| 5 2 6 6 6 6 1 5 5 5 2 3 5 3 3 3 2 2 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:net type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 Range as input support for IPv4 added */ /* 2 nomatch flag support added */ /* 3 Counters support added */ /* 4 Comments support added */ /* 5 Forceadd support added */ /* 6 skbinfo support added */ #define IPSET_TYPE_REV_MAX 7 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:net"); /* Type specific function prefix */ #define HTYPE hash_net #define IP_SET_HASH_WITH_NETS /* IPv4 variant */ /* Member elements */ struct hash_net4_elem { __be32 ip; u16 padding0; u8 nomatch; u8 cidr; }; /* Common functions */ static bool hash_net4_data_equal(const struct hash_net4_elem *ip1, const struct hash_net4_elem *ip2, u32 *multi) { return ip1->ip == ip2->ip && ip1->cidr == ip2->cidr; } static int hash_net4_do_data_match(const struct hash_net4_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_net4_data_set_flags(struct hash_net4_elem *elem, u32 flags) { elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH; } static void hash_net4_data_reset_flags(struct hash_net4_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_net4_data_netmask(struct hash_net4_elem *elem, u8 cidr) { elem->ip &= ip_set_netmask(cidr); elem->cidr = cidr; } static bool hash_net4_data_list(struct sk_buff *skb, const struct hash_net4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_net4_data_next(struct hash_net4_elem *next, const struct hash_net4_elem *d) { next->ip = d->ip; } #define MTYPE hash_net4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_net4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (e.cidr == 0) return -EINVAL; if (adt == IPSET_TEST) e.cidr = HOST_MASK; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); e.ip &= ip_set_netmask(e.cidr); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_net4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip = 0, ip_to = 0, i = 0; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { e.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!e.cidr || e.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } ip_to = ip; if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip_to < ip) swap(ip, ip_to); if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } if (retried) ip = ntohl(h->next.ip); do { i++; e.ip = htonl(ip); if (i > IPSET_MAX_RANGE) { hash_net4_data_next(&h->next, &e); return -ERANGE; } ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } while (ip++ < ip_to); return ret; } /* IPv6 variant */ struct hash_net6_elem { union nf_inet_addr ip; u16 padding0; u8 nomatch; u8 cidr; }; /* Common functions */ static bool hash_net6_data_equal(const struct hash_net6_elem *ip1, const struct hash_net6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->cidr == ip2->cidr; } static int hash_net6_do_data_match(const struct hash_net6_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_net6_data_set_flags(struct hash_net6_elem *elem, u32 flags) { elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH; } static void hash_net6_data_reset_flags(struct hash_net6_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_net6_data_netmask(struct hash_net6_elem *elem, u8 cidr) { ip6_netmask(&elem->ip, cidr); elem->cidr = cidr; } static bool hash_net6_data_list(struct sk_buff *skb, const struct hash_net6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_net6_data_next(struct hash_net6_elem *next, const struct hash_net6_elem *d) { } #undef MTYPE #undef HOST_MASK #define MTYPE hash_net6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_net6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net6_elem e = { .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (e.cidr == 0) return -EINVAL; if (adt == IPSET_TEST) e.cidr = HOST_MASK; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); ip6_netmask(&e.ip, e.cidr); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net6_elem e = { .cidr = HOST_MASK }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { e.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!e.cidr || e.cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } ip6_netmask(&e.ip, e.cidr); if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } static struct ip_set_type hash_net_type __read_mostly = { .name = "hash:net", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_net_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_net_init(void) { return ip_set_type_register(&hash_net_type); } static void __exit hash_net_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_net_type); } module_init(hash_net_init); module_exit(hash_net_fini); |
| 42 2 13 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> static void nft_fib_inet_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_fib *priv = nft_expr_priv(expr); switch (nft_pf(pkt)) { case NFPROTO_IPV4: switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: return nft_fib4_eval(expr, regs, pkt); case NFT_FIB_RESULT_ADDRTYPE: return nft_fib4_eval_type(expr, regs, pkt); } break; case NFPROTO_IPV6: switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: return nft_fib6_eval(expr, regs, pkt); case NFT_FIB_RESULT_ADDRTYPE: return nft_fib6_eval_type(expr, regs, pkt); } break; } regs->verdict.code = NF_DROP; } static struct nft_expr_type nft_fib_inet_type; static const struct nft_expr_ops nft_fib_inet_ops = { .type = &nft_fib_inet_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_fib)), .eval = nft_fib_inet_eval, .init = nft_fib_init, .dump = nft_fib_dump, .validate = nft_fib_validate, }; static struct nft_expr_type nft_fib_inet_type __read_mostly = { .family = NFPROTO_INET, .name = "fib", .ops = &nft_fib_inet_ops, .policy = nft_fib_policy, .maxattr = NFTA_FIB_MAX, .owner = THIS_MODULE, }; static int __init nft_fib_inet_module_init(void) { return nft_register_expr(&nft_fib_inet_type); } static void __exit nft_fib_inet_module_exit(void) { nft_unregister_expr(&nft_fib_inet_type); } module_init(nft_fib_inet_module_init); module_exit(nft_fib_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_ALIAS_NFT_AF_EXPR(1, "fib"); MODULE_DESCRIPTION("nftables fib inet support"); |
| 1105 1108 1110 5 5 1 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock - Credential hooks * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2024-2025 Microsoft Corporation */ #include <linux/binfmts.h> #include <linux/cred.h> #include <linux/lsm_hooks.h> #include "common.h" #include "cred.h" #include "ruleset.h" #include "setup.h" static void hook_cred_transfer(struct cred *const new, const struct cred *const old) { const struct landlock_cred_security *const old_llcred = landlock_cred(old); landlock_get_ruleset(old_llcred->domain); *landlock_cred(new) = *old_llcred; } static int hook_cred_prepare(struct cred *const new, const struct cred *const old, const gfp_t gfp) { hook_cred_transfer(new, old); return 0; } static void hook_cred_free(struct cred *const cred) { struct landlock_ruleset *const dom = landlock_cred(cred)->domain; if (dom) landlock_put_ruleset_deferred(dom); } #ifdef CONFIG_AUDIT static int hook_bprm_creds_for_exec(struct linux_binprm *const bprm) { /* Resets for each execution. */ landlock_cred(bprm->cred)->domain_exec = 0; return 0; } #endif /* CONFIG_AUDIT */ static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, hook_cred_prepare), LSM_HOOK_INIT(cred_transfer, hook_cred_transfer), LSM_HOOK_INIT(cred_free, hook_cred_free), #ifdef CONFIG_AUDIT LSM_HOOK_INIT(bprm_creds_for_exec, hook_bprm_creds_for_exec), #endif /* CONFIG_AUDIT */ }; __init void landlock_add_cred_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), &landlock_lsmid); } |
| 15 15 3 3 3 3 3 2 3 1 1 1 1 1 1 1 1 1 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 4 3 1 1 10 7 1 1 1 2 1 2 2 6 1 4 1 5 4 1 1 1 3 3 1 1 1 2 13 14 5 2 2 3 2 1 1 15 8 5 5 2 3 3 2 2 2 2 2 2 2 2 2 2 2 3 2 2 2 2 1 15 36 7 1 1 2 15 26 1 11 8 2 2 3 10 3 2 2 1 4 3 1 1 3 2 1 1 1 2 1 1 12 6 3 1 2 3 2 1 1 14 9 2 5 4 3 13 8 2 2 1 4 2 1 1 2 5 1 1 2 1 14 1 4 2 5 2 8 3 2 1 2 6 5 1 1 1 1 8 6 2 8 7 1 1 4 3 1 10 7 1 1 1 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright (c) 2017 Mellanox Technologies. All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include <linux/module.h> #include <linux/pid.h> #include <linux/pid_namespace.h> #include <linux/mutex.h> #include <net/netlink.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_netlink.h> #include <rdma/frmr_pools.h> #include "core_priv.h" #include "cma_priv.h" #include "restrack.h" #include "uverbs.h" #include "frmr_pools.h" /* * This determines whether a non-privileged user is allowed to specify a * controlled QKEY or not, when true non-privileged user is allowed to specify * a controlled QKEY. */ static bool privileged_qkey; static DEFINE_MUTEX(nldev_dellink_mutex); typedef int (*res_fill_func_t)(struct sk_buff*, bool, struct rdma_restrack_entry*, uint32_t); /* * Sort array elements by the netlink attribute name */ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = { [RDMA_NLDEV_ATTR_CHARDEV] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_CHARDEV_ABI] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_CHARDEV_NAME] = { .type = NLA_NUL_STRING, .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, [RDMA_NLDEV_ATTR_CHARDEV_TYPE] = { .type = NLA_NUL_STRING, .len = RDMA_NLDEV_ATTR_CHARDEV_TYPE_SIZE }, [RDMA_NLDEV_ATTR_DEV_DIM] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_DEV_INDEX] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, .len = IB_DEVICE_NAME_MAX }, [RDMA_NLDEV_ATTR_DEV_NODE_TYPE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_DEV_PROTOCOL] = { .type = NLA_NUL_STRING, .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, [RDMA_NLDEV_ATTR_DRIVER] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_DRIVER_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_DRIVER_PRINT_TYPE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_DRIVER_STRING] = { .type = NLA_NUL_STRING, .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, [RDMA_NLDEV_ATTR_DRIVER_S32] = { .type = NLA_S32 }, [RDMA_NLDEV_ATTR_DRIVER_S64] = { .type = NLA_S64 }, [RDMA_NLDEV_ATTR_DRIVER_U32] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_DRIVER_U64] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_FW_VERSION] = { .type = NLA_NUL_STRING, .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, [RDMA_NLDEV_ATTR_LID] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_LINK_TYPE] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ }, [RDMA_NLDEV_ATTR_LMC] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_NDEV_INDEX] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_NDEV_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ }, [RDMA_NLDEV_ATTR_NODE_GUID] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_PORT_INDEX] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_PORT_STATE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_RES_CM_ID] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_CM_IDN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_CQ] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_CQE] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_CQN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_CQ_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_CTX] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_CTXN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_CTX_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_DST_ADDR] = { .len = sizeof(struct __kernel_sockaddr_storage) }, [RDMA_NLDEV_ATTR_RES_IOVA] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_RES_KERN_NAME] = { .type = NLA_NUL_STRING, .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, [RDMA_NLDEV_ATTR_RES_LKEY] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_LQPN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_MR] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_MRLEN] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_RES_MRN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_MR_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_RES_PD] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_PDN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_PD_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_PID] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_POLL_CTX] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_RES_PS] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_QP] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_QP_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_RAW] = { .type = NLA_BINARY }, [RDMA_NLDEV_ATTR_RES_RKEY] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_RQPN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_RQ_PSN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_SQ_PSN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_SRC_ADDR] = { .len = sizeof(struct __kernel_sockaddr_storage) }, [RDMA_NLDEV_ATTR_RES_STATE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_RES_SUMMARY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR]= { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_NAME]= { .type = NLA_NUL_STRING, .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, [RDMA_NLDEV_ATTR_RES_TYPE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_RES_SUBTYPE] = { .type = NLA_NUL_STRING, .len = RDMA_NLDEV_ATTR_EMPTY_STRING }, [RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY]= { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_USECNT] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_RES_SRQ] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_RES_SRQN] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_RES_SRQ_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_MIN_RANGE] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_MAX_RANGE] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_SM_LID] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_SUBNET_PREFIX] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_STAT_MODE] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_STAT_RES] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_STAT_COUNTER] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_STAT_COUNTER_ID] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_STAT_HWCOUNTERS] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME] = { .type = NLA_NUL_STRING }, [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_UVERBS_DRIVER_ID] = { .type = NLA_U32 }, [RDMA_NLDEV_NET_NS_FD] = { .type = NLA_U32 }, [RDMA_NLDEV_SYS_ATTR_NETNS_MODE] = { .type = NLA_U8 }, [RDMA_NLDEV_SYS_ATTR_COPY_ON_FORK] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_INDEX] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_STAT_HWCOUNTER_DYNAMIC] = { .type = NLA_U8 }, [RDMA_NLDEV_SYS_ATTR_PRIVILEGED_QKEY_MODE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_DRIVER_DETAILS] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_DEV_TYPE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_PARENT_NAME] = { .type = NLA_NUL_STRING }, [RDMA_NLDEV_ATTR_NAME_ASSIGN_TYPE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_EVENT_TYPE] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_STAT_OPCOUNTER_ENABLED] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_FRMR_POOLS] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_FRMR_POOL_ENTRY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_FRMR_POOL_KEY] = { .type = NLA_NESTED }, [RDMA_NLDEV_ATTR_FRMR_POOL_KEY_ATS] = { .type = NLA_U8 }, [RDMA_NLDEV_ATTR_FRMR_POOL_KEY_ACCESS_FLAGS] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_FRMR_POOL_KEY_VENDOR_KEY] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_FRMR_POOL_KEY_NUM_DMA_BLOCKS] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_FRMR_POOL_QUEUE_HANDLES] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_FRMR_POOL_MAX_IN_USE] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_FRMR_POOL_IN_USE] = { .type = NLA_U64 }, [RDMA_NLDEV_ATTR_FRMR_POOLS_AGING_PERIOD] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_FRMR_POOL_PINNED_HANDLES] = { .type = NLA_U32 }, [RDMA_NLDEV_ATTR_FRMR_POOL_KEY_KERNEL_VENDOR_KEY] = { .type = NLA_U64 }, }; static int put_driver_name_print_type(struct sk_buff *msg, const char *name, enum rdma_nldev_print_type print_type) { if (nla_put_string(msg, RDMA_NLDEV_ATTR_DRIVER_STRING, name)) return -EMSGSIZE; if (print_type != RDMA_NLDEV_PRINT_TYPE_UNSPEC && nla_put_u8(msg, RDMA_NLDEV_ATTR_DRIVER_PRINT_TYPE, print_type)) return -EMSGSIZE; return 0; } static int _rdma_nl_put_driver_u32(struct sk_buff *msg, const char *name, enum rdma_nldev_print_type print_type, u32 value) { if (put_driver_name_print_type(msg, name, print_type)) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DRIVER_U32, value)) return -EMSGSIZE; return 0; } static int _rdma_nl_put_driver_u64(struct sk_buff *msg, const char *name, enum rdma_nldev_print_type print_type, u64 value) { if (put_driver_name_print_type(msg, name, print_type)) return -EMSGSIZE; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_DRIVER_U64, value, RDMA_NLDEV_ATTR_PAD)) return -EMSGSIZE; return 0; } int rdma_nl_put_driver_string(struct sk_buff *msg, const char *name, const char *str) { if (put_driver_name_print_type(msg, name, RDMA_NLDEV_PRINT_TYPE_UNSPEC)) return -EMSGSIZE; if (nla_put_string(msg, RDMA_NLDEV_ATTR_DRIVER_STRING, str)) return -EMSGSIZE; return 0; } EXPORT_SYMBOL(rdma_nl_put_driver_string); int rdma_nl_put_driver_u32(struct sk_buff *msg, const char *name, u32 value) { return _rdma_nl_put_driver_u32(msg, name, RDMA_NLDEV_PRINT_TYPE_UNSPEC, value); } EXPORT_SYMBOL(rdma_nl_put_driver_u32); int rdma_nl_put_driver_u32_hex(struct sk_buff *msg, const char *name, u32 value) { return _rdma_nl_put_driver_u32(msg, name, RDMA_NLDEV_PRINT_TYPE_HEX, value); } EXPORT_SYMBOL(rdma_nl_put_driver_u32_hex); int rdma_nl_put_driver_u64(struct sk_buff *msg, const char *name, u64 value) { return _rdma_nl_put_driver_u64(msg, name, RDMA_NLDEV_PRINT_TYPE_UNSPEC, value); } EXPORT_SYMBOL(rdma_nl_put_driver_u64); int rdma_nl_put_driver_u64_hex(struct sk_buff *msg, const char *name, u64 value) { return _rdma_nl_put_driver_u64(msg, name, RDMA_NLDEV_PRINT_TYPE_HEX, value); } EXPORT_SYMBOL(rdma_nl_put_driver_u64_hex); bool rdma_nl_get_privileged_qkey(void) { return privileged_qkey; } EXPORT_SYMBOL(rdma_nl_get_privileged_qkey); static int fill_nldev_handle(struct sk_buff *msg, struct ib_device *device) { if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index)) return -EMSGSIZE; if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, dev_name(&device->dev))) return -EMSGSIZE; return 0; } static int fill_dev_info(struct sk_buff *msg, struct ib_device *device) { char fw[IB_FW_VERSION_NAME_MAX]; int ret = 0; u32 port; if (fill_nldev_handle(msg, device)) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device))) return -EMSGSIZE; BUILD_BUG_ON(sizeof(device->attrs.device_cap_flags) != sizeof(u64)); if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS, device->attrs.device_cap_flags, RDMA_NLDEV_ATTR_PAD)) return -EMSGSIZE; ib_get_device_fw_str(device, fw); /* Device without FW has strlen(fw) = 0 */ if (strlen(fw) && nla_put_string(msg, RDMA_NLDEV_ATTR_FW_VERSION, fw)) return -EMSGSIZE; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_NODE_GUID, be64_to_cpu(device->node_guid), RDMA_NLDEV_ATTR_PAD)) return -EMSGSIZE; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SYS_IMAGE_GUID, be64_to_cpu(device->attrs.sys_image_guid), RDMA_NLDEV_ATTR_PAD)) return -EMSGSIZE; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_NODE_TYPE, device->node_type)) return -EMSGSIZE; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, device->use_cq_dim)) return -EMSGSIZE; if (device->type && nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_TYPE, device->type)) return -EMSGSIZE; if (device->parent && nla_put_string(msg, RDMA_NLDEV_ATTR_PARENT_NAME, dev_name(&device->parent->dev))) return -EMSGSIZE; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_NAME_ASSIGN_TYPE, device->name_assign_type)) return -EMSGSIZE; /* * Link type is determined on first port and mlx4 device * which can potentially have two different link type for the same * IB device is considered as better to be avoided in the future, */ port = rdma_start_port(device); if (rdma_cap_opa_mad(device, port)) ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "opa"); else if (rdma_protocol_ib(device, port)) ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "ib"); else if (rdma_protocol_iwarp(device, port)) ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "iw"); else if (rdma_protocol_roce(device, port)) ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "roce"); else if (rdma_protocol_usnic(device, port)) ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_PROTOCOL, "usnic"); return ret; } static int fill_port_info(struct sk_buff *msg, struct ib_device *device, u32 port, const struct net *net) { struct net_device *netdev = NULL; struct ib_port_attr attr; int ret; u64 cap_flags = 0; if (fill_nldev_handle(msg, device)) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) return -EMSGSIZE; ret = ib_query_port(device, port, &attr); if (ret) return ret; if (rdma_protocol_ib(device, port)) { BUILD_BUG_ON((sizeof(attr.port_cap_flags) + sizeof(attr.port_cap_flags2)) > sizeof(u64)); cap_flags = attr.port_cap_flags | ((u64)attr.port_cap_flags2 << 32); if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS, cap_flags, RDMA_NLDEV_ATTR_PAD)) return -EMSGSIZE; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SUBNET_PREFIX, attr.subnet_prefix, RDMA_NLDEV_ATTR_PAD)) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_LID, attr.lid)) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_SM_LID, attr.sm_lid)) return -EMSGSIZE; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_LMC, attr.lmc)) return -EMSGSIZE; } if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_STATE, attr.state)) return -EMSGSIZE; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_PHYS_STATE, attr.phys_state)) return -EMSGSIZE; netdev = ib_device_get_netdev(device, port); if (netdev && net_eq(dev_net(netdev), net)) { ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_NDEV_INDEX, netdev->ifindex); if (ret) goto out; ret = nla_put_string(msg, RDMA_NLDEV_ATTR_NDEV_NAME, netdev->name); } out: dev_put(netdev); return ret; } static int fill_res_info_entry(struct sk_buff *msg, const char *name, u64 curr) { struct nlattr *entry_attr; entry_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY); if (!entry_attr) return -EMSGSIZE; if (nla_put_string(msg, RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_NAME, name)) goto err; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_SUMMARY_ENTRY_CURR, curr, RDMA_NLDEV_ATTR_PAD)) goto err; nla_nest_end(msg, entry_attr); return 0; err: nla_nest_cancel(msg, entry_attr); return -EMSGSIZE; } static int fill_res_info(struct sk_buff *msg, struct ib_device *device, bool show_details) { static const char * const names[RDMA_RESTRACK_MAX] = { [RDMA_RESTRACK_PD] = "pd", [RDMA_RESTRACK_CQ] = "cq", [RDMA_RESTRACK_QP] = "qp", [RDMA_RESTRACK_CM_ID] = "cm_id", [RDMA_RESTRACK_MR] = "mr", [RDMA_RESTRACK_CTX] = "ctx", [RDMA_RESTRACK_SRQ] = "srq", }; struct nlattr *table_attr; int ret, i, curr; if (fill_nldev_handle(msg, device)) return -EMSGSIZE; table_attr = nla_nest_start_noflag(msg, RDMA_NLDEV_ATTR_RES_SUMMARY); if (!table_attr) return -EMSGSIZE; for (i = 0; i < RDMA_RESTRACK_MAX; i++) { if (!names[i]) continue; curr = rdma_restrack_count(device, i, show_details); ret = fill_res_info_entry(msg, names[i], curr); if (ret) goto err; } nla_nest_end(msg, table_attr); return 0; err: nla_nest_cancel(msg, table_attr); return ret; } static int fill_res_name_pid(struct sk_buff *msg, struct rdma_restrack_entry *res) { int err = 0; /* * For user resources, user is should read /proc/PID/comm to get the * name of the task file. */ if (rdma_is_kernel_res(res)) { err = nla_put_string(msg, RDMA_NLDEV_ATTR_RES_KERN_NAME, res->kern_name); } else { pid_t pid; pid = task_pid_vnr(res->task); /* * Task is dead and in zombie state. * There is no need to print PID anymore. */ if (pid) /* * This part is racy, task can be killed and PID will * be zero right here but it is ok, next query won't * return PID. We don't promise real-time reflection * of SW objects. */ err = nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PID, pid); } return err ? -EMSGSIZE : 0; } static int fill_res_qp_entry_query(struct sk_buff *msg, struct rdma_restrack_entry *res, struct ib_device *dev, struct ib_qp *qp) { struct ib_qp_init_attr qp_init_attr; struct ib_qp_attr qp_attr; int ret; ret = ib_query_qp(qp, &qp_attr, 0, &qp_init_attr); if (ret) return ret; if (qp->qp_type == IB_QPT_RC || qp->qp_type == IB_QPT_UC) { if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_RQPN, qp_attr.dest_qp_num)) goto err; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_RQ_PSN, qp_attr.rq_psn)) goto err; } if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_SQ_PSN, qp_attr.sq_psn)) goto err; if (qp->qp_type == IB_QPT_RC || qp->qp_type == IB_QPT_UC || qp->qp_type == IB_QPT_XRC_INI || qp->qp_type == IB_QPT_XRC_TGT) { if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_PATH_MIG_STATE, qp_attr.path_mig_state)) goto err; } if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, qp->qp_type)) goto err; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_STATE, qp_attr.qp_state)) goto err; if (dev->ops.fill_res_qp_entry) return dev->ops.fill_res_qp_entry(msg, qp); return 0; err: return -EMSGSIZE; } static int fill_res_qp_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_qp *qp = container_of(res, struct ib_qp, res); struct ib_device *dev = qp->device; int ret; if (port && port != qp->port) return -EAGAIN; /* In create_qp() port is not set yet */ if (qp->port && nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, qp->port)) return -EMSGSIZE; ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qp->qp_num); if (ret) return -EMSGSIZE; if (!rdma_is_kernel_res(res) && nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PDN, qp->pd->res.id)) return -EMSGSIZE; ret = fill_res_name_pid(msg, res); if (ret) return -EMSGSIZE; return fill_res_qp_entry_query(msg, res, dev, qp); } static int fill_res_qp_raw_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_qp *qp = container_of(res, struct ib_qp, res); struct ib_device *dev = qp->device; if (port && port != qp->port) return -EAGAIN; if (!dev->ops.fill_res_qp_entry_raw) return -EINVAL; return dev->ops.fill_res_qp_entry_raw(msg, qp); } static int fill_res_cm_id_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct rdma_id_private *id_priv = container_of(res, struct rdma_id_private, res); struct ib_device *dev = id_priv->id.device; struct rdma_cm_id *cm_id = &id_priv->id; if (port && port != cm_id->port_num) return -EAGAIN; if (cm_id->port_num && nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, cm_id->port_num)) goto err; if (id_priv->qp_num) { if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, id_priv->qp_num)) goto err; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, cm_id->qp_type)) goto err; } if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PS, cm_id->ps)) goto err; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_STATE, id_priv->state)) goto err; if (cm_id->route.addr.src_addr.ss_family && nla_put(msg, RDMA_NLDEV_ATTR_RES_SRC_ADDR, sizeof(cm_id->route.addr.src_addr), &cm_id->route.addr.src_addr)) goto err; if (cm_id->route.addr.dst_addr.ss_family && nla_put(msg, RDMA_NLDEV_ATTR_RES_DST_ADDR, sizeof(cm_id->route.addr.dst_addr), &cm_id->route.addr.dst_addr)) goto err; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CM_IDN, res->id)) goto err; if (fill_res_name_pid(msg, res)) goto err; if (dev->ops.fill_res_cm_id_entry) return dev->ops.fill_res_cm_id_entry(msg, cm_id); return 0; err: return -EMSGSIZE; } static int fill_res_cq_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_cq *cq = container_of(res, struct ib_cq, res); struct ib_device *dev = cq->device; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CQE, cq->cqe)) return -EMSGSIZE; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_USECNT, atomic_read(&cq->usecnt), RDMA_NLDEV_ATTR_PAD)) return -EMSGSIZE; /* Poll context is only valid for kernel CQs */ if (rdma_is_kernel_res(res) && nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_POLL_CTX, cq->poll_ctx)) return -EMSGSIZE; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, (cq->dim != NULL))) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CQN, res->id)) return -EMSGSIZE; if (!rdma_is_kernel_res(res) && nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CTXN, cq->uobject->uevent.uobject.context->res.id)) return -EMSGSIZE; if (fill_res_name_pid(msg, res)) return -EMSGSIZE; return (dev->ops.fill_res_cq_entry) ? dev->ops.fill_res_cq_entry(msg, cq) : 0; } static int fill_res_cq_raw_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_cq *cq = container_of(res, struct ib_cq, res); struct ib_device *dev = cq->device; if (!dev->ops.fill_res_cq_entry_raw) return -EINVAL; return dev->ops.fill_res_cq_entry_raw(msg, cq); } static int fill_res_mr_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_mr *mr = container_of(res, struct ib_mr, res); struct ib_device *dev = mr->pd->device; if (has_cap_net_admin) { if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_RKEY, mr->rkey)) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LKEY, mr->lkey)) return -EMSGSIZE; } if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_MRLEN, mr->length, RDMA_NLDEV_ATTR_PAD)) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_MRN, res->id)) return -EMSGSIZE; if (!rdma_is_kernel_res(res) && nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PDN, mr->pd->res.id)) return -EMSGSIZE; if (fill_res_name_pid(msg, res)) return -EMSGSIZE; return (dev->ops.fill_res_mr_entry) ? dev->ops.fill_res_mr_entry(msg, mr) : 0; } static int fill_res_mr_raw_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_mr *mr = container_of(res, struct ib_mr, res); struct ib_device *dev = mr->pd->device; if (!dev->ops.fill_res_mr_entry_raw) return -EINVAL; return dev->ops.fill_res_mr_entry_raw(msg, mr); } static int fill_res_pd_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_pd *pd = container_of(res, struct ib_pd, res); if (has_cap_net_admin) { if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LOCAL_DMA_LKEY, pd->local_dma_lkey)) goto err; if ((pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) && nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_UNSAFE_GLOBAL_RKEY, pd->unsafe_global_rkey)) goto err; } if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_USECNT, atomic_read(&pd->usecnt), RDMA_NLDEV_ATTR_PAD)) goto err; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PDN, res->id)) goto err; if (!rdma_is_kernel_res(res) && nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CTXN, pd->uobject->context->res.id)) goto err; return fill_res_name_pid(msg, res); err: return -EMSGSIZE; } static int fill_res_ctx_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_ucontext *ctx = container_of(res, struct ib_ucontext, res); if (rdma_is_kernel_res(res)) return 0; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CTXN, ctx->res.id)) return -EMSGSIZE; return fill_res_name_pid(msg, res); } static int fill_res_range_qp_entry(struct sk_buff *msg, uint32_t min_range, uint32_t max_range) { struct nlattr *entry_attr; if (!min_range) return 0; entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP_ENTRY); if (!entry_attr) return -EMSGSIZE; if (min_range == max_range) { if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, min_range)) goto err; } else { if (nla_put_u32(msg, RDMA_NLDEV_ATTR_MIN_RANGE, min_range)) goto err; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_MAX_RANGE, max_range)) goto err; } nla_nest_end(msg, entry_attr); return 0; err: nla_nest_cancel(msg, entry_attr); return -EMSGSIZE; } static int fill_res_srq_qps(struct sk_buff *msg, struct ib_srq *srq) { uint32_t min_range = 0, prev = 0; struct rdma_restrack_entry *res; struct rdma_restrack_root *rt; struct nlattr *table_attr; struct ib_qp *qp = NULL; unsigned long id = 0; table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP); if (!table_attr) return -EMSGSIZE; rt = &srq->device->res[RDMA_RESTRACK_QP]; xa_lock(&rt->xa); xa_for_each(&rt->xa, id, res) { if (!rdma_restrack_get(res)) continue; qp = container_of(res, struct ib_qp, res); if (!qp->srq || (qp->srq->res.id != srq->res.id)) { rdma_restrack_put(res); continue; } if (qp->qp_num < prev) /* qp_num should be ascending */ goto err_loop; if (min_range == 0) { min_range = qp->qp_num; } else if (qp->qp_num > (prev + 1)) { if (fill_res_range_qp_entry(msg, min_range, prev)) goto err_loop; min_range = qp->qp_num; } prev = qp->qp_num; rdma_restrack_put(res); } xa_unlock(&rt->xa); if (fill_res_range_qp_entry(msg, min_range, prev)) goto err; nla_nest_end(msg, table_attr); return 0; err_loop: rdma_restrack_put(res); xa_unlock(&rt->xa); err: nla_nest_cancel(msg, table_attr); return -EMSGSIZE; } static int fill_res_srq_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_srq *srq = container_of(res, struct ib_srq, res); struct ib_device *dev = srq->device; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_SRQN, srq->res.id)) goto err; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, srq->srq_type)) goto err; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_PDN, srq->pd->res.id)) goto err; if (ib_srq_has_cq(srq->srq_type)) { if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CQN, srq->ext.cq->res.id)) goto err; } if (fill_res_srq_qps(msg, srq)) goto err; if (fill_res_name_pid(msg, res)) goto err; if (dev->ops.fill_res_srq_entry) return dev->ops.fill_res_srq_entry(msg, srq); return 0; err: return -EMSGSIZE; } static int fill_res_srq_raw_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_srq *srq = container_of(res, struct ib_srq, res); struct ib_device *dev = srq->device; if (!dev->ops.fill_res_srq_entry_raw) return -EINVAL; return dev->ops.fill_res_srq_entry_raw(msg, srq); } static int fill_stat_counter_mode(struct sk_buff *msg, struct rdma_counter *counter) { struct rdma_counter_mode *m = &counter->mode; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, m->mode)) return -EMSGSIZE; if (m->mode == RDMA_COUNTER_MODE_AUTO) { if ((m->mask & RDMA_COUNTER_MASK_QP_TYPE) && nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_TYPE, m->param.qp_type)) return -EMSGSIZE; if ((m->mask & RDMA_COUNTER_MASK_PID) && fill_res_name_pid(msg, &counter->res)) return -EMSGSIZE; } return 0; } static int fill_stat_counter_qp_entry(struct sk_buff *msg, u32 qpn) { struct nlattr *entry_attr; entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP_ENTRY); if (!entry_attr) return -EMSGSIZE; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn)) goto err; nla_nest_end(msg, entry_attr); return 0; err: nla_nest_cancel(msg, entry_attr); return -EMSGSIZE; } static int fill_stat_counter_qps(struct sk_buff *msg, struct rdma_counter *counter) { struct rdma_restrack_entry *res; struct rdma_restrack_root *rt; struct nlattr *table_attr; struct ib_qp *qp = NULL; unsigned long id = 0; int ret = 0; table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_QP); if (!table_attr) return -EMSGSIZE; rt = &counter->device->res[RDMA_RESTRACK_QP]; xa_lock(&rt->xa); xa_for_each(&rt->xa, id, res) { qp = container_of(res, struct ib_qp, res); if (!qp->counter || (qp->counter->id != counter->id)) continue; ret = fill_stat_counter_qp_entry(msg, qp->qp_num); if (ret) goto err; } xa_unlock(&rt->xa); nla_nest_end(msg, table_attr); return 0; err: xa_unlock(&rt->xa); nla_nest_cancel(msg, table_attr); return ret; } int rdma_nl_stat_hwcounter_entry(struct sk_buff *msg, const char *name, u64 value) { struct nlattr *entry_attr; entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY); if (!entry_attr) return -EMSGSIZE; if (nla_put_string(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME, name)) goto err; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE, value, RDMA_NLDEV_ATTR_PAD)) goto err; nla_nest_end(msg, entry_attr); return 0; err: nla_nest_cancel(msg, entry_attr); return -EMSGSIZE; } EXPORT_SYMBOL(rdma_nl_stat_hwcounter_entry); static int fill_stat_mr_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct ib_mr *mr = container_of(res, struct ib_mr, res); struct ib_device *dev = mr->pd->device; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_MRN, res->id)) goto err; if (dev->ops.fill_stat_mr_entry) return dev->ops.fill_stat_mr_entry(msg, mr); return 0; err: return -EMSGSIZE; } static int fill_stat_counter_hwcounters(struct sk_buff *msg, struct rdma_counter *counter) { struct rdma_hw_stats *st = counter->stats; struct nlattr *table_attr; int i; table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS); if (!table_attr) return -EMSGSIZE; mutex_lock(&st->lock); for (i = 0; i < st->num_counters; i++) { if (test_bit(i, st->is_disabled)) continue; if (rdma_nl_stat_hwcounter_entry(msg, st->descs[i].name, st->value[i])) goto err; } mutex_unlock(&st->lock); nla_nest_end(msg, table_attr); return 