_storage_delete_elem(struct bpf_map *map, void *key) { struct file *f; int fd, err; fd = *(int *)key; f = fget_raw(fd); if (!f) return -EBADF; err = inode_storage_delete(f->f_inode, map); fput(f); return err; } BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, void *, value, u64, flags) { struct bpf_local_storage_data *sdata; if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) return (unsigned long)NULL; /* explicitly check that the inode_storage_ptr is not * NULL as inode_storage_lookup returns NULL in this case and * bpf_local_storage_update expects the owner to have a * valid storage pointer. */ if (!inode || !inode_storage_ptr(inode)) return (unsigned long)NULL; sdata = inode_storage_lookup(inode, map, true); if (sdata) return (unsigned long)sdata->data; /* This helper must only called from where the inode is guaranteed * to have a refcount and cannot be freed. */ if (flags & BPF_LOCAL_STORAGE_GET_F_CREATE) { sdata = bpf_local_storage_update( inode, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST); return IS_ERR(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } return (unsigned long)NULL; } BPF_CALL_2(bpf_inode_storage_delete, struct bpf_map *, map, struct inode *, inode) { if (!inode) return -EINVAL; /* This helper must only called from where the inode is guaranteed * to have a refcount and cannot be freed. */ return inode_storage_delete(inode, map); } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) { struct bpf_local_storage_map *smap; smap = bpf_local_storage_map_alloc(attr); if (IS_ERR(smap)) return ERR_CAST(smap); smap->cache_idx = bpf_local_storage_cache_idx_get(&inode_cache); return &smap->map; } static void inode_storage_map_free(struct bpf_map *map) { struct bpf_local_storage_map *smap; smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(&inode_cache, smap->cache_idx); bpf_local_storage_map_free(smap, NULL); } static int inode_storage_map_btf_id; const struct bpf_map_ops inode_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = inode_storage_map_alloc, .map_free = inode_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_inode_storage_lookup_elem, .map_update_elem = bpf_fd_inode_storage_update_elem, .map_delete_elem = bpf_fd_inode_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_btf_name = "bpf_local_storage_map", .map_btf_id = &inode_storage_map_btf_id, .map_owner_storage_ptr = inode_storage_ptr, }; BTF_ID_LIST_SINGLE(bpf_inode_storage_btf_ids, struct, inode) const struct bpf_func_proto bpf_inode_storage_get_proto = { .func = bpf_inode_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &bpf_inode_storage_btf_ids[0], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_inode_storage_delete_proto = { .func = bpf_inode_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &bpf_inode_storage_btf_ids[0], }; |
| 1824 1825 1827 1827 1828 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * netprio_cgroup.h Control Group Priority set * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #ifndef _NETPRIO_CGROUP_H #define _NETPRIO_CGROUP_H #include <linux/cgroup.h> #include <linux/hardirq.h> #include <linux/rcupdate.h> #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map { struct rcu_head rcu; u32 priomap_len; u32 priomap[]; }; static inline u32 task_netprioidx(struct task_struct *p) { struct cgroup_subsys_state *css; u32 idx; rcu_read_lock(); css = task_css(p, net_prio_cgrp_id); idx = css->id; rcu_read_unlock(); return idx; } static inline void sock_update_netprioidx(struct sock_cgroup_data *skcd) { if (in_interrupt()) return; sock_cgroup_set_prioidx(skcd, task_netprioidx(current)); } #else /* !CONFIG_CGROUP_NET_PRIO */ static inline u32 task_netprioidx(struct task_struct *p) { return 0; } static inline void sock_update_netprioidx(struct sock_cgroup_data *skcd) { } #endif /* CONFIG_CGROUP_NET_PRIO */ #endif /* _NET_CLS_CGROUP_H */ |
| 7 410 7 3 1 6 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* linux/net/inet/arp.h */ #ifndef _ARP_H #define _ARP_H #include <linux/if_arp.h> #include <linux/hash.h> #include <net/neighbour.h> extern struct neigh_table arp_tbl; static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd) { u32 key = *(const u32 *)pkey; u32 val = key ^ hash32_ptr(dev); return val * hash_rnd[0]; } #ifdef CONFIG_INET static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) key = INADDR_ANY; return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } #else static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { return NULL; } #endif static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); return n; } static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } void arp_init(void); int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *th); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir); void arp_ifdown(struct net_device *dev); int arp_invalidate(struct net_device *dev, __be32 ip, bool force); struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw); void arp_xmit(struct sk_buff *skb); #endif /* _ARP_H */ |
| 16812 5455 1097 493 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H #define HAVE_JUMP_LABEL_BATCH #include <asm/asm.h> #include <asm/nops.h> #ifndef __ASSEMBLY__ #include <linux/stringify.h> #include <linux/types.h> #define JUMP_TABLE_ENTRY \ ".pushsection __jump_table, \"aw\" \n\t" \ _ASM_ALIGN "\n\t" \ ".long 1b - . \n\t" \ ".long %l[l_yes] - . \n\t" \ _ASM_PTR "%c0 + %c1 - .\n\t" \ ".popsection \n\t" #ifdef CONFIG_STACK_VALIDATION static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" "jmp %l[l_yes] # objtool NOPs this \n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (2 | branch) : : l_yes); return false; l_yes: return true; } #else static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { asm_volatile_goto("1:" ".byte " __stringify(BYTES_NOP5) "\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } #endif /* STACK_VALIDATION */ static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { asm_volatile_goto("1:" "jmp %l[l_yes]\n\t" JUMP_TABLE_ENTRY : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } extern int arch_jump_entry_size(struct jump_entry *entry); #endif /* __ASSEMBLY__ */ #endif |
| 50 19 19 19 152 102 50 50 50 50 22 22 22 22 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 | // SPDX-License-Identifier: GPL-2.0 #include "cgroup-internal.h" #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/nsproxy.h> #include <linux/proc_ns.h> /* cgroup namespaces */ static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES); } static void dec_cgroup_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES); } static struct cgroup_namespace *alloc_cgroup_ns(void) { struct cgroup_namespace *new_ns; int ret; new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL_ACCOUNT); if (!new_ns) return ERR_PTR(-ENOMEM); ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); return ERR_PTR(ret); } refcount_set(&new_ns->ns.count, 1); new_ns->ns.ops = &cgroupns_operations; return new_ns; } void free_cgroup_ns(struct cgroup_namespace *ns) { put_css_set(ns->root_cset); dec_cgroup_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kfree(ns); } EXPORT_SYMBOL(free_cgroup_ns); struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { struct cgroup_namespace *new_ns; struct ucounts *ucounts; struct css_set *cset; BUG_ON(!old_ns); if (!(flags & CLONE_NEWCGROUP)) { get_cgroup_ns(old_ns); return old_ns; } /* Allow only sysadmin to create cgroup namespace. */ if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); ucounts = inc_cgroup_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); /* It is not safe to take cgroup_mutex here */ spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); spin_unlock_irq(&css_set_lock); new_ns = alloc_cgroup_ns(); if (IS_ERR(new_ns)) { put_css_set(cset); dec_cgroup_namespaces(ucounts); return new_ns; } new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; new_ns->root_cset = cset; return new_ns; } static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) { return container_of(ns, struct cgroup_namespace, ns); } static int cgroupns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); if (!ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN) || !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Don't need to do anything if we are attaching to our own cgroupns. */ if (cgroup_ns == nsproxy->cgroup_ns) return 0; get_cgroup_ns(cgroup_ns); put_cgroup_ns(nsproxy->cgroup_ns); nsproxy->cgroup_ns = cgroup_ns; return 0; } static struct ns_common *cgroupns_get(struct task_struct *task) { struct cgroup_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->cgroup_ns; get_cgroup_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void cgroupns_put(struct ns_common *ns) { put_cgroup_ns(to_cg_ns(ns)); } static struct user_namespace *cgroupns_owner(struct ns_common *ns) { return to_cg_ns(ns)->user_ns; } const struct proc_ns_operations cgroupns_operations = { .name = "cgroup", .type = CLONE_NEWCGROUP, .get = cgroupns_get, .put = cgroupns_put, .install = cgroupns_install, .owner = cgroupns_owner, }; |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 | // SPDX-License-Identifier: GPL-2.0 /* * This contains functions for filename crypto management * * Copyright (C) 2015, Google, Inc. * Copyright (C) 2015, Motorola Mobility * * Written by Uday Savagaonkar, 2014. * Modified by Jaegeuk Kim, 2015. * * This has not yet undergone a rigorous security audit. */ #include <linux/namei.h> #include <linux/scatterlist.h> #include <crypto/hash.h> #include <crypto/sha2.h> #include <crypto/skcipher.h> #include "fscrypt_private.h" /* * struct fscrypt_nokey_name - identifier for directory entry when key is absent * * When userspace lists an encrypted directory without access to the key, the * filesystem must present a unique "no-key name" for each filename that allows * it to find the directory entry again if requested. Naively, that would just * mean using the ciphertext filenames. However, since the ciphertext filenames * can contain illegal characters ('\0' and '/'), they must be encoded in some * way. We use base64url. But that can cause names to exceed NAME_MAX (255 * bytes), so we also need to use a strong hash to abbreviate long names. * * The filesystem may also need another kind of hash, the "dirhash", to quickly * find the directory entry. Since filesystems normally compute the dirhash * over the on-disk filename (i.e. the ciphertext), it's not computable from * no-key names that abbreviate the ciphertext using the strong hash to fit in * NAME_MAX. It's also not computable if it's a keyed hash taken over the * plaintext (but it may still be available in the on-disk directory entry); * casefolded directories use this type of dirhash. At least in these cases, * each no-key name must include the name's dirhash too. * * To meet all these requirements, we base64url-encode the following * variable-length structure. It contains the dirhash, or 0's if the filesystem * didn't provide one; up to 149 bytes of the ciphertext name; and for * ciphertexts longer than 149 bytes, also the SHA-256 of the remaining bytes. * * This ensures that each no-key name contains everything needed to find the * directory entry again, contains only legal characters, doesn't exceed * NAME_MAX, is unambiguous unless there's a SHA-256 collision, and that we only * take the performance hit of SHA-256 on very long filenames (which are rare). */ struct fscrypt_nokey_name { u32 dirhash[2]; u8 bytes[149]; u8 sha256[SHA256_DIGEST_SIZE]; }; /* 189 bytes => 252 bytes base64url-encoded, which is <= NAME_MAX (255) */ /* * Decoded size of max-size no-key name, i.e. a name that was abbreviated using * the strong hash and thus includes the 'sha256' field. This isn't simply * sizeof(struct fscrypt_nokey_name), as the padding at the end isn't included. */ #define FSCRYPT_NOKEY_NAME_MAX offsetofend(struct fscrypt_nokey_name, sha256) /* Encoded size of max-size no-key name */ #define FSCRYPT_NOKEY_NAME_MAX_ENCODED \ FSCRYPT_BASE64URL_CHARS(FSCRYPT_NOKEY_NAME_MAX) static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) { if (str->len == 1 && str->name[0] == '.') return true; if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') return true; return false; } /** * fscrypt_fname_encrypt() - encrypt a filename * @inode: inode of the parent directory (for regular filenames) * or of the symlink (for symlink targets) * @iname: the filename to encrypt * @out: (output) the encrypted filename * @olen: size of the encrypted filename. It must be at least @iname->len. * Any extra space is filled with NUL padding before encryption. * * Return: 0 on success, -errno on failure */ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, u8 *out, unsigned int olen) { struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); const struct fscrypt_info *ci = inode->i_crypt_info; struct crypto_skcipher *tfm = ci->ci_enc_key.tfm; union fscrypt_iv iv; struct scatterlist sg; int res; /* * Copy the filename to the output buffer for encrypting in-place and * pad it with the needed number of NUL bytes. */ if (WARN_ON(olen < iname->len)) return -ENOBUFS; memcpy(out, iname->name, iname->len); memset(out + iname->len, 0, olen - iname->len); /* Initialize the IV */ fscrypt_generate_iv(&iv, 0, ci); /* Set up the encryption request */ req = skcipher_request_alloc(tfm, GFP_NOFS); if (!req) return -ENOMEM; skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); sg_init_one(&sg, out, olen); skcipher_request_set_crypt(req, &sg, &sg, olen, &iv); /* Do the encryption */ res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); skcipher_request_free(req); if (res < 0) { fscrypt_err(inode, "Filename encryption failed: %d", res); return res; } return 0; } /** * fname_decrypt() - decrypt a filename * @inode: inode of the parent directory (for regular filenames) * or of the symlink (for symlink targets) * @iname: the encrypted filename to decrypt * @oname: (output) the decrypted filename. The caller must have allocated * enough space for this, e.g. using fscrypt_fname_alloc_buffer(). * * Return: 0 on success, -errno on failure */ static int fname_decrypt(const struct inode *inode, const struct fscrypt_str *iname, struct fscrypt_str *oname) { struct skcipher_request *req = NULL; DECLARE_CRYPTO_WAIT(wait); struct scatterlist src_sg, dst_sg; const struct fscrypt_info *ci = inode->i_crypt_info; struct crypto_skcipher *tfm = ci->ci_enc_key.tfm; union fscrypt_iv iv; int res; /* Allocate request */ req = skcipher_request_alloc(tfm, GFP_NOFS); if (!req) return -ENOMEM; skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, crypto_req_done, &wait); /* Initialize IV */ fscrypt_generate_iv(&iv, 0, ci); /* Create decryption request */ sg_init_one(&src_sg, iname->name, iname->len); sg_init_one(&dst_sg, oname->name, oname->len); skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, &iv); res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait); skcipher_request_free(req); if (res < 0) { fscrypt_err(inode, "Filename decryption failed: %d", res); return res; } oname->len = strnlen(oname->name, iname->len); return 0; } static const char base64url_table[65] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_"; #define FSCRYPT_BASE64URL_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3) /** * fscrypt_base64url_encode() - base64url-encode some binary data * @src: the binary data to encode * @srclen: the length of @src in bytes * @dst: (output) the base64url-encoded string. Not NUL-terminated. * * Encodes data using base64url encoding, i.e. the "Base 64 Encoding with URL * and Filename Safe Alphabet" specified by RFC 4648. '='-padding isn't used, * as it's unneeded and not required by the RFC. base64url is used instead of * base64 to avoid the '/' character, which isn't allowed in filenames. * * Return: the length of the resulting base64url-encoded string in bytes. * This will be equal to FSCRYPT_BASE64URL_CHARS(srclen). */ static int fscrypt_base64url_encode(const u8 *src, int srclen, char *dst) { u32 ac = 0; int bits = 0; int i; char *cp = dst; for (i = 0; i < srclen; i++) { ac = (ac << 8) | src[i]; bits += 8; do { bits -= 6; *cp++ = base64url_table[(ac >> bits) & 0x3f]; } while (bits >= 6); } if (bits) *cp++ = base64url_table[(ac << (6 - bits)) & 0x3f]; return cp - dst; } /** * fscrypt_base64url_decode() - base64url-decode a string * @src: the string to decode. Doesn't need to be NUL-terminated. * @srclen: the length of @src in bytes * @dst: (output) the decoded binary data * * Decodes a string using base64url encoding, i.e. the "Base 64 Encoding with * URL and Filename Safe Alphabet" specified by RFC 4648. '='-padding isn't * accepted, nor are non-encoding characters such as whitespace. * * This implementation hasn't been optimized for performance. * * Return: the length of the resulting decoded binary data in bytes, * or -1 if the string isn't a valid base64url string. */ static int fscrypt_base64url_decode(const char *src, int srclen, u8 *dst) { u32 ac = 0; int bits = 0; int i; u8 *bp = dst; for (i = 0; i < srclen; i++) { const char *p = strchr(base64url_table, src[i]); if (p == NULL || src[i] == 0) return -1; ac = (ac << 6) | (p - base64url_table); bits += 6; if (bits >= 8) { bits -= 8; *bp++ = (u8)(ac >> bits); } } if (ac & ((1 << bits) - 1)) return -1; return bp - dst; } bool fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, u32 orig_len, u32 max_len, u32 *encrypted_len_ret) { int padding = 4 << (fscrypt_policy_flags(policy) & FSCRYPT_POLICY_FLAGS_PAD_MASK); u32 encrypted_len; if (orig_len > max_len) return false; encrypted_len = max(orig_len, (u32)FS_CRYPTO_BLOCK_SIZE); encrypted_len = round_up(encrypted_len, padding); *encrypted_len_ret = min(encrypted_len, max_len); return true; } /** * fscrypt_fname_alloc_buffer() - allocate a buffer for presented filenames * @max_encrypted_len: maximum length of encrypted filenames the buffer will be * used to present * @crypto_str: (output) buffer to allocate * * Allocate a buffer that is large enough to hold any decrypted or encoded * filename (null-terminated), for the given maximum encrypted filename length. * * Return: 0 on success, -errno on failure */ int fscrypt_fname_alloc_buffer(u32 max_encrypted_len, struct fscrypt_str *crypto_str) { u32 max_presented_len = max_t(u32, FSCRYPT_NOKEY_NAME_MAX_ENCODED, max_encrypted_len); crypto_str->name = kmalloc(max_presented_len + 1, GFP_NOFS); if (!crypto_str->name) return -ENOMEM; crypto_str->len = max_presented_len; return 0; } EXPORT_SYMBOL(fscrypt_fname_alloc_buffer); /** * fscrypt_fname_free_buffer() - free a buffer for presented filenames * @crypto_str: the buffer to free * * Free a buffer that was allocated by fscrypt_fname_alloc_buffer(). */ void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) { if (!crypto_str) return; kfree(crypto_str->name); crypto_str->name = NULL; } EXPORT_SYMBOL(fscrypt_fname_free_buffer); /** * fscrypt_fname_disk_to_usr() - convert an encrypted filename to * user-presentable form * @inode: inode of the parent directory (for regular filenames) * or of the symlink (for symlink targets) * @hash: first part of the name's dirhash, if applicable. This only needs to * be provided if the filename is located in an indexed directory whose * encryption key may be unavailable. Not needed for symlink targets. * @minor_hash: second part of the name's dirhash, if applicable * @iname: encrypted filename to convert. May also be "." or "..", which * aren't actually encrypted. * @oname: output buffer for the user-presentable filename. The caller must * have allocated enough space for this, e.g. using * fscrypt_fname_alloc_buffer(). * * If the key is available, we'll decrypt the disk name. Otherwise, we'll * encode it for presentation in fscrypt_nokey_name format. * See struct fscrypt_nokey_name for details. * * Return: 0 on success, -errno on failure */ int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, struct fscrypt_str *oname) { const struct qstr qname = FSTR_TO_QSTR(iname); struct fscrypt_nokey_name nokey_name; u32 size; /* size of the unencoded no-key name */ if (fscrypt_is_dot_dotdot(&qname)) { oname->name[0] = '.'; oname->name[iname->len - 1] = '.'; oname->len = iname->len; return 0; } if (iname->len < FS_CRYPTO_BLOCK_SIZE) return -EUCLEAN; if (fscrypt_has_encryption_key(inode)) return fname_decrypt(inode, iname, oname); /* * Sanity check that struct fscrypt_nokey_name doesn't have padding * between fields and that its encoded size never exceeds NAME_MAX. */ BUILD_BUG_ON(offsetofend(struct fscrypt_nokey_name, dirhash) != offsetof(struct fscrypt_nokey_name, bytes)); BUILD_BUG_ON(offsetofend(struct fscrypt_nokey_name, bytes) != offsetof(struct fscrypt_nokey_name, sha256)); BUILD_BUG_ON(FSCRYPT_NOKEY_NAME_MAX_ENCODED > NAME_MAX); nokey_name.dirhash[0] = hash; nokey_name.dirhash[1] = minor_hash; if (iname->len <= sizeof(nokey_name.bytes)) { memcpy(nokey_name.bytes, iname->name, iname->len); size = offsetof(struct fscrypt_nokey_name, bytes[iname->len]); } else { memcpy(nokey_name.bytes, iname->name, sizeof(nokey_name.bytes)); /* Compute strong hash of remaining part of name. */ sha256(&iname->name[sizeof(nokey_name.bytes)], iname->len - sizeof(nokey_name.bytes), nokey_name.sha256); size = FSCRYPT_NOKEY_NAME_MAX; } oname->len = fscrypt_base64url_encode((const u8 *)&nokey_name, size, oname->name); return 0; } EXPORT_SYMBOL(fscrypt_fname_disk_to_usr); /** * fscrypt_setup_filename() - prepare to search a possibly encrypted directory * @dir: the directory that will be searched * @iname: the user-provided filename being searched for * @lookup: 1 if we're allowed to proceed without the key because it's * ->lookup() or we're finding the dir_entry for deletion; 0 if we cannot * proceed without the key because we're going to create the dir_entry. * @fname: the filename information to be filled in * * Given a user-provided filename @iname, this function sets @fname->disk_name * to the name that would be stored in the on-disk directory entry, if possible. * If the directory is unencrypted this is simply @iname. Else, if we have the * directory's encryption key, then @iname is the plaintext, so we encrypt it to * get the disk_name. * * Else, for keyless @lookup operations, @iname should be a no-key name, so we * decode it to get the struct fscrypt_nokey_name. Non-@lookup operations will * be impossible in this case, so we fail them with ENOKEY. * * If successful, fscrypt_free_filename() must be called later to clean up. * * Return: 0 on success, -errno on failure */ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct fscrypt_name *fname) { struct fscrypt_nokey_name *nokey_name; int ret; memset(fname, 0, sizeof(struct fscrypt_name)); fname->usr_fname = iname; if (!IS_ENCRYPTED(dir) || fscrypt_is_dot_dotdot(iname)) { fname->disk_name.name = (unsigned char *)iname->name; fname->disk_name.len = iname->len; return 0; } ret = fscrypt_get_encryption_info(dir, lookup); if (ret) return ret; if (fscrypt_has_encryption_key(dir)) { if (!fscrypt_fname_encrypted_size(&dir->i_crypt_info->ci_policy, iname->len, dir->i_sb->s_cop->max_namelen, &fname->crypto_buf.len)) return -ENAMETOOLONG; fname->crypto_buf.name = kmalloc(fname->crypto_buf.len, GFP_NOFS); if (!fname->crypto_buf.name) return -ENOMEM; ret = fscrypt_fname_encrypt(dir, iname, fname->crypto_buf.name, fname->crypto_buf.len); if (ret) goto errout; fname->disk_name.name = fname->crypto_buf.name; fname->disk_name.len = fname->crypto_buf.len; return 0; } if (!lookup) return -ENOKEY; fname->is_nokey_name = true; /* * We don't have the key and we are doing a lookup; decode the * user-supplied name */ if (iname->len > FSCRYPT_NOKEY_NAME_MAX_ENCODED) return -ENOENT; fname->crypto_buf.name = kmalloc(FSCRYPT_NOKEY_NAME_MAX, GFP_KERNEL); if (fname->crypto_buf.name == NULL) return -ENOMEM; ret = fscrypt_base64url_decode(iname->name, iname->len, fname->crypto_buf.name); if (ret < (int)offsetof(struct fscrypt_nokey_name, bytes[1]) || (ret > offsetof(struct fscrypt_nokey_name, sha256) && ret != FSCRYPT_NOKEY_NAME_MAX)) { ret = -ENOENT; goto errout; } fname->crypto_buf.len = ret; nokey_name = (void *)fname->crypto_buf.name; fname->hash = nokey_name->dirhash[0]; fname->minor_hash = nokey_name->dirhash[1]; if (ret != FSCRYPT_NOKEY_NAME_MAX) { /* The full ciphertext filename is available. */ fname->disk_name.name = nokey_name->bytes; fname->disk_name.len = ret - offsetof(struct fscrypt_nokey_name, bytes); } return 0; errout: kfree(fname->crypto_buf.name); return ret; } EXPORT_SYMBOL(fscrypt_setup_filename); /** * fscrypt_match_name() - test whether the given name matches a directory entry * @fname: the name being searched for * @de_name: the name from the directory entry * @de_name_len: the length of @de_name in bytes * * Normally @fname->disk_name will be set, and in that case we simply compare * that to the name stored in the directory entry. The only exception is that * if we don't have the key for an encrypted directory and the name we're * looking for is very long, then we won't have the full disk_name and instead * we'll need to match against a fscrypt_nokey_name that includes a strong hash. * * Return: %true if the name matches, otherwise %false. */ bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len) { const struct fscrypt_nokey_name *nokey_name = (const void *)fname->crypto_buf.name; u8 digest[SHA256_DIGEST_SIZE]; if (likely(fname->disk_name.name)) { if (de_name_len != fname->disk_name.len) return false; return !memcmp(de_name, fname->disk_name.name, de_name_len); } if (de_name_len <= sizeof(nokey_name->bytes)) return false; if (memcmp(de_name, nokey_name->bytes, sizeof(nokey_name->bytes))) return false; sha256(&de_name[sizeof(nokey_name->bytes)], de_name_len - sizeof(nokey_name->bytes), digest); return !memcmp(digest, nokey_name->sha256, sizeof(digest)); } EXPORT_SYMBOL_GPL(fscrypt_match_name); /** * fscrypt_fname_siphash() - calculate the SipHash of a filename * @dir: the parent directory * @name: the filename to calculate the SipHash of * * Given a plaintext filename @name and a directory @dir which uses SipHash as * its dirhash method and has had its fscrypt key set up, this function * calculates the SipHash of that name using the directory's secret dirhash key. * * Return: the SipHash of @name using the hash key of @dir */ u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name) { const struct fscrypt_info *ci = dir->i_crypt_info; WARN_ON(!ci->ci_dirhash_key_initialized); return siphash(name->name, name->len, &ci->ci_dirhash_key); } EXPORT_SYMBOL_GPL(fscrypt_fname_siphash); /* * Validate dentries in encrypted directories to make sure we aren't potentially * caching stale dentries after a key has been added. */ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *dir; int err; int valid; /* * Plaintext names are always valid, since fscrypt doesn't support * reverting to no-key names without evicting the directory's inode * -- which implies eviction of the dentries in the directory. */ if (!(dentry->d_flags & DCACHE_NOKEY_NAME)) return 1; /* * No-key name; valid if the directory's key is still unavailable. * * Although fscrypt forbids rename() on no-key names, we still must use * dget_parent() here rather than use ->d_parent directly. That's * because a corrupted fs image may contain directory hard links, which * the VFS handles by moving the directory's dentry tree in the dcache * each time ->lookup() finds the directory and it already has a dentry * elsewhere. Thus ->d_parent can be changing, and we must safely grab * a reference to some ->d_parent to prevent it from being freed. */ if (flags & LOOKUP_RCU) return -ECHILD; dir = dget_parent(dentry); /* * Pass allow_unsupported=true, so that files with an unsupported * encryption policy can be deleted. */ err = fscrypt_get_encryption_info(d_inode(dir), true); valid = !fscrypt_has_encryption_key(d_inode(dir)); dput(dir); if (err < 0) return err; return valid; } EXPORT_SYMBOL_GPL(fscrypt_d_revalidate); |
| 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/if_vlan.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_vlan.h> #include <net/tc_act/tc_vlan.h> static unsigned int vlan_net_id; static struct tc_action_ops act_vlan_ops; static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_vlan *v = to_vlan(a); struct tcf_vlan_params *p; int action; int err; u16 tci; tcf_lastuse_update(&v->tcf_tm); tcf_action_update_bstats(&v->common, skb); /* Ensure 'data' points at mac_header prior calling vlan manipulating * functions. */ if (skb_at_tc_ingress(skb)) skb_push_rcsum(skb, skb->mac_len); action = READ_ONCE(v->tcf_action); p = rcu_dereference_bh(v->vlan_p); switch (p->tcfv_action) { case TCA_VLAN_ACT_POP: err = skb_vlan_pop(skb); if (err) goto drop; break; case TCA_VLAN_ACT_PUSH: err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid | (p->tcfv_push_prio << VLAN_PRIO_SHIFT)); if (err) goto drop; break; case TCA_VLAN_ACT_MODIFY: /* No-op if no vlan tag (either hw-accel or in-payload) */ if (!skb_vlan_tagged(skb)) goto out; /* extract existing tag (and guarantee no hw-accel tag) */ if (skb_vlan_tag_present(skb)) { tci = skb_vlan_tag_get(skb); __vlan_hwaccel_clear_tag(skb); } else { /* in-payload vlan tag, pop it */ err = __skb_vlan_pop(skb, &tci); if (err) goto drop; } /* replace the vid */ tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid; /* replace prio bits, if tcfv_push_prio specified */ if (p->tcfv_push_prio_exists) { tci &= ~VLAN_PRIO_MASK; tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT; } /* put updated tci as hwaccel tag */ __vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci); break; case TCA_VLAN_ACT_POP_ETH: err = skb_eth_pop(skb); if (err) goto drop; break; case TCA_VLAN_ACT_PUSH_ETH: err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src); if (err) goto drop; break; default: BUG(); } out: if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); return action; drop: tcf_action_inc_drop_qstats(&v->common); return TC_ACT_SHOT; } static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = { [TCA_VLAN_UNSPEC] = { .strict_start_type = TCA_VLAN_PUSH_ETH_DST }, [TCA_VLAN_PARMS] = { .len = sizeof(struct tc_vlan) }, [TCA_VLAN_PUSH_VLAN_ID] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PROTOCOL] = { .type = NLA_U16 }, [TCA_VLAN_PUSH_VLAN_PRIORITY] = { .type = NLA_U8 }, [TCA_VLAN_PUSH_ETH_DST] = NLA_POLICY_ETH_ADDR, [TCA_VLAN_PUSH_ETH_SRC] = NLA_POLICY_ETH_ADDR, }; static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_VLAN_MAX + 1]; struct tcf_chain *goto_ch = NULL; bool push_prio_exists = false; struct tcf_vlan_params *p; struct tc_vlan *parm; struct tcf_vlan *v; int action; u16 push_vid = 0; __be16 push_proto = 0; u8 push_prio = 0; bool exists = false; int ret = 0, err; u32 index; if (!nla) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_VLAN_MAX, nla, vlan_policy, NULL); if (err < 0) return err; if (!tb[TCA_VLAN_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_VLAN_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return 0; switch (parm->v_action) { case TCA_VLAN_ACT_POP: break; case TCA_VLAN_ACT_PUSH: case TCA_VLAN_ACT_MODIFY: if (!tb[TCA_VLAN_PUSH_VLAN_ID]) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]); if (push_vid >= VLAN_VID_MASK) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -ERANGE; } if (tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]) { push_proto = nla_get_be16(tb[TCA_VLAN_PUSH_VLAN_PROTOCOL]); switch (push_proto) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): break; default: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EPROTONOSUPPORT; } } else { push_proto = htons(ETH_P_8021Q); } push_prio_exists = !!tb[TCA_VLAN_PUSH_VLAN_PRIORITY]; if (push_prio_exists) push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]); break; case TCA_VLAN_ACT_POP_ETH: break; case TCA_VLAN_ACT_PUSH_ETH: if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } break; default: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } action = parm->v_action; if (!exists) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_vlan_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; v = to_vlan(*a); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) { err = -ENOMEM; goto put_chain; } p->tcfv_action = action; p->tcfv_push_vid = push_vid; p->tcfv_push_prio = push_prio; p->tcfv_push_prio_exists = push_prio_exists || action == TCA_VLAN_ACT_PUSH; p->tcfv_push_proto = push_proto; if (action == TCA_VLAN_ACT_PUSH_ETH) { nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST], ETH_ALEN); nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC], ETH_ALEN); } spin_lock_bh(&v->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock)); spin_unlock_bh(&v->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) kfree_rcu(p, rcu); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static void tcf_vlan_cleanup(struct tc_action *a) { struct tcf_vlan *v = to_vlan(a); struct tcf_vlan_params *p; p = rcu_dereference_protected(v->vlan_p, 1); if (p) kfree_rcu(p, rcu); } static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_vlan *v = to_vlan(a); struct tcf_vlan_params *p; struct tc_vlan opt = { .index = v->tcf_index, .refcnt = refcount_read(&v->tcf_refcnt) - ref, .bindcnt = atomic_read(&v->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&v->tcf_lock); opt.action = v->tcf_action; p = rcu_dereference_protected(v->vlan_p, lockdep_is_held(&v->tcf_lock)); opt.v_action = p->tcfv_action; if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if ((p->tcfv_action == TCA_VLAN_ACT_PUSH || p->tcfv_action == TCA_VLAN_ACT_MODIFY) && (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, p->tcfv_push_proto) || (p->tcfv_push_prio_exists && nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, p->tcfv_push_prio)))) goto nla_put_failure; if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) { if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN, p->tcfv_push_dst)) goto nla_put_failure; if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN, p->tcfv_push_src)) goto nla_put_failure; } tcf_tm_dump(&t, &v->tcf_tm); if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD)) goto nla_put_failure; spin_unlock_bh(&v->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&v->tcf_lock); nlmsg_trim(skb, b); return -1; } static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, vlan_net_id); return tcf_generic_walker(tn, skb, cb, type, ops, extack); } static void tcf_vlan_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_vlan *v = to_vlan(a); struct tcf_t *tm = &v->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, vlan_net_id); return tcf_idr_search(tn, a, index); } static size_t tcf_vlan_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_vlan)) + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */ + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */ + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */ } static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .id = TCA_ID_VLAN, .owner = THIS_MODULE, .act = tcf_vlan_act, .dump = tcf_vlan_dump, .init = tcf_vlan_init, .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, .stats_update = tcf_vlan_stats_update, .get_fill_size = tcf_vlan_get_fill_size, .lookup = tcf_vlan_search, .size = sizeof(struct tcf_vlan), }; static __net_init int vlan_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, vlan_net_id); return tc_action_net_init(net, tn, &act_vlan_ops); } static void __net_exit vlan_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, vlan_net_id); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit_batch = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct tc_action_net), }; static int __init vlan_init_module(void) { return tcf_register_action(&act_vlan_ops, &vlan_net_ops); } static void __exit vlan_cleanup_module(void) { tcf_unregister_action(&act_vlan_ops, &vlan_net_ops); } module_init(vlan_init_module); module_exit(vlan_cleanup_module); MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>"); MODULE_DESCRIPTION("vlan manipulation actions"); MODULE_LICENSE("GPL v2"); |
| 2749 2748 7 140 140 2659 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set. */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS ((slab_flags_t __force)0x00000100U) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U) /* DEBUG: Poison objects */ #define SLAB_POISON ((slab_flags_t __force)0x00000800U) /* Align objs on cache lines */ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC ((slab_flags_t __force)0x00040000U) /* * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * rcu_read_lock() * again: * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * goto again; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * goto again; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ /* Defer freeing slabs to RCU */ #define SLAB_TYPESAFE_BY_RCU ((slab_flags_t __force)0x00080000U) /* Spread some memory over cpuset */ #define SLAB_MEM_SPREAD ((slab_flags_t __force)0x00100000U) /* Trace allocations and frees */ #define SLAB_TRACE ((slab_flags_t __force)0x00200000U) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS ((slab_flags_t __force)0x00400000U) #else # define SLAB_DEBUG_OBJECTS 0 #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE ((slab_flags_t __force)0x00800000U) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB ((slab_flags_t __force)0x02000000U) #else # define SLAB_FAILSLAB 0 #endif /* Account to memcg */ #ifdef CONFIG_MEMCG_KMEM # define SLAB_ACCOUNT ((slab_flags_t __force)0x04000000U) #else # define SLAB_ACCOUNT 0 #endif #ifdef CONFIG_KASAN #define SLAB_KASAN ((slab_flags_t __force)0x08000000U) #else #define SLAB_KASAN 0 #endif /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab deactivation flag */ #define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct mem_cgroup; /* * struct kmem_cache related prototypes */ void __init kmem_cache_init(void); bool slab_is_available(void); extern bool usercopy_fallback; struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); struct kmem_cache *kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ kmem_cache_create(#__struct, sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), NULL) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ kmem_cache_create_usercopy(#__struct, \ sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), \ offsetof(struct __struct, __field), \ sizeof_field(struct __struct, __field), NULL) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); #ifdef CONFIG_PRINTK bool kmem_valid_obj(void *object); void kmem_dump_obj(void *object); #endif #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user); #else static inline void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user) { } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN) #else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN * aligned pointers. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ #ifdef CONFIG_SLAB /* * The largest kmalloc size supported by the SLAB allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is * less than 32 MB. * * WARNING: Its not easy to increase this value since the allocators have * to do various tricks to work around compiler limitations in order to * ensure proper constant folding. */ #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) #define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif #endif #ifdef CONFIG_SLUB /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif #ifdef CONFIG_SLOB /* * SLOB passes all requests larger than one page to the page allocator. * No kmalloc array is necessary since objects of different sizes can * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. * * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP * is for accounted but unreclaimable and non-dma objects. All the other * kmem caches can have both accounted and unaccounted objects. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif #ifndef CONFIG_MEMCG_KMEM KMALLOC_CGROUP = KMALLOC_NORMAL, #else KMALLOC_CGROUP, #endif KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif NR_KMALLOC_TYPES }; #ifndef CONFIG_SLOB extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; /* * Define gfp bits that should not be set for KMALLOC_NORMAL. */ #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ (IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0)) static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for all the relevant flags. */ if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0)) return KMALLOC_NORMAL; /* * At least one of the flags has to be set. Their priorities in * decreasing order are: * 1) __GFP_DMA * 2) __GFP_RECLAIMABLE * 3) __GFP_ACCOUNT */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n * * Note: __kmalloc_index() is compile-time optimized, and not runtime optimized; * typical usage is via kmalloc_index() and therefore evaluated at compile-time. * Callers where !size_is_constant should only be test modules, where runtime * overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab(). */ static __always_inline unsigned int __kmalloc_index(size_t size, bool size_is_constant) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (size <= 4 * 1024 * 1024) return 22; if (size <= 8 * 1024 * 1024) return 23; if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; if ((IS_ENABLED(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 110000) && !IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } #define kmalloc_index(s) __kmalloc_index(s, true) #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *, void *); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); /* * Caller must not use kfree_bulk() on memory not originally allocated * by kmalloc(), because the SLOB allocator cannot handle this. */ static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc(size, flags); } static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) { return kmem_cache_alloc(s, flags); } #endif #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_slab_alignment __malloc; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) { void *ret = kmem_cache_alloc(s, flags); ret = kasan_kmalloc(s, ret, size, flags); return ret; } static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { void *ret = kmem_cache_alloc_node(s, gfpflags, node); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } #endif /* CONFIG_TRACING */ extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { return kmalloc_order(size, flags, order); } #endif static __always_inline void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); return kmalloc_order_trace(size, flags, order); } /** * kmalloc - allocate memory * @size: how many bytes of memory are required. * @flags: the type of memory to allocate. * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * %GFP_HIGHUSER * Allocate memory from high memory on behalf of user. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { #ifndef CONFIG_SLOB unsigned int index; #endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB index = kmalloc_index(size); if (!index) return ZERO_SIZE_PTR; return kmem_cache_alloc_trace( kmalloc_caches[kmalloc_type(flags)][index], flags, size); #endif } return __kmalloc(size, flags); } static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; return kmem_cache_alloc_node_trace( kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif return __kmalloc_node(size, flags, node); } /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc(bytes, flags); return __kmalloc(bytes, flags); } /** * krealloc_array - reallocate memory for an array. * @p: pointer to the memory chunk to reallocate * @new_n: new number of elements to alloc * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ static __must_check inline void * krealloc_array(void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return krealloc(p, bytes, flags); } /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { return kmalloc_array(n, size, flags | __GFP_ZERO); } /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node(bytes, flags, node); return __kmalloc_node(bytes, flags, node); } static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) { return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } #ifdef CONFIG_NUMA extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) #else /* CONFIG_NUMA */ #define kmalloc_node_track_caller(size, flags, node) \ kmalloc_track_caller(size, flags) #endif /* CONFIG_NUMA */ /* * Shortcuts */ static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) { return kmem_cache_alloc(k, flags | __GFP_ZERO); } /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kzalloc(size_t size, gfp_t flags) { return kmalloc(size, flags | __GFP_ZERO); } /** * kzalloc_node - allocate zeroed memory from a particular memory node. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). * @node: memory node from which to allocate */ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags | __GFP_ZERO, node); } unsigned int kmem_cache_size(struct kmem_cache *s); void __init kmem_cache_init_late(void); #if defined(CONFIG_SMP) && defined(CONFIG_SLAB) int slab_prepare_cpu(unsigned int cpu); int slab_dead_cpu(unsigned int cpu); #else #define slab_prepare_cpu NULL #define slab_dead_cpu NULL #endif #endif /* _LINUX_SLAB_H */ |