0; err: mutex_unlock(&st->lock); nla_nest_cancel(msg, table_attr); return -EMSGSIZE; } static int fill_res_counter_entry(struct sk_buff *msg, bool has_cap_net_admin, struct rdma_restrack_entry *res, uint32_t port) { struct rdma_counter *counter = container_of(res, struct rdma_counter, res); if (port && port != counter->port) return -EAGAIN; /* Dump it even query failed */ rdma_counter_query_stats(counter); if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, counter->port) || nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, counter->id) || fill_stat_counter_mode(msg, counter) || fill_stat_counter_qps(msg, counter) || fill_stat_counter_hwcounters(msg, counter)) return -EMSGSIZE; return 0; } static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_device *device; struct sk_buff *msg; u32 index; int err; err = __nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, extack); if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOMEM; goto err; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET), 0, 0); if (!nlh) { err = -EMSGSIZE; goto err_free; } err = fill_dev_info(msg, device); if (err) goto err_free; nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_free: nlmsg_free(msg); err: ib_device_put(device); return err; } static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_device *device; u32 index; int err; err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; if (tb[RDMA_NLDEV_ATTR_DEV_NAME]) { char name[IB_DEVICE_NAME_MAX] = {}; nla_strscpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME], IB_DEVICE_NAME_MAX); if (strlen(name) == 0) { err = -EINVAL; goto done; } err = ib_device_rename(device, name); goto done; } if (tb[RDMA_NLDEV_NET_NS_FD]) { u32 ns_fd; ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]); err = ib_device_set_netns_put(skb, device, ns_fd); goto put_done; } if (tb[RDMA_NLDEV_ATTR_DEV_DIM]) { u8 use_dim; use_dim = nla_get_u8(tb[RDMA_NLDEV_ATTR_DEV_DIM]); err = ib_device_set_dim(device, use_dim); goto done; } done: ib_device_put(device); put_done: return err; } static int _nldev_get_dumpit(struct ib_device *device, struct sk_buff *skb, struct netlink_callback *cb, unsigned int idx) { int start = cb->args[0]; struct nlmsghdr *nlh; if (idx < start) return 0; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET), 0, NLM_F_MULTI); if (!nlh || fill_dev_info(skb, device)) { nlmsg_cancel(skb, nlh); goto out; } nlmsg_end(skb, nlh); idx++; out: cb->args[0] = idx; return skb->len; } static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { /* * There is no need to take lock, because * we are relying on ib_core's locking. */ return ib_enum_all_devs(_nldev_get_dumpit, skb, cb); } static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_device *device; struct sk_buff *msg; u32 index; u32 port; int err; err = __nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, extack); if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); if (!rdma_is_port_valid(device, port)) { err = -EINVAL; goto err; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOMEM; goto err; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET), 0, 0); if (!nlh) { err = -EMSGSIZE; goto err_free; } err = fill_port_info(msg, device, port, sock_net(skb->sk)); if (err) goto err_free; nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_free: nlmsg_free(msg); err: ib_device_put(device); return err; } static int nldev_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_device *device; int start = cb->args[0]; struct nlmsghdr *nlh; u32 idx = 0; u32 ifindex; int err; unsigned int p; err = __nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, NULL); if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) return -EINVAL; ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), ifindex); if (!device) return -EINVAL; rdma_for_each_port (device, p) { /* * The dumpit function returns all information from specific * index. This specific index is taken from the netlink * messages request sent by user and it is available * in cb->args[0]. * * Usually, the user doesn't fill this field and it causes * to return everything. * */ if (idx < start) { idx++; continue; } nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_PORT_GET), 0, NLM_F_MULTI); if (!nlh || fill_port_info(skb, device, p, sock_net(skb->sk))) { nlmsg_cancel(skb, nlh); goto out; } idx++; nlmsg_end(skb, nlh); } out: ib_device_put(device); cb->args[0] = idx; return skb->len; } static int nldev_res_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; bool show_details = false; struct ib_device *device; struct sk_buff *msg; u32 index; int ret; ret = __nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, extack); if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; if (tb[RDMA_NLDEV_ATTR_DRIVER_DETAILS]) show_details = nla_get_u8(tb[RDMA_NLDEV_ATTR_DRIVER_DETAILS]); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto err; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_RES_GET), 0, 0); if (!nlh) { ret = -EMSGSIZE; goto err_free; } ret = fill_res_info(msg, device, show_details); if (ret) goto err_free; nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_free: nlmsg_free(msg); err: ib_device_put(device); return ret; } static int _nldev_res_get_dumpit(struct ib_device *device, struct sk_buff *skb, struct netlink_callback *cb, unsigned int idx) { int start = cb->args[0]; struct nlmsghdr *nlh; if (idx < start) return 0; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_RES_GET), 0, NLM_F_MULTI); if (!nlh || fill_res_info(skb, device, false)) { nlmsg_cancel(skb, nlh); goto out; } nlmsg_end(skb, nlh); idx++; out: cb->args[0] = idx; return skb->len; } static int nldev_res_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return ib_enum_all_devs(_nldev_res_get_dumpit, skb, cb); } struct nldev_fill_res_entry { enum rdma_nldev_attr nldev_attr; u8 flags; u32 entry; u32 id; }; enum nldev_res_flags { NLDEV_PER_DEV = 1 << 0, }; static const struct nldev_fill_res_entry fill_entries[RDMA_RESTRACK_MAX] = { [RDMA_RESTRACK_QP] = { .nldev_attr = RDMA_NLDEV_ATTR_RES_QP, .entry = RDMA_NLDEV_ATTR_RES_QP_ENTRY, .id = RDMA_NLDEV_ATTR_RES_LQPN, }, [RDMA_RESTRACK_CM_ID] = { .nldev_attr = RDMA_NLDEV_ATTR_RES_CM_ID, .entry = RDMA_NLDEV_ATTR_RES_CM_ID_ENTRY, .id = RDMA_NLDEV_ATTR_RES_CM_IDN, }, [RDMA_RESTRACK_CQ] = { .nldev_attr = RDMA_NLDEV_ATTR_RES_CQ, .flags = NLDEV_PER_DEV, .entry = RDMA_NLDEV_ATTR_RES_CQ_ENTRY, .id = RDMA_NLDEV_ATTR_RES_CQN, }, [RDMA_RESTRACK_MR] = { .nldev_attr = RDMA_NLDEV_ATTR_RES_MR, .flags = NLDEV_PER_DEV, .entry = RDMA_NLDEV_ATTR_RES_MR_ENTRY, .id = RDMA_NLDEV_ATTR_RES_MRN, }, [RDMA_RESTRACK_PD] = { .nldev_attr = RDMA_NLDEV_ATTR_RES_PD, .flags = NLDEV_PER_DEV, .entry = RDMA_NLDEV_ATTR_RES_PD_ENTRY, .id = RDMA_NLDEV_ATTR_RES_PDN, }, [RDMA_RESTRACK_COUNTER] = { .nldev_attr = RDMA_NLDEV_ATTR_STAT_COUNTER, .entry = RDMA_NLDEV_ATTR_STAT_COUNTER_ENTRY, .id = RDMA_NLDEV_ATTR_STAT_COUNTER_ID, }, [RDMA_RESTRACK_CTX] = { .nldev_attr = RDMA_NLDEV_ATTR_RES_CTX, .flags = NLDEV_PER_DEV, .entry = RDMA_NLDEV_ATTR_RES_CTX_ENTRY, .id = RDMA_NLDEV_ATTR_RES_CTXN, }, [RDMA_RESTRACK_SRQ] = { .nldev_attr = RDMA_NLDEV_ATTR_RES_SRQ, .flags = NLDEV_PER_DEV, .entry = RDMA_NLDEV_ATTR_RES_SRQ_ENTRY, .id = RDMA_NLDEV_ATTR_RES_SRQN, }, }; static noinline_for_stack int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, enum rdma_restrack_type res_type, res_fill_func_t fill_func) { const struct nldev_fill_res_entry *fe = &fill_entries[res_type]; struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct rdma_restrack_entry *res; struct ib_device *device; u32 index, id, port = 0; bool has_cap_net_admin; struct sk_buff *msg; int ret; ret = __nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, extack); if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !fe->id || !tb[fe->id]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) { port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); if (!rdma_is_port_valid(device, port)) { ret = -EINVAL; goto err; } } if ((port && fe->flags & NLDEV_PER_DEV) || (!port && ~fe->flags & NLDEV_PER_DEV)) { ret = -EINVAL; goto err; } id = nla_get_u32(tb[fe->id]); res = rdma_restrack_get_byid(device, res_type, id); if (IS_ERR(res)) { ret = PTR_ERR(res); goto err; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto err_get; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NL_GET_OP(nlh->nlmsg_type)), 0, 0); if (!nlh || fill_nldev_handle(msg, device)) { ret = -EMSGSIZE; goto err_free; } has_cap_net_admin = netlink_capable(skb, CAP_NET_ADMIN); ret = fill_func(msg, has_cap_net_admin, res, port); if (ret) goto err_free; rdma_restrack_put(res); nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_free: nlmsg_free(msg); err_get: rdma_restrack_put(res); err: ib_device_put(device); return ret; } static int res_get_common_dumpit(struct sk_buff *skb, struct netlink_callback *cb, enum rdma_restrack_type res_type, res_fill_func_t fill_func) { const struct nldev_fill_res_entry *fe = &fill_entries[res_type]; struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct rdma_restrack_entry *res; struct rdma_restrack_root *rt; int err, ret = 0, idx = 0; bool show_details = false; struct nlattr *table_attr; struct nlattr *entry_attr; struct ib_device *device; int start = cb->args[0]; bool has_cap_net_admin; struct nlmsghdr *nlh; unsigned long id; u32 index, port = 0; bool filled = false; err = __nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, NULL); /* * Right now, we are expecting the device index to get res information, * but it is possible to extend this code to return all devices in * one shot by checking the existence of RDMA_NLDEV_ATTR_DEV_INDEX. * if it doesn't exist, we will iterate over all devices. * * But it is not needed for now. */ if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; if (tb[RDMA_NLDEV_ATTR_DRIVER_DETAILS]) show_details = nla_get_u8(tb[RDMA_NLDEV_ATTR_DRIVER_DETAILS]); /* * If no PORT_INDEX is supplied, we will return all QPs from that device */ if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) { port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); if (!rdma_is_port_valid(device, port)) { ret = -EINVAL; goto err_index; } } nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NL_GET_OP(cb->nlh->nlmsg_type)), 0, NLM_F_MULTI); if (!nlh || fill_nldev_handle(skb, device)) { ret = -EMSGSIZE; goto err; } table_attr = nla_nest_start_noflag(skb, fe->nldev_attr); if (!table_attr) { ret = -EMSGSIZE; goto err; } has_cap_net_admin = netlink_capable(cb->skb, CAP_NET_ADMIN); rt = &device->res[res_type]; xa_lock(&rt->xa); /* * FIXME: if the skip ahead is something common this loop should * use xas_for_each & xas_pause to optimize, we can have a lot of * objects. */ xa_for_each(&rt->xa, id, res) { if (xa_get_mark(&rt->xa, res->id, RESTRACK_DD) && !show_details) goto next; if (idx < start || !rdma_restrack_get(res)) goto next; xa_unlock(&rt->xa); filled = true; entry_attr = nla_nest_start_noflag(skb, fe->entry); if (!entry_attr) { ret = -EMSGSIZE; rdma_restrack_put(res); goto msg_full; } ret = fill_func(skb, has_cap_net_admin, res, port); rdma_restrack_put(res); if (ret) { nla_nest_cancel(skb, entry_attr); if (ret == -EMSGSIZE) goto msg_full; if (ret == -EAGAIN) goto again; goto res_err; } nla_nest_end(skb, entry_attr); again: xa_lock(&rt->xa); next: idx++; } xa_unlock(&rt->xa); msg_full: nla_nest_end(skb, table_attr); nlmsg_end(skb, nlh); cb->args[0] = idx; /* * No more entries to fill, cancel the message and * return 0 to mark end of dumpit. */ if (!filled) goto err; ib_device_put(device); return skb->len; res_err: nla_nest_cancel(skb, table_attr); err: nlmsg_cancel(skb, nlh); err_index: ib_device_put(device); return ret; } #define RES_GET_FUNCS(name, type) \ static int nldev_res_get_##name##_dumpit(struct sk_buff *skb, \ struct netlink_callback *cb) \ { \ return res_get_common_dumpit(skb, cb, type, \ fill_res_##name##_entry); \ } \ static int nldev_res_get_##name##_doit(struct sk_buff *skb, \ struct nlmsghdr *nlh, \ struct netlink_ext_ack *extack) \ { \ return res_get_common_doit(skb, nlh, extack, type, \ fill_res_##name##_entry); \ } RES_GET_FUNCS(qp, RDMA_RESTRACK_QP); RES_GET_FUNCS(qp_raw, RDMA_RESTRACK_QP); RES_GET_FUNCS(cm_id, RDMA_RESTRACK_CM_ID); RES_GET_FUNCS(cq, RDMA_RESTRACK_CQ); RES_GET_FUNCS(cq_raw, RDMA_RESTRACK_CQ); RES_GET_FUNCS(pd, RDMA_RESTRACK_PD); RES_GET_FUNCS(mr, RDMA_RESTRACK_MR); RES_GET_FUNCS(mr_raw, RDMA_RESTRACK_MR); RES_GET_FUNCS(counter, RDMA_RESTRACK_COUNTER); RES_GET_FUNCS(ctx, RDMA_RESTRACK_CTX); RES_GET_FUNCS(srq, RDMA_RESTRACK_SRQ); RES_GET_FUNCS(srq_raw, RDMA_RESTRACK_SRQ); static LIST_HEAD(link_ops); static DECLARE_RWSEM(link_ops_rwsem); static const struct rdma_link_ops *link_ops_get(const char *type) { const struct rdma_link_ops *ops; list_for_each_entry(ops, &link_ops, list) { if (!strcmp(ops->type, type)) goto out; } ops = NULL; out: return ops; } void rdma_link_register(struct rdma_link_ops *ops) { down_write(&link_ops_rwsem); if (WARN_ON_ONCE(link_ops_get(ops->type))) goto out; list_add(&ops->list, &link_ops); out: up_write(&link_ops_rwsem); } EXPORT_SYMBOL(rdma_link_register); void rdma_link_unregister(struct rdma_link_ops *ops) { down_write(&link_ops_rwsem); list_del(&ops->list); up_write(&link_ops_rwsem); } EXPORT_SYMBOL(rdma_link_unregister); static int nldev_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; char ibdev_name[IB_DEVICE_NAME_MAX]; const struct rdma_link_ops *ops; char ndev_name[IFNAMSIZ]; struct net_device *ndev; char type[IFNAMSIZ]; int err; err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (err || !tb[RDMA_NLDEV_ATTR_DEV_NAME] || !tb[RDMA_NLDEV_ATTR_LINK_TYPE] || !tb[RDMA_NLDEV_ATTR_NDEV_NAME]) return -EINVAL; nla_strscpy(ibdev_name, tb[RDMA_NLDEV_ATTR_DEV_NAME], sizeof(ibdev_name)); if (strchr(ibdev_name, '%') || strlen(ibdev_name) == 0) return -EINVAL; nla_strscpy(type, tb[RDMA_NLDEV_ATTR_LINK_TYPE], sizeof(type)); nla_strscpy(ndev_name, tb[RDMA_NLDEV_ATTR_NDEV_NAME], sizeof(ndev_name)); ndev = dev_get_by_name(sock_net(skb->sk), ndev_name); if (!ndev) return -ENODEV; down_read(&link_ops_rwsem); ops = link_ops_get(type); #ifdef CONFIG_MODULES if (!ops) { up_read(&link_ops_rwsem); request_module("rdma-link-%s", type); down_read(&link_ops_rwsem); ops = link_ops_get(type); } #endif err = ops ? ops->newlink(ibdev_name, ndev) : -EINVAL; up_read(&link_ops_rwsem); dev_put(ndev); return err; } static int nldev_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_device *device; u32 index; int err; err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; if (!(device->attrs.kernel_cap_flags & IBK_ALLOW_USER_UNREG)) { ib_device_put(device); return -EINVAL; } /* * This path is triggered by the 'rdma link delete' administrative command. * For Soft-RoCE (RXE), we ensure that transport sockets are closed here. * Note: iWARP driver does not implement .dellink, so this logic is * implicitly scoped to the driver supporting dynamic link deletion like RXE. */ if (device->link_ops && device->link_ops->dellink) { mutex_lock(&nldev_dellink_mutex); err = device->link_ops->dellink(device); mutex_unlock(&nldev_dellink_mutex); if (err) return err; } ib_unregister_device_and_put(device); return 0; } static int nldev_get_chardev(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; char client_name[RDMA_NLDEV_ATTR_CHARDEV_TYPE_SIZE]; struct ib_client_nl_info data = {}; struct ib_device *ibdev = NULL; struct sk_buff *msg; u32 index; int err; err = __nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, extack); if (err || !tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE]) return -EINVAL; nla_strscpy(client_name, tb[RDMA_NLDEV_ATTR_CHARDEV_TYPE], sizeof(client_name)); if (tb[RDMA_NLDEV_ATTR_DEV_INDEX]) { index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); ibdev = ib_device_get_by_index(sock_net(skb->sk), index); if (!ibdev) return -EINVAL; if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) { data.port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); if (!rdma_is_port_valid(ibdev, data.port)) { err = -EINVAL; goto out_put; } } else { data.port = -1; } } else if (tb[RDMA_NLDEV_ATTR_PORT_INDEX]) { return -EINVAL; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { err = -ENOMEM; goto out_put; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET_CHARDEV), 0, 0); if (!nlh) { err = -EMSGSIZE; goto out_nlmsg; } data.nl_msg = msg; err = ib_get_client_nl_info(ibdev, client_name, &data); if (err) goto out_nlmsg; err = nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CHARDEV, huge_encode_dev(data.cdev->devt), RDMA_NLDEV_ATTR_PAD); if (err) goto out_data; err = nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CHARDEV_ABI, data.abi, RDMA_NLDEV_ATTR_PAD); if (err) goto out_data; if (nla_put_string(msg, RDMA_NLDEV_ATTR_CHARDEV_NAME, dev_name(data.cdev))) { err = -EMSGSIZE; goto out_data; } nlmsg_end(msg, nlh); put_device(data.cdev); if (ibdev) ib_device_put(ibdev); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); out_data: put_device(data.cdev); out_nlmsg: nlmsg_free(msg); out_put: if (ibdev) ib_device_put(ibdev); return err; } static int nldev_sys_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct sk_buff *msg; int err; err = __nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, extack); if (err) return err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_SYS_GET), 0, 0); if (!nlh) { nlmsg_free(msg); return -EMSGSIZE; } err = nla_put_u8(msg, RDMA_NLDEV_SYS_ATTR_NETNS_MODE, (u8)ib_devices_shared_netns); if (err) { nlmsg_free(msg); return err; } err = nla_put_u8(msg, RDMA_NLDEV_SYS_ATTR_PRIVILEGED_QKEY_MODE, (u8)privileged_qkey); if (err) { nlmsg_free(msg); return err; } err = nla_put_u8(msg, RDMA_NLDEV_SYS_ATTR_MONITOR_MODE, 1); if (err) { nlmsg_free(msg); return err; } /* * Copy-on-fork is supported. * See commits: * 70e806e4e645 ("mm: Do early cow for pinned pages during fork() for ptes") * 4eae4efa2c29 ("hugetlb: do early cow when page pinned on src mm") * for more details. Don't backport this without them. * * Return value ignored on purpose, assume copy-on-fork is not * supported in case of failure. */ nla_put_u8(msg, RDMA_NLDEV_SYS_ATTR_COPY_ON_FORK, 1); nlmsg_end(msg, nlh); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); } static int nldev_set_sys_set_netns_doit(struct nlattr *tb[]) { u8 enable; int err; enable = nla_get_u8(tb[RDMA_NLDEV_SYS_ATTR_NETNS_MODE]); /* Only 0 and 1 are supported */ if (enable > 1) return -EINVAL; err = rdma_compatdev_set(enable); return err; } static int nldev_set_sys_set_pqkey_doit(struct nlattr *tb[]) { u8 enable; enable = nla_get_u8(tb[RDMA_NLDEV_SYS_ATTR_PRIVILEGED_QKEY_MODE]); /* Only 0 and 1 are supported */ if (enable > 1) return -EINVAL; privileged_qkey = enable; return 0; } static int nldev_set_sys_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; int err; err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (err) return -EINVAL; if (tb[RDMA_NLDEV_SYS_ATTR_NETNS_MODE]) return nldev_set_sys_set_netns_doit(tb); if (tb[RDMA_NLDEV_SYS_ATTR_PRIVILEGED_QKEY_MODE]) return nldev_set_sys_set_pqkey_doit(tb); return -EINVAL; } static int nldev_stat_set_mode_doit(struct sk_buff *msg, struct netlink_ext_ack *extack, struct nlattr *tb[], struct ib_device *device, u32 port) { u32 mode, mask = 0, qpn, cntn = 0; bool opcnt = false; int ret; /* Currently only counter for QP is supported */ if (!tb[RDMA_NLDEV_ATTR_STAT_RES] || nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP) return -EINVAL; if (tb[RDMA_NLDEV_ATTR_STAT_OPCOUNTER_ENABLED]) opcnt = !!nla_get_u8( tb[RDMA_NLDEV_ATTR_STAT_OPCOUNTER_ENABLED]); mode = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_MODE]); if (mode == RDMA_COUNTER_MODE_AUTO) { if (tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK]) mask = nla_get_u32( tb[RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK]); return rdma_counter_set_auto_mode(device, port, mask, opcnt, extack); } if (!tb[RDMA_NLDEV_ATTR_RES_LQPN]) return -EINVAL; qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]); if (tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]) { cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]); ret = rdma_counter_bind_qpn(device, port, qpn, cntn); if (ret) return ret; } else { ret = rdma_counter_bind_qpn_alloc(device, port, qpn, &cntn); if (ret) return ret; } if (nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn) || nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn)) { ret = -EMSGSIZE; goto err_fill; } return 0; err_fill: rdma_counter_unbind_qpn(device, port, qpn, cntn); return ret; } static int nldev_stat_set_counter_dynamic_doit(struct nlattr *tb[], struct ib_device *device, u32 port) { struct rdma_hw_stats *stats; struct nlattr *entry_attr; unsigned long *target; int rem, i, ret = 0; u32 index; stats = ib_get_hw_stats_port(device, port); if (!stats) return -EINVAL; target = kcalloc(BITS_TO_LONGS(stats->num_counters), sizeof(*stats->is_disabled), GFP_KERNEL); if (!target) return -ENOMEM; nla_for_each_nested(entry_attr, tb[RDMA_NLDEV_ATTR_STAT_HWCOUNTERS], rem) { index = nla_get_u32(entry_attr); if ((index >= stats->num_counters) || !(stats->descs[index].flags & IB_STAT_FLAG_OPTIONAL)) { ret = -EINVAL; goto out; } set_bit(index, target); } for (i = 0; i < stats->num_counters; i++) { if (!(stats->descs[i].flags & IB_STAT_FLAG_OPTIONAL)) continue; ret = rdma_counter_modify(device, port, i, test_bit(i, target)); if (ret) goto out; } out: kfree(target); return ret; } static int nldev_stat_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_device *device; struct sk_buff *msg; u32 index, port; int ret; ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); if (!rdma_is_port_valid(device, port)) { ret = -EINVAL; goto err_put_device; } if (!tb[RDMA_NLDEV_ATTR_STAT_MODE] && !tb[RDMA_NLDEV_ATTR_STAT_HWCOUNTERS]) { ret = -EINVAL; goto err_put_device; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto err_put_device; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_STAT_SET), 0, 0); if (!nlh || fill_nldev_handle(msg, device) || nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) { ret = -EMSGSIZE; goto err_free_msg; } if (tb[RDMA_NLDEV_ATTR_STAT_MODE]) { ret = nldev_stat_set_mode_doit(msg, extack, tb, device, port); if (ret) goto err_free_msg; } if (tb[RDMA_NLDEV_ATTR_STAT_HWCOUNTERS]) { ret = nldev_stat_set_counter_dynamic_doit(tb, device, port); if (ret) goto err_free_msg; } nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_free_msg: nlmsg_free(msg); err_put_device: ib_device_put(device); return ret; } static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_device *device; struct sk_buff *msg; u32 index, port, qpn, cntn; int ret; ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES] || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX] || !tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID] || !tb[RDMA_NLDEV_ATTR_RES_LQPN]) return -EINVAL; if (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES]) != RDMA_NLDEV_ATTR_RES_QP) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); if (!rdma_is_port_valid(device, port)) { ret = -EINVAL; goto err; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto err; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_STAT_SET), 0, 0); if (!nlh) { ret = -EMSGSIZE; goto err_fill; } cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]); qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]); if (fill_nldev_handle(msg, device) || nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) || nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn) || nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LQPN, qpn)) { ret = -EMSGSIZE; goto err_fill; } ret = rdma_counter_unbind_qpn(device, port, qpn, cntn); if (ret) goto err_fill; nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_fill: nlmsg_free(msg); err: ib_device_put(device); return ret; } static noinline_for_stack int stat_get_doit_default_counter(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct nlattr *tb[]) { struct rdma_hw_stats *stats; struct nlattr *table_attr; struct ib_device *device; int ret, num_cnts, i; struct sk_buff *msg; u32 index, port; u64 v; if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; if (!device->ops.alloc_hw_port_stats || !device->ops.get_hw_stats) { ret = -EINVAL; goto err; } port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); stats = ib_get_hw_stats_port(device, port); if (!stats) { ret = -EINVAL; goto err; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto err; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_STAT_GET), 0, 0); if (!nlh || fill_nldev_handle(msg, device) || nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) { ret = -EMSGSIZE; goto err_msg; } mutex_lock(&stats->lock); num_cnts = device->ops.get_hw_stats(device, stats, port, 0); if (num_cnts < 0) { ret = -EINVAL; goto err_stats; } table_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS); if (!table_attr) { ret = -EMSGSIZE; goto err_stats; } for (i = 0; i < num_cnts; i++) { if (test_bit(i, stats->is_disabled)) continue; v = stats->value[i] + rdma_counter_get_hwstat_value(device, port, i); if (rdma_nl_stat_hwcounter_entry(msg, stats->descs[i].name, v)) { ret = -EMSGSIZE; goto err_table; } } nla_nest_end(msg, table_attr); mutex_unlock(&stats->lock); nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_table: nla_nest_cancel(msg, table_attr); err_stats: mutex_unlock(&stats->lock); err_msg: nlmsg_free(msg); err: ib_device_put(device); return ret; } static noinline_for_stack int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct nlattr *tb[]) { static enum rdma_nl_counter_mode mode; static enum rdma_nl_counter_mask mask; struct ib_device *device; struct sk_buff *msg; u32 index, port; bool opcnt; int ret; if (tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]) return nldev_res_get_counter_doit(skb, nlh, extack); if (!tb[RDMA_NLDEV_ATTR_STAT_MODE] || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) return -EINVAL; index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), index); if (!device) return -EINVAL; port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); if (!rdma_is_port_valid(device, port)) { ret = -EINVAL; goto err; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto err; } nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_STAT_GET), 0, 0); if (!nlh) { ret = -EMSGSIZE; goto err_msg; } ret = rdma_counter_get_mode(device, port, &mode, &mask, &opcnt); if (ret) goto err_msg; if (fill_nldev_handle(msg, device) || nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) || nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode)) { ret = -EMSGSIZE; goto err_msg; } if ((mode == RDMA_COUNTER_MODE_AUTO) && nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask)) { ret = -EMSGSIZE; goto err_msg; } if ((mode == RDMA_COUNTER_MODE_AUTO) && nla_put_u8(msg, RDMA_NLDEV_ATTR_STAT_OPCOUNTER_ENABLED, opcnt)) { ret = -EMSGSIZE; goto err_msg; } nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_msg: nlmsg_free(msg); err: ib_device_put(device); return ret; } static int nldev_stat_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; int ret; ret = __nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, extack); if (ret) return -EINVAL; if (!tb[RDMA_NLDEV_ATTR_STAT_RES]) return stat_get_doit_default_counter(skb, nlh, extack, tb); switch (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES])) { case RDMA_NLDEV_ATTR_RES_QP: ret = stat_get_doit_qp(skb, nlh, extack, tb); break; case RDMA_NLDEV_ATTR_RES_MR: ret = res_get_common_doit(skb, nlh, extack, RDMA_RESTRACK_MR, fill_stat_mr_entry); break; default: ret = -EINVAL; break; } return ret; } static int nldev_stat_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; int ret; ret = __nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, NULL); if (ret || !tb[RDMA_NLDEV_ATTR_STAT_RES]) return -EINVAL; switch (nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_RES])) { case RDMA_NLDEV_ATTR_RES_QP: ret = nldev_res_get_counter_dumpit(skb, cb); break; case RDMA_NLDEV_ATTR_RES_MR: ret = res_get_common_dumpit(skb, cb, RDMA_RESTRACK_MR, fill_stat_mr_entry); break; default: ret = -EINVAL; break; } return ret; } static int nldev_stat_get_counter_status_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX], *table, *entry; struct rdma_hw_stats *stats; struct ib_device *device; struct sk_buff *msg; u32 devid, port; int ret, i; ret = __nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, extack); if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_PORT_INDEX]) return -EINVAL; devid = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), devid); if (!device) return -EINVAL; port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]); if (!rdma_is_port_valid(device, port)) { ret = -EINVAL; goto err; } stats = ib_get_hw_stats_port(device, port); if (!stats) { ret = -EINVAL; goto err; } msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; goto err; } nlh = nlmsg_put( msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_STAT_GET_STATUS), 0, 0); ret = -EMSGSIZE; if (!nlh || fill_nldev_handle(msg, device) || nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port)) goto err_msg; table = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTERS); if (!table) goto err_msg; mutex_lock(&stats->lock); for (i = 0; i < stats->num_counters; i++) { entry = nla_nest_start(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY); if (!entry) goto err_msg_table; if (nla_put_string(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME, stats->descs[i].name) || nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_INDEX, i)) goto err_msg_entry; if ((stats->descs[i].flags & IB_STAT_FLAG_OPTIONAL) && (nla_put_u8(msg, RDMA_NLDEV_ATTR_STAT_HWCOUNTER_DYNAMIC, !test_bit(i, stats->is_disabled)))) goto err_msg_entry; nla_nest_end(msg, entry); } mutex_unlock(&stats->lock); nla_nest_end(msg, table); nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); err_msg_entry: nla_nest_cancel(msg, entry); err_msg_table: mutex_unlock(&stats->lock); nla_nest_cancel(msg, table); err_msg: nlmsg_free(msg); err: ib_device_put(device); return ret; } static int nldev_newdev(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; enum rdma_nl_dev_type type; struct ib_device *parent; char name[IFNAMSIZ] = {}; u32 parentid; int ret; ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX] || !tb[RDMA_NLDEV_ATTR_DEV_NAME] || !tb[RDMA_NLDEV_ATTR_DEV_TYPE]) return -EINVAL; nla_strscpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME], sizeof(name)); type = nla_get_u8(tb[RDMA_NLDEV_ATTR_DEV_TYPE]); parentid = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); parent = ib_device_get_by_index(sock_net(skb->sk), parentid); if (!parent) return -EINVAL; ret = ib_add_sub_device(parent, type, name); ib_device_put(parent); return ret; } static int nldev_deldev(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_device *device; u32 devid; int ret; ret = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (ret || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) return -EINVAL; devid = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]); device = ib_device_get_by_index(sock_net(skb->sk), devid); if (!device) return -EINVAL; return ib_del_sub_device_and_put(device); } static int fill_frmr_pool_key(struct sk_buff *msg, struct ib_frmr_key *key) { struct nlattr *key_attr; key_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_FRMR_POOL_KEY); if (!key_attr) return -EMSGSIZE; if (nla_put_u8(msg, RDMA_NLDEV_ATTR_FRMR_POOL_KEY_ATS, key->ats)) goto err; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_FRMR_POOL_KEY_ACCESS_FLAGS, key->access_flags)) goto err; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_FRMR_POOL_KEY_VENDOR_KEY, key->vendor_key, RDMA_NLDEV_ATTR_PAD)) goto err; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_FRMR_POOL_KEY_NUM_DMA_BLOCKS, key->num_dma_blocks, RDMA_NLDEV_ATTR_PAD)) goto err; if (key->kernel_vendor_key && nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_FRMR_POOL_KEY_KERNEL_VENDOR_KEY, key->kernel_vendor_key, RDMA_NLDEV_ATTR_PAD)) goto err; nla_nest_end(msg, key_attr); return 0; err: return -EMSGSIZE; } static int fill_frmr_pool_entry(struct sk_buff *msg, struct ib_frmr_pool *pool) { if (fill_frmr_pool_key(msg, &pool->key)) return -EMSGSIZE; spin_lock(&pool->lock); if (nla_put_u32(msg, RDMA_NLDEV_ATTR_FRMR_POOL_QUEUE_HANDLES, pool->queue.ci + pool->inactive_queue.ci)) goto err_unlock; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_FRMR_POOL_MAX_IN_USE, pool->max_in_use, RDMA_NLDEV_ATTR_PAD)) goto err_unlock; if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_FRMR_POOL_IN_USE, pool->in_use, RDMA_NLDEV_ATTR_PAD)) goto err_unlock; if (nla_put_u32(msg, RDMA_NLDEV_ATTR_FRMR_POOL_PINNED_HANDLES, pool->pinned_handles)) goto err_unlock; spin_unlock(&pool->lock); return 0; err_unlock: spin_unlock(&pool->lock); return -EMSGSIZE; } static int nldev_frmr_pools_parse_key(struct nlattr *tb[], struct ib_frmr_key *key, struct netlink_ext_ack *extack) { if (tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_ATS]) key->ats = nla_get_u8(tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_ATS]); if (tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_ACCESS_FLAGS]) key->access_flags = nla_get_u32( tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_ACCESS_FLAGS]); if (tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_VENDOR_KEY]) key->vendor_key = nla_get_u64( tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_VENDOR_KEY]); if (tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_NUM_DMA_BLOCKS]) key->num_dma_blocks = nla_get_u64( tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_NUM_DMA_BLOCKS]); if (tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY_KERNEL_VENDOR_KEY]) return -EINVAL; return 0; } static int nldev_frmr_pools_set_pinned(struct ib_device *device, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct nlattr *key_tb[RDMA_NLDEV_ATTR_MAX]; struct ib_frmr_key key = { 0 }; u32 pinned_handles = 0; int err = 0; pinned_handles = nla_get_u32(tb[RDMA_NLDEV_ATTR_FRMR_POOL_PINNED_HANDLES]); if (!tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY]) return -EINVAL; err = nla_parse_nested(key_tb, RDMA_NLDEV_ATTR_MAX - 1, tb[RDMA_NLDEV_ATTR_FRMR_POOL_KEY], nldev_policy, extack); if (err) return err; err = nldev_frmr_pools_parse_key(key_tb, &key, extack); if (err) return err; err = ib_frmr_pools_set_pinned(device, &key, pinned_handles); return err; } static int nldev_frmr_pools_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *tb[RDMA_NLDEV_ATTR_MAX]; struct ib_frmr_pools *pools; int err, ret = 0, idx = 0; struct ib_frmr_pool *pool; struct nlattr *table_attr; struct nlattr *entry_attr; bool show_details = false; struct ib_device *device; int start = cb->args[0]; struct rb_node *node; struct nlmsghdr *nlh; bool filled = false; err = __nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, NL_VALIDATE_LIBERAL, NULL); if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX]) return -EINVAL; device = ib_device_get_by_index( sock_net(skb->sk), nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX])); if (!device) return -EINVAL; if (tb[RDMA_NLDEV_ATTR_DRIVER_DETAILS]) show_details = nla_get_u8(tb[RDMA_NLDEV_ATTR_DRIVER_DETAILS]); pools = device->frmr_pools; if (!pools) { ib_device_put(device); return 0; } nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_FRMR_POOLS_GET), 0, NLM_F_MULTI); if (!nlh || fill_nldev_handle(skb, device)) { ret = -EMSGSIZE; goto err; } table_attr = nla_nest_start_noflag(skb, RDMA_NLDEV_ATTR_FRMR_POOLS); if (!table_attr) { ret = -EMSGSIZE; goto err; } read_lock(&pools->rb_lock); for (node = rb_first(&pools->rb_root); node; node = rb_next(node)) { pool = rb_entry(node, struct ib_frmr_pool, node); if (pool->key.kernel_vendor_key && !show_details) continue; if (idx < start) { idx++; continue; } filled = true; entry_attr = nla_nest_start_noflag( skb, RDMA_NLDEV_ATTR_FRMR_POOL_ENTRY); if (!entry_attr) { ret = -EMSGSIZE; goto end_msg; } if (fill_frmr_pool_entry(skb, pool)) { nla_nest_cancel(skb, entry_attr); ret = -EMSGSIZE; goto end_msg; } nla_nest_end(skb, entry_attr); idx++; } end_msg: read_unlock(&pools->rb_lock); nla_nest_end(skb, table_attr); nlmsg_end(skb, nlh); cb->args[0] = idx; /* * No more entries to fill, cancel the message and * return 0 to mark end of dumpit. */ if (!filled) goto err; ib_device_put(device); return skb->len; err: nlmsg_cancel(skb, nlh); ib_device_put(device); return ret; } static int nldev_frmr_pools_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ib_device *device; struct nlattr **tb; u32 aging_period; int err; tb = kzalloc_objs(*tb, RDMA_NLDEV_ATTR_MAX, GFP_KERNEL); if (!tb) return -ENOMEM; err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1, nldev_policy, extack); if (err) goto free_tb; if (!tb[RDMA_NLDEV_ATTR_DEV_INDEX]) { err = -EINVAL; goto free_tb; } device = ib_device_get_by_index( sock_net(skb->sk), nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX])); if (!device) { err = -EINVAL; goto free_tb; } if (tb[RDMA_NLDEV_ATTR_FRMR_POOLS_AGING_PERIOD]) { aging_period = nla_get_u32( tb[RDMA_NLDEV_ATTR_FRMR_POOLS_AGING_PERIOD]); err = ib_frmr_pools_set_aging_period(device, aging_period); goto done; } if (tb[RDMA_NLDEV_ATTR_FRMR_POOL_PINNED_HANDLES]) err = nldev_frmr_pools_set_pinned(device, tb, extack); done: ib_device_put(device); free_tb: kfree(tb); return err; } static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { [RDMA_NLDEV_CMD_GET] = { .doit = nldev_get_doit, .dump = nldev_get_dumpit, }, [RDMA_NLDEV_CMD_GET_CHARDEV] = { .doit = nldev_get_chardev, }, [RDMA_NLDEV_CMD_SET] = { .doit = nldev_set_doit, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_NEWLINK] = { .doit = nldev_newlink, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_DELLINK] = { .doit = nldev_dellink, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_PORT_GET] = { .doit = nldev_port_get_doit, .dump = nldev_port_get_dumpit, }, [RDMA_NLDEV_CMD_RES_GET] = { .doit = nldev_res_get_doit, .dump = nldev_res_get_dumpit, }, [RDMA_NLDEV_CMD_RES_QP_GET] = { .doit = nldev_res_get_qp_doit, .dump = nldev_res_get_qp_dumpit, }, [RDMA_NLDEV_CMD_RES_CM_ID_GET] = { .doit = nldev_res_get_cm_id_doit, .dump = nldev_res_get_cm_id_dumpit, }, [RDMA_NLDEV_CMD_RES_CQ_GET] = { .doit = nldev_res_get_cq_doit, .dump = nldev_res_get_cq_dumpit, }, [RDMA_NLDEV_CMD_RES_MR_GET] = { .doit = nldev_res_get_mr_doit, .dump = nldev_res_get_mr_dumpit, }, [RDMA_NLDEV_CMD_RES_PD_GET] = { .doit = nldev_res_get_pd_doit, .dump = nldev_res_get_pd_dumpit, }, [RDMA_NLDEV_CMD_RES_CTX_GET] = { .doit = nldev_res_get_ctx_doit, .dump = nldev_res_get_ctx_dumpit, }, [RDMA_NLDEV_CMD_RES_SRQ_GET] = { .doit = nldev_res_get_srq_doit, .dump = nldev_res_get_srq_dumpit, }, [RDMA_NLDEV_CMD_SYS_GET] = { .doit = nldev_sys_get_doit, }, [RDMA_NLDEV_CMD_SYS_SET] = { .doit = nldev_set_sys_set_doit, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_STAT_SET] = { .doit = nldev_stat_set_doit, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_STAT_GET] = { .doit = nldev_stat_get_doit, .dump = nldev_stat_get_dumpit, }, [RDMA_NLDEV_CMD_STAT_DEL] = { .doit = nldev_stat_del_doit, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_RES_QP_GET_RAW] = { .doit = nldev_res_get_qp_raw_doit, .dump = nldev_res_get_qp_raw_dumpit, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_RES_CQ_GET_RAW] = { .doit = nldev_res_get_cq_raw_doit, .dump = nldev_res_get_cq_raw_dumpit, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_RES_MR_GET_RAW] = { .doit = nldev_res_get_mr_raw_doit, .dump = nldev_res_get_mr_raw_dumpit, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_RES_SRQ_GET_RAW] = { .doit = nldev_res_get_srq_raw_doit, .dump = nldev_res_get_srq_raw_dumpit, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_STAT_GET_STATUS] = { .doit = nldev_stat_get_counter_status_doit, }, [RDMA_NLDEV_CMD_NEWDEV] = { .doit = nldev_newdev, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_DELDEV] = { .doit = nldev_deldev, .