| 106 106 106 20 20 16 4 22 2 20 22 68 68 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 | // SPDX-License-Identifier: GPL-2.0-or-later /* RxRPC virtual connection handler, common bits. * * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/net.h> #include <linux/skbuff.h> #include "ar-internal.h" /* * Time till a connection expires after last use (in seconds). */ unsigned int __read_mostly rxrpc_connection_expiry = 10 * 60; unsigned int __read_mostly rxrpc_closed_conn_expiry = 10; static void rxrpc_destroy_connection(struct rcu_head *); static void rxrpc_connection_timer(struct timer_list *timer) { struct rxrpc_connection *conn = container_of(timer, struct rxrpc_connection, timer); rxrpc_queue_conn(conn); } /* * allocate a new connection */ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) { struct rxrpc_connection *conn; _enter(""); conn = kzalloc(sizeof(struct rxrpc_connection), gfp); if (conn) { INIT_LIST_HEAD(&conn->cache_link); timer_setup(&conn->timer, &rxrpc_connection_timer, 0); INIT_WORK(&conn->processor, &rxrpc_process_connection); INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); skb_queue_head_init(&conn->rx_queue); conn->security = &rxrpc_no_security; spin_lock_init(&conn->state_lock); conn->debug_id = atomic_inc_return(&rxrpc_debug_id); conn->idle_timestamp = jiffies; } _leave(" = %p{%d}", conn, conn ? conn->debug_id : 0); return conn; } /* * Look up a connection in the cache by protocol parameters. * * If successful, a pointer to the connection is returned, but no ref is taken. * NULL is returned if there is no match. * * When searching for a service call, if we find a peer but no connection, we * return that through *_peer in case we need to create a new service call. * * The caller must be holding the RCU read lock. */ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, struct sk_buff *skb, struct rxrpc_peer **_peer) { struct rxrpc_connection *conn; struct rxrpc_conn_proto k; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct sockaddr_rxrpc srx; struct rxrpc_peer *peer; _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); if (rxrpc_extract_addr_from_skb(&srx, skb) < 0) goto not_found; if (srx.transport.family != local->srx.transport.family && (srx.transport.family == AF_INET && local->srx.transport.family != AF_INET6)) { pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n", srx.transport.family, local->srx.transport.family); goto not_found; } k.epoch = sp->hdr.epoch; k.cid = sp->hdr.cid & RXRPC_CIDMASK; if (rxrpc_to_server(sp)) { /* We need to look up service connections by the full protocol * parameter set. We look up the peer first as an intermediate * step and then the connection from the peer's tree. */ peer = rxrpc_lookup_peer_rcu(local, &srx); if (!peer) goto not_found; *_peer = peer; conn = rxrpc_find_service_conn_rcu(peer, skb); if (!conn || refcount_read(&conn->ref) == 0) goto not_found; _leave(" = %p", conn); return conn; } else { /* Look up client connections by connection ID alone as their * IDs are unique for this machine. */ conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); if (!conn || refcount_read(&conn->ref) == 0) { _debug("no conn"); goto not_found; } if (conn->proto.epoch != k.epoch || conn->params.local != local) goto not_found; peer = conn->params.peer; switch (srx.transport.family) { case AF_INET: if (peer->srx.transport.sin.sin_port != srx.transport.sin.sin_port || peer->srx.transport.sin.sin_addr.s_addr != srx.transport.sin.sin_addr.s_addr) goto not_found; break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: if (peer->srx.transport.sin6.sin6_port != srx.transport.sin6.sin6_port || memcmp(&peer->srx.transport.sin6.sin6_addr, &srx.transport.sin6.sin6_addr, sizeof(struct in6_addr)) != 0) goto not_found; break; #endif default: BUG(); } _leave(" = %p", conn); return conn; } not_found: _leave(" = NULL"); return NULL; } /* * Disconnect a call and clear any channel it occupies when that call * terminates. The caller must hold the channel_lock and must release the * call's ref on the connection. */ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, struct rxrpc_call *call) { struct rxrpc_channel *chan = &conn->channels[call->cid & RXRPC_CHANNELMASK]; _enter("%d,%x", conn->debug_id, call->cid); if (rcu_access_pointer(chan->call) == call) { /* Save the result of the call so that we can repeat it if necessary * through the channel, whilst disposing of the actual call record. */ trace_rxrpc_disconnect_call(call); switch (call->completion) { case RXRPC_CALL_SUCCEEDED: chan->last_seq = call->rx_hard_ack; chan->last_type = RXRPC_PACKET_TYPE_ACK; break; case RXRPC_CALL_LOCALLY_ABORTED: chan->last_abort = call->abort_code; chan->last_type = RXRPC_PACKET_TYPE_ABORT; break; default: chan->last_abort = RX_CALL_DEAD; chan->last_type = RXRPC_PACKET_TYPE_ABORT; break; } /* Sync with rxrpc_conn_retransmit(). */ smp_wmb(); chan->last_call = chan->call_id; chan->call_id = chan->call_counter; rcu_assign_pointer(chan->call, NULL); } _leave(""); } /* * Disconnect a call and clear any channel it occupies when that call * terminates. */ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; call->peer->cong_cwnd = call->cong_cwnd; if (!hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); hlist_del_rcu(&call->error_link); spin_unlock_bh(&call->peer->lock); } if (rxrpc_is_client_call(call)) return rxrpc_disconnect_client_call(conn->bundle, call); spin_lock(&conn->bundle->channel_lock); __rxrpc_disconnect_call(conn, call); spin_unlock(&conn->bundle->channel_lock); set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); conn->idle_timestamp = jiffies; } /* * Kill off a connection. */ void rxrpc_kill_connection(struct rxrpc_connection *conn) { struct rxrpc_net *rxnet = conn->params.local->rxnet; ASSERT(!rcu_access_pointer(conn->channels[0].call) && !rcu_access_pointer(conn->channels[1].call) && !rcu_access_pointer(conn->channels[2].call) && !rcu_access_pointer(conn->channels[3].call)); ASSERT(list_empty(&conn->cache_link)); write_lock(&rxnet->conn_lock); list_del_init(&conn->proc_link); write_unlock(&rxnet->conn_lock); /* Drain the Rx queue. Note that even though we've unpublished, an * incoming packet could still be being added to our Rx queue, so we * will need to drain it again in the RCU cleanup handler. */ rxrpc_purge_queue(&conn->rx_queue); /* Leave final destruction to RCU. The connection processor work item * must carry a ref on the connection to prevent us getting here whilst * it is queued or running. */ call_rcu(&conn->rcu, rxrpc_destroy_connection); } /* * Queue a connection's work processor, getting a ref to pass to the work * queue. */ bool rxrpc_queue_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); int r; if (!__refcount_inc_not_zero(&conn->ref, &r)) return false; if (rxrpc_queue_work(&conn->processor)) trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, r + 1, here); else rxrpc_put_connection(conn); return true; } /* * Note the re-emergence of a connection. */ void rxrpc_see_connection(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); if (conn) { int n = refcount_read(&conn->ref); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here); } } /* * Get a ref on a connection. */ struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); int r; __refcount_inc(&conn->ref, &r); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, r, here); return conn; } /* * Try to get a ref on a connection. */ struct rxrpc_connection * rxrpc_get_connection_maybe(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); int r; if (conn) { if (__refcount_inc_not_zero(&conn->ref, &r)) trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, r + 1, here); else conn = NULL; } return conn; } /* * Set the service connection reap timer. */ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, unsigned long reap_at) { if (rxnet->live) timer_reduce(&rxnet->service_conn_reap_timer, reap_at); } /* * Release a service connection */ void rxrpc_put_service_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); unsigned int debug_id = conn->debug_id; int r; __refcount_dec(&conn->ref, &r); trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, r - 1, here); if (r - 1 == 1) rxrpc_set_service_reap_timer(conn->params.local->rxnet, jiffies + rxrpc_connection_expiry); } /* * destroy a virtual connection */ static void rxrpc_destroy_connection(struct rcu_head *rcu) { struct rxrpc_connection *conn = container_of(rcu, struct rxrpc_connection, rcu); _enter("{%d,u=%d}", conn->debug_id, refcount_read(&conn->ref)); ASSERTCMP(refcount_read(&conn->ref), ==, 0); _net("DESTROY CONN %d", conn->debug_id); del_timer_sync(&conn->timer); rxrpc_purge_queue(&conn->rx_queue); conn->security->clear(conn); key_put(conn->params.key); rxrpc_put_bundle(conn->bundle); rxrpc_put_peer(conn->params.peer); if (atomic_dec_and_test(&conn->params.local->rxnet->nr_conns)) wake_up_var(&conn->params.local->rxnet->nr_conns); rxrpc_put_local(conn->params.local); kfree(conn); _leave(""); } /* * reap dead service connections */ void rxrpc_service_connection_reaper(struct work_struct *work) { struct rxrpc_connection *conn, *_p; struct rxrpc_net *rxnet = container_of(work, struct rxrpc_net, service_conn_reaper); unsigned long expire_at, earliest, idle_timestamp, now; LIST_HEAD(graveyard); _enter(""); now = jiffies; earliest = now + MAX_JIFFY_OFFSET; write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { ASSERTCMP(refcount_read(&conn->ref), >, 0); if (likely(refcount_read(&conn->ref) > 1)) continue; if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) continue; if (rxnet->live && !conn->params.local->dead) { idle_timestamp = READ_ONCE(conn->idle_timestamp); expire_at = idle_timestamp + rxrpc_connection_expiry * HZ; if (conn->params.local->service_closed) expire_at = idle_timestamp + rxrpc_closed_conn_expiry * HZ; _debug("reap CONN %d { u=%d,t=%ld }", conn->debug_id, refcount_read(&conn->ref), (long)expire_at - (long)now); if (time_before(now, expire_at)) { if (time_before(expire_at, earliest)) earliest = expire_at; continue; } } /* The usage count sits at 1 whilst the object is unused on the * list; we reduce that to 0 to make the object unavailable. */ if (!refcount_dec_if_one(&conn->ref)) continue; trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL); if (rxrpc_conn_is_client(conn)) BUG(); else rxrpc_unpublish_service_conn(conn); list_move_tail(&conn->link, &graveyard); } write_unlock(&rxnet->conn_lock); if (earliest != now + MAX_JIFFY_OFFSET) { _debug("reschedule reaper %ld", (long)earliest - (long)now); ASSERT(time_after(earliest, now)); rxrpc_set_service_reap_timer(rxnet, earliest); } while (!list_empty(&graveyard)) { conn = list_entry(graveyard.next, struct rxrpc_connection, link); list_del_init(&conn->link); ASSERTCMP(refcount_read(&conn->ref), ==, 0); rxrpc_kill_connection(conn); } _leave(""); } /* * preemptively destroy all the service connection records rather than * waiting for them to time out */ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) { struct rxrpc_connection *conn, *_p; bool leak = false; _enter(""); atomic_dec(&rxnet->nr_conns); rxrpc_destroy_all_client_connections(rxnet); del_timer_sync(&rxnet->service_conn_reap_timer); rxrpc_queue_work(&rxnet->service_conn_reaper); flush_workqueue(rxrpc_workqueue); write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { pr_err("AF_RXRPC: Leaked conn %p {%d}\n", conn, refcount_read(&conn->ref)); leak = true; } write_unlock(&rxnet->conn_lock); BUG_ON(leak); ASSERT(list_empty(&rxnet->conn_proc_list)); /* We need to wait for the connections to be destroyed by RCU as they * pin things that we still need to get rid of. */ wait_var_event(&rxnet->nr_conns, !atomic_read(&rxnet->nr_conns)); _leave(""); } |
| 693 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_LABELS_H #define _NF_CONNTRACK_LABELS_H #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <linux/types.h> #include <net/net_namespace.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_extend.h> #include <uapi/linux/netfilter/xt_connlabel.h> #define NF_CT_LABELS_MAX_SIZE ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE) struct nf_conn_labels { unsigned long bits[NF_CT_LABELS_MAX_SIZE / sizeof(long)]; }; static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_LABELS return nf_ct_ext_find(ct, NF_CT_EXT_LABELS); #else return NULL; #endif } static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_LABELS struct net *net = nf_ct_net(ct); if (net->ct.labels_used == 0) return NULL; return nf_ct_ext_add(ct, NF_CT_EXT_LABELS, GFP_ATOMIC); #else return NULL; #endif } int nf_connlabels_replace(struct nf_conn *ct, const u32 *data, const u32 *mask, unsigned int words); #ifdef CONFIG_NF_CONNTRACK_LABELS int nf_conntrack_labels_init(void); void nf_conntrack_labels_fini(void); int nf_connlabels_get(struct net *net, unsigned int bit); void nf_connlabels_put(struct net *net); #else static inline int nf_conntrack_labels_init(void) { return 0; } static inline void nf_conntrack_labels_fini(void) {} static inline int nf_connlabels_get(struct net *net, unsigned int bit) { return 0; } static inline void nf_connlabels_put(struct net *net) {} #endif #endif /* _NF_CONNTRACK_LABELS_H */ |
| 417 417 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/pm_qos.h> static inline void device_pm_init_common(struct device *dev) { if (!dev->power.early_init) { spin_lock_init(&dev->power.lock); dev->power.qos = NULL; dev->power.early_init = true; } } #ifdef CONFIG_PM static inline void pm_runtime_early_init(struct device *dev) { dev->power.disable_depth = 1; device_pm_init_common(dev); } extern void pm_runtime_init(struct device *dev); extern void pm_runtime_reinit(struct device *dev); extern void pm_runtime_remove(struct device *dev); extern u64 pm_runtime_active_time(struct device *dev); #define WAKE_IRQ_DEDICATED_ALLOCATED BIT(0) #define WAKE_IRQ_DEDICATED_MANAGED BIT(1) #define WAKE_IRQ_DEDICATED_REVERSE BIT(2) #define WAKE_IRQ_DEDICATED_MASK (WAKE_IRQ_DEDICATED_ALLOCATED | \ WAKE_IRQ_DEDICATED_MANAGED | \ WAKE_IRQ_DEDICATED_REVERSE) #define WAKE_IRQ_DEDICATED_ENABLED BIT(3) struct wake_irq { struct device *dev; unsigned int status; int irq; const char *name; }; extern void dev_pm_arm_wake_irq(struct wake_irq *wirq); extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq); extern void dev_pm_enable_wake_irq_check(struct device *dev, bool can_change_status); extern void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable); extern void dev_pm_enable_wake_irq_complete(struct device *dev); #ifdef CONFIG_PM_SLEEP extern void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq); extern void device_wakeup_detach_irq(struct device *dev); extern void device_wakeup_arm_wake_irqs(void); extern void device_wakeup_disarm_wake_irqs(void); #else static inline void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq) {} static inline void device_wakeup_detach_irq(struct device *dev) { } #endif /* CONFIG_PM_SLEEP */ /* * sysfs.c */ extern int dpm_sysfs_add(struct device *dev); extern void dpm_sysfs_remove(struct device *dev); extern void rpm_sysfs_remove(struct device *dev); extern int wakeup_sysfs_add(struct device *dev); extern void wakeup_sysfs_remove(struct device *dev); extern int pm_qos_sysfs_add_resume_latency(struct device *dev); extern void pm_qos_sysfs_remove_resume_latency(struct device *dev); extern int pm_qos_sysfs_add_flags(struct device *dev); extern void pm_qos_sysfs_remove_flags(struct device *dev); extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev); extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev); extern int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); #else /* CONFIG_PM */ static inline void pm_runtime_early_init(struct device *dev) { device_pm_init_common(dev); } static inline void pm_runtime_init(struct device *dev) {} static inline void pm_runtime_reinit(struct device *dev) {} static inline void pm_runtime_remove(struct device *dev) {} static inline int dpm_sysfs_add(struct device *dev) { return 0; } static inline void dpm_sysfs_remove(struct device *dev) {} static inline int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) { return 0; } #endif #ifdef CONFIG_PM_SLEEP /* kernel/power/main.c */ extern int pm_async_enabled; /* drivers/base/power/main.c */ extern struct list_head dpm_list; /* The active device list */ static inline struct device *to_device(struct list_head *entry) { return container_of(entry, struct device, power.entry); } extern void device_pm_sleep_init(struct device *dev); extern void device_pm_add(struct device *); extern void device_pm_remove(struct device *); extern void device_pm_move_before(struct device *, struct device *); extern void device_pm_move_after(struct device *, struct device *); extern void device_pm_move_last(struct device *); extern void device_pm_check_callbacks(struct device *dev); static inline bool device_pm_initialized(struct device *dev) { return dev->power.in_dpm_list; } /* drivers/base/power/wakeup_stats.c */ extern int wakeup_source_sysfs_add(struct device *parent, struct wakeup_source *ws); extern void wakeup_source_sysfs_remove(struct wakeup_source *ws); extern int pm_wakeup_source_sysfs_add(struct device *parent); #else /* !CONFIG_PM_SLEEP */ static inline void device_pm_sleep_init(struct device *dev) {} static inline void device_pm_add(struct device *dev) {} static inline void device_pm_remove(struct device *dev) { pm_runtime_remove(dev); } static inline void device_pm_move_before(struct device *deva, struct device *devb) {} static inline void device_pm_move_after(struct device *deva, struct device *devb) {} static inline void device_pm_move_last(struct device *dev) {} static inline void device_pm_check_callbacks(struct device *dev) {} static inline bool device_pm_initialized(struct device *dev) { return device_is_registered(dev); } static inline int pm_wakeup_source_sysfs_add(struct device *parent) { return 0; } #endif /* !CONFIG_PM_SLEEP */ static inline void device_pm_init(struct device *dev) { device_pm_init_common(dev); device_pm_sleep_init(dev); pm_runtime_init(dev); } |
| 41 41 39 39 26 26 19 19 26 26 55 1 55 1 55 55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP CUBIC: Binary Increase Congestion control for TCP v2.3 * Home page: * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of CUBIC TCP in * Sangtae Ha, Injong Rhee and Lisong Xu, * "CUBIC: A New TCP-Friendly High-Speed TCP Variant" * in ACM SIGOPS Operating System Review, July 2008. * Available from: * http://netsrv.csc.ncsu.edu/export/cubic_a_new_tcp_2008.pdf * * CUBIC integrates a new slow start algorithm, called HyStart. * The details of HyStart are presented in * Sangtae Ha and Injong Rhee, * "Taming the Elephants: New TCP Slow Start", NCSU TechReport 2008. * Available from: * http://netsrv.csc.ncsu.edu/export/hystart_techreport_2008.pdf * * All testing results are available from: * http://netsrv.csc.ncsu.edu/wiki/index.php/TCP_Testing * * Unless CUBIC is enabled and congestion window is large * this behaves the same as the original Reno. */ #include <linux/mm.h> #include <linux/module.h> #include <linux/math64.h> #include <net/tcp.h> #define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation * max_cwnd = snd_cwnd * beta */ #define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ /* Two methods of hybrid slow start */ #define HYSTART_ACK_TRAIN 0x1 #define HYSTART_DELAY 0x2 /* Number of delay samples for detecting the increase of delay */ #define HYSTART_MIN_SAMPLES 8 #define HYSTART_DELAY_MIN (4000U) /* 4 ms */ #define HYSTART_DELAY_MAX (16000U) /* 16 ms */ #define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) static int fast_convergence __read_mostly = 1; static int beta __read_mostly = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */ static int initial_ssthresh __read_mostly; static int bic_scale __read_mostly = 41; static int tcp_friendliness __read_mostly = 1; static int hystart __read_mostly = 1; static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY; static int hystart_low_window __read_mostly = 16; static int hystart_ack_delta_us __read_mostly = 2000; static u32 cube_rtt_scale __read_mostly; static u32 beta_scale __read_mostly; static u64 cube_factor __read_mostly; /* Note parameters that are used for precomputing scale factors are read-only */ module_param(fast_convergence, int, 0644); MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence"); module_param(beta, int, 0644); MODULE_PARM_DESC(beta, "beta for multiplicative increase"); module_param(initial_ssthresh, int, 0644); MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold"); module_param(bic_scale, int, 0444); MODULE_PARM_DESC(bic_scale, "scale (scaled by 1024) value for bic function (bic_scale/1024)"); module_param(tcp_friendliness, int, 0644); MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness"); module_param(hystart, int, 0644); MODULE_PARM_DESC(hystart, "turn on/off hybrid slow start algorithm"); module_param(hystart_detect, int, 0644); MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms" " 1: packet-train 2: delay 3: both packet-train and delay"); module_param(hystart_low_window, int, 0644); MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start"); module_param(hystart_ack_delta_us, int, 0644); MODULE_PARM_DESC(hystart_ack_delta_us, "spacing between ack's indicating train (usecs)"); /* BIC TCP Parameters */ struct bictcp { u32 cnt; /* increase cwnd by 1 after ACKs */ u32 last_max_cwnd; /* last maximum snd_cwnd */ u32 last_cwnd; /* the last snd_cwnd */ u32 last_time; /* time when updated last_cwnd */ u32 bic_origin_point;/* origin point of bic function */ u32 bic_K; /* time to origin point from the beginning of the current epoch */ u32 delay_min; /* min delay (usec) */ u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ u16 unused; u8 sample_cnt; /* number of samples to decide curr_rtt */ u8 found; /* the exit point is found? */ u32 round_start; /* beginning of each round */ u32 end_seq; /* end_seq of the round */ u32 last_ack; /* last time when the ACK spacing is close */ u32 curr_rtt; /* the minimum rtt of current round */ }; static inline void bictcp_reset(struct bictcp *ca) { memset(ca, 0, offsetof(struct bictcp, unused)); ca->found = 0; } static inline u32 bictcp_clock_us(const struct sock *sk) { return tcp_sk(sk)->tcp_mstamp; } static inline void bictcp_hystart_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); ca->round_start = ca->last_ack = bictcp_clock_us(sk); ca->end_seq = tp->snd_nxt; ca->curr_rtt = ~0U; ca->sample_cnt = 0; } static void cubictcp_init(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); if (hystart) bictcp_hystart_reset(sk); if (!hystart && initial_ssthresh) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); u32 now = tcp_jiffies32; s32 delta; delta = now - tcp_sk(sk)->lsndtime; /* We were application limited (idle) for a while. * Shift epoch_start to keep cwnd growth to cubic curve. */ if (ca->epoch_start && delta > 0) { ca->epoch_start += delta; if (after(ca->epoch_start, now)) ca->epoch_start = now; } return; } } /* calculate the cubic root of x using a table lookup followed by one * Newton-Raphson iteration. * Avg err ~= 0.195% */ static u32 cubic_root(u64 a) { u32 x, b, shift; /* * cbrt(x) MSB values for x MSB values in [0..63]. * Precomputed then refined by hand - Willy Tarreau * * For x in [0..63], * v = cbrt(x << 18) - 1 * cbrt(x) = (v[x] + 10) >> 6 */ static const u8 v[] = { /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118, /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156, /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179, /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199, /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215, /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229, /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242, /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254, }; b = fls64(a); if (b < 7) { /* a in [0..63] */ return ((u32)v[(u32)a] + 35) >> 6; } b = ((b * 84) >> 8) - 1; shift = (a >> (b * 3)); x = ((u32)(((u32)v[shift] + 10) << b)) >> 6; /* * Newton-Raphson iteration * 2 * x = ( 2 * x + a / x ) / 3 * k+1 k k */ x = (2 * x + (u32)div64_u64(a, (u64)x * (u64)(x - 1))); x = ((x * 341) >> 10); return x; } /* * Compute congestion window to use. */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) { u32 delta, bic_target, max_cnt; u64 offs, t; ca->ack_cnt += acked; /* count the number of ACKed packets */ if (ca->last_cwnd == cwnd && (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; /* The CUBIC function can update ca->cnt at most once per jiffy. * On all cwnd reduction events, ca->epoch_start is set to 0, * which will force a recalculation of ca->cnt. */ if (ca->epoch_start && tcp_jiffies32 == ca->last_time) goto tcp_friendliness; ca->last_cwnd = cwnd; ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) { ca->epoch_start = tcp_jiffies32; /* record beginning */ ca->ack_cnt = acked; /* start counting */ ca->tcp_cwnd = cwnd; /* syn with cubic */ if (ca->last_max_cwnd <= cwnd) { ca->bic_K = 0; ca->bic_origin_point = cwnd; } else { /* Compute new K based on * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ) */ ca->bic_K = cubic_root(cube_factor * (ca->last_max_cwnd - cwnd)); ca->bic_origin_point = ca->last_max_cwnd; } } /* cubic function - calc*/ /* calculate c * time^3 / rtt, * while considering overflow in calculation of time^3 * (so time^3 is done by using 64 bit) * and without the support of division of 64bit numbers * (so all divisions are done by using 32 bit) * also NOTE the unit of those veriables * time = (t - K) / 2^bictcp_HZ * c = bic_scale >> 10 * rtt = (srtt >> 3) / HZ * !!! The following code does not have overflow problems, * if the cwnd < 1 million packets !!! */ t = (s32)(tcp_jiffies32 - ca->epoch_start); t += usecs_to_jiffies(ca->delay_min); /* change the unit from HZ to bictcp_HZ */ t <<= BICTCP_HZ; do_div(t, HZ); if (t < ca->bic_K) /* t - K */ offs = ca->bic_K - t; else offs = t - ca->bic_K; /* c/rtt * (t-K)^3 */ delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ); if (t < ca->bic_K) /* below origin*/ bic_target = ca->bic_origin_point - delta; else /* above origin*/ bic_target = ca->bic_origin_point + delta; /* cubic function - calc bictcp_cnt*/ if (bic_target > cwnd) { ca->cnt = cwnd / (bic_target - cwnd); } else { ca->cnt = 100 * cwnd; /* very small increment*/ } /* * The initial growth of cubic function may be too conservative * when the available bandwidth is still unknown. */ if (ca->last_max_cwnd == 0 && ca->cnt > 20) ca->cnt = 20; /* increase cwnd 5% per RTT */ tcp_friendliness: /* TCP Friendly */ if (tcp_friendliness) { u32 scale = beta_scale; delta = (cwnd * scale) >> 3; while (ca->ack_cnt > delta) { /* update tcp cwnd */ ca->ack_cnt -= delta; ca->tcp_cwnd++; } if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */ delta = ca->tcp_cwnd - cwnd; max_cnt = cwnd / delta; if (ca->cnt > max_cnt) ca->cnt = max_cnt; } } /* The maximum rate of cwnd increase CUBIC allows is 1 packet per * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. */ ca->cnt = max(ca->cnt, 2U); } static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); if (!tcp_is_cwnd_limited(sk)) return; if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } bictcp_update(ca, tcp_snd_cwnd(tp), acked); tcp_cong_avoid_ai(tp, ca->cnt, acked); } static u32 cubictcp_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); ca->epoch_start = 0; /* end of epoch */ /* Wmax and fast convergence */ if (tcp_snd_cwnd(tp) < ca->last_max_cwnd && fast_convergence) ca->last_max_cwnd = (tcp_snd_cwnd(tp) * (BICTCP_BETA_SCALE + beta)) / (2 * BICTCP_BETA_SCALE); else ca->last_max_cwnd = tcp_snd_cwnd(tp); return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); } static void cubictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) { bictcp_reset(inet_csk_ca(sk)); bictcp_hystart_reset(sk); } } /* Account for TSO/GRO delays. * Otherwise short RTT flows could get too small ssthresh, since during * slow start we begin with small TSO packets and ca->delay_min would * not account for long aggregation delay when TSO packets get bigger. * Ideally even with a very small RTT we would like to have at least one * TSO packet being sent and received by GRO, and another one in qdisc layer. * We apply another 100% factor because @rate is doubled at this point. * We cap the cushion to 1ms. */ static u32 hystart_ack_delay(struct sock *sk) { unsigned long rate; rate = READ_ONCE(sk->sk_pacing_rate); if (!rate) return 0; return min_t(u64, USEC_PER_MSEC, div64_ul((u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate)); } static void hystart_update(struct sock *sk, u32 delay) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 threshold; if (after(tp->snd_una, ca->end_seq)) bictcp_hystart_reset(sk); if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); /* first detection parameter - ack-train detection */ if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) { ca->last_ack = now; threshold = ca->delay_min + hystart_ack_delay(sk); /* Hystart ack train triggers if we get ack past * ca->delay_min/2. * Pacing might have delayed packets up to RTT/2 * during slow start. */ if (sk->sk_pacing_status == SK_PACING_NONE) threshold >>= 1; if ((s32)(now - ca->round_start) > threshold) { ca->found = 1; pr_debug("hystart_ack_train (%u > %u) delay_min %u (+ ack_delay %u) cwnd %u\n", now - ca->round_start, threshold, ca->delay_min, hystart_ack_delay(sk), tcp_snd_cwnd(tp)); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINDETECT); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINCWND, tcp_snd_cwnd(tp)); tp->snd_ssthresh = tcp_snd_cwnd(tp); } } } if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ if (ca->curr_rtt > delay) ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { ca->found = 1; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYDETECT); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYCWND, tcp_snd_cwnd(tp)); tp->snd_ssthresh = tcp_snd_cwnd(tp); } } } } static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 delay; /* Some calls are for duplicates without timetamps */ if (sample->rtt_us < 0) return; /* Discard delay samples right after fast recovery */ if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) return; delay = sample->rtt_us; if (delay == 0) delay = 1; /* first time call or link delay decreases */ if (ca->delay_min == 0 || ca->delay_min > delay) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ if (!ca->found && tcp_in_slow_start(tp) && hystart && tcp_snd_cwnd(tp) >= hystart_low_window) hystart_update(sk, delay); } static struct tcp_congestion_ops cubictcp __read_mostly = { .init = cubictcp_init, .ssthresh = cubictcp_recalc_ssthresh, .cong_avoid = cubictcp_cong_avoid, .set_state = cubictcp_state, .undo_cwnd = tcp_reno_undo_cwnd, .cwnd_event = cubictcp_cwnd_event, .pkts_acked = cubictcp_acked, .owner = THIS_MODULE, .name = "cubic", }; static int __init cubictcp_register(void) { BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); /* Precompute a bunch of the scaling factors that are used per-packet * based on SRTT of 100ms */ beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3 / (BICTCP_BETA_SCALE - beta); cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */ /* calculate the "K" for (wmax-cwnd) = c/rtt * K^3 * so K = cubic_root( (wmax-cwnd)*rtt/c ) * the unit of K is bictcp_HZ=2^10, not HZ * * c = bic_scale >> 10 * rtt = 100ms * * the following code has been designed and tested for * cwnd < 1 million packets * RTT < 100 seconds * HZ < 1,000,00 (corresponding to 10 nano-second) */ /* 1/c * 2^2*bictcp_HZ * srtt */ cube_factor = 1ull << (10+3*BICTCP_HZ); /* 2^40 */ /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); return tcp_register_congestion_control(&cubictcp); } static void __exit cubictcp_unregister(void) { tcp_unregister_congestion_control(&cubictcp); } module_init(cubictcp_register); module_exit(cubictcp_unregister); MODULE_AUTHOR("Sangtae Ha, Stephen Hemminger"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CUBIC TCP"); MODULE_VERSION("2.3"); |
| 54 54 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_proto_tcp.c: TCP load balancing support for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Julian Anastasov <ja@ssi.bg> * * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> * * Network name space (netns) aware. * Global data moved to netns i.e struct netns_ipvs * tcp_timeouts table has copy per netns in a hash table per * protocol ip_vs_proto_data and is handled by netns */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/kernel.h> #include <linux/ip.h> #include <linux/tcp.h> /* for tcphdr */ #include <net/ip.h> #include <net/tcp.h> /* for csum_tcpudp_magic */ #include <net/ip6_checksum.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/indirect_call_wrapper.h> #include <net/ip_vs.h> static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_service *svc; struct tcphdr _tcph, *th; __be16 _ports[2], *ports = NULL; /* In the event of icmp, we're only guaranteed to have the first 8 * bytes of the transport header, so we only check the rest of the * TCP packet for non-ICMP packets */ if (likely(!ip_vs_iph_icmp(iph))) { th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); if (th) { if (th->rst || !(sysctl_sloppy_tcp(ipvs) || th->syn)) return 1; ports = &th->source; } } else { ports = skb_header_pointer( skb, iph->len, sizeof(_ports), &_ports); } if (!ports) { *verdict = NF_DROP; return 0; } /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ if (likely(!ip_vs_iph_inverse(iph))) svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->daddr, ports[1]); else svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->saddr, ports[0]); if (svc) { int ignored; if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( */ *verdict = NF_DROP; return 0; } /* * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ *cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph); if (!*cpp && ignored <= 0) { if (!ignored) *verdict = ip_vs_leave(svc, skb, pd, iph); else *verdict = NF_DROP; return 0; } } /* NF_ACCEPT */ return 1; } static inline void tcp_fast_csum_update(int af, struct tcphdr *tcph, const union nf_inet_addr *oldip, const union nf_inet_addr *newip, __be16 oldport, __be16 newport) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcph->check = csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldport, newport, ~csum_unfold(tcph->check)))); else #endif tcph->check = csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldport, newport, ~csum_unfold(tcph->check)))); } static inline void tcp_partial_csum_update(int af, struct tcphdr *tcph, const union nf_inet_addr *oldip, const union nf_inet_addr *newip, __be16 oldlen, __be16 newlen) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcph->check = ~csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldlen, newlen, csum_unfold(tcph->check)))); else #endif tcph->check = ~csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldlen, newlen, csum_unfold(tcph->check)))); } INDIRECT_CALLABLE_SCOPE int tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct tcphdr *tcph; unsigned int tcphoff = iph->len; bool payload_csum = false; int oldlen; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ if (!(ret = ip_vs_app_pkt_out(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) oldlen = skb->len - tcphoff; else payload_csum = true; } tcph = (void *)skb_network_header(skb) + tcphoff; tcph->source = cp->vport; /* Adjust TCP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { tcp_partial_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, htons(oldlen), htons(skb->len - tcphoff)); } else if (!payload_csum) { /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ tcph->check = 0; skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) tcph->check = csum_ipv6_magic(&cp->vaddr.in6, &cp->caddr.in6, skb->len - tcphoff, cp->protocol, skb->csum); else #endif tcph->check = csum_tcpudp_magic(cp->vaddr.ip, cp->caddr.ip, skb->len - tcphoff, cp->protocol, skb->csum); skb->ip_summed = CHECKSUM_UNNECESSARY; IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n", pp->name, tcph->check, (char*)&(tcph->check) - (char*)tcph); } return 1; } static int tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct tcphdr *tcph; unsigned int tcphoff = iph->len; bool payload_csum = false; int oldlen; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif oldlen = skb->len - tcphoff; /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, tcphoff + sizeof(*tcph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* * Attempt ip_vs_app call. * It will fix ip_vs_conn and iph ack_seq stuff */ if (!(ret = ip_vs_app_pkt_in(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) oldlen = skb->len - tcphoff; else payload_csum = true; } tcph = (void *)skb_network_header(skb) + tcphoff; tcph->dest = cp->dport; /* * Adjust TCP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { tcp_partial_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, htons(oldlen), htons(skb->len - tcphoff)); } else if (!payload_csum) { /* Only port and addr are changed, do fast csum update */ tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ tcph->check = 0; skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) tcph->check = csum_ipv6_magic(&cp->caddr.in6, &cp->daddr.in6, skb->len - tcphoff, cp->protocol, skb->csum); else #endif tcph->check = csum_tcpudp_magic(cp->caddr.ip, cp->daddr.ip, skb->len - tcphoff, cp->protocol, skb->csum); skb->ip_summed = CHECKSUM_UNNECESSARY; } return 1; } static int tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { unsigned int tcphoff; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) tcphoff = sizeof(struct ipv6hdr); else #endif tcphoff = ip_hdrlen(skb); switch (skb->ip_summed) { case CHECKSUM_NONE: skb->csum = skb_checksum(skb, tcphoff, skb->len - tcphoff, 0); fallthrough; case CHECKSUM_COMPLETE: #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - tcphoff, ipv6_hdr(skb)->nexthdr, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } } else #endif if (csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - tcphoff, ip_hdr(skb)->protocol, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } break; default: /* No need to checksum. */ break; } return 1; } #define TCP_DIR_INPUT 0 #define TCP_DIR_OUTPUT 4 #define TCP_DIR_INPUT_ONLY 8 static const int tcp_state_off[IP_VS_DIR_LAST] = { [IP_VS_DIR_INPUT] = TCP_DIR_INPUT, [IP_VS_DIR_OUTPUT] = TCP_DIR_OUTPUT, [IP_VS_DIR_INPUT_ONLY] = TCP_DIR_INPUT_ONLY, }; /* * Timeout table[state] */ static const int tcp_timeouts[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = 2*HZ, [IP_VS_TCP_S_ESTABLISHED] = 15*60*HZ, [IP_VS_TCP_S_SYN_SENT] = 2*60*HZ, [IP_VS_TCP_S_SYN_RECV] = 1*60*HZ, [IP_VS_TCP_S_FIN_WAIT] = 2*60*HZ, [IP_VS_TCP_S_TIME_WAIT] = 2*60*HZ, [IP_VS_TCP_S_CLOSE] = 10*HZ, [IP_VS_TCP_S_CLOSE_WAIT] = 60*HZ, [IP_VS_TCP_S_LAST_ACK] = 30*HZ, [IP_VS_TCP_S_LISTEN] = 2*60*HZ, [IP_VS_TCP_S_SYNACK] = 120*HZ, [IP_VS_TCP_S_LAST] = 2*HZ, }; static const char *const tcp_state_name_table[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = "NONE", [IP_VS_TCP_S_ESTABLISHED] = "ESTABLISHED", [IP_VS_TCP_S_SYN_SENT] = "SYN_SENT", [IP_VS_TCP_S_SYN_RECV] = "SYN_RECV", [IP_VS_TCP_S_FIN_WAIT] = "FIN_WAIT", [IP_VS_TCP_S_TIME_WAIT] = "TIME_WAIT", [IP_VS_TCP_S_CLOSE] = "CLOSE", [IP_VS_TCP_S_CLOSE_WAIT] = "CLOSE_WAIT", [IP_VS_TCP_S_LAST_ACK] = "LAST_ACK", [IP_VS_TCP_S_LISTEN] = "LISTEN", [IP_VS_TCP_S_SYNACK] = "SYNACK", [IP_VS_TCP_S_LAST] = "BUG!", }; static const bool tcp_state_active_table[IP_VS_TCP_S_LAST] = { [IP_VS_TCP_S_NONE] = false, [IP_VS_TCP_S_ESTABLISHED] = true, [IP_VS_TCP_S_SYN_SENT] = true, [IP_VS_TCP_S_SYN_RECV] = true, [IP_VS_TCP_S_FIN_WAIT] = false, [IP_VS_TCP_S_TIME_WAIT] = false, [IP_VS_TCP_S_CLOSE] = false, [IP_VS_TCP_S_CLOSE_WAIT] = false, [IP_VS_TCP_S_LAST_ACK] = false, [IP_VS_TCP_S_LISTEN] = false, [IP_VS_TCP_S_SYNACK] = true, }; #define sNO IP_VS_TCP_S_NONE #define sES IP_VS_TCP_S_ESTABLISHED #define sSS IP_VS_TCP_S_SYN_SENT #define sSR IP_VS_TCP_S_SYN_RECV #define sFW IP_VS_TCP_S_FIN_WAIT #define sTW IP_VS_TCP_S_TIME_WAIT #define sCL IP_VS_TCP_S_CLOSE #define sCW IP_VS_TCP_S_CLOSE_WAIT #define sLA IP_VS_TCP_S_LAST_ACK #define sLI IP_VS_TCP_S_LISTEN #define sSA IP_VS_TCP_S_SYNACK struct tcp_states_t { int next_state[IP_VS_TCP_S_LAST]; }; static const char * tcp_state_name(int state) { if (state >= IP_VS_TCP_S_LAST) return "ERR!"; return tcp_state_name_table[state] ? tcp_state_name_table[state] : "?"; } static bool tcp_state_active(int state) { if (state >= IP_VS_TCP_S_LAST) return false; return tcp_state_active_table[state]; } static struct tcp_states_t tcp_states[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sSR }}, /* OUTPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSS, sES, sSS, sSR, sSS, sSS, sSS, sSS, sSS, sLI, sSR }}, /*fin*/ {{sTW, sFW, sSS, sTW, sFW, sTW, sCL, sTW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sLA, sES, sES }}, /*rst*/ {{sCL, sCL, sSS, sCL, sCL, sTW, sCL, sCL, sCL, sCL, sCL }}, /* INPUT-ONLY */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; static struct tcp_states_t tcp_states_dos[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }}, /*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sSA }}, /*ack*/ {{sES, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, /* OUTPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSS, sES, sSS, sSA, sSS, sSS, sSS, sSS, sSS, sLI, sSA }}, /*fin*/ {{sTW, sFW, sSS, sTW, sFW, sTW, sCL, sTW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sLA, sES, sES }}, /*rst*/ {{sCL, sCL, sSS, sCL, sCL, sTW, sCL, sCL, sCL, sCL, sCL }}, /* INPUT-ONLY */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSA, sES, sES, sSR, sSA, sSA, sSA, sSA, sSA, sSA, sSA }}, /*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }}, /*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }}, /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; static void tcp_timeout_change(struct ip_vs_proto_data *pd, int flags) { int on = (flags & 1); /* secure_tcp */ /* ** FIXME: change secure_tcp to independent sysctl var ** or make it per-service or per-app because it is valid ** for most if not for all of the applications. Something ** like "capabilities" (flags) for each object. */ pd->tcp_state_table = (on ? tcp_states_dos : tcp_states); } static inline int tcp_state_idx(struct tcphdr *th) { if (th->rst) return 3; if (th->syn) return 0; if (th->fin) return 1; if (th->ack) return 2; return -1; } static inline void set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, struct tcphdr *th) { int state_idx; int new_state = IP_VS_TCP_S_CLOSE; int state_off = tcp_state_off[direction]; /* * Update state offset to INPUT_ONLY if necessary * or delete NO_OUTPUT flag if output packet detected */ if (cp->flags & IP_VS_CONN_F_NOOUTPUT) { if (state_off == TCP_DIR_OUTPUT) cp->flags &= ~IP_VS_CONN_F_NOOUTPUT; else state_off = TCP_DIR_INPUT_ONLY; } if ((state_idx = tcp_state_idx(th)) < 0) { IP_VS_DBG(8, "tcp_state_idx=%d!!!\n", state_idx); goto tcp_state_out; } new_state = pd->tcp_state_table[state_off+state_idx].next_state[cp->state]; tcp_state_out: if (new_state != cp->state) { struct ip_vs_dest *dest = cp->dest; IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] c:%s:%d v:%s:%d " "d:%s:%d state: %s->%s conn->refcnt:%d\n", pd->pp->name, ((state_off == TCP_DIR_OUTPUT) ? "output " : "input "), th->syn ? 'S' : '.', th->fin ? 'F' : '.', th->ack ? 'A' : '.', th->rst ? 'R' : '.', IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport), tcp_state_name(cp->state), tcp_state_name(new_state), refcount_read(&cp->refcnt)); if (dest) { if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && !tcp_state_active(new_state)) { atomic_dec(&dest->activeconns); atomic_inc(&dest->inactconns); cp->flags |= IP_VS_CONN_F_INACTIVE; } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && tcp_state_active(new_state)) { atomic_inc(&dest->activeconns); atomic_dec(&dest->inactconns); cp->flags &= ~IP_VS_CONN_F_INACTIVE; } } if (new_state == IP_VS_TCP_S_ESTABLISHED) ip_vs_control_assure_ct(cp); } if (likely(pd)) cp->timeout = pd->timeout_table[cp->state = new_state]; else /* What to do ? */ cp->timeout = tcp_timeouts[cp->state = new_state]; } /* * Handle state transitions */ static void tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { struct tcphdr _tcph, *th; #ifdef CONFIG_IP_VS_IPV6 int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); #else int ihl = ip_hdrlen(skb); #endif th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph); if (th == NULL) return; spin_lock_bh(&cp->lock); set_tcp_state(pd, cp, direction, th); spin_unlock_bh(&cp->lock); } static inline __u16 tcp_app_hashkey(__be16 port) { return (((__force u16)port >> TCP_APP_TAB_BITS) ^ (__force u16)port) & TCP_APP_TAB_MASK; } static int tcp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); hash = tcp_app_hashkey(port); list_for_each_entry(i, &ipvs->tcp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } list_add_rcu(&inc->p_list, &ipvs->tcp_apps[hash]); atomic_inc(&pd->appcnt); out: return ret; } static void tcp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); } static int tcp_app_conn_bind(struct ip_vs_conn *cp) { struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; /* Default binding: bind app only for NAT */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) return 0; /* Lookup application incarnations and bind the right one */ hash = tcp_app_hashkey(cp->vport); list_for_each_entry_rcu(inc, &ipvs->tcp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", __func__, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), inc->name, ntohs(inc->port)); cp->app = inc; if (inc->init_conn) result = inc->init_conn(inc, cp); break; } } return result; } /* * Set LISTEN timeout. (ip_vs_conn_put will setup timer) */ void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp) { struct ip_vs_proto_data *pd = ip_vs_proto_data_get(cp->ipvs, IPPROTO_TCP); spin_lock_bh(&cp->lock); cp->state = IP_VS_TCP_S_LISTEN; cp->timeout = (pd ? pd->timeout_table[IP_VS_TCP_S_LISTEN] : tcp_timeouts[IP_VS_TCP_S_LISTEN]); spin_unlock_bh(&cp->lock); } /* --------------------------------------------- * timeouts is netns related now. * --------------------------------------------- */ static int __ip_vs_tcp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, sizeof(tcp_timeouts)); if (!pd->timeout_table) return -ENOMEM; pd->tcp_state_table = tcp_states; return 0; } static void __ip_vs_tcp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } struct ip_vs_protocol ip_vs_protocol_tcp = { .name = "TCP", .protocol = IPPROTO_TCP, .num_states = IP_VS_TCP_S_LAST, .dont_defrag = 0, .init = NULL, .exit = NULL, .init_netns = __ip_vs_tcp_init, .exit_netns = __ip_vs_tcp_exit, .register_app = tcp_register_app, .unregister_app = tcp_unregister_app, .conn_schedule = tcp_conn_schedule, .conn_in_get = ip_vs_conn_in_get_proto, .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = tcp_snat_handler, .dnat_handler = tcp_dnat_handler, .state_name = tcp_state_name, .state_transition = tcp_state_transition, .app_conn_bind = tcp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = tcp_timeout_change, }; |
| 166 204 26 152 3 8 124 164 417 410 429 45 22 417 26 55 279 228 228 230 5 11 7 32 35 8 18 10 113 52 53 114 114 96 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 | // SPDX-License-Identifier: GPL-2.0 /* * Convert integer string representation to an integer. * If an integer doesn't fit into specified type, -E is returned. * * Integer starts with optional sign. * kstrtou*() functions do not accept sign "-". * * Radix 0 means autodetection: leading "0x" implies radix 16, * leading "0" implies radix 8, otherwise radix is 10. * Autodetection hints work after optional sign, but not before. * * If -E is returned, result is not touched. */ #include <linux/ctype.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/kstrtox.h> #include <linux/math64.h> #include <linux/types.h> #include <linux/uaccess.h> #include "kstrtox.h" const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) { if (*base == 0) { if (s[0] == '0') { if (_tolower(s[1]) == 'x' && isxdigit(s[2])) *base = 16; else *base = 8; } else *base = 10; } if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x') s += 2; return s; } /* * Convert non-negative integer string representation in explicitly given radix * to an integer. A maximum of max_chars characters will be converted. * * Return number of characters consumed maybe or-ed with overflow bit. * If overflow occurs, result integer (incorrect) is still returned. * * Don't you dare use this function. */ unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *p, size_t max_chars) { unsigned long long res; unsigned int rv; res = 0; rv = 0; while (max_chars--) { unsigned int c = *s; unsigned int lc = c | 0x20; /* don't tolower() this line */ unsigned int val; if ('0' <= c && c <= '9') val = c - '0'; else if ('a' <= lc && lc <= 'f') val = lc - 'a' + 10; else break; if (val >= base) break; /* * Check for overflow only if we are within range of * it in the max base we support (16) */ if (unlikely(res & (~0ull << 60))) { if (res > div_u64(ULLONG_MAX - val, base)) rv |= KSTRTOX_OVERFLOW; } res = res * base + val; rv++; s++; } *p = res; return rv; } unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) { return _parse_integer_limit(s, base, p, INT_MAX); } static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) { unsigned long long _res; unsigned int rv; s = _parse_integer_fixup_radix(s, &base); rv = _parse_integer(s, base, &_res); if (rv & KSTRTOX_OVERFLOW) return -ERANGE; if (rv == 0) return -EINVAL; s += rv; if (*s == '\n') s++; if (*s) return -EINVAL; *res = _res; return 0; } /** * kstrtoull - convert a string to an unsigned long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoull(). Return code must be checked. */ int kstrtoull(const char *s, unsigned int base, unsigned long long *res) { if (s[0] == '+') s++; return _kstrtoull(s, base, res); } EXPORT_SYMBOL(kstrtoull); /** * kstrtoll - convert a string to a long long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoll(). Return code must be checked. */ int kstrtoll(const char *s, unsigned int base, long long *res) { unsigned long long tmp; int rv; if (s[0] == '-') { rv = _kstrtoull(s + 1, base, &tmp); if (rv < 0) return rv; if ((long long)-tmp > 0) return -ERANGE; *res = -tmp; } else { rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if ((long long)tmp < 0) return -ERANGE; *res = tmp; } return 0; } EXPORT_SYMBOL(kstrtoll); /* Internal, do not use. */ int _kstrtoul(const char *s, unsigned int base, unsigned long *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtoul); /* Internal, do not use. */ int _kstrtol(const char *s, unsigned int base, long *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (long)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(_kstrtol); /** * kstrtouint - convert a string to an unsigned int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtoul(). Return code must be checked. */ int kstrtouint(const char *s, unsigned int base, unsigned int *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (unsigned int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtouint); /** * kstrtoint - convert a string to an int * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign or a minus sign. * @base: The number base to use. The maximum supported base is 16. If base is * given as 0, then the base of the string is automatically detected with the * conventional semantics - If it begins with 0x the number will be parsed as a * hexadecimal (case insensitive), if it otherwise begins with 0, it will be * parsed as an octal number. Otherwise it will be parsed as a decimal. * @res: Where to write the result of the conversion on success. * * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. * Preferred over simple_strtol(). Return code must be checked. */ int kstrtoint(const char *s, unsigned int base, int *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (int)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtoint); int kstrtou16(const char *s, unsigned int base, u16 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou16); int kstrtos16(const char *s, unsigned int base, s16 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s16)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos16); int kstrtou8(const char *s, unsigned int base, u8 *res) { unsigned long long tmp; int rv; rv = kstrtoull(s, base, &tmp); if (rv < 0) return rv; if (tmp != (u8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtou8); int kstrtos8(const char *s, unsigned int base, s8 *res) { long long tmp; int rv; rv = kstrtoll(s, base, &tmp); if (rv < 0) return rv; if (tmp != (s8)tmp) return -ERANGE; *res = tmp; return 0; } EXPORT_SYMBOL(kstrtos8); /** * kstrtobool - convert common user inputs into boolean values * @s: input string * @res: result * * This routine returns 0 iff the first character is one of 'Yy1Nn0', or * [oO][NnFf] for "on" and "off". Otherwise it will return -EINVAL. Value * pointed to by res is updated upon finding a match. */ int kstrtobool(const char *s, bool *res) { if (!s) return -EINVAL; switch (s[0]) { case 'y': case 'Y': case '1': *res = true; return 0; case 'n': case 'N': case '0': *res = false; return 0; case 'o': case 'O': switch (s[1]) { case 'n': case 'N': *res = true; return 0; case 'f': case 'F': *res = false; return 0; default: break; } break; default: break; } return -EINVAL; } EXPORT_SYMBOL(kstrtobool); /* * Since "base" would be a nonsense argument, this open-codes the * _from_user helper instead of using the helper macro below. */ int kstrtobool_from_user(const char __user *s, size_t count, bool *res) { /* Longest string needed to differentiate, newline, terminator */ char buf[4]; count = min(count, sizeof(buf) - 1); if (copy_from_user(buf, s, count)) return -EFAULT; buf[count] = '\0'; return kstrtobool(buf, res); } EXPORT_SYMBOL(kstrtobool_from_user); #define kstrto_from_user(f, g, type) \ int f(const char __user *s, size_t count, unsigned int base, type *res) \ { \ /* sign, base 2 representation, newline, terminator */ \ char buf[1 + sizeof(type) * 8 + 1 + 1]; \ \ count = min(count, sizeof(buf) - 1); \ if (copy_from_user(buf, s, count)) \ return -EFAULT; \ buf[count] = '\0'; \ return g(buf, base, res); \ } \ EXPORT_SYMBOL(f) kstrto_from_user(kstrtoull_from_user, kstrtoull, unsigned long long); kstrto_from_user(kstrtoll_from_user, kstrtoll, long long); kstrto_from_user(kstrtoul_from_user, kstrtoul, unsigned long); kstrto_from_user(kstrtol_from_user, kstrtol, long); kstrto_from_user(kstrtouint_from_user, kstrtouint, unsigned int); kstrto_from_user(kstrtoint_from_user, kstrtoint, int); kstrto_from_user(kstrtou16_from_user, kstrtou16, u16); kstrto_from_user(kstrtos16_from_user, kstrtos16, s16); kstrto_from_user(kstrtou8_from_user, kstrtou8, u8); kstrto_from_user(kstrtos8_from_user, kstrtos8, s8); |
| 954 955 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* Copyright (c) 2018, Mellanox Technologies 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 <crypto/aead.h> #include <linux/highmem.h> #include <linux/module.h> #include <linux/netdevice.h> #include <net/dst.h> #include <net/inet_connection_sock.h> #include <net/tcp.h> #include <net/tls.h> #include "trace.h" /* device_offload_lock is used to synchronize tls_dev_add * against NETDEV_DOWN notifications. */ static DECLARE_RWSEM(device_offload_lock); static struct workqueue_struct *destruct_wq __read_mostly; static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); static struct page *dummy_page; static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { kfree(tls_offload_ctx_tx(ctx)); kfree(ctx->tx.rec_seq); kfree(ctx->tx.iv); } if (ctx->rx_conf == TLS_HW) kfree(tls_offload_ctx_rx(ctx)); tls_ctx_free(NULL, ctx); } static void tls_device_tx_del_task(struct work_struct *work) { struct tls_offload_context_tx *offload_ctx = container_of(work, struct tls_offload_context_tx, destruct_work); struct tls_context *ctx = offload_ctx->ctx; struct net_device *netdev = ctx->netdev; netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); dev_put(netdev); ctx->netdev = NULL; tls_device_free_ctx(ctx); } static void tls_device_queue_ctx_destruction(struct tls_context *ctx) { unsigned long flags; bool async_cleanup; spin_lock_irqsave(&tls_device_lock, flags); if (unlikely(!refcount_dec_and_test(&ctx->refcount))) { spin_unlock_irqrestore(&tls_device_lock, flags); return; } list_del(&ctx->list); /* Remove from tls_device_list / tls_device_down_list */ async_cleanup = ctx->netdev && ctx->tx_conf == TLS_HW; if (async_cleanup) { struct tls_offload_context_tx *offload_ctx = tls_offload_ctx_tx(ctx); /* queue_work inside the spinlock * to make sure tls_device_down waits for that work. */ queue_work(destruct_wq, &offload_ctx->destruct_work); } spin_unlock_irqrestore(&tls_device_lock, flags); if (!async_cleanup) tls_device_free_ctx(ctx); } /* We assume that the socket is already connected */ static struct net_device *get_netdev_for_sock(struct sock *sk) { struct dst_entry *dst = sk_dst_get(sk); struct net_device *netdev = NULL; if (likely(dst)) { netdev = netdev_sk_get_lowest_dev(dst->dev, sk); dev_hold(netdev); } dst_release(dst); return netdev; } static void destroy_record(struct tls_record_info *record) { int i; for (i = 0; i < record->num_frags; i++) __skb_frag_unref(&record->frags[i], false); kfree(record); } static void delete_all_records(struct tls_offload_context_tx *offload_ctx) { struct tls_record_info *info, *temp; list_for_each_entry_safe(info, temp, &offload_ctx->records_list, list) { list_del(&info->list); destroy_record(info); } offload_ctx->retransmit_hint = NULL; } static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_record_info *info, *temp; struct tls_offload_context_tx *ctx; u64 deleted_records = 0; unsigned long flags; if (!tls_ctx) return; ctx = tls_offload_ctx_tx(tls_ctx); spin_lock_irqsave(&ctx->lock, flags); info = ctx->retransmit_hint; if (info && !before(acked_seq, info->end_seq)) ctx->retransmit_hint = NULL; list_for_each_entry_safe(info, temp, &ctx->records_list, list) { if (before(acked_seq, info->end_seq)) break; list_del(&info->list); destroy_record(info); deleted_records++; } ctx->unacked_record_sn += deleted_records; spin_unlock_irqrestore(&ctx->lock, flags); } /* At this point, there should be no references on this * socket and no in-flight SKBs associated with this * socket, so it is safe to free all the resources. */ void tls_device_sk_destruct(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); tls_ctx->sk_destruct(sk); if (tls_ctx->tx_conf == TLS_HW) { if (ctx->open_record) destroy_record(ctx->open_record); delete_all_records(ctx); crypto_free_aead(ctx->aead_send); clean_acked_data_disable(inet_csk(sk)); } tls_device_queue_ctx_destruction(tls_ctx); } EXPORT_SYMBOL_GPL(tls_device_sk_destruct); void tls_device_free_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); tls_free_partial_record(sk, tls_ctx); } void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); trace_tls_device_tx_resync_req(sk, got_seq, exp_seq); WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags)); } EXPORT_SYMBOL_GPL(tls_offload_tx_resync_request); static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx, u32 seq) { struct net_device *netdev; struct sk_buff *skb; int err = 0; u8 *rcd_sn; skb = tcp_write_queue_tail(sk); if (skb) TCP_SKB_CB(skb)->eor = 1; rcd_sn = tls_ctx->tx.rec_seq; trace_tls_device_tx_resync_send(sk, seq, rcd_sn); down_read(&device_offload_lock); netdev = tls_ctx->netdev; if (netdev) err = netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, TLS_OFFLOAD_CTX_DIR_TX); up_read(&device_offload_lock); if (err) return; clear_bit_unlock(TLS_TX_SYNC_SCHED, &tls_ctx->flags); } static void tls_append_frag(struct tls_record_info *record, struct page_frag *pfrag, int size) { skb_frag_t *frag; frag = &record->frags[record->num_frags - 1]; if (skb_frag_page(frag) == pfrag->page && skb_frag_off(frag) + skb_frag_size(frag) == pfrag->offset) { skb_frag_size_add(frag, size); } else { ++frag; __skb_frag_set_page(frag, pfrag->page); skb_frag_off_set(frag, pfrag->offset); skb_frag_size_set(frag, size); ++record->num_frags; get_page(pfrag->page); } pfrag->offset += size; record->len += size; } static int tls_push_record(struct sock *sk, struct tls_context *ctx, struct tls_offload_context_tx *offload_ctx, struct tls_record_info *record, int flags) { struct tls_prot_info *prot = &ctx->prot_info; struct tcp_sock *tp = tcp_sk(sk); skb_frag_t *frag; int i; record->end_seq = tp->write_seq + record->len; list_add_tail_rcu(&record->list, &offload_ctx->records_list); offload_ctx->open_record = NULL; if (test_bit(TLS_TX_SYNC_SCHED, &ctx->flags)) tls_device_resync_tx(sk, ctx, tp->write_seq); tls_advance_record_sn(sk, prot, &ctx->tx); for (i = 0; i < record->num_frags; i++) { frag = &record->frags[i]; sg_unmark_end(&offload_ctx->sg_tx_data[i]); sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag), skb_frag_size(frag), skb_frag_off(frag)); sk_mem_charge(sk, skb_frag_size(frag)); get_page(skb_frag_page(frag)); } sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]); /* all ready, send */ return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } static void tls_device_record_close(struct sock *sk, struct tls_context *ctx, struct tls_record_info *record, struct page_frag *pfrag, unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) * if we can't allocate memory now use the dummy page */ if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { dummy_tag_frag.page = dummy_page; dummy_tag_frag.offset = 0; pfrag = &dummy_tag_frag; } tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, struct page_frag *pfrag, size_t prepend_size) { struct tls_record_info *record; skb_frag_t *frag; record = kmalloc(sizeof(*record), GFP_KERNEL); if (!record) return -ENOMEM; frag = &record->frags[0]; __skb_frag_set_page(frag, pfrag->page); skb_frag_off_set(frag, pfrag->offset); skb_frag_size_set(frag, prepend_size); get_page(pfrag->page); pfrag->offset += prepend_size; record->num_frags = 1; record->len = prepend_size; offload_ctx->open_record = record; return 0; } static int tls_do_allocation(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct page_frag *pfrag, size_t prepend_size) { int ret; if (!offload_ctx->open_record) { if (unlikely(!skb_page_frag_refill(prepend_size, pfrag, sk->sk_allocation))) { READ_ONCE(sk->sk_prot)->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return -ENOMEM; } ret = tls_create_new_record(offload_ctx, pfrag, prepend_size); if (ret) return ret; if (pfrag->size > pfrag->offset) return 0; } if (!sk_page_frag_refill(sk, pfrag)) return -ENOMEM; return 0; } static int tls_device_copy_data(void *addr, size_t bytes, struct iov_iter *i) { size_t pre_copy, nocache; pre_copy = ~((unsigned long)addr - 1) & (SMP_CACHE_BYTES - 1); if (pre_copy) { pre_copy = min(pre_copy, bytes); if (copy_from_iter(addr, pre_copy, i) != pre_copy) return -EFAULT; bytes -= pre_copy; addr += pre_copy; } nocache = round_down(bytes, SMP_CACHE_BYTES); if (copy_from_iter_nocache(addr, nocache, i) != nocache) return -EFAULT; bytes -= nocache; addr += nocache; if (bytes && copy_from_iter(addr, bytes, i) != bytes) return -EFAULT; return 0; } static int tls_push_data(struct sock *sk, struct iov_iter *msg_iter, size_t size, int flags, unsigned char record_type) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); struct tls_record_info *record; int tls_push_record_flags; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; bool more = false; bool done = false; int copy, rc = 0; long timeo; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST)) return -EOPNOTSUPP; if (unlikely(sk->sk_err)) return -sk->sk_err; flags |= MSG_SENDPAGE_DECRYPTED; tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (tls_is_partially_sent_record(tls_ctx)) { rc = tls_push_partial_record(sk, tls_ctx, flags); if (rc < 0) return rc; } pfrag = sk_page_frag(sk); /* TLS_HEADER_SIZE is not counted as part of the TLS record, and * we need to leave room for an authentication tag. */ max_open_record_len = TLS_MAX_PAYLOAD_SIZE + prot->prepend_size; do { rc = tls_do_allocation(sk, ctx, pfrag, prot->prepend_size); if (unlikely(rc)) { rc = sk_stream_wait_memory(sk, &timeo); if (!rc) continue; record = ctx->open_record; if (!record) break; handle_error: if (record_type != TLS_RECORD_TYPE_DATA) { /* avoid sending partial * record with type != * application_data */ size = orig_size; destroy_record(record); ctx->open_record = NULL; } else if (record->len > prot->prepend_size) { goto last_record; } break; } record = ctx->open_record; copy = min_t(size_t, size, (pfrag->size - pfrag->offset)); copy = min_t(size_t, copy, (max_open_record_len - record->len)); if (copy) { rc = tls_device_copy_data(page_address(pfrag->page) + pfrag->offset, copy, msg_iter); if (rc) goto handle_error; tls_append_frag(record, pfrag, copy); } size -= copy; if (!size) { last_record: tls_push_record_flags = flags; if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) { more = true; break; } done = true; } if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { tls_device_record_close(sk, tls_ctx, record, pfrag, record_type); rc = tls_push_record(sk, tls_ctx, ctx, record, tls_push_record_flags); if (rc < 0) break; } } while (!done); tls_ctx->pending_open_record_frags = more; if (orig_size - size > 0) rc = orig_size - size; return rc; } int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { unsigned char record_type = TLS_RECORD_TYPE_DATA; struct tls_context *tls_ctx = tls_get_ctx(sk); int rc; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (unlikely(msg->msg_controllen)) { rc = tls_proccess_cmsg(sk, msg, &record_type); if (rc) goto out; } rc = tls_push_data(sk, &msg->msg_iter, size, msg->msg_flags, record_type); out: release_sock(sk); mutex_unlock(&tls_ctx->tx_lock); return rc; } int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter msg_iter; char *kaddr; struct kvec iov; int rc; if (flags & MSG_SENDPAGE_NOTLAST) flags |= MSG_MORE; mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (flags & MSG_OOB) { rc = -EOPNOTSUPP; goto out; } kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size); rc = tls_push_data(sk, &msg_iter, size, flags, TLS_RECORD_TYPE_DATA); kunmap(page); out: release_sock(sk); mutex_unlock(&tls_ctx->tx_lock); return rc; } struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || before(seq, info->end_seq - info->len)) { /* if retransmit_hint is irrelevant start * from the beginning of the list */ info = list_first_entry_or_null(&context->records_list, struct tls_record_info, list); if (!info) return NULL; /* send the start_marker record if seq number is before the * tls offload start marker sequence number. This record is * required to handle TCP packets which are before TLS offload * started. * And if it's not start marker, look if this seq number * belongs to the list. */ if (likely(!tls_record_is_start_marker(info))) { /* we have the first record, get the last record to see * if this seq number belongs to the list. */ last = list_last_entry(&context->records_list, struct tls_record_info, list); if (!between(seq, tls_record_start_seq(info), last->end_seq)) return NULL; } record_sn = context->unacked_record_sn; } /* We just need the _rcu for the READ_ONCE() */ rcu_read_lock(); list_for_each_entry_from_rcu(info, &context->records_list, list) { if (before(seq, info->end_seq)) { if (!context->retransmit_hint || after(info->end_seq, context->retransmit_hint->end_seq)) { context->hint_record_sn = record_sn; context->retransmit_hint = info; } *p_record_sn = record_sn; goto exit_rcu_unlock; } record_sn++; } info = NULL; exit_rcu_unlock: rcu_read_unlock(); return info; } EXPORT_SYMBOL(tls_get_record); static int tls_device_push_pending_record(struct sock *sk, int flags) { struct iov_iter msg_iter; iov_iter_kvec(&msg_iter, WRITE, NULL, 0, 0); return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA); } void tls_device_write_space(struct sock *sk, struct tls_context *ctx) { if (tls_is_partially_sent_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; WARN_ON_ONCE(sk->sk_write_pending); sk->sk_allocation = GFP_ATOMIC; tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_DECRYPTED); sk->sk_allocation = sk_allocation; } } static void tls_device_resync_rx(struct tls_context *tls_ctx, struct sock *sk, u32 seq, u8 *rcd_sn) { struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); struct net_device *netdev; trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type); rcu_read_lock(); netdev = READ_ONCE(tls_ctx->netdev); if (netdev) netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, TLS_OFFLOAD_CTX_DIR_RX); rcu_read_unlock(); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICERESYNC); } static bool tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async, s64 resync_req, u32 *seq, u16 *rcd_delta) { u32 is_async = resync_req & RESYNC_REQ_ASYNC; u32 req_seq = resync_req >> 32; u32 req_end = req_seq + ((resync_req >> 16) & 0xffff); u16 i; *rcd_delta = 0; if (is_async) { /* shouldn't get to wraparound: * too long in async stage, something bad happened */ if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) return false; /* asynchronous stage: log all headers seq such that * req_seq <= seq <= end_seq, and wait for real resync request */ if (before(*seq, req_seq)) return false; if (!after(*seq, req_end) && resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX) resync_async->log[resync_async->loglen++] = *seq; resync_async->rcd_delta++; return false; } /* synchronous stage: check against the logged entries and * proceed to check the next entries if no match was found */ for (i = 0; i < resync_async->loglen; i++) if (req_seq == resync_async->log[i] && atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) { *rcd_delta = resync_async->rcd_delta - i; *seq = req_seq; resync_async->loglen = 0; resync_async->rcd_delta = 0; return true; } resync_async->loglen = 0; resync_async->rcd_delta = 0; if (req_seq == *seq && atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) return true; return false; } void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_rx *rx_ctx; u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE]; u32 sock_data, is_req_pending; struct tls_prot_info *prot; s64 resync_req; u16 rcd_delta; u32 req_seq; if (tls_ctx->rx_conf != TLS_HW) return; if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) return; prot = &tls_ctx->prot_info; rx_ctx = tls_offload_ctx_rx(tls_ctx); memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size); switch (rx_ctx->resync_type) { case TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ: resync_req = atomic64_read(&rx_ctx->resync_req); req_seq = resync_req >> 32; seq += TLS_HEADER_SIZE - 1; is_req_pending = resync_req; if (likely(!is_req_pending) || req_seq != seq || !atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) return; break; case TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT: if (likely(!rx_ctx->resync_nh_do_now)) return; /* head of next rec is already in, note that the sock_inq will * include the currently parsed message when called from parser */ sock_data = tcp_inq(sk); if (sock_data > rcd_len) { trace_tls_device_rx_resync_nh_delay(sk, sock_data, rcd_len); return; } rx_ctx->resync_nh_do_now = 0; seq += rcd_len; tls_bigint_increment(rcd_sn, prot->rec_seq_size); break; case TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC: resync_req = atomic64_read(&rx_ctx->resync_async->req); is_req_pending = resync_req; if (likely(!is_req_pending)) return; if (!tls_device_rx_resync_async(rx_ctx->resync_async, resync_req, &seq, &rcd_delta)) return; tls_bigint_subtract(rcd_sn, rcd_delta); break; } tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn); } static void tls_device_core_ctrl_rx_resync(struct tls_context *tls_ctx, struct tls_offload_context_rx *ctx, struct sock *sk, struct sk_buff *skb) { struct strp_msg *rxm; /* device will request resyncs by itself based on stream scan */ if (ctx->resync_type != TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT) return; /* already scheduled */ if (ctx->resync_nh_do_now) return; /* seen decrypted fragments since last fully-failed record */ if (ctx->resync_nh_reset) { ctx->resync_nh_reset = 0; ctx->resync_nh.decrypted_failed = 1; ctx->resync_nh.decrypted_tgt = TLS_DEVICE_RESYNC_NH_START_IVAL; return; } if (++ctx->resync_nh.decrypted_failed <= ctx->resync_nh.decrypted_tgt) return; /* doing resync, bump the next target in case it fails */ if (ctx->resync_nh.decrypted_tgt < TLS_DEVICE_RESYNC_NH_MAX_IVAL) ctx->resync_nh.decrypted_tgt *= 2; else ctx->resync_nh.decrypted_tgt += TLS_DEVICE_RESYNC_NH_MAX_IVAL; rxm = strp_msg(skb); /* head of next rec is already in, parser will sync for us */ if (tcp_inq(sk) > rxm->full_len) { trace_tls_device_rx_resync_nh_schedule(sk); ctx->resync_nh_do_now = 1; } else { struct tls_prot_info *prot = &tls_ctx->prot_info; u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE]; memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size); tls_bigint_increment(rcd_sn, prot->rec_seq_size); tls_device_resync_rx(tls_ctx, sk, tcp_sk(sk)->copied_seq, rcd_sn); } } static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb) { struct strp_msg *rxm = strp_msg(skb); int err = 0, offset = rxm->offset, copy, nsg, data_len, pos; struct sk_buff *skb_iter, *unused; struct scatterlist sg[1]; char *orig_buf, *buf; orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE, sk->sk_allocation); if (!orig_buf) return -ENOMEM; buf = orig_buf; nsg = skb_cow_data(skb, 0, &unused); if (unlikely(nsg < 0)) { err = nsg; goto free_buf; } sg_init_table(sg, 1); sg_set_buf(&sg[0], buf, rxm->full_len + TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); err = skb_copy_bits(skb, offset, buf, TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); if (err) goto free_buf; /* We are interested only in the decrypted data not the auth */ err = decrypt_skb(sk, skb, sg); if (err != -EBADMSG) goto free_buf; else err = 0; data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE; if (skb_pagelen(skb) > offset) { copy = min_t(int, skb_pagelen(skb) - offset, data_len); if (skb->decrypted) { err = skb_store_bits(skb, offset, buf, copy); if (err) goto free_buf; } offset += copy; buf += copy; } pos = skb_pagelen(skb); skb_walk_frags(skb, skb_iter) { int frag_pos; /* Practically all frags must belong to msg if reencrypt * is needed with current strparser and coalescing logic, * but strparser may "get optimized", so let's be safe. */ if (pos + skb_iter->len <= offset) goto done_with_frag; if (pos >= data_len + rxm->offset) break; frag_pos = offset - pos; copy = min_t(int, skb_iter->len - frag_pos, data_len + rxm->offset - offset); if (skb_iter->decrypted) { err = skb_store_bits(skb_iter, frag_pos, buf, copy); if (err) goto free_buf; } offset += copy; buf += copy; done_with_frag: pos += skb_iter->len; } free_buf: kfree(orig_buf); return err; } int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, struct sk_buff *skb, struct strp_msg *rxm) { struct tls_offload_context_rx *ctx = tls_offload_ctx_rx(tls_ctx); int is_decrypted = skb->decrypted; int is_encrypted = !is_decrypted; struct sk_buff *skb_iter; /* Check if all the data is decrypted already */ skb_walk_frags(skb, skb_iter) { is_decrypted &= skb_iter->decrypted; is_encrypted &= !skb_iter->decrypted; } trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len, tls_ctx->rx.rec_seq, rxm->full_len, is_encrypted, is_decrypted); if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) { if (likely(is_encrypted || is_decrypted)) return is_decrypted; /* After tls_device_down disables the offload, the next SKB will * likely have initial fragments decrypted, and final ones not * decrypted. We need to reencrypt that single SKB. */ return tls_device_reencrypt(sk, skb); } /* Return immediately if the record is either entirely plaintext or * entirely ciphertext. Otherwise handle reencrypt partially decrypted * record. */ if (is_decrypted) { ctx->resync_nh_reset = 1; return is_decrypted; } if (is_encrypted) { tls_device_core_ctrl_rx_resync(tls_ctx, ctx, sk, skb); return 0; } ctx->resync_nh_reset = 1; return tls_device_reencrypt(sk, skb); } static void tls_device_attach(struct tls_context *ctx, struct sock *sk, struct net_device *netdev) { if (sk->sk_destruct != tls_device_sk_destruct) { refcount_set(&ctx->refcount, 1); dev_hold(netdev); ctx->netdev = netdev; spin_lock_irq(&tls_device_lock); list_add_tail(&ctx->list, &tls_device_list); spin_unlock_irq(&tls_device_lock); ctx->sk_destruct = sk->sk_destruct; smp_store_release(&sk->sk_destruct, tls_device_sk_destruct); } } int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) { u16 nonce_size, tag_size, iv_size, rec_seq_size, salt_size; struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_prot_info *prot = &tls_ctx->prot_info; struct tls_record_info *start_marker_record; struct tls_offload_context_tx *offload_ctx; struct tls_crypto_info *crypto_info; struct net_device *netdev; char *iv, *rec_seq; struct sk_buff *skb; __be64 rcd_sn; int rc; if (!ctx) return -EINVAL; if (ctx->priv_ctx_tx) return -EEXIST; start_marker_record = kmalloc(sizeof(*start_marker_record), GFP_KERNEL); if (!start_marker_record) return -ENOMEM; offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_TX, GFP_KERNEL); if (!offload_ctx) { rc = -ENOMEM; goto free_marker_record; } crypto_info = &ctx->crypto_send.info; if (crypto_info->version != TLS_1_2_VERSION) { rc = -EOPNOTSUPP; goto free_offload_ctx; } switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE; iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv; rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE; salt_size = TLS_CIPHER_AES_GCM_128_SALT_SIZE; rec_seq = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq; break; default: rc = -EINVAL; goto free_offload_ctx; } /* Sanity-check the rec_seq_size for stack allocations */ if (rec_seq_size > TLS_MAX_REC_SEQ_SIZE) { rc = -EINVAL; goto free_offload_ctx; } prot->version = crypto_info->version; prot->cipher_type = crypto_info->cipher_type; prot->prepend_size = TLS_HEADER_SIZE + nonce_size; prot->tag_size = tag_size; prot->overhead_size = prot->prepend_size + prot->tag_size; prot->iv_size = iv_size; prot->salt_size = salt_size; ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, GFP_KERNEL); if (!ctx->tx.iv) { rc = -ENOMEM; goto free_offload_ctx; } memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); prot->rec_seq_size = rec_seq_size; ctx->tx.rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL); if (!ctx->tx.rec_seq) { rc = -ENOMEM; goto free_iv; } rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info); if (rc) goto free_rec_seq; /* start at rec_seq - 1 to account for the start marker record */ memcpy(&rcd_sn, ctx->tx.rec_seq, sizeof(rcd_sn)); offload_ctx->unacked_record_sn = be64_to_cpu(rcd_sn) - 1; start_marker_record->end_seq = tcp_sk(sk)->write_seq; start_marker_record->len = 0; start_marker_record->num_frags = 0; INIT_WORK(&offload_ctx->destruct_work, tls_device_tx_del_task); offload_ctx->ctx = ctx; INIT_LIST_HEAD(&offload_ctx->records_list); list_add_tail(&start_marker_record->list, &offload_ctx->records_list); spin_lock_init(&offload_ctx->lock); sg_init_table(offload_ctx->sg_tx_data, ARRAY_SIZE(offload_ctx->sg_tx_data)); clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked); ctx->push_pending_record = tls_device_push_pending_record; /* TLS offload is greatly simplified if we don't send * SKBs where only part of the payload needs to be encrypted. * So mark the last skb in the write queue as end of record. */ skb = tcp_write_queue_tail(sk); if (skb) TCP_SKB_CB(skb)->eor = 1; netdev = get_netdev_for_sock(sk); if (!netdev) { pr_err_ratelimited("%s: netdev not found\n", __func__); rc = -EINVAL; goto disable_cad; } if (!(netdev->features & NETIF_F_HW_TLS_TX)) { rc = -EOPNOTSUPP; goto release_netdev; } /* Avoid offloading if the device is down * We don't want to offload new flows after * the NETDEV_DOWN event * * device_offload_lock is taken in tls_devices's NETDEV_DOWN * handler thus protecting from the device going down before * ctx was added to tls_device_list. */ down_read(&device_offload_lock); if (!(netdev->flags & IFF_UP)) { rc = -EINVAL; goto release_lock; } ctx->priv_ctx_tx = offload_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, &ctx->crypto_send.info, tcp_sk(sk)->write_seq); trace_tls_device_offload_set(sk, TLS_OFFLOAD_CTX_DIR_TX, tcp_sk(sk)->write_seq, rec_seq, rc); if (rc) goto release_lock; tls_device_attach(ctx, sk, netdev); up_read(&device_offload_lock); /* following this assignment tls_is_sk_tx_device_offloaded * will return true and the context might be accessed * by the netdev's xmit function. */ smp_store_release(&sk->sk_validate_xmit_skb, tls_validate_xmit_skb); dev_put(netdev); return 0; release_lock: up_read(&device_offload_lock); release_netdev: dev_put(netdev); disable_cad: clean_acked_data_disable(inet_csk(sk)); crypto_free_aead(offload_ctx->aead_send); free_rec_seq: kfree(ctx->tx.rec_seq); free_iv: kfree(ctx->tx.iv); free_offload_ctx: kfree(offload_ctx); ctx->priv_ctx_tx = NULL; free_marker_record: kfree(start_marker_record); return rc; } int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) { struct tls12_crypto_info_aes_gcm_128 *info; struct tls_offload_context_rx *context; struct net_device *netdev; int rc = 0; if (ctx->crypto_recv.info.version != TLS_1_2_VERSION) return -EOPNOTSUPP; netdev = get_netdev_for_sock(sk); if (!netdev) { pr_err_ratelimited("%s: netdev not found\n", __func__); return -EINVAL; } if (!(netdev->features & NETIF_F_HW_TLS_RX)) { rc = -EOPNOTSUPP; goto release_netdev; } /* Avoid offloading if the device is down * We don't want to offload new flows after * the NETDEV_DOWN event * * device_offload_lock is taken in tls_devices's NETDEV_DOWN * handler thus protecting from the device going down before * ctx was added to tls_device_list. */ down_read(&device_offload_lock); if (!(netdev->flags & IFF_UP)) { rc = -EINVAL; goto release_lock; } context = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_RX, GFP_KERNEL); if (!context) { rc = -ENOMEM; goto release_lock; } context->resync_nh_reset = 1; ctx->priv_ctx_rx = context; rc = tls_set_sw_offload(sk, ctx, 0); if (rc) goto release_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, &ctx->crypto_recv.info, tcp_sk(sk)->copied_seq); info = (void *)&ctx->crypto_recv.info; trace_tls_device_offload_set(sk, TLS_OFFLOAD_CTX_DIR_RX, tcp_sk(sk)->copied_seq, info->rec_seq, rc); if (rc) goto free_sw_resources; tls_device_attach(ctx, sk, netdev); up_read(&device_offload_lock); dev_put(netdev); return 0; free_sw_resources: up_read(&device_offload_lock); tls_sw_free_resources_rx(sk); down_read(&device_offload_lock); release_ctx: ctx->priv_ctx_rx = NULL; release_lock: up_read(&device_offload_lock); release_netdev: dev_put(netdev); return rc; } void tls_device_offload_cleanup_rx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct net_device *netdev; down_read(&device_offload_lock); netdev = tls_ctx->netdev; if (!netdev) goto out; netdev->tlsdev_ops->tls_dev_del(netdev, tls_ctx, TLS_OFFLOAD_CTX_DIR_RX); if (tls_ctx->tx_conf != TLS_HW) { dev_put(netdev); tls_ctx->netdev = NULL; } else { set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags); } out: up_read(&device_offload_lock); tls_sw_release_resources_rx(sk); } static int tls_device_down(struct net_device *netdev) { struct tls_context *ctx, *tmp; unsigned long flags; LIST_HEAD(list); /* Request a write lock to block new offload attempts */ down_write(&device_offload_lock); spin_lock_irqsave(&tls_device_lock, flags); list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) { if (ctx->netdev != netdev || !refcount_inc_not_zero(&ctx->refcount)) continue; list_move(&ctx->list, &list); } spin_unlock_irqrestore(&tls_device_lock, flags); list_for_each_entry_safe(ctx, tmp, &list, list) { /* Stop offloaded TX and switch to the fallback. * tls_is_sk_tx_device_offloaded will return false. */ WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw); /* Stop the RX and TX resync. * tls_dev_resync must not be called after tls_dev_del. */ WRITE_ONCE(ctx->netdev, NULL); /* Start skipping the RX resync logic completely. */ set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags); /* Sync with inflight packets. After this point: * TX: no non-encrypted packets will be passed to the driver. * RX: resync requests from the driver will be ignored. */ synchronize_net(); /* Release the offload context on the driver side. */ if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); if (ctx->rx_conf == TLS_HW && !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); dev_put(netdev); /* Move the context to a separate list for two reasons: * 1. When the context is deallocated, list_del is called. * 2. It's no longer an offloaded context, so we don't want to * run offload-specific code on this context. */ spin_lock_irqsave(&tls_device_lock, flags); list_move_tail(&ctx->list, &tls_device_down_list); spin_unlock_irqrestore(&tls_device_lock, flags); /* Device contexts for RX and TX will be freed in on sk_destruct * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. * Now release the ref taken above. */ if (refcount_dec_and_test(&ctx->refcount)) { /* sk_destruct ran after tls_device_down took a ref, and * it returned early. Complete the destruction here. */ list_del(&ctx->list); tls_device_free_ctx(ctx); } } up_write(&device_offload_lock); flush_workqueue(destruct_wq); return NOTIFY_DONE; } static int tls_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (!dev->tlsdev_ops && !(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX))) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_FEAT_CHANGE: if (netif_is_bond_master(dev)) return NOTIFY_DONE; if ((dev->features & NETIF_F_HW_TLS_RX) && !dev->tlsdev_ops->tls_dev_resync) return NOTIFY_BAD; if (dev->tlsdev_ops && dev->tlsdev_ops->tls_dev_add && dev->tlsdev_ops->tls_dev_del) return NOTIFY_DONE; else return NOTIFY_BAD; case NETDEV_DOWN: return tls_device_down(dev); } return NOTIFY_DONE; } static struct notifier_block tls_dev_notifier = { .notifier_call = tls_dev_event, }; int __init tls_device_init(void) { int err; dummy_page = alloc_page(GFP_KERNEL); if (!dummy_page) return -ENOMEM; destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); if (!destruct_wq) { err = -ENOMEM; goto err_free_dummy; } err = register_netdevice_notifier(&tls_dev_notifier); if (err) goto err_destroy_wq; return 0; err_destroy_wq: destroy_workqueue(destruct_wq); err_free_dummy: put_page(dummy_page); return err; } void __exit tls_device_cleanup(void) { unregister_netdevice_notifier(&tls_dev_notifier); flush_workqueue(destruct_wq); destroy_workqueue(destruct_wq); clean_acked_data_flush(); put_page(dummy_page); } |