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_FRMR_POOLS_GET] = { .dump = nldev_frmr_pools_get_dumpit, }, [RDMA_NLDEV_CMD_FRMR_POOLS_SET] = { .doit = nldev_frmr_pools_set_doit, .flags = RDMA_NL_ADMIN_PERM, }, }; static int fill_mon_netdev_rename(struct sk_buff *msg, struct ib_device *device, u32 port, const struct net *net) { struct net_device *netdev = ib_device_get_netdev(device, port); int ret = 0; if (!netdev || !net_eq(dev_net(netdev), net)) goto out; ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_NDEV_INDEX, netdev->ifindex); if (ret) goto out; ret = nla_put_string(msg, RDMA_NLDEV_ATTR_NDEV_NAME, netdev->name); out: dev_put(netdev); return ret; } static int fill_mon_netdev_association(struct sk_buff *msg, struct ib_device *device, u32 port, const struct net *net) { struct net_device *netdev = ib_device_get_netdev(device, port); int ret = 0; if (netdev && !net_eq(dev_net(netdev), net)) goto out; ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index); if (ret) goto out; ret = nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, dev_name(&device->dev)); if (ret) goto out; ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port); if (ret) goto out; if (netdev) { ret = nla_put_u32(msg, RDMA_NLDEV_ATTR_NDEV_INDEX, netdev->ifindex); if (ret) goto out; ret = nla_put_string(msg, RDMA_NLDEV_ATTR_NDEV_NAME, netdev->name); } out: dev_put(netdev); return ret; } static void rdma_nl_notify_err_msg(struct ib_device *device, u32 port_num, enum rdma_nl_notify_event_type type) { struct net_device *netdev; switch (type) { case RDMA_REGISTER_EVENT: dev_warn_ratelimited(&device->dev, "Failed to send RDMA monitor register device event\n"); break; case RDMA_UNREGISTER_EVENT: dev_warn_ratelimited(&device->dev, "Failed to send RDMA monitor unregister device event\n"); break; case RDMA_NETDEV_ATTACH_EVENT: netdev = ib_device_get_netdev(device, port_num); dev_warn_ratelimited(&device->dev, "Failed to send RDMA monitor netdev attach event: port %d netdev %d\n", port_num, netdev->ifindex); dev_put(netdev); break; case RDMA_NETDEV_DETACH_EVENT: dev_warn_ratelimited(&device->dev, "Failed to send RDMA monitor netdev detach event: port %d\n", port_num); break; case RDMA_RENAME_EVENT: dev_warn_ratelimited(&device->dev, "Failed to send RDMA monitor rename device event\n"); break; case RDMA_NETDEV_RENAME_EVENT: netdev = ib_device_get_netdev(device, port_num); dev_warn_ratelimited(&device->dev, "Failed to send RDMA monitor netdev rename event: port %d netdev %d\n", port_num, netdev->ifindex); dev_put(netdev); break; default: break; } } int rdma_nl_notify_event(struct ib_device *device, u32 port_num, enum rdma_nl_notify_event_type type) { struct sk_buff *skb; int ret = -EMSGSIZE; struct net *net; void *nlh; net = read_pnet(&device->coredev.rdma_net); if (!net) return -EINVAL; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; nlh = nlmsg_put(skb, 0, 0, RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_MONITOR), 0, 0); if (!nlh) goto err_free; switch (type) { case RDMA_REGISTER_EVENT: case RDMA_UNREGISTER_EVENT: case RDMA_RENAME_EVENT: ret = fill_nldev_handle(skb, device); if (ret) goto err_free; break; case RDMA_NETDEV_ATTACH_EVENT: case RDMA_NETDEV_DETACH_EVENT: ret = fill_mon_netdev_association(skb, device, port_num, net); if (ret) goto err_free; break; case RDMA_NETDEV_RENAME_EVENT: ret = fill_mon_netdev_rename(skb, device, port_num, net); if (ret) goto err_free; break; default: break; } ret = nla_put_u8(skb, RDMA_NLDEV_ATTR_EVENT_TYPE, type); if (ret) goto err_free; nlmsg_end(skb, nlh); ret = rdma_nl_multicast(net, skb, RDMA_NL_GROUP_NOTIFY, GFP_KERNEL); if (ret && ret != -ESRCH) { skb = NULL; /* skb is freed in the netlink send-op handling */ goto err_free; } return 0; err_free: rdma_nl_notify_err_msg(device, port_num, type); nlmsg_free(skb); return ret; } void __init nldev_init(void) { rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table); } void nldev_exit(void) { rdma_nl_unregister(RDMA_NL_NLDEV); } MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_NLDEV, 5); |
| 8 8 8 8 18 16 2 16 23 1 1 1 20 17 17 1 20 3 17 16 4 8 8 3 5 8 8 5 4 3 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/ext4/verity.c: fs-verity support for ext4 * * Copyright 2019 Google LLC */ /* * Implementation of fsverity_operations for ext4. * * ext4 stores the verity metadata (Merkle tree and fsverity_descriptor) past * the end of the file, starting at the first 64K boundary beyond i_size. This * approach works because (a) verity files are readonly, and (b) pages fully * beyond i_size aren't visible to userspace but can be read/written internally * by ext4 with only some relatively small changes to ext4. This approach * avoids having to depend on the EA_INODE feature and on rearchitecturing * ext4's xattr support to support paging multi-gigabyte xattrs into memory, and * to support encrypting xattrs. Note that the verity metadata *must* be * encrypted when the file is, since it contains hashes of the plaintext data. * * Using a 64K boundary rather than a 4K one keeps things ready for * architectures with 64K pages, and it doesn't necessarily waste space on-disk * since there can be a hole between i_size and the start of the Merkle tree. */ #include <linux/quotaops.h> #include "ext4.h" #include "ext4_extents.h" #include "ext4_jbd2.h" static inline loff_t ext4_verity_metadata_pos(const struct inode *inode) { return round_up(inode->i_size, 65536); } /* * Read some verity metadata from the inode. __vfs_read() can't be used because * we need to read beyond i_size. */ static int pagecache_read(struct inode *inode, void *buf, size_t count, loff_t pos) { while (count) { struct folio *folio; size_t n; folio = read_mapping_folio(inode->i_mapping, pos >> PAGE_SHIFT, NULL); if (IS_ERR(folio)) return PTR_ERR(folio); n = memcpy_from_file_folio(buf, folio, pos, count); folio_put(folio); buf += n; pos += n; count -= n; } return 0; } /* * Write some verity metadata to the inode for FS_IOC_ENABLE_VERITY. * kernel_write() can't be used because the file descriptor is readonly. */ static int pagecache_write(struct inode *inode, const void *buf, size_t count, loff_t pos) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; if (pos + count > inode->i_sb->s_maxbytes) return -EFBIG; while (count) { size_t n = min_t(size_t, count, PAGE_SIZE - offset_in_page(pos)); struct folio *folio; void *fsdata = NULL; int res; res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata); if (res) return res; memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n); res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata); if (res < 0) return res; if (res != n) return -EIO; buf += n; pos += n; count -= n; } return 0; } static int ext4_begin_enable_verity(struct file *filp) { struct inode *inode = file_inode(filp); const int credits = 2; /* superblock and inode for ext4_orphan_add() */ handle_t *handle; int err; if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX)) return -EINVAL; if (ext4_verity_in_progress(inode)) return -EBUSY; /* * Since the file was opened readonly, we have to initialize the jbd * inode and quotas here and not rely on ->open() doing it. This must * be done before evicting the inline data. */ err = ext4_inode_attach_jinode(inode); if (err) return err; err = dquot_initialize(inode); if (err) return err; err = ext4_convert_inline_data(inode); if (err) return err; if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { ext4_warning_inode(inode, "verity is only allowed on extent-based files"); return -EOPNOTSUPP; } /* * ext4 uses the last allocated block to find the verity descriptor, so * we must remove any other blocks past EOF which might confuse things. */ err = ext4_truncate(inode); if (err) return err; handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); err = ext4_orphan_add(handle, inode); if (err == 0) ext4_set_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); ext4_journal_stop(handle); return err; } /* * ext4 stores the verity descriptor beginning on the next filesystem block * boundary after the Merkle tree. Then, the descriptor size is stored in the * last 4 bytes of the last allocated filesystem block --- which is either the * block in which the descriptor ends, or the next block after that if there * weren't at least 4 bytes remaining. * * We can't simply store the descriptor in an xattr because it *must* be * encrypted when ext4 encryption is used, but ext4 encryption doesn't encrypt * xattrs. Also, if the descriptor includes a large signature blob it may be * too large to store in an xattr without the EA_INODE feature. */ static int ext4_write_verity_descriptor(struct inode *inode, const void *desc, size_t desc_size, u64 merkle_tree_size) { const u64 desc_pos = round_up(ext4_verity_metadata_pos(inode) + merkle_tree_size, i_blocksize(inode)); const u64 desc_end = desc_pos + desc_size; const __le32 desc_size_disk = cpu_to_le32(desc_size); const u64 desc_size_pos = round_up(desc_end + sizeof(desc_size_disk), i_blocksize(inode)) - sizeof(desc_size_disk); int err; err = pagecache_write(inode, desc, desc_size, desc_pos); if (err) return err; return pagecache_write(inode, &desc_size_disk, sizeof(desc_size_disk), desc_size_pos); } static int ext4_end_enable_verity(struct file *filp, const void *desc, size_t desc_size, u64 merkle_tree_size) { struct inode *inode = file_inode(filp); const int credits = 2; /* superblock and inode for ext4_orphan_del() */ handle_t *handle; struct ext4_iloc iloc; int err = 0; /* * If an error already occurred (which fs/verity/ signals by passing * desc == NULL), then only clean-up is needed. */ if (desc == NULL) goto cleanup; /* Append the verity descriptor. */ err = ext4_write_verity_descriptor(inode, desc, desc_size, merkle_tree_size); if (err) goto cleanup; /* * Write all pages (both data and verity metadata). Note that this must * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages * beyond i_size won't be written properly. For crash consistency, this * also must happen before the verity inode flag gets persisted. */ err = filemap_write_and_wait(inode->i_mapping); if (err) goto cleanup; /* * Finally, set the verity inode flag and remove the inode from the * orphan list (in a single transaction). */ handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto cleanup; } ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_VERITY, handle); err = ext4_orphan_del(handle, inode); if (err) goto stop_and_cleanup; err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto stop_and_cleanup; ext4_set_inode_flag(inode, EXT4_INODE_VERITY); ext4_set_inode_flags(inode, false); err = ext4_mark_iloc_dirty(handle, inode, &iloc); if (err) goto stop_and_cleanup; ext4_journal_stop(handle); ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); return 0; stop_and_cleanup: ext4_journal_stop(handle); cleanup: /* * Verity failed to be enabled, so clean up by truncating any verity * metadata that was written beyond i_size (both from cache and from * disk), removing the inode from the orphan list (if it wasn't done * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS. */ truncate_inode_pages(inode->i_mapping, inode->i_size); ext4_truncate(inode); ext4_orphan_del(NULL, inode); ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); return err; } static int ext4_get_verity_descriptor_location(struct inode *inode, size_t *desc_size_ret, u64 *desc_pos_ret) { struct ext4_ext_path *path; struct ext4_extent *last_extent; u32 end_lblk; u64 desc_size_pos; __le32 desc_size_disk; u32 desc_size; u64 desc_pos; int err; /* * Descriptor size is in last 4 bytes of last allocated block. * See ext4_write_verity_descriptor(). */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { EXT4_ERROR_INODE(inode, "verity file doesn't use extents"); return -EFSCORRUPTED; } path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0); if (IS_ERR(path)) return PTR_ERR(path); last_extent = path[path->p_depth].p_ext; if (!last_extent) { EXT4_ERROR_INODE(inode, "verity file has no extents"); ext4_free_ext_path(path); return -EFSCORRUPTED; } end_lblk = le32_to_cpu(last_extent->ee_block) + ext4_ext_get_actual_len(last_extent); desc_size_pos = EXT4_LBLK_TO_B(inode, end_lblk); ext4_free_ext_path(path); if (desc_size_pos < sizeof(desc_size_disk)) goto bad; desc_size_pos -= sizeof(desc_size_disk); err = pagecache_read(inode, &desc_size_disk, sizeof(desc_size_disk), desc_size_pos); if (err) return err; desc_size = le32_to_cpu(desc_size_disk); /* * The descriptor is stored just before the desc_size_disk, but starting * on a filesystem block boundary. */ if (desc_size > INT_MAX || desc_size > desc_size_pos) goto bad; desc_pos = round_down(desc_size_pos - desc_size, i_blocksize(inode)); if (desc_pos < ext4_verity_metadata_pos(inode)) goto bad; *desc_size_ret = desc_size; *desc_pos_ret = desc_pos; return 0; bad: EXT4_ERROR_INODE(inode, "verity file corrupted; can't find descriptor"); return -EFSCORRUPTED; } static int ext4_get_verity_descriptor(struct inode *inode, void *buf, size_t buf_size) { size_t desc_size = 0; u64 desc_pos = 0; int err; err = ext4_get_verity_descriptor_location(inode, &desc_size, &desc_pos); if (err) return err; if (buf_size) { if (desc_size > buf_size) return -ERANGE; err = pagecache_read(inode, buf, desc_size, desc_pos); if (err) return err; } return desc_size; } static struct page *ext4_read_merkle_tree_page(struct inode *inode, pgoff_t index) { index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; return generic_read_merkle_tree_page(inode, index); } static void ext4_readahead_merkle_tree(struct inode *inode, pgoff_t index, unsigned long nr_pages) { index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT; generic_readahead_merkle_tree(inode, index, nr_pages); } static int ext4_write_merkle_tree_block(struct file *file, const void *buf, u64 pos, unsigned int size) { pos += ext4_verity_metadata_pos(file_inode(file)); return pagecache_write(file_inode(file), buf, size, pos); } const struct fsverity_operations ext4_verityops = { .begin_enable_verity = ext4_begin_enable_verity, .end_enable_verity = ext4_end_enable_verity, .get_verity_descriptor = ext4_get_verity_descriptor, .read_merkle_tree_page = ext4_read_merkle_tree_page, .readahead_merkle_tree = ext4_readahead_merkle_tree, .write_merkle_tree_block = ext4_write_merkle_tree_block, }; |
| 431 68 96 2866 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/bitops.h> #include <asm/types.h> /** * DOC: __sw_hweightN - returns the hamming weight of a N-bit word * @w: the word to weigh * * The Hamming Weight of a number is the total number of bits set in it. */ unsigned int __sw_hweight32(unsigned int w) { #ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x55555555; w = (w & 0x33333333) + ((w >> 2) & 0x33333333); w = (w + (w >> 4)) & 0x0f0f0f0f; return (w * 0x01010101) >> 24; #else unsigned int res = w - ((w >> 1) & 0x55555555); res = (res & 0x33333333) + ((res >> 2) & 0x33333333); res = (res + (res >> 4)) & 0x0F0F0F0F; res = res + (res >> 8); return (res + (res >> 16)) & 0x000000FF; #endif } EXPORT_SYMBOL(__sw_hweight32); unsigned int __sw_hweight16(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x5555); res = (res & 0x3333) + ((res >> 2) & 0x3333); res = (res + (res >> 4)) & 0x0F0F; return (res + (res >> 8)) & 0x00FF; } EXPORT_SYMBOL(__sw_hweight16); unsigned int __sw_hweight8(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x55); res = (res & 0x33) + ((res >> 2) & 0x33); return (res + (res >> 4)) & 0x0F; } EXPORT_SYMBOL(__sw_hweight8); unsigned long __sw_hweight64(__u64 w) { #if BITS_PER_LONG == 32 return __sw_hweight32((unsigned int)(w >> 32)) + __sw_hweight32((unsigned int)w); #elif BITS_PER_LONG == 64 #ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x5555555555555555ul; w = (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul); w = (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful; return (w * 0x0101010101010101ul) >> 56; #else __u64 res = w - ((w >> 1) & 0x5555555555555555ul); res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul); res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful; res = res + (res >> 8); res = res + (res >> 16); return (res + (res >> 32)) & 0x00000000000000FFul; #endif #endif } EXPORT_SYMBOL(__sw_hweight64); |
| 41 41 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cache.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/pid_namespace.h> #include "internal.h" /* * /proc/thread_self: */ static const char *proc_thread_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; if (!pid) return ERR_PTR(-ENOENT); name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!name)) return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%u/task/%u", tgid, pid); set_delayed_call(done, kfree_link, name); return name; } static const struct inode_operations proc_thread_self_inode_operations = { .get_link = proc_thread_self_get_link, }; unsigned thread_self_inum __ro_after_init; int proc_setup_thread_self(struct super_block *s) { struct dentry *thread_self; int ret = -ENOMEM; thread_self = d_alloc_name(s->s_root, "thread-self"); if (thread_self) { struct inode *inode = new_inode(s); if (inode) { inode->i_ino = thread_self_inum; simple_inode_init_ts(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_thread_self_inode_operations; d_make_persistent(thread_self, inode); ret = 0; } dput(thread_self); } if (ret) pr_err("proc_fill_super: can't allocate /proc/thread-self\n"); return ret; } void __init proc_thread_self_init(void) { proc_alloc_inum(&thread_self_inum); } |
| 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/net/sunrpc/auth.c * * Generic RPC client authentication API. * * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de> */ #include <linux/types.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/hash.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/gss_api.h> #include <linux/spinlock.h> #include <trace/events/sunrpc.h> #define RPC_CREDCACHE_DEFAULT_HASHBITS (4) struct rpc_cred_cache { struct hlist_head *hashtable; unsigned int hashbits; spinlock_t lock; }; static unsigned int auth_hashbits = RPC_CREDCACHE_DEFAULT_HASHBITS; static const struct rpc_authops __rcu *auth_flavors[RPC_AUTH_MAXFLAVOR] = { [RPC_AUTH_NULL] = (const struct rpc_authops __force __rcu *)&authnull_ops, [RPC_AUTH_UNIX] = (const struct rpc_authops __force __rcu *)&authunix_ops, [RPC_AUTH_TLS] = (const struct rpc_authops __force __rcu *)&authtls_ops, }; static LIST_HEAD(cred_unused); static unsigned long number_cred_unused; static struct cred machine_cred = { .usage = ATOMIC_INIT(1), }; /* * Return the machine_cred pointer to be used whenever * the a generic machine credential is needed. */ const struct cred *rpc_machine_cred(void) { return &machine_cred; } EXPORT_SYMBOL_GPL(rpc_machine_cred); #define MAX_HASHTABLE_BITS (14) static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp) { unsigned long num; unsigned int nbits; int ret; if (!val) goto out_inval; ret = kstrtoul(val, 0, &num); if (ret) goto out_inval; nbits = fls(num - 1); if (nbits > MAX_HASHTABLE_BITS || nbits < 2) goto out_inval; *(unsigned int *)kp->arg = nbits; return 0; out_inval: return -EINVAL; } static int param_get_hashtbl_sz(char *buffer, const struct kernel_param *kp) { unsigned int nbits; nbits = *(unsigned int *)kp->arg; return sprintf(buffer, "%u\n", 1U << nbits); } #define param_check_hashtbl_sz(name, p) __param_check(name, p, unsigned int); static const struct kernel_param_ops param_ops_hashtbl_sz = { .set = param_set_hashtbl_sz, .get = param_get_hashtbl_sz, }; module_param_named(auth_hashtable_size, auth_hashbits, hashtbl_sz, 0644); MODULE_PARM_DESC(auth_hashtable_size, "RPC credential cache hashtable size"); static unsigned long auth_max_cred_cachesize = ULONG_MAX; module_param(auth_max_cred_cachesize, ulong, 0644); MODULE_PARM_DESC(auth_max_cred_cachesize, "RPC credential maximum total cache size"); static u32 pseudoflavor_to_flavor(u32 flavor) { if (flavor > RPC_AUTH_MAXFLAVOR) return RPC_AUTH_GSS; return flavor; } int rpcauth_register(const struct rpc_authops *ops) { const struct rpc_authops *old; rpc_authflavor_t flavor; if ((flavor = ops->au_flavor) >= RPC_AUTH_MAXFLAVOR) return -EINVAL; old = cmpxchg((const struct rpc_authops ** __force)&auth_flavors[flavor], NULL, ops); if (old == NULL || old == ops) return 0; return -EPERM; } EXPORT_SYMBOL_GPL(rpcauth_register); int rpcauth_unregister(const struct rpc_authops *ops) { const struct rpc_authops *old; rpc_authflavor_t flavor; if ((flavor = ops->au_flavor) >= RPC_AUTH_MAXFLAVOR) return -EINVAL; old = cmpxchg((const struct rpc_authops ** __force)&auth_flavors[flavor], ops, NULL); if (old == ops || old == NULL) return 0; return -EPERM; } EXPORT_SYMBOL_GPL(rpcauth_unregister); static const struct rpc_authops * rpcauth_get_authops(rpc_authflavor_t flavor) { const struct rpc_authops *ops; if (flavor >= RPC_AUTH_MAXFLAVOR) return NULL; rcu_read_lock(); ops = rcu_dereference(auth_flavors[flavor]); if (ops == NULL) { rcu_read_unlock(); request_module("rpc-auth-%u", flavor); rcu_read_lock(); ops = rcu_dereference(auth_flavors[flavor]); if (ops == NULL) goto out; } if (!try_module_get(ops->owner)) ops = NULL; out: rcu_read_unlock(); return ops; } static void rpcauth_put_authops(const struct rpc_authops *ops) { module_put(ops->owner); } /** * rpcauth_get_pseudoflavor - check if security flavor is supported * @flavor: a security flavor * @info: a GSS mech OID, quality of protection, and service value * * Verifies that an appropriate kernel module is available or already loaded. * Returns an equivalent pseudoflavor, or RPC_AUTH_MAXFLAVOR if "flavor" is * not supported locally. */ rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t flavor, struct rpcsec_gss_info *info) { const struct rpc_authops *ops = rpcauth_get_authops(flavor); rpc_authflavor_t pseudoflavor; if (!ops) return RPC_AUTH_MAXFLAVOR; pseudoflavor = flavor; if (ops->info2flavor != NULL) pseudoflavor = ops->info2flavor(info); rpcauth_put_authops(ops); return pseudoflavor; } EXPORT_SYMBOL_GPL(rpcauth_get_pseudoflavor); /** * rpcauth_get_gssinfo - find GSS tuple matching a GSS pseudoflavor * @pseudoflavor: GSS pseudoflavor to match * @info: rpcsec_gss_info structure to fill in * * Returns zero and fills in "info" if pseudoflavor matches a * supported mechanism. */ int rpcauth_get_gssinfo(rpc_authflavor_t pseudoflavor, struct rpcsec_gss_info *info) { rpc_authflavor_t flavor = pseudoflavor_to_flavor(pseudoflavor); const struct rpc_authops *ops; int result; ops = rpcauth_get_authops(flavor); if (ops == NULL) return -ENOENT; result = -ENOENT; if (ops->flavor2info != NULL) result = ops->flavor2info(pseudoflavor, info); rpcauth_put_authops(ops); return result; } EXPORT_SYMBOL_GPL(rpcauth_get_gssinfo); struct rpc_auth * rpcauth_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) { struct rpc_auth *auth = ERR_PTR(-EINVAL); const struct rpc_authops *ops; u32 flavor = pseudoflavor_to_flavor(args->pseudoflavor); ops = rpcauth_get_authops(flavor); if (ops == NULL) goto out; auth = ops->create(args, clnt); rpcauth_put_authops(ops); if (IS_ERR(auth)) return auth; if (clnt->cl_auth) rpcauth_release(clnt->cl_auth); clnt->cl_auth = auth; out: return auth; } EXPORT_SYMBOL_GPL(rpcauth_create); void rpcauth_release(struct rpc_auth *auth) { if (!refcount_dec_and_test(&auth->au_count)) return; auth->au_ops->destroy(auth); } static DEFINE_SPINLOCK(rpc_credcache_lock); /* * On success, the caller is responsible for freeing the reference * held by the hashtable */ static bool rpcauth_unhash_cred_locked(struct rpc_cred *cred) { if (!test_and_clear_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags)) return false; hlist_del_rcu(&cred->cr_hash); return true; } static bool rpcauth_unhash_cred(struct rpc_cred *cred) { spinlock_t *cache_lock; bool ret; if (!test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags)) return false; cache_lock = &cred->cr_auth->au_credcache->lock; spin_lock(cache_lock); ret = rpcauth_unhash_cred_locked(cred); spin_unlock(cache_lock); return ret; } /* * Initialize RPC credential cache */ int rpcauth_init_credcache(struct rpc_auth *auth) { struct rpc_cred_cache *new; unsigned int hashsize; new = kmalloc_obj(*new); if (!new) goto out_nocache; new->hashbits = auth_hashbits; hashsize = 1U << new->hashbits; new->hashtable = kzalloc_objs(new->hashtable[0], hashsize); if (!new->hashtable) goto out_nohashtbl; spin_lock_init(&new->lock); auth->au_credcache = new; return 0; out_nohashtbl: kfree(new); out_nocache: return -ENOMEM; } EXPORT_SYMBOL_GPL(rpcauth_init_credcache); char * rpcauth_stringify_acceptor(struct rpc_cred *cred) { if (!cred->cr_ops->crstringify_acceptor) return NULL; return cred->cr_ops->crstringify_acceptor(cred); } EXPORT_SYMBOL_GPL(rpcauth_stringify_acceptor); /* * Destroy a list of credentials */ static inline void rpcauth_destroy_credlist(struct list_head *head) { struct rpc_cred *cred; while (!list_empty(head)) { cred = list_entry(head->next, struct rpc_cred, cr_lru); list_del_init(&cred->cr_lru); put_rpccred(cred); } } static void rpcauth_lru_add_locked(struct rpc_cred *cred) { if (!list_empty(&cred->cr_lru)) return; number_cred_unused++; list_add_tail(&cred->cr_lru, &cred_unused); } static void rpcauth_lru_add(struct rpc_cred *cred) { if (!list_empty(&cred->cr_lru)) return; spin_lock(&rpc_credcache_lock); rpcauth_lru_add_locked(cred); spin_unlock(&rpc_credcache_lock); } static void rpcauth_lru_remove_locked(struct rpc_cred *cred) { if (list_empty(&cred->cr_lru)) return; number_cred_unused--; list_del_init(&cred->cr_lru); } static void rpcauth_lru_remove(struct rpc_cred *cred) { if (list_empty(&cred->cr_lru)) return; spin_lock(&rpc_credcache_lock); rpcauth_lru_remove_locked(cred); spin_unlock(&rpc_credcache_lock); } /* * Clear the RPC credential cache, and delete those credentials * that are not referenced. */ void rpcauth_clear_credcache(struct rpc_cred_cache *cache) { LIST_HEAD(free); struct hlist_head *head; struct rpc_cred *cred; unsigned int hashsize = 1U << cache->hashbits; int i; spin_lock(&rpc_credcache_lock); spin_lock(&cache->lock); for (i = 0; i < hashsize; i++) { head = &cache->hashtable[i]; while (!hlist_empty(head)) { cred = hlist_entry(head->first, struct rpc_cred, cr_hash); rpcauth_unhash_cred_locked(cred); /* Note: We now hold a reference to cred */ rpcauth_lru_remove_locked(cred); list_add_tail(&cred->cr_lru, &free); } } spin_unlock(&cache->lock); spin_unlock(&rpc_credcache_lock); rpcauth_destroy_credlist(&free); } /* * Destroy the RPC credential cache */ void rpcauth_destroy_credcache(struct rpc_auth *auth) { struct rpc_cred_cache *cache = auth->au_credcache; if (cache) { auth->au_credcache = NULL; rpcauth_clear_credcache(cache); kfree(cache->hashtable); kfree(cache); } } EXPORT_SYMBOL_GPL(rpcauth_destroy_credcache); #define RPC_AUTH_EXPIRY_MORATORIUM (60 * HZ) /* * Remove stale credentials. Avoid sleeping inside the loop. */ static long rpcauth_prune_expired(struct list_head *free, int nr_to_scan) { struct rpc_cred *cred, *next; unsigned long expired = jiffies - RPC_AUTH_EXPIRY_MORATORIUM; long freed = 0; list_for_each_entry_safe(cred, next, &cred_unused, cr_lru) { if (nr_to_scan-- == 0) break; if (refcount_read(&cred->cr_count) > 1) { rpcauth_lru_remove_locked(cred); continue; } /* * Enforce a 60 second garbage collection moratorium * Note that the cred_unused list must be time-ordered. */ if (time_in_range(cred->cr_expire, expired, jiffies)) continue; if (!rpcauth_unhash_cred(cred)) continue; rpcauth_lru_remove_locked(cred); freed++; list_add_tail(&cred->cr_lru, free); } return freed ? freed : SHRINK_STOP; } static unsigned long rpcauth_cache_do_shrink(int nr_to_scan) { LIST_HEAD(free); unsigned long freed; spin_lock(&rpc_credcache_lock); freed = rpcauth_prune_expired(&free, nr_to_scan); spin_unlock(&rpc_credcache_lock); rpcauth_destroy_credlist(&free); return freed; } /* * Run memory cache shrinker. */ static unsigned long rpcauth_cache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { if ((sc->gfp_mask & GFP_KERNEL) != GFP_KERNEL) return SHRINK_STOP; /* nothing left, don't come back */ if (list_empty(&cred_unused)) return SHRINK_STOP; return rpcauth_cache_do_shrink(sc->nr_to_scan); } static unsigned long rpcauth_cache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { return number_cred_unused; } static void rpcauth_cache_enforce_limit(void) { unsigned long diff; unsigned int nr_to_scan; if (number_cred_unused <= auth_max_cred_cachesize) return; diff = number_cred_unused - auth_max_cred_cachesize; nr_to_scan = 100; if (diff < nr_to_scan) nr_to_scan = diff; rpcauth_cache_do_shrink(nr_to_scan); } /* * Look up a process' credentials in the authentication cache */ struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, int flags, gfp_t gfp) { LIST_HEAD(free); struct rpc_cred_cache *cache = auth->au_credcache; struct rpc_cred *cred = NULL, *entry, *new; unsigned int nr; nr = auth->au_ops->hash_cred(acred, cache->hashbits); rcu_read_lock(); hlist_for_each_entry_rcu(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; cred = get_rpccred(entry); if (cred) break; } rcu_read_unlock(); if (cred != NULL) goto found; new = auth->au_ops->crcreate(auth, acred, flags, gfp); if (IS_ERR(new)) { cred = new; goto out; } spin_lock(&cache->lock); hlist_for_each_entry(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; cred = get_rpccred(entry); if (cred) break; } if (cred == NULL) { cred = new; set_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags); refcount_inc(&cred->cr_count); hlist_add_head_rcu(&cred->cr_hash, &cache->hashtable[nr]); } else list_add_tail(&new->cr_lru, &free); spin_unlock(&cache->lock); rpcauth_cache_enforce_limit(); found: if (test_bit(RPCAUTH_CRED_NEW, &cred->cr_flags) && cred->cr_ops->cr_init != NULL && !(flags & RPCAUTH_LOOKUP_NEW)) { int res = cred->cr_ops->cr_init(auth, cred); if (res < 0) { put_rpccred(cred); cred = ERR_PTR(res); } } rpcauth_destroy_credlist(&free); out: return cred; } EXPORT_SYMBOL_GPL(rpcauth_lookup_credcache); struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *auth, int flags) { struct auth_cred acred; struct rpc_cred *ret; const struct cred *cred = current_cred(); memset(&acred, 0, sizeof(acred)); acred.cred = cred; ret = auth->au_ops->lookup_cred(auth, &acred, flags); return ret; } EXPORT_SYMBOL_GPL(rpcauth_lookupcred); void rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred, struct rpc_auth *auth, const struct rpc_credops *ops) { INIT_HLIST_NODE(&cred->cr_hash); INIT_LIST_HEAD(&cred->cr_lru); refcount_set(&cred->cr_count, 1); cred->cr_auth = auth; cred->cr_flags = 0; cred->cr_ops = ops; cred->cr_expire = jiffies; cred->cr_cred = get_cred(acred->cred); } EXPORT_SYMBOL_GPL(rpcauth_init_cred); static struct rpc_cred * rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { .cred = get_task_cred(&init_task), }; struct rpc_cred *ret; if (RPC_IS_ASYNC(task)) lookupflags |= RPCAUTH_LOOKUP_ASYNC; ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags); put_cred(acred.cred); return ret; } static struct rpc_cred * rpcauth_bind_machine_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { .principal = task->tk_client->cl_principal, .cred = init_task.cred, }; if (!acred.principal) return NULL; if (RPC_IS_ASYNC(task)) lookupflags |= RPCAUTH_LOOKUP_ASYNC; return auth->au_ops->lookup_cred(auth, &acred, lookupflags); } static struct rpc_cred * rpcauth_bind_new_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; return rpcauth_lookupcred(auth, lookupflags); } static int rpcauth_bindcred(struct rpc_task *task, const struct cred *cred, int flags) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_cred *new = NULL; int lookupflags = 0; struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { .cred = cred, }; if (flags & RPC_TASK_ASYNC) lookupflags |= RPCAUTH_LOOKUP_NEW | RPCAUTH_LOOKUP_ASYNC; if (task->tk_op_cred) /* Task must use exactly this rpc_cred */ new = get_rpccred(task->tk_op_cred); else if (cred != NULL && cred != &machine_cred) new = auth->au_ops->lookup_cred(auth, &acred, lookupflags); else if (cred == &machine_cred) new = rpcauth_bind_machine_cred(task, lookupflags); /* If machine cred couldn't be bound, try a root cred */ if (new) ; else if (cred == &machine_cred) new = rpcauth_bind_root_cred(task, lookupflags); else if (flags & RPC_TASK_NULLCREDS) new = authnull_ops.lookup_cred(NULL, NULL, 0); else new = rpcauth_bind_new_cred(task, lookupflags); if (IS_ERR(new)) return PTR_ERR(new); put_rpccred(req->rq_cred); req->rq_cred = new; return 0; } void put_rpccred(struct rpc_cred *cred) { if (cred == NULL) return; rcu_read_lock(); if (refcount_dec_and_test(&cred->cr_count)) goto destroy; if (refcount_read(&cred->cr_count) != 1 || !test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags)) goto out; if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0) { cred->cr_expire = jiffies; rpcauth_lru_add(cred); /* Race breaker */ if (unlikely(!test_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags))) rpcauth_lru_remove(cred); } else if (rpcauth_unhash_cred(cred)) { rpcauth_lru_remove(cred); if (refcount_dec_and_test(&cred->cr_count)) goto destroy; } out: rcu_read_unlock(); return; destroy: rcu_read_unlock(); cred->cr_ops->crdestroy(cred); } EXPORT_SYMBOL_GPL(put_rpccred); /** * rpcauth_marshcred - Append RPC credential to end of @xdr * @task: controlling RPC task * @xdr: xdr_stream containing initial portion of RPC Call header * * On success, an appropriate verifier is added to @xdr, @xdr is * updated to point past the verifier, and zero is returned. * Otherwise, @xdr is in an undefined state and a negative errno * is returned. */ int rpcauth_marshcred(struct rpc_task *task, struct xdr_stream *xdr) { const struct rpc_credops *ops = task->tk_rqstp->rq_cred->cr_ops; return ops->crmarshal(task, xdr); } /** * rpcauth_wrap_req_encode - XDR encode the RPC procedure * @task: controlling RPC task * @xdr: stream where on-the-wire bytes are to be marshalled * * On success, @xdr contains the encoded and wrapped message. * Otherwise, @xdr is in an undefined state. */ int rpcauth_wrap_req_encode(struct rpc_task *task, struct xdr_stream *xdr) { kxdreproc_t encode = task->tk_msg.rpc_proc->p_encode; encode(task->tk_rqstp, xdr, task->tk_msg.rpc_argp); return 0; } EXPORT_SYMBOL_GPL(rpcauth_wrap_req_encode); /** * rpcauth_wrap_req - XDR encode and wrap the RPC procedure * @task: controlling RPC task * @xdr: stream where on-the-wire bytes are to be marshalled * * On success, @xdr contains the encoded and wrapped message, * and zero is returned. Otherwise, @xdr is in an undefined * state and a negative errno is returned. */ int rpcauth_wrap_req(struct rpc_task *task, struct xdr_stream *xdr) { const struct rpc_credops *ops = task->tk_rqstp->rq_cred->cr_ops; return ops->crwrap_req(task, xdr); } /** * rpcauth_checkverf - Validate verifier in RPC Reply header * @task: controlling RPC task * @xdr: xdr_stream containing RPC Reply header * * Return values: * %0: Verifier is valid. @xdr now points past the verifier. * %-EIO: Verifier is corrupted or message ended early. * %-EACCES: Verifier is intact but not valid. * %-EPROTONOSUPPORT: Server does not support the requested auth type. * * When a negative errno is returned, @xdr is left in an undefined * state. */ int rpcauth_checkverf(struct rpc_task *task, struct xdr_stream *xdr) { const struct rpc_credops *ops = task->tk_rqstp->rq_cred->cr_ops; return ops->crvalidate(task, xdr); } /** * rpcauth_unwrap_resp_decode - Invoke XDR decode function * @task: controlling RPC task * @xdr: stream where the Reply message resides * * Returns zero on success; otherwise a negative errno is returned. */ int rpcauth_unwrap_resp_decode(struct rpc_task *task, struct xdr_stream *xdr) { kxdrdproc_t decode = task->tk_msg.rpc_proc->p_decode; return decode(task->tk_rqstp, xdr, task->tk_msg.rpc_resp); } EXPORT_SYMBOL_GPL(rpcauth_unwrap_resp_decode); /** * rpcauth_unwrap_resp - Invoke unwrap and decode function for the cred * @task: controlling RPC task * @xdr: stream where the Reply message resides * * Returns zero on success; otherwise a negative errno is returned. */ int rpcauth_unwrap_resp(struct rpc_task *task, struct xdr_stream *xdr) { const struct rpc_credops *ops = task->tk_rqstp->rq_cred->cr_ops; return ops->crunwrap_resp(task, xdr); } bool rpcauth_xmit_need_reencode(struct rpc_task *task) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; if (!cred || !cred->cr_ops->crneed_reencode) return false; return cred->cr_ops->crneed_reencode(task); } int rpcauth_refreshcred(struct rpc_task *task) { struct rpc_cred *cred; int err; cred = task->tk_rqstp->rq_cred; if (cred == NULL) { err = rpcauth_bindcred(task, task->tk_msg.rpc_cred, task->tk_flags); if (err < 0) goto out; cred = task->tk_rqstp->rq_cred; } err = cred->cr_ops->crrefresh(task); out: if (err < 0) task->tk_status = err; return err; } void rpcauth_invalcred(struct rpc_task *task) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; if (cred) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); } int rpcauth_uptodatecred(struct rpc_task *task) { struct rpc_cred *cred = task->tk_rqstp->rq_cred; return cred == NULL || test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0; } static struct shrinker *rpc_cred_shrinker; int __init rpcauth_init_module(void) { int err; err = rpc_init_authunix(); if (err < 0) goto out1; rpc_cred_shrinker = shrinker_alloc(0, "sunrpc_cred"); if (!rpc_cred_shrinker) { err = -ENOMEM; goto out2; } rpc_cred_shrinker->count_objects = rpcauth_cache_shrink_count; rpc_cred_shrinker->scan_objects = rpcauth_cache_shrink_scan; shrinker_register(rpc_cred_shrinker); return 0; out2: rpc_destroy_authunix(); out1: return err; } void rpcauth_remove_module(void) { rpc_destroy_authunix(); shrinker_free(rpc_cred_shrinker); } |