| 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | // SPDX-License-Identifier: GPL-2.0-or-later /* RxRPC key management * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * RxRPC keys should have a description of describing their purpose: * "afs@CAMBRIDGE.REDHAT.COM> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/skcipher.h> #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/key-type.h> #include <linux/ctype.h> #include <linux/slab.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <keys/rxrpc-type.h> #include <keys/user-type.h> #include "ar-internal.h" static int rxrpc_vet_description_s(const char *); static int rxrpc_preparse_s(struct key_preparsed_payload *); static void rxrpc_free_preparse_s(struct key_preparsed_payload *); static void rxrpc_destroy_s(struct key *); static void rxrpc_describe_s(const struct key *, struct seq_file *); /* * rxrpc server keys take "<serviceId>:<securityIndex>[:<sec-specific>]" as the * description and the key material as the payload. */ struct key_type key_type_rxrpc_s = { .name = "rxrpc_s", .flags = KEY_TYPE_NET_DOMAIN, .vet_description = rxrpc_vet_description_s, .preparse = rxrpc_preparse_s, .free_preparse = rxrpc_free_preparse_s, .instantiate = generic_key_instantiate, .destroy = rxrpc_destroy_s, .describe = rxrpc_describe_s, }; /* * Vet the description for an RxRPC server key. */ static int rxrpc_vet_description_s(const char *desc) { unsigned long service, sec_class; char *p; service = simple_strtoul(desc, &p, 10); if (*p != ':' || service > 65535) return -EINVAL; sec_class = simple_strtoul(p + 1, &p, 10); if ((*p && *p != ':') || sec_class < 1 || sec_class > 255) return -EINVAL; return 0; } /* * Preparse a server secret key. */ static int rxrpc_preparse_s(struct key_preparsed_payload *prep) { const struct rxrpc_security *sec; unsigned int service, sec_class; int n; _enter("%zu", prep->datalen); if (!prep->orig_description) return -EINVAL; if (sscanf(prep->orig_description, "%u:%u%n", &service, &sec_class, &n) != 2) return -EINVAL; sec = rxrpc_security_lookup(sec_class); if (!sec) return -ENOPKG; prep->payload.data[1] = (struct rxrpc_security *)sec; if (!sec->preparse_server_key) return -EINVAL; return sec->preparse_server_key(prep); } static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep) { const struct rxrpc_security *sec = prep->payload.data[1]; if (sec && sec->free_preparse_server_key) sec->free_preparse_server_key(prep); } static void rxrpc_destroy_s(struct key *key) { const struct rxrpc_security *sec = key->payload.data[1]; if (sec && sec->destroy_server_key) sec->destroy_server_key(key); } static void rxrpc_describe_s(const struct key *key, struct seq_file *m) { const struct rxrpc_security *sec = key->payload.data[1]; seq_puts(m, key->description); if (sec && sec->describe_server_key) sec->describe_server_key(key, m); } /* * grab the security keyring for a server socket */ int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen) { struct key *key; char *description; _enter(""); if (optlen <= 0 || optlen > PAGE_SIZE - 1) return -EINVAL; description = memdup_sockptr_nul(optval, optlen); if (IS_ERR(description)) return PTR_ERR(description); key = request_key(&key_type_keyring, description, NULL); if (IS_ERR(key)) { kfree(description); _leave(" = %ld", PTR_ERR(key)); return PTR_ERR(key); } rx->securities = key; kfree(description); _leave(" = 0 [key %x]", key->serial); return 0; } |
| 7 7 2 2 7 7 7 829 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 3 7 7 7 7 7 7 7 7 7 7 7 7 7 7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); mark_page_accessed(bh->b_page); } EXPORT_SYMBOL(touch_buffer); void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* * Returns if the page has dirty or writeback buffers. If all the buffers * are unlocked and clean then the PageDirty information is stale. If * any of the pages are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) return; if (PageWriteback(page)) *writeback = true; head = page_buffers(page); bh = head; do { if (buffer_locked(bh)) *writeback = true; if (buffer_dirty(bh)) *dirty = true; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(buffer_check_dirty_writeback); /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); static void buffer_io_error(struct buffer_head *bh, char *msg) { if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR "Buffer I/O error on dev %pg, logical block %llu%s\n", bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. This is what ll_rw_block uses too. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { __end_buffer_read_notouch(bh, uptodate); put_bh(bh); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } EXPORT_SYMBOL(end_buffer_write_sync); /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's * private_lock. * * Hack idea: for the blockdev mapping, private_lock contention * may be quite high. This code could TryLock the page, and if that * succeeds, there is no need to take private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; struct page *page; int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; spin_lock(&bd_mapping->private_lock); if (!page_has_buffers(page)) goto out_unlock; head = page_buffers(page); bh = head; do { if (!buffer_mapped(bh)) all_mapped = 0; else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } bh = bh->b_this_page; } while (bh != head); /* we might be here because some of the buffers on this page are * not mapped. This is due to various races between * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); if (all_mapped && __ratelimit(&last_warned)) { printk("__find_get_block_slow() failed. block=%llu, " "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " "device %pg blocksize: %d\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); put_page(page); out: return ret; } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct page *page; int page_uptodate = 1; BUG_ON(!buffer_async_read(bh)); page = bh->b_page; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); SetPageError(page); } /* * Be _very_ careful from here on. Bad things can happen if * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ first = page_buffers(page); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) page_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); spin_unlock_irqrestore(&first->b_uptodate_lock, flags); /* * If none of the buffers had errors and they are all * uptodate then we can set the page uptodate. */ if (page_uptodate && !PageError(page)) SetPageUptodate(page); unlock_page(page); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } struct decrypt_bh_ctx { struct work_struct work; struct buffer_head *bh; }; static void decrypt_bh(struct work_struct *work) { struct decrypt_bh_ctx *ctx = container_of(work, struct decrypt_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size, bh_offset(bh)); end_buffer_async_read(bh, err == 0); kfree(ctx); } /* * I/O completion handler for block_read_full_page() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { /* Decrypt if needed */ if (uptodate && fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) { struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { INIT_WORK(&ctx->work, decrypt_bh); ctx->bh = bh; fscrypt_enqueue_decrypt_work(&ctx->work); return; } uptodate = 0; } end_buffer_async_read(bh, uptodate); } /* * Completion handler for block_write_full_page() - pages which are unlocked * during I/O, and which have PageWriteback cleared upon I/O completion. */ void end_buffer_async_write(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct page *page; BUG_ON(!buffer_async_write(bh)); page = bh->b_page; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } first = page_buffers(page); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; while (tmp != bh) { if (buffer_async_write(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); end_page_writeback(page); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } EXPORT_SYMBOL(end_buffer_async_write); /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { bh->b_end_io = handler; set_buffer_async_write(bh); } void mark_buffer_async_write(struct buffer_head *bh) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } EXPORT_SYMBOL(mark_buffer_async_write); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. * So the locking for private_list is via the private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, * mapping->private_lock does *not* protect mapping->private_list! In fact, * mapping->private_list will always be protected by the backing blockdev's * ->private_lock. * * Which introduces a requirement: all buffers on an address_space's * ->private_list must be from the same address_space: the blockdev's. * * address_spaces which do not place buffers at ->private_list via these * utility functions are free to use private_lock and private_list for * whatever they want. The only requirement is that list_empty(private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The * filesystems should do that. invalidate_inode_buffers() should just go * BUG_ON(!list_empty). * * FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should * take an address_space, not an inode. And it should be called * mark_buffer_dirty_fsync() to clearly define why those buffers are being * queued up. * * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the * list if it is already on a list. Because if the buffer is on a list, * it *must* already be on the right one. If not, the filesystem is being * silly. This will save a ton of locking. But first we have to ensure * that buffers are taken *off* the old inode's list when they are freed * (presumably in truncate). That requires careful auditing of all * filesystems (do it inside bforget()). It could also be done by bringing * b_inode back. */ /* * The buffer's backing address_space's private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) { return !list_empty(&inode->i_data.private_list); } /* * osync is designed to support O_SYNC io. It waits synchronously for * all already-submitted IO to complete, but does not queue any new * writes to the disk. * * To do O_SYNC writes, just queue the buffer writes with ll_rw_block as * you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head *p; int err = 0; spin_lock(lock); repeat: list_for_each_prev(p, list) { bh = BH_ENTRY(p); if (buffer_locked(bh)) { get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); goto repeat; } } spin_unlock(lock); return err; } void emergency_thaw_bdev(struct super_block *sb) { while (sb->s_bdev && !thaw_bdev(sb->s_bdev)) printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev); } /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). * @mapping is a file or directory which needs those buffers to be written for * a successful fsync(). */ int sync_mapping_buffers(struct address_space *mapping) { struct address_space *buffer_mapping = mapping->private_data; if (buffer_mapping == NULL || list_empty(&mapping->private_list)) return 0; return fsync_buffers_list(&buffer_mapping->private_lock, &mapping->private_list); } EXPORT_SYMBOL(sync_mapping_buffers); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) ll_rw_block(REQ_OP_WRITE, 0, 1, &bh); put_bh(bh); } } void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; struct address_space *buffer_mapping = bh->b_page->mapping; mark_buffer_dirty(bh); if (!mapping->private_data) { mapping->private_data = buffer_mapping; } else { BUG_ON(mapping->private_data != buffer_mapping); } if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->private_list); bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); /* * Add a page to the dirty page list. * * It is a sad fact of life that this function is called from several places * deeply under spinlocking. It may not sleep. * * If the page has buffers, the uptodate buffers are set dirty, to preserve * dirty-state coherency between the page and the buffers. It the page does * not have buffers then when they are later attached they will all be set * dirty. * * The buffers are dirtied before the page is dirtied. There's a small race * window in which a writepage caller may see the page cleanness but not the * buffer dirtiness. That's fine. If this code were to set the page dirty * before the buffers, a concurrent writepage caller could clear the page dirty * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean * page on the dirty page list. * * We use private_lock to lock against try_to_free_buffers while using the * page's buffer list. Also use this to protect against clean buffers being * added to the page after it was set dirty. * * FIXME: may need to call ->reservepage here as well. That's rather up to the * address_space though. */ int __set_page_dirty_buffers(struct page *page) { int newly_dirty; struct address_space *mapping = page_mapping(page); if (unlikely(!mapping)) return !TestSetPageDirty(page); spin_lock(&mapping->private_lock); if (page_has_buffers(page)) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; do { set_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); } /* * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ lock_page_memcg(page); newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); if (newly_dirty) __set_page_dirty(page, mapping, 1); unlock_page_memcg(page); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } EXPORT_SYMBOL(__set_page_dirty_buffers); /* * Write out and wait upon a list of buffers. * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. * * During this second stage, any subsequent updates to the file may end * up refiling the buffer on the original inode's dirty list again, so * there is a chance we will end up with a buffer queued for write but * not yet completed on that list. So, as a final cleanup we go through * the osync code to catch these locked, dirty buffers without requeuing * any newly dirty buffers for write. */ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head tmp; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; INIT_LIST_HEAD(&tmp); blk_start_plug(&plug); spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); bh->b_assoc_map = mapping; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(lock); /* * Ensure any pending I/O completes so that * write_dirty_buffer() actually writes the * current contents - it is a noop if I/O is * still in flight on potentially older * contents. */ write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note * that we will not run the very last mapping, * wait_on_buffer() will do that for us * through sync_buffer(). */ brelse(bh); spin_lock(lock); } } } spin_unlock(lock); blk_finish_plug(&plug); spin_lock(lock); while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, &mapping->private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); } spin_unlock(lock); err2 = osync_buffers_list(lock, list); if (err) return err; else return err2; } /* * Invalidate any and all dirty buffers on a given inode. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * * NOTE: we take the inode's blockdev's mapping's private_lock. Which * assumes that all the buffers are against the blockdev. Not true * for reiserfs. */ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); spin_unlock(&buffer_mapping->private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); /* * Remove any clean buffers from the inode's buffer list. This is called * when we're trying to free the inode itself. Those buffers can pin it. * * Returns true if all buffers were removed. */ int remove_inode_buffers(struct inode *inode) { int ret = 1; if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { ret = 0; break; } __remove_assoc_queue(bh); } spin_unlock(&buffer_mapping->private_lock); } return ret; } /* * Create the appropriate buffers when given a page for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry) { struct buffer_head *bh, *head; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; long offset; struct mem_cgroup *memcg, *old_memcg; if (retry) gfp |= __GFP_NOFAIL; /* The page lock pins the memcg */ memcg = page_memcg(page); old_memcg = set_active_memcg(memcg); head = NULL; offset = PAGE_SIZE; while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; bh->b_size = size; /* Link the buffer to its page */ set_bh_page(bh, page, offset); } out: set_active_memcg(old_memcg); return head; /* * In case anything failed, we just free everything we got. */ no_grow: if (head) { do { bh = head; head = head->b_this_page; free_buffer_head(bh); } while (head); } goto out; } EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void link_dev_buffers(struct page *page, struct buffer_head *head) { struct buffer_head *bh, *tail; bh = head; do { tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; attach_page_private(page, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); loff_t sz = i_size_read(bdev->bd_inode); if (sz) { unsigned int sizebits = blksize_bits(size); retval = (sz >> sizebits); } return retval; } /* * Initialise the state of a blockdev page's buffers. */ static sector_t init_page_buffers(struct page *page, struct block_device *bdev, sector_t block, int size) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size); do { if (!buffer_mapped(bh)) { bh->b_end_io = NULL; bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); if (block < end_block) set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); /* * Caller needs to validate requested block against end of device. */ return end_block; } /* * Create the page-cache page that contains the requested block. * * This is used purely for blockdev mappings. */ static int grow_dev_page(struct block_device *bdev, sector_t block, pgoff_t index, int size, int sizebits, gfp_t gfp) { struct inode *inode = bdev->bd_inode; struct page *page; struct buffer_head *bh; sector_t end_block; int ret = 0; gfp_t gfp_mask; gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; /* * XXX: __getblk_slow() can not really deal with failure and * will endlessly loop on improvised global reclaim. Prefer * looping in the allocator rather than here, at least that * code knows what it's doing. */ gfp_mask |= __GFP_NOFAIL; page = find_or_create_page(inode->i_mapping, index, gfp_mask); BUG_ON(!PageLocked(page)); if (page_has_buffers(page)) { bh = page_buffers(page); if (bh->b_size == size) { end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); goto done; } if (!try_to_free_buffers(page)) goto failed; } /* * Allocate some buffers for this page */ bh = alloc_page_buffers(page, size, true); /* * Link the page to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not * run under the page lock. */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; failed: unlock_page(page); put_page(page); return ret; } /* * Create buffers for the specified block device block's page. If * that page was dirty, the buffers are set dirty also. */ static int grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp) { pgoff_t index; int sizebits; sizebits = PAGE_SHIFT - __ffs(size); index = block >> sizebits; /* * Check for a block which wants to lie outside our maximum possible * pagecache index. (this comparison is done using sector_t types). */ if (unlikely(index != block >> sizebits)) { printk(KERN_ERR "%s: requested out-of-range block %llu for " "device %pg\n", __func__, (unsigned long long)block, bdev); return -EIO; } /* Create a page with the proper size buffers.. */ return grow_dev_page(bdev, block, index, size, sizebits, gfp); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { printk(KERN_ERR "getblk(): invalid block size %d requested\n", size); printk(KERN_ERR "logical block size: %d\n", bdev_logical_block_size(bdev)); dump_stack(); return NULL; } for (;;) { struct buffer_head *bh; int ret; bh = __find_get_block(bdev, block, size); if (bh) return bh; ret = grow_buffers(bdev, block, size, gfp); if (ret < 0) return NULL; } } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_page() against that page will discover all the uptodate * buffers, will set the page uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); trace_block_dirty_buffer(bh); /* * Very *carefully* optimize the it-is-already-dirty case. * * Don't let the final "is it dirty" escape to before we * perhaps modified the buffer. */ if (buffer_dirty(bh)) { smp_mb(); if (buffer_dirty(bh)) return; } if (!test_set_buffer_dirty(bh)) { struct page *page = bh->b_page; struct address_space *mapping = NULL; lock_page_memcg(page); if (!TestSetPageDirty(page)) { mapping = page_mapping(page); if (mapping) __set_page_dirty(page, mapping, 0); } unlock_page_memcg(page); if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); void mark_buffer_write_io_error(struct buffer_head *bh) { struct super_block *sb; set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ if (bh->b_page && bh->b_page->mapping) mapping_set_error(bh->b_page->mapping, -EIO); if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); rcu_read_lock(); sb = READ_ONCE(bh->b_bdev->bd_super); if (sb) errseq_set(&sb->s_wb_err, -EIO); rcu_read_unlock(); } EXPORT_SYMBOL(mark_buffer_write_io_error); /* * Decrement a buffer_head's reference count. If all buffers against a page * have zero reference count, are clean and unlocked, and if the page is clean * and unlocked then try_to_free_buffers() may strip the buffers from the page * in preparation for freeing it (sometimes, rarely, buffers are removed from * a page but it ends up not being freed, and buffers may later be reattached). */ void __brelse(struct buffer_head * buf) { if (atomic_read(&buf->b_count)) { put_bh(buf); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); /* * bforget() is like brelse(), except it discards any * potentially dirty data. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_page->mapping; spin_lock(&buffer_mapping->private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->private_lock); } __brelse(bh); } EXPORT_SYMBOL(__bforget); static struct buffer_head *__bread_slow(struct buffer_head *bh) { lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); return bh; } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; } brelse(bh); return NULL; } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }}; #ifdef CONFIG_SMP #define bh_lru_lock() local_irq_disable() #define bh_lru_unlock() local_irq_enable() #else #define bh_lru_lock() preempt_disable() #define bh_lru_unlock() preempt_enable() #endif static inline void check_irqs_on(void) { #ifdef irqs_disabled BUG_ON(irqs_disabled()); #endif } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = bh; struct bh_lru *b; int i; check_irqs_on(); bh_lru_lock(); /* * the refcount of buffer_head in bh_lru prevents dropping the * attached page(i.e., try_to_free_buffers) so it could cause * failing page migration. * Skip putting upcoming bh into bh_lru until migration is done. */ if (lru_cache_disabled()) { bh_lru_unlock(); return; } b = this_cpu_ptr(&bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { swap(evictee, b->bhs[i]); if (evictee == bh) { bh_lru_unlock(); return; } } get_bh(bh); bh_lru_unlock(); brelse(evictee); } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; unsigned int i; check_irqs_on(); bh_lru_lock(); for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; break; } } bh_lru_unlock(); return ret; } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL */ struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); } else touch_buffer(bh); return bh; } EXPORT_SYMBOL(__find_get_block); /* * __getblk_gfp() will locate (and, if necessary, create) the buffer_head * which corresponds to the passed block_device, block and size. The * returned buffer has its reference count incremented. * * __getblk_gfp() will lock up the machine if grow_dev_page's * try_to_free_buffers() attempt is failing. FIXME, perhaps? */ struct buffer_head * __getblk_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __find_get_block(bdev, block, size); might_sleep(); if (bh == NULL) bh = __getblk_slow(bdev, block, size, gfp); return bh; } EXPORT_SYMBOL(__getblk_gfp); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = __getblk(bdev, block, size); if (likely(bh)) { ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); brelse(bh); } } EXPORT_SYMBOL(__breadahead); void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh)) { ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); brelse(bh); } } EXPORT_SYMBOL(__breadahead_gfp); /** * __bread_gfp() - reads a specified block and returns the bh * @bdev: the block_device to read from * @block: number of block * @size: size (in bytes) to read * @gfp: page allocation flag * * Reads a specified block, and returns buffer head that contains it. * The page cache can be allocated from non-movable area * not to prevent page migration if you set gfp to zero. * It returns NULL if the block was unreadable. */ struct buffer_head * __bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } EXPORT_SYMBOL(__bread_gfp); static void __invalidate_bh_lrus(struct bh_lru *b) { int i; for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } } /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); __invalidate_bh_lrus(b); put_cpu_var(bh_lrus); } bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) return true; } return false; } void invalidate_bh_lrus(void) { on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); /* * It's called from workqueue context so we need a bh_lru_lock to close * the race with preemption/irq. */ void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset) { bh->b_page = page; BUG_ON(offset >= PAGE_SIZE); if (PageHighMem(page)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else bh->b_data = page_address(page) + offset; } EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD \ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ 1 << BH_Delay | 1 << BH_Unwritten) static void discard_buffer(struct buffer_head * bh) { unsigned long b_state, b_state_old; lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; b_state = bh->b_state; for (;;) { b_state_old = cmpxchg(&bh->b_state, b_state, (b_state & ~BUFFER_FLAGS_DISCARD)); if (b_state_old == b_state) break; b_state = b_state_old; } unlock_buffer(bh); } /** * block_invalidatepage - invalidate part or all of a buffer-backed page * * @page: the page which is affected * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. * * block_invalidatepage() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { struct buffer_head *head, *bh, *next; unsigned int curr_off = 0; unsigned int stop = length + offset; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) goto out; /* * Check for overflow */ BUG_ON(stop > PAGE_SIZE || stop < length); head = page_buffers(page); bh = head; do { unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; /* * Are we still fully in range ? */ if (next_off > stop) goto out; /* * is this block fully invalidated? */ if (offset <= curr_off) discard_buffer(bh); curr_off = next_off; bh = next; } while (bh != head); /* * We release buffers only if the entire page is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ if (length == PAGE_SIZE) try_to_release_page(page, 0); out: return; } EXPORT_SYMBOL(block_invalidatepage); /* * We attach and possibly dirty the buffers atomically wrt * __set_page_dirty_buffers() via private_lock. try_to_free_buffers * is already excluded via the page lock. */ void create_empty_buffers(struct page *page, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; head = alloc_page_buffers(page, blocksize, true); bh = head; do { bh->b_state |= b_state; tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; spin_lock(&page->mapping->private_lock); if (PageUptodate(page) || PageDirty(page)) { bh = head; do { if (PageDirty(page)) set_buffer_dirty(bh); if (PageUptodate(page)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } attach_page_private(page, head); spin_unlock(&page->mapping->private_lock); } EXPORT_SYMBOL(create_empty_buffers); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; struct pagevec pvec; pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits); pagevec_init(&pvec); while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) { count = pagevec_count(&pvec); for (i = 0; i < count; i++) { struct page *page = pvec.pages[i]; if (!page_has_buffers(page)) continue; /* * We use page lock instead of bd_mapping->private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ lock_page(page); /* Recheck when the page is locked which pins bhs */ if (!page_has_buffers(page)) goto unlock_page; head = page_buffers(page); bh = head; do { if (!buffer_mapped(bh) || (bh->b_blocknr < block)) goto next; if (bh->b_blocknr >= block + len) break; clear_buffer_dirty(bh); wait_on_buffer(bh); clear_buffer_req(bh); next: bh = bh->b_this_page; } while (bh != head); unlock_page: unlock_page(page); } pagevec_release(&pvec); cond_resched(); /* End of range already reached? */ if (index > end || !index) break; } } EXPORT_SYMBOL(clean_bdev_aliases); /* * Size is a power-of-two in the range 512..PAGE_SIZE, * and the case we care about most is PAGE_SIZE. * * So this *could* possibly be written with those * constraints in mind (relevant mostly if some * architecture has a slow bit-scan instruction) */ static inline int block_size_bits(unsigned int blocksize) { return ilog2(blocksize); } static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state) { BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits), b_state); return page_buffers(page); } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_page is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_page() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_page() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; unsigned int blocksize, bbits; int nr_underway = 0; int write_flags = wbc_to_write_flags(wbc); head = create_page_buffers(page, inode, (1 << BH_Dirty)|(1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from __set_page_dirty_buffers * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it * then we just miss that fact, and the page stays dirty. * * Buffers outside i_size may be dirtied by __set_page_dirty_buffers; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; bbits = block_size_bits(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); last_block = (i_size_read(inode) - 1) >> bbits; /* * Get all the dirty buffers mapped to disk addresses and * handle any aliases from the underlying blockdev's mapping. */ do { if (block > last_block) { /* * mapped buffers outside i_size will occur, because * this page can be outside i_size when there is a * truncate in progress. */ /* * The buffer was zeroed by block_write_full_page() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; block++; } while (bh != head); do { if (!buffer_mapped(bh)) continue; /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the page. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. */ if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); continue; } if (test_clear_buffer_dirty(bh)) { mark_buffer_async_write_endio(bh, handler); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* * The page and its buffers are protected by PageWriteback(), so we can * drop the bh refcounts early. */ BUG_ON(PageWriteback(page)); set_page_writeback(page); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); unlock_page(page); err = 0; done: if (nr_underway == 0) { /* * The page was marked dirty, but the buffers were * clean. Someone wrote them back by hand with * ll_rw_block/submit_bh. A rare case. */ end_page_writeback(page); /* * The page and buffer_heads can be released at any time from * here on. */ } return err; recover: /* * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. * The page is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ do { if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write_endio(bh, handler); } else { /* * The buffer may have been set dirty during * attachment to a dirty page. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); SetPageError(page); BUG_ON(PageWriteback(page)); mapping_set_error(page->mapping, err); set_page_writeback(page); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); unlock_page(page); goto done; } EXPORT_SYMBOL(__block_write_full_page); /* * If a page has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) { unsigned int block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) return; bh = head = page_buffers(page); block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!PageUptodate(page)) { unsigned start, size; start = max(from, block_start); size = min(to, block_end) - start; zero_user(page, start, size); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(page_zero_new_buffers); static void iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { loff_t offset = block << inode->i_blkbits; bh->b_bdev = iomap->bdev; /* * Block points to offset in file we need to map, iomap contains * the offset at which the map starts. If the map ends before the * current block, then do not map the buffer and let the caller * handle it. */ BUG_ON(offset >= iomap->offset + iomap->length); switch (iomap->type) { case IOMAP_HOLE: /* * If the buffer is not up to date or beyond the current EOF, * we need to mark it as new to ensure sub-block zeroing is * executed if necessary. */ if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); break; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); break; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions * in the block we are not writing to are zeroed. Mark the * buffer as new to ensure this. */ set_buffer_new(bh); set_buffer_unwritten(bh); fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) set_buffer_new(bh); bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); break; } } int __block_write_begin_int(struct page *page, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap) { unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + len; struct inode *inode = page->mapping->host; unsigned block_start, block_end; sector_t block; int err = 0; unsigned blocksize, bbits; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!PageLocked(page)); BUG_ON(from > PAGE_SIZE); BUG_ON(to > PAGE_SIZE); BUG_ON(from > to); head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); for(bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); if (get_block) { err = get_block(inode, block, bh, 1); if (err) break; } else { iomap_to_bh(inode, block, bh, iomap); } if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (PageUptodate(page)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) zero_user_segments(page, to, block_end, block_start, from); continue; } } if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { ll_rw_block(REQ_OP_READ, 0, 1, &bh); *wait_bh++=bh; } } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) page_zero_new_buffers(page, from, to); return err; } int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { return __block_write_begin_int(page, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); static int __block_commit_write(struct inode *inode, struct page *page, unsigned from, unsigned to) { unsigned block_start, block_end; int partial = 0; unsigned blocksize; struct buffer_head *bh, *head; bh = head = page_buffers(page); blocksize = bh->b_size; block_start = 0; do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = 1; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } if (buffer_new(bh)) clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; } while (bh != head); /* * If this is a partial write which happened to make all buffers * uptodate then we can optimize away a bogus readpage() for * the next read(). Here we 'discover' whether the page went * uptodate as a result of this (potentially partial) write. */ if (!partial) SetPageUptodate(page); return 0; } /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; status = __block_write_begin(page, pos, len, get_block); if (unlikely(status)) { unlock_page(page); put_page(page); page = NULL; } *pagep = page; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; unsigned start; start = pos & (PAGE_SIZE - 1); if (unlikely(copied < len)) { /* * The buffers that were written will now be uptodate, so we * don't have to worry about a readpage reading them and * overwriting a partial write. However if we have encountered * a short write and only partially written into a buffer, it * will not be marked uptodate, so a readpage might come in and * destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate page as a zero-length write, and force the * caller to redo the whole thing. */ if (!PageUptodate(page)) copied = 0; page_zero_new_buffers(page, start+copied, start+len); } flush_dcache_page(page); /* This could be a short (even 0-length) commit */ __block_commit_write(inode, page, start, start+copied); return copied; } EXPORT_SYMBOL(block_write_end); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = true; } unlock_page(page); put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL(generic_write_end); /* * block_is_partially_uptodate checks whether buffers within a page are * uptodate or not. * * Returns true if all buffers which correspond to a file portion * we want to read are uptodate. */ int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; int ret = 1; if (!page_has_buffers(page)) return 0; head = page_buffers(page); blocksize = head->b_size; to = min_t(unsigned, PAGE_SIZE - from, count); to = from + to; if (from < blocksize && to > PAGE_SIZE - blocksize) return 0; bh = head; block_start = 0; do { block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { ret = 0; break; } if (block_end >= to) break; } block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } EXPORT_SYMBOL(block_is_partially_uptodate); /* * Generic "read page" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the page asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * page struct once IO has completed. */ int block_read_full_page(struct page *page, get_block_t *get_block) { struct inode *inode = page->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; unsigned int blocksize, bbits; int nr, i; int fully_mapped = 1; head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); iblock = (sector_t)page->index << (PAGE_SHIFT - bbits); lblock = (i_size_read(inode)+blocksize-1) >> bbits; bh = head; nr = 0; i = 0; do { if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = 0; fully_mapped = 0; if (iblock < lblock) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) SetPageError(page); } if (!buffer_mapped(bh)) { zero_user(page, i * blocksize, blocksize); if (!err) set_buffer_uptodate(bh); continue; } /* * get_block() might have updated the buffer * synchronously */ if (buffer_uptodate(bh)) continue; } arr[nr++] = bh; } while (i++, iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) SetPageMappedToDisk(page); if (!nr) { /* * All buffers are uptodate - we can set the page uptodate * as well. But not if get_block() returned an error. */ if (!PageError(page)) SetPageUptodate(page); unlock_page(page); return 0; } /* Stage two: lock the buffers */ for (i = 0; i < nr; i++) { bh = arr[i]; lock_buffer(bh); mark_buffer_async_read(bh); } /* * Stage 3: start the IO. Check for uptodateness * inside the buffer lock in case another process reading * the underlying blockdev brought it uptodate (the sct fix). */ for (i = 0; i < nr; i++) { bh = arr[i]; if (buffer_uptodate(bh)) end_buffer_async_read(bh, 1); else submit_bh(REQ_OP_READ, 0, bh); } return 0; } EXPORT_SYMBOL(block_read_full_page); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; err = pagecache_write_begin(NULL, mapping, size, 0, AOP_FLAG_CONT_EXPAND, &page, &fsdata); if (err) goto out; err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata); BUG_ON(err > 0); out: return err; } EXPORT_SYMBOL(generic_cont_expand_simple); static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = PAGE_SIZE - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, 0, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { err = -EINTR; goto out; } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; } if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = offset - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, 0, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; } out: return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); if (err) return err; zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } return block_write_begin(mapping, pos, len, flags, pagep, get_block); } EXPORT_SYMBOL(cont_write_begin); int block_commit_write(struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; __block_commit_write(inode,page,from,to); return 0; } EXPORT_SYMBOL(block_commit_write); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; lock_page(page); size = i_size_read(inode); if ((page->mapping != inode->i_mapping) || (page_offset(page) > size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } /* page is wholly or partially inside EOF */ if (((page->index + 1) << PAGE_SHIFT) > size) end = size & ~PAGE_MASK; else end = PAGE_SIZE; ret = __block_write_begin(page, 0, end, get_block); if (!ret) ret = block_commit_write(page, 0, end); if (unlikely(ret < 0)) goto out_unlock; set_page_dirty(page); wait_for_stable_page(page); return 0; out_unlock: unlock_page(page); return ret; } EXPORT_SYMBOL(block_page_mkwrite); /* * nobh_write_begin()'s prereads are special: the buffer_heads are freed * immediately, while under the page lock. So it needs a special end_io * handler which does not touch the bh after unlocking it. */ static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate) { __end_buffer_read_notouch(bh, uptodate); } /* * Attach the singly-linked list of buffers created by nobh_write_begin, to * the page (converting it to circular linked list and taking care of page * dirty races). */ static void attach_nobh_buffers(struct page *page, struct buffer_head *head) { struct buffer_head *bh; BUG_ON(!PageLocked(page)); spin_lock(&page->mapping->private_lock); bh = head; do { if (PageDirty(page)) set_buffer_dirty(bh); if (!bh->b_this_page) bh->b_this_page = head; bh = bh->b_this_page; } while (bh != head); attach_page_private(page, head); spin_unlock(&page->mapping->private_lock); } /* * On entry, the page is fully not uptodate. * On exit the page is fully uptodate in the areas outside (from,to) * The filesystem needs to handle block truncation upon failure. */ int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block) { struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; const unsigned blocksize = 1 << blkbits; struct buffer_head *head, *bh; struct page *page; pgoff_t index; unsigned from, to; unsigned block_in_page; unsigned block_start, block_end; sector_t block_in_file; int nr_reads = 0; int ret = 0; int is_mapped_to_disk = 1; index = pos >> PAGE_SHIFT; from = pos & (PAGE_SIZE - 1); to = from + len; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; *pagep = page; *fsdata = NULL; if (page_has_buffers(page)) { ret = __block_write_begin(page, pos, len, get_block); if (unlikely(ret)) goto out_release; return ret; } if (PageMappedToDisk(page)) return 0; /* * Allocate buffers so that we can keep track of state, and potentially * attach them to the page if an error occurs. In the common case of * no error, they will just be freed again without ever being attached * to the page (which is all OK, because we're under the page lock). * * Be careful: the buffer linked list is a NULL terminated one, rather * than the circular one we're used to. */ head = alloc_page_buffers(page, blocksize, false); if (!head) { ret = -ENOMEM; goto out_release; } block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); /* * We loop across all blocks in the page, whether or not they are * part of the affected region. This is so we can discover if the * page is fully mapped-to-disk. */ for (block_start = 0, block_in_page = 0, bh = head; block_start < PAGE_SIZE; block_in_page++, block_start += blocksize, bh = bh->b_this_page) { int create; block_end = block_start + blocksize; bh->b_state = 0; create = 1; if (block_start >= to) create = 0; ret = get_block(inode, block_in_file + block_in_page, bh, create); if (ret) goto failed; if (!buffer_mapped(bh)) is_mapped_to_disk = 0; if (buffer_new(bh)) clean_bdev_bh_alias(bh); if (PageUptodate(page)) { set_buffer_uptodate(bh); continue; } if (buffer_new(bh) || !buffer_mapped(bh)) { zero_user_segments(page, block_start, from, to, block_end); continue; } if (buffer_uptodate(bh)) continue; /* reiserfs does this */ if (block_start < from || block_end > to) { lock_buffer(bh); bh->b_end_io = end_buffer_read_nobh; submit_bh(REQ_OP_READ, 0, bh); nr_reads++; } } if (nr_reads) { /* * The page is locked, so these buffers are protected from * any VM or truncate activity. Hence we don't need to care * for the buffer_head refcounts. */ for (bh = head; bh; bh = bh->b_this_page) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) ret = -EIO; } if (ret) goto failed; } if (is_mapped_to_disk) SetPageMappedToDisk(page); *fsdata = head; /* to be released by nobh_write_end */ return 0; failed: BUG_ON(!ret); /* * Error recovery is a bit difficult. We need to zero out blocks that * were newly allocated, and dirty them to ensure they get written out. * Buffers need to be attached to the page at this point, otherwise * the handling of potential IO errors during writeout would be hard * (could try doing synchronous writeout, but what if that fails too?) */ attach_nobh_buffers(page, head); page_zero_new_buffers(page, from, to); out_release: unlock_page(page); put_page(page); *pagep = NULL; return ret; } EXPORT_SYMBOL(nobh_write_begin); int nobh_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; struct buffer_head *head = fsdata; struct buffer_head *bh; BUG_ON(fsdata != NULL && page_has_buffers(page)); if (unlikely(copied < len) && head) attach_nobh_buffers(page, head); if (page_has_buffers(page)) return generic_write_end(file, mapping, pos, len, copied, page, fsdata); SetPageUptodate(page); set_page_dirty(page); if (pos+copied > inode->i_size) { i_size_write(inode, pos+copied); mark_inode_dirty(inode); } unlock_page(page); put_page(page); while (head) { bh = head; head = head->b_this_page; free_buffer_head(bh); } return copied; } EXPORT_SYMBOL(nobh_write_end); /* * nobh_writepage() - based on block_full_write_page() except * that it tries to operate without attaching bufferheads to * the page. */ int nobh_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; int ret; /* Is the page fully inside i_size? */ if (page->index < end_index) goto out; /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_SIZE); out: ret = mpage_writepage(page, get_block, wbc); if (ret == -EAGAIN) ret = __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); return ret; } EXPORT_SYMBOL(nobh_writepage); int nobh_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; struct buffer_head map_bh; int err; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; if (!page) goto out; if (page_has_buffers(page)) { has_buffers: unlock_page(page); put_page(page); return block_truncate_page(mapping, from, get_block); } /* Find the buffer that contains "offset" */ pos = blocksize; while (offset >= pos) { iblock++; pos += blocksize; } map_bh.b_size = blocksize; map_bh.b_state = 0; err = get_block(inode, iblock, &map_bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(&map_bh)) goto unlock; /* Ok, it's mapped. Make sure it's up-to-date */ if (!PageUptodate(page)) { err = mapping->a_ops->readpage(NULL, page); if (err) { put_page(page); goto out; } lock_page(page); if (!PageUptodate(page)) { err = -EIO; goto unlock; } if (page_has_buffers(page)) goto has_buffers; } zero_user(page, offset, length); set_page_dirty(page); err = 0; unlock: unlock_page(page); put_page(page); out: return err; } EXPORT_SYMBOL(nobh_truncate_page); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; struct buffer_head *bh; int err; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; if (!page) goto out; if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); /* Find the buffer that contains "offset" */ bh = page_buffers(page); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } err = 0; if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; } /* Ok, it's mapped. Make sure it's up-to-date */ if (PageUptodate(page)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { err = -EIO; ll_rw_block(REQ_OP_READ, 0, 1, &bh); wait_on_buffer(bh); /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; } zero_user(page, offset, length); mark_buffer_dirty(bh); err = 0; unlock: unlock_page(page); put_page(page); out: return err; } EXPORT_SYMBOL(block_truncate_page); /* * The generic ->writepage function for buffer-backed address_spaces */ int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; /* Is the page fully inside i_size? */ if (page->index < end_index) return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_SIZE); return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); } EXPORT_SYMBOL(block_write_full_page); sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { struct inode *inode = mapping->host; struct buffer_head tmp = { .b_size = i_blocksize(inode), }; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL(generic_block_bmap); static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { struct bio *bio; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); BUG_ON(buffer_delay(bh)); BUG_ON(buffer_unwritten(bh)); /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); bio = bio_alloc(GFP_NOIO, 1); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); BUG_ON(bio->bi_iter.bi_size != bh->b_size); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; if (buffer_meta(bh)) op_flags |= REQ_META; if (buffer_prio(bh)) op_flags |= REQ_PRIO; bio_set_op_attrs(bio, op, op_flags); /* Take care of bh's that straddle the end of the device */ guard_bio_eod(bio); if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size); } submit_bio(bio); return 0; } int submit_bh(int op, int op_flags, struct buffer_head *bh) { return submit_bh_wbc(op, op_flags, bh, 0, NULL); } EXPORT_SYMBOL(submit_bh); /** * ll_rw_block: low-level access to block devices (DEPRECATED) * @op: whether to %READ or %WRITE * @op_flags: req_flag_bits * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * * ll_rw_block() takes an array of pointers to &struct buffer_heads, and * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE. * @op_flags contains flags modifying the detailed I/O behavior, most notably * %REQ_RAHEAD. * * This function drops any buffer that it cannot get a lock on (with the * BH_Lock state bit), any buffer that appears to be clean when doing a write * request, and any buffer that appears to be up-to-date when doing read * request. Further it marks as clean buffers that are processed for * writing (the buffer cache won't assume that they are actually clean * until the buffer gets unlocked). * * ll_rw_block sets b_end_io to simple completion handler that marks * the buffer up-to-date (if appropriate), unlocks the buffer and wakes * any waiters. * * All of the buffers must be for the same device, and must also be a * multiple of the current approved size for the device. */ void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[]) { int i; for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; if (!trylock_buffer(bh)) continue; if (op == WRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(op, op_flags, bh); continue; } } else { if (!buffer_uptodate(bh)) { bh->b_end_io = end_buffer_read_sync; get_bh(bh); submit_bh(op, op_flags, bh); continue; } } unlock_buffer(bh); } } EXPORT_SYMBOL(ll_rw_block); void write_dirty_buffer(struct buffer_head *bh, int op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { unlock_buffer(bh); return; } bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE, op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) { int ret = 0; WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { /* * The bh should be mapped, but it might not be if the * device was hot-removed. Not much we can do but fail the I/O. */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); wait_on_buffer(bh); if (!ret && !buffer_uptodate(bh)) ret = -EIO; } else { unlock_buffer(bh); } return ret; } EXPORT_SYMBOL(__sync_dirty_buffer); int sync_dirty_buffer(struct buffer_head *bh) { return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL(sync_dirty_buffer); /* * try_to_free_buffers() checks if all the buffers on this particular page * are unused, and releases them if so. * * Exclusion against try_to_free_buffers may be obtained by either * locking the page or by holding its mapping's private_lock. * * If the page is dirty but all the buffers are clean then we need to * be sure to mark the page clean as well. This is because the page * may be against a block device, and a later reattachment of buffers * to a dirty page will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem pages: if all the buffers are * clean then we set the page clean and proceed. To do that, we require * total exclusion from __set_page_dirty_buffers(). That is obtained with * private_lock. * * try_to_free_buffers() is non-blocking. */ static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } static int drop_buffers(struct page *page, struct buffer_head **buffers_to_free) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh; bh = head; do { if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; } while (bh != head); do { struct buffer_head *next = bh->b_this_page; if (bh->b_assoc_map) __remove_assoc_queue(bh); bh = next; } while (bh != head); *buffers_to_free = head; detach_page_private(page); return 1; failed: return 0; } int try_to_free_buffers(struct page *page) { struct address_space * const mapping = page->mapping; struct buffer_head *buffers_to_free = NULL; int ret = 0; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(page, &buffers_to_free); goto out; } spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) * then we can have clean buffers against a dirty page. We * clean the page here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all * the page's buffers clean. We discover that here and clean * the page also. * * private_lock must be held over this entire operation in order * to synchronise against __set_page_dirty_buffers and prevent the * dirty bit from being lost. */ if (ret) cancel_dirty_page(page); spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; do { struct buffer_head *next = bh->b_this_page; free_buffer_head(bh); bh = next; } while (bh != buffers_to_free); } return ret; } EXPORT_SYMBOL(try_to_free_buffers); /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __read_mostly; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads; int buffer_heads_over_limit; struct bh_accounting { int nr; /* Number of live bh's */ int ratelimit; /* Limit cacheline bouncing */ }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0}; static void recalc_bh_state(void) { int i; int tot = 0; if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } return ret; } EXPORT_SYMBOL(alloc_buffer_head); void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); preempt_disable(); __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; return 0; } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { if (!buffer_uptodate(bh)) { lock_buffer(bh); if (!buffer_uptodate(bh)) return 0; unlock_buffer(bh); } return 1; } EXPORT_SYMBOL(bh_uptodate_or_lock); /** * bh_submit_read - Submit a locked buffer for reading * @bh: struct buffer_head * * Returns zero on success and -EIO on error. */ int bh_submit_read(struct buffer_head *bh) { BUG_ON(!buffer_locked(bh)); if (buffer_uptodate(bh)) { unlock_buffer(bh); return 0; } get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return 0; return -EIO; } EXPORT_SYMBOL(bh_submit_read); void __init buffer_init(void) { unsigned long nrpages; int ret; bh_cachep = kmem_cache_create("buffer_head", sizeof(struct buffer_head), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD), NULL); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", NULL, buffer_exit_cpu_dead); WARN_ON(ret < 0); } |
| 39 35 252 222 35 35 67 58 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/sem.c * Copyright (C) 1992 Krishna Balasubramanian * Copyright (C) 1995 Eric Schenk, Bruno Haible * * /proc/sysvipc/sem support (c) 1999 Dragos Acostachioaie <dragos@iname.com> * * SMP-threaded, sysctl's added * (c) 1999 Manfred Spraul <manfred@colorfullife.com> * Enforced range limit on SEM_UNDO * (c) 2001 Red Hat Inc * Lockless wakeup * (c) 2003 Manfred Spraul <manfred@colorfullife.com> * (c) 2016 Davidlohr Bueso <dave@stgolabs.net> * Further wakeup optimizations, documentation * (c) 2010 Manfred Spraul <manfred@colorfullife.com> * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> * * namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> * * Implementation notes: (May 2010) * This file implements System V semaphores. * * User space visible behavior: * - FIFO ordering for semop() operations (just FIFO, not starvation * protection) * - multiple semaphore operations that alter the same semaphore in * one semop() are handled. * - sem_ctime (time of last semctl()) is updated in the IPC_SET, SETVAL and * SETALL calls. * - two Linux specific semctl() commands: SEM_STAT, SEM_INFO. * - undo adjustments at process exit are limited to 0..SEMVMX. * - namespace are supported. * - SEMMSL, SEMMNS, SEMOPM and SEMMNI can be configured at runtime by writing * to /proc/sys/kernel/sem. * - statistics about the usage are reported in /proc/sysvipc/sem. * * Internals: * - scalability: * - all global variables are read-mostly. * - semop() calls and semctl(RMID) are synchronized by RCU. * - most operations do write operations (actually: spin_lock calls) to * the per-semaphore array structure. * Thus: Perfect SMP scaling between independent semaphore arrays. * If multiple semaphores in one array are used, then cache line * trashing on the semaphore array spinlock will limit the scaling. * - semncnt and semzcnt are calculated on demand in count_semcnt() * - the task that performs a successful semop() scans the list of all * sleeping tasks and completes any pending operations that can be fulfilled. * Semaphores are actively given to waiting tasks (necessary for FIFO). * (see update_queue()) * - To improve the scalability, the actual wake-up calls are performed after * dropping all locks. (see wake_up_sem_queue_prepare()) * - All work is done by the waker, the woken up task does not have to do * anything - not even acquiring a lock or dropping a refcount. * - A woken up task may not even touch the semaphore array anymore, it may * have been destroyed already by a semctl(RMID). * - UNDO values are stored in an array (one per process and per * semaphore array, lazily allocated). For backwards compatibility, multiple * modes for the UNDO variables are supported (per process, per thread) * (see copy_semundo, CLONE_SYSVSEM) * - There are two lists of the pending operations: a per-array list * and per-semaphore list (stored in the array). This allows to achieve FIFO * ordering without always scanning all pending operations. * The worst-case behavior is nevertheless O(N^2) for N wakeups. */ #include <linux/compat.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/time.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/seq_file.h> #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> #include <linux/sched/wake_q.h> #include <linux/nospec.h> #include <linux/rhashtable.h> #include <linux/uaccess.h> #include "util.h" /* One semaphore structure for each semaphore in the system. */ struct sem { int semval; /* current value */ /* * PID of the process that last modified the semaphore. For * Linux, specifically these are: * - semop * - semctl, via SETVAL and SETALL. * - at task exit when performing undo adjustments (see exit_sem). */ struct pid *sempid; spinlock_t lock; /* spinlock for fine-grained semtimedop */ struct list_head pending_alter; /* pending single-sop operations */ /* that alter the semaphore */ struct list_head pending_const; /* pending single-sop operations */ /* that do not alter the semaphore*/ time64_t sem_otime; /* candidate for sem_otime */ } ____cacheline_aligned_in_smp; /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ time64_t sem_ctime; /* create/last semctl() time */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ /* that do not alter semvals */ struct list_head list_id; /* undo requests on this array */ int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ unsigned int use_global_lock;/* >0: global lock required */ struct sem sems[]; } __randomize_layout; /* One queue for each sleeping process in the system. */ struct sem_queue { struct list_head list; /* queue of pending operations */ struct task_struct *sleeper; /* this process */ struct sem_undo *undo; /* undo structure */ struct pid *pid; /* process id of requesting process */ int status; /* completion status of operation */ struct sembuf *sops; /* array of pending operations */ struct sembuf *blocking; /* the operation that blocked */ int nsops; /* number of operations */ bool alter; /* does *sops alter the array? */ bool dupsop; /* sops on more than one sem_num */ }; /* Each task has a list of undo requests. They are executed automatically * when the process exits. */ struct sem_undo { struct list_head list_proc; /* per-process list: * * all undos from one process * rcu protected */ struct rcu_head rcu; /* rcu struct for sem_undo */ struct sem_undo_list *ulp; /* back ptr to sem_undo_list */ struct list_head list_id; /* per semaphore array list: * all undos for one array */ int semid; /* semaphore set identifier */ short *semadj; /* array of adjustments */ /* one per semaphore */ }; /* sem_undo_list controls shared access to the list of sem_undo structures * that may be shared among all a CLONE_SYSVSEM task group. */ struct sem_undo_list { refcount_t refcnt; spinlock_t lock; struct list_head list_proc; }; #define sem_ids(ns) ((ns)->ids[IPC_SEM_IDS]) static int newary(struct ipc_namespace *, struct ipc_params *); static void freeary(struct ipc_namespace *, struct kern_ipc_perm *); #ifdef CONFIG_PROC_FS static int sysvipc_sem_proc_show(struct seq_file *s, void *it); #endif #define SEMMSL_FAST 256 /* 512 bytes on stack */ #define SEMOPM_FAST 64 /* ~ 372 bytes on stack */ /* * Switching from the mode suitable for simple ops * to the mode for complex ops is costly. Therefore: * use some hysteresis */ #define USE_GLOBAL_LOCK_HYSTERESIS 10 /* * Locking: * a) global sem_lock() for read/write * sem_undo.id_next, * sem_array.complex_count, * sem_array.pending{_alter,_const}, * sem_array.sem_undo * * b) global or semaphore sem_lock() for read/write: * sem_array.sems[i].pending_{const,alter}: * * c) special: * sem_undo_list.list_proc: * * undo_list->lock for write * * rcu for read * use_global_lock: * * global sem_lock() for write * * either local or global sem_lock() for read. * * Memory ordering: * Most ordering is enforced by using spin_lock() and spin_unlock(). * * Exceptions: * 1) use_global_lock: (SEM_BARRIER_1) * Setting it from non-zero to 0 is a RELEASE, this is ensured by * using smp_store_release(): Immediately after setting it to 0, * a simple op can start. * Testing if it is non-zero is an ACQUIRE, this is ensured by using * smp_load_acquire(). * Setting it from 0 to non-zero must be ordered with regards to * this smp_load_acquire(), this is guaranteed because the smp_load_acquire() * is inside a spin_lock() and after a write from 0 to non-zero a * spin_lock()+spin_unlock() is done. * To prevent the compiler/cpu temporarily writing 0 to use_global_lock, * READ_ONCE()/WRITE_ONCE() is used. * * 2) queue.status: (SEM_BARRIER_2) * Initialization is done while holding sem_lock(), so no further barrier is * required. * Setting it to a result code is a RELEASE, this is ensured by both a * smp_store_release() (for case a) and while holding sem_lock() * (for case b). * The ACQUIRE when reading the result code without holding sem_lock() is * achieved by using READ_ONCE() + smp_acquire__after_ctrl_dep(). * (case a above). * Reading the result code while holding sem_lock() needs no further barriers, * the locks inside sem_lock() enforce ordering (case b above) * * 3) current->state: * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock(). * The wakeup is handled using the wake_q infrastructure. wake_q wakeups may * happen immediately after calling wake_q_add. As wake_q_add_safe() is called * when holding sem_lock(), no further barriers are required. * * See also ipc/mqueue.c for more details on the covered races. */ #define sc_semmsl sem_ctls[0] #define sc_semmns sem_ctls[1] #define sc_semopm sem_ctls[2] #define sc_semmni sem_ctls[3] void sem_init_ns(struct ipc_namespace *ns) { ns->sc_semmsl = SEMMSL; ns->sc_semmns = SEMMNS; ns->sc_semopm = SEMOPM; ns->sc_semmni = SEMMNI; ns->used_sems = 0; ipc_init_ids(&ns->ids[IPC_SEM_IDS]); } #ifdef CONFIG_IPC_NS void sem_exit_ns(struct ipc_namespace *ns) { free_ipcs(ns, &sem_ids(ns), freeary); idr_destroy(&ns->ids[IPC_SEM_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_SEM_IDS].key_ht); } #endif void __init sem_init(void) { sem_init_ns(&init_ipc_ns); ipc_init_proc_interface("sysvipc/sem", " key semid perms nsems uid gid cuid cgid otime ctime\n", IPC_SEM_IDS, sysvipc_sem_proc_show); } /** * unmerge_queues - unmerge queues, if possible. * @sma: semaphore array * * The function unmerges the wait queues if complex_count is 0. * It must be called prior to dropping the global semaphore array lock. */ static void unmerge_queues(struct sem_array *sma) { struct sem_queue *q, *tq; /* complex operations still around? */ if (sma->complex_count) return; /* * We will switch back to simple mode. * Move all pending operation back into the per-semaphore * queues. */ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { struct sem *curr; curr = &sma->sems[q->sops[0].sem_num]; list_add_tail(&q->list, &curr->pending_alter); } INIT_LIST_HEAD(&sma->pending_alter); } /** * merge_queues - merge single semop queues into global queue * @sma: semaphore array * * This function merges all per-semaphore queues into the global queue. * It is necessary to achieve FIFO ordering for the pending single-sop * operations when a multi-semop operation must sleep. * Only the alter operations must be moved, the const operations can stay. */ static void merge_queues(struct sem_array *sma) { int i; for (i = 0; i < sma->sem_nsems; i++) { struct sem *sem = &sma->sems[i]; list_splice_init(&sem->pending_alter, &sma->pending_alter); } } static void sem_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); struct sem_array *sma = container_of(p, struct sem_array, sem_perm); security_sem_free(&sma->sem_perm); kvfree(sma); } /* * Enter the mode suitable for non-simple operations: * Caller must own sem_perm.lock. */ static void complexmode_enter(struct sem_array *sma) { int i; struct sem *sem; if (sma->use_global_lock > 0) { /* * We are already in global lock mode. * Nothing to do, just reset the * counter until we return to simple mode. */ WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS); return; } WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS); for (i = 0; i < sma->sem_nsems; i++) { sem = &sma->sems[i]; spin_lock(&sem->lock); spin_unlock(&sem->lock); } } /* * Try to leave the mode that disallows simple operations: * Caller must own sem_perm.lock. */ static void complexmode_tryleave(struct sem_array *sma) { if (sma->complex_count) { /* Complex ops are sleeping. * We must stay in complex mode */ return; } if (sma->use_global_lock == 1) { /* See SEM_BARRIER_1 for purpose/pairing */ smp_store_release(&sma->use_global_lock, 0); } else { WRITE_ONCE(sma->use_global_lock, sma->use_global_lock-1); } } #define SEM_GLOBAL_LOCK (-1) /* * If the request contains only one semaphore operation, and there are * no complex transactions pending, lock only the semaphore involved. * Otherwise, lock the entire semaphore array, since we either have * multiple semaphores in our own semops, or we need to look at * semaphores from other pending complex operations. */ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, int nsops) { struct sem *sem; int idx; if (nsops != 1) { /* Complex operation - acquire a full lock */ ipc_lock_object(&sma->sem_perm); /* Prevent parallel simple ops */ complexmode_enter(sma); return SEM_GLOBAL_LOCK; } /* * Only one semaphore affected - try to optimize locking. * Optimized locking is possible if no complex operation * is either enqueued or processed right now. * * Both facts are tracked by use_global_mode. */ idx = array_index_nospec(sops->sem_num, sma->sem_nsems); sem = &sma->sems[idx]; /* * Initial check for use_global_lock. Just an optimization, * no locking, no memory barrier. */ if (!READ_ONCE(sma->use_global_lock)) { /* * It appears that no complex operation is around. * Acquire the per-semaphore lock. */ spin_lock(&sem->lock); /* see SEM_BARRIER_1 for purpose/pairing */ if (!smp_load_acquire(&sma->use_global_lock)) { /* fast path successful! */ return sops->sem_num; } spin_unlock(&sem->lock); } /* slow path: acquire the full lock */ ipc_lock_object(&sma->sem_perm); if (sma->use_global_lock == 0) { /* * The use_global_lock mode ended while we waited for * sma->sem_perm.lock. Thus we must switch to locking * with sem->lock. * Unlike in the fast path, there is no need to recheck * sma->use_global_lock after we have acquired sem->lock: * We own sma->sem_perm.lock, thus use_global_lock cannot * change. */ spin_lock(&sem->lock); ipc_unlock_object(&sma->sem_perm); return sops->sem_num; } else { /* * Not a false alarm, thus continue to use the global lock * mode. No need for complexmode_enter(), this was done by * the caller that has set use_global_mode to non-zero. */ return SEM_GLOBAL_LOCK; } } static inline void sem_unlock(struct sem_array *sma, int locknum) { if (locknum == SEM_GLOBAL_LOCK) { unmerge_queues(sma); complexmode_tryleave(sma); ipc_unlock_object(&sma->sem_perm); } else { struct sem *sem = &sma->sems[locknum]; spin_unlock(&sem->lock); } } /* * sem_lock_(check_) routines are called in the paths where the rwsem * is not held. * * The caller holds the RCU read lock. */ static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&sem_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct sem_array, sem_perm); } static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&sem_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct sem_array, sem_perm); } static inline void sem_lock_and_putref(struct sem_array *sma) { sem_lock(sma, NULL, -1); ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); } static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) { ipc_rmid(&sem_ids(ns), &s->sem_perm); } static struct sem_array *sem_alloc(size_t nsems) { struct sem_array *sma; if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0])) return NULL; sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL_ACCOUNT); if (unlikely(!sma)) return NULL; return sma; } /** * newary - Create a new semaphore set * @ns: namespace * @params: ptr to the structure that contains key, semflg and nsems * * Called with sem_ids.rwsem held (as a writer) */ static int newary(struct ipc_namespace *ns, struct ipc_params *params) { int retval; struct sem_array *sma; key_t key = params->key; int nsems = params->u.nsems; int semflg = params->flg; int i; if (!nsems) return -EINVAL; if (ns->used_sems + nsems > ns->sc_semmns) return -ENOSPC; sma = sem_alloc(nsems); if (!sma) return -ENOMEM; sma->sem_perm.mode = (semflg & S_IRWXUGO); sma->sem_perm.key = key; sma->sem_perm.security = NULL; retval = security_sem_alloc(&sma->sem_perm); if (retval) { kvfree(sma); return retval; } for (i = 0; i < nsems; i++) { INIT_LIST_HEAD(&sma->sems[i].pending_alter); INIT_LIST_HEAD(&sma->sems[i].pending_const); spin_lock_init(&sma->sems[i].lock); } sma->complex_count = 0; sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS; INIT_LIST_HEAD(&sma->pending_alter); INIT_LIST_HEAD(&sma->pending_const); INIT_LIST_HEAD(&sma->list_id); sma->sem_nsems = nsems; sma->sem_ctime = ktime_get_real_seconds(); /* ipc_addid() locks sma upon success. */ retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); if (retval < 0) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return retval; } ns->used_sems += nsems; sem_unlock(sma, -1); rcu_read_unlock(); return sma->sem_perm.id; } /* * Called with sem_ids.rwsem and ipcp locked. */ static int sem_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) { struct sem_array *sma; sma = container_of(ipcp, struct sem_array, sem_perm); if (params->u.nsems > sma->sem_nsems) return -EINVAL; return 0; } long ksys_semget(key_t key, int nsems, int semflg) { struct ipc_namespace *ns; static const struct ipc_ops sem_ops = { .getnew = newary, .associate = security_sem_associate, .more_checks = sem_more_checks, }; struct ipc_params sem_params; ns = current->nsproxy->ipc_ns; if (nsems < 0 || nsems > ns->sc_semmsl) return -EINVAL; sem_params.key = key; sem_params.flg = semflg; sem_params.u.nsems = nsems; return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params); } SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) { return ksys_semget(key, nsems, semflg); } /** * perform_atomic_semop[_slow] - Attempt to perform semaphore * operations on a given array. * @sma: semaphore array * @q: struct sem_queue that describes the operation * * Caller blocking are as follows, based the value * indicated by the semaphore operation (sem_op): * * (1) >0 never blocks. * (2) 0 (wait-for-zero operation): semval is non-zero. * (3) <0 attempting to decrement semval to a value smaller than zero. * * Returns 0 if the operation was possible. * Returns 1 if the operation is impossible, the caller must sleep. * Returns <0 for error codes. */ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q) { int result, sem_op, nsops; struct pid *pid; struct sembuf *sop; struct sem *curr; struct sembuf *sops; struct sem_undo *un; sops = q->sops; nsops = q->nsops; un = q->undo; for (sop = sops; sop < sops + nsops; sop++) { int idx = array_index_nospec(sop->sem_num, sma->sem_nsems); curr = &sma->sems[idx]; sem_op = sop->sem_op; result = curr->semval; if (!sem_op && result) goto would_block; result += sem_op; if (result < 0) goto would_block; if (result > SEMVMX) goto out_of_range; if (sop->sem_flg & SEM_UNDO) { int undo = un->semadj[sop->sem_num] - sem_op; /* Exceeding the undo range is an error. */ if (undo < (-SEMAEM - 1) || undo > SEMAEM) goto out_of_range; un->semadj[sop->sem_num] = undo; } curr->semval = result; } sop--; pid = q->pid; while (sop >= sops) { ipc_update_pid(&sma->sems[sop->sem_num].sempid, pid); sop--; } return 0; out_of_range: result = -ERANGE; goto undo; would_block: q->blocking = sop; if (sop->sem_flg & IPC_NOWAIT) result = -EAGAIN; else result = 1; undo: sop--; while (sop >= sops) { sem_op = sop->sem_op; sma->sems[sop->sem_num].semval -= sem_op; if (sop->sem_flg & SEM_UNDO) un->semadj[sop->sem_num] += sem_op; sop--; } return result; } static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q) { int result, sem_op, nsops; struct sembuf *sop; struct sem *curr; struct sembuf *sops; struct sem_undo *un; sops = q->sops; nsops = q->nsops; un = q->undo; if (unlikely(q->dupsop)) return perform_atomic_semop_slow(sma, q); /* * We scan the semaphore set twice, first to ensure that the entire * operation can succeed, therefore avoiding any pointless writes * to shared memory and having to undo such changes in order to block * until the operations can go through. */ for (sop = sops; sop < sops + nsops; sop++) { int idx = array_index_nospec(sop->sem_num, sma->sem_nsems); curr = &sma->sems[idx]; sem_op = sop->sem_op; result = curr->semval; if (!sem_op && result) goto would_block; /* wait-for-zero */ result += sem_op; if (result < 0) goto would_block; if (result > SEMVMX) return -ERANGE; if (sop->sem_flg & SEM_UNDO) { int undo = un->semadj[sop->sem_num] - sem_op; /* Exceeding the undo range is an error. */ if (undo < (-SEMAEM - 1) || undo > SEMAEM) return -ERANGE; } } for (sop = sops; sop < sops + nsops; sop++) { curr = &sma->sems[sop->sem_num]; sem_op = sop->sem_op; result = curr->semval; if (sop->sem_flg & SEM_UNDO) { int undo = un->semadj[sop->sem_num] - sem_op; un->semadj[sop->sem_num] = undo; } curr->semval += sem_op; ipc_update_pid(&curr->sempid, q->pid); } return 0; would_block: q->blocking = sop; return sop->sem_flg & IPC_NOWAIT ? -EAGAIN : 1; } static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error, struct wake_q_head *wake_q) { struct task_struct *sleeper; sleeper = get_task_struct(q->sleeper); /* see SEM_BARRIER_2 for purpose/pairing */ smp_store_release(&q->status, error); wake_q_add_safe(wake_q, sleeper); } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) { list_del(&q->list); if (q->nsops > 1) sma->complex_count--; } /** check_restart(sma, q) * @sma: semaphore array * @q: the operation that just completed * * update_queue is O(N^2) when it restarts scanning the whole queue of * waiting operations. Therefore this function checks if the restart is * really necessary. It is called after a previously waiting operation * modified the array. * Note that wait-for-zero operations are handled without restart. */ static inline int check_restart(struct sem_array *sma, struct sem_queue *q) { /* pending complex alter operations are too difficult to analyse */ if (!list_empty(&sma->pending_alter)) return 1; /* we were a sleeping complex operation. Too difficult */ if (q->nsops > 1) return 1; /* It is impossible that someone waits for the new value: * - complex operations always restart. * - wait-for-zero are handled separately. * - q is a previously sleeping simple operation that * altered the array. It must be a decrement, because * simple increments never sleep. * - If there are older (higher priority) decrements * in the queue, then they have observed the original * semval value and couldn't proceed. The operation * decremented to value - thus they won't proceed either. */ return 0; } /** * wake_const_ops - wake up non-alter tasks * @sma: semaphore array. * @semnum: semaphore that was modified. * @wake_q: lockless wake-queue head. * * wake_const_ops must be called after a semaphore in a semaphore array * was set to 0. If complex const operations are pending, wake_const_ops must * be called with semnum = -1, as well as with the number of each modified * semaphore. * The tasks that must be woken up are added to @wake_q. The return code * is stored in q->pid. * The function returns 1 if at least one operation was completed successfully. */ static int wake_const_ops(struct sem_array *sma, int semnum, struct wake_q_head *wake_q) { struct sem_queue *q, *tmp; struct list_head *pending_list; int semop_completed = 0; if (semnum == -1) pending_list = &sma->pending_const; else pending_list = &sma->sems[semnum].pending_const; list_for_each_entry_safe(q, tmp, pending_list, list) { int error = perform_atomic_semop(sma, q); if (error > 0) continue; /* operation completed, remove from queue & wakeup */ unlink_queue(sma, q); wake_up_sem_queue_prepare(q, error, wake_q); if (error == 0) semop_completed = 1; } return semop_completed; } /** * do_smart_wakeup_zero - wakeup all wait for zero tasks * @sma: semaphore array * @sops: operations that were performed * @nsops: number of operations * @wake_q: lockless wake-queue head * * Checks all required queue for wait-for-zero operations, based * on the actual changes that were performed on the semaphore array. * The function returns 1 if at least one operation was completed successfully. */ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops, int nsops, struct wake_q_head *wake_q) { int i; int semop_completed = 0; int got_zero = 0; /* first: the per-semaphore queues, if known */ if (sops) { for (i = 0; i < nsops; i++) { int num = sops[i].sem_num; if (sma->sems[num].semval == 0) { got_zero = 1; semop_completed |= wake_const_ops(sma, num, wake_q); } } } else { /* * No sops means modified semaphores not known. * Assume all were changed. */ for (i = 0; i < sma->sem_nsems; i++) { if (sma->sems[i].semval == 0) { got_zero = 1; semop_completed |= wake_const_ops(sma, i, wake_q); } } } /* * If one of the modified semaphores got 0, * then check the global queue, too. */ if (got_zero) semop_completed |= wake_const_ops(sma, -1, wake_q); return semop_completed; } /** * update_queue - look for tasks that can be completed. * @sma: semaphore array. * @semnum: semaphore that was modified. * @wake_q: lockless wake-queue head. * * update_queue must be called after a semaphore in a semaphore array * was modified. If multiple semaphores were modified, update_queue must * be called with semnum = -1, as well as with the number of each modified * semaphore. * The tasks that must be woken up are added to @wake_q. The return code * is stored in q->pid. * The function internally checks if const operations can now succeed. * * The function return 1 if at least one semop was completed successfully. */ static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *wake_q) { struct sem_queue *q, *tmp; struct list_head *pending_list; int semop_completed = 0; if (semnum == -1) pending_list = &sma->pending_alter; else pending_list = &sma->sems[semnum].pending_alter; again: list_for_each_entry_safe(q, tmp, pending_list, list) { int error, restart; /* If we are scanning the single sop, per-semaphore list of * one semaphore and that semaphore is 0, then it is not * necessary to scan further: simple increments * that affect only one entry succeed immediately and cannot * be in the per semaphore pending queue, and decrements * cannot be successful if the value is already 0. */ if (semnum != -1 && sma->sems[semnum].semval == 0) break; error = perform_atomic_semop(sma, q); /* Does q->sleeper still need to sleep? */ if (error > 0) continue; unlink_queue(sma, q); if (error) { restart = 0; } else { semop_completed = 1; do_smart_wakeup_zero(sma, q->sops, q->nsops, wake_q); restart = check_restart(sma, q); } wake_up_sem_queue_prepare(q, error, wake_q); if (restart) goto again; } return semop_completed; } /** * set_semotime - set sem_otime * @sma: semaphore array * @sops: operations that modified the array, may be NULL * * sem_otime is replicated to avoid cache line trashing. * This function sets one instance to the current time. */ static void set_semotime(struct sem_array *sma, struct sembuf *sops) { if (sops == NULL) { sma->sems[0].sem_otime = ktime_get_real_seconds(); } else { sma->sems[sops[0].sem_num].sem_otime = ktime_get_real_seconds(); } } /** * do_smart_update - optimized update_queue * @sma: semaphore array * @sops: operations that were performed * @nsops: number of operations * @otime: force setting otime * @wake_q: lockless wake-queue head * * do_smart_update() does the required calls to update_queue and wakeup_zero, * based on the actual changes that were performed on the semaphore array. * Note that the function does not do the actual wake-up: the caller is * responsible for calling wake_up_q(). * It is safe to perform this call after dropping all locks. */ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsops, int otime, struct wake_q_head *wake_q) { int i; otime |= do_smart_wakeup_zero(sma, sops, nsops, wake_q); if (!list_empty(&sma->pending_alter)) { /* semaphore array uses the global queue - just process it. */ otime |= update_queue(sma, -1, wake_q); } else { if (!sops) { /* * No sops, thus the modified semaphores are not * known. Check all. */ for (i = 0; i < sma->sem_nsems; i++) otime |= update_queue(sma, i, wake_q); } else { /* * Check the semaphores that were increased: * - No complex ops, thus all sleeping ops are * decrease. * - if we decreased the value, then any sleeping * semaphore ops won't be able to run: If the * previous value was too small, then the new * value will be too small, too. */ for (i = 0; i < nsops; i++) { if (sops[i].sem_op > 0) { otime |= update_queue(sma, sops[i].sem_num, wake_q); } } } } if (otime) set_semotime(sma, sops); } /* * check_qop: Test if a queued operation sleeps on the semaphore semnum */ static int check_qop(struct sem_array *sma, int semnum, struct sem_queue *q, bool count_zero) { struct sembuf *sop = q->blocking; /* * Linux always (since 0.99.10) reported a task as sleeping on all * semaphores. This violates SUS, therefore it was changed to the * standard compliant behavior. * Give the administrators a chance to notice that an application * might misbehave because it relies on the Linux behavior. */ pr_info_once("semctl(GETNCNT/GETZCNT) is since 3.16 Single Unix Specification compliant.