| 32 32 32 32 32 31 5 40 40 1 1 1 43 42 54 54 4 1 49 54 47 3 44 2 1 1 5 1 4 40 39 1 39 1 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 | // 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/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; netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL); #endif return 0; } static void seq_file_net_put_net(struct seq_file *seq) { #ifdef CONFIG_NET_NS struct seq_net_private *priv = seq->private; put_net_track(priv->net, &priv->ns_tracker); #else put_net(&init_net); #endif } static int seq_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; seq_file_net_put_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_track(current->nsproxy->net_ns, &p->ns_tracker, GFP_KERNEL); #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_track(p->net, &p->ns_tracker); #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. * @state_size: The size of the per-file private state to allocate. * @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 mnt_idmap *idmap, 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(&nop_mnt_idmap, request_mask, 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, .setattr = proc_nochmod_setattr, }; 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; /* * This PDE acts only as an anchor for /proc/${pid}/net hierarchy. * Corresponding inode (PDE(inode) == net->proc_net) is never * instantiated therefore blanket zeroing is fine. * net->proc_net_stat inode is instantiated normally. */ err = -ENOMEM; netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) goto out; netd->subdir = RB_ROOT; netd->data = net; netd->nlink = 2; netd->namelen = 3; netd->parent = &proc_root; netd->name = netd->inline_name; memcpy(netd->name, "net", 4); uid = make_kuid(net->user_ns, 0); if (!uid_valid(uid)) uid = netd->uid; gid = make_kgid(net->user_ns, 0); if (!gid_valid(gid)) gid = netd->gid; proc_set_user(netd, uid, gid); /* Seed dentry revalidation for /proc/${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); } |
| 2 2 2 3 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 | /* * Copyright (c) 2006 Oracle. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/percpu.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/export.h> #include "rds.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); EXPORT_PER_CPU_SYMBOL_GPL(rds_stats); /* :.,$s/unsigned long\>.*\<s_\(.*\);/"\1",/g */ static const char *const rds_stat_names[] = { "conn_reset", "recv_drop_bad_checksum", "recv_drop_old_seq", "recv_drop_no_sock", "recv_drop_dead_sock", "recv_deliver_raced", "recv_delivered", "recv_queued", "recv_immediate_retry", "recv_delayed_retry", "recv_ack_required", "recv_rdma_bytes", "recv_ping", "send_queue_empty", "send_queue_full", "send_lock_contention", "send_lock_queue_raced", "send_immediate_retry", "send_delayed_retry", "send_drop_acked", "send_ack_required", "send_queued", "send_rdma", "send_rdma_bytes", "send_pong", "page_remainder_hit", "page_remainder_miss", "copy_to_user", "copy_from_user", "cong_update_queued", "cong_update_received", "cong_send_error", "cong_send_blocked", "recv_bytes_added_to_sock", "recv_bytes_freed_fromsock", "send_stuck_rm", "mprds_catchup_tx0_retries", }; void rds_stats_info_copy(struct rds_info_iterator *iter, uint64_t *values, const char *const *names, size_t nr) { struct rds_info_counter ctr; size_t i; for (i = 0; i < nr; i++) { BUG_ON(strlen(names[i]) >= sizeof(ctr.name)); strscpy_pad(ctr.name, names[i]); ctr.value = values[i]; rds_info_copy(iter, &ctr, sizeof(ctr)); } } EXPORT_SYMBOL_GPL(rds_stats_info_copy); /* * This gives global counters across all the transports. The strings * are copied in so that the tool doesn't need knowledge of the specific * stats that we're exporting. Some are pretty implementation dependent * and may change over time. That doesn't stop them from being useful. * * This is the only function in the chain that knows about the byte granular * length in userspace. It converts it to number of stat entries that the * rest of the functions operate in. */ static void rds_stats_info(struct socket *sock, unsigned int len, struct rds_info_iterator *iter, struct rds_info_lengths *lens) { struct rds_statistics stats = {0, }; uint64_t *src; uint64_t *sum; size_t i; int cpu; unsigned int avail; avail = len / sizeof(struct rds_info_counter); if (avail < ARRAY_SIZE(rds_stat_names)) { avail = 0; goto trans; } for_each_online_cpu(cpu) { src = (uint64_t *)&(per_cpu(rds_stats, cpu)); sum = (uint64_t *)&stats; for (i = 0; i < sizeof(stats) / sizeof(uint64_t); i++) *(sum++) += *(src++); } rds_stats_info_copy(iter, (uint64_t *)&stats, rds_stat_names, ARRAY_SIZE(rds_stat_names)); avail -= ARRAY_SIZE(rds_stat_names); trans: lens->each = sizeof(struct rds_info_counter); lens->nr = rds_trans_stats_info_copy(iter, avail) + ARRAY_SIZE(rds_stat_names); } void rds_stats_exit(void) { rds_info_deregister_func(RDS_INFO_COUNTERS, rds_stats_info); } int rds_stats_init(void) { rds_info_register_func(RDS_INFO_COUNTERS, rds_stats_info); return 0; } |
| 106 68 76 99 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_FRAG_H__ #define __NET_FRAG_H__ #include <linux/rhashtable-types.h> #include <linux/completion.h> #include <linux/in6.h> #include <linux/rbtree_types.h> #include <linux/refcount.h> #include <net/dropreason-core.h> /* Per netns frag queues directory */ struct fqdir { /* sysctls */ long high_thresh; long low_thresh; int timeout; int max_dist; struct inet_frags *f; struct net *net; bool dead; struct rhashtable rhashtable ____cacheline_aligned_in_smp; /* Keep atomic mem on separate cachelines in structs that include it */ atomic_long_t mem ____cacheline_aligned_in_smp; struct work_struct destroy_work; struct llist_node free_list; }; /** * enum: fragment queue flags * * @INET_FRAG_FIRST_IN: first fragment has arrived * @INET_FRAG_LAST_IN: final fragment has arrived * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction * @INET_FRAG_HASH_DEAD: inet_frag_kill() has not removed fq from rhashtable * @INET_FRAG_DROP: if skbs must be dropped (instead of being consumed) */ enum { INET_FRAG_FIRST_IN = BIT(0), INET_FRAG_LAST_IN = BIT(1), INET_FRAG_COMPLETE = BIT(2), INET_FRAG_HASH_DEAD = BIT(3), INET_FRAG_DROP = BIT(4), }; struct frag_v4_compare_key { __be32 saddr; __be32 daddr; u32 user; u32 vif; __be16 id; u16 protocol; }; struct frag_v6_compare_key { struct in6_addr saddr; struct in6_addr daddr; u32 user; __be32 id; u32 iif; }; /** * struct inet_frag_queue - fragment queue * * @node: rhash node * @key: keys identifying this frag. * @timer: queue expiration timer * @lock: spinlock protecting this frag * @refcnt: reference count of the queue * @rb_fragments: received fragments rb-tree root * @fragments_tail: received fragments tail * @last_run_head: the head of the last "run". see ip_fragment.c * @stamp: timestamp of the last received fragment * @len: total length of the original datagram * @meat: length of received fragments so far * @tstamp_type: stamp has a mono delivery time (EDT) * @flags: fragment queue flags * @max_size: maximum received fragment size * @fqdir: pointer to struct fqdir * @rcu: rcu head for freeing deferall */ struct inet_frag_queue { struct rhash_head node; union { struct frag_v4_compare_key v4; struct frag_v6_compare_key v6; } key; struct timer_list timer; spinlock_t lock; refcount_t refcnt; struct rb_root rb_fragments; struct sk_buff *fragments_tail; struct sk_buff *last_run_head; ktime_t stamp; int len; int meat; u8 tstamp_type; __u8 flags; u16 max_size; struct fqdir *fqdir; struct rcu_head rcu; }; struct inet_frags { unsigned int qsize; void (*constructor)(struct inet_frag_queue *q, const void *arg); void (*destructor)(struct inet_frag_queue *); void (*frag_expire)(struct timer_list *t); struct kmem_cache *frags_cachep; const char *frags_cache_name; struct rhashtable_params rhash_params; refcount_t refcnt; struct completion completion; }; int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *); int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net); void fqdir_pre_exit(struct fqdir *fqdir); void fqdir_exit(struct fqdir *fqdir); void inet_frag_kill(struct inet_frag_queue *q, int *refs); void inet_frag_destroy(struct inet_frag_queue *q); struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key); void inet_frag_queue_flush(struct inet_frag_queue *q, enum skb_drop_reason reason); static inline void inet_frag_putn(struct inet_frag_queue *q, int refs) { if (refs && refcount_sub_and_test(refs, &q->refcnt)) inet_frag_destroy(q); } /* Memory Tracking Functions. */ static inline long frag_mem_limit(const struct fqdir *fqdir) { return atomic_long_read(&fqdir->mem); } static inline void sub_frag_mem_limit(struct fqdir *fqdir, long val) { atomic_long_sub(val, &fqdir->mem); } static inline void add_frag_mem_limit(struct fqdir *fqdir, long val) { atomic_long_add(val, &fqdir->mem); } /* RFC 3168 support : * We want to check ECN values of all fragments, do detect invalid combinations. * In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value. */ #define IPFRAG_ECN_NOT_ECT 0x01 /* one frag had ECN_NOT_ECT */ #define IPFRAG_ECN_ECT_1 0x02 /* one frag had ECN_ECT_1 */ #define IPFRAG_ECN_ECT_0 0x04 /* one frag had ECN_ECT_0 */ #define IPFRAG_ECN_CE 0x08 /* one frag had ECN_CE */ extern const u8 ip_frag_ecn_table[16]; /* Return values of inet_frag_queue_insert() */ #define IPFRAG_OK 0 #define IPFRAG_DUP 1 #define IPFRAG_OVERLAP 2 int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, int offset, int end); void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce); struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q); #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * NFC hardware simulation driver * Copyright (c) 2013, Intel Corporation. */ #include <linux/device.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/nfc.h> #include <net/nfc/nfc.h> #include <net/nfc/digital.h> #define NFCSIM_ERR(d, fmt, args...) nfc_err(&d->nfc_digital_dev->nfc_dev->dev, \ "%s: " fmt, __func__, ## args) #define NFCSIM_DBG(d, fmt, args...) dev_dbg(&d->nfc_digital_dev->nfc_dev->dev, \ "%s: " fmt, __func__, ## args) #define NFCSIM_VERSION "0.2" #define NFCSIM_MODE_NONE 0 #define NFCSIM_MODE_INITIATOR 1 #define NFCSIM_MODE_TARGET 2 #define NFCSIM_CAPABILITIES (NFC_DIGITAL_DRV_CAPS_IN_CRC | \ NFC_DIGITAL_DRV_CAPS_TG_CRC) struct nfcsim { struct nfc_digital_dev *nfc_digital_dev; struct work_struct recv_work; struct delayed_work send_work; struct nfcsim_link *link_in; struct nfcsim_link *link_out; bool up; u8 mode; u8 rf_tech; u16 recv_timeout; nfc_digital_cmd_complete_t cb; void *arg; u8 dropframe; }; struct nfcsim_link { struct mutex lock; u8 rf_tech; u8 mode; u8 shutdown; struct sk_buff *skb; wait_queue_head_t recv_wait; u8 cond; }; static struct nfcsim_link *nfcsim_link_new(void) { struct nfcsim_link *link; link = kzalloc_obj(struct nfcsim_link); if (!link) return NULL; mutex_init(&link->lock); init_waitqueue_head(&link->recv_wait); return link; } static void nfcsim_link_free(struct nfcsim_link *link) { dev_kfree_skb(link->skb); kfree(link); } static void nfcsim_link_recv_wake(struct nfcsim_link *link) { link->cond = 1; wake_up_interruptible(&link->recv_wait); } static void nfcsim_link_set_skb(struct nfcsim_link *link, struct sk_buff *skb, u8 rf_tech, u8 mode) { mutex_lock(&link->lock); dev_kfree_skb(link->skb); link->skb = skb; link->rf_tech = rf_tech; link->mode = mode; mutex_unlock(&link->lock); } static void nfcsim_link_recv_cancel(struct nfcsim_link *link) { mutex_lock(&link->lock); link->mode = NFCSIM_MODE_NONE; mutex_unlock(&link->lock); nfcsim_link_recv_wake(link); } static void nfcsim_link_shutdown(struct nfcsim_link *link) { mutex_lock(&link->lock); link->shutdown = 1; link->mode = NFCSIM_MODE_NONE; mutex_unlock(&link->lock); nfcsim_link_recv_wake(link); } static struct sk_buff *nfcsim_link_recv_skb(struct nfcsim_link *link, int timeout, u8 rf_tech, u8 mode) { int rc; struct sk_buff *skb; rc = wait_event_interruptible_timeout(link->recv_wait, link->cond, msecs_to_jiffies(timeout)); mutex_lock(&link->lock); skb = link->skb; link->skb = NULL; if (!rc) { rc = -ETIMEDOUT; goto done; } if (!skb || link->rf_tech != rf_tech || link->mode == mode) { rc = -EINVAL; goto done; } if (link->shutdown) { rc = -ENODEV; goto done; } done: mutex_unlock(&link->lock); if (rc < 0) { dev_kfree_skb(skb); skb = ERR_PTR(rc); } link->cond = 0; return skb; } static void nfcsim_send_wq(struct work_struct *work) { struct nfcsim *dev = container_of(work, struct nfcsim, send_work.work); /* * To effectively send data, the device just wake up its link_out which * is the link_in of the peer device. The exchanged skb has already been * stored in the dev->link_out through nfcsim_link_set_skb(). */ nfcsim_link_recv_wake(dev->link_out); } static void nfcsim_recv_wq(struct work_struct *work) { struct nfcsim *dev = container_of(work, struct nfcsim, recv_work); struct sk_buff *skb; skb = nfcsim_link_recv_skb(dev->link_in, dev->recv_timeout, dev->rf_tech, dev->mode); if (!dev->up) { NFCSIM_ERR(dev, "Device is down\n"); if (!IS_ERR(skb)) dev_kfree_skb(skb); return; } dev->cb(dev->nfc_digital_dev, dev->arg, skb); } static int nfcsim_send(struct nfc_digital_dev *ddev, struct sk_buff *skb, u16 timeout, nfc_digital_cmd_complete_t cb, void *arg) { struct nfcsim *dev = nfc_digital_get_drvdata(ddev); u8 delay; if (!dev->up) { NFCSIM_ERR(dev, "Device is down\n"); return -ENODEV; } dev->recv_timeout = timeout; dev->cb = cb; dev->arg = arg; schedule_work(&dev->recv_work); if (dev->dropframe) { NFCSIM_DBG(dev, "dropping frame (out of %d)\n", dev->dropframe); dev_kfree_skb(skb); dev->dropframe--; return 0; } if (skb) { nfcsim_link_set_skb(dev->link_out, skb, dev->rf_tech, dev->mode); /* Add random delay (between 3 and 10 ms) before sending data */ get_random_bytes(&delay, 1); delay = 3 + (delay & 0x07); schedule_delayed_work(&dev->send_work, msecs_to_jiffies(delay)); } return 0; } static void nfcsim_abort_cmd(struct nfc_digital_dev *ddev) { const struct nfcsim *dev = nfc_digital_get_drvdata(ddev); nfcsim_link_recv_cancel(dev->link_in); } static int nfcsim_switch_rf(struct nfc_digital_dev *ddev, bool on) { struct nfcsim *dev = nfc_digital_get_drvdata(ddev); dev->up = on; return 0; } static int nfcsim_in_configure_hw(struct nfc_digital_dev *ddev, int type, int param) { struct nfcsim *dev = nfc_digital_get_drvdata(ddev); switch (type) { case NFC_DIGITAL_CONFIG_RF_TECH: dev->up = true; dev->mode = NFCSIM_MODE_INITIATOR; dev->rf_tech = param; break; case NFC_DIGITAL_CONFIG_FRAMING: break; default: NFCSIM_ERR(dev, "Invalid configuration type: %d\n", type); return -EINVAL; } return 0; } static int nfcsim_in_send_cmd(struct nfc_digital_dev *ddev, struct sk_buff *skb, u16 timeout, nfc_digital_cmd_complete_t cb, void *arg) { return nfcsim_send(ddev, skb, timeout, cb, arg); } static int nfcsim_tg_configure_hw(struct nfc_digital_dev *ddev, int type, int param) { struct nfcsim *dev = nfc_digital_get_drvdata(ddev); switch (type) { case NFC_DIGITAL_CONFIG_RF_TECH: dev->up = true; dev->mode = NFCSIM_MODE_TARGET; dev->rf_tech = param; break; case NFC_DIGITAL_CONFIG_FRAMING: break; default: NFCSIM_ERR(dev, "Invalid configuration type: %d\n", type); return -EINVAL; } return 0; } static int nfcsim_tg_send_cmd(struct nfc_digital_dev *ddev, struct sk_buff *skb, u16 timeout, nfc_digital_cmd_complete_t cb, void *arg) { return nfcsim_send(ddev, skb, timeout, cb, arg); } static int nfcsim_tg_listen(struct nfc_digital_dev *ddev, u16 timeout, nfc_digital_cmd_complete_t cb, void *arg) { return nfcsim_send(ddev, NULL, timeout, cb, arg); } static const struct nfc_digital_ops nfcsim_digital_ops = { .in_configure_hw = nfcsim_in_configure_hw, .in_send_cmd = nfcsim_in_send_cmd, .tg_listen = nfcsim_tg_listen, .tg_configure_hw = nfcsim_tg_configure_hw, .tg_send_cmd = nfcsim_tg_send_cmd, .abort_cmd = nfcsim_abort_cmd, .switch_rf = nfcsim_switch_rf, }; static struct dentry *nfcsim_debugfs_root; static void nfcsim_debugfs_init(void) { nfcsim_debugfs_root = debugfs_create_dir("nfcsim", NULL); } static void nfcsim_debugfs_remove(void) { debugfs_remove_recursive(nfcsim_debugfs_root); } static void nfcsim_debugfs_init_dev(struct nfcsim *dev) { struct dentry *dev_dir; char devname[5]; /* nfcX\0 */ u32 idx; int n; if (!nfcsim_debugfs_root) { NFCSIM_ERR(dev, "nfcsim debugfs not initialized\n"); return; } idx = dev->nfc_digital_dev->nfc_dev->idx; n = snprintf(devname, sizeof(devname), "nfc%d", idx); if (n >= sizeof(devname)) { NFCSIM_ERR(dev, "Could not compute dev name for dev %d\n", idx); return; } dev_dir = debugfs_create_dir(devname, nfcsim_debugfs_root); debugfs_create_u8("dropframe", 0664, dev_dir, &dev->dropframe); } static struct nfcsim *nfcsim_device_new(struct nfcsim_link *link_in, struct nfcsim_link *link_out) { struct nfcsim *dev; int rc; dev = kzalloc_obj(struct nfcsim); if (!dev) return ERR_PTR(-ENOMEM); INIT_DELAYED_WORK(&dev->send_work, nfcsim_send_wq); INIT_WORK(&dev->recv_work, nfcsim_recv_wq); dev->nfc_digital_dev = nfc_digital_allocate_device(&nfcsim_digital_ops, NFC_PROTO_NFC_DEP_MASK, NFCSIM_CAPABILITIES, 0, 0); if (!dev->nfc_digital_dev) { kfree(dev); return ERR_PTR(-ENOMEM); } nfc_digital_set_drvdata(dev->nfc_digital_dev, dev); dev->link_in = link_in; dev->link_out = link_out; rc = nfc_digital_register_device(dev->nfc_digital_dev); if (rc) { pr_err("Could not register digital device (%d)\n", rc); nfc_digital_free_device(dev->nfc_digital_dev); kfree(dev); return ERR_PTR(rc); } nfcsim_debugfs_init_dev(dev); return dev; } static void nfcsim_device_free(struct nfcsim *dev) { nfc_digital_unregister_device(dev->nfc_digital_dev); dev->up = false; nfcsim_link_shutdown(dev->link_in); cancel_delayed_work_sync(&dev->send_work); cancel_work_sync(&dev->recv_work); nfc_digital_free_device(dev->nfc_digital_dev); kfree(dev); } static struct nfcsim *dev0; static struct nfcsim *dev1; static int __init nfcsim_init(void) { struct nfcsim_link *link0, *link1; int rc; link0 = nfcsim_link_new(); link1 = nfcsim_link_new(); if (!link0 || !link1) { rc = -ENOMEM; goto exit_err; } nfcsim_debugfs_init(); dev0 = nfcsim_device_new(link0, link1); if (IS_ERR(dev0)) { rc = PTR_ERR(dev0); goto exit_err; } dev1 = nfcsim_device_new(link1, link0); if (IS_ERR(dev1)) { nfcsim_device_free(dev0); rc = PTR_ERR(dev1); goto exit_err; } pr_info("nfcsim " NFCSIM_VERSION " initialized\n"); return 0; exit_err: pr_err("Failed to initialize nfcsim driver (%d)\n", rc); if (link0) nfcsim_link_free(link0); if (link1) nfcsim_link_free(link1); return rc; } static void __exit nfcsim_exit(void) { struct nfcsim_link *link0, *link1; link0 = dev0->link_in; link1 = dev0->link_out; nfcsim_device_free(dev0); nfcsim_device_free(dev1); nfcsim_link_free(link0); nfcsim_link_free(link1); nfcsim_debugfs_remove(); } module_init(nfcsim_init); module_exit(nfcsim_exit); MODULE_DESCRIPTION("NFCSim driver ver " NFCSIM_VERSION); MODULE_VERSION(NFCSIM_VERSION); MODULE_LICENSE("GPL"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef __DSA_USER_H #define __DSA_USER_H #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/list.h> #include <linux/netpoll.h> #include <linux/types.h> #include <net/dsa.h> #include <net/gro_cells.h> struct net_device; struct netlink_ext_ack; extern struct notifier_block dsa_user_switchdev_notifier; extern struct notifier_block dsa_user_switchdev_blocking_notifier; struct dsa_user_priv { /* Copy of CPU port xmit for faster access in user transmit hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); struct gro_cells gcells; /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif /* TC context */ struct list_head mall_tc_list; }; void dsa_user_mii_bus_init(struct dsa_switch *ds); int dsa_user_create(struct dsa_port *dp); void dsa_user_destroy(struct net_device *user_dev); int dsa_user_suspend(struct net_device *user_dev); int dsa_user_resume(struct net_device *user_dev); int dsa_user_register_notifier(void); void dsa_user_unregister_notifier(void); int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr); void dsa_user_host_uc_uninstall(struct net_device *dev); void dsa_user_sync_ha(struct net_device *dev); void dsa_user_unsync_ha(struct net_device *dev); void dsa_user_setup_tagger(struct net_device *user); int dsa_user_change_mtu(struct net_device *dev, int new_mtu); int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack); int dsa_user_manage_vlan_filtering(struct net_device *dev, bool vlan_filtering); static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); return p->dp; } static inline struct net_device * dsa_user_to_conduit(const struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return dsa_port_to_conduit(dp); } #endif |
| 5078 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 | #undef TRACE_SYSTEM #define TRACE_SYSTEM netlink #if !defined(_TRACE_NETLINK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NETLINK_H #include <linux/tracepoint.h> TRACE_EVENT(netlink_extack, TP_PROTO(const char *msg), TP_ARGS(msg), TP_STRUCT__entry( __string( msg, msg ) ), TP_fast_assign( __assign_str(msg); ), TP_printk("msg=%s", __get_str(msg)) ); #endif /* _TRACE_NETLINK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 110 27 397 391 280 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Spanning tree protocol; timer-related code * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/times.h> #include "br_private.h" #include "br_private_stp.h" /* called under bridge lock */ static int br_is_designated_for_some_port(const struct net_bridge *br) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->state != BR_STATE_DISABLED && !memcmp(&p->designated_bridge, &br->bridge_id, 8)) return 1; } return 0; } static void br_hello_timer_expired(struct timer_list *t) { struct net_bridge *br = timer_container_of(br, t, hello_timer); br_debug(br, "hello timer expired\n"); spin_lock(&br->lock); if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); if (br->stp_enabled == BR_KERNEL_STP) mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time)); } spin_unlock(&br->lock); } static void br_message_age_timer_expired(struct timer_list *t) { struct net_bridge_port *p = timer_container_of(p, t, message_age_timer); struct net_bridge *br = p->br; const bridge_id *id = &p->designated_bridge; int was_root; if (p->state == BR_STATE_DISABLED) return; br_info(br, "port %u(%s) neighbor %.2x%.2x.%pM lost\n", (unsigned int) p->port_no, p->dev->name, id->prio[0], id->prio[1], &id->addr); /* * According to the spec, the message age timer cannot be * running when we are the root bridge. So.. this was_root * check is redundant. I'm leaving it in for now, though. */ spin_lock(&br->lock); if (p->state == BR_STATE_DISABLED) goto unlock; was_root = br_is_root_bridge(br); br_become_designated_port(p); br_configuration_update(br); br_port_state_selection(br); if (br_is_root_bridge(br) && !was_root) br_become_root_bridge(br); unlock: spin_unlock(&br->lock); } static void br_forward_delay_timer_expired(struct timer_list *t) { struct net_bridge_port *p = timer_container_of(p, t, forward_delay_timer); struct net_bridge *br = p->br; br_debug(br, "port %u(%s) forward delay timer\n", (unsigned int) p->port_no, p->dev->name); spin_lock(&br->lock); if (p->state == BR_STATE_LISTENING) { br_set_state(p, BR_STATE_LEARNING); mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); } else if (p->state == BR_STATE_LEARNING) { br_set_state(p, BR_STATE_FORWARDING); if (br_is_designated_for_some_port(br)) br_topology_change_detection(br); netif_carrier_on(br->dev); } rcu_read_lock(); br_ifinfo_notify(RTM_NEWLINK, NULL, p); rcu_read_unlock(); spin_unlock(&br->lock); } static void br_tcn_timer_expired(struct timer_list *t) { struct net_bridge *br = timer_container_of(br, t, tcn_timer); br_debug(br, "tcn timer expired\n"); spin_lock(&br->lock); if (!br_is_root_bridge(br) && (br->dev->flags & IFF_UP)) { br_transmit_tcn(br); mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time); } spin_unlock(&br->lock); } static void br_topology_change_timer_expired(struct timer_list *t) { struct net_bridge *br = timer_container_of(br, t, topology_change_timer); br_debug(br, "topo change timer expired\n"); spin_lock(&br->lock); br->topology_change_detected = 0; __br_set_topology_change(br, 0); spin_unlock(&br->lock); } static void br_hold_timer_expired(struct timer_list *t) { struct net_bridge_port *p = timer_container_of(p, t, hold_timer); br_debug(p->br, "port %u(%s) hold timer expired\n", (unsigned int) p->port_no, p->dev->name); spin_lock(&p->br->lock); if (p->config_pending) br_transmit_config(p); spin_unlock(&p->br->lock); } void br_stp_timer_init(struct net_bridge *br) { timer_setup(&br->hello_timer, br_hello_timer_expired, 0); timer_setup(&br->tcn_timer, br_tcn_timer_expired, 0); timer_setup(&br->topology_change_timer, br_topology_change_timer_expired, 0); } void br_stp_port_timer_init(struct net_bridge_port *p) { timer_setup(&p->message_age_timer, br_message_age_timer_expired, 0); timer_setup(&p->forward_delay_timer, br_forward_delay_timer_expired, 0); timer_setup(&p->hold_timer, br_hold_timer_expired, 0); } /* Report ticks left (in USER_HZ) used for API */ unsigned long br_timer_value(const struct timer_list *timer) { return timer_pending(timer) ? jiffies_delta_to_clock_t(timer->expires - jiffies) : 0; } |
| 74 1 1 2 59 12 6 6 64 67 68 67 67 68 38 38 34 14 18 61 64 27 14 61 30 31 17 11 5 52 11 46 57 26 57 2 62 58 6 63 6 58 36 28 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 | // SPDX-License-Identifier: GPL-2.0-or-later /* mpi-pow.c - MPI functions * Copyright (C) 1994, 1996, 1998, 2000 Free Software Foundation, Inc. * * This file is part of GnuPG. * * Note: This code is heavily based on the GNU MP Library. * Actually it's the same code with only minor changes in the * way the data is stored; this is to support the abstraction * of an optional secure memory allocation which may be used * to avoid revealing of sensitive data due to paging etc. * The GNU MP Library itself is published under the LGPL; * however I decided to publish this code under the plain GPL. */ #include <linux/export.h> #include <linux/sched.h> #include <linux/string.h> #include "mpi-internal.h" #include "longlong.h" /**************** * RES = BASE ^ EXP mod MOD */ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod) { mpi_ptr_t mp_marker = NULL, bp_marker = NULL, ep_marker = NULL; struct karatsuba_ctx karactx = {}; mpi_ptr_t xp_marker = NULL; mpi_ptr_t tspace = NULL; mpi_ptr_t rp, ep, mp, bp; mpi_size_t esize, msize, bsize, rsize; int msign, bsign, rsign; mpi_size_t size; int mod_shift_cnt; int negative_result; int assign_rp = 0; mpi_size_t tsize = 0; /* to avoid compiler warning */ /* fixme: we should check that the warning is void */ int rc = -ENOMEM; esize = exp->nlimbs; msize = mod->nlimbs; size = 2 * msize; msign = mod->sign; rp = res->d; ep = exp->d; if (!msize) return -EINVAL; if (!esize) { /* Exponent is zero, result is 1 mod MOD, i.e., 1 or 0 * depending on if MOD equals 1. */ res->nlimbs = (msize == 1 && mod->d[0] == 1) ? 0 : 1; if (res->nlimbs) { if (mpi_resize(res, 1) < 0) goto enomem; rp = res->d; rp[0] = 1; } res->sign = 0; goto leave; } /* Normalize MOD (i.e. make its most significant bit set) as required by * mpn_divrem. This will make the intermediate values in the calculation * slightly larger, but the correct result is obtained after a final * reduction using the original MOD value. */ mp = mp_marker = mpi_alloc_limb_space(msize); if (!mp) goto enomem; mod_shift_cnt = count_leading_zeros(mod->d[msize - 1]); if (mod_shift_cnt) mpihelp_lshift(mp, mod->d, msize, mod_shift_cnt); else MPN_COPY(mp, mod->d, msize); bsize = base->nlimbs; bsign = base->sign; if (bsize > msize) { /* The base is larger than the module. Reduce it. */ /* Allocate (BSIZE + 1) with space for remainder and quotient. * (The quotient is (bsize - msize + 1) limbs.) */ bp = bp_marker = mpi_alloc_limb_space(bsize + 1); if (!bp) goto enomem; MPN_COPY(bp, base->d, bsize); /* We don't care about the quotient, store it above the remainder, * at BP + MSIZE. */ mpihelp_divrem(bp + msize, 0, bp, bsize, mp, msize); bsize = msize; /* Canonicalize the base, since we are going to multiply with it * quite a few times. */ MPN_NORMALIZE(bp, bsize); } else bp = base->d; if (!bsize) { res->nlimbs = 0; res->sign = 0; goto leave; } if (res->alloced < size) { /* We have to allocate more space for RES. If any of the input * parameters are identical to RES, defer deallocation of the old * space. */ if (rp == ep || rp == mp || rp == bp) { rp = mpi_alloc_limb_space(size); if (!rp) goto enomem; assign_rp = 1; } else { if (mpi_resize(res, size) < 0) goto enomem; rp = res->d; } } else { /* Make BASE, EXP and MOD not overlap with RES. */ if (rp == bp) { /* RES and BASE are identical. Allocate temp. space for BASE. */ BUG_ON(bp_marker); bp = bp_marker = mpi_alloc_limb_space(bsize); if (!bp) goto enomem; MPN_COPY(bp, rp, bsize); } if (rp == ep) { /* RES and EXP are identical. Allocate temp. space for EXP. */ ep = ep_marker = mpi_alloc_limb_space(esize); if (!ep) goto enomem; MPN_COPY(ep, rp, esize); } if (rp == mp) { /* RES and MOD are identical. Allocate temporary space for MOD. */ BUG_ON(mp_marker); mp = mp_marker = mpi_alloc_limb_space(msize); if (!mp) goto enomem; MPN_COPY(mp, rp, msize); } } MPN_COPY(rp, bp, bsize); rsize = bsize; rsign = bsign; { mpi_size_t i; mpi_ptr_t xp; int c; mpi_limb_t e; mpi_limb_t carry_limb; xp = xp_marker = mpi_alloc_limb_space(2 * (msize + 1)); if (!xp) goto enomem; negative_result = (ep[0] & 1) && base->sign; i = esize - 1; e = ep[i]; c = count_leading_zeros(e); e = (e << c) << 1; /* shift the exp bits to the left, lose msb */ c = BITS_PER_MPI_LIMB - 1 - c; /* Main loop. * * Make the result be pointed to alternately by XP and RP. This * helps us avoid block copying, which would otherwise be necessary * with the overlap restrictions of mpihelp_divmod. With 50% probability * the result after this loop will be in the area originally pointed * by RP (==RES->d), and with 50% probability in the area originally * pointed to by XP. */ for (;;) { while (c) { mpi_size_t xsize; /*if (mpihelp_mul_n(xp, rp, rp, rsize) < 0) goto enomem */ if (rsize < KARATSUBA_THRESHOLD) mpih_sqr_n_basecase(xp, rp, rsize); else { if (!tspace) { tsize = 2 * rsize; tspace = mpi_alloc_limb_space(tsize); if (!tspace) goto enomem; } else if (tsize < (2 * rsize)) { mpi_free_limb_space(tspace); tsize = 2 * rsize; tspace = mpi_alloc_limb_space(tsize); if (!tspace) goto enomem; } mpih_sqr_n(xp, rp, rsize, tspace); } xsize = 2 * rsize; if (xsize > msize) { mpihelp_divrem(xp + msize, 0, xp, xsize, mp, msize); xsize = msize; } swap(rp, xp); rsize = xsize; if ((mpi_limb_signed_t) e < 0) { /*mpihelp_mul( xp, rp, rsize, bp, bsize ); */ if (bsize < KARATSUBA_THRESHOLD) { mpi_limb_t tmp; if (mpihelp_mul (xp, rp, rsize, bp, bsize, &tmp) < 0) goto enomem; } else { if (mpihelp_mul_karatsuba_case (xp, rp, rsize, bp, bsize, &karactx) < 0) goto enomem; } xsize = rsize + bsize; if (xsize > msize) { mpihelp_divrem(xp + msize, 0, xp, xsize, mp, msize); xsize = msize; } swap(rp, xp); rsize = xsize; } e <<= 1; c--; cond_resched(); } i--; if (i < 0) break; e = ep[i]; c = BITS_PER_MPI_LIMB; } /* We shifted MOD, the modulo reduction argument, left MOD_SHIFT_CNT * steps. Adjust the result by reducing it with the original MOD. * * Also make sure the result is put in RES->d (where it already * might be, see above). */ if (mod_shift_cnt) { carry_limb = mpihelp_lshift(res->d, rp, rsize, mod_shift_cnt); rp = res->d; if (carry_limb) { rp[rsize] = carry_limb; rsize++; } } else { MPN_COPY(res->d, rp, rsize); rp = res->d; } if (rsize >= msize) { mpihelp_divrem(rp + msize, 0, rp, rsize, mp, msize); rsize = msize; } /* Remove any leading zero words from the result. */ if (mod_shift_cnt) mpihelp_rshift(rp, rp, rsize, mod_shift_cnt); MPN_NORMALIZE(rp, rsize); } if (negative_result && rsize) { if (mod_shift_cnt) mpihelp_rshift(mp, mp, msize, mod_shift_cnt); mpihelp_sub(rp, mp, msize, rp, rsize); rsize = msize; rsign = msign; MPN_NORMALIZE(rp, rsize); } res->nlimbs = rsize; res->sign = rsign; leave: rc = 0; enomem: mpihelp_release_karatsuba_ctx(&karactx); if (assign_rp) mpi_assign_limb_space(res, rp, size); if (mp_marker) mpi_free_limb_space(mp_marker); if (bp_marker) mpi_free_limb_space(bp_marker); if (ep_marker) mpi_free_limb_space(ep_marker); if (xp_marker) mpi_free_limb_space(xp_marker); if (tspace) mpi_free_limb_space(tspace); return rc; } EXPORT_SYMBOL_GPL(mpi_powm); |