\n" "The task %s (%d) triggered the difference, watch for misbehavior.\n", current->comm, task_pid_nr(current)); if (sop->sem_num != semnum) return 0; if (count_zero && sop->sem_op == 0) return 1; if (!count_zero && sop->sem_op < 0) return 1; return 0; } /* The following counts are associated to each semaphore: * semncnt number of tasks waiting on semval being nonzero * semzcnt number of tasks waiting on semval being zero * * Per definition, a task waits only on the semaphore of the first semop * that cannot proceed, even if additional operation would block, too. */ static int count_semcnt(struct sem_array *sma, ushort semnum, bool count_zero) { struct list_head *l; struct sem_queue *q; int semcnt; semcnt = 0; /* First: check the simple operations. They are easy to evaluate */ if (count_zero) l = &sma->sems[semnum].pending_const; else l = &sma->sems[semnum].pending_alter; list_for_each_entry(q, l, list) { /* all task on a per-semaphore list sleep on exactly * that semaphore */ semcnt++; } /* Then: check the complex operations. */ list_for_each_entry(q, &sma->pending_alter, list) { semcnt += check_qop(sma, semnum, q, count_zero); } if (count_zero) { list_for_each_entry(q, &sma->pending_const, list) { semcnt += check_qop(sma, semnum, q, count_zero); } } return semcnt; } /* Free a semaphore set. freeary() is called with sem_ids.rwsem locked * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem * remains locked on exit. */ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct sem_undo *un, *tu; struct sem_queue *q, *tq; struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm); int i; DEFINE_WAKE_Q(wake_q); /* Free the existing undo structures for this semaphore set. */ ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry_safe(un, tu, &sma->list_id, list_id) { list_del(&un->list_id); spin_lock(&un->ulp->lock); un->semid = -1; list_del_rcu(&un->list_proc); spin_unlock(&un->ulp->lock); kvfree_rcu(un, rcu); } /* Wake up all pending processes and let them fail with EIDRM. */ list_for_each_entry_safe(q, tq, &sma->pending_const, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } for (i = 0; i < sma->sem_nsems; i++) { struct sem *sem = &sma->sems[i]; list_for_each_entry_safe(q, tq, &sem->pending_const, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } list_for_each_entry_safe(q, tq, &sem->pending_alter, list) { unlink_queue(sma, q); wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); } ipc_update_pid(&sem->sempid, NULL); } /* Remove the semaphore set from the IDR */ sem_rmid(ns, sma); sem_unlock(sma, -1); rcu_read_unlock(); wake_up_q(&wake_q); ns->used_sems -= sma->sem_nsems; ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); } static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct semid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->sem_perm, &out.sem_perm); out.sem_otime = in->sem_otime; out.sem_ctime = in->sem_ctime; out.sem_nsems = in->sem_nsems; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } static time64_t get_semotime(struct sem_array *sma) { int i; time64_t res; res = sma->sems[0].sem_otime; for (i = 1; i < sma->sem_nsems; i++) { time64_t to = sma->sems[i].sem_otime; if (to > res) res = to; } return res; } static int semctl_stat(struct ipc_namespace *ns, int semid, int cmd, struct semid64_ds *semid64) { struct sem_array *sma; time64_t semotime; int err; memset(semid64, 0, sizeof(*semid64)); rcu_read_lock(); if (cmd == SEM_STAT || cmd == SEM_STAT_ANY) { sma = sem_obtain_object(ns, semid); if (IS_ERR(sma)) { err = PTR_ERR(sma); goto out_unlock; } } else { /* IPC_STAT */ sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { err = PTR_ERR(sma); goto out_unlock; } } /* see comment for SHM_STAT_ANY */ if (cmd == SEM_STAT_ANY) audit_ipc_obj(&sma->sem_perm); else { err = -EACCES; if (ipcperms(ns, &sma->sem_perm, S_IRUGO)) goto out_unlock; } err = security_sem_semctl(&sma->sem_perm, cmd); if (err) goto out_unlock; ipc_lock_object(&sma->sem_perm); if (!ipc_valid_object(&sma->sem_perm)) { ipc_unlock_object(&sma->sem_perm); err = -EIDRM; goto out_unlock; } kernel_to_ipc64_perm(&sma->sem_perm, &semid64->sem_perm); semotime = get_semotime(sma); semid64->sem_otime = semotime; semid64->sem_ctime = sma->sem_ctime; #ifndef CONFIG_64BIT semid64->sem_otime_high = semotime >> 32; semid64->sem_ctime_high = sma->sem_ctime >> 32; #endif semid64->sem_nsems = sma->sem_nsems; if (cmd == IPC_STAT) { /* * As defined in SUS: * Return 0 on success */ err = 0; } else { /* * SEM_STAT and SEM_STAT_ANY (both Linux specific) * Return the full id, including the sequence number */ err = sma->sem_perm.id; } ipc_unlock_object(&sma->sem_perm); out_unlock: rcu_read_unlock(); return err; } static int semctl_info(struct ipc_namespace *ns, int semid, int cmd, void __user *p) { struct seminfo seminfo; int max_idx; int err; err = security_sem_semctl(NULL, cmd); if (err) return err; memset(&seminfo, 0, sizeof(seminfo)); seminfo.semmni = ns->sc_semmni; seminfo.semmns = ns->sc_semmns; seminfo.semmsl = ns->sc_semmsl; seminfo.semopm = ns->sc_semopm; seminfo.semvmx = SEMVMX; seminfo.semmnu = SEMMNU; seminfo.semmap = SEMMAP; seminfo.semume = SEMUME; down_read(&sem_ids(ns).rwsem); if (cmd == SEM_INFO) { seminfo.semusz = sem_ids(ns).in_use; seminfo.semaem = ns->used_sems; } else { seminfo.semusz = SEMUSZ; seminfo.semaem = SEMAEM; } max_idx = ipc_get_maxidx(&sem_ids(ns)); up_read(&sem_ids(ns).rwsem); if (copy_to_user(p, &seminfo, sizeof(struct seminfo))) return -EFAULT; return (max_idx < 0) ? 0 : max_idx; } static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum, int val) { struct sem_undo *un; struct sem_array *sma; struct sem *curr; int err; DEFINE_WAKE_Q(wake_q); if (val > SEMVMX || val < 0) return -ERANGE; rcu_read_lock(); sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { rcu_read_unlock(); return PTR_ERR(sma); } if (semnum < 0 || semnum >= sma->sem_nsems) { rcu_read_unlock(); return -EINVAL; } if (ipcperms(ns, &sma->sem_perm, S_IWUGO)) { rcu_read_unlock(); return -EACCES; } err = security_sem_semctl(&sma->sem_perm, SETVAL); if (err) { rcu_read_unlock(); return -EACCES; } sem_lock(sma, NULL, -1); if (!ipc_valid_object(&sma->sem_perm)) { sem_unlock(sma, -1); rcu_read_unlock(); return -EIDRM; } semnum = array_index_nospec(semnum, sma->sem_nsems); curr = &sma->sems[semnum]; ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry(un, &sma->list_id, list_id) un->semadj[semnum] = 0; curr->semval = val; ipc_update_pid(&curr->sempid, task_tgid(current)); sma->sem_ctime = ktime_get_real_seconds(); /* maybe some queued-up processes were waiting for this */ do_smart_update(sma, NULL, 0, 0, &wake_q); sem_unlock(sma, -1); rcu_read_unlock(); wake_up_q(&wake_q); return 0; } static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, int cmd, void __user *p) { struct sem_array *sma; struct sem *curr; int err, nsems; ushort fast_sem_io[SEMMSL_FAST]; ushort *sem_io = fast_sem_io; DEFINE_WAKE_Q(wake_q); rcu_read_lock(); sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { rcu_read_unlock(); return PTR_ERR(sma); } nsems = sma->sem_nsems; err = -EACCES; if (ipcperms(ns, &sma->sem_perm, cmd == SETALL ? S_IWUGO : S_IRUGO)) goto out_rcu_wakeup; err = security_sem_semctl(&sma->sem_perm, cmd); if (err) goto out_rcu_wakeup; err = -EACCES; switch (cmd) { case GETALL: { ushort __user *array = p; int i; sem_lock(sma, NULL, -1); if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } if (nsems > SEMMSL_FAST) { if (!ipc_rcu_getref(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } sem_unlock(sma, -1); rcu_read_unlock(); sem_io = kvmalloc_array(nsems, sizeof(ushort), GFP_KERNEL); if (sem_io == NULL) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; } rcu_read_lock(); sem_lock_and_putref(sma); if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } } for (i = 0; i < sma->sem_nsems; i++) sem_io[i] = sma->sems[i].semval; sem_unlock(sma, -1); rcu_read_unlock(); err = 0; if (copy_to_user(array, sem_io, nsems*sizeof(ushort))) err = -EFAULT; goto out_free; } case SETALL: { int i; struct sem_undo *un; if (!ipc_rcu_getref(&sma->sem_perm)) { err = -EIDRM; goto out_rcu_wakeup; } rcu_read_unlock(); if (nsems > SEMMSL_FAST) { sem_io = kvmalloc_array(nsems, sizeof(ushort), GFP_KERNEL); if (sem_io == NULL) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return -ENOMEM; } } if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); err = -EFAULT; goto out_free; } for (i = 0; i < nsems; i++) { if (sem_io[i] > SEMVMX) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); err = -ERANGE; goto out_free; } } rcu_read_lock(); sem_lock_and_putref(sma); if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } for (i = 0; i < nsems; i++) { sma->sems[i].semval = sem_io[i]; ipc_update_pid(&sma->sems[i].sempid, task_tgid(current)); } ipc_assert_locked_object(&sma->sem_perm); list_for_each_entry(un, &sma->list_id, list_id) { for (i = 0; i < nsems; i++) un->semadj[i] = 0; } sma->sem_ctime = ktime_get_real_seconds(); /* maybe some queued-up processes were waiting for this */ do_smart_update(sma, NULL, 0, 0, &wake_q); err = 0; goto out_unlock; } /* GETVAL, GETPID, GETNCTN, GETZCNT: fall-through */ } err = -EINVAL; if (semnum < 0 || semnum >= nsems) goto out_rcu_wakeup; sem_lock(sma, NULL, -1); if (!ipc_valid_object(&sma->sem_perm)) { err = -EIDRM; goto out_unlock; } semnum = array_index_nospec(semnum, nsems); curr = &sma->sems[semnum]; switch (cmd) { case GETVAL: err = curr->semval; goto out_unlock; case GETPID: err = pid_vnr(curr->sempid); goto out_unlock; case GETNCNT: err = count_semcnt(sma, semnum, 0); goto out_unlock; case GETZCNT: err = count_semcnt(sma, semnum, 1); goto out_unlock; } out_unlock: sem_unlock(sma, -1); out_rcu_wakeup: rcu_read_unlock(); wake_up_q(&wake_q); out_free: if (sem_io != fast_sem_io) kvfree(sem_io); return err; } static inline unsigned long copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct semid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->sem_perm.uid = tbuf_old.sem_perm.uid; out->sem_perm.gid = tbuf_old.sem_perm.gid; out->sem_perm.mode = tbuf_old.sem_perm.mode; return 0; } default: return -EINVAL; } } /* * This function handles some semctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int semctl_down(struct ipc_namespace *ns, int semid, int cmd, struct semid64_ds *semid64) { struct sem_array *sma; int err; struct kern_ipc_perm *ipcp; down_write(&sem_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &sem_ids(ns), semid, cmd, &semid64->sem_perm, 0); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } sma = container_of(ipcp, struct sem_array, sem_perm); err = security_sem_semctl(&sma->sem_perm, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: sem_lock(sma, NULL, -1); /* freeary unlocks the ipc object and rcu */ freeary(ns, ipcp); goto out_up; case IPC_SET: sem_lock(sma, NULL, -1); err = ipc_update_perm(&semid64->sem_perm, ipcp); if (err) goto out_unlock0; sma->sem_ctime = ktime_get_real_seconds(); break; default: err = -EINVAL; goto out_unlock1; } out_unlock0: sem_unlock(sma, -1); out_unlock1: rcu_read_unlock(); out_up: up_write(&sem_ids(ns).rwsem); return err; } static long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg, int version) { struct ipc_namespace *ns; void __user *p = (void __user *)arg; struct semid64_ds semid64; int err; if (semid < 0) return -EINVAL; ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: case SEM_INFO: return semctl_info(ns, semid, cmd, p); case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: err = semctl_stat(ns, semid, cmd, &semid64); if (err < 0) return err; if (copy_semid_to_user(p, &semid64, version)) err = -EFAULT; return err; case GETALL: case GETVAL: case GETPID: case GETNCNT: case GETZCNT: case SETALL: return semctl_main(ns, semid, semnum, cmd, p); case SETVAL: { int val; #if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN) /* big-endian 64bit */ val = arg >> 32; #else /* 32bit or little-endian 64bit */ val = arg; #endif return semctl_setval(ns, semid, semnum, val); } case IPC_SET: if (copy_semid_from_user(&semid64, p, version)) return -EFAULT; fallthrough; case IPC_RMID: return semctl_down(ns, semid, cmd, &semid64); default: return -EINVAL; } } SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) { return ksys_semctl(semid, semnum, cmd, arg, IPC_64); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION long ksys_old_semctl(int semid, int semnum, int cmd, unsigned long arg) { int version = ipc_parse_version(&cmd); return ksys_semctl(semid, semnum, cmd, arg, version); } SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) { return ksys_old_semctl(semid, semnum, cmd, arg); } #endif #ifdef CONFIG_COMPAT struct compat_semid_ds { struct compat_ipc_perm sem_perm; old_time32_t sem_otime; old_time32_t sem_ctime; compat_uptr_t sem_base; compat_uptr_t sem_pending; compat_uptr_t sem_pending_last; compat_uptr_t undo; unsigned short sem_nsems; }; static int copy_compat_semid_from_user(struct semid64_ds *out, void __user *buf, int version) { memset(out, 0, sizeof(*out)); if (version == IPC_64) { struct compat_semid64_ds __user *p = buf; return get_compat_ipc64_perm(&out->sem_perm, &p->sem_perm); } else { struct compat_semid_ds __user *p = buf; return get_compat_ipc_perm(&out->sem_perm, &p->sem_perm); } } static int copy_compat_semid_to_user(void __user *buf, struct semid64_ds *in, int version) { if (version == IPC_64) { struct compat_semid64_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc64_perm(&v.sem_perm, &in->sem_perm); v.sem_otime = lower_32_bits(in->sem_otime); v.sem_otime_high = upper_32_bits(in->sem_otime); v.sem_ctime = lower_32_bits(in->sem_ctime); v.sem_ctime_high = upper_32_bits(in->sem_ctime); v.sem_nsems = in->sem_nsems; return copy_to_user(buf, &v, sizeof(v)); } else { struct compat_semid_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc_perm(&v.sem_perm, &in->sem_perm); v.sem_otime = in->sem_otime; v.sem_ctime = in->sem_ctime; v.sem_nsems = in->sem_nsems; return copy_to_user(buf, &v, sizeof(v)); } } static long compat_ksys_semctl(int semid, int semnum, int cmd, int arg, int version) { void __user *p = compat_ptr(arg); struct ipc_namespace *ns; struct semid64_ds semid64; int err; ns = current->nsproxy->ipc_ns; if (semid < 0) return -EINVAL; switch (cmd & (~IPC_64)) { case IPC_INFO: case SEM_INFO: return semctl_info(ns, semid, cmd, p); case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: err = semctl_stat(ns, semid, cmd, &semid64); if (err < 0) return err; if (copy_compat_semid_to_user(p, &semid64, version)) err = -EFAULT; return err; case GETVAL: case GETPID: case GETNCNT: case GETZCNT: case GETALL: case SETALL: return semctl_main(ns, semid, semnum, cmd, p); case SETVAL: return semctl_setval(ns, semid, semnum, arg); case IPC_SET: if (copy_compat_semid_from_user(&semid64, p, version)) return -EFAULT; fallthrough; case IPC_RMID: return semctl_down(ns, semid, cmd, &semid64); default: return -EINVAL; } } COMPAT_SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, int, arg) { return compat_ksys_semctl(semid, semnum, cmd, arg, IPC_64); } #ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg) { int version = compat_ipc_parse_version(&cmd); return compat_ksys_semctl(semid, semnum, cmd, arg, version); } COMPAT_SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, int, arg) { return compat_ksys_old_semctl(semid, semnum, cmd, arg); } #endif #endif /* If the task doesn't already have a undo_list, then allocate one * here. We guarantee there is only one thread using this undo list, * and current is THE ONE * * If this allocation and assignment succeeds, but later * portions of this code fail, there is no need to free the sem_undo_list. * Just let it stay associated with the task, and it'll be freed later * at exit time. * * This can block, so callers must hold no locks. */ static inline int get_undo_list(struct sem_undo_list **undo_listp) { struct sem_undo_list *undo_list; undo_list = current->sysvsem.undo_list; if (!undo_list) { undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL_ACCOUNT); if (undo_list == NULL) return -ENOMEM; spin_lock_init(&undo_list->lock); refcount_set(&undo_list->refcnt, 1); INIT_LIST_HEAD(&undo_list->list_proc); current->sysvsem.undo_list = undo_list; } *undo_listp = undo_list; return 0; } static struct sem_undo *__lookup_undo(struct sem_undo_list *ulp, int semid) { struct sem_undo *un; list_for_each_entry_rcu(un, &ulp->list_proc, list_proc, spin_is_locked(&ulp->lock)) { if (un->semid == semid) return un; } return NULL; } static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid) { struct sem_undo *un; assert_spin_locked(&ulp->lock); un = __lookup_undo(ulp, semid); if (un) { list_del_rcu(&un->list_proc); list_add_rcu(&un->list_proc, &ulp->list_proc); } return un; } /** * find_alloc_undo - lookup (and if not present create) undo array * @ns: namespace * @semid: semaphore array id * * The function looks up (and if not present creates) the undo structure. * The size of the undo structure depends on the size of the semaphore * array, thus the alloc path is not that straightforward. * Lifetime-rules: sem_undo is rcu-protected, on success, the function * performs a rcu_read_lock(). */ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) { struct sem_array *sma; struct sem_undo_list *ulp; struct sem_undo *un, *new; int nsems, error; error = get_undo_list(&ulp); if (error) return ERR_PTR(error); rcu_read_lock(); spin_lock(&ulp->lock); un = lookup_undo(ulp, semid); spin_unlock(&ulp->lock); if (likely(un != NULL)) goto out; /* no undo structure around - allocate one. */ /* step 1: figure out the size of the semaphore array */ sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { rcu_read_unlock(); return ERR_CAST(sma); } nsems = sma->sem_nsems; if (!ipc_rcu_getref(&sma->sem_perm)) { rcu_read_unlock(); un = ERR_PTR(-EIDRM); goto out; } rcu_read_unlock(); /* step 2: allocate new undo structure */ new = kvzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL_ACCOUNT); if (!new) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return ERR_PTR(-ENOMEM); } /* step 3: Acquire the lock on semaphore array */ rcu_read_lock(); sem_lock_and_putref(sma); if (!ipc_valid_object(&sma->sem_perm)) { sem_unlock(sma, -1); rcu_read_unlock(); kvfree(new); un = ERR_PTR(-EIDRM); goto out; } spin_lock(&ulp->lock); /* * step 4: check for races: did someone else allocate the undo struct? */ un = lookup_undo(ulp, semid); if (un) { spin_unlock(&ulp->lock); kvfree(new); goto success; } /* step 5: initialize & link new undo structure */ new->semadj = (short *) &new[1]; new->ulp = ulp; new->semid = semid; assert_spin_locked(&ulp->lock); list_add_rcu(&new->list_proc, &ulp->list_proc); ipc_assert_locked_object(&sma->sem_perm); list_add(&new->list_id, &sma->list_id); un = new; spin_unlock(&ulp->lock); success: sem_unlock(sma, -1); out: return un; } long __do_semtimedop(int semid, struct sembuf *sops, unsigned nsops, const struct timespec64 *timeout, struct ipc_namespace *ns) { int error = -EINVAL; struct sem_array *sma; struct sembuf *sop; struct sem_undo *un; int max, locknum; bool undos = false, alter = false, dupsop = false; struct sem_queue queue; unsigned long dup = 0, jiffies_left = 0; if (nsops < 1 || semid < 0) return -EINVAL; if (nsops > ns->sc_semopm) return -E2BIG; if (timeout) { if (timeout->tv_sec < 0 || timeout->tv_nsec < 0 || timeout->tv_nsec >= 1000000000L) { error = -EINVAL; goto out; } jiffies_left = timespec64_to_jiffies(timeout); } max = 0; for (sop = sops; sop < sops + nsops; sop++) { unsigned long mask = 1ULL << ((sop->sem_num) % BITS_PER_LONG); if (sop->sem_num >= max) max = sop->sem_num; if (sop->sem_flg & SEM_UNDO) undos = true; if (dup & mask) { /* * There was a previous alter access that appears * to have accessed the same semaphore, thus use * the dupsop logic. "appears", because the detection * can only check % BITS_PER_LONG. */ dupsop = true; } if (sop->sem_op != 0) { alter = true; dup |= mask; } } if (undos) { /* On success, find_alloc_undo takes the rcu_read_lock */ un = find_alloc_undo(ns, semid); if (IS_ERR(un)) { error = PTR_ERR(un); goto out; } } else { un = NULL; rcu_read_lock(); } sma = sem_obtain_object_check(ns, semid); if (IS_ERR(sma)) { rcu_read_unlock(); error = PTR_ERR(sma); goto out; } error = -EFBIG; if (max >= sma->sem_nsems) { rcu_read_unlock(); goto out; } error = -EACCES; if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO)) { rcu_read_unlock(); goto out; } error = security_sem_semop(&sma->sem_perm, sops, nsops, alter); if (error) { rcu_read_unlock(); goto out; } error = -EIDRM; locknum = sem_lock(sma, sops, nsops); /* * We eventually might perform the following check in a lockless * fashion, considering ipc_valid_object() locking constraints. * If nsops == 1 and there is no contention for sem_perm.lock, then * only a per-semaphore lock is held and it's OK to proceed with the * check below. More details on the fine grained locking scheme * entangled here and why it's RMID race safe on comments at sem_lock() */ if (!ipc_valid_object(&sma->sem_perm)) goto out_unlock; /* * semid identifiers are not unique - find_alloc_undo may have * allocated an undo structure, it was invalidated by an RMID * and now a new array with received the same id. Check and fail. * This case can be detected checking un->semid. The existence of * "un" itself is guaranteed by rcu. */ if (un && un->semid == -1) goto out_unlock; queue.sops = sops; queue.nsops = nsops; queue.undo = un; queue.pid = task_tgid(current); queue.alter = alter; queue.dupsop = dupsop; error = perform_atomic_semop(sma, &queue); if (error == 0) { /* non-blocking successful path */ DEFINE_WAKE_Q(wake_q); /* * If the operation was successful, then do * the required updates. */ if (alter) do_smart_update(sma, sops, nsops, 1, &wake_q); else set_semotime(sma, sops); sem_unlock(sma, locknum); rcu_read_unlock(); wake_up_q(&wake_q); goto out; } if (error < 0) /* non-blocking error path */ goto out_unlock; /* * We need to sleep on this operation, so we put the current * task into the pending queue and go to sleep. */ if (nsops == 1) { struct sem *curr; int idx = array_index_nospec(sops->sem_num, sma->sem_nsems); curr = &sma->sems[idx]; if (alter) { if (sma->complex_count) { list_add_tail(&queue.list, &sma->pending_alter); } else { list_add_tail(&queue.list, &curr->pending_alter); } } else { list_add_tail(&queue.list, &curr->pending_const); } } else { if (!sma->complex_count) merge_queues(sma); if (alter) list_add_tail(&queue.list, &sma->pending_alter); else list_add_tail(&queue.list, &sma->pending_const); sma->complex_count++; } do { /* memory ordering ensured by the lock in sem_lock() */ WRITE_ONCE(queue.status, -EINTR); queue.sleeper = current; /* memory ordering is ensured by the lock in sem_lock() */ __set_current_state(TASK_INTERRUPTIBLE); sem_unlock(sma, locknum); rcu_read_unlock(); if (timeout) jiffies_left = schedule_timeout(jiffies_left); else schedule(); /* * fastpath: the semop has completed, either successfully or * not, from the syscall pov, is quite irrelevant to us at this * point; we're done. * * We _do_ care, nonetheless, about being awoken by a signal or * spuriously. The queue.status is checked again in the * slowpath (aka after taking sem_lock), such that we can detect * scenarios where we were awakened externally, during the * window between wake_q_add() and wake_up_q(). */ rcu_read_lock(); error = READ_ONCE(queue.status); if (error != -EINTR) { /* see SEM_BARRIER_2 for purpose/pairing */ smp_acquire__after_ctrl_dep(); rcu_read_unlock(); goto out; } locknum = sem_lock(sma, sops, nsops); if (!ipc_valid_object(&sma->sem_perm)) goto out_unlock; /* * No necessity for any barrier: We are protect by sem_lock() */ error = READ_ONCE(queue.status); /* * If queue.status != -EINTR we are woken up by another process. * Leave without unlink_queue(), but with sem_unlock(). */ if (error != -EINTR) goto out_unlock; /* * If an interrupt occurred we have to clean up the queue. */ if (timeout && jiffies_left == 0) error = -EAGAIN; } while (error == -EINTR && !signal_pending(current)); /* spurious */ unlink_queue(sma, &queue); out_unlock: sem_unlock(sma, locknum); rcu_read_unlock(); out: return error; } static long do_semtimedop(int semid, struct sembuf __user *tsops, unsigned nsops, const struct timespec64 *timeout) { struct sembuf fast_sops[SEMOPM_FAST]; struct sembuf *sops = fast_sops; struct ipc_namespace *ns; int ret; ns = current->nsproxy->ipc_ns; if (nsops > ns->sc_semopm) return -E2BIG; if (nsops < 1) return -EINVAL; if (nsops > SEMOPM_FAST) { sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); if (sops == NULL) return -ENOMEM; } if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) { ret = -EFAULT; goto out_free; } ret = __do_semtimedop(semid, sops, nsops, timeout, ns); out_free: if (sops != fast_sops) kvfree(sops); return ret; } long ksys_semtimedop(int semid, struct sembuf __user *tsops, unsigned int nsops, const struct __kernel_timespec __user *timeout) { if (timeout) { struct timespec64 ts; if (get_timespec64(&ts, timeout)) return -EFAULT; return do_semtimedop(semid, tsops, nsops, &ts); } return do_semtimedop(semid, tsops, nsops, NULL); } SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, unsigned int, nsops, const struct __kernel_timespec __user *, timeout) { return ksys_semtimedop(semid, tsops, nsops, timeout); } #ifdef CONFIG_COMPAT_32BIT_TIME long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, unsigned int nsops, const struct old_timespec32 __user *timeout) { if (timeout) { struct timespec64 ts; if (get_old_timespec32(&ts, timeout)) return -EFAULT; return do_semtimedop(semid, tsems, nsops, &ts); } return do_semtimedop(semid, tsems, nsops, NULL); } SYSCALL_DEFINE4(semtimedop_time32, int, semid, struct sembuf __user *, tsems, unsigned int, nsops, const struct old_timespec32 __user *, timeout) { return compat_ksys_semtimedop(semid, tsems, nsops, timeout); } #endif SYSCALL_DEFINE3(semop, int, semid, struct sembuf __user *, tsops, unsigned, nsops) { return do_semtimedop(semid, tsops, nsops, NULL); } /* If CLONE_SYSVSEM is set, establish sharing of SEM_UNDO state between * parent and child tasks. */ int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) { struct sem_undo_list *undo_list; int error; if (clone_flags & CLONE_SYSVSEM) { error = get_undo_list(&undo_list); if (error) return error; refcount_inc(&undo_list->refcnt); tsk->sysvsem.undo_list = undo_list; } else tsk->sysvsem.undo_list = NULL; return 0; } /* * add semadj values to semaphores, free undo structures. * undo structures are not freed when semaphore arrays are destroyed * so some of them may be out of date. * IMPLEMENTATION NOTE: There is some confusion over whether the * set of adjustments that needs to be done should be done in an atomic * manner or not. That is, if we are attempting to decrement the semval * should we queue up and wait until we can do so legally? * The original implementation attempted to do this (queue and wait). * The current implementation does not do so. The POSIX standard * and SVID should be consulted to determine what behavior is mandated. */ void exit_sem(struct task_struct *tsk) { struct sem_undo_list *ulp; ulp = tsk->sysvsem.undo_list; if (!ulp) return; tsk->sysvsem.undo_list = NULL; if (!refcount_dec_and_test(&ulp->refcnt)) return; for (;;) { struct sem_array *sma; struct sem_undo *un; int semid, i; DEFINE_WAKE_Q(wake_q); cond_resched(); rcu_read_lock(); un = list_entry_rcu(ulp->list_proc.next, struct sem_undo, list_proc); if (&un->list_proc == &ulp->list_proc) { /* * We must wait for freeary() before freeing this ulp, * in case we raced with last sem_undo. There is a small * possibility where we exit while freeary() didn't * finish unlocking sem_undo_list. */ spin_lock(&ulp->lock); spin_unlock(&ulp->lock); rcu_read_unlock(); break; } spin_lock(&ulp->lock); semid = un->semid; spin_unlock(&ulp->lock); /* exit_sem raced with IPC_RMID, nothing to do */ if (semid == -1) { rcu_read_unlock(); continue; } sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid); /* exit_sem raced with IPC_RMID, nothing to do */ if (IS_ERR(sma)) { rcu_read_unlock(); continue; } sem_lock(sma, NULL, -1); /* exit_sem raced with IPC_RMID, nothing to do */ if (!ipc_valid_object(&sma->sem_perm)) { sem_unlock(sma, -1); rcu_read_unlock(); continue; } un = __lookup_undo(ulp, semid); if (un == NULL) { /* exit_sem raced with IPC_RMID+semget() that created * exactly the same semid. Nothing to do. */ sem_unlock(sma, -1); rcu_read_unlock(); continue; } /* remove un from the linked lists */ ipc_assert_locked_object(&sma->sem_perm); list_del(&un->list_id); spin_lock(&ulp->lock); list_del_rcu(&un->list_proc); spin_unlock(&ulp->lock); /* perform adjustments registered in un */ for (i = 0; i < sma->sem_nsems; i++) { struct sem *semaphore = &sma->sems[i]; if (un->semadj[i]) { semaphore->semval += un->semadj[i]; /* * Range checks of the new semaphore value, * not defined by sus: * - Some unices ignore the undo entirely * (e.g. HP UX 11i 11.22, Tru64 V5.1) * - some cap the value (e.g. FreeBSD caps * at 0, but doesn't enforce SEMVMX) * * Linux caps the semaphore value, both at 0 * and at SEMVMX. * * Manfred <manfred@colorfullife.com> */ if (semaphore->semval < 0) semaphore->semval = 0; if (semaphore->semval > SEMVMX) semaphore->semval = SEMVMX; ipc_update_pid(&semaphore->sempid, task_tgid(current)); } } /* maybe some queued-up processes were waiting for this */ do_smart_update(sma, NULL, 0, 1, &wake_q); sem_unlock(sma, -1); rcu_read_unlock(); wake_up_q(&wake_q); kvfree_rcu(un, rcu); } kfree(ulp); } #ifdef CONFIG_PROC_FS static int sysvipc_sem_proc_show(struct seq_file *s, void *it) { struct user_namespace *user_ns = seq_user_ns(s); struct kern_ipc_perm *ipcp = it; struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm); time64_t sem_otime; /* * The proc interface isn't aware of sem_lock(), it calls * ipc_lock_object(), i.e. spin_lock(&sma->sem_perm.lock). * (in sysvipc_find_ipc) * In order to stay compatible with sem_lock(), we must * enter / leave complex_mode. */ complexmode_enter(sma); sem_otime = get_semotime(sma); seq_printf(s, "%10d %10d %4o %10u %5u %5u %5u %5u %10llu %10llu\n", sma->sem_perm.key, sma->sem_perm.id, sma->sem_perm.mode, sma->sem_nsems, from_kuid_munged(user_ns, sma->sem_perm.uid), from_kgid_munged(user_ns, sma->sem_perm.gid), from_kuid_munged(user_ns, sma->sem_perm.cuid), from_kgid_munged(user_ns, sma->sem_perm.cgid), sem_otime, sma->sem_ctime); complexmode_tryleave(sma); return 0; } #endif |
| 52 53 53 49 12 6 7 4 5 32 30 32 31 1 1 1 28 32 30 28 15 15 8 8 6 1 32 32 32 48 45 45 15 2 16 48 48 38 45 45 22 44 2 1 1 2 1 1 25 27 1 1 15 14 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Spanning tree protocol; generic parts * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/rculist.h> #include <net/switchdev.h> #include "br_private.h" #include "br_private_stp.h" /* since time values in bpdu are in jiffies and then scaled (1/256) * before sending, make sure that is at least one STP tick. */ #define MESSAGE_AGE_INCR ((HZ / 256) + 1) static const char *const br_port_state_names[] = { [BR_STATE_DISABLED] = "disabled", [BR_STATE_LISTENING] = "listening", [BR_STATE_LEARNING] = "learning", [BR_STATE_FORWARDING] = "forwarding", [BR_STATE_BLOCKING] = "blocking", }; void br_set_state(struct net_bridge_port *p, unsigned int state) { struct switchdev_attr attr = { .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_PORT_STP_STATE, .flags = SWITCHDEV_F_DEFER, .u.stp_state = state, }; int err; /* Don't change the state of the ports if they are driven by a different * protocol. */ if (p->flags & BR_MRP_AWARE) return; p->state = state; err = switchdev_port_attr_set(p->dev, &attr, NULL); if (err && err != -EOPNOTSUPP) br_warn(p->br, "error setting offload STP state on port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); else br_info(p->br, "port %u(%s) entered %s state\n", (unsigned int) p->port_no, p->dev->name, br_port_state_names[p->state]); if (p->br->stp_enabled == BR_KERNEL_STP) { switch (p->state) { case BR_STATE_BLOCKING: p->stp_xstats.transition_blk++; break; case BR_STATE_FORWARDING: p->stp_xstats.transition_fwd++; break; } } } u8 br_port_get_stp_state(const struct net_device *dev) { struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_rtnl(dev); if (!p) return BR_STATE_DISABLED; return p->state; } EXPORT_SYMBOL_GPL(br_port_get_stp_state); /* called under bridge lock */ struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no) { struct net_bridge_port *p; list_for_each_entry_rcu(p, &br->port_list, list, lockdep_is_held(&br->lock)) { if (p->port_no == port_no) return p; } return NULL; } /* called under bridge lock */ static int br_should_become_root_port(const struct net_bridge_port *p, u16 root_port) { struct net_bridge *br; struct net_bridge_port *rp; int t; br = p->br; if (p->state == BR_STATE_DISABLED || br_is_designated_port(p)) return 0; if (memcmp(&br->bridge_id, &p->designated_root, 8) <= 0) return 0; if (!root_port) return 1; rp = br_get_port(br, root_port); t = memcmp(&p->designated_root, &rp->designated_root, 8); if (t < 0) return 1; else if (t > 0) return 0; if (p->designated_cost + p->path_cost < rp->designated_cost + rp->path_cost) return 1; else if (p->designated_cost + p->path_cost > rp->designated_cost + rp->path_cost) return 0; t = memcmp(&p->designated_bridge, &rp->designated_bridge, 8); if (t < 0) return 1; else if (t > 0) return 0; if (p->designated_port < rp->designated_port) return 1; else if (p->designated_port > rp->designated_port) return 0; if (p->port_id < rp->port_id) return 1; return 0; } static void br_root_port_block(const struct net_bridge *br, struct net_bridge_port *p) { br_notice(br, "port %u(%s) tried to become root port (blocked)", (unsigned int) p->port_no, p->dev->name); br_set_state(p, BR_STATE_LISTENING); br_ifinfo_notify(RTM_NEWLINK, NULL, p); if (br->forward_delay > 0) mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); } /* called under bridge lock */ static void br_root_selection(struct net_bridge *br) { struct net_bridge_port *p; u16 root_port = 0; list_for_each_entry(p, &br->port_list, list) { if (!br_should_become_root_port(p, root_port)) continue; if (p->flags & BR_ROOT_BLOCK) br_root_port_block(br, p); else root_port = p->port_no; } br->root_port = root_port; if (!root_port) { br->designated_root = br->bridge_id; br->root_path_cost = 0; } else { p = br_get_port(br, root_port); br->designated_root = p->designated_root; br->root_path_cost = p->designated_cost + p->path_cost; } } /* called under bridge lock */ void br_become_root_bridge(struct net_bridge *br) { br->max_age = br->bridge_max_age; br->hello_time = br->bridge_hello_time; br->forward_delay = br->bridge_forward_delay; br_topology_change_detection(br); del_timer(&br->tcn_timer); if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); mod_timer(&br->hello_timer, jiffies + br->hello_time); } } /* called under bridge lock */ void br_transmit_config(struct net_bridge_port *p) { struct br_config_bpdu bpdu; struct net_bridge *br; if (timer_pending(&p->hold_timer)) { p->config_pending = 1; return; } br = p->br; bpdu.topology_change = br->topology_change; bpdu.topology_change_ack = p->topology_change_ack; bpdu.root = br->designated_root; bpdu.root_path_cost = br->root_path_cost; bpdu.bridge_id = br->bridge_id; bpdu.port_id = p->port_id; if (br_is_root_bridge(br)) bpdu.message_age = 0; else { struct net_bridge_port *root = br_get_port(br, br->root_port); bpdu.message_age = (jiffies - root->designated_age) + MESSAGE_AGE_INCR; } bpdu.max_age = br->max_age; bpdu.hello_time = br->hello_time; bpdu.forward_delay = br->forward_delay; if (bpdu.message_age < br->max_age) { br_send_config_bpdu(p, &bpdu); p->topology_change_ack = 0; p->config_pending = 0; if (p->br->stp_enabled == BR_KERNEL_STP) mod_timer(&p->hold_timer, round_jiffies(jiffies + BR_HOLD_TIME)); } } /* called under bridge lock */ static void br_record_config_information(struct net_bridge_port *p, const struct br_config_bpdu *bpdu) { p->designated_root = bpdu->root; p->designated_cost = bpdu->root_path_cost; p->designated_bridge = bpdu->bridge_id; p->designated_port = bpdu->port_id; p->designated_age = jiffies - bpdu->message_age; mod_timer(&p->message_age_timer, jiffies + (bpdu->max_age - bpdu->message_age)); } /* called under bridge lock */ static void br_record_config_timeout_values(struct net_bridge *br, const struct br_config_bpdu *bpdu) { br->max_age = bpdu->max_age; br->hello_time = bpdu->hello_time; br->forward_delay = bpdu->forward_delay; __br_set_topology_change(br, bpdu->topology_change); } /* called under bridge lock */ void br_transmit_tcn(struct net_bridge *br) { struct net_bridge_port *p; p = br_get_port(br, br->root_port); if (p) br_send_tcn_bpdu(p); else br_notice(br, "root port %u not found for topology notice\n", br->root_port); } /* called under bridge lock */ static int br_should_become_designated_port(const struct net_bridge_port *p) { struct net_bridge *br; int t; br = p->br; if (br_is_designated_port(p)) return 1; if (memcmp(&p->designated_root, &br->designated_root, 8)) return 1; if (br->root_path_cost < p->designated_cost) return 1; else if (br->root_path_cost > p->designated_cost) return 0; t = memcmp(&br->bridge_id, &p->designated_bridge, 8); if (t < 0) return 1; else if (t > 0) return 0; if (p->port_id < p->designated_port) return 1; return 0; } /* called under bridge lock */ static void br_designated_port_selection(struct net_bridge *br) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->state != BR_STATE_DISABLED && br_should_become_designated_port(p)) br_become_designated_port(p); } } /* called under bridge lock */ static int br_supersedes_port_info(const struct net_bridge_port *p, const struct br_config_bpdu *bpdu) { int t; t = memcmp(&bpdu->root, &p->designated_root, 8); if (t < 0) return 1; else if (t > 0) return 0; if (bpdu->root_path_cost < p->designated_cost) return 1; else if (bpdu->root_path_cost > p->designated_cost) return 0; t = memcmp(&bpdu->bridge_id, &p->designated_bridge, 8); if (t < 0) return 1; else if (t > 0) return 0; if (memcmp(&bpdu->bridge_id, &p->br->bridge_id, 8)) return 1; if (bpdu->port_id <= p->designated_port) return 1; return 0; } /* called under bridge lock */ static void br_topology_change_acknowledged(struct net_bridge *br) { br->topology_change_detected = 0; del_timer(&br->tcn_timer); } /* called under bridge lock */ void br_topology_change_detection(struct net_bridge *br) { int isroot = br_is_root_bridge(br); if (br->stp_enabled != BR_KERNEL_STP) return; br_info(br, "topology change detected, %s\n", isroot ? "propagating" : "sending tcn bpdu"); if (isroot) { __br_set_topology_change(br, 1); mod_timer(&br->topology_change_timer, jiffies + br->bridge_forward_delay + br->bridge_max_age); } else if (!br->topology_change_detected) { br_transmit_tcn(br); mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time); } br->topology_change_detected = 1; } /* called under bridge lock */ void br_config_bpdu_generation(struct net_bridge *br) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->state != BR_STATE_DISABLED && br_is_designated_port(p)) br_transmit_config(p); } } /* called under bridge lock */ static void br_reply(struct net_bridge_port *p) { br_transmit_config(p); } /* called under bridge lock */ void br_configuration_update(struct net_bridge *br) { br_root_selection(br); br_designated_port_selection(br); } /* called under bridge lock */ void br_become_designated_port(struct net_bridge_port *p) { struct net_bridge *br; br = p->br; p->designated_root = br->designated_root; p->designated_cost = br->root_path_cost; p->designated_bridge = br->bridge_id; p->designated_port = p->port_id; } /* called under bridge lock */ static void br_make_blocking(struct net_bridge_port *p) { if (p->state != BR_STATE_DISABLED && p->state != BR_STATE_BLOCKING) { if (p->state == BR_STATE_FORWARDING || p->state == BR_STATE_LEARNING) br_topology_change_detection(p->br); br_set_state(p, BR_STATE_BLOCKING); br_ifinfo_notify(RTM_NEWLINK, NULL, p); del_timer(&p->forward_delay_timer); } } /* called under bridge lock */ static void br_make_forwarding(struct net_bridge_port *p) { struct net_bridge *br = p->br; if (p->state != BR_STATE_BLOCKING) return; if (br->stp_enabled == BR_NO_STP || br->forward_delay == 0) { br_set_state(p, BR_STATE_FORWARDING); br_topology_change_detection(br); del_timer(&p->forward_delay_timer); } else if (br->stp_enabled == BR_KERNEL_STP) br_set_state(p, BR_STATE_LISTENING); else br_set_state(p, BR_STATE_LEARNING); br_ifinfo_notify(RTM_NEWLINK, NULL, p); if (br->forward_delay != 0) mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); } /* called under bridge lock */ void br_port_state_selection(struct net_bridge *br) { struct net_bridge_port *p; unsigned int liveports = 0; list_for_each_entry(p, &br->port_list, list) { if (p->state == BR_STATE_DISABLED) continue; /* Don't change port states if userspace is handling STP */ if (br->stp_enabled != BR_USER_STP) { if (p->port_no == br->root_port) { p->config_pending = 0; p->topology_change_ack = 0; br_make_forwarding(p); } else if (br_is_designated_port(p)) { del_timer(&p->message_age_timer); br_make_forwarding(p); } else { p->config_pending = 0; p->topology_change_ack = 0; br_make_blocking(p); } } if (p->state != BR_STATE_BLOCKING) br_multicast_enable_port(p); /* Multicast is not disabled for the port when it goes in * blocking state because the timers will expire and stop by * themselves without sending more queries. */ if (p->state == BR_STATE_FORWARDING) ++liveports; } if (liveports == 0) netif_carrier_off(br->dev); else netif_carrier_on(br->dev); } /* called under bridge lock */ static void br_topology_change_acknowledge(struct net_bridge_port *p) { p->topology_change_ack = 1; br_transmit_config(p); } /* called under bridge lock */ void br_received_config_bpdu(struct net_bridge_port *p, const struct br_config_bpdu *bpdu) { struct net_bridge *br; int was_root; p->stp_xstats.rx_bpdu++; br = p->br; was_root = br_is_root_bridge(br); if (br_supersedes_port_info(p, bpdu)) { br_record_config_information(p, bpdu); br_configuration_update(br); br_port_state_selection(br); if (!br_is_root_bridge(br) && was_root) { del_timer(&br->hello_timer); if (br->topology_change_detected) { del_timer(&br->topology_change_timer); br_transmit_tcn(br); mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time); } } if (p->port_no == br->root_port) { br_record_config_timeout_values(br, bpdu); br_config_bpdu_generation(br); if (bpdu->topology_change_ack) br_topology_change_acknowledged(br); } } else if (br_is_designated_port(p)) { br_reply(p); } } /* called under bridge lock */ void br_received_tcn_bpdu(struct net_bridge_port *p) { p->stp_xstats.rx_tcn++; if (br_is_designated_port(p)) { br_info(p->br, "port %u(%s) received tcn bpdu\n", (unsigned int) p->port_no, p->dev->name); br_topology_change_detection(p->br); br_topology_change_acknowledge(p); } } /* Change bridge STP parameter */ int br_set_hello_time(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); if (t < BR_MIN_HELLO_TIME || t > BR_MAX_HELLO_TIME) return -ERANGE; spin_lock_bh(&br->lock); br->bridge_hello_time = t; if (br_is_root_bridge(br)) br->hello_time = br->bridge_hello_time; spin_unlock_bh(&br->lock); return 0; } int br_set_max_age(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); if (t < BR_MIN_MAX_AGE || t > BR_MAX_MAX_AGE) return -ERANGE; spin_lock_bh(&br->lock); br->bridge_max_age = t; if (br_is_root_bridge(br)) br->max_age = br->bridge_max_age; spin_unlock_bh(&br->lock); return 0; } /* called under bridge lock */ int __set_ageing_time(struct net_device *dev, unsigned long t) { struct switchdev_attr attr = { .orig_dev = dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP | SWITCHDEV_F_DEFER, .u.ageing_time = jiffies_to_clock_t(t), }; int err; err = switchdev_port_attr_set(dev, &attr, NULL); if (err && err != -EOPNOTSUPP) return err; return 0; } /* Set time interval that dynamic forwarding entries live * For pure software bridge, allow values outside the 802.1 * standard specification for special cases: * 0 - entry never ages (all permanent) * 1 - entry disappears (no persistence) * * Offloaded switch entries maybe more restrictive */ int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time) { unsigned long t = clock_t_to_jiffies(ageing_time); int err; err = __set_ageing_time(br->dev, t); if (err) return err; spin_lock_bh(&br->lock); br->bridge_ageing_time = t; br->ageing_time = t; spin_unlock_bh(&br->lock); mod_delayed_work(system_long_wq, &br->gc_work, 0); return 0; } clock_t br_get_ageing_time(const struct net_device *br_dev) { const struct net_bridge *br; if (!netif_is_bridge_master(br_dev)) return 0; br = netdev_priv(br_dev); return jiffies_to_clock_t(br->ageing_time); } EXPORT_SYMBOL_GPL(br_get_ageing_time); /* called under bridge lock */ void __br_set_topology_change(struct net_bridge *br, unsigned char val) { unsigned long t; int err; if (br->stp_enabled == BR_KERNEL_STP && br->topology_change != val) { /* On topology change, set the bridge ageing time to twice the * forward delay. Otherwise, restore its default ageing time. */ if (val) { t = 2 * br->forward_delay; br_debug(br, "decreasing ageing time to %lu\n", t); } else { t = br->bridge_ageing_time; br_debug(br, "restoring ageing time to %lu\n", t); } err = __set_ageing_time(br->dev, t); if (err) br_warn(br, "error offloading ageing time\n"); else br->ageing_time = t; } br->topology_change = val; } void __br_set_forward_delay(struct net_bridge *br, unsigned long t) { br->bridge_forward_delay = t; if (br_is_root_bridge(br)) br->forward_delay = br->bridge_forward_delay; } int br_set_forward_delay(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); int err = -ERANGE; spin_lock_bh(&br->lock); if (br->stp_enabled != BR_NO_STP && (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY)) goto unlock; __br_set_forward_delay(br, t); err = 0; unlock: spin_unlock_bh(&br->lock); return err; } |