| 93 58 49 37 58 1 28 67 57 42 15 4 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 | #ifndef __NET_SCHED_CODEL_IMPL_H #define __NET_SCHED_CODEL_IMPL_H /* * Codel - The Controlled-Delay Active Queue Management algorithm * * Copyright (C) 2011-2012 Kathleen Nichols <nichols@pollere.com> * Copyright (C) 2011-2012 Van Jacobson <van@pollere.net> * Copyright (C) 2012 Michael D. Taht <dave.taht@bufferbloat.net> * Copyright (C) 2012,2015 Eric Dumazet <edumazet@google.com> * * 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, * without modification. * 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. The names of the authors may not 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. * * 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. * */ /* Controlling Queue Delay (CoDel) algorithm * ========================================= * Source : Kathleen Nichols and Van Jacobson * http://queue.acm.org/detail.cfm?id=2209336 * * Implemented on linux by Dave Taht and Eric Dumazet */ #include <net/inet_ecn.h> static void codel_params_init(struct codel_params *params) { params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; params->ce_threshold_mask = 0; params->ce_threshold_selector = 0; params->ecn = false; } static void codel_vars_init(struct codel_vars *vars) { memset(vars, 0, sizeof(*vars)); } static void codel_stats_init(struct codel_stats *stats) { stats->maxpacket = 0; } /* * http://en.wikipedia.org/wiki/Methods_of_computing_square_roots#Iterative_methods_for_reciprocal_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 */ static void codel_Newton_step(struct codel_vars *vars) { u32 invsqrt = ((u32)vars->rec_inv_sqrt) << REC_INV_SQRT_SHIFT; u32 invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; u64 val = (3LL << 32) - ((u64)vars->count * invsqrt2); val >>= 2; /* avoid overflow in following multiply */ val = (val * invsqrt) >> (32 - 2 + 1); vars->rec_inv_sqrt = val >> REC_INV_SQRT_SHIFT; } /* * CoDel control_law is t + interval/sqrt(count) * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid * both sqrt() and divide operation. */ static codel_time_t codel_control_law(codel_time_t t, codel_time_t interval, u32 rec_inv_sqrt) { return t + reciprocal_scale(interval, rec_inv_sqrt << REC_INV_SQRT_SHIFT); } static bool codel_should_drop(const struct sk_buff *skb, void *ctx, struct codel_vars *vars, struct codel_params *params, struct codel_stats *stats, codel_skb_len_t skb_len_func, codel_skb_time_t skb_time_func, u32 *backlog, codel_time_t now) { bool ok_to_drop; u32 skb_len; if (!skb) { vars->first_above_time = 0; return false; } skb_len = skb_len_func(skb); WRITE_ONCE(vars->ldelay, now - skb_time_func(skb)); if (unlikely(skb_len > stats->maxpacket)) WRITE_ONCE(stats->maxpacket, skb_len); if (codel_time_before(vars->ldelay, params->target) || *backlog <= params->mtu) { /* went below - stay below for at least interval */ vars->first_above_time = 0; return false; } ok_to_drop = false; if (vars->first_above_time == 0) { /* just went above from below. If we stay above * for at least interval we'll say it's ok to drop */ vars->first_above_time = now + params->interval; } else if (codel_time_after(now, vars->first_above_time)) { ok_to_drop = true; } return ok_to_drop; } static struct sk_buff *codel_dequeue(void *ctx, u32 *backlog, struct codel_params *params, struct codel_vars *vars, struct codel_stats *stats, codel_skb_len_t skb_len_func, codel_skb_time_t skb_time_func, codel_skb_drop_t drop_func, codel_skb_dequeue_t dequeue_func) { struct sk_buff *skb = dequeue_func(vars, ctx); codel_time_t now; bool drop; if (!skb) { vars->first_above_time = 0; WRITE_ONCE(vars->dropping, false); return skb; } now = codel_get_time(); drop = codel_should_drop(skb, ctx, vars, params, stats, skb_len_func, skb_time_func, backlog, now); if (vars->dropping) { if (!drop) { /* sojourn time below target - leave dropping state */ WRITE_ONCE(vars->dropping, false); } else if (codel_time_after_eq(now, vars->drop_next)) { /* It's time for the next drop. Drop the current * packet and dequeue the next. The dequeue might * take us out of dropping state. * If not, schedule the next drop. * A large backlog might result in drop rates so high * that the next drop should happen now, * hence the while loop. */ while (vars->dropping && codel_time_after_eq(now, vars->drop_next)) { /* dont care of possible wrap * since there is no more divide. */ WRITE_ONCE(vars->count, vars->count + 1); codel_Newton_step(vars); if (params->ecn && INET_ECN_set_ce(skb)) { WRITE_ONCE(stats->ecn_mark, stats->ecn_mark + 1); WRITE_ONCE(vars->drop_next, codel_control_law(vars->drop_next, params->interval, vars->rec_inv_sqrt)); goto end; } stats->drop_len += skb_len_func(skb); drop_func(skb, ctx); stats->drop_count++; skb = dequeue_func(vars, ctx); if (!codel_should_drop(skb, ctx, vars, params, stats, skb_len_func, skb_time_func, backlog, now)) { /* leave dropping state */ WRITE_ONCE(vars->dropping, false); } else { /* and schedule the next drop */ WRITE_ONCE(vars->drop_next, codel_control_law(vars->drop_next, params->interval, vars->rec_inv_sqrt)); } } } } else if (drop) { u32 delta; if (params->ecn && INET_ECN_set_ce(skb)) { WRITE_ONCE(stats->ecn_mark, stats->ecn_mark + 1); } else { stats->drop_len += skb_len_func(skb); drop_func(skb, ctx); stats->drop_count++; skb = dequeue_func(vars, ctx); drop = codel_should_drop(skb, ctx, vars, params, stats, skb_len_func, skb_time_func, backlog, now); } WRITE_ONCE(vars->dropping, true); /* if min went above target close to when we last went below it * assume that the drop rate that controlled the queue on the * last cycle is a good starting point to control it now. */ delta = vars->count - vars->lastcount; if (delta > 1 && codel_time_before(now - vars->drop_next, 16 * params->interval)) { WRITE_ONCE(vars->count, delta); /* we dont care if rec_inv_sqrt approximation * is not very precise : * Next Newton steps will correct it quadratically. */ codel_Newton_step(vars); } else { WRITE_ONCE(vars->count, 1); vars->rec_inv_sqrt = ~0U >> REC_INV_SQRT_SHIFT; } WRITE_ONCE(vars->lastcount, vars->count); WRITE_ONCE(vars->drop_next, codel_control_law(now, params->interval, vars->rec_inv_sqrt)); } end: if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) { bool set_ce = true; if (params->ce_threshold_mask) { int dsfield = skb_get_dsfield(skb); set_ce = (dsfield >= 0 && (((u8)dsfield & params->ce_threshold_mask) == params->ce_threshold_selector)); } if (set_ce && INET_ECN_set_ce(skb)) WRITE_ONCE(stats->ce_mark, stats->ce_mark + 1); } return skb; } #endif |
| 16 10 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 | /* * linux/fs/nls/nls_cp860.c * * Charset cp860 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e3, 0x00e0, 0x00c1, 0x00e7, 0x00ea, 0x00ca, 0x00e8, 0x00cd, 0x00d4, 0x00ec, 0x00c3, 0x00c2, /* 0x90*/ 0x00c9, 0x00c0, 0x00c8, 0x00f4, 0x00f5, 0x00f2, 0x00da, 0x00f9, 0x00cc, 0x00d5, 0x00dc, 0x00a2, 0x00a3, 0x00d9, 0x20a7, 0x00d3, /* 0xa0*/ 0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba, 0x00bf, 0x00d2, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, /* 0xd0*/ 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, /* 0xe0*/ 0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4, 0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229, /* 0xf0*/ 0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0xad, 0x9b, 0x9c, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0xa6, 0xae, 0xaa, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0xf8, 0xf1, 0xfd, 0x00, 0x00, 0xe6, 0x00, 0xfa, /* 0xb0-0xb7 */ 0x00, 0x00, 0xa7, 0xaf, 0xac, 0xab, 0x00, 0xa8, /* 0xb8-0xbf */ 0x91, 0x86, 0x8f, 0x8e, 0x00, 0x00, 0x00, 0x80, /* 0xc0-0xc7 */ 0x92, 0x90, 0x89, 0x00, 0x98, 0x8b, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0xa5, 0xa9, 0x9f, 0x8c, 0x99, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x9d, 0x96, 0x00, 0x9a, 0x00, 0x00, 0xe1, /* 0xd8-0xdf */ 0x85, 0xa0, 0x83, 0x84, 0x00, 0x00, 0x00, 0x87, /* 0xe0-0xe7 */ 0x8a, 0x82, 0x88, 0x00, 0x8d, 0xa1, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0xa4, 0x95, 0xa2, 0x93, 0x94, 0x00, 0xf6, /* 0xf0-0xf7 */ 0x00, 0x97, 0xa3, 0x00, 0x81, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0xe2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0xe9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0xe4, 0x00, 0x00, 0xe8, 0x00, /* 0xa0-0xa7 */ 0x00, 0xea, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0xe0, 0x00, 0x00, 0xeb, 0xee, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0xe3, 0x00, 0x00, 0xe5, 0xe7, 0x00, 0xed, 0x00, /* 0xc0-0xc7 */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xfc, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x9e, /* 0xa0-0xa7 */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0xf9, 0xfb, 0x00, 0x00, 0x00, 0xec, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0xef, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xf7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0xf0, 0x00, 0x00, 0xf3, 0xf2, 0x00, 0x00, /* 0x60-0x67 */ }; static const unsigned char page23[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0xf4, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0xd5, 0xd6, 0xc9, 0xb8, 0xb7, 0xbb, /* 0x50-0x57 */ 0xd4, 0xd3, 0xc8, 0xbe, 0xbd, 0xbc, 0xc6, 0xc7, /* 0x58-0x5f */ 0xcc, 0xb5, 0xb6, 0xb9, 0xd1, 0xd2, 0xcb, 0xcf, /* 0x60-0x67 */ 0xd0, 0xca, 0xd8, 0xd7, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0xdd, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0xde, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, NULL, page22, page23, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x87, 0x81, 0x82, 0x83, 0x84, 0x85, 0xa0, 0x87, /* 0x80-0x87 */ 0x88, 0x88, 0x8a, 0xa1, 0x93, 0x8d, 0x84, 0x83, /* 0x88-0x8f */ 0x82, 0x85, 0x8a, 0x93, 0x94, 0x95, 0xa3, 0x97, /* 0x90-0x97 */ 0x8d, 0x94, 0x81, 0x9b, 0x9c, 0x97, 0x9e, 0xa2, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa4, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0x95, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0x00, 0xe3, 0xe5, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xed, 0x00, 0x00, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x9a, 0x90, 0x8f, 0x8e, 0x91, 0x86, 0x80, /* 0x80-0x87 */ 0x89, 0x89, 0x92, 0x8b, 0x8c, 0x98, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x8c, 0x99, 0xa9, 0x96, 0x9d, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0x86, 0x8b, 0x9f, 0x96, 0xa5, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0x00, 0xe1, 0xe2, 0x00, 0xe4, 0xe4, 0x00, 0x00, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0x00, 0xec, 0xe8, 0x00, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp860", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp860(void) { return register_nls(&table); } static void __exit exit_nls_cp860(void) { unregister_nls(&table); } module_init(init_nls_cp860) module_exit(exit_nls_cp860) MODULE_DESCRIPTION("NLS Codepage 860 (Portuguese)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 22 1 22 20 1 14 7 17 16 6 17 17 1 7 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 | /* * Copyright (c) 2016 Intel Corporation * * Permission to use, copy, modify, distribute, and sell this software and its * documentation for any purpose is hereby granted without fee, provided that * the above copyright notice appear in all copies and that both that copyright * notice and this permission notice appear in supporting documentation, and * that the name of the copyright holders not be used in advertising or * publicity pertaining to distribution of the software without specific, * written prior permission. The copyright holders make no representations * about the suitability of this software for any purpose. It is provided "as * is" without express or implied warranty. * * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE * OF THIS SOFTWARE. */ #include <linux/export.h> #include <linux/uaccess.h> #include <drm/drm_drv.h> #include <drm/drm_encoder.h> #include <drm/drm_file.h> #include <drm/drm_framebuffer.h> #include <drm/drm_managed.h> #include <drm/drm_mode_config.h> #include <drm/drm_print.h> #include <drm/drm_colorop.h> #include <linux/dma-resv.h> #include "drm_crtc_internal.h" #include "drm_internal.h" int drm_modeset_register_all(struct drm_device *dev) { int ret; ret = drm_plane_register_all(dev); if (ret) goto err_plane; ret = drm_crtc_register_all(dev); if (ret) goto err_crtc; ret = drm_encoder_register_all(dev); if (ret) goto err_encoder; ret = drm_connector_register_all(dev); if (ret) goto err_connector; return 0; err_connector: drm_encoder_unregister_all(dev); err_encoder: drm_crtc_unregister_all(dev); err_crtc: drm_plane_unregister_all(dev); err_plane: return ret; } void drm_modeset_unregister_all(struct drm_device *dev) { drm_connector_unregister_all(dev); drm_encoder_unregister_all(dev); drm_crtc_unregister_all(dev); drm_plane_unregister_all(dev); } /** * drm_mode_getresources - get graphics configuration * @dev: drm device for the ioctl * @data: data pointer for the ioctl * @file_priv: drm file for the ioctl call * * Construct a set of configuration description structures and return * them to the user, including CRTC, connector and framebuffer configuration. * * Called by the user via ioctl. * * Returns: * Zero on success, negative errno on failure. */ int drm_mode_getresources(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_mode_card_res *card_res = data; struct drm_framebuffer *fb; struct drm_connector *connector; struct drm_crtc *crtc; struct drm_encoder *encoder; int count, ret = 0; uint32_t __user *fb_id; uint32_t __user *crtc_id; uint32_t __user *connector_id; uint32_t __user *encoder_id; struct drm_connector_list_iter conn_iter; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; mutex_lock(&file_priv->fbs_lock); count = 0; fb_id = u64_to_user_ptr(card_res->fb_id_ptr); list_for_each_entry(fb, &file_priv->fbs, filp_head) { if (count < card_res->count_fbs && put_user(fb->base.id, fb_id + count)) { mutex_unlock(&file_priv->fbs_lock); return -EFAULT; } count++; } card_res->count_fbs = count; mutex_unlock(&file_priv->fbs_lock); card_res->max_height = dev->mode_config.max_height; card_res->min_height = dev->mode_config.min_height; card_res->max_width = dev->mode_config.max_width; card_res->min_width = dev->mode_config.min_width; count = 0; crtc_id = u64_to_user_ptr(card_res->crtc_id_ptr); drm_for_each_crtc(crtc, dev) { if (drm_lease_held(file_priv, crtc->base.id)) { if (count < card_res->count_crtcs && put_user(crtc->base.id, crtc_id + count)) return -EFAULT; count++; } } card_res->count_crtcs = count; count = 0; encoder_id = u64_to_user_ptr(card_res->encoder_id_ptr); drm_for_each_encoder(encoder, dev) { if (count < card_res->count_encoders && put_user(encoder->base.id, encoder_id + count)) return -EFAULT; count++; } card_res->count_encoders = count; drm_connector_list_iter_begin(dev, &conn_iter); count = 0; connector_id = u64_to_user_ptr(card_res->connector_id_ptr); /* * FIXME: the connectors on the list may not be fully initialized yet, * if the ioctl is called before the connectors are registered. (See * drm_dev_register()->drm_modeset_register_all() for static and * drm_connector_dynamic_register() for dynamic connectors.) * The driver should only get registered after static connectors are * fully initialized and dynamic connectors should be added to the * connector list only after fully initializing them. */ drm_for_each_connector_iter(connector, &conn_iter) { /* only expose writeback connectors if userspace understands them */ if (!file_priv->writeback_connectors && (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)) continue; if (drm_lease_held(file_priv, connector->base.id)) { if (count < card_res->count_connectors && put_user(connector->base.id, connector_id + count)) { drm_connector_list_iter_end(&conn_iter); return -EFAULT; } count++; } } card_res->count_connectors = count; drm_connector_list_iter_end(&conn_iter); return ret; } /** * drm_mode_config_reset - call ->reset callbacks * @dev: drm device * * This functions calls all the crtc's, encoder's and connector's ->reset * callback. Drivers can use this in e.g. their driver load or resume code to * reset hardware and software state. */ void drm_mode_config_reset(struct drm_device *dev) { struct drm_crtc *crtc; struct drm_colorop *colorop; struct drm_plane *plane; struct drm_encoder *encoder; struct drm_connector *connector; struct drm_connector_list_iter conn_iter; drm_for_each_colorop(colorop, dev) drm_colorop_reset(colorop); drm_for_each_plane(plane, dev) if (plane->funcs->reset) plane->funcs->reset(plane); drm_for_each_crtc(crtc, dev) if (crtc->funcs->reset) crtc->funcs->reset(crtc); drm_for_each_encoder(encoder, dev) if (encoder->funcs && encoder->funcs->reset) encoder->funcs->reset(encoder); drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) if (connector->funcs->reset) connector->funcs->reset(connector); drm_connector_list_iter_end(&conn_iter); } EXPORT_SYMBOL(drm_mode_config_reset); /* * Global properties */ static const struct drm_prop_enum_list drm_plane_type_enum_list[] = { { DRM_PLANE_TYPE_OVERLAY, "Overlay" }, { DRM_PLANE_TYPE_PRIMARY, "Primary" }, { DRM_PLANE_TYPE_CURSOR, "Cursor" }, }; static int drm_mode_create_standard_properties(struct drm_device *dev) { struct drm_property *prop; int ret; ret = drm_connector_create_standard_properties(dev); if (ret) return ret; prop = drm_property_create_enum(dev, DRM_MODE_PROP_IMMUTABLE, "type", drm_plane_type_enum_list, ARRAY_SIZE(drm_plane_type_enum_list)); if (!prop) return -ENOMEM; dev->mode_config.plane_type_property = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "SRC_X", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_src_x = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "SRC_Y", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_src_y = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "SRC_W", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_src_w = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "SRC_H", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_src_h = prop; prop = drm_property_create_signed_range(dev, DRM_MODE_PROP_ATOMIC, "CRTC_X", INT_MIN, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_x = prop; prop = drm_property_create_signed_range(dev, DRM_MODE_PROP_ATOMIC, "CRTC_Y", INT_MIN, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_y = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "CRTC_W", 0, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_w = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "CRTC_H", 0, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_h = prop; prop = drm_property_create_object(dev, DRM_MODE_PROP_ATOMIC, "FB_ID", DRM_MODE_OBJECT_FB); if (!prop) return -ENOMEM; dev->mode_config.prop_fb_id = prop; prop = drm_property_create_signed_range(dev, DRM_MODE_PROP_ATOMIC, "IN_FENCE_FD", -1, INT_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_in_fence_fd = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC, "OUT_FENCE_PTR", 0, U64_MAX); if (!prop) return -ENOMEM; dev->mode_config.prop_out_fence_ptr = prop; prop = drm_property_create_object(dev, DRM_MODE_PROP_ATOMIC, "CRTC_ID", DRM_MODE_OBJECT_CRTC); if (!prop) return -ENOMEM; dev->mode_config.prop_crtc_id = prop; prop = drm_property_create(dev, DRM_MODE_PROP_ATOMIC | DRM_MODE_PROP_BLOB, "FB_DAMAGE_CLIPS", 0); if (!prop) return -ENOMEM; dev->mode_config.prop_fb_damage_clips = prop; prop = drm_property_create_bool(dev, DRM_MODE_PROP_ATOMIC, "ACTIVE"); if (!prop) return -ENOMEM; dev->mode_config.prop_active = prop; prop = drm_property_create(dev, DRM_MODE_PROP_ATOMIC | DRM_MODE_PROP_BLOB, "MODE_ID", 0); if (!prop) return -ENOMEM; dev->mode_config.prop_mode_id = prop; prop = drm_property_create_bool(dev, 0, "VRR_ENABLED"); if (!prop) return -ENOMEM; dev->mode_config.prop_vrr_enabled = prop; prop = drm_property_create(dev, DRM_MODE_PROP_BLOB, "DEGAMMA_LUT", 0); if (!prop) return -ENOMEM; dev->mode_config.degamma_lut_property = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_IMMUTABLE, "DEGAMMA_LUT_SIZE", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.degamma_lut_size_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_BLOB, "CTM", 0); if (!prop) return -ENOMEM; dev->mode_config.ctm_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_BLOB, "GAMMA_LUT", 0); if (!prop) return -ENOMEM; dev->mode_config.gamma_lut_property = prop; prop = drm_property_create_range(dev, DRM_MODE_PROP_IMMUTABLE, "GAMMA_LUT_SIZE", 0, UINT_MAX); if (!prop) return -ENOMEM; dev->mode_config.gamma_lut_size_property = prop; prop = drm_property_create_range(dev, 0, "BACKGROUND_COLOR", 0, U64_MAX); if (!prop) return -ENOMEM; dev->mode_config.background_color_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_BLOB, "IN_FORMATS", 0); if (!prop) return -ENOMEM; dev->mode_config.modifiers_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_BLOB, "IN_FORMATS_ASYNC", 0); if (!prop) return -ENOMEM; dev->mode_config.async_modifiers_property = prop; prop = drm_property_create(dev, DRM_MODE_PROP_IMMUTABLE | DRM_MODE_PROP_BLOB, "SIZE_HINTS", 0); if (!prop) return -ENOMEM; dev->mode_config.size_hints_property = prop; return 0; } static void drm_mode_config_init_release(struct drm_device *dev, void *ptr) { drm_mode_config_cleanup(dev); } /** * drmm_mode_config_init - managed DRM mode_configuration structure * initialization * @dev: DRM device * * Initialize @dev's mode_config structure, used for tracking the graphics * configuration of @dev. * * Since this initializes the modeset locks, no locking is possible. Which is no * problem, since this should happen single threaded at init time. It is the * driver's problem to ensure this guarantee. * * Cleanup is automatically handled through registering drm_mode_config_cleanup * with drmm_add_action(). * * Returns: 0 on success, negative error value on failure. */ int drmm_mode_config_init(struct drm_device *dev) { int ret; mutex_init(&dev->mode_config.mutex); drm_modeset_lock_init(&dev->mode_config.connection_mutex); mutex_init(&dev->mode_config.idr_mutex); mutex_init(&dev->mode_config.fb_lock); mutex_init(&dev->mode_config.blob_lock); INIT_LIST_HEAD(&dev->mode_config.fb_list); INIT_LIST_HEAD(&dev->mode_config.crtc_list); INIT_LIST_HEAD(&dev->mode_config.connector_list); INIT_LIST_HEAD(&dev->mode_config.encoder_list); INIT_LIST_HEAD(&dev->mode_config.property_list); INIT_LIST_HEAD(&dev->mode_config.property_blob_list); INIT_LIST_HEAD(&dev->mode_config.plane_list); INIT_LIST_HEAD(&dev->mode_config.colorop_list); INIT_LIST_HEAD(&dev->mode_config.privobj_list); idr_init_base(&dev->mode_config.object_idr, 1); idr_init_base(&dev->mode_config.tile_idr, 1); ida_init(&dev->mode_config.connector_ida); spin_lock_init(&dev->mode_config.connector_list_lock); init_llist_head(&dev->mode_config.connector_free_list); INIT_WORK(&dev->mode_config.connector_free_work, drm_connector_free_work_fn); ret = drm_mode_create_standard_properties(dev); if (ret) { drm_mode_config_cleanup(dev); return ret; } /* Just to be sure */ dev->mode_config.num_fb = 0; dev->mode_config.num_connector = 0; dev->mode_config.num_crtc = 0; dev->mode_config.num_encoder = 0; dev->mode_config.num_total_plane = 0; dev->mode_config.num_colorop = 0; if (IS_ENABLED(CONFIG_LOCKDEP)) { struct drm_modeset_acquire_ctx modeset_ctx; struct ww_acquire_ctx resv_ctx; struct dma_resv resv; int ret; dma_resv_init(&resv); drm_modeset_acquire_init(&modeset_ctx, 0); ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &modeset_ctx); if (ret == -EDEADLK) ret = drm_modeset_backoff(&modeset_ctx); might_fault(); ww_acquire_init(&resv_ctx, &reservation_ww_class); ret = dma_resv_lock(&resv, &resv_ctx); if (ret == -EDEADLK) dma_resv_lock_slow(&resv, &resv_ctx); dma_resv_unlock(&resv); ww_acquire_fini(&resv_ctx); drm_modeset_drop_locks(&modeset_ctx); drm_modeset_acquire_fini(&modeset_ctx); dma_resv_fini(&resv); } return drmm_add_action_or_reset(dev, drm_mode_config_init_release, NULL); } EXPORT_SYMBOL(drmm_mode_config_init); /** * drm_mode_config_cleanup - free up DRM mode_config info * @dev: DRM device * * Free up all the connectors and CRTCs associated with this DRM device, then * free up the framebuffers and associated buffer objects. * * Note that since this /should/ happen single-threaded at driver/device * teardown time, no locking is required. It's the driver's job to ensure that * this guarantee actually holds true. * * FIXME: With the managed drmm_mode_config_init() it is no longer necessary for * drivers to explicitly call this function. */ void drm_mode_config_cleanup(struct drm_device *dev) { struct drm_connector *connector; struct drm_connector_list_iter conn_iter; struct drm_crtc *crtc, *ct; struct drm_encoder *encoder, *enct; struct drm_framebuffer *fb, *fbt; struct drm_property *property, *pt; struct drm_property_blob *blob, *bt; struct drm_plane *plane, *plt; struct drm_colorop *colorop, *copt; list_for_each_entry_safe(encoder, enct, &dev->mode_config.encoder_list, head) { encoder->funcs->destroy(encoder); } drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) { /* drm_connector_list_iter holds an full reference to the * current connector itself, which means it is inherently safe * against unreferencing the current connector - but not against * deleting it right away. */ drm_connector_put(connector); } drm_connector_list_iter_end(&conn_iter); /* connector_iter drops references in a work item. */ flush_work(&dev->mode_config.connector_free_work); if (WARN_ON(!list_empty(&dev->mode_config.connector_list))) { drm_connector_list_iter_begin(dev, &conn_iter); drm_for_each_connector_iter(connector, &conn_iter) DRM_ERROR("connector %s leaked!\n", connector->name); drm_connector_list_iter_end(&conn_iter); } list_for_each_entry_safe(property, pt, &dev->mode_config.property_list, head) { drm_property_destroy(dev, property); } list_for_each_entry_safe(colorop, copt, &dev->mode_config.colorop_list, head) { colorop->funcs->destroy(colorop); } list_for_each_entry_safe(plane, plt, &dev->mode_config.plane_list, head) { plane->funcs->destroy(plane); } list_for_each_entry_safe(crtc, ct, &dev->mode_config.crtc_list, head) { crtc->funcs->destroy(crtc); } list_for_each_entry_safe(blob, bt, &dev->mode_config.property_blob_list, head_global) { drm_property_blob_put(blob); } /* * Single-threaded teardown context, so it's not required to grab the * fb_lock to protect against concurrent fb_list access. Contrary, it * would actually deadlock with the drm_framebuffer_cleanup function. * * Also, if there are any framebuffers left, that's a driver leak now, * so politely WARN about this. */ WARN_ON(!list_empty(&dev->mode_config.fb_list)); list_for_each_entry_safe(fb, fbt, &dev->mode_config.fb_list, head) { struct drm_printer p = drm_dbg_printer(dev, DRM_UT_KMS, "[leaked fb]"); drm_printf(&p, "framebuffer[%u]:\n", fb->base.id); drm_framebuffer_print_info(&p, 1, fb); drm_framebuffer_free(&fb->base.refcount); } ida_destroy(&dev->mode_config.connector_ida); idr_destroy(&dev->mode_config.tile_idr); idr_destroy(&dev->mode_config.object_idr); drm_modeset_lock_fini(&dev->mode_config.connection_mutex); } EXPORT_SYMBOL(drm_mode_config_cleanup); static u32 full_encoder_mask(struct drm_device *dev) { struct drm_encoder *encoder; u32 encoder_mask = 0; drm_for_each_encoder(encoder, dev) encoder_mask |= drm_encoder_mask(encoder); return encoder_mask; } /* * For some reason we want the encoder itself included in * possible_clones. Make life easy for drivers by allowing them * to leave possible_clones unset if no cloning is possible. */ static void fixup_encoder_possible_clones(struct drm_encoder *encoder) { if (encoder->possible_clones == 0) encoder->possible_clones = drm_encoder_mask(encoder); } static void validate_encoder_possible_clones(struct drm_encoder *encoder) { struct drm_device *dev = encoder->dev; u32 encoder_mask = full_encoder_mask(dev); struct drm_encoder *other; drm_for_each_encoder(other, dev) { WARN(!!(encoder->possible_clones & drm_encoder_mask(other)) != !!(other->possible_clones & drm_encoder_mask(encoder)), "possible_clones mismatch: " "[ENCODER:%d:%s] mask=0x%x possible_clones=0x%x vs. " "[ENCODER:%d:%s] mask=0x%x possible_clones=0x%x\n", encoder->base.id, encoder->name, drm_encoder_mask(encoder), encoder->possible_clones, other->base.id, other->name, drm_encoder_mask(other), other->possible_clones); } WARN((encoder->possible_clones & drm_encoder_mask(encoder)) == 0 || (encoder->possible_clones & ~encoder_mask) != 0, "Bogus possible_clones: " "[ENCODER:%d:%s] possible_clones=0x%x (full encoder mask=0x%x)\n", encoder->base.id, encoder->name, encoder->possible_clones, encoder_mask); } static u32 full_crtc_mask(struct drm_device *dev) { struct drm_crtc *crtc; u32 crtc_mask = 0; drm_for_each_crtc(crtc, dev) crtc_mask |= drm_crtc_mask(crtc); return crtc_mask; } static void validate_encoder_possible_crtcs(struct drm_encoder *encoder) { u32 crtc_mask = full_crtc_mask(encoder->dev); WARN((encoder->possible_crtcs & crtc_mask) == 0 || (encoder->possible_crtcs & ~crtc_mask) != 0, "Bogus possible_crtcs: " "[ENCODER:%d:%s] possible_crtcs=0x%x (full crtc mask=0x%x)\n", encoder->base.id, encoder->name, encoder->possible_crtcs, crtc_mask); } void drm_mode_config_validate(struct drm_device *dev) { struct drm_encoder *encoder; struct drm_crtc *crtc; struct drm_plane *plane; u32 primary_with_crtc = 0, cursor_with_crtc = 0; unsigned int num_primary = 0; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return; drm_for_each_encoder(encoder, dev) fixup_encoder_possible_clones(encoder); drm_for_each_encoder(encoder, dev) { validate_encoder_possible_clones(encoder); validate_encoder_possible_crtcs(encoder); } drm_for_each_crtc(crtc, dev) { WARN(!crtc->primary, "Missing primary plane on [CRTC:%d:%s]\n", crtc->base.id, crtc->name); WARN(crtc->cursor && crtc->funcs->cursor_set, "[CRTC:%d:%s] must not have both a cursor plane and a cursor_set func", crtc->base.id, crtc->name); WARN(crtc->cursor && crtc->funcs->cursor_set2, "[CRTC:%d:%s] must not have both a cursor plane and a cursor_set2 func", crtc->base.id, crtc->name); WARN(crtc->cursor && crtc->funcs->cursor_move, "[CRTC:%d:%s] must not have both a cursor plane and a cursor_move func", crtc->base.id, crtc->name); if (crtc->primary) { WARN(!(crtc->primary->possible_crtcs & drm_crtc_mask(crtc)), "Bogus primary plane possible_crtcs: [PLANE:%d:%s] must be compatible with [CRTC:%d:%s]\n", crtc->primary->base.id, crtc->primary->name, crtc->base.id, crtc->name); WARN(primary_with_crtc & drm_plane_mask(crtc->primary), "Primary plane [PLANE:%d:%s] used for multiple CRTCs", crtc->primary->base.id, crtc->primary->name); primary_with_crtc |= drm_plane_mask(crtc->primary); } if (crtc->cursor) { WARN(!(crtc->cursor->possible_crtcs & drm_crtc_mask(crtc)), "Bogus cursor plane possible_crtcs: [PLANE:%d:%s] must be compatible with [CRTC:%d:%s]\n", crtc->cursor->base.id, crtc->cursor->name, crtc->base.id, crtc->name); WARN(cursor_with_crtc & drm_plane_mask(crtc->cursor), "Cursor plane [PLANE:%d:%s] used for multiple CRTCs", crtc->cursor->base.id, crtc->cursor->name); cursor_with_crtc |= drm_plane_mask(crtc->cursor); } } drm_for_each_plane(plane, dev) { if (plane->type == DRM_PLANE_TYPE_PRIMARY) num_primary++; } WARN(num_primary != dev->mode_config.num_crtc, "Must have as many primary planes as there are CRTCs, but have %u primary planes and %u CRTCs", num_primary, dev->mode_config.num_crtc); } |
| 22 3 22 112 3 108 108 108 988 992 86 605 606 58 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _PROTO_MEMORY_H #define _PROTO_MEMORY_H #include <net/sock.h> #include <net/hotdata.h> /* 1 MB per cpu, in page units */ #define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) static inline bool sk_has_memory_pressure(const struct sock *sk) { return sk->sk_prot->memory_pressure != NULL; } static inline bool proto_memory_pressure(const struct proto *prot) { if (!prot->memory_pressure) return false; return !!READ_ONCE(*prot->memory_pressure); } static inline bool sk_under_global_memory_pressure(const struct sock *sk) { return proto_memory_pressure(sk->sk_prot); } static inline bool sk_under_memory_pressure(const struct sock *sk) { if (!sk->sk_prot->memory_pressure) return false; if (mem_cgroup_sk_enabled(sk) && mem_cgroup_sk_under_memory_pressure(sk)) return true; if (sk->sk_bypass_prot_mem) return false; return !!READ_ONCE(*sk->sk_prot->memory_pressure); } static inline long proto_memory_allocated(const struct proto *prot) { return max(0L, atomic_long_read(prot->memory_allocated)); } static inline long sk_memory_allocated(const struct sock *sk) { return proto_memory_allocated(sk->sk_prot); } static inline void proto_memory_pcpu_drain(struct proto *proto) { int val = this_cpu_xchg(*proto->per_cpu_fw_alloc, 0); if (val) atomic_long_add(val, proto->memory_allocated); } static inline void sk_memory_allocated_add(const struct sock *sk, int val) { struct proto *proto = sk->sk_prot; val = this_cpu_add_return(*proto->per_cpu_fw_alloc, val); if (unlikely(val >= READ_ONCE(net_hotdata.sysctl_mem_pcpu_rsv))) proto_memory_pcpu_drain(proto); } static inline void sk_memory_allocated_sub(const struct sock *sk, int val) { struct proto *proto = sk->sk_prot; val = this_cpu_sub_return(*proto->per_cpu_fw_alloc, val); if (unlikely(val <= -READ_ONCE(net_hotdata.sysctl_mem_pcpu_rsv))) proto_memory_pcpu_drain(proto); } #endif /* _PROTO_MEMORY_H */ |
| 5 6 6 1 1 15 15 15 21 21 21 21 6 6 6 15 16 16 7 11 6 6 6 1 6 6 11 4 7 5 1 6 6 21 17 6 19 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 | // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2010-2011 EIA Electronics, // Kurt Van Dijck <kurt.van.dijck@eia.be> // Copyright (c) 2017-2019 Pengutronix, // Marc Kleine-Budde <kernel@pengutronix.de> // Copyright (c) 2017-2019 Pengutronix, // Oleksij Rempel <kernel@pengutronix.de> /* bus for j1939 remote devices * Since rtnetlink, no real bus is used. */ #include <net/sock.h> #include "j1939-priv.h" static void __j1939_ecu_release(struct kref *kref) { struct j1939_ecu *ecu = container_of(kref, struct j1939_ecu, kref); struct j1939_priv *priv = ecu->priv; list_del(&ecu->list); kfree(ecu); j1939_priv_put(priv); } void j1939_ecu_put(struct j1939_ecu *ecu) { kref_put(&ecu->kref, __j1939_ecu_release); } static void j1939_ecu_get(struct j1939_ecu *ecu) { kref_get(&ecu->kref); } static bool j1939_ecu_is_mapped_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; lockdep_assert_held(&priv->lock); return j1939_ecu_find_by_addr_locked(priv, ecu->addr) == ecu; } /* ECU device interface */ /* map ECU to a bus address space */ static void j1939_ecu_map_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; struct j1939_addr_ent *ent; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(ecu->addr)) return; ent = &priv->ents[ecu->addr]; if (ent->ecu) { netdev_warn(priv->ndev, "Trying to map already mapped ECU, addr: 0x%02x, name: 0x%016llx. Skip it.\n", ecu->addr, ecu->name); return; } j1939_ecu_get(ecu); ent->ecu = ecu; ent->nusers += ecu->nusers; } /* unmap ECU from a bus address space */ void j1939_ecu_unmap_locked(struct j1939_ecu *ecu) { struct j1939_priv *priv = ecu->priv; struct j1939_addr_ent *ent; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(ecu->addr)) return; if (!j1939_ecu_is_mapped_locked(ecu)) return; ent = &priv->ents[ecu->addr]; ent->ecu = NULL; ent->nusers -= ecu->nusers; j1939_ecu_put(ecu); } void j1939_ecu_unmap(struct j1939_ecu *ecu) { write_lock_bh(&ecu->priv->lock); j1939_ecu_unmap_locked(ecu); write_unlock_bh(&ecu->priv->lock); } void j1939_ecu_unmap_all(struct j1939_priv *priv) { int i; write_lock_bh(&priv->lock); for (i = 0; i < ARRAY_SIZE(priv->ents); i++) if (priv->ents[i].ecu) j1939_ecu_unmap_locked(priv->ents[i].ecu); write_unlock_bh(&priv->lock); } void j1939_ecu_timer_start(struct j1939_ecu *ecu) { /* The ECU is held here and released in the * j1939_ecu_timer_handler() or j1939_ecu_timer_cancel(). */ j1939_ecu_get(ecu); /* Schedule timer in 250 msec to commit address change. */ hrtimer_start(&ecu->ac_timer, ms_to_ktime(250), HRTIMER_MODE_REL_SOFT); } void j1939_ecu_timer_cancel(struct j1939_ecu *ecu) { if (hrtimer_cancel(&ecu->ac_timer)) j1939_ecu_put(ecu); } static enum hrtimer_restart j1939_ecu_timer_handler(struct hrtimer *hrtimer) { struct j1939_ecu *ecu = container_of(hrtimer, struct j1939_ecu, ac_timer); struct j1939_priv *priv = ecu->priv; write_lock_bh(&priv->lock); /* TODO: can we test if ecu->addr is unicast before starting * the timer? */ j1939_ecu_map_locked(ecu); /* The corresponding j1939_ecu_get() is in * j1939_ecu_timer_start(). */ j1939_ecu_put(ecu); write_unlock_bh(&priv->lock); return HRTIMER_NORESTART; } struct j1939_ecu *j1939_ecu_create_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); ecu = kzalloc_obj(*ecu, gfp_any()); if (!ecu) return ERR_PTR(-ENOMEM); kref_init(&ecu->kref); ecu->addr = J1939_IDLE_ADDR; ecu->name = name; hrtimer_setup(&ecu->ac_timer, j1939_ecu_timer_handler, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); INIT_LIST_HEAD(&ecu->list); j1939_priv_get(priv); ecu->priv = priv; list_add_tail(&ecu->list, &priv->ecus); return ecu; } struct j1939_ecu *j1939_ecu_find_by_addr_locked(struct j1939_priv *priv, u8 addr) { lockdep_assert_held(&priv->lock); return priv->ents[addr].ecu; } struct j1939_ecu *j1939_ecu_get_by_addr_locked(struct j1939_priv *priv, u8 addr) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); if (!j1939_address_is_unicast(addr)) return NULL; ecu = j1939_ecu_find_by_addr_locked(priv, addr); if (ecu) j1939_ecu_get(ecu); return ecu; } struct j1939_ecu *j1939_ecu_get_by_addr(struct j1939_priv *priv, u8 addr) { struct j1939_ecu *ecu; read_lock_bh(&priv->lock); ecu = j1939_ecu_get_by_addr_locked(priv, addr); read_unlock_bh(&priv->lock); return ecu; } /* get pointer to ecu without increasing ref counter */ static struct j1939_ecu *j1939_ecu_find_by_name_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); list_for_each_entry(ecu, &priv->ecus, list) { if (ecu->name == name) return ecu; } return NULL; } struct j1939_ecu *j1939_ecu_get_by_name_locked(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; lockdep_assert_held(&priv->lock); if (!name) return NULL; ecu = j1939_ecu_find_by_name_locked(priv, name); if (ecu) j1939_ecu_get(ecu); return ecu; } struct j1939_ecu *j1939_ecu_get_by_name(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; read_lock_bh(&priv->lock); ecu = j1939_ecu_get_by_name_locked(priv, name); read_unlock_bh(&priv->lock); return ecu; } u8 j1939_name_to_addr(struct j1939_priv *priv, name_t name) { struct j1939_ecu *ecu; int addr = J1939_IDLE_ADDR; if (!name) return J1939_NO_ADDR; read_lock_bh(&priv->lock); ecu = j1939_ecu_find_by_name_locked(priv, name); if (ecu && j1939_ecu_is_mapped_locked(ecu)) /* ecu's SA is registered */ addr = ecu->addr; read_unlock_bh(&priv->lock); return addr; } /* TX addr/name accounting * Transport protocol needs to know if a SA is local or not * These functions originate from userspace manipulating sockets, * so locking is straigforward */ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) { struct j1939_ecu *ecu; int err = 0; write_lock_bh(&priv->lock); if (j1939_address_is_unicast(sa)) priv->ents[sa].nusers++; if (!name) goto done; ecu = j1939_ecu_get_by_name_locked(priv, name); if (!ecu) ecu = j1939_ecu_create_locked(priv, name); err = PTR_ERR_OR_ZERO(ecu); if (err) { if (j1939_address_is_unicast(sa)) priv->ents[sa].nusers--; goto done; } ecu->nusers++; /* TODO: do we care if ecu->addr != sa? */ if (j1939_ecu_is_mapped_locked(ecu)) /* ecu's sa is active already */ priv->ents[ecu->addr].nusers++; done: write_unlock_bh(&priv->lock); return err; } void j1939_local_ecu_put(struct j1939_priv *priv, name_t name, u8 sa) { struct j1939_ecu *ecu; write_lock_bh(&priv->lock); if (j1939_address_is_unicast(sa)) priv->ents[sa].nusers--; if (!name) goto done; ecu = j1939_ecu_find_by_name_locked(priv, name); if (WARN_ON_ONCE(!ecu)) goto done; ecu->nusers--; /* TODO: do we care if ecu->addr != sa? */ if (j1939_ecu_is_mapped_locked(ecu)) /* ecu's sa is active already */ priv->ents[ecu->addr].nusers--; j1939_ecu_put(ecu); done: write_unlock_bh(&priv->lock); } |
| 112 112 112 95 39 113 110 8 8 8 8 8 8 2 2 2 2 2 18 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 | // SPDX-License-Identifier: GPL-2.0 /* * Block stat tracking code * * Copyright (C) 2016 Jens Axboe */ #include <linux/kernel.h> #include <linux/rculist.h> #include "blk-stat.h" #include "blk-mq.h" #include "blk.h" struct blk_queue_stats { struct list_head callbacks; spinlock_t lock; int accounting; }; void blk_rq_stat_init(struct blk_rq_stat *stat) { stat->min = -1ULL; stat->max = stat->nr_samples = stat->mean = 0; stat->batch = 0; } /* src is a per-cpu stat, mean isn't initialized */ void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { if (dst->nr_samples + src->nr_samples <= dst->nr_samples) return; dst->min = min(dst->min, src->min); dst->max = max(dst->max, src->max); dst->mean = div_u64(src->batch + dst->mean * dst->nr_samples, dst->nr_samples + src->nr_samples); dst->nr_samples += src->nr_samples; } void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value) { stat->min = min(stat->min, value); stat->max = max(stat->max, value); stat->batch += value; stat->nr_samples++; } void blk_stat_add(struct request *rq, u64 now) { struct request_queue *q = rq->q; struct blk_stat_callback *cb; struct blk_rq_stat *stat; int bucket, cpu; u64 value; value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0; rcu_read_lock(); cpu = get_cpu(); list_for_each_entry_rcu(cb, &q->stats->callbacks, list) { if (!blk_stat_is_active(cb)) continue; bucket = cb->bucket_fn(rq); if (bucket < 0) continue; stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket]; blk_rq_stat_add(stat, value); } put_cpu(); rcu_read_unlock(); } static void blk_stat_timer_fn(struct timer_list *t) { struct blk_stat_callback *cb = timer_container_of(cb, t, timer); unsigned int bucket; int cpu; for (bucket = 0; bucket < cb->buckets; bucket++) blk_rq_stat_init(&cb->stat[bucket]); for_each_online_cpu(cpu) { struct blk_rq_stat *cpu_stat; cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu); for (bucket = 0; bucket < cb->buckets; bucket++) { blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]); blk_rq_stat_init(&cpu_stat[bucket]); } } cb->timer_fn(cb); } struct blk_stat_callback * blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *), int (*bucket_fn)(const struct request *), unsigned int buckets, void *data) { struct blk_stat_callback *cb; cb = kmalloc_obj(*cb); if (!cb) return NULL; cb->stat = kmalloc_objs(struct blk_rq_stat, buckets); if (!cb->stat) { kfree(cb); return NULL; } cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat), __alignof__(struct blk_rq_stat)); if (!cb->cpu_stat) { kfree(cb->stat); kfree(cb); return NULL; } cb->timer_fn = timer_fn; cb->bucket_fn = bucket_fn; cb->data = data; cb->buckets = buckets; timer_setup(&cb->timer, blk_stat_timer_fn, 0); return cb; } void blk_stat_add_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned int bucket; unsigned long flags; int cpu; for_each_possible_cpu(cpu) { struct blk_rq_stat *cpu_stat; cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu); for (bucket = 0; bucket < cb->buckets; bucket++) blk_rq_stat_init(&cpu_stat[bucket]); } spin_lock_irqsave(&q->stats->lock, flags); list_add_tail_rcu(&cb->list, &q->stats->callbacks); blk_queue_flag_set(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } void blk_stat_remove_callback(struct request_queue *q, struct blk_stat_callback *cb) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); list_del_rcu(&cb->list); if (list_empty(&q->stats->callbacks) && !q->stats->accounting) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); timer_delete_sync(&cb->timer); } static void blk_stat_free_callback_rcu(struct rcu_head *head) { struct blk_stat_callback *cb; cb = container_of(head, struct blk_stat_callback, rcu); free_percpu(cb->cpu_stat); kfree(cb->stat); kfree(cb); } void blk_stat_free_callback(struct blk_stat_callback *cb) { if (cb) call_rcu(&cb->rcu, blk_stat_free_callback_rcu); } void blk_stat_disable_accounting(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); if (!--q->stats->accounting && list_empty(&q->stats->callbacks)) blk_queue_flag_clear(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_disable_accounting); void blk_stat_enable_accounting(struct request_queue *q) { unsigned long flags; spin_lock_irqsave(&q->stats->lock, flags); if (!q->stats->accounting++ && list_empty(&q->stats->callbacks)) blk_queue_flag_set(QUEUE_FLAG_STATS, q); spin_unlock_irqrestore(&q->stats->lock, flags); } EXPORT_SYMBOL_GPL(blk_stat_enable_accounting); struct blk_queue_stats *blk_alloc_queue_stats(void) { struct blk_queue_stats *stats; stats = kmalloc_obj(*stats); if (!stats) return NULL; INIT_LIST_HEAD(&stats->callbacks); spin_lock_init(&stats->lock); stats->accounting = 0; return stats; } void blk_free_queue_stats(struct blk_queue_stats *stats) { if (!stats) return; WARN_ON(!list_empty(&stats->callbacks)); kfree(stats); } |
| 2 10 3 6 2 153 157 76 58 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2009-2021 Christoph Hellwig * * NOTE: none of these tracepoints shall be considered a stable kernel ABI * as they can change at any time. * * Current conventions for printing numbers measuring specific units: * * offset: byte offset into a subcomponent of a file operation * pos: file offset, in bytes * length: length of a file operation, in bytes * ino: inode number * * Numbers describing space allocations should be formatted in hexadecimal. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM iomap #if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define _IOMAP_TRACE_H #include <linux/tracepoint.h> struct inode; DECLARE_EVENT_CLASS(iomap_readpage_class, TP_PROTO(struct inode *inode, int nr_pages), TP_ARGS(inode, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(int, nr_pages) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_pages = nr_pages; ), TP_printk("dev %d:%d ino 0x%llx nr_pages %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->nr_pages) ) #define DEFINE_READPAGE_EVENT(name) \ DEFINE_EVENT(iomap_readpage_class, name, \ TP_PROTO(struct inode *inode, int nr_pages), \ TP_ARGS(inode, nr_pages)) DEFINE_READPAGE_EVENT(iomap_readpage); DEFINE_READPAGE_EVENT(iomap_readahead); DECLARE_EVENT_CLASS(iomap_range_class, TP_PROTO(struct inode *inode, loff_t off, u64 len), TP_ARGS(inode, off, len), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, size) __field(loff_t, offset) __field(u64, length) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->size = i_size_read(inode); __entry->offset = off; __entry->length = len; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx length 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->offset, __entry->length) ) #define DEFINE_RANGE_EVENT(name) \ DEFINE_EVENT(iomap_range_class, name, \ TP_PROTO(struct inode *inode, loff_t off, u64 len),\ TP_ARGS(inode, off, len)) DEFINE_RANGE_EVENT(iomap_writeback_folio); DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); DEFINE_RANGE_EVENT(iomap_dio_rw_queued); DEFINE_RANGE_EVENT(iomap_zero_iter); #define IOMAP_TYPE_STRINGS \ { IOMAP_HOLE, "HOLE" }, \ { IOMAP_DELALLOC, "DELALLOC" }, \ { IOMAP_MAPPED, "MAPPED" }, \ { IOMAP_UNWRITTEN, "UNWRITTEN" }, \ { IOMAP_INLINE, "INLINE" } #define IOMAP_FLAGS_STRINGS \ { IOMAP_WRITE, "WRITE" }, \ { IOMAP_ZERO, "ZERO" }, \ { IOMAP_REPORT, "REPORT" }, \ { IOMAP_FAULT, "FAULT" }, \ { IOMAP_DIRECT, "DIRECT" }, \ { IOMAP_NOWAIT, "NOWAIT" }, \ { IOMAP_OVERWRITE_ONLY, "OVERWRITE_ONLY" }, \ { IOMAP_UNSHARE, "UNSHARE" }, \ { IOMAP_DAX, "DAX" }, \ { IOMAP_ATOMIC, "ATOMIC" }, \ { IOMAP_DONTCACHE, "DONTCACHE" } #define IOMAP_F_FLAGS_STRINGS \ { IOMAP_F_NEW, "NEW" }, \ { IOMAP_F_DIRTY, "DIRTY" }, \ { IOMAP_F_SHARED, "SHARED" }, \ { IOMAP_F_MERGED, "MERGED" }, \ { IOMAP_F_BUFFER_HEAD, "BH" }, \ { IOMAP_F_XATTR, "XATTR" }, \ { IOMAP_F_BOUNDARY, "BOUNDARY" }, \ { IOMAP_F_ANON_WRITE, "ANON_WRITE" }, \ { IOMAP_F_ATOMIC_BIO, "ATOMIC_BIO" }, \ { IOMAP_F_PRIVATE, "PRIVATE" }, \ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" }, \ { IOMAP_F_STALE, "STALE" } #define IOMAP_DIO_STRINGS \ {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" }, \ {IOMAP_DIO_FSBLOCK_ALIGNED, "DIO_FSBLOCK_ALIGNED" } DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), TP_ARGS(inode, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr 0x%llx offset 0x%llx " "length 0x%llx type %s (0x%x) flags %s (0x%x)", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __entry->type, __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS), __entry->flags) ) #define DEFINE_IOMAP_EVENT(name) \ DEFINE_EVENT(iomap_class, name, \ TP_PROTO(struct inode *inode, struct iomap *iomap), \ TP_ARGS(inode, iomap)) DEFINE_IOMAP_EVENT(iomap_iter_dstmap); DEFINE_IOMAP_EVENT(iomap_iter_srcmap); TRACE_EVENT(iomap_add_to_ioend, TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len, struct iomap *iomap), TP_ARGS(inode, pos, dirty_len, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, pos) __field(u64, dirty_len) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->dirty_len = dirty_len; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d pos 0x%llx dirty len 0x%llx " "addr 0x%llx offset 0x%llx length 0x%llx type %s (0x%x) flags %s (0x%x)", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->pos, __entry->dirty_len, __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __entry->type, __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS), __entry->flags) ); TRACE_EVENT(iomap_iter, TP_PROTO(struct iomap_iter *iter, const void *ops, unsigned long caller), TP_ARGS(iter, ops, caller), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, pos) __field(u64, length) __field(int, status) __field(unsigned int, flags) __field(const void *, ops) __field(unsigned long, caller) ), TP_fast_assign( __entry->dev = iter->inode->i_sb->s_dev; __entry->ino = iter->inode->i_ino; __entry->pos = iter->pos; __entry->length = iomap_length(iter); __entry->status = iter->status; __entry->flags = iter->flags; __entry->ops = ops; __entry->caller = caller; ), TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx status %d flags %s (0x%x) ops %ps caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->length, __entry->status, __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS), __entry->flags, __entry->ops, (void *)__entry->caller) ); TRACE_EVENT(iomap_dio_rw_begin, TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, unsigned int dio_flags, size_t done_before), TP_ARGS(iocb, iter, dio_flags, done_before), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, isize) __field(loff_t, pos) __field(size_t, count) __field(size_t, done_before) __field(int, ki_flags) __field(unsigned int, dio_flags) __field(bool, aio) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->isize = file_inode(iocb->ki_filp)->i_size; __entry->pos = iocb->ki_pos; __entry->count = iov_iter_count(iter); __entry->done_before = done_before; __entry->ki_flags = iocb->ki_flags; __entry->dio_flags = dio_flags; __entry->aio = !is_sync_kiocb(iocb); ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx length 0x%zx done_before 0x%zx flags %s dio_flags %s aio %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->pos, __entry->count, __entry->done_before, __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), __print_flags(__entry->dio_flags, "|", IOMAP_DIO_STRINGS), __entry->aio) ); TRACE_EVENT(iomap_dio_complete, TP_PROTO(struct kiocb *iocb, int error, ssize_t ret), TP_ARGS(iocb, error, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, isize) __field(loff_t, pos) __field(int, ki_flags) __field(bool, aio) __field(int, error) __field(ssize_t, ret) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->isize = file_inode(iocb->ki_filp)->i_size; __entry->pos = iocb->ki_pos; __entry->ki_flags = iocb->ki_flags; __entry->aio = !is_sync_kiocb(iocb); __entry->error = error; __entry->ret = ret; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx flags %s aio %d error %d ret %zd", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->pos, __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), __entry->aio, __entry->error, __entry->ret) ); #endif /* _IOMAP_TRACE_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 3 9 1 1 1 1 116 116 1 116 1 78 61 116 77 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Synchronous Compression operations * * Copyright 2015 LG Electronics Inc. * Copyright (c) 2016, Intel Corporation * Author: Giovanni Cabiddu <giovanni.cabiddu@intel.com> */ #include <crypto/internal/scompress.h> #include <crypto/scatterwalk.h> #include <linux/cpumask.h> #include <linux/cryptouser.h> #include <linux/err.h> #include <linux/highmem.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/overflow.h> #include <linux/scatterlist.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/workqueue.h> #include <net/netlink.h> #include "compress.h" struct scomp_scratch { spinlock_t lock; union { void *src __guarded_by(&lock); unsigned long saddr __guarded_by(&lock); }; }; static DEFINE_PER_CPU(struct scomp_scratch, scomp_scratch) = { .lock = __SPIN_LOCK_UNLOCKED(scomp_scratch.lock), }; static const struct crypto_type crypto_scomp_type; static DEFINE_MUTEX(scomp_lock); static int scomp_scratch_users __guarded_by(&scomp_lock); static cpumask_t scomp_scratch_want; static void scomp_scratch_workfn(struct work_struct *work); static DECLARE_WORK(scomp_scratch_work, scomp_scratch_workfn); static int __maybe_unused crypto_scomp_report( struct sk_buff *skb, struct crypto_alg *alg) { struct crypto_report_comp rscomp; memset(&rscomp, 0, sizeof(rscomp)); strscpy(rscomp.type, "scomp", sizeof(rscomp.type)); return nla_put(skb, CRYPTOCFGA_REPORT_COMPRESS, sizeof(rscomp), &rscomp); } static void __maybe_unused crypto_scomp_show(struct seq_file *m, struct crypto_alg *alg) { seq_puts(m, "type : scomp\n"); } static void crypto_scomp_free_scratches(void) __context_unsafe(/* frees @scratch */) { struct scomp_scratch *scratch; int i; for_each_possible_cpu(i) { scratch = per_cpu_ptr(&scomp_scratch, i); free_page(scratch->saddr); scratch->src = NULL; } } static int scomp_alloc_scratch(struct scomp_scratch *scratch, int cpu) { int node = cpu_to_node(cpu); struct page *page; page = alloc_pages_node(node, GFP_KERNEL, 0); if (!page) return -ENOMEM; spin_lock_bh(&scratch->lock); scratch->src = page_address(page); spin_unlock_bh(&scratch->lock); return 0; } static void scomp_scratch_workfn(struct work_struct *work) { int cpu; for_each_cpu(cpu, &scomp_scratch_want) { struct scomp_scratch *scratch; scratch = per_cpu_ptr(&scomp_scratch, cpu); if (context_unsafe(scratch->src)) continue; if (scomp_alloc_scratch(scratch, cpu)) break; cpumask_clear_cpu(cpu, &scomp_scratch_want); } } static int crypto_scomp_alloc_scratches(void) __context_unsafe(/* allocates @scratch */) { unsigned int i = cpumask_first(cpu_possible_mask); struct scomp_scratch *scratch; scratch = per_cpu_ptr(&scomp_scratch, i); return scomp_alloc_scratch(scratch, i); } static int crypto_scomp_init_tfm(struct crypto_tfm *tfm) { struct scomp_alg *alg = crypto_scomp_alg(__crypto_scomp_tfm(tfm)); int ret = 0; mutex_lock(&scomp_lock); ret = crypto_acomp_alloc_streams(&alg->streams); if (ret) goto unlock; if (!scomp_scratch_users++) { ret = crypto_scomp_alloc_scratches(); if (ret) scomp_scratch_users--; } unlock: mutex_unlock(&scomp_lock); return ret; } #define scomp_lock_scratch(...) __acquire_ret(_scomp_lock_scratch(__VA_ARGS__), &__ret->lock) static struct scomp_scratch *_scomp_lock_scratch(void) __acquires_ret { int cpu = raw_smp_processor_id(); struct scomp_scratch *scratch; scratch = per_cpu_ptr(&scomp_scratch, cpu); spin_lock(&scratch->lock); if (likely(scratch->src)) return scratch; spin_unlock(&scratch->lock); cpumask_set_cpu(cpu, &scomp_scratch_want); schedule_work(&scomp_scratch_work); scratch = per_cpu_ptr(&scomp_scratch, cpumask_first(cpu_possible_mask)); spin_lock(&scratch->lock); return scratch; } static inline void scomp_unlock_scratch(struct scomp_scratch *scratch) __releases(&scratch->lock) { spin_unlock(&scratch->lock); } static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir) { struct crypto_acomp *tfm = crypto_acomp_reqtfm(req); struct crypto_scomp **tfm_ctx = acomp_tfm_ctx(tfm); bool src_isvirt = acomp_request_src_isvirt(req); bool dst_isvirt = acomp_request_dst_isvirt(req); struct crypto_scomp *scomp = *tfm_ctx; unsigned int slen = req->slen; unsigned int dlen = req->dlen; struct page *spage, *dpage; unsigned int n; const u8 *src; size_t soff; size_t doff; u8 *dst; int ret; if (!req->src || !slen) return -EINVAL; if (!req->dst || !dlen) return -EINVAL; if (dst_isvirt) dst = req->dvirt; else { if (dlen <= req->dst->length) { dpage = sg_page(req->dst); doff = req->dst->offset; } else return -ENOSYS; dpage += doff / PAGE_SIZE; doff = offset_in_page(doff); n = (dlen - 1) / PAGE_SIZE; n += (offset_in_page(dlen - 1) + doff) / PAGE_SIZE; if (PageHighMem(dpage + n) && size_add(doff, dlen) > PAGE_SIZE) return -ENOSYS; dst = kmap_local_page(dpage) + doff; } if (src_isvirt) src = req->svirt; else { src = NULL; do { if (slen <= req->src->length) { spage = sg_page(req->src); soff = req->src->offset; } else break; spage = spage + soff / PAGE_SIZE; soff = offset_in_page(soff); n = (slen - 1) / PAGE_SIZE; n += (offset_in_page(slen - 1) + soff) / PAGE_SIZE; if (PageHighMem(spage + n) && size_add(soff, slen) > PAGE_SIZE) break; src = kmap_local_page(spage) + soff; } while (0); } struct crypto_acomp_stream *stream = crypto_acomp_lock_stream_bh(&crypto_scomp_alg(scomp)->streams); if (!src_isvirt && !src) { struct scomp_scratch *scratch = scomp_lock_scratch(); const u8 *src = scratch->src; memcpy_from_sglist(scratch->src, req->src, 0, slen); if (dir) ret = crypto_scomp_compress(scomp, src, slen, dst, &dlen, stream->ctx); else ret = crypto_scomp_decompress(scomp, src, slen, dst, &dlen, stream->ctx); scomp_unlock_scratch(scratch); } else if (dir) ret = crypto_scomp_compress(scomp, src, slen, dst, &dlen, stream->ctx); else ret = crypto_scomp_decompress(scomp, src, slen, dst, &dlen, stream->ctx); crypto_acomp_unlock_stream_bh(stream); req->dlen = dlen; if (!src_isvirt && src) kunmap_local(src); if (!dst_isvirt) { kunmap_local(dst); dlen += doff; for (;;) { flush_dcache_page(dpage); if (dlen <= PAGE_SIZE) break; dlen -= PAGE_SIZE; dpage++; } } return ret; } static int scomp_acomp_compress(struct acomp_req *req) { return scomp_acomp_comp_decomp(req, 1); } static int scomp_acomp_decompress(struct acomp_req *req) { return scomp_acomp_comp_decomp(req, 0); } static void crypto_exit_scomp_ops_async(struct crypto_tfm *tfm) { struct crypto_scomp **ctx = crypto_tfm_ctx(tfm); crypto_free_scomp(*ctx); flush_work(&scomp_scratch_work); mutex_lock(&scomp_lock); if (!--scomp_scratch_users) crypto_scomp_free_scratches(); mutex_unlock(&scomp_lock); } int crypto_init_scomp_ops_async(struct crypto_tfm *tfm) { struct crypto_alg *calg = tfm->__crt_alg; struct crypto_acomp *crt = __crypto_acomp_tfm(tfm); struct crypto_scomp **ctx = crypto_tfm_ctx(tfm); struct crypto_scomp *scomp; if (!crypto_mod_get(calg)) return -EAGAIN; scomp = crypto_create_tfm(calg, &crypto_scomp_type); if (IS_ERR(scomp)) { crypto_mod_put(calg); return PTR_ERR(scomp); } *ctx = scomp; tfm->exit = crypto_exit_scomp_ops_async; crt->compress = scomp_acomp_compress; crt->decompress = scomp_acomp_decompress; return 0; } static void crypto_scomp_destroy(struct crypto_alg *alg) { struct scomp_alg *scomp = __crypto_scomp_alg(alg); crypto_acomp_free_streams(&scomp->streams); } static const struct crypto_type crypto_scomp_type = { .extsize = crypto_alg_extsize, .init_tfm = crypto_scomp_init_tfm, .destroy = crypto_scomp_destroy, #ifdef CONFIG_PROC_FS .show = crypto_scomp_show, #endif #if IS_ENABLED(CONFIG_CRYPTO_USER) .report = crypto_scomp_report, #endif .maskclear = ~CRYPTO_ALG_TYPE_MASK, .maskset = CRYPTO_ALG_TYPE_MASK, .type = CRYPTO_ALG_TYPE_SCOMPRESS, .tfmsize = offsetof(struct crypto_scomp, base), .algsize = offsetof(struct scomp_alg, base), }; static void scomp_prepare_alg(struct scomp_alg *alg) { struct crypto_alg *base = &alg->calg.base; comp_prepare_alg(&alg->calg); base->cra_flags |= CRYPTO_ALG_REQ_VIRT; } int crypto_register_scomp(struct scomp_alg *alg) { struct crypto_alg *base = &alg->calg.base; scomp_prepare_alg(alg); base->cra_type = &crypto_scomp_type; base->cra_flags |= CRYPTO_ALG_TYPE_SCOMPRESS; return crypto_register_alg(base); } EXPORT_SYMBOL_GPL(crypto_register_scomp); void crypto_unregister_scomp(struct scomp_alg *alg) { crypto_unregister_alg(&alg->base); } EXPORT_SYMBOL_GPL(crypto_unregister_scomp); int crypto_register_scomps(struct scomp_alg *algs, int count) { int i, ret; for (i = 0; i < count; i++) { ret = crypto_register_scomp(&algs[i]); if (ret) { crypto_unregister_scomps(algs, i); return ret; } } return 0; } EXPORT_SYMBOL_GPL(crypto_register_scomps); void crypto_unregister_scomps(struct scomp_alg *algs, int count) { int i; for (i = count - 1; i >= 0; --i) crypto_unregister_scomp(&algs[i]); } EXPORT_SYMBOL_GPL(crypto_unregister_scomps); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Synchronous compression type"); |
| 7 3 1 2 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) International Business Machines Corp., 2006 * * Author: Artem Bityutskiy (Битюцкий Артём) */ /* This file mostly implements UBI kernel API functions */ #include <linux/module.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/fs.h> #include <asm/div64.h> #include "ubi.h" /** * ubi_do_get_device_info - get information about UBI device. * @ubi: UBI device description object * @di: the information is stored here * * This function is the same as 'ubi_get_device_info()', but it assumes the UBI * device is locked and cannot disappear. */ void ubi_do_get_device_info(struct ubi_device *ubi, struct ubi_device_info *di) { di->ubi_num = ubi->ubi_num; di->leb_size = ubi->leb_size; di->leb_start = ubi->leb_start; di->min_io_size = ubi->min_io_size; di->max_write_size = ubi->max_write_size; di->ro_mode = ubi->ro_mode; di->cdev = ubi->cdev.dev; } EXPORT_SYMBOL_GPL(ubi_do_get_device_info); /** * ubi_get_device_info - get information about UBI device. * @ubi_num: UBI device number * @di: the information is stored here * * This function returns %0 in case of success, %-EINVAL if the UBI device * number is invalid, and %-ENODEV if there is no such UBI device. */ int ubi_get_device_info(int ubi_num, struct ubi_device_info *di) { struct ubi_device *ubi; if (ubi_num < 0 || ubi_num >= UBI_MAX_DEVICES) return -EINVAL; ubi = ubi_get_device(ubi_num); if (!ubi) return -ENODEV; ubi_do_get_device_info(ubi, di); ubi_put_device(ubi); return 0; } EXPORT_SYMBOL_GPL(ubi_get_device_info); /** * ubi_do_get_volume_info - get information about UBI volume. * @ubi: UBI device description object * @vol: volume description object * @vi: the information is stored here */ void ubi_do_get_volume_info(struct ubi_device *ubi, struct ubi_volume *vol, struct ubi_volume_info *vi) { vi->vol_id = vol->vol_id; vi->ubi_num = ubi->ubi_num; vi->size = vol->reserved_pebs; vi->used_bytes = vol->used_bytes; vi->vol_type = vol->vol_type; vi->corrupted = vol->corrupted; vi->upd_marker = vol->upd_marker; vi->alignment = vol->alignment; vi->usable_leb_size = vol->usable_leb_size; vi->name_len = vol->name_len; vi->name = vol->name; vi->cdev = vol->cdev.dev; vi->dev = &vol->dev; } /** * ubi_get_volume_info - get information about UBI volume. * @desc: volume descriptor * @vi: the information is stored here */ void ubi_get_volume_info(struct ubi_volume_desc *desc, struct ubi_volume_info *vi) { ubi_do_get_volume_info(desc->vol->ubi, desc->vol, vi); } EXPORT_SYMBOL_GPL(ubi_get_volume_info); /** * ubi_open_volume - open UBI volume. * @ubi_num: UBI device number * @vol_id: volume ID * @mode: open mode * * The @mode parameter specifies if the volume should be opened in read-only * mode, read-write mode, or exclusive mode. The exclusive mode guarantees that * nobody else will be able to open this volume. UBI allows to have many volume * readers and one writer at a time. * * If a static volume is being opened for the first time since boot, it will be * checked by this function, which means it will be fully read and the CRC * checksum of each logical eraseblock will be checked. * * This function returns volume descriptor in case of success and a negative * error code in case of failure. */ struct ubi_volume_desc *ubi_open_volume(int ubi_num, int vol_id, int mode) { int err; struct ubi_volume_desc *desc; struct ubi_device *ubi; struct ubi_volume *vol; dbg_gen("open device %d, volume %d, mode %d", ubi_num, vol_id, mode); if (ubi_num < 0 || ubi_num >= UBI_MAX_DEVICES) return ERR_PTR(-EINVAL); if (mode != UBI_READONLY && mode != UBI_READWRITE && mode != UBI_EXCLUSIVE && mode != UBI_METAONLY) return ERR_PTR(-EINVAL); /* * First of all, we have to get the UBI device to prevent its removal. */ ubi = ubi_get_device(ubi_num); if (!ubi) return ERR_PTR(-ENODEV); if (vol_id < 0 || vol_id >= ubi->vtbl_slots) { err = -EINVAL; goto out_put_ubi; } desc = kmalloc_obj(struct ubi_volume_desc); if (!desc) { err = -ENOMEM; goto out_put_ubi; } err = -ENODEV; if (!try_module_get(THIS_MODULE)) goto out_free; spin_lock(&ubi->volumes_lock); vol = ubi->volumes[vol_id]; if (!vol || vol->is_dead) goto out_unlock; err = -EBUSY; switch (mode) { case UBI_READONLY: if (vol->exclusive) goto out_unlock; vol->readers += 1; break; case UBI_READWRITE: if (vol->exclusive || vol->writers > 0) goto out_unlock; vol->writers += 1; break; case UBI_EXCLUSIVE: if (vol->exclusive || vol->writers || vol->readers || vol->metaonly) goto out_unlock; vol->exclusive = 1; break; case UBI_METAONLY: if (vol->metaonly || vol->exclusive) goto out_unlock; vol->metaonly = 1; break; } get_device(&vol->dev); vol->ref_count += 1; spin_unlock(&ubi->volumes_lock); desc->vol = vol; desc->mode = mode; mutex_lock(&ubi->ckvol_mutex); if (!vol->checked && !vol->skip_check) { /* This is the first open - check the volume */ err = ubi_check_volume(ubi, vol_id); if (err < 0) { mutex_unlock(&ubi->ckvol_mutex); ubi_close_volume(desc); return ERR_PTR(err); } if (err == 1) { ubi_warn(ubi, "volume %d on UBI device %d is corrupted", vol_id, ubi->ubi_num); vol->corrupted = 1; } vol->checked = 1; } mutex_unlock(&ubi->ckvol_mutex); return desc; out_unlock: spin_unlock(&ubi->volumes_lock); module_put(THIS_MODULE); out_free: kfree(desc); out_put_ubi: ubi_err(ubi, "cannot open device %d, volume %d, error %d", ubi_num, vol_id, err); ubi_put_device(ubi); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(ubi_open_volume); /** * ubi_open_volume_nm - open UBI volume by name. * @ubi_num: UBI device number * @name: volume name * @mode: open mode * * This function is similar to 'ubi_open_volume()', but opens a volume by name. */ struct ubi_volume_desc *ubi_open_volume_nm(int ubi_num, const char *name, int mode) { int i, vol_id = -1, len; struct ubi_device *ubi; struct ubi_volume_desc *ret; dbg_gen("open device %d, volume %s, mode %d", ubi_num, name, mode); if (!name) return ERR_PTR(-EINVAL); len = strnlen(name, UBI_VOL_NAME_MAX + 1); if (len > UBI_VOL_NAME_MAX) return ERR_PTR(-EINVAL); if (ubi_num < 0 || ubi_num >= UBI_MAX_DEVICES) return ERR_PTR(-EINVAL); ubi = ubi_get_device(ubi_num); if (!ubi) return ERR_PTR(-ENODEV); spin_lock(&ubi->volumes_lock); /* Walk all volumes of this UBI device */ for (i = 0; i < ubi->vtbl_slots; i++) { struct ubi_volume *vol = ubi->volumes[i]; if (vol && len == vol->name_len && !strcmp(name, vol->name)) { vol_id = i; break; } } spin_unlock(&ubi->volumes_lock); if (vol_id >= 0) ret = ubi_open_volume(ubi_num, vol_id, mode); else ret = ERR_PTR(-ENODEV); /* * We should put the UBI device even in case of success, because * 'ubi_open_volume()' took a reference as well. */ ubi_put_device(ubi); return ret; } EXPORT_SYMBOL_GPL(ubi_open_volume_nm); /** * ubi_get_num_by_path - get UBI device and volume number from device path * @pathname: volume character device node path * @ubi_num: pointer to UBI device number to be set * @vol_id: pointer to UBI volume ID to be set * * Returns 0 on success and sets ubi_num and vol_id, returns error otherwise. */ int ubi_get_num_by_path(const char *pathname, int *ubi_num, int *vol_id) { int error; struct path path; struct kstat stat; error = kern_path(pathname, LOOKUP_FOLLOW, &path); if (error) return error; error = vfs_getattr(&path, &stat, STATX_TYPE, AT_STATX_SYNC_AS_STAT); path_put(&path); if (error) return error; if (!S_ISCHR(stat.mode)) return -EINVAL; *ubi_num = ubi_major2num(MAJOR(stat.rdev)); *vol_id = MINOR(stat.rdev) - 1; if (*vol_id < 0 || *ubi_num < 0) return -ENODEV; return 0; } /** * ubi_open_volume_path - open UBI volume by its character device node path. * @pathname: volume character device node path * @mode: open mode * * This function is similar to 'ubi_open_volume()', but opens a volume the path * to its character device node. */ struct ubi_volume_desc *ubi_open_volume_path(const char *pathname, int mode) { int error, ubi_num, vol_id; dbg_gen("open volume %s, mode %d", pathname, mode); if (!pathname || !*pathname) return ERR_PTR(-EINVAL); error = ubi_get_num_by_path(pathname, &ubi_num, &vol_id); if (error) return ERR_PTR(error); return ubi_open_volume(ubi_num, vol_id, mode); } EXPORT_SYMBOL_GPL(ubi_open_volume_path); /** * ubi_close_volume - close UBI volume. * @desc: volume descriptor */ void ubi_close_volume(struct ubi_volume_desc *desc) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; dbg_gen("close device %d, volume %d, mode %d", ubi->ubi_num, vol->vol_id, desc->mode); spin_lock(&ubi->volumes_lock); switch (desc->mode) { case UBI_READONLY: vol->readers -= 1; break; case UBI_READWRITE: vol->writers -= 1; break; case UBI_EXCLUSIVE: vol->exclusive = 0; break; case UBI_METAONLY: vol->metaonly = 0; break; } vol->ref_count -= 1; spin_unlock(&ubi->volumes_lock); kfree(desc); put_device(&vol->dev); ubi_put_device(ubi); module_put(THIS_MODULE); } EXPORT_SYMBOL_GPL(ubi_close_volume); /** * leb_read_sanity_check - does sanity checks on read requests. * @desc: volume descriptor * @lnum: logical eraseblock number to read from * @offset: offset within the logical eraseblock to read from * @len: how many bytes to read * * This function is used by ubi_leb_read() and ubi_leb_read_sg() * to perform sanity checks. */ static int leb_read_sanity_check(struct ubi_volume_desc *desc, int lnum, int offset, int len) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; int vol_id = vol->vol_id; if (vol_id < 0 || vol_id >= ubi->vtbl_slots || lnum < 0 || lnum >= vol->used_ebs || offset < 0 || len < 0 || offset + len > vol->usable_leb_size) return -EINVAL; if (vol->vol_type == UBI_STATIC_VOLUME) { if (vol->used_ebs == 0) /* Empty static UBI volume */ return 0; if (lnum == vol->used_ebs - 1 && offset + len > vol->last_eb_bytes) return -EINVAL; } if (vol->upd_marker) return -EBADF; return 0; } /** * ubi_leb_read - read data. * @desc: volume descriptor * @lnum: logical eraseblock number to read from * @buf: buffer where to store the read data * @offset: offset within the logical eraseblock to read from * @len: how many bytes to read * @check: whether UBI has to check the read data's CRC or not. * * This function reads data from offset @offset of logical eraseblock @lnum and * stores the data at @buf. When reading from static volumes, @check specifies * whether the data has to be checked or not. If yes, the whole logical * eraseblock will be read and its CRC checksum will be checked (i.e., the CRC * checksum is per-eraseblock). So checking may substantially slow down the * read speed. The @check argument is ignored for dynamic volumes. * * In case of success, this function returns zero. In case of failure, this * function returns a negative error code. * * %-EBADMSG error code is returned: * o for both static and dynamic volumes if MTD driver has detected a data * integrity problem (unrecoverable ECC checksum mismatch in case of NAND); * o for static volumes in case of data CRC mismatch. * * If the volume is damaged because of an interrupted update this function just * returns immediately with %-EBADF error code. */ int ubi_leb_read(struct ubi_volume_desc *desc, int lnum, char *buf, int offset, int len, int check) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; int err, vol_id = vol->vol_id; dbg_gen("read %d bytes from LEB %d:%d:%d", len, vol_id, lnum, offset); err = leb_read_sanity_check(desc, lnum, offset, len); if (err < 0) return err; if (len == 0) return 0; err = ubi_eba_read_leb(ubi, vol, lnum, buf, offset, len, check); if (err && mtd_is_eccerr(err) && vol->vol_type == UBI_STATIC_VOLUME) { ubi_warn(ubi, "mark volume %d as corrupted", vol_id); vol->corrupted = 1; } return err; } EXPORT_SYMBOL_GPL(ubi_leb_read); /** * ubi_leb_read_sg - read data into a scatter gather list. * @desc: volume descriptor * @lnum: logical eraseblock number to read from * @sgl: UBI scatter gather list to store the read data * @offset: offset within the logical eraseblock to read from * @len: how many bytes to read * @check: whether UBI has to check the read data's CRC or not. * * This function works exactly like ubi_leb_read_sg(). But instead of * storing the read data into a buffer it writes to an UBI scatter gather * list. */ int ubi_leb_read_sg(struct ubi_volume_desc *desc, int lnum, struct ubi_sgl *sgl, int offset, int len, int check) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; int err, vol_id = vol->vol_id; dbg_gen("read %d bytes from LEB %d:%d:%d", len, vol_id, lnum, offset); err = leb_read_sanity_check(desc, lnum, offset, len); if (err < 0) return err; if (len == 0) return 0; err = ubi_eba_read_leb_sg(ubi, vol, sgl, lnum, offset, len, check); if (err && mtd_is_eccerr(err) && vol->vol_type == UBI_STATIC_VOLUME) { ubi_warn(ubi, "mark volume %d as corrupted", vol_id); vol->corrupted = 1; } return err; } EXPORT_SYMBOL_GPL(ubi_leb_read_sg); /** * ubi_leb_write - write data. * @desc: volume descriptor * @lnum: logical eraseblock number to write to * @buf: data to write * @offset: offset within the logical eraseblock where to write * @len: how many bytes to write * * This function writes @len bytes of data from @buf to offset @offset of * logical eraseblock @lnum. * * This function takes care of physical eraseblock write failures. If write to * the physical eraseblock write operation fails, the logical eraseblock is * re-mapped to another physical eraseblock, the data is recovered, and the * write finishes. UBI has a pool of reserved physical eraseblocks for this. * * If all the data were successfully written, zero is returned. If an error * occurred and UBI has not been able to recover from it, this function returns * a negative error code. Note, in case of an error, it is possible that * something was still written to the flash media, but that may be some * garbage. * * If the volume is damaged because of an interrupted update this function just * returns immediately with %-EBADF code. */ int ubi_leb_write(struct ubi_volume_desc *desc, int lnum, const void *buf, int offset, int len) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; int vol_id = vol->vol_id; dbg_gen("write %d bytes to LEB %d:%d:%d", len, vol_id, lnum, offset); if (vol_id < 0 || vol_id >= ubi->vtbl_slots) return -EINVAL; if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME) return -EROFS; if (!ubi_leb_valid(vol, lnum) || offset < 0 || len < 0 || offset + len > vol->usable_leb_size || offset & (ubi->min_io_size - 1) || len & (ubi->min_io_size - 1)) return -EINVAL; if (vol->upd_marker) return -EBADF; if (len == 0) return 0; return ubi_eba_write_leb(ubi, vol, lnum, buf, offset, len); } EXPORT_SYMBOL_GPL(ubi_leb_write); /* * ubi_leb_change - change logical eraseblock atomically. * @desc: volume descriptor * @lnum: logical eraseblock number to change * @buf: data to write * @len: how many bytes to write * * This function changes the contents of a logical eraseblock atomically. @buf * has to contain new logical eraseblock data, and @len - the length of the * data, which has to be aligned. The length may be shorter than the logical * eraseblock size, ant the logical eraseblock may be appended to more times * later on. This function guarantees that in case of an unclean reboot the old * contents is preserved. Returns zero in case of success and a negative error * code in case of failure. */ int ubi_leb_change(struct ubi_volume_desc *desc, int lnum, const void *buf, int len) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; int vol_id = vol->vol_id; dbg_gen("atomically write %d bytes to LEB %d:%d", len, vol_id, lnum); if (vol_id < 0 || vol_id >= ubi->vtbl_slots) return -EINVAL; if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME) return -EROFS; if (!ubi_leb_valid(vol, lnum) || len < 0 || len > vol->usable_leb_size || len & (ubi->min_io_size - 1)) return -EINVAL; if (vol->upd_marker) return -EBADF; if (len == 0) return 0; return ubi_eba_atomic_leb_change(ubi, vol, lnum, buf, len); } EXPORT_SYMBOL_GPL(ubi_leb_change); /** * ubi_leb_erase - erase logical eraseblock. * @desc: volume descriptor * @lnum: logical eraseblock number * * This function un-maps logical eraseblock @lnum and synchronously erases the * correspondent physical eraseblock. Returns zero in case of success and a * negative error code in case of failure. * * If the volume is damaged because of an interrupted update this function just * returns immediately with %-EBADF code. */ int ubi_leb_erase(struct ubi_volume_desc *desc, int lnum) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; int err; dbg_gen("erase LEB %d:%d", vol->vol_id, lnum); if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME) return -EROFS; if (!ubi_leb_valid(vol, lnum)) return -EINVAL; if (vol->upd_marker) return -EBADF; err = ubi_eba_unmap_leb(ubi, vol, lnum); if (err) return err; return ubi_wl_flush(ubi, vol->vol_id, lnum); } EXPORT_SYMBOL_GPL(ubi_leb_erase); /** * ubi_leb_unmap - un-map logical eraseblock. * @desc: volume descriptor * @lnum: logical eraseblock number * * This function un-maps logical eraseblock @lnum and schedules the * corresponding physical eraseblock for erasure, so that it will eventually be * physically erased in background. This operation is much faster than the * erase operation. * * Unlike erase, the un-map operation does not guarantee that the logical * eraseblock will contain all 0xFF bytes when UBI is initialized again. For * example, if several logical eraseblocks are un-mapped, and an unclean reboot * happens after this, the logical eraseblocks will not necessarily be * un-mapped again when this MTD device is attached. They may actually be * mapped to the same physical eraseblocks again. So, this function has to be * used with care. * * In other words, when un-mapping a logical eraseblock, UBI does not store * any information about this on the flash media, it just marks the logical * eraseblock as "un-mapped" in RAM. If UBI is detached before the physical * eraseblock is physically erased, it will be mapped again to the same logical * eraseblock when the MTD device is attached again. * * The main and obvious use-case of this function is when the contents of a * logical eraseblock has to be re-written. Then it is much more efficient to * first un-map it, then write new data, rather than first erase it, then write * new data. Note, once new data has been written to the logical eraseblock, * UBI guarantees that the old contents has gone forever. In other words, if an * unclean reboot happens after the logical eraseblock has been un-mapped and * then written to, it will contain the last written data. * * This function returns zero in case of success and a negative error code in * case of failure. If the volume is damaged because of an interrupted update * this function just returns immediately with %-EBADF code. */ int ubi_leb_unmap(struct ubi_volume_desc *desc, int lnum) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; dbg_gen("unmap LEB %d:%d", vol->vol_id, lnum); if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME) return -EROFS; if (!ubi_leb_valid(vol, lnum)) return -EINVAL; if (vol->upd_marker) return -EBADF; return ubi_eba_unmap_leb(ubi, vol, lnum); } EXPORT_SYMBOL_GPL(ubi_leb_unmap); /** * ubi_leb_map - map logical eraseblock to a physical eraseblock. * @desc: volume descriptor * @lnum: logical eraseblock number * * This function maps an un-mapped logical eraseblock @lnum to a physical * eraseblock. This means, that after a successful invocation of this * function the logical eraseblock @lnum will be empty (contain only %0xFF * bytes) and be mapped to a physical eraseblock, even if an unclean reboot * happens. * * This function returns zero in case of success, %-EBADF if the volume is * damaged because of an interrupted update, %-EBADMSG if the logical * eraseblock is already mapped, and other negative error codes in case of * other failures. */ int ubi_leb_map(struct ubi_volume_desc *desc, int lnum) { struct ubi_volume *vol = desc->vol; struct ubi_device *ubi = vol->ubi; dbg_gen("map LEB %d:%d", vol->vol_id, lnum); if (desc->mode == UBI_READONLY || vol->vol_type == UBI_STATIC_VOLUME) return -EROFS; if (!ubi_leb_valid(vol, lnum)) return -EINVAL; if (vol->upd_marker) return -EBADF; if (ubi_eba_is_mapped(vol, lnum)) return -EBADMSG; return ubi_eba_write_leb(ubi, vol, lnum, NULL, 0, 0); } EXPORT_SYMBOL_GPL(ubi_leb_map); /** * ubi_is_mapped - check if logical eraseblock is mapped. * @desc: volume descriptor * @lnum: logical eraseblock number * * This function checks if logical eraseblock @lnum is mapped to a physical * eraseblock. If a logical eraseblock is un-mapped, this does not necessarily * mean it will still be un-mapped after the UBI device is re-attached. The * logical eraseblock may become mapped to the physical eraseblock it was last * mapped to. * * This function returns %1 if the LEB is mapped, %0 if not, and a negative * error code in case of failure. If the volume is damaged because of an * interrupted update this function just returns immediately with %-EBADF error * code. */ int ubi_is_mapped(struct ubi_volume_desc *desc, int lnum) { struct ubi_volume *vol = desc->vol; dbg_gen("test LEB %d:%d", vol->vol_id, lnum); if (!ubi_leb_valid(vol, lnum)) return -EINVAL; if (vol->upd_marker) return -EBADF; return ubi_eba_is_mapped(vol, lnum); } EXPORT_SYMBOL_GPL(ubi_is_mapped); /** * ubi_sync - synchronize UBI device buffers. * @ubi_num: UBI device to synchronize * * The underlying MTD device may cache data in hardware or in software. This * function ensures the caches are flushed. Returns zero in case of success and * a negative error code in case of failure. */ int ubi_sync(int ubi_num) { struct ubi_device *ubi; ubi = ubi_get_device(ubi_num); if (!ubi) return -ENODEV; mtd_sync(ubi->mtd); ubi_put_device(ubi); return 0; } EXPORT_SYMBOL_GPL(ubi_sync); BLOCKING_NOTIFIER_HEAD(ubi_notifiers); /** * ubi_register_volume_notifier - register a volume notifier. * @nb: the notifier description object * @ignore_existing: if non-zero, do not send "added" notification for all * already existing volumes * * This function registers a volume notifier, which means that * 'nb->notifier_call()' will be invoked when an UBI volume is created, * removed, re-sized, re-named, or updated. The first argument of the function * is the notification type. The second argument is pointer to a * &struct ubi_notification object which describes the notification event. * Using UBI API from the volume notifier is prohibited. * * This function returns zero in case of success and a negative error code * in case of failure. */ int ubi_register_volume_notifier(struct notifier_block *nb, int ignore_existing) { int err; err = blocking_notifier_chain_register(&ubi_notifiers, nb); if (err != 0) return err; if (ignore_existing) return 0; /* * We are going to walk all UBI devices and all volumes, and * notify the user about existing volumes by the %UBI_VOLUME_ADDED * event. We have to lock the @ubi_devices_mutex to make sure UBI * devices do not disappear. */ mutex_lock(&ubi_devices_mutex); ubi_enumerate_volumes(nb); mutex_unlock(&ubi_devices_mutex); return err; } EXPORT_SYMBOL_GPL(ubi_register_volume_notifier); /** * ubi_unregister_volume_notifier - unregister the volume notifier. * @nb: the notifier description object * * This function unregisters volume notifier @nm and returns zero in case of * success and a negative error code in case of failure. */ int ubi_unregister_volume_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&ubi_notifiers, nb); } EXPORT_SYMBOL_GPL(ubi_unregister_volume_notifier); |
| 35 28 4 12 30 30 30 11 28 7 21 40 41 73 71 7 67 6 62 8 8 3 2 5 5 7 7 1 1 2 4 6 6 4 4 3 51 49 2 56 1 3 54 54 54 54 4 32 22 3 2 6 5 3 2 4 6 1 6 4 3 3 1 2 2 3 6 5 1 3 2 1 45 2 5 38 43 43 7 5 5 42 1 5 2 2 3 1 28 1 7 10 2 9 280 256 3 3 5 3 8 3 1 12 38 15 13 3 15 2 39 1 38 38 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * Added support for a Unix98-style ptmx device. * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998 * */ #include <linux/module.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/fcntl.h> #include <linux/sched/signal.h> #include <linux/string.h> #include <linux/major.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/device.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/devpts_fs.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/poll.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/ioctl.h> #include <linux/compat.h> #include "tty.h" #undef TTY_DEBUG_HANGUP #ifdef TTY_DEBUG_HANGUP # define tty_debug_hangup(tty, f, args...) tty_debug(tty, f, ##args) #else # define tty_debug_hangup(tty, f, args...) do {} while (0) #endif #ifdef CONFIG_UNIX98_PTYS static struct tty_driver *ptm_driver; static struct tty_driver *pts_driver; static DEFINE_MUTEX(devpts_mutex); #endif static void pty_close(struct tty_struct *tty, struct file *filp) { if (tty->driver->subtype == PTY_TYPE_MASTER) WARN_ON(tty->count > 1); else { if (tty_io_error(tty)) return; if (tty->count > 2) return; } set_bit(TTY_IO_ERROR, &tty->flags); wake_up_interruptible(&tty->read_wait); wake_up_interruptible(&tty->write_wait); scoped_guard(spinlock_irq, &tty->ctrl.lock) tty->ctrl.packet = false; /* Review - krefs on tty_link ?? */ if (!tty->link) return; set_bit(TTY_OTHER_CLOSED, &tty->link->flags); wake_up_interruptible(&tty->link->read_wait); wake_up_interruptible(&tty->link->write_wait); if (tty->driver->subtype == PTY_TYPE_MASTER) { set_bit(TTY_OTHER_CLOSED, &tty->flags); #ifdef CONFIG_UNIX98_PTYS if (tty->driver == ptm_driver) { guard(mutex)(&devpts_mutex); if (tty->link->driver_data) devpts_pty_kill(tty->link->driver_data); } #endif tty_vhangup(tty->link); } } /* * The unthrottle routine is called by the line discipline to signal * that it can receive more characters. For PTY's, the TTY_THROTTLED * flag is always set, to force the line discipline to always call the * unthrottle routine when there are fewer than TTY_THRESHOLD_UNTHROTTLE * characters in the queue. This is necessary since each time this * happens, we need to wake up any sleeping processes that could be * (1) trying to send data to the pty, or (2) waiting in wait_until_sent() * for the pty buffer to be drained. */ static void pty_unthrottle(struct tty_struct *tty) { tty_wakeup(tty->link); set_bit(TTY_THROTTLED, &tty->flags); } /** * pty_write - write to a pty * @tty: the tty we write from * @buf: kernel buffer of data * @c: bytes to write * * Our "hardware" write method. Data is coming from the ldisc which * may be in a non sleeping state. We simply throw this at the other * end of the link as if we were an IRQ handler receiving stuff for * the other side of the pty/tty pair. */ static ssize_t pty_write(struct tty_struct *tty, const u8 *buf, size_t c) { struct tty_struct *to = tty->link; if (tty->flow.stopped || !c) return 0; return tty_insert_flip_string_and_push_buffer(to->port, buf, c); } /** * pty_write_room - write space * @tty: tty we are writing from * * Report how many bytes the ldisc can send into the queue for * the other device. */ static unsigned int pty_write_room(struct tty_struct *tty) { if (tty->flow.stopped) return 0; return tty_buffer_space_avail(tty->link->port); } /* Set the lock flag on a pty */ static int pty_set_lock(struct tty_struct *tty, int __user *arg) { int val; if (get_user(val, arg)) return -EFAULT; if (val) set_bit(TTY_PTY_LOCK, &tty->flags); else clear_bit(TTY_PTY_LOCK, &tty->flags); return 0; } static int pty_get_lock(struct tty_struct *tty, int __user *arg) { int locked = test_bit(TTY_PTY_LOCK, &tty->flags); return put_user(locked, arg); } /* Set the packet mode on a pty */ static int pty_set_pktmode(struct tty_struct *tty, int __user *arg) { int want_pktmode; if (get_user(want_pktmode, arg)) return -EFAULT; guard(spinlock_irq)(&tty->ctrl.lock); if (!want_pktmode) { tty->ctrl.packet = false; return 0; } if (tty->ctrl.packet) return 0; tty->link->ctrl.pktstatus = 0; smp_mb(); tty->ctrl.packet = true; return 0; } /* Get the packet mode of a pty */ static int pty_get_pktmode(struct tty_struct *tty, int __user *arg) { int pktmode = tty->ctrl.packet; return put_user(pktmode, arg); } /* Send a signal to the slave */ static int pty_signal(struct tty_struct *tty, int sig) { struct pid *pgrp; if (sig != SIGINT && sig != SIGQUIT && sig != SIGTSTP) return -EINVAL; if (tty->link) { pgrp = tty_get_pgrp(tty->link); if (pgrp) kill_pgrp(pgrp, sig, 1); put_pid(pgrp); } return 0; } static void pty_flush_buffer(struct tty_struct *tty) { struct tty_struct *to = tty->link; if (!to) return; tty_buffer_flush(to, NULL); if (to->ctrl.packet) { guard(spinlock_irq)(&tty->ctrl.lock); tty->ctrl.pktstatus |= TIOCPKT_FLUSHWRITE; wake_up_interruptible(&to->read_wait); } } static int pty_open(struct tty_struct *tty, struct file *filp) { if (!tty || !tty->link) return -ENODEV; if (test_bit(TTY_OTHER_CLOSED, &tty->flags)) goto out; if (test_bit(TTY_PTY_LOCK, &tty->link->flags)) goto out; if (tty->driver->subtype == PTY_TYPE_SLAVE && tty->link->count != 1) goto out; clear_bit(TTY_IO_ERROR, &tty->flags); clear_bit(TTY_OTHER_CLOSED, &tty->link->flags); set_bit(TTY_THROTTLED, &tty->flags); return 0; out: set_bit(TTY_IO_ERROR, &tty->flags); return -EIO; } static void pty_set_termios(struct tty_struct *tty, const struct ktermios *old_termios) { /* See if packet mode change of state. */ if (tty->link && tty->link->ctrl.packet) { int extproc = (old_termios->c_lflag & EXTPROC) | L_EXTPROC(tty); int old_flow = ((old_termios->c_iflag & IXON) && (old_termios->c_cc[VSTOP] == '\023') && (old_termios->c_cc[VSTART] == '\021')); int new_flow = (I_IXON(tty) && STOP_CHAR(tty) == '\023' && START_CHAR(tty) == '\021'); if ((old_flow != new_flow) || extproc) { scoped_guard(spinlock_irq, &tty->ctrl.lock) { if (old_flow != new_flow) { tty->ctrl.pktstatus &= ~(TIOCPKT_DOSTOP | TIOCPKT_NOSTOP); if (new_flow) tty->ctrl.pktstatus |= TIOCPKT_DOSTOP; else tty->ctrl.pktstatus |= TIOCPKT_NOSTOP; } if (extproc) tty->ctrl.pktstatus |= TIOCPKT_IOCTL; } wake_up_interruptible(&tty->link->read_wait); } } tty->termios.c_cflag &= ~(CSIZE | PARENB); tty->termios.c_cflag |= (CS8 | CREAD); } /** * pty_resize - resize event * @tty: tty being resized * @ws: window size being set. * * Update the termios variables and send the necessary signals to * peform a terminal resize correctly */ static int pty_resize(struct tty_struct *tty, struct winsize *ws) { struct pid *pgrp, *rpgrp; struct tty_struct *pty = tty->link; /* For a PTY we need to lock the tty side */ guard(mutex)(&tty->winsize_mutex); if (!memcmp(ws, &tty->winsize, sizeof(*ws))) return 0; /* Signal the foreground process group of both ptys */ pgrp = tty_get_pgrp(tty); rpgrp = tty_get_pgrp(pty); if (pgrp) kill_pgrp(pgrp, SIGWINCH, 1); if (rpgrp != pgrp && rpgrp) kill_pgrp(rpgrp, SIGWINCH, 1); put_pid(pgrp); put_pid(rpgrp); tty->winsize = *ws; pty->winsize = *ws; /* Never used so will go away soon */ return 0; } /** * pty_start - start() handler * pty_stop - stop() handler * @tty: tty being flow-controlled * * Propagates the TIOCPKT status to the master pty. * * NB: only the master pty can be in packet mode so only the slave * needs start()/stop() handlers */ static void pty_start(struct tty_struct *tty) { if (!tty->link || !tty->link->ctrl.packet) return; scoped_guard(spinlock_irqsave, &tty->ctrl.lock) { tty->ctrl.pktstatus &= ~TIOCPKT_STOP; tty->ctrl.pktstatus |= TIOCPKT_START; } wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN); } static void pty_stop(struct tty_struct *tty) { if (!tty->link || !tty->link->ctrl.packet) return; scoped_guard(spinlock_irqsave, &tty->ctrl.lock) { tty->ctrl.pktstatus &= ~TIOCPKT_START; tty->ctrl.pktstatus |= TIOCPKT_STOP; } wake_up_interruptible_poll(&tty->link->read_wait, EPOLLIN); } /** * pty_common_install - set up the pty pair * @driver: the pty driver * @tty: the tty being instantiated * @legacy: true if this is BSD style * * Perform the initial set up for the tty/pty pair. Called from the * tty layer when the port is first opened. * * Locking: the caller must hold the tty_mutex */ static int pty_common_install(struct tty_driver *driver, struct tty_struct *tty, bool legacy) { struct tty_struct *o_tty; struct tty_port *ports[2]; int idx = tty->index; int retval = -ENOMEM; /* Opening the slave first has always returned -EIO */ if (driver->subtype != PTY_TYPE_MASTER) return -EIO; ports[0] = kmalloc_obj(**ports); ports[1] = kmalloc_obj(**ports); if (!ports[0] || !ports[1]) goto err; if (!try_module_get(driver->other->owner)) { /* This cannot in fact currently happen */ goto err; } o_tty = alloc_tty_struct(driver->other, idx); if (!o_tty) goto err_put_module; tty_set_lock_subclass(o_tty); lockdep_set_subclass(&o_tty->termios_rwsem, TTY_LOCK_SLAVE); if (legacy) { /* We always use new tty termios data so we can do this the easy way .. */ tty_init_termios(tty); tty_init_termios(o_tty); driver->other->ttys[idx] = o_tty; driver->ttys[idx] = tty; } else { memset(&tty->termios_locked, 0, sizeof(tty->termios_locked)); tty->termios = driver->init_termios; memset(&o_tty->termios_locked, 0, sizeof(tty->termios_locked)); o_tty->termios = driver->other->init_termios; } /* * Everything allocated ... set up the o_tty structure. */ tty_driver_kref_get(driver->other); /* Establish the links in both directions */ tty->link = o_tty; o_tty->link = tty; tty_port_init(ports[0]); tty_port_init(ports[1]); tty_buffer_set_limit(ports[0], 8192); tty_buffer_set_limit(ports[1], 8192); o_tty->port = ports[0]; tty->port = ports[1]; o_tty->port->itty = o_tty; tty_buffer_set_lock_subclass(o_tty->port); tty_driver_kref_get(driver); tty->count++; o_tty->count++; return 0; err_put_module: module_put(driver->other->owner); err: kfree(ports[0]); kfree(ports[1]); return retval; } static void pty_cleanup(struct tty_struct *tty) { tty_port_put(tty->port); } /* Traditional BSD devices */ #ifdef CONFIG_LEGACY_PTYS static int pty_install(struct tty_driver *driver, struct tty_struct *tty) { return pty_common_install(driver, tty, true); } static void pty_remove(struct tty_driver *driver, struct tty_struct *tty) { struct tty_struct *pair = tty->link; driver->ttys[tty->index] = NULL; if (pair) pair->driver->ttys[pair->index] = NULL; } static int pty_bsd_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { switch (cmd) { case TIOCSPTLCK: /* Set PT Lock (disallow slave open) */ return pty_set_lock(tty, (int __user *) arg); case TIOCGPTLCK: /* Get PT Lock status */ return pty_get_lock(tty, (int __user *)arg); case TIOCPKT: /* Set PT packet mode */ return pty_set_pktmode(tty, (int __user *)arg); case TIOCGPKT: /* Get PT packet mode */ return pty_get_pktmode(tty, (int __user *)arg); case TIOCSIG: /* Send signal to other side of pty */ return pty_signal(tty, (int) arg); case TIOCGPTN: /* TTY returns ENOTTY, but glibc expects EINVAL here */ return -EINVAL; } return -ENOIOCTLCMD; } #ifdef CONFIG_COMPAT static long pty_bsd_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { /* * PTY ioctls don't require any special translation between 32-bit and * 64-bit userspace, they are already compatible. */ return pty_bsd_ioctl(tty, cmd, (unsigned long)compat_ptr(arg)); } #else #define pty_bsd_compat_ioctl NULL #endif static int legacy_count = CONFIG_LEGACY_PTY_COUNT; /* * not really modular, but the easiest way to keep compat with existing * bootargs behaviour is to continue using module_param here. */ module_param(legacy_count, int, 0); /* * The master side of a pty can do TIOCSPTLCK and thus * has pty_bsd_ioctl. */ static const struct tty_operations master_pty_ops_bsd = { .install = pty_install, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .ioctl = pty_bsd_ioctl, .compat_ioctl = pty_bsd_compat_ioctl, .cleanup = pty_cleanup, .resize = pty_resize, .remove = pty_remove }; static const struct tty_operations slave_pty_ops_bsd = { .install = pty_install, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .set_termios = pty_set_termios, .cleanup = pty_cleanup, .resize = pty_resize, .start = pty_start, .stop = pty_stop, .remove = pty_remove }; static void __init legacy_pty_init(void) { struct tty_driver *pty_driver, *pty_slave_driver; if (legacy_count <= 0) return; pty_driver = tty_alloc_driver(legacy_count, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_ALLOC | TTY_DRIVER_NO_WORKQUEUE); if (IS_ERR(pty_driver)) panic("Couldn't allocate pty driver"); pty_slave_driver = tty_alloc_driver(legacy_count, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_ALLOC | TTY_DRIVER_NO_WORKQUEUE); if (IS_ERR(pty_slave_driver)) panic("Couldn't allocate pty slave driver"); pty_driver->driver_name = "pty_master"; pty_driver->name = "pty"; pty_driver->major = PTY_MASTER_MAJOR; pty_driver->minor_start = 0; pty_driver->type = TTY_DRIVER_TYPE_PTY; pty_driver->subtype = PTY_TYPE_MASTER; pty_driver->init_termios = tty_std_termios; pty_driver->init_termios.c_iflag = 0; pty_driver->init_termios.c_oflag = 0; pty_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pty_driver->init_termios.c_lflag = 0; pty_driver->init_termios.c_ispeed = 38400; pty_driver->init_termios.c_ospeed = 38400; pty_driver->other = pty_slave_driver; tty_set_operations(pty_driver, &master_pty_ops_bsd); pty_slave_driver->driver_name = "pty_slave"; pty_slave_driver->name = "ttyp"; pty_slave_driver->major = PTY_SLAVE_MAJOR; pty_slave_driver->minor_start = 0; pty_slave_driver->type = TTY_DRIVER_TYPE_PTY; pty_slave_driver->subtype = PTY_TYPE_SLAVE; pty_slave_driver->init_termios = tty_std_termios; pty_slave_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pty_slave_driver->init_termios.c_ispeed = 38400; pty_slave_driver->init_termios.c_ospeed = 38400; pty_slave_driver->other = pty_driver; tty_set_operations(pty_slave_driver, &slave_pty_ops_bsd); if (tty_register_driver(pty_driver)) panic("Couldn't register pty driver"); if (tty_register_driver(pty_slave_driver)) panic("Couldn't register pty slave driver"); } #else static inline void legacy_pty_init(void) { } #endif /* Unix98 devices */ #ifdef CONFIG_UNIX98_PTYS static struct cdev ptmx_cdev; static struct file *ptm_open_peer_file(struct file *master, struct tty_struct *tty, int flags) { struct path path; struct file *file; /* Compute the slave's path */ path.mnt = devpts_mntget(master, tty->driver_data); if (IS_ERR(path.mnt)) return ERR_CAST(path.mnt); path.dentry = tty->link->driver_data; file = dentry_open(&path, flags, current_cred()); mntput(path.mnt); return file; } /** * ptm_open_peer - open the peer of a pty * @master: the open struct file of the ptmx device node * @tty: the master of the pty being opened * @flags: the flags for open * * Provide a race free way for userspace to open the slave end of a pty * (where they have the master fd and cannot access or trust the mount * namespace /dev/pts was mounted inside). */ int ptm_open_peer(struct file *master, struct tty_struct *tty, int flags) { if (tty->driver != ptm_driver) return -EIO; return FD_ADD(flags, ptm_open_peer_file(master, tty, flags)); } static int pty_unix98_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { switch (cmd) { case TIOCSPTLCK: /* Set PT Lock (disallow slave open) */ return pty_set_lock(tty, (int __user *)arg); case TIOCGPTLCK: /* Get PT Lock status */ return pty_get_lock(tty, (int __user *)arg); case TIOCPKT: /* Set PT packet mode */ return pty_set_pktmode(tty, (int __user *)arg); case TIOCGPKT: /* Get PT packet mode */ return pty_get_pktmode(tty, (int __user *)arg); case TIOCGPTN: /* Get PT Number */ return put_user(tty->index, (unsigned int __user *)arg); case TIOCSIG: /* Send signal to other side of pty */ return pty_signal(tty, (int) arg); } return -ENOIOCTLCMD; } #ifdef CONFIG_COMPAT static long pty_unix98_compat_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { /* * PTY ioctls don't require any special translation between 32-bit and * 64-bit userspace, they are already compatible. */ return pty_unix98_ioctl(tty, cmd, cmd == TIOCSIG ? arg : (unsigned long)compat_ptr(arg)); } #else #define pty_unix98_compat_ioctl NULL #endif /** * ptm_unix98_lookup - find a pty master * @driver: ptm driver * @file: unused * @idx: tty index * * Look up a pty master device. Called under the tty_mutex for now. * This provides our locking. */ static struct tty_struct *ptm_unix98_lookup(struct tty_driver *driver, struct file *file, int idx) { /* Master must be open via /dev/ptmx */ return ERR_PTR(-EIO); } /** * pts_unix98_lookup - find a pty slave * @driver: pts driver * @file: file pointer to tty * @idx: tty index * * Look up a pty master device. Called under the tty_mutex for now. * This provides our locking for the tty pointer. */ static struct tty_struct *pts_unix98_lookup(struct tty_driver *driver, struct file *file, int idx) { guard(mutex)(&devpts_mutex); /* Master must be open before slave */ return devpts_get_priv(file->f_path.dentry) ? : ERR_PTR(-EIO); } static int pty_unix98_install(struct tty_driver *driver, struct tty_struct *tty) { return pty_common_install(driver, tty, false); } /* this is called once with whichever end is closed last */ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) { struct pts_fs_info *fsi; if (tty->driver->subtype == PTY_TYPE_MASTER) fsi = tty->driver_data; else fsi = tty->link->driver_data; if (fsi) { devpts_kill_index(fsi, tty->index); devpts_release(fsi); } } static void pty_show_fdinfo(struct tty_struct *tty, struct seq_file *m) { seq_printf(m, "tty-index:\t%d\n", tty->index); } static const struct tty_operations ptm_unix98_ops = { .lookup = ptm_unix98_lookup, .install = pty_unix98_install, .remove = pty_unix98_remove, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .ioctl = pty_unix98_ioctl, .compat_ioctl = pty_unix98_compat_ioctl, .resize = pty_resize, .cleanup = pty_cleanup, .show_fdinfo = pty_show_fdinfo, }; static const struct tty_operations pty_unix98_ops = { .lookup = pts_unix98_lookup, .install = pty_unix98_install, .remove = pty_unix98_remove, .open = pty_open, .close = pty_close, .write = pty_write, .write_room = pty_write_room, .flush_buffer = pty_flush_buffer, .unthrottle = pty_unthrottle, .set_termios = pty_set_termios, .start = pty_start, .stop = pty_stop, .cleanup = pty_cleanup, }; /** * ptmx_open - open a unix 98 pty master * @inode: inode of device file * @filp: file pointer to tty * * Allocate a unix98 pty master device from the ptmx driver. * * Locking: tty_mutex protects the init_dev work. tty->count should * protect the rest. * allocated_ptys_lock handles the list of free pty numbers */ static int ptmx_open(struct inode *inode, struct file *filp) { struct pts_fs_info *fsi; struct tty_struct *tty; struct dentry *dentry; int retval; int index; nonseekable_open(inode, filp); /* We refuse fsnotify events on ptmx, since it's a shared resource */ file_set_fsnotify_mode(filp, FMODE_NONOTIFY); retval = tty_alloc_file(filp); if (retval) return retval; fsi = devpts_acquire(filp); if (IS_ERR(fsi)) { retval = PTR_ERR(fsi); goto out_free_file; } /* find a device that is not in use. */ scoped_guard(mutex, &devpts_mutex) index = devpts_new_index(fsi); retval = index; if (index < 0) goto out_put_fsi; /* The tty returned here is locked so we can safely drop the mutex */ scoped_guard(mutex, &tty_mutex) tty = tty_init_dev(ptm_driver, index); retval = PTR_ERR(tty); if (IS_ERR(tty)) goto out; /* * From here on out, the tty is "live", and the index and * fsi will be killed/put by the tty_release() */ set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ tty->driver_data = fsi; tty_add_file(tty, filp); dentry = devpts_pty_new(fsi, index, tty->link); if (IS_ERR(dentry)) { retval = PTR_ERR(dentry); goto err_release; } tty->link->driver_data = dentry; retval = ptm_driver->ops->open(tty, filp); if (retval) goto err_release; tty_debug_hangup(tty, "opening (count=%d)\n", tty->count); tty_unlock(tty); return 0; err_release: tty_unlock(tty); // This will also put-ref the fsi tty_release(inode, filp); return retval; out: devpts_kill_index(fsi, index); out_put_fsi: devpts_release(fsi); out_free_file: tty_free_file(filp); return retval; } static struct file_operations ptmx_fops __ro_after_init; static void __init unix98_pty_init(void) { ptm_driver = tty_alloc_driver(NR_UNIX98_PTY_MAX, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV | TTY_DRIVER_DEVPTS_MEM | TTY_DRIVER_DYNAMIC_ALLOC | TTY_DRIVER_NO_WORKQUEUE); if (IS_ERR(ptm_driver)) panic("Couldn't allocate Unix98 ptm driver"); pts_driver = tty_alloc_driver(NR_UNIX98_PTY_MAX, TTY_DRIVER_RESET_TERMIOS | TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV | TTY_DRIVER_DEVPTS_MEM | TTY_DRIVER_DYNAMIC_ALLOC | TTY_DRIVER_NO_WORKQUEUE); if (IS_ERR(pts_driver)) panic("Couldn't allocate Unix98 pts driver"); ptm_driver->driver_name = "pty_master"; ptm_driver->name = "ptm"; ptm_driver->major = UNIX98_PTY_MASTER_MAJOR; ptm_driver->minor_start = 0; ptm_driver->type = TTY_DRIVER_TYPE_PTY; ptm_driver->subtype = PTY_TYPE_MASTER; ptm_driver->init_termios = tty_std_termios; ptm_driver->init_termios.c_iflag = 0; ptm_driver->init_termios.c_oflag = 0; ptm_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; ptm_driver->init_termios.c_lflag = 0; ptm_driver->init_termios.c_ispeed = 38400; ptm_driver->init_termios.c_ospeed = 38400; ptm_driver->other = pts_driver; tty_set_operations(ptm_driver, &ptm_unix98_ops); pts_driver->driver_name = "pty_slave"; pts_driver->name = "pts"; pts_driver->major = UNIX98_PTY_SLAVE_MAJOR; pts_driver->minor_start = 0; pts_driver->type = TTY_DRIVER_TYPE_PTY; pts_driver->subtype = PTY_TYPE_SLAVE; pts_driver->init_termios = tty_std_termios; pts_driver->init_termios.c_cflag = B38400 | CS8 | CREAD; pts_driver->init_termios.c_ispeed = 38400; pts_driver->init_termios.c_ospeed = 38400; pts_driver->other = ptm_driver; tty_set_operations(pts_driver, &pty_unix98_ops); if (tty_register_driver(ptm_driver)) panic("Couldn't register Unix98 ptm driver"); if (tty_register_driver(pts_driver)) panic("Couldn't register Unix98 pts driver"); /* Now create the /dev/ptmx special device */ tty_default_fops(&ptmx_fops); ptmx_fops.open = ptmx_open; cdev_init(&ptmx_cdev, &ptmx_fops); if (cdev_add(&ptmx_cdev, MKDEV(TTYAUX_MAJOR, 2), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 2), 1, "/dev/ptmx") < 0) panic("Couldn't register /dev/ptmx driver"); device_create(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 2), NULL, "ptmx"); } #else static inline void unix98_pty_init(void) { } #endif static int __init pty_init(void) { legacy_pty_init(); unix98_pty_init(); return 0; } device_initcall(pty_init); |
| 421 427 314 314 7 47 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMENS_H #define _LINUX_TIMENS_H #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> #include <linux/time64.h> #include <linux/cleanup.h> struct user_namespace; extern struct user_namespace init_user_ns; struct seq_file; struct vm_area_struct; struct timens_offsets { struct timespec64 monotonic; struct timespec64 boottime; }; struct time_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; struct timens_offsets offsets; #ifdef CONFIG_TIME_NS_VDSO struct page *vvar_page; #endif /* If set prevents changing offsets after any task joined namespace. */ bool frozen_offsets; } __randomize_layout; extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS static inline struct time_namespace *to_time_ns(struct ns_common *ns) { return container_of(ns, struct time_namespace, ns); } void __init time_ns_init(void); static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { ns_ref_inc(ns); return ns; } struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); static inline void put_time_ns(struct time_namespace *ns) { if (ns_ref_put(ns)) free_time_ns(ns); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m); struct proc_timens_offset { int clockid; struct timespec64 val; }; int proc_timens_set_offset(struct file *file, struct task_struct *p, struct proc_timens_offset *offsets, int n); static inline void timens_add_monotonic(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->monotonic); } static inline void timens_add_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->boottime); } static inline u64 timens_add_boottime_ns(u64 nsec) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; return nsec + timespec64_to_ns(&ns_offsets->boottime); } static inline void timens_sub_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_sub(*ts, ns_offsets->boottime); } ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, struct timens_offsets *offsets); static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { struct time_namespace *ns = current->nsproxy->time_ns; if (likely(ns == &init_time_ns)) return tim; return do_timens_ktime_to_host(clockid, tim, &ns->offsets); } #else static inline void __init time_ns_init(void) { } static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { return NULL; } static inline void put_time_ns(struct time_namespace *ns) { } static inline struct time_namespace *copy_time_ns(u64 flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { if (flags & CLONE_NEWTIME) return ERR_PTR(-EINVAL); return old_ns; } static inline void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { return; } static inline void timens_add_monotonic(struct timespec64 *ts) { } static inline void timens_add_boottime(struct timespec64 *ts) { } static inline u64 timens_add_boottime_ns(u64 nsec) { return nsec; } static inline void timens_sub_boottime(struct timespec64 *ts) { } static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { return tim; } #endif #ifdef CONFIG_TIME_NS_VDSO extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns); struct page *find_timens_vvar_page(struct vm_area_struct *vma); #else /* !CONFIG_TIME_NS_VDSO */ static inline void timens_commit(struct task_struct *tsk, struct time_namespace *ns) { } static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) { return NULL; } #endif /* CONFIG_TIME_NS_VDSO */ DEFINE_FREE(time_ns, struct time_namespace *, if (_T) put_time_ns(_T)) #endif /* _LINUX_TIMENS_H */ |