| 54 54 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/types.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/xdr.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/svcauth.h> #include <linux/sunrpc/gss_api.h> #include <linux/sunrpc/addr.h> #include <linux/err.h> #include <linux/seq_file.h> #include <linux/hash.h> #include <linux/string.h> #include <linux/slab.h> #include <net/sock.h> #include <net/ipv6.h> #include <linux/kernel.h> #include <linux/user_namespace.h> #define RPCDBG_FACILITY RPCDBG_AUTH #include "netns.h" /* * AUTHUNIX and AUTHNULL credentials are both handled here. * AUTHNULL is treated just like AUTHUNIX except that the uid/gid * are always nobody (-2). i.e. we do the same IP address checks for * AUTHNULL as for AUTHUNIX, and that is done here. */ struct unix_domain { struct auth_domain h; /* other stuff later */ }; extern struct auth_ops svcauth_null; extern struct auth_ops svcauth_unix; static void svcauth_unix_domain_release_rcu(struct rcu_head *head) { struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head); struct unix_domain *ud = container_of(dom, struct unix_domain, h); kfree(dom->name); kfree(ud); } static void svcauth_unix_domain_release(struct auth_domain *dom) { call_rcu(&dom->rcu_head, svcauth_unix_domain_release_rcu); } struct auth_domain *unix_domain_find(char *name) { struct auth_domain *rv; struct unix_domain *new = NULL; rv = auth_domain_find(name); while(1) { if (rv) { if (new && rv != &new->h) svcauth_unix_domain_release(&new->h); if (rv->flavour != &svcauth_unix) { auth_domain_put(rv); return NULL; } return rv; } new = kmalloc(sizeof(*new), GFP_KERNEL); if (new == NULL) return NULL; kref_init(&new->h.ref); new->h.name = kstrdup(name, GFP_KERNEL); if (new->h.name == NULL) { kfree(new); return NULL; } new->h.flavour = &svcauth_unix; rv = auth_domain_lookup(name, &new->h); } } EXPORT_SYMBOL_GPL(unix_domain_find); /************************************************** * cache for IP address to unix_domain * as needed by AUTH_UNIX */ #define IP_HASHBITS 8 #define IP_HASHMAX (1<<IP_HASHBITS) struct ip_map { struct cache_head h; char m_class[8]; /* e.g. "nfsd" */ struct in6_addr m_addr; struct unix_domain *m_client; struct rcu_head m_rcu; }; static void ip_map_put(struct kref *kref) { struct cache_head *item = container_of(kref, struct cache_head, ref); struct ip_map *im = container_of(item, struct ip_map,h); if (test_bit(CACHE_VALID, &item->flags) && !test_bit(CACHE_NEGATIVE, &item->flags)) auth_domain_put(&im->m_client->h); kfree_rcu(im, m_rcu); } static inline int hash_ip6(const struct in6_addr *ip) { return hash_32(ipv6_addr_hash(ip), IP_HASHBITS); } static int ip_map_match(struct cache_head *corig, struct cache_head *cnew) { struct ip_map *orig = container_of(corig, struct ip_map, h); struct ip_map *new = container_of(cnew, struct ip_map, h); return strcmp(orig->m_class, new->m_class) == 0 && ipv6_addr_equal(&orig->m_addr, &new->m_addr); } static void ip_map_init(struct cache_head *cnew, struct cache_head *citem) { struct ip_map *new = container_of(cnew, struct ip_map, h); struct ip_map *item = container_of(citem, struct ip_map, h); strcpy(new->m_class, item->m_class); new->m_addr = item->m_addr; } static void update(struct cache_head *cnew, struct cache_head *citem) { struct ip_map *new = container_of(cnew, struct ip_map, h); struct ip_map *item = container_of(citem, struct ip_map, h); kref_get(&item->m_client->h.ref); new->m_client = item->m_client; } static struct cache_head *ip_map_alloc(void) { struct ip_map *i = kmalloc(sizeof(*i), GFP_KERNEL); if (i) return &i->h; else return NULL; } static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_pipe_upcall(cd, h); } static void ip_map_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) { char text_addr[40]; struct ip_map *im = container_of(h, struct ip_map, h); if (ipv6_addr_v4mapped(&(im->m_addr))) { snprintf(text_addr, 20, "%pI4", &im->m_addr.s6_addr32[3]); } else { snprintf(text_addr, 40, "%pI6", &im->m_addr); } qword_add(bpp, blen, im->m_class); qword_add(bpp, blen, text_addr); (*bpp)[-1] = '\n'; } static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class, struct in6_addr *addr); static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, struct unix_domain *udom, time64_t expiry); static int ip_map_parse(struct cache_detail *cd, char *mesg, int mlen) { /* class ipaddress [domainname] */ /* should be safe just to use the start of the input buffer * for scratch: */ char *buf = mesg; int len; char class[8]; union { struct sockaddr sa; struct sockaddr_in s4; struct sockaddr_in6 s6; } address; struct sockaddr_in6 sin6; int err; struct ip_map *ipmp; struct auth_domain *dom; time64_t expiry; if (mesg[mlen-1] != '\n') return -EINVAL; mesg[mlen-1] = 0; /* class */ len = qword_get(&mesg, class, sizeof(class)); if (len <= 0) return -EINVAL; /* ip address */ len = qword_get(&mesg, buf, mlen); if (len <= 0) return -EINVAL; if (rpc_pton(cd->net, buf, len, &address.sa, sizeof(address)) == 0) return -EINVAL; switch (address.sa.sa_family) { case AF_INET: /* Form a mapped IPv4 address in sin6 */ sin6.sin6_family = AF_INET6; ipv6_addr_set_v4mapped(address.s4.sin_addr.s_addr, &sin6.sin6_addr); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: memcpy(&sin6, &address.s6, sizeof(sin6)); break; #endif default: return -EINVAL; } expiry = get_expiry(&mesg); if (expiry ==0) return -EINVAL; /* domainname, or empty for NEGATIVE */ len = qword_get(&mesg, buf, mlen); if (len < 0) return -EINVAL; if (len) { dom = unix_domain_find(buf); if (dom == NULL) return -ENOENT; } else dom = NULL; /* IPv6 scope IDs are ignored for now */ ipmp = __ip_map_lookup(cd, class, &sin6.sin6_addr); if (ipmp) { err = __ip_map_update(cd, ipmp, container_of(dom, struct unix_domain, h), expiry); } else err = -ENOMEM; if (dom) auth_domain_put(dom); cache_flush(); return err; } static int ip_map_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { struct ip_map *im; struct in6_addr addr; char *dom = "-no-domain-"; if (h == NULL) { seq_puts(m, "#class IP domain\n"); return 0; } im = container_of(h, struct ip_map, h); /* class addr domain */ addr = im->m_addr; if (test_bit(CACHE_VALID, &h->flags) && !test_bit(CACHE_NEGATIVE, &h->flags)) dom = im->m_client->h.name; if (ipv6_addr_v4mapped(&addr)) { seq_printf(m, "%s %pI4 %s\n", im->m_class, &addr.s6_addr32[3], dom); } else { seq_printf(m, "%s %pI6 %s\n", im->m_class, &addr, dom); } return 0; } static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class, struct in6_addr *addr) { struct ip_map ip; struct cache_head *ch; strcpy(ip.m_class, class); ip.m_addr = *addr; ch = sunrpc_cache_lookup_rcu(cd, &ip.h, hash_str(class, IP_HASHBITS) ^ hash_ip6(addr)); if (ch) return container_of(ch, struct ip_map, h); else return NULL; } static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, struct unix_domain *udom, time64_t expiry) { struct ip_map ip; struct cache_head *ch; ip.m_client = udom; ip.h.flags = 0; if (!udom) set_bit(CACHE_NEGATIVE, &ip.h.flags); ip.h.expiry_time = expiry; ch = sunrpc_cache_update(cd, &ip.h, &ipm->h, hash_str(ipm->m_class, IP_HASHBITS) ^ hash_ip6(&ipm->m_addr)); if (!ch) return -ENOMEM; cache_put(ch, cd); return 0; } void svcauth_unix_purge(struct net *net) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); cache_purge(sn->ip_map_cache); } EXPORT_SYMBOL_GPL(svcauth_unix_purge); static inline struct ip_map * ip_map_cached_get(struct svc_xprt *xprt) { struct ip_map *ipm = NULL; struct sunrpc_net *sn; if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) { spin_lock(&xprt->xpt_lock); ipm = xprt->xpt_auth_cache; if (ipm != NULL) { sn = net_generic(xprt->xpt_net, sunrpc_net_id); if (cache_is_expired(sn->ip_map_cache, &ipm->h)) { /* * The entry has been invalidated since it was * remembered, e.g. by a second mount from the * same IP address. */ xprt->xpt_auth_cache = NULL; spin_unlock(&xprt->xpt_lock); cache_put(&ipm->h, sn->ip_map_cache); return NULL; } cache_get(&ipm->h); } spin_unlock(&xprt->xpt_lock); } return ipm; } static inline void ip_map_cached_put(struct svc_xprt *xprt, struct ip_map *ipm) { if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) { spin_lock(&xprt->xpt_lock); if (xprt->xpt_auth_cache == NULL) { /* newly cached, keep the reference */ xprt->xpt_auth_cache = ipm; ipm = NULL; } spin_unlock(&xprt->xpt_lock); } if (ipm) { struct sunrpc_net *sn; sn = net_generic(xprt->xpt_net, sunrpc_net_id); cache_put(&ipm->h, sn->ip_map_cache); } } void svcauth_unix_info_release(struct svc_xprt *xpt) { struct ip_map *ipm; ipm = xpt->xpt_auth_cache; if (ipm != NULL) { struct sunrpc_net *sn; sn = net_generic(xpt->xpt_net, sunrpc_net_id); cache_put(&ipm->h, sn->ip_map_cache); } } /**************************************************************************** * auth.unix.gid cache * simple cache to map a UID to a list of GIDs * because AUTH_UNIX aka AUTH_SYS has a max of UNX_NGROUPS */ #define GID_HASHBITS 8 #define GID_HASHMAX (1<<GID_HASHBITS) struct unix_gid { struct cache_head h; kuid_t uid; struct group_info *gi; struct rcu_head rcu; }; static int unix_gid_hash(kuid_t uid) { return hash_long(from_kuid(&init_user_ns, uid), GID_HASHBITS); } static void unix_gid_free(struct rcu_head *rcu) { struct unix_gid *ug = container_of(rcu, struct unix_gid, rcu); struct cache_head *item = &ug->h; if (test_bit(CACHE_VALID, &item->flags) && !test_bit(CACHE_NEGATIVE, &item->flags)) put_group_info(ug->gi); kfree(ug); } static void unix_gid_put(struct kref *kref) { struct cache_head *item = container_of(kref, struct cache_head, ref); struct unix_gid *ug = container_of(item, struct unix_gid, h); call_rcu(&ug->rcu, unix_gid_free); } static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew) { struct unix_gid *orig = container_of(corig, struct unix_gid, h); struct unix_gid *new = container_of(cnew, struct unix_gid, h); return uid_eq(orig->uid, new->uid); } static void unix_gid_init(struct cache_head *cnew, struct cache_head *citem) { struct unix_gid *new = container_of(cnew, struct unix_gid, h); struct unix_gid *item = container_of(citem, struct unix_gid, h); new->uid = item->uid; } static void unix_gid_update(struct cache_head *cnew, struct cache_head *citem) { struct unix_gid *new = container_of(cnew, struct unix_gid, h); struct unix_gid *item = container_of(citem, struct unix_gid, h); get_group_info(item->gi); new->gi = item->gi; } static struct cache_head *unix_gid_alloc(void) { struct unix_gid *g = kmalloc(sizeof(*g), GFP_KERNEL); if (g) return &g->h; else return NULL; } static int unix_gid_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_pipe_upcall_timeout(cd, h); } static void unix_gid_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) { char tuid[20]; struct unix_gid *ug = container_of(h, struct unix_gid, h); snprintf(tuid, 20, "%u", from_kuid(&init_user_ns, ug->uid)); qword_add(bpp, blen, tuid); (*bpp)[-1] = '\n'; } static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid); static int unix_gid_parse(struct cache_detail *cd, char *mesg, int mlen) { /* uid expiry Ngid gid0 gid1 ... gidN-1 */ int id; kuid_t uid; int gids; int rv; int i; int err; time64_t expiry; struct unix_gid ug, *ugp; if (mesg[mlen - 1] != '\n') return -EINVAL; mesg[mlen-1] = 0; rv = get_int(&mesg, &id); if (rv) return -EINVAL; uid = make_kuid(current_user_ns(), id); ug.uid = uid; expiry = get_expiry(&mesg); if (expiry == 0) return -EINVAL; rv = get_int(&mesg, &gids); if (rv || gids < 0 || gids > 8192) return -EINVAL; ug.gi = groups_alloc(gids); if (!ug.gi) return -ENOMEM; for (i = 0 ; i < gids ; i++) { int gid; kgid_t kgid; rv = get_int(&mesg, &gid); err = -EINVAL; if (rv) goto out; kgid = make_kgid(current_user_ns(), gid); if (!gid_valid(kgid)) goto out; ug.gi->gid[i] = kgid; } groups_sort(ug.gi); ugp = unix_gid_lookup(cd, uid); if (ugp) { struct cache_head *ch; ug.h.flags = 0; ug.h.expiry_time = expiry; ch = sunrpc_cache_update(cd, &ug.h, &ugp->h, unix_gid_hash(uid)); if (!ch) err = -ENOMEM; else { err = 0; cache_put(ch, cd); } } else err = -ENOMEM; out: if (ug.gi) put_group_info(ug.gi); return err; } static int unix_gid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { struct user_namespace *user_ns = m->file->f_cred->user_ns; struct unix_gid *ug; int i; int glen; if (h == NULL) { seq_puts(m, "#uid cnt: gids...\n"); return 0; } ug = container_of(h, struct unix_gid, h); if (test_bit(CACHE_VALID, &h->flags) && !test_bit(CACHE_NEGATIVE, &h->flags)) glen = ug->gi->ngroups; else glen = 0; seq_printf(m, "%u %d:", from_kuid_munged(user_ns, ug->uid), glen); for (i = 0; i < glen; i++) seq_printf(m, " %d", from_kgid_munged(user_ns, ug->gi->gid[i])); seq_printf(m, "\n"); return 0; } static const struct cache_detail unix_gid_cache_template = { .owner = THIS_MODULE, .hash_size = GID_HASHMAX, .name = "auth.unix.gid", .cache_put = unix_gid_put, .cache_upcall = unix_gid_upcall, .cache_request = unix_gid_request, .cache_parse = unix_gid_parse, .cache_show = unix_gid_show, .match = unix_gid_match, .init = unix_gid_init, .update = unix_gid_update, .alloc = unix_gid_alloc, }; int unix_gid_cache_create(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd; int err; cd = cache_create_net(&unix_gid_cache_template, net); if (IS_ERR(cd)) return PTR_ERR(cd); err = cache_register_net(cd, net); if (err) { cache_destroy_net(cd, net); return err; } sn->unix_gid_cache = cd; return 0; } void unix_gid_cache_destroy(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd = sn->unix_gid_cache; sn->unix_gid_cache = NULL; cache_purge(cd); cache_unregister_net(cd, net); cache_destroy_net(cd, net); } static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid) { struct unix_gid ug; struct cache_head *ch; ug.uid = uid; ch = sunrpc_cache_lookup_rcu(cd, &ug.h, unix_gid_hash(uid)); if (ch) return container_of(ch, struct unix_gid, h); else return NULL; } static struct group_info *unix_gid_find(kuid_t uid, struct svc_rqst *rqstp) { struct unix_gid *ug; struct group_info *gi; int ret; struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); ug = unix_gid_lookup(sn->unix_gid_cache, uid); if (!ug) return ERR_PTR(-EAGAIN); ret = cache_check(sn->unix_gid_cache, &ug->h, &rqstp->rq_chandle); switch (ret) { case -ENOENT: return ERR_PTR(-ENOENT); case -ETIMEDOUT: return ERR_PTR(-ESHUTDOWN); case 0: gi = get_group_info(ug->gi); cache_put(&ug->h, sn->unix_gid_cache); return gi; default: return ERR_PTR(-EAGAIN); } } int svcauth_unix_set_client(struct svc_rqst *rqstp) { struct sockaddr_in *sin; struct sockaddr_in6 *sin6, sin6_storage; struct ip_map *ipm; struct group_info *gi; struct svc_cred *cred = &rqstp->rq_cred; struct svc_xprt *xprt = rqstp->rq_xprt; struct net *net = xprt->xpt_net; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); switch (rqstp->rq_addr.ss_family) { case AF_INET: sin = svc_addr_in(rqstp); sin6 = &sin6_storage; ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &sin6->sin6_addr); break; case AF_INET6: sin6 = svc_addr_in6(rqstp); break; default: BUG(); } rqstp->rq_client = NULL; if (rqstp->rq_proc == 0) goto out; rqstp->rq_auth_stat = rpc_autherr_badcred; ipm = ip_map_cached_get(xprt); if (ipm == NULL) ipm = __ip_map_lookup(sn->ip_map_cache, rqstp->rq_server->sv_program->pg_class, &sin6->sin6_addr); if (ipm == NULL) return SVC_DENIED; switch (cache_check(sn->ip_map_cache, &ipm->h, &rqstp->rq_chandle)) { default: BUG(); case -ETIMEDOUT: return SVC_CLOSE; case -EAGAIN: return SVC_DROP; case -ENOENT: return SVC_DENIED; case 0: rqstp->rq_client = &ipm->m_client->h; kref_get(&rqstp->rq_client->ref); ip_map_cached_put(xprt, ipm); break; } gi = unix_gid_find(cred->cr_uid, rqstp); switch (PTR_ERR(gi)) { case -EAGAIN: return SVC_DROP; case -ESHUTDOWN: return SVC_CLOSE; case -ENOENT: break; default: put_group_info(cred->cr_group_info); cred->cr_group_info = gi; } out: rqstp->rq_auth_stat = rpc_auth_ok; return SVC_OK; } EXPORT_SYMBOL_GPL(svcauth_unix_set_client); static int svcauth_null_accept(struct svc_rqst *rqstp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; struct svc_cred *cred = &rqstp->rq_cred; if (argv->iov_len < 3*4) return SVC_GARBAGE; if (svc_getu32(argv) != 0) { dprintk("svc: bad null cred\n"); rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { dprintk("svc: bad null verf\n"); rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } /* Signal that mapping to nobody uid/gid is required */ cred->cr_uid = INVALID_UID; cred->cr_gid = INVALID_GID; cred->cr_group_info = groups_alloc(0); if (cred->cr_group_info == NULL) return SVC_CLOSE; /* kmalloc failure - client must retry */ /* Put NULL verifier */ svc_putnl(resv, RPC_AUTH_NULL); svc_putnl(resv, 0); rqstp->rq_cred.cr_flavor = RPC_AUTH_NULL; return SVC_OK; } static int svcauth_null_release(struct svc_rqst *rqstp) { if (rqstp->rq_client) auth_domain_put(rqstp->rq_client); rqstp->rq_client = NULL; if (rqstp->rq_cred.cr_group_info) put_group_info(rqstp->rq_cred.cr_group_info); rqstp->rq_cred.cr_group_info = NULL; return 0; /* don't drop */ } struct auth_ops svcauth_null = { .name = "null", .owner = THIS_MODULE, .flavour = RPC_AUTH_NULL, .accept = svcauth_null_accept, .release = svcauth_null_release, .set_client = svcauth_unix_set_client, }; static int svcauth_unix_accept(struct svc_rqst *rqstp) { struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; struct svc_cred *cred = &rqstp->rq_cred; struct user_namespace *userns; u32 slen, i; int len = argv->iov_len; if ((len -= 3*4) < 0) return SVC_GARBAGE; svc_getu32(argv); /* length */ svc_getu32(argv); /* time stamp */ slen = XDR_QUADLEN(svc_getnl(argv)); /* machname length */ if (slen > 64 || (len -= (slen + 3)*4) < 0) goto badcred; argv->iov_base = (void*)((__be32*)argv->iov_base + slen); /* skip machname */ argv->iov_len -= slen*4; /* * Note: we skip uid_valid()/gid_valid() checks here for * backwards compatibility with clients that use -1 id's. * Instead, -1 uid or gid is later mapped to the * (export-specific) anonymous id by nfsd_setuser. * Supplementary gid's will be left alone. */ userns = (rqstp->rq_xprt && rqstp->rq_xprt->xpt_cred) ? rqstp->rq_xprt->xpt_cred->user_ns : &init_user_ns; cred->cr_uid = make_kuid(userns, svc_getnl(argv)); /* uid */ cred->cr_gid = make_kgid(userns, svc_getnl(argv)); /* gid */ slen = svc_getnl(argv); /* gids length */ if (slen > UNX_NGROUPS || (len -= (slen + 2)*4) < 0) goto badcred; cred->cr_group_info = groups_alloc(slen); if (cred->cr_group_info == NULL) return SVC_CLOSE; for (i = 0; i < slen; i++) { kgid_t kgid = make_kgid(userns, svc_getnl(argv)); cred->cr_group_info->gid[i] = kgid; } groups_sort(cred->cr_group_info); if (svc_getu32(argv) != htonl(RPC_AUTH_NULL) || svc_getu32(argv) != 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } /* Put NULL verifier */ svc_putnl(resv, RPC_AUTH_NULL); svc_putnl(resv, 0); rqstp->rq_cred.cr_flavor = RPC_AUTH_UNIX; return SVC_OK; badcred: rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } static int svcauth_unix_release(struct svc_rqst *rqstp) { /* Verifier (such as it is) is already in place. */ if (rqstp->rq_client) auth_domain_put(rqstp->rq_client); rqstp->rq_client = NULL; if (rqstp->rq_cred.cr_group_info) put_group_info(rqstp->rq_cred.cr_group_info); rqstp->rq_cred.cr_group_info = NULL; return 0; } struct auth_ops svcauth_unix = { .name = "unix", .owner = THIS_MODULE, .flavour = RPC_AUTH_UNIX, .accept = svcauth_unix_accept, .release = svcauth_unix_release, .domain_release = svcauth_unix_domain_release, .set_client = svcauth_unix_set_client, }; static const struct cache_detail ip_map_cache_template = { .owner = THIS_MODULE, .hash_size = IP_HASHMAX, .name = "auth.unix.ip", .cache_put = ip_map_put, .cache_upcall = ip_map_upcall, .cache_request = ip_map_request, .cache_parse = ip_map_parse, .cache_show = ip_map_show, .match = ip_map_match, .init = ip_map_init, .update = update, .alloc = ip_map_alloc, }; int ip_map_cache_create(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd; int err; cd = cache_create_net(&ip_map_cache_template, net); if (IS_ERR(cd)) return PTR_ERR(cd); err = cache_register_net(cd, net); if (err) { cache_destroy_net(cd, net); return err; } sn->ip_map_cache = cd; return 0; } void ip_map_cache_destroy(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd = sn->ip_map_cache; sn->ip_map_cache = NULL; cache_purge(cd); cache_unregister_net(cd, net); cache_destroy_net(cd, net); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/bad_inode.c * * Copyright (C) 1997, Stephen Tweedie * * Provide stub functions for unreadable inodes * * Fabian Frederick : August 2003 - All file operations assigned to EIO */ #include <linux/fs.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/time.h> #include <linux/namei.h> #include <linux/poll.h> #include <linux/fiemap.h> static int bad_file_open(struct inode *inode, struct file *filp) { return -EIO; } static const struct file_operations bad_file_ops = { .open = bad_file_open, }; static int bad_inode_create(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return -EIO; } static struct dentry *bad_inode_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return ERR_PTR(-EIO); } static int bad_inode_link (struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_unlink(struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_symlink(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, const char *symname) { return -EIO; } static int bad_inode_mkdir(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t mode) { return -EIO; } static int bad_inode_rmdir (struct inode *dir, struct dentry *dentry) { return -EIO; } static int bad_inode_mknod(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { return -EIO; } static int bad_inode_rename2(struct user_namespace *mnt_userns, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { return -EIO; } static int bad_inode_readlink(struct dentry *dentry, char __user *buffer, int buflen) { return -EIO; } static int bad_inode_permission(struct user_namespace *mnt_userns, struct inode *inode, int mask) { return -EIO; } static int bad_inode_getattr(struct user_namespace *mnt_userns, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { return -EIO; } static int bad_inode_setattr(struct user_namespace *mnt_userns, struct dentry *direntry, struct iattr *attrs) { return -EIO; } static ssize_t bad_inode_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { return -EIO; } static const char *bad_inode_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { return ERR_PTR(-EIO); } static struct posix_acl *bad_inode_get_acl(struct inode *inode, int type, bool rcu) { return ERR_PTR(-EIO); } static int bad_inode_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { return -EIO; } static int bad_inode_update_time(struct inode *inode, struct timespec64 *time, int flags) { return -EIO; } static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry, struct file *file, unsigned int open_flag, umode_t create_mode) { return -EIO; } static int bad_inode_tmpfile(struct user_namespace *mnt_userns, struct inode *inode, struct dentry *dentry, umode_t mode) { return -EIO; } static int bad_inode_set_acl(struct user_namespace *mnt_userns, struct inode *inode, struct posix_acl *acl, int type) { return -EIO; } static const struct inode_operations bad_inode_ops = { .create = bad_inode_create, .lookup = bad_inode_lookup, .link = bad_inode_link, .unlink = bad_inode_unlink, .symlink = bad_inode_symlink, .mkdir = bad_inode_mkdir, .rmdir = bad_inode_rmdir, .mknod = bad_inode_mknod, .rename = bad_inode_rename2, .readlink = bad_inode_readlink, .permission = bad_inode_permission, .getattr = bad_inode_getattr, .setattr = bad_inode_setattr, .listxattr = bad_inode_listxattr, .get_link = bad_inode_get_link, .get_acl = bad_inode_get_acl, .fiemap = bad_inode_fiemap, .update_time = bad_inode_update_time, .atomic_open = bad_inode_atomic_open, .tmpfile = bad_inode_tmpfile, .set_acl = bad_inode_set_acl, }; /* * When a filesystem is unable to read an inode due to an I/O error in * its read_inode() function, it can call make_bad_inode() to return a * set of stubs which will return EIO errors as required. * * We only need to do limited initialisation: all other fields are * preinitialised to zero automatically. */ /** * make_bad_inode - mark an inode bad due to an I/O error * @inode: Inode to mark bad * * When an inode cannot be read due to a media or remote network * failure this function makes the inode "bad" and causes I/O operations * on it to fail from this point on. */ void make_bad_inode(struct inode *inode) { remove_inode_hash(inode); inode->i_mode = S_IFREG; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_op = &bad_inode_ops; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &bad_file_ops; } EXPORT_SYMBOL(make_bad_inode); /* * This tests whether an inode has been flagged as bad. The test uses * &bad_inode_ops to cover the case of invalidated inodes as well as * those created by make_bad_inode() above. */ /** * is_bad_inode - is an inode errored * @inode: inode to test * * Returns true if the inode in question has been marked as bad. */ bool is_bad_inode(struct inode *inode) { return (inode->i_op == &bad_inode_ops); } EXPORT_SYMBOL(is_bad_inode); /** * iget_failed - Mark an under-construction inode as dead and release it * @inode: The inode to discard * * Mark an under-construction inode as dead and release it. */ void iget_failed(struct inode *inode) { make_bad_inode(inode); unlock_new_inode(inode); iput(inode); } EXPORT_SYMBOL(iget_failed); |
| 1 3 3 3 3 3 3 3 3 3 3 3 3 2 2 2 2 3 3 3 2 1 3 3 3 3 3 1 1 3 3 3 3 3 3 13 13 1 8 4 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * SME code for cfg80211 * both driver SME event handling and the SME implementation * (for nl80211's connect() and wext) * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2009, 2020 Intel Corporation. All rights reserved. * Copyright 2017 Intel Deutschland GmbH */ #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/wireless.h> #include <linux/export.h> #include <net/iw_handler.h> #include <net/cfg80211.h> #include <net/rtnetlink.h> #include "nl80211.h" #include "reg.h" #include "rdev-ops.h" /* * Software SME in cfg80211, using auth/assoc/deauth calls to the * driver. This is for implementing nl80211's connect/disconnect * and wireless extensions (if configured.) */ struct cfg80211_conn { struct cfg80211_connect_params params; /* these are sub-states of the _CONNECTING sme_state */ enum { CFG80211_CONN_SCANNING, CFG80211_CONN_SCAN_AGAIN, CFG80211_CONN_AUTHENTICATE_NEXT, CFG80211_CONN_AUTHENTICATING, CFG80211_CONN_AUTH_FAILED_TIMEOUT, CFG80211_CONN_ASSOCIATE_NEXT, CFG80211_CONN_ASSOCIATING, CFG80211_CONN_ASSOC_FAILED, CFG80211_CONN_ASSOC_FAILED_TIMEOUT, CFG80211_CONN_DEAUTH, CFG80211_CONN_ABANDON, CFG80211_CONN_CONNECTED, } state; u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; const u8 *ie; size_t ie_len; bool auto_auth, prev_bssid_valid; }; static void cfg80211_sme_free(struct wireless_dev *wdev) { if (!wdev->conn) return; kfree(wdev->conn->ie); kfree(wdev->conn); wdev->conn = NULL; } static int cfg80211_conn_scan(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_scan_request *request; int n_channels, err; ASSERT_WDEV_LOCK(wdev); if (rdev->scan_req || rdev->scan_msg) return -EBUSY; if (wdev->conn->params.channel) n_channels = 1; else n_channels = ieee80211_get_num_supported_channels(wdev->wiphy); request = kzalloc(sizeof(*request) + sizeof(request->ssids[0]) + sizeof(request->channels[0]) * n_channels, GFP_KERNEL); if (!request) return -ENOMEM; if (wdev->conn->params.channel) { enum nl80211_band band = wdev->conn->params.channel->band; struct ieee80211_supported_band *sband = wdev->wiphy->bands[band]; if (!sband) { kfree(request); return -EINVAL; } request->channels[0] = wdev->conn->params.channel; request->rates[band] = (1 << sband->n_bitrates) - 1; } else { int i = 0, j; enum nl80211_band band; struct ieee80211_supported_band *bands; struct ieee80211_channel *channel; for (band = 0; band < NUM_NL80211_BANDS; band++) { bands = wdev->wiphy->bands[band]; if (!bands) continue; for (j = 0; j < bands->n_channels; j++) { channel = &bands->channels[j]; if (channel->flags & IEEE80211_CHAN_DISABLED) continue; request->channels[i++] = channel; } request->rates[band] = (1 << bands->n_bitrates) - 1; } n_channels = i; } request->n_channels = n_channels; request->ssids = (void *)request + struct_size(request, channels, n_channels); request->n_ssids = 1; memcpy(request->ssids[0].ssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len); request->ssids[0].ssid_len = wdev->conn->params.ssid_len; eth_broadcast_addr(request->bssid); request->wdev = wdev; request->wiphy = &rdev->wiphy; request->scan_start = jiffies; rdev->scan_req = request; err = rdev_scan(rdev, request); if (!err) { wdev->conn->state = CFG80211_CONN_SCANNING; nl80211_send_scan_start(rdev, wdev); dev_hold(wdev->netdev); } else { rdev->scan_req = NULL; kfree(request); } return err; } static int cfg80211_conn_do_work(struct wireless_dev *wdev, enum nl80211_timeout_reason *treason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_connect_params *params; struct cfg80211_assoc_request req = {}; int err; ASSERT_WDEV_LOCK(wdev); if (!wdev->conn) return 0; params = &wdev->conn->params; switch (wdev->conn->state) { case CFG80211_CONN_SCANNING: /* didn't find it during scan ... */ return -ENOENT; case CFG80211_CONN_SCAN_AGAIN: return cfg80211_conn_scan(wdev); case CFG80211_CONN_AUTHENTICATE_NEXT: if (WARN_ON(!rdev->ops->auth)) return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_AUTHENTICATING; return cfg80211_mlme_auth(rdev, wdev->netdev, params->channel, params->auth_type, params->bssid, params->ssid, params->ssid_len, NULL, 0, params->key, params->key_len, params->key_idx, NULL, 0); case CFG80211_CONN_AUTH_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_AUTH; return -ENOTCONN; case CFG80211_CONN_ASSOCIATE_NEXT: if (WARN_ON(!rdev->ops->assoc)) return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_ASSOCIATING; if (wdev->conn->prev_bssid_valid) req.prev_bssid = wdev->conn->prev_bssid; req.ie = params->ie; req.ie_len = params->ie_len; req.use_mfp = params->mfp != NL80211_MFP_NO; req.crypto = params->crypto; req.flags = params->flags; req.ht_capa = params->ht_capa; req.ht_capa_mask = params->ht_capa_mask; req.vht_capa = params->vht_capa; req.vht_capa_mask = params->vht_capa_mask; err = cfg80211_mlme_assoc(rdev, wdev->netdev, params->channel, params->bssid, params->ssid, params->ssid_len, &req); if (err) cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); return err; case CFG80211_CONN_ASSOC_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_ASSOC; fallthrough; case CFG80211_CONN_ASSOC_FAILED: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); return -ENOTCONN; case CFG80211_CONN_DEAUTH: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); fallthrough; case CFG80211_CONN_ABANDON: /* free directly, disconnected event already sent */ cfg80211_sme_free(wdev); return 0; default: return 0; } } void cfg80211_conn_work(struct work_struct *work) { struct cfg80211_registered_device *rdev = container_of(work, struct cfg80211_registered_device, conn_work); struct wireless_dev *wdev; u8 bssid_buf[ETH_ALEN], *bssid = NULL; enum nl80211_timeout_reason treason; wiphy_lock(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) continue; wdev_lock(wdev); if (!netif_running(wdev->netdev)) { wdev_unlock(wdev); continue; } if (!wdev->conn || wdev->conn->state == CFG80211_CONN_CONNECTED) { wdev_unlock(wdev); continue; } if (wdev->conn->params.bssid) { memcpy(bssid_buf, wdev->conn->params.bssid, ETH_ALEN); bssid = bssid_buf; } treason = NL80211_TIMEOUT_UNSPECIFIED; if (cfg80211_conn_do_work(wdev, &treason)) { struct cfg80211_connect_resp_params cr; memset(&cr, 0, sizeof(cr)); cr.status = -1; cr.bssid = bssid; cr.timeout_reason = treason; __cfg80211_connect_result(wdev->netdev, &cr, false); } wdev_unlock(wdev); } wiphy_unlock(&rdev->wiphy); } static void cfg80211_step_auth_next(struct cfg80211_conn *conn, struct cfg80211_bss *bss) { memcpy(conn->bssid, bss->bssid, ETH_ALEN); conn->params.bssid = conn->bssid; conn->params.channel = bss->channel; conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; } /* Returned bss is reference counted and must be cleaned up appropriately. */ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; ASSERT_WDEV_LOCK(wdev); bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (!bss) return NULL; cfg80211_step_auth_next(wdev->conn, bss); schedule_work(&rdev->conn_work); return bss; } static void __cfg80211_sme_scan_done(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; ASSERT_WDEV_LOCK(wdev); if (!wdev->conn) return; if (wdev->conn->state != CFG80211_CONN_SCANNING && wdev->conn->state != CFG80211_CONN_SCAN_AGAIN) return; bss = cfg80211_get_conn_bss(wdev); if (bss) cfg80211_put_bss(&rdev->wiphy, bss); else schedule_work(&rdev->conn_work); } void cfg80211_sme_scan_done(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; wdev_lock(wdev); __cfg80211_sme_scan_done(dev); wdev_unlock(wdev); } void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; u16 status_code = le16_to_cpu(mgmt->u.auth.status_code); ASSERT_WDEV_LOCK(wdev); if (!wdev->conn || wdev->conn->state == CFG80211_CONN_CONNECTED) return; if (status_code == WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG && wdev->conn->auto_auth && wdev->conn->params.auth_type != NL80211_AUTHTYPE_NETWORK_EAP) { /* select automatically between only open, shared, leap */ switch (wdev->conn->params.auth_type) { case NL80211_AUTHTYPE_OPEN_SYSTEM: if (wdev->connect_keys) wdev->conn->params.auth_type = NL80211_AUTHTYPE_SHARED_KEY; else wdev->conn->params.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; break; case NL80211_AUTHTYPE_SHARED_KEY: wdev->conn->params.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; break; default: /* huh? */ wdev->conn->params.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; break; } wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; schedule_work(&rdev->conn_work); } else if (status_code != WLAN_STATUS_SUCCESS) { struct cfg80211_connect_resp_params cr; memset(&cr, 0, sizeof(cr)); cr.status = status_code; cr.bssid = mgmt->bssid; cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED; __cfg80211_connect_result(wdev->netdev, &cr, false); } else if (wdev->conn->state == CFG80211_CONN_AUTHENTICATING) { wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); } } bool cfg80211_sme_rx_assoc_resp(struct wireless_dev *wdev, u16 status) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return false; if (status == WLAN_STATUS_SUCCESS) { wdev->conn->state = CFG80211_CONN_CONNECTED; return false; } if (wdev->conn->prev_bssid_valid) { /* * Some stupid APs don't accept reassoc, so we * need to fall back to trying regular assoc; * return true so no event is sent to userspace. */ wdev->conn->prev_bssid_valid = false; wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); return true; } wdev->conn->state = CFG80211_CONN_ASSOC_FAILED; schedule_work(&rdev->conn_work); return false; } void cfg80211_sme_deauth(struct wireless_dev *wdev) { cfg80211_sme_free(wdev); } void cfg80211_sme_auth_timeout(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_AUTH_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } void cfg80211_sme_disassoc(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_DEAUTH; schedule_work(&rdev->conn_work); } void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_ASSOC_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_ABANDON; schedule_work(&rdev->conn_work); } static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev, const u8 *ies, size_t ies_len, const u8 **out_ies, size_t *out_ies_len) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *buf; size_t offs; if (!rdev->wiphy.extended_capabilities_len || (ies && cfg80211_find_ie(WLAN_EID_EXT_CAPABILITY, ies, ies_len))) { *out_ies = kmemdup(ies, ies_len, GFP_KERNEL); if (!*out_ies) return -ENOMEM; *out_ies_len = ies_len; return 0; } buf = kmalloc(ies_len + rdev->wiphy.extended_capabilities_len + 2, GFP_KERNEL); if (!buf) return -ENOMEM; if (ies_len) { static const u8 before_extcapa[] = { /* not listing IEs expected to be created by driver */ WLAN_EID_RSN, WLAN_EID_QOS_CAPA, WLAN_EID_RRM_ENABLED_CAPABILITIES, WLAN_EID_MOBILITY_DOMAIN, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, WLAN_EID_BSS_COEX_2040, }; offs = ieee80211_ie_split(ies, ies_len, before_extcapa, ARRAY_SIZE(before_extcapa), 0); memcpy(buf, ies, offs); /* leave a whole for extended capabilities IE */ memcpy(buf + offs + rdev->wiphy.extended_capabilities_len + 2, ies + offs, ies_len - offs); } else { offs = 0; } /* place extended capabilities IE (with only driver capabilities) */ buf[offs] = WLAN_EID_EXT_CAPABILITY; buf[offs + 1] = rdev->wiphy.extended_capabilities_len; memcpy(buf + offs + 2, rdev->wiphy.extended_capabilities, rdev->wiphy.extended_capabilities_len); *out_ies = buf; *out_ies_len = ies_len + rdev->wiphy.extended_capabilities_len + 2; return 0; } static int cfg80211_sme_connect(struct wireless_dev *wdev, struct cfg80211_connect_params *connect, const u8 *prev_bssid) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; int err; if (!rdev->ops->auth || !rdev->ops->assoc) return -EOPNOTSUPP; if (wdev->current_bss) { cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); wdev->current_bss = NULL; cfg80211_sme_free(wdev); } if (wdev->conn) return -EINPROGRESS; wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL); if (!wdev->conn) return -ENOMEM; /* * Copy all parameters, and treat explicitly IEs, BSSID, SSID. */ memcpy(&wdev->conn->params, connect, sizeof(*connect)); if (connect->bssid) { wdev->conn->params.bssid = wdev->conn->bssid; memcpy(wdev->conn->bssid, connect->bssid, ETH_ALEN); } if (cfg80211_sme_get_conn_ies(wdev, connect->ie, connect->ie_len, &wdev->conn->ie, &wdev->conn->params.ie_len)) { kfree(wdev->conn); wdev->conn = NULL; return -ENOMEM; } wdev->conn->params.ie = wdev->conn->ie; if (connect->auth_type == NL80211_AUTHTYPE_AUTOMATIC) { wdev->conn->auto_auth = true; /* start with open system ... should mostly work */ wdev->conn->params.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; } else { wdev->conn->auto_auth = false; } wdev->conn->params.ssid = wdev->ssid; wdev->conn->params.ssid_len = wdev->ssid_len; /* see if we have the bss already */ bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (prev_bssid) { memcpy(wdev->conn->prev_bssid, prev_bssid, ETH_ALEN); wdev->conn->prev_bssid_valid = true; } /* we're good if we have a matching bss struct */ if (bss) { enum nl80211_timeout_reason treason; cfg80211_step_auth_next(wdev->conn, bss); err = cfg80211_conn_do_work(wdev, &treason); cfg80211_put_bss(wdev->wiphy, bss); } else { /* otherwise we'll need to scan for the AP first */ err = cfg80211_conn_scan(wdev); /* * If we can't scan right now, then we need to scan again * after the current scan finished, since the parameters * changed (unless we find a good AP anyway). */ if (err == -EBUSY) { err = 0; wdev->conn->state = CFG80211_CONN_SCAN_AGAIN; } } if (err) cfg80211_sme_free(wdev); return err; } static int cfg80211_sme_disconnect(struct wireless_dev *wdev, u16 reason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int err; if (!wdev->conn) return 0; if (!rdev->ops->deauth) return -EOPNOTSUPP; if (wdev->conn->state == CFG80211_CONN_SCANNING || wdev->conn->state == CFG80211_CONN_SCAN_AGAIN) { err = 0; goto out; } /* wdev->conn->params.bssid must be set if > SCANNING */ err = cfg80211_mlme_deauth(rdev, wdev->netdev, wdev->conn->params.bssid, NULL, 0, reason, false); out: cfg80211_sme_free(wdev); return err; } /* * code shared for in-device and software SME */ static bool cfg80211_is_all_idle(void) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; bool is_all_idle = true; /* * All devices must be idle as otherwise if you are actively * scanning some new beacon hints could be learned and would * count as new regulatory hints. * Also if there is any other active beaconing interface we * need not issue a disconnect hint and reset any info such * as chan dfs state, etc. */ list_for_each_entry(rdev, &cfg80211_rdev_list, list) { list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { wdev_lock(wdev); if (wdev->conn || wdev->current_bss || cfg80211_beaconing_iface_active(wdev)) is_all_idle = false; wdev_unlock(wdev); } } return is_all_idle; } static void disconnect_work(struct work_struct *work) { rtnl_lock(); if (cfg80211_is_all_idle()) regulatory_hint_disconnect(); rtnl_unlock(); } DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); /* * API calls for drivers implementing connect/disconnect and * SME event handling */ /* This method must consume bss one way or another */ void __cfg80211_connect_result(struct net_device *dev, struct cfg80211_connect_resp_params *cr, bool wextev) { struct wireless_dev *wdev = dev->ieee80211_ptr; const u8 *country_ie; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif ASSERT_WDEV_LOCK(wdev); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) { cfg80211_put_bss(wdev->wiphy, cr->bss); return; } wdev->unprot_beacon_reported = 0; nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev, cr, GFP_KERNEL); #ifdef CONFIG_CFG80211_WEXT if (wextev) { if (cr->req_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->req_ie_len; wireless_send_event(dev, IWEVASSOCREQIE, &wrqu, cr->req_ie); } if (cr->resp_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->resp_ie_len; wireless_send_event(dev, IWEVASSOCRESPIE, &wrqu, cr->resp_ie); } memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; if (cr->bssid && cr->status == WLAN_STATUS_SUCCESS) { memcpy(wrqu.ap_addr.sa_data, cr->bssid, ETH_ALEN); memcpy(wdev->wext.prev_bssid, cr->bssid, ETH_ALEN); wdev->wext.prev_bssid_valid = true; } wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); } #endif if (!cr->bss && (cr->status == WLAN_STATUS_SUCCESS)) { WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect); cr->bss = cfg80211_get_bss(wdev->wiphy, NULL, cr->bssid, wdev->ssid, wdev->ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (cr->bss) cfg80211_hold_bss(bss_from_pub(cr->bss)); } if (wdev->current_bss) { cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); wdev->current_bss = NULL; } if (cr->status != WLAN_STATUS_SUCCESS) { kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; wdev->ssid_len = 0; wdev->conn_owner_nlportid = 0; if (cr->bss) { cfg80211_unhold_bss(bss_from_pub(cr->bss)); cfg80211_put_bss(wdev->wiphy, cr->bss); } cfg80211_sme_free(wdev); return; } if (WARN_ON(!cr->bss)) return; wdev->current_bss = bss_from_pub(cr->bss); if (!(wdev->wiphy->flags & WIPHY_FLAG_HAS_STATIC_WEP)) cfg80211_upload_connect_keys(wdev); rcu_read_lock(); country_ie = ieee80211_bss_get_ie(cr->bss, WLAN_EID_COUNTRY); if (!country_ie) { rcu_read_unlock(); return; } country_ie = kmemdup(country_ie, 2 + country_ie[1], GFP_ATOMIC); rcu_read_unlock(); if (!country_ie) return; /* * ieee80211_bss_get_ie() ensures we can access: * - country_ie + 2, the start of the country ie data, and * - and country_ie[1] which is the IE length */ regulatory_hint_country_ie(wdev->wiphy, cr->bss->channel->band, country_ie + 2, country_ie[1]); kfree(country_ie); } /* Consumes bss object one way or another */ void cfg80211_connect_done(struct net_device *dev, struct cfg80211_connect_resp_params *params, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; u8 *next; if (params->bss) { struct cfg80211_internal_bss *ibss = bss_from_pub(params->bss); if (list_empty(&ibss->list)) { struct cfg80211_bss *found = NULL, *tmp = params->bss; found = cfg80211_get_bss(wdev->wiphy, NULL, params->bss->bssid, wdev->ssid, wdev->ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (found) { /* The same BSS is already updated so use it * instead, as it has latest info. */ params->bss = found; } else { /* Update with BSS provided by driver, it will * be freshly added and ref cnted, we can free * the old one. * * signal_valid can be false, as we are not * expecting the BSS to be found. * * keep the old timestamp to avoid confusion */ cfg80211_bss_update(rdev, ibss, false, ibss->ts); } cfg80211_put_bss(wdev->wiphy, tmp); } } ev = kzalloc(sizeof(*ev) + (params->bssid ? ETH_ALEN : 0) + params->req_ie_len + params->resp_ie_len + params->fils.kek_len + params->fils.pmk_len + (params->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); if (!ev) { cfg80211_put_bss(wdev->wiphy, params->bss); return; } ev->type = EVENT_CONNECT_RESULT; next = ((u8 *)ev) + sizeof(*ev); if (params->bssid) { ev->cr.bssid = next; memcpy((void *)ev->cr.bssid, params->bssid, ETH_ALEN); next += ETH_ALEN; } if (params->req_ie_len) { ev->cr.req_ie = next; ev->cr.req_ie_len = params->req_ie_len; memcpy((void *)ev->cr.req_ie, params->req_ie, params->req_ie_len); next += params->req_ie_len; } if (params->resp_ie_len) { ev->cr.resp_ie = next; ev->cr.resp_ie_len = params->resp_ie_len; memcpy((void *)ev->cr.resp_ie, params->resp_ie, params->resp_ie_len); next += params->resp_ie_len; } if (params->fils.kek_len) { ev->cr.fils.kek = next; ev->cr.fils.kek_len = params->fils.kek_len; memcpy((void *)ev->cr.fils.kek, params->fils.kek, params->fils.kek_len); next += params->fils.kek_len; } if (params->fils.pmk_len) { ev->cr.fils.pmk = next; ev->cr.fils.pmk_len = params->fils.pmk_len; memcpy((void *)ev->cr.fils.pmk, params->fils.pmk, params->fils.pmk_len); next += params->fils.pmk_len; } if (params->fils.pmkid) { ev->cr.fils.pmkid = next; memcpy((void *)ev->cr.fils.pmkid, params->fils.pmkid, WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } ev->cr.fils.update_erp_next_seq_num = params->fils.update_erp_next_seq_num; if (params->fils.update_erp_next_seq_num) ev->cr.fils.erp_next_seq_num = params->fils.erp_next_seq_num; if (params->bss) cfg80211_hold_bss(bss_from_pub(params->bss)); ev->cr.bss = params->bss; ev->cr.status = params->status; ev->cr.timeout_reason = params->timeout_reason; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_connect_done); /* Consumes bss object one way or another */ void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info) { #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif ASSERT_WDEV_LOCK(wdev); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) goto out; if (WARN_ON(!wdev->current_bss)) goto out; cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); wdev->current_bss = NULL; if (WARN_ON(!info->bss)) return; cfg80211_hold_bss(bss_from_pub(info->bss)); wdev->current_bss = bss_from_pub(info->bss); wdev->unprot_beacon_reported = 0; nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy), wdev->netdev, info, GFP_KERNEL); #ifdef CONFIG_CFG80211_WEXT if (info->req_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = info->req_ie_len; wireless_send_event(wdev->netdev, IWEVASSOCREQIE, &wrqu, info->req_ie); } if (info->resp_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = info->resp_ie_len; wireless_send_event(wdev->netdev, IWEVASSOCRESPIE, &wrqu, info->resp_ie); } memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; memcpy(wrqu.ap_addr.sa_data, info->bss->bssid, ETH_ALEN); memcpy(wdev->wext.prev_bssid, info->bss->bssid, ETH_ALEN); wdev->wext.prev_bssid_valid = true; wireless_send_event(wdev->netdev, SIOCGIWAP, &wrqu, NULL); #endif return; out: cfg80211_put_bss(wdev->wiphy, info->bss); } /* Consumes info->bss object one way or another */ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; u8 *next; if (!info->bss) { info->bss = cfg80211_get_bss(wdev->wiphy, info->channel, info->bssid, wdev->ssid, wdev->ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); } if (WARN_ON(!info->bss)) return; ev = kzalloc(sizeof(*ev) + info->req_ie_len + info->resp_ie_len + info->fils.kek_len + info->fils.pmk_len + (info->fils.pmkid ? WLAN_PMKID_LEN : 0), gfp); if (!ev) { cfg80211_put_bss(wdev->wiphy, info->bss); return; } ev->type = EVENT_ROAMED; next = ((u8 *)ev) + sizeof(*ev); if (info->req_ie_len) { ev->rm.req_ie = next; ev->rm.req_ie_len = info->req_ie_len; memcpy((void *)ev->rm.req_ie, info->req_ie, info->req_ie_len); next += info->req_ie_len; } if (info->resp_ie_len) { ev->rm.resp_ie = next; ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); next += info->resp_ie_len; } if (info->fils.kek_len) { ev->rm.fils.kek = next; ev->rm.fils.kek_len = info->fils.kek_len; memcpy((void *)ev->rm.fils.kek, info->fils.kek, info->fils.kek_len); next += info->fils.kek_len; } if (info->fils.pmk_len) { ev->rm.fils.pmk = next; ev->rm.fils.pmk_len = info->fils.pmk_len; memcpy((void *)ev->rm.fils.pmk, info->fils.pmk, info->fils.pmk_len); next += info->fils.pmk_len; } if (info->fils.pmkid) { ev->rm.fils.pmkid = next; memcpy((void *)ev->rm.fils.pmkid, info->fils.pmkid, WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } ev->rm.fils.update_erp_next_seq_num = info->fils.update_erp_next_seq_num; if (info->fils.update_erp_next_seq_num) ev->rm.fils.erp_next_seq_num = info->fils.erp_next_seq_num; ev->rm.bss = info->bss; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_roamed); void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) { ASSERT_WDEV_LOCK(wdev); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return; if (WARN_ON(!wdev->current_bss) || WARN_ON(!ether_addr_equal(wdev->current_bss->pub.bssid, bssid))) return; nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, bssid); } void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; if (WARN_ON(!bssid)) return; ev = kzalloc(sizeof(*ev), gfp); if (!ev) return; ev->type = EVENT_PORT_AUTHORIZED; memcpy(ev->pa.bssid, bssid, ETH_ALEN); /* * Use the wdev event list so that if there are pending * connected/roamed events, they will be reported first. */ spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_port_authorized); void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int i; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif ASSERT_WDEV_LOCK(wdev); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; if (wdev->current_bss) { cfg80211_unhold_bss(wdev->current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub); } wdev->current_bss = NULL; wdev->ssid_len = 0; wdev->conn_owner_nlportid = 0; kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); /* stop critical protocol if supported */ if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) { rdev->crit_proto_nlportid = 0; rdev_crit_proto_stop(rdev, wdev); } /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. */ if (rdev->ops->del_key) { int max_key_idx = 5; if (wiphy_ext_feature_isset( wdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION) || wiphy_ext_feature_isset( wdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT)) max_key_idx = 7; for (i = 0; i <= max_key_idx; i++) rdev_del_key(rdev, dev, i, false, NULL); } rdev_set_qos_map(rdev, dev, NULL); #ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); wdev->wext.connect.ssid_len = 0; #endif schedule_work(&cfg80211_disconnect_work); } void cfg80211_disconnected(struct net_device *dev, u16 reason, const u8 *ie, size_t ie_len, bool locally_generated, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; ev = kzalloc(sizeof(*ev) + ie_len, gfp); if (!ev) return; ev->type = EVENT_DISCONNECTED; ev->dc.ie = ((u8 *)ev) + sizeof(*ev); ev->dc.ie_len = ie_len; memcpy((void *)ev->dc.ie, ie, ie_len); ev->dc.reason = reason; ev->dc.locally_generated = locally_generated; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_disconnected); /* * API calls for nl80211/wext compatibility code */ int cfg80211_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *connect, struct cfg80211_cached_keys *connkeys, const u8 *prev_bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; ASSERT_WDEV_LOCK(wdev); /* * If we have an ssid_len, we're trying to connect or are * already connected, so reject a new SSID unless it's the * same (which is the case for re-association.) */ if (wdev->ssid_len && (wdev->ssid_len != connect->ssid_len || memcmp(wdev->ssid, connect->ssid, wdev->ssid_len))) return -EALREADY; /* * If connected, reject (re-)association unless prev_bssid * matches the current BSSID. */ if (wdev->current_bss) { if (!prev_bssid) return -EALREADY; if (!ether_addr_equal(prev_bssid, wdev->current_bss->pub.bssid)) return -ENOTCONN; } /* * Reject if we're in the process of connecting with WEP, * this case isn't very interesting and trying to handle * it would make the code much more complex. */ if (wdev->connect_keys) return -EINPROGRESS; cfg80211_oper_and_ht_capa(&connect->ht_capa_mask, rdev->wiphy.ht_capa_mod_mask); cfg80211_oper_and_vht_capa(&connect->vht_capa_mask, rdev->wiphy.vht_capa_mod_mask); if (connkeys && connkeys->def >= 0) { int idx; u32 cipher; idx = connkeys->def; cipher = connkeys->params[idx].cipher; /* If given a WEP key we may need it for shared key auth */ if (cipher == WLAN_CIPHER_SUITE_WEP40 || cipher == WLAN_CIPHER_SUITE_WEP104) { connect->key_idx = idx; connect->key = connkeys->params[idx].key; connect->key_len = connkeys->params[idx].key_len; /* * If ciphers are not set (e.g. when going through * iwconfig), we have to set them appropriately here. */ if (connect->crypto.cipher_group == 0) connect->crypto.cipher_group = cipher; if (connect->crypto.n_ciphers_pairwise == 0) { connect->crypto.n_ciphers_pairwise = 1; connect->crypto.ciphers_pairwise[0] = cipher; } } connect->crypto.wep_keys = connkeys->params; connect->crypto.wep_tx_key = connkeys->def; } else { if (WARN_ON(connkeys)) return -EINVAL; /* connect can point to wdev->wext.connect which * can hold key data from a previous connection */ connect->key = NULL; connect->key_len = 0; connect->key_idx = 0; } wdev->connect_keys = connkeys; memcpy(wdev->ssid, connect->ssid, connect->ssid_len); wdev->ssid_len = connect->ssid_len; wdev->conn_bss_type = connect->pbss ? IEEE80211_BSS_TYPE_PBSS : IEEE80211_BSS_TYPE_ESS; if (!rdev->ops->connect) err = cfg80211_sme_connect(wdev, connect, prev_bssid); else err = rdev_connect(rdev, dev, connect); if (err) { wdev->connect_keys = NULL; /* * This could be reassoc getting refused, don't clear * ssid_len in that case. */ if (!wdev->current_bss) wdev->ssid_len = 0; return err; } return 0; } int cfg80211_disconnect(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 reason, bool wextev) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err = 0; ASSERT_WDEV_LOCK(wdev); kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; wdev->conn_owner_nlportid = 0; if (wdev->conn) err = cfg80211_sme_disconnect(wdev, reason); else if (!rdev->ops->disconnect) cfg80211_mlme_down(rdev, dev); else if (wdev->ssid_len) err = rdev_disconnect(rdev, dev, reason); /* * Clear ssid_len unless we actually were fully connected, * in which case cfg80211_disconnected() will take care of * this later. */ if (!wdev->current_bss) wdev->ssid_len = 0; return err; } /* * Used to clean up after the connection / connection attempt owner socket * disconnects */ void cfg80211_autodisconnect_wk(struct work_struct *work) { struct wireless_dev *wdev = container_of(work, struct wireless_dev, disconnect_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); wdev_lock(wdev); if (wdev->conn_owner_nlportid) { switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: __cfg80211_leave_ibss(rdev, wdev->netdev, false); break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: __cfg80211_stop_ap(rdev, wdev->netdev, false); break; case NL80211_IFTYPE_MESH_POINT: __cfg80211_leave_mesh(rdev, wdev->netdev); break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: /* * Use disconnect_bssid if still connecting and * ops->disconnect not implemented. Otherwise we can * use cfg80211_disconnect. */ if (rdev->ops->disconnect || wdev->current_bss) cfg80211_disconnect(rdev, wdev->netdev, WLAN_REASON_DEAUTH_LEAVING, true); else cfg80211_mlme_deauth(rdev, wdev->netdev, wdev->disconnect_bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); break; default: break; } } wdev_unlock(wdev); } |
| 4582 4580 90 90 91 92 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /* * This function is both preempt and irq safe. The former is due to explicit * preemption disable. The latter is guaranteed by the fact that the slow path * is explicitly protected by an irq-safe spinlock whereas the fast patch uses * this_cpu_add which is irq-safe by definition. Hence there is no need muck * with irq state before calling this one */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; preempt_disable(); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock_irqrestore(&fbc->lock, flags); } else { this_cpu_add(*fbc->counters, amount); } preempt_enable(); } EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key) { unsigned long flags __maybe_unused; raw_spin_lock_init(&fbc->lock); lockdep_set_class(&fbc->lock, key); fbc->count = amount; fbc->counters = alloc_percpu_gfp(s32, gfp); if (!fbc->counters) return -ENOMEM; debug_percpu_counter_activate(fbc); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc->list); spin_lock_irqsave(&percpu_counters_lock, flags); list_add(&fbc->list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init); void percpu_counter_destroy(struct percpu_counter *fbc) { unsigned long flags __maybe_unused; if (!fbc->counters) return; debug_percpu_counter_deactivate(fbc); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); list_del(&fbc->list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc->counters); fbc->counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 22 22 22 16 10 8 3 3 20 6 4 4 5 8 7 4 3 7 3 3 3 1 2 2 1 1 1 1 3 1 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * cfg80211 wext compat for managed mode. * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2009, 2020-2021 Intel Corporation. */ #include <linux/export.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <net/cfg80211.h> #include <net/cfg80211-wext.h> #include "wext-compat.h" #include "nl80211.h" int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { struct cfg80211_cached_keys *ck = NULL; const u8 *prev_bssid = NULL; int err, i; ASSERT_RTNL(); ASSERT_WDEV_LOCK(wdev); if (!netif_running(wdev->netdev)) return 0; wdev->wext.connect.ie = wdev->wext.ie; wdev->wext.connect.ie_len = wdev->wext.ie_len; /* Use default background scan period */ wdev->wext.connect.bg_scan_period = -1; if (wdev->wext.keys) { wdev->wext.keys->def = wdev->wext.default_key; if (wdev->wext.default_key != -1) wdev->wext.connect.privacy = true; } if (!wdev->wext.connect.ssid_len) return 0; if (wdev->wext.keys && wdev->wext.keys->def != -1) { ck = kmemdup(wdev->wext.keys, sizeof(*ck), GFP_KERNEL); if (!ck) return -ENOMEM; for (i = 0; i < CFG80211_MAX_WEP_KEYS; i++) ck->params[i].key = ck->data[i]; } if (wdev->wext.prev_bssid_valid) prev_bssid = wdev->wext.prev_bssid; err = cfg80211_connect(rdev, wdev->netdev, &wdev->wext.connect, ck, prev_bssid); if (err) kfree_sensitive(ck); return err; } int cfg80211_mgd_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *wextfreq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct ieee80211_channel *chan = NULL; int err, freq; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; freq = cfg80211_wext_freq(wextfreq); if (freq < 0) return freq; if (freq) { chan = ieee80211_get_channel(wdev->wiphy, freq); if (!chan) return -EINVAL; if (chan->flags & IEEE80211_CHAN_DISABLED) return -EINVAL; } wdev_lock(wdev); if (wdev->conn) { bool event = true; if (wdev->wext.connect.channel == chan) { err = 0; goto out; } /* if SSID set, we'll try right again, avoid event */ if (wdev->wext.connect.ssid_len) event = false; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, event); if (err) goto out; } wdev->wext.connect.channel = chan; err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); return err; } int cfg80211_mgd_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_channel *chan = NULL; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; wdev_lock(wdev); if (wdev->current_bss) chan = wdev->current_bss->pub.channel; else if (wdev->wext.connect.channel) chan = wdev->wext.connect.channel; wdev_unlock(wdev); if (chan) { freq->m = chan->center_freq; freq->e = 6; return 0; } /* no channel if not joining */ return -EINVAL; } int cfg80211_mgd_wext_siwessid(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); size_t len = data->length; int err; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (!data->flags) len = 0; /* iwconfig uses nul termination in SSID.. */ if (len > 0 && ssid[len - 1] == '\0') len--; wdev_lock(wdev); err = 0; if (wdev->conn) { bool event = true; if (wdev->wext.connect.ssid && len && len == wdev->wext.connect.ssid_len && memcmp(wdev->wext.connect.ssid, ssid, len) == 0) goto out; /* if SSID set now, we'll try to connect, avoid event */ if (len) event = false; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, event); if (err) goto out; } wdev->wext.prev_bssid_valid = false; wdev->wext.connect.ssid = wdev->wext.ssid; memcpy(wdev->wext.ssid, ssid, len); wdev->wext.connect.ssid_len = len; wdev->wext.connect.crypto.control_port = false; wdev->wext.connect.crypto.control_port_ethertype = cpu_to_be16(ETH_P_PAE); err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); return err; } int cfg80211_mgd_wext_giwessid(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; int ret = 0; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; data->flags = 0; wdev_lock(wdev); if (wdev->current_bss) { const u8 *ie; rcu_read_lock(); ie = ieee80211_bss_get_ie(&wdev->current_bss->pub, WLAN_EID_SSID); if (ie) { data->flags = 1; data->length = ie[1]; if (data->length > IW_ESSID_MAX_SIZE) ret = -EINVAL; else memcpy(ssid, ie + 2, data->length); } rcu_read_unlock(); } else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { data->flags = 1; data->length = wdev->wext.connect.ssid_len; memcpy(ssid, wdev->wext.connect.ssid, data->length); } wdev_unlock(wdev); return ret; } int cfg80211_mgd_wext_siwap(struct net_device *dev, struct iw_request_info *info, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *bssid = ap_addr->sa_data; int err; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (ap_addr->sa_family != ARPHRD_ETHER) return -EINVAL; /* automatic mode */ if (is_zero_ether_addr(bssid) || is_broadcast_ether_addr(bssid)) bssid = NULL; wdev_lock(wdev); if (wdev->conn) { err = 0; /* both automatic */ if (!bssid && !wdev->wext.connect.bssid) goto out; /* fixed already - and no change */ if (wdev->wext.connect.bssid && bssid && ether_addr_equal(bssid, wdev->wext.connect.bssid)) goto out; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, false); if (err) goto out; } if (bssid) { memcpy(wdev->wext.bssid, bssid, ETH_ALEN); wdev->wext.connect.bssid = wdev->wext.bssid; } else wdev->wext.connect.bssid = NULL; err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); return err; } int cfg80211_mgd_wext_giwap(struct net_device *dev, struct iw_request_info *info, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; ap_addr->sa_family = ARPHRD_ETHER; wdev_lock(wdev); if (wdev->current_bss) memcpy(ap_addr->sa_data, wdev->current_bss->pub.bssid, ETH_ALEN); else eth_zero_addr(ap_addr->sa_data); wdev_unlock(wdev); return 0; } int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *ie = extra; int ie_len = data->length, err; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!ie_len) ie = NULL; wdev_lock(wdev); /* no change */ err = 0; if (wdev->wext.ie_len == ie_len && memcmp(wdev->wext.ie, ie, ie_len) == 0) goto out; if (ie_len) { ie = kmemdup(extra, ie_len, GFP_KERNEL); if (!ie) { err = -ENOMEM; goto out; } } else ie = NULL; kfree(wdev->wext.ie); wdev->wext.ie = ie; wdev->wext.ie_len = ie_len; if (wdev->conn) { err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, false); if (err) goto out; } /* userspace better not think we'll reconnect */ err = 0; out: wdev_unlock(wdev); return err; } int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_mlme *mlme = (struct iw_mlme *)extra; struct cfg80211_registered_device *rdev; int err; if (!wdev) return -EOPNOTSUPP; rdev = wiphy_to_rdev(wdev->wiphy); if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; if (mlme->addr.sa_family != ARPHRD_ETHER) return -EINVAL; wiphy_lock(&rdev->wiphy); wdev_lock(wdev); switch (mlme->cmd) { case IW_MLME_DEAUTH: case IW_MLME_DISASSOC: err = cfg80211_disconnect(rdev, dev, mlme->reason_code, true); break; default: err = -EOPNOTSUPP; break; } wdev_unlock(wdev); wiphy_unlock(&rdev->wiphy); return err; } |
| 15 15 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 | /* vcan.c - Virtual CAN interface * * Copyright (c) 2002-2017 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/init.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/can.h> #include <linux/can/can-ml.h> #include <linux/can/dev.h> #include <linux/can/skb.h> #include <linux/slab.h> #include <net/rtnetlink.h> #define DRV_NAME "vcan" MODULE_DESCRIPTION("virtual CAN interface"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); /* CAN test feature: * Enable the echo on driver level for testing the CAN core echo modes. * See Documentation/networking/can.rst for details. */ static bool echo; /* echo testing. Default: 0 (Off) */ module_param(echo, bool, 0444); MODULE_PARM_DESC(echo, "Echo sent frames (for testing). Default: 0 (Off)"); static void vcan_rx(struct sk_buff *skb, struct net_device *dev) { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; struct net_device_stats *stats = &dev->stats; stats->rx_packets++; stats->rx_bytes += cfd->len; skb->pkt_type = PACKET_BROADCAST; skb->dev = dev; skb->ip_summed = CHECKSUM_UNNECESSARY; netif_rx_ni(skb); } static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev) { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; struct net_device_stats *stats = &dev->stats; int loop; if (can_dropped_invalid_skb(dev, skb)) return NETDEV_TX_OK; stats->tx_packets++; stats->tx_bytes += cfd->len; /* set flag whether this packet has to be looped back */ loop = skb->pkt_type == PACKET_LOOPBACK; if (!echo) { /* no echo handling available inside this driver */ if (loop) { /* only count the packets here, because the * CAN core already did the echo for us */ stats->rx_packets++; stats->rx_bytes += cfd->len; } consume_skb(skb); return NETDEV_TX_OK; } /* perform standard echo handling for CAN network interfaces */ if (loop) { skb = can_create_echo_skb(skb); if (!skb) return NETDEV_TX_OK; /* receive with packet counting */ vcan_rx(skb, dev); } else { /* no looped packets => no counting */ consume_skb(skb); } return NETDEV_TX_OK; } static int vcan_change_mtu(struct net_device *dev, int new_mtu) { /* Do not allow changing the MTU while running */ if (dev->flags & IFF_UP) return -EBUSY; if (new_mtu != CAN_MTU && new_mtu != CANFD_MTU) return -EINVAL; dev->mtu = new_mtu; return 0; } static const struct net_device_ops vcan_netdev_ops = { .ndo_start_xmit = vcan_tx, .ndo_change_mtu = vcan_change_mtu, }; static void vcan_setup(struct net_device *dev) { dev->type = ARPHRD_CAN; dev->mtu = CANFD_MTU; dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 0; dev->flags = IFF_NOARP; can_set_ml_priv(dev, netdev_priv(dev)); /* set flags according to driver capabilities */ if (echo) dev->flags |= IFF_ECHO; dev->netdev_ops = &vcan_netdev_ops; dev->needs_free_netdev = true; } static struct rtnl_link_ops vcan_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct can_ml_priv), .setup = vcan_setup, }; static __init int vcan_init_module(void) { pr_info("Virtual CAN interface driver\n"); if (echo) pr_info("enabled echo on driver level.\n"); return rtnl_link_register(&vcan_link_ops); } static __exit void vcan_cleanup_module(void) { rtnl_link_unregister(&vcan_link_ops); } module_init(vcan_init_module); module_exit(vcan_cleanup_module); |
| 6 4 3 6 6 6 6 12 12 9 4 6 6 12 12 6 18 18 3 12 20 1 1 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 | // SPDX-License-Identifier: GPL-2.0 /* XDP sockets monitoring support * * Copyright(c) 2019 Intel Corporation. * * Author: Björn Töpel <bjorn.topel@intel.com> */ #include <linux/module.h> #include <net/xdp_sock.h> #include <linux/xdp_diag.h> #include <linux/sock_diag.h> #include "xsk_queue.h" #include "xsk.h" static int xsk_diag_put_info(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xdp_diag_info di = {}; di.ifindex = xs->dev ? xs->dev->ifindex : 0; di.queue_id = xs->queue_id; return nla_put(nlskb, XDP_DIAG_INFO, sizeof(di), &di); } static int xsk_diag_put_ring(const struct xsk_queue *queue, int nl_type, struct sk_buff *nlskb) { struct xdp_diag_ring dr = {}; dr.entries = queue->nentries; return nla_put(nlskb, nl_type, sizeof(dr), &dr); } static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs, struct sk_buff *nlskb) { int err = 0; if (xs->rx) err = xsk_diag_put_ring(xs->rx, XDP_DIAG_RX_RING, nlskb); if (!err && xs->tx) err = xsk_diag_put_ring(xs->tx, XDP_DIAG_TX_RING, nlskb); return err; } static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xsk_buff_pool *pool = xs->pool; struct xdp_umem *umem = xs->umem; struct xdp_diag_umem du = {}; int err; if (!umem) return 0; du.id = umem->id; du.size = umem->size; du.num_pages = umem->npgs; du.chunk_size = umem->chunk_size; du.headroom = umem->headroom; du.ifindex = (pool && pool->netdev) ? pool->netdev->ifindex : 0; du.queue_id = pool ? pool->queue_id : 0; du.flags = 0; if (umem->zc) du.flags |= XDP_DU_F_ZEROCOPY; du.refs = refcount_read(&umem->users); err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); if (!err && pool && pool->fq) err = xsk_diag_put_ring(pool->fq, XDP_DIAG_UMEM_FILL_RING, nlskb); if (!err && pool && pool->cq) err = xsk_diag_put_ring(pool->cq, XDP_DIAG_UMEM_COMPLETION_RING, nlskb); return err; } static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb) { struct xdp_diag_stats du = {}; du.n_rx_dropped = xs->rx_dropped; du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx); du.n_rx_full = xs->rx_queue_full; du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0; du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx); du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx); return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du); } static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb, struct xdp_diag_req *req, struct user_namespace *user_ns, u32 portid, u32 seq, u32 flags, int sk_ino) { struct xdp_sock *xs = xdp_sk(sk); struct xdp_diag_msg *msg; struct nlmsghdr *nlh; nlh = nlmsg_put(nlskb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*msg), flags); if (!nlh) return -EMSGSIZE; msg = nlmsg_data(nlh); memset(msg, 0, sizeof(*msg)); msg->xdiag_family = AF_XDP; msg->xdiag_type = sk->sk_type; msg->xdiag_ino = sk_ino; sock_diag_save_cookie(sk, msg->xdiag_cookie); mutex_lock(&xs->mutex); if (READ_ONCE(xs->state) == XSK_UNBOUND) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_INFO) && nla_put_u32(nlskb, XDP_DIAG_UID, from_kuid_munged(user_ns, sock_i_uid(sk)))) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_RING_CFG) && xsk_diag_put_rings_cfg(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_UMEM) && xsk_diag_put_umem(xs, nlskb)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_MEMINFO) && sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO)) goto out_nlmsg_trim; if ((req->xdiag_show & XDP_SHOW_STATS) && xsk_diag_put_stats(xs, nlskb)) goto out_nlmsg_trim; mutex_unlock(&xs->mutex); nlmsg_end(nlskb, nlh); return 0; out_nlmsg_trim: mutex_unlock(&xs->mutex); nlmsg_cancel(nlskb, nlh); return -EMSGSIZE; } static int xsk_diag_dump(struct sk_buff *nlskb, struct netlink_callback *cb) { struct xdp_diag_req *req = nlmsg_data(cb->nlh); struct net *net = sock_net(nlskb->sk); int num = 0, s_num = cb->args[0]; struct sock *sk; mutex_lock(&net->xdp.lock); sk_for_each(sk, &net->xdp.list) { if (!net_eq(sock_net(sk), net)) continue; if (num++ < s_num) continue; if (xsk_diag_fill(sk, nlskb, req, sk_user_ns(NETLINK_CB(cb->skb).sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, sock_i_ino(sk)) < 0) { num--; break; } } mutex_unlock(&net->xdp.lock); cb->args[0] = num; return nlskb->len; } static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr) { struct netlink_dump_control c = { .dump = xsk_diag_dump }; int hdrlen = sizeof(struct xdp_diag_req); struct net *net = sock_net(nlskb->sk); if (nlmsg_len(hdr) < hdrlen) return -EINVAL; if (!(hdr->nlmsg_flags & NLM_F_DUMP)) return -EOPNOTSUPP; return netlink_dump_start(net->diag_nlsk, nlskb, hdr, &c); } static const struct sock_diag_handler xsk_diag_handler = { .family = AF_XDP, .dump = xsk_diag_handler_dump, }; static int __init xsk_diag_init(void) { return sock_diag_register(&xsk_diag_handler); } static void __exit xsk_diag_exit(void) { sock_diag_unregister(&xsk_diag_handler); } module_init(xsk_diag_init); module_exit(xsk_diag_exit); MODULE_LICENSE("GPL"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP); |
| 415 414 416 416 416 143 143 143 143 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 | // SPDX-License-Identifier: GPL-2.0 /* sysfs entries for device PM */ #include <linux/device.h> #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/pm_qos.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeup.h> #include <linux/atomic.h> #include <linux/jiffies.h> #include "power.h" /* * control - Report/change current runtime PM setting of the device * * Runtime power management of a device can be blocked with the help of * this attribute. All devices have one of the following two values for * the power/control file: * * + "auto\n" to allow the device to be power managed at run time; * + "on\n" to prevent the device from being power managed at run time; * * The default for all devices is "auto", which means that devices may be * subject to automatic power management, depending on their drivers. * Changing this attribute to "on" prevents the driver from power managing * the device at run time. Doing that while the device is suspended causes * it to be woken up. * * wakeup - Report/change current wakeup option for device * * Some devices support "wakeup" events, which are hardware signals * used to activate devices from suspended or low power states. Such * devices have one of three values for the sysfs power/wakeup file: * * + "enabled\n" to issue the events; * + "disabled\n" not to do so; or * + "\n" for temporary or permanent inability to issue wakeup. * * (For example, unconfigured USB devices can't issue wakeups.) * * Familiar examples of devices that can issue wakeup events include * keyboards and mice (both PS2 and USB styles), power buttons, modems, * "Wake-On-LAN" Ethernet links, GPIO lines, and more. Some events * will wake the entire system from a suspend state; others may just * wake up the device (if the system as a whole is already active). * Some wakeup events use normal IRQ lines; other use special out * of band signaling. * * It is the responsibility of device drivers to enable (or disable) * wakeup signaling as part of changing device power states, respecting * the policy choices provided through the driver model. * * Devices may not be able to generate wakeup events from all power * states. Also, the events may be ignored in some configurations; * for example, they might need help from other devices that aren't * active, or which may have wakeup disabled. Some drivers rely on * wakeup events internally (unless they are disabled), keeping * their hardware in low power modes whenever they're unused. This * saves runtime power, without requiring system-wide sleep states. * * async - Report/change current async suspend setting for the device * * Asynchronous suspend and resume of the device during system-wide power * state transitions can be enabled by writing "enabled" to this file. * Analogously, if "disabled" is written to this file, the device will be * suspended and resumed synchronously. * * All devices have one of the following two values for power/async: * * + "enabled\n" to permit the asynchronous suspend/resume of the device; * + "disabled\n" to forbid it; * * NOTE: It generally is unsafe to permit the asynchronous suspend/resume * of a device unless it is certain that all of the PM dependencies of the * device are known to the PM core. However, for some devices this * attribute is set to "enabled" by bus type code or device drivers and in * that cases it should be safe to leave the default value. * * autosuspend_delay_ms - Report/change a device's autosuspend_delay value * * Some drivers don't want to carry out a runtime suspend as soon as a * device becomes idle; they want it always to remain idle for some period * of time before suspending it. This period is the autosuspend_delay * value (expressed in milliseconds) and it can be controlled by the user. * If the value is negative then the device will never be runtime * suspended. * * NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay * value are used only if the driver calls pm_runtime_use_autosuspend(). * * wakeup_count - Report the number of wakeup events related to the device */ const char power_group_name[] = "power"; EXPORT_SYMBOL_GPL(power_group_name); static const char ctrl_auto[] = "auto"; static const char ctrl_on[] = "on"; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", dev->power.runtime_auto ? ctrl_auto : ctrl_on); } static ssize_t control_store(struct device * dev, struct device_attribute *attr, const char * buf, size_t n) { device_lock(dev); if (sysfs_streq(buf, ctrl_auto)) pm_runtime_allow(dev); else if (sysfs_streq(buf, ctrl_on)) pm_runtime_forbid(dev); else n = -EINVAL; device_unlock(dev); return n; } static DEVICE_ATTR_RW(control); static ssize_t runtime_active_time_show(struct device *dev, struct device_attribute *attr, char *buf) { u64 tmp = pm_runtime_active_time(dev); do_div(tmp, NSEC_PER_MSEC); return sysfs_emit(buf, "%llu\n", tmp); } static DEVICE_ATTR_RO(runtime_active_time); static ssize_t runtime_suspended_time_show(struct device *dev, struct device_attribute *attr, char *buf) { u64 tmp = pm_runtime_suspended_time(dev); do_div(tmp, NSEC_PER_MSEC); return sysfs_emit(buf, "%llu\n", tmp); } static DEVICE_ATTR_RO(runtime_suspended_time); static ssize_t runtime_status_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *output; if (dev->power.runtime_error) { output = "error"; } else if (dev->power.disable_depth) { output = "unsupported"; } else { switch (dev->power.runtime_status) { case RPM_SUSPENDED: output = "suspended"; break; case RPM_SUSPENDING: output = "suspending"; break; case RPM_RESUMING: output = "resuming"; break; case RPM_ACTIVE: output = "active"; break; default: return -EIO; } } return sysfs_emit(buf, "%s\n", output); } static DEVICE_ATTR_RO(runtime_status); static ssize_t autosuspend_delay_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { if (!dev->power.use_autosuspend) return -EIO; return sysfs_emit(buf, "%d\n", dev->power.autosuspend_delay); } static ssize_t autosuspend_delay_ms_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { long delay; if (!dev->power.use_autosuspend) return -EIO; if (kstrtol(buf, 10, &delay) != 0 || delay != (int) delay) return -EINVAL; device_lock(dev); pm_runtime_set_autosuspend_delay(dev, delay); device_unlock(dev); return n; } static DEVICE_ATTR_RW(autosuspend_delay_ms); static ssize_t pm_qos_resume_latency_us_show(struct device *dev, struct device_attribute *attr, char *buf) { s32 value = dev_pm_qos_requested_resume_latency(dev); if (value == 0) return sysfs_emit(buf, "n/a\n"); if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) value = 0; return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_resume_latency_us_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { s32 value; int ret; if (!kstrtos32(buf, 0, &value)) { /* * Prevent users from writing negative or "no constraint" values * directly. */ if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) return -EINVAL; if (value == 0) value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } else if (sysfs_streq(buf, "n/a")) { value = 0; } else { return -EINVAL; } ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req, value); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_resume_latency_us); static ssize_t pm_qos_latency_tolerance_us_show(struct device *dev, struct device_attribute *attr, char *buf) { s32 value = dev_pm_qos_get_user_latency_tolerance(dev); if (value < 0) return sysfs_emit(buf, "%s\n", "auto"); if (value == PM_QOS_LATENCY_ANY) return sysfs_emit(buf, "%s\n", "any"); return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { s32 value; int ret; if (kstrtos32(buf, 0, &value) == 0) { /* Users can't write negative values directly */ if (value < 0) return -EINVAL; } else { if (sysfs_streq(buf, "auto")) value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (sysfs_streq(buf, "any")) value = PM_QOS_LATENCY_ANY; else return -EINVAL; } ret = dev_pm_qos_update_user_latency_tolerance(dev, value); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_latency_tolerance_us); static ssize_t pm_qos_no_power_off_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev) & PM_QOS_FLAG_NO_POWER_OFF)); } static ssize_t pm_qos_no_power_off_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { int ret; if (kstrtoint(buf, 0, &ret)) return -EINVAL; if (ret != 0 && ret != 1) return -EINVAL; ret = d |