| 25 3 132 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #ifndef __IPVLAN_H #define __IPVLAN_H #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_link.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/inetdevice.h> #include <linux/netfilter.h> #include <net/ip.h> #include <net/ip6_route.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #define IPVLAN_DRV "ipvlan" #define IPV_DRV_VER "0.1" #define IPVLAN_HASH_SIZE (1 << BITS_PER_BYTE) #define IPVLAN_HASH_MASK (IPVLAN_HASH_SIZE - 1) #define IPVLAN_MAC_FILTER_BITS 8 #define IPVLAN_MAC_FILTER_SIZE (1 << IPVLAN_MAC_FILTER_BITS) #define IPVLAN_MAC_FILTER_MASK (IPVLAN_MAC_FILTER_SIZE - 1) #define IPVLAN_QBACKLOG_LIMIT 1000 typedef enum { IPVL_IPV6 = 0, IPVL_ICMPV6, IPVL_IPV4, IPVL_ARP, } ipvl_hdr_type; struct ipvl_pcpu_stats { u64_stats_t rx_pkts; u64_stats_t rx_bytes; u64_stats_t rx_mcast; u64_stats_t tx_pkts; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errs; u32 tx_drps; }; struct ipvl_port; struct ipvl_dev { struct net_device *dev; struct list_head pnode; struct ipvl_port *port; struct net_device *phy_dev; struct list_head addrs; struct ipvl_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE); netdev_features_t sfeatures; u32 msg_enable; }; struct ipvl_addr { struct ipvl_dev *master; /* Back pointer to master */ union { struct in6_addr ip6; /* IPv6 address on logical interface */ struct in_addr ip4; /* IPv4 address on logical interface */ } ipu; #define ip6addr ipu.ip6 #define ip4addr ipu.ip4 struct hlist_node hlnode; /* Hash-table linkage */ struct list_head anode; /* logical-interface linkage */ ipvl_hdr_type atype; struct rcu_head rcu; }; struct ipvl_port { struct net_device *dev; possible_net_t pnet; struct hlist_head hlhead[IPVLAN_HASH_SIZE]; spinlock_t addrs_lock; /* guards hash-table and addrs */ struct list_head ipvlans; u16 mode; u16 flags; u16 dev_id_start; struct work_struct wq; struct sk_buff_head backlog; int count; struct ida ida; netdevice_tracker dev_tracker; }; struct ipvl_skb_cb { bool tx_pkt; }; #define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0])) static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d) { return rcu_dereference(d->rx_handler_data); } static inline struct ipvl_port *ipvlan_port_get_rcu_bh(const struct net_device *d) { return rcu_dereference_bh(d->rx_handler_data); } static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d) { return rtnl_dereference(d->rx_handler_data); } static inline bool ipvlan_is_private(const struct ipvl_port *port) { return !!(port->flags & IPVLAN_F_PRIVATE); } static inline void ipvlan_mark_private(struct ipvl_port *port) { port->flags |= IPVLAN_F_PRIVATE; } static inline void ipvlan_clear_private(struct ipvl_port *port) { port->flags &= ~IPVLAN_F_PRIVATE; } static inline bool ipvlan_is_vepa(const struct ipvl_port *port) { return !!(port->flags & IPVLAN_F_VEPA); } static inline void ipvlan_mark_vepa(struct ipvl_port *port) { port->flags |= IPVLAN_F_VEPA; } static inline void ipvlan_clear_vepa(struct ipvl_port *port) { port->flags &= ~IPVLAN_F_VEPA; } void ipvlan_init_secret(void); unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); void ipvlan_process_multicast(struct work_struct *work); int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev); void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr); struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6); bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6); void ipvlan_ht_addr_del(struct ipvl_addr *addr); struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, int addr_type, bool use_dest); void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type); void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); int ipvlan_link_register(struct rtnl_link_ops *ops); #ifdef CONFIG_IPVLAN_L3S int ipvlan_l3s_register(struct ipvl_port *port); void ipvlan_l3s_unregister(struct ipvl_port *port); void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet); int ipvlan_l3s_init(void); void ipvlan_l3s_cleanup(void); #else static inline int ipvlan_l3s_register(struct ipvl_port *port) { return -ENOTSUPP; } static inline void ipvlan_l3s_unregister(struct ipvl_port *port) { } static inline void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet) { } static inline int ipvlan_l3s_init(void) { return 0; } static inline void ipvlan_l3s_cleanup(void) { } #endif /* CONFIG_IPVLAN_L3S */ static inline bool netif_is_ipvlan_port(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == ipvlan_handle_frame; } #endif /* __IPVLAN_H */ |
| 99 24 99 60 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 | /* * linux/fs/nls/nls_iso8859-1.c * * Charset iso8859-1 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, /* 0x90*/ 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, /* 0xa0*/ 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, /* 0xb0*/ 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, /* 0xc0*/ 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, /* 0xd0*/ 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7, 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df, /* 0xe0*/ 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, /* 0xf0*/ 0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7, 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xc0-0xc7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xc8-0xcf */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xd7, /* 0xd0-0xd7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0xf0-0xf7 */ 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, /* 0xa0-0xa7 */ 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0x00, 0xb6, 0xb7, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, /* 0xd8-0xdf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xe0-0xe7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xe8-0xef */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xf7, /* 0xf0-0xf7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0x00, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "iso8859-1", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_iso8859_1(void) { return register_nls(&table); } static void __exit exit_nls_iso8859_1(void) { unregister_nls(&table); } module_init(init_nls_iso8859_1) module_exit(exit_nls_iso8859_1) MODULE_DESCRIPTION("NLS ISO 8859-1 (Latin 1; Western European Languages)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 6912 17743 1139 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM skb #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SKB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #undef FN #define FN(reason) TRACE_DEFINE_ENUM(SKB_DROP_REASON_##reason); DEFINE_DROP_REASON(FN, FN) #undef FN #undef FNe #define FN(reason) { SKB_DROP_REASON_##reason, #reason }, #define FNe(reason) { SKB_DROP_REASON_##reason, #reason } /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location, enum skb_drop_reason reason, struct sock *rx_sk), TP_ARGS(skb, location, reason, rx_sk), TP_STRUCT__entry( __field(void *, skbaddr) __field(void *, location) __field(void *, rx_sk) __field(unsigned short, protocol) __field(enum skb_drop_reason, reason) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->rx_sk = rx_sk; __entry->protocol = ntohs(skb->protocol); __entry->reason = reason; ), TP_printk("skbaddr=%p rx_sk=%p protocol=%u location=%pS reason: %s", __entry->skbaddr, __entry->rx_sk, __entry->protocol, __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) ); #undef FN #undef FNe TRACE_EVENT(consume_skb, TP_PROTO(struct sk_buff *skb, void *location), TP_ARGS(skb, location), TP_STRUCT__entry( __field( void *, skbaddr) __field( void *, location) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; ), TP_printk("skbaddr=%p location=%pS", __entry->skbaddr, __entry->location) ); TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), TP_ARGS(skb, len), TP_STRUCT__entry( __field( const void *, skbaddr ) __field( int, len ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = len; ), TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len) ); #endif /* _TRACE_SKB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 250 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NETMEM_PRIV_H #define __NETMEM_PRIV_H static inline unsigned long netmem_get_pp_magic(netmem_ref netmem) { return netmem_to_nmdesc(netmem)->pp_magic & ~PP_DMA_INDEX_MASK; } static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic) { netmem_to_nmdesc(netmem)->pp_magic |= pp_magic; } static inline void netmem_clear_pp_magic(netmem_ref netmem) { WARN_ON_ONCE(netmem_to_nmdesc(netmem)->pp_magic & PP_DMA_INDEX_MASK); netmem_to_nmdesc(netmem)->pp_magic = 0; } static inline bool netmem_is_pp(netmem_ref netmem) { return (netmem_get_pp_magic(netmem) & PP_MAGIC_MASK) == PP_SIGNATURE; } static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool) { netmem_to_nmdesc(netmem)->pp = pool; } static inline void netmem_set_dma_addr(netmem_ref netmem, unsigned long dma_addr) { netmem_to_nmdesc(netmem)->dma_addr = dma_addr; } static inline unsigned long netmem_get_dma_index(netmem_ref netmem) { unsigned long magic; if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) return 0; magic = netmem_to_nmdesc(netmem)->pp_magic; return (magic & PP_DMA_INDEX_MASK) >> PP_DMA_INDEX_SHIFT; } static inline void netmem_set_dma_index(netmem_ref netmem, unsigned long id) { unsigned long magic; if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) return; magic = netmem_get_pp_magic(netmem) | (id << PP_DMA_INDEX_SHIFT); netmem_to_nmdesc(netmem)->pp_magic = magic; } #endif |
| 4 2 32 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_GUE_H #define __NET_GUE_H /* Definitions for the GUE header, standard and private flags, lengths * of optional fields are below. * * Diagram of GUE header: * * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |Ver|C| Hlen | Proto/ctype | Standard flags |P| * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | | * ~ Fields (optional) ~ * | | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Private flags (optional, P bit is set) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | | * ~ Private fields (optional) ~ * | | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * C bit indicates control message when set, data message when unset. * For a control message, proto/ctype is interpreted as a type of * control message. For data messages, proto/ctype is the IP protocol * of the next header. * * P bit indicates private flags field is present. The private flags * may refer to options placed after this field. */ #include <asm/byteorder.h> #include <linux/types.h> struct guehdr { union { struct { #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 hlen:5, control:1, version:2; #elif defined (__BIG_ENDIAN_BITFIELD) __u8 version:2, control:1, hlen:5; #else #error "Please fix <asm/byteorder.h>" #endif __u8 proto_ctype; __be16 flags; }; __be32 word; }; }; /* Standard flags in GUE header */ #define GUE_FLAG_PRIV htons(1<<0) /* Private flags are in options */ #define GUE_LEN_PRIV 4 #define GUE_FLAGS_ALL (GUE_FLAG_PRIV) /* Private flags in the private option extension */ #define GUE_PFLAG_REMCSUM htonl(1U << 31) #define GUE_PLEN_REMCSUM 4 #define GUE_PFLAGS_ALL (GUE_PFLAG_REMCSUM) /* Functions to compute options length corresponding to flags. * If we ever have a lot of flags this can be potentially be * converted to a more optimized algorithm (table lookup * for instance). */ static inline size_t guehdr_flags_len(__be16 flags) { return ((flags & GUE_FLAG_PRIV) ? GUE_LEN_PRIV : 0); } static inline size_t guehdr_priv_flags_len(__be32 flags) { return 0; } /* Validate standard and private flags. Returns non-zero (meaning invalid) * if there is an unknown standard or private flags, or the options length for * the flags exceeds the options length specific in hlen of the GUE header. */ static inline int validate_gue_flags(struct guehdr *guehdr, size_t optlen) { __be16 flags = guehdr->flags; size_t len; if (flags & ~GUE_FLAGS_ALL) return 1; len = guehdr_flags_len(flags); if (len > optlen) return 1; if (flags & GUE_FLAG_PRIV) { /* Private flags are last four bytes accounted in * guehdr_flags_len */ __be32 pflags = *(__be32 *)((void *)&guehdr[1] + len - GUE_LEN_PRIV); if (pflags & ~GUE_PFLAGS_ALL) return 1; len += guehdr_priv_flags_len(pflags); if (len > optlen) return 1; } return 0; } #endif |
| 5 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains the base functions to manage periodic tick * related events. * * Copyright(C) 2005-2006, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/compiler.h> #include <linux/cpu.h> #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> #include <linux/nmi.h> #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> #include <linux/module.h> #include <trace/events/power.h> #include <asm/irq_regs.h> #include "tick-internal.h" /* * Tick devices */ DEFINE_PER_CPU(struct tick_device, tick_cpu_device); /* * Tick next event: keeps track of the tick time. It's updated by the * CPU which handles the tick and protected by jiffies_lock. There is * no requirement to write hold the jiffies seqcount for it. */ ktime_t tick_next_period; /* * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This * variable has two functions: * * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the * timekeeping lock all at once. Only the CPU which is assigned to do the * update is handling it. * * 2) Hand off the duty in the NOHZ idle case by setting the value to * TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks * at it will take over and keep the time keeping alive. The handover * procedure also covers cpu hotplug. */ int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT; #ifdef CONFIG_NO_HZ_FULL /* * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns * tick_do_timer_cpu and it should be taken over by an eligible secondary * when one comes online. */ static int tick_do_timer_boot_cpu __read_mostly = -1; #endif /* * Debugging: see timer_list.c */ struct tick_device *tick_get_device(int cpu) { return &per_cpu(tick_cpu_device, cpu); } /** * tick_is_oneshot_available - check for a oneshot capable event device */ int tick_is_oneshot_available(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return 0; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) return 1; return tick_broadcast_oneshot_available(); } /* * Periodic tick */ static void tick_periodic(int cpu) { if (READ_ONCE(tick_do_timer_cpu) == cpu) { raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); /* Keep track of the next tick event */ tick_next_period = ktime_add_ns(tick_next_period, TICK_NSEC); do_timer(1); write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); update_wall_time(); } update_process_times(user_mode(get_irq_regs())); profile_tick(CPU_PROFILING); } /* * Event handler for periodic ticks */ void tick_handle_periodic(struct clock_event_device *dev) { int cpu = smp_processor_id(); ktime_t next = dev->next_event; dev->next_event_forced = 0; tick_periodic(cpu); /* * The cpu might have transitioned to HIGHRES or NOHZ mode via * update_process_times() -> run_local_timers() -> * hrtimer_run_queues(). */ if (IS_ENABLED(CONFIG_TICK_ONESHOT) && dev->event_handler != tick_handle_periodic) return; if (!clockevent_state_oneshot(dev)) return; for (;;) { /* * Setup the next period for devices, which do not have * periodic mode: */ next = ktime_add_ns(next, TICK_NSEC); if (!clockevents_program_event(dev, next, false)) return; /* * Have to be careful here. If we're in oneshot mode, * before we call tick_periodic() in a loop, we need * to be sure we're using a real hardware clocksource. * Otherwise we could get trapped in an infinite * loop, as the tick_periodic() increments jiffies, * which then will increment time, possibly causing * the loop to trigger again and again. */ if (timekeeping_valid_for_hres()) tick_periodic(cpu); } } /* * Setup the device for a periodic tick */ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) { tick_set_periodic_handler(dev, broadcast); /* Broadcast setup ? */ if (!tick_device_is_functional(dev)) return; if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && !tick_broadcast_oneshot_active()) { clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC); } else { unsigned int seq; ktime_t next; do { seq = read_seqcount_begin(&jiffies_seq); next = tick_next_period; } while (read_seqcount_retry(&jiffies_seq, seq)); clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); for (;;) { if (!clockevents_program_event(dev, next, false)) return; next = ktime_add_ns(next, TICK_NSEC); } } } /* * Setup the tick device */ static void tick_setup_device(struct tick_device *td, struct clock_event_device *newdev, int cpu, const struct cpumask *cpumask) { void (*handler)(struct clock_event_device *) = NULL; ktime_t next_event = 0; /* * First device setup ? */ if (!td->evtdev) { /* * If no cpu took the do_timer update, assign it to * this cpu: */ if (READ_ONCE(tick_do_timer_cpu) == TICK_DO_TIMER_BOOT) { WRITE_ONCE(tick_do_timer_cpu, cpu); tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* * The boot CPU may be nohz_full, in which case the * first housekeeping secondary will take do_timer() * from it. */ if (tick_nohz_full_cpu(cpu)) tick_do_timer_boot_cpu = cpu; } else if (tick_do_timer_boot_cpu != -1 && !tick_nohz_full_cpu(cpu)) { tick_do_timer_boot_cpu = -1; /* * The boot CPU will stay in periodic (NOHZ disabled) * mode until clocksource_done_booting() called after * smp_init() selects a high resolution clocksource and * timekeeping_notify() kicks the NOHZ stuff alive. * * So this WRITE_ONCE can only race with the READ_ONCE * check in tick_periodic() but this race is harmless. */ WRITE_ONCE(tick_do_timer_cpu, cpu); #endif } /* * Startup in periodic mode first. */ td->mode = TICKDEV_MODE_PERIODIC; } else { handler = td->evtdev->event_handler; next_event = td->evtdev->next_event; td->evtdev->event_handler = clockevents_handle_noop; } td->evtdev = newdev; /* * When the device is not per cpu, pin the interrupt to the * current cpu: */ if (!cpumask_equal(newdev->cpumask, cpumask)) irq_set_affinity(newdev->irq, cpumask); /* * When global broadcasting is active, check if the current * device is registered as a placeholder for broadcast mode. * This allows us to handle this x86 misfeature in a generic * way. This function also returns !=0 when we keep the * current active broadcast state for this CPU. */ if (tick_device_uses_broadcast(newdev, cpu)) return; if (td->mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(newdev, 0); else tick_setup_oneshot(newdev, handler, next_event); } void tick_install_replacement(struct clock_event_device *newdev) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); int cpu = smp_processor_id(); clockevents_exchange_device(td->evtdev, newdev); tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) tick_oneshot_notify(); } static bool tick_check_percpu(struct clock_event_device *curdev, struct clock_event_device *newdev, int cpu) { if (!cpumask_test_cpu(cpu, newdev->cpumask)) return false; if (cpumask_equal(newdev->cpumask, cpumask_of(cpu))) return true; /* Check if irq affinity can be set */ if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq)) return false; /* Prefer an existing cpu local device */ if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu))) return false; return true; } static bool tick_check_preferred(struct clock_event_device *curdev, struct clock_event_device *newdev) { /* Prefer oneshot capable device */ if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) { if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT)) return false; if (tick_oneshot_mode_active()) return false; } /* * Use the higher rated one, but prefer a CPU local device with a lower * rating than a non-CPU local device */ return !curdev || newdev->rating > curdev->rating || !cpumask_equal(curdev->cpumask, newdev->cpumask); } /* * Check whether the new device is a better fit than curdev. curdev * can be NULL ! */ bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev) { if (!tick_check_percpu(curdev, newdev, smp_processor_id())) return false; return tick_check_preferred(curdev, newdev); } /* * Check, if the new registered device should be used. Called with * clockevents_lock held and interrupts disabled. */ void tick_check_new_device(struct clock_event_device *newdev) { struct clock_event_device *curdev; struct tick_device *td; int cpu; cpu = smp_processor_id(); td = &per_cpu(tick_cpu_device, cpu); curdev = td->evtdev; if (!tick_check_replacement(curdev, newdev)) goto out_bc; if (!try_module_get(newdev->owner)) return; /* * Replace the eventually existing device by the new * device. If the current device is the broadcast device, do * not give it back to the clockevents layer ! */ if (tick_is_broadcast_device(curdev)) { clockevents_shutdown(curdev); curdev = NULL; } clockevents_exchange_device(curdev, newdev); tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) tick_oneshot_notify(); return; out_bc: /* * Can the new device be used as a broadcast device ? */ tick_install_broadcast_device(newdev, cpu); } /** * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode * @state: The target state (enter/exit) * * The system enters/leaves a state, where affected devices might stop * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. * * Called with interrupts disabled, so clockevents_lock is not * required here because the local clock event device cannot go away * under us. */ int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP)) return 0; return __tick_broadcast_oneshot_control(state); } EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); #ifdef CONFIG_HOTPLUG_CPU void tick_assert_timekeeping_handover(void) { WARN_ON_ONCE(tick_do_timer_cpu == smp_processor_id()); } /* * Stop the tick and transfer the timekeeping job away from a dying cpu. */ int tick_cpu_dying(unsigned int dying_cpu) { /* * If the current CPU is the timekeeper, it's the only one that can * safely hand over its duty. Also all online CPUs are in stop * machine, guaranteed not to be idle, therefore there is no * concurrency and it's safe to pick any online successor. */ if (tick_do_timer_cpu == dying_cpu) tick_do_timer_cpu = cpumask_first(cpu_online_mask); /* Make sure the CPU won't try to retake the timekeeping duty */ tick_sched_timer_dying(dying_cpu); /* Remove CPU from timer broadcasting */ tick_offline_cpu(dying_cpu); return 0; } /* * Shutdown an event device on the outgoing CPU: * * Called by the dying CPU during teardown, with clockevents_lock held * and interrupts disabled. */ void tick_shutdown(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *dev = td->evtdev; td->mode = TICKDEV_MODE_PERIODIC; if (dev) { clockevents_exchange_device(dev, NULL); dev->event_handler = clockevents_handle_noop; td->evtdev = NULL; } } #endif /** * tick_suspend_local - Suspend the local tick device * * Called from the local cpu for freeze with interrupts disabled. * * No locks required. Nothing can change the per cpu device. */ void tick_suspend_local(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); clockevents_shutdown(td->evtdev); } /** * tick_resume_local - Resume the local tick device * * Called from the local CPU for unfreeze or XEN resume magic. * * No locks required. Nothing can change the per cpu device. */ void tick_resume_local(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); bool broadcast = tick_resume_check_broadcast(); clockevents_tick_resume(td->evtdev); if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(td->evtdev, 0); else tick_resume_oneshot(); } /* * Ensure that hrtimers are up to date and the clockevents device * is reprogrammed correctly when high resolution timers are * enabled. */ hrtimers_resume_local(); } /** * tick_suspend - Suspend the tick and the broadcast device * * Called from syscore_suspend() via timekeeping_suspend with only one * CPU online and interrupts disabled or from tick_unfreeze() under * tick_freeze_lock. * * No locks required. Nothing can change the per cpu device. */ void tick_suspend(void) { tick_suspend_local(); tick_suspend_broadcast(); } /** * tick_resume - Resume the tick and the broadcast device * * Called from syscore_resume() via timekeeping_resume with only one * CPU online and interrupts disabled. * * No locks required. Nothing can change the per cpu device. */ void tick_resume(void) { tick_resume_broadcast(); tick_resume_local(); } #ifdef CONFIG_SUSPEND static DEFINE_RAW_SPINLOCK(tick_freeze_lock); static DEFINE_WAIT_OVERRIDE_MAP(tick_freeze_map, LD_WAIT_SLEEP); static unsigned int tick_freeze_depth; /** * tick_freeze - Suspend the local tick and (possibly) timekeeping. * * Check if this is the last online CPU executing the function and if so, * suspend timekeeping. Otherwise suspend the local tick. * * Call with interrupts disabled. Must be balanced with %tick_unfreeze(). * Interrupts must not be enabled before the subsequent %tick_unfreeze(). */ void tick_freeze(void) { raw_spin_lock(&tick_freeze_lock); tick_freeze_depth++; if (tick_freeze_depth == num_online_cpus()) { trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), true); /* * All other CPUs have their interrupts disabled and are * suspended to idle. Other tasks have been frozen so there * is no scheduling happening. This means that there is no * concurrency in the system at this point. Therefore it is * okay to acquire a sleeping lock on PREEMPT_RT, such as a * spinlock, because the lock cannot be held by other CPUs * or threads and acquiring it cannot block. * * Inform lockdep about the situation. */ lock_map_acquire_try(&tick_freeze_map); system_state = SYSTEM_SUSPEND; sched_clock_suspend(); timekeeping_suspend(); lock_map_release(&tick_freeze_map); } else { tick_suspend_local(); } raw_spin_unlock(&tick_freeze_lock); } /** * tick_unfreeze - Resume the local tick and (possibly) timekeeping. * * Check if this is the first CPU executing the function and if so, resume * timekeeping. Otherwise resume the local tick. * * Call with interrupts disabled. Must be balanced with %tick_freeze(). * Interrupts must not be enabled after the preceding %tick_freeze(). */ void tick_unfreeze(void) { raw_spin_lock(&tick_freeze_lock); if (tick_freeze_depth == num_online_cpus()) { /* * Similar to tick_freeze(). On resumption the first CPU may * acquire uncontended sleeping locks while other CPUs block on * tick_freeze_lock. */ lock_map_acquire_try(&tick_freeze_map); timekeeping_resume(); sched_clock_resume(); lock_map_release(&tick_freeze_map); system_state = SYSTEM_RUNNING; trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false); } else { touch_softlockup_watchdog(); tick_resume_local(); } tick_freeze_depth--; raw_spin_unlock(&tick_freeze_lock); } #endif /* CONFIG_SUSPEND */ /** * tick_init - initialize the tick control */ void __init tick_init(void) { tick_broadcast_init(); tick_nohz_init(); } |
| 33 33 25 25 8 8 8 24 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | // SPDX-License-Identifier: GPL-2.0 /* * of.c The helpers for hcd device tree support * * Copyright (C) 2016 Freescale Semiconductor, Inc. * Author: Peter Chen <peter.chen@freescale.com> * Copyright (C) 2017 Johan Hovold <johan@kernel.org> */ #include <linux/of.h> #include <linux/of_graph.h> #include <linux/usb/of.h> /** * usb_of_get_device_node() - get a USB device node * @hub: hub to which device is connected * @port1: one-based index of port * * Look up the node of a USB device given its parent hub device and one-based * port number. * * Return: A pointer to the node with incremented refcount if found, or * %NULL otherwise. */ struct device_node *usb_of_get_device_node(struct usb_device *hub, int port1) { struct device_node *node; u32 reg; for_each_child_of_node(hub->dev.of_node, node) { if (of_property_read_u32(node, "reg", ®)) continue; if (reg == port1) return node; } return NULL; } EXPORT_SYMBOL_GPL(usb_of_get_device_node); /** * usb_of_has_combined_node() - determine whether a device has a combined node * @udev: USB device * * Determine whether a USB device has a so called combined node which is * shared with its sole interface. This is the case if and only if the device * has a node and its descriptors report the following: * * 1) bDeviceClass is 0 or 9, and * 2) bNumConfigurations is 1, and * 3) bNumInterfaces is 1. * * Return: True iff the device has a device node and its descriptors match the * criteria for a combined node. */ bool usb_of_has_combined_node(struct usb_device *udev) { struct usb_device_descriptor *ddesc = &udev->descriptor; struct usb_config_descriptor *cdesc; if (!udev->dev.of_node) return false; switch (ddesc->bDeviceClass) { case USB_CLASS_PER_INTERFACE: case USB_CLASS_HUB: if (ddesc->bNumConfigurations == 1) { cdesc = &udev->config->desc; if (cdesc->bNumInterfaces == 1) return true; } } return false; } EXPORT_SYMBOL_GPL(usb_of_has_combined_node); static bool usb_of_has_devices_or_graph(const struct usb_device *hub) { const struct device_node *np = hub->dev.of_node; if (of_graph_is_present(np)) return true; for_each_child_of_node_scoped(np, child) if (of_property_present(child, "reg")) return true; return false; } /** * usb_of_get_connect_type() - get a USB hub's port connect_type * @hub: hub to which port is for @port1 * @port1: one-based index of port * * Get the connect_type of @port1 based on the device node for @hub. If the * port is described in the OF graph, the connect_type is "hotplug". If the * @hub has a child device has with a 'reg' property equal to @port1 the * connect_type is "hard-wired". If there isn't an OF graph or child node at * all then the connect_type is "unknown". Otherwise, the port is considered * "unused" because it isn't described at all. * * Return: A connect_type for @port1 based on the device node for @hub. */ enum usb_port_connect_type usb_of_get_connect_type(struct usb_device *hub, int port1) { struct device_node *np, *child, *ep, *remote_np; enum usb_port_connect_type connect_type; /* Only set connect_type if binding has ports/hardwired devices. */ if (!usb_of_has_devices_or_graph(hub)) return USB_PORT_CONNECT_TYPE_UNKNOWN; /* Assume port is unused if there's a graph or a child node. */ connect_type = USB_PORT_NOT_USED; np = hub->dev.of_node; /* * Hotplug ports are connected to an available remote node, e.g. * usb-a-connector compatible node, in the OF graph. */ if (of_graph_is_present(np)) { ep = of_graph_get_endpoint_by_regs(np, port1, -1); if (ep) { remote_np = of_graph_get_remote_port_parent(ep); of_node_put(ep); if (of_device_is_available(remote_np)) connect_type = USB_PORT_CONNECT_TYPE_HOT_PLUG; of_node_put(remote_np); } } /* * Hard-wired ports are child nodes with a reg property corresponding * to the port number, i.e. a usb device. */ child = usb_of_get_device_node(hub, port1); if (of_device_is_available(child)) connect_type = USB_PORT_CONNECT_TYPE_HARD_WIRED; of_node_put(child); return connect_type; } EXPORT_SYMBOL_GPL(usb_of_get_connect_type); /** * usb_of_get_interface_node() - get a USB interface node * @udev: USB device of interface * @config: configuration value * @ifnum: interface number * * Look up the node of a USB interface given its USB device, configuration * value and interface number. * * Return: A pointer to the node with incremented refcount if found, or * %NULL otherwise. */ struct device_node * usb_of_get_interface_node(struct usb_device *udev, u8 config, u8 ifnum) { struct device_node *node; u32 reg[2]; for_each_child_of_node(udev->dev.of_node, node) { if (of_property_read_u32_array(node, "reg", reg, 2)) continue; if (reg[0] == ifnum && reg[1] == config) return node; } return NULL; } EXPORT_SYMBOL_GPL(usb_of_get_interface_node); |
| 121 121 141 66 66 59 59 142 143 142 143 2 2 2 143 143 143 223 223 224 224 140 156 156 2 70 158 158 224 143 1 157 158 223 158 157 45 57 158 57 158 158 158 158 158 89 157 51 51 68 9 68 68 158 155 158 106 1 149 8 8 97 158 156 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/page-io.c * * This contains the new page_io functions for ext4 * * Written by Theodore Ts'o, 2010. */ #include <linux/blk-crypto.h> #include <linux/fs.h> #include <linux/time.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/string.h> #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/mpage.h> #include <linux/namei.h> #include <linux/uio.h> #include <linux/bio.h> #include <linux/workqueue.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" static struct kmem_cache *io_end_cachep; static struct kmem_cache *io_end_vec_cachep; int __init ext4_init_pageio(void) { io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT); if (io_end_cachep == NULL) return -ENOMEM; io_end_vec_cachep = KMEM_CACHE(ext4_io_end_vec, 0); if (io_end_vec_cachep == NULL) { kmem_cache_destroy(io_end_cachep); return -ENOMEM; } return 0; } void ext4_exit_pageio(void) { kmem_cache_destroy(io_end_cachep); kmem_cache_destroy(io_end_vec_cachep); } struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end) { struct ext4_io_end_vec *io_end_vec; io_end_vec = kmem_cache_zalloc(io_end_vec_cachep, GFP_NOFS); if (!io_end_vec) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&io_end_vec->list); list_add_tail(&io_end_vec->list, &io_end->list_vec); return io_end_vec; } static void ext4_free_io_end_vec(ext4_io_end_t *io_end) { struct ext4_io_end_vec *io_end_vec, *tmp; if (list_empty(&io_end->list_vec)) return; list_for_each_entry_safe(io_end_vec, tmp, &io_end->list_vec, list) { list_del(&io_end_vec->list); kmem_cache_free(io_end_vec_cachep, io_end_vec); } } struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end) { BUG_ON(list_empty(&io_end->list_vec)); return list_last_entry(&io_end->list_vec, struct ext4_io_end_vec, list); } /* * Print an buffer I/O error compatible with the fs/buffer.c. This * provides compatibility with dmesg scrapers that look for a specific * buffer I/O error message. We really need a unified error reporting * structure to userspace ala Digital Unix's uerf system, but it's * probably not going to happen in my lifetime, due to LKML politics... */ static void buffer_io_error(struct buffer_head *bh) { printk_ratelimited(KERN_ERR "Buffer I/O error on device %pg, logical block %llu\n", bh->b_bdev, (unsigned long long)bh->b_blocknr); } static void ext4_finish_bio(struct bio *bio) { struct folio_iter fi; bio_for_each_folio_all(fi, bio) { struct folio *folio = fi.folio; struct folio *io_folio = NULL; struct buffer_head *bh, *head; size_t bio_start = fi.offset; size_t bio_end = bio_start + fi.length; unsigned under_io = 0; unsigned long flags; if (fscrypt_is_bounce_folio(folio)) { io_folio = folio; folio = fscrypt_pagecache_folio(folio); } if (bio->bi_status) { int err = blk_status_to_errno(bio->bi_status); mapping_set_error(folio->mapping, err); } bh = head = folio_buffers(folio); /* * We check all buffers in the folio under b_uptodate_lock * to avoid races with other end io clearing async_write flags */ spin_lock_irqsave(&head->b_uptodate_lock, flags); do { if (bh_offset(bh) < bio_start || bh_offset(bh) + bh->b_size > bio_end) { if (buffer_async_write(bh)) under_io++; continue; } clear_buffer_async_write(bh); if (bio->bi_status) { set_buffer_write_io_error(bh); buffer_io_error(bh); } } while ((bh = bh->b_this_page) != head); spin_unlock_irqrestore(&head->b_uptodate_lock, flags); if (!under_io) { fscrypt_free_bounce_page(&io_folio->page); folio_end_writeback(folio); } } } static void ext4_release_io_end(ext4_io_end_t *io_end) { struct bio *bio, *next_bio; BUG_ON(!list_empty(&io_end->list)); BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN); WARN_ON(io_end->handle); for (bio = io_end->bio; bio; bio = next_bio) { next_bio = bio->bi_private; ext4_finish_bio(bio); bio_put(bio); } ext4_free_io_end_vec(io_end); kmem_cache_free(io_end_cachep, io_end); } /* * On successful IO, check a range of space and convert unwritten extents to * written. On IO failure, check if journal abort is needed. Note that * we are protected from truncate touching same part of extent tree by the * fact that truncate code waits for all DIO to finish (thus exclusion from * direct IO is achieved) and also waits for PageWriteback bits. Thus we * cannot get to ext4_ext_truncate() before all IOs overlapping that range are * completed (happens from ext4_free_ioend()). */ static int ext4_end_io_end(ext4_io_end_t *io_end) { struct inode *inode = io_end->inode; handle_t *handle = io_end->handle; struct super_block *sb = inode->i_sb; int ret = 0; ext4_debug("ext4_end_io_nolock: io_end 0x%p from inode %llu,list->next 0x%p," "list->prev 0x%p\n", io_end, inode->i_ino, io_end->list.next, io_end->list.prev); /* * Do not convert the unwritten extents if data writeback fails, * or stale data may be exposed. */ io_end->handle = NULL; /* Following call will use up the handle */ if (unlikely(io_end->flag & EXT4_IO_END_FAILED)) { ret = -EIO; if (handle) jbd2_journal_free_reserved(handle); if (test_opt(sb, DATA_ERR_ABORT)) jbd2_journal_abort(EXT4_SB(sb)->s_journal, ret); } else { ret = ext4_convert_unwritten_io_end_vec(handle, io_end); } if (ret < 0 && !ext4_emergency_state(sb) && io_end->flag & EXT4_IO_END_UNWRITTEN) { ext4_msg(sb, KERN_EMERG, "failed to convert unwritten extents to written " "extents -- potential data loss! " "(inode %llu, error %d)", inode->i_ino, ret); } ext4_clear_io_unwritten_flag(io_end); ext4_release_io_end(io_end); return ret; } static void dump_completed_IO(struct inode *inode, struct list_head *head) { #ifdef EXT4FS_DEBUG struct list_head *cur, *before, *after; ext4_io_end_t *io_end, *io_end0, *io_end1; if (list_empty(head)) return; ext4_debug("Dump inode %llu completed io list\n", inode->i_ino); list_for_each_entry(io_end, head, list) { cur = &io_end->list; before = cur->prev; io_end0 = container_of(before, ext4_io_end_t, list); after = cur->next; io_end1 = container_of(after, ext4_io_end_t, list); ext4_debug("io 0x%p from inode %llu,prev 0x%p,next 0x%p\n", io_end, inode->i_ino, io_end0, io_end1); } #endif } static bool ext4_io_end_defer_completion(ext4_io_end_t *io_end) { if (io_end->flag & EXT4_IO_END_UNWRITTEN && !list_empty(&io_end->list_vec)) return true; if (test_opt(io_end->inode->i_sb, DATA_ERR_ABORT) && io_end->flag & EXT4_IO_END_FAILED && !ext4_emergency_state(io_end->inode->i_sb)) return true; return false; } /* Add the io_end to per-inode completed end_io list. */ static void ext4_add_complete_io(ext4_io_end_t *io_end) { struct ext4_inode_info *ei = EXT4_I(io_end->inode); struct ext4_sb_info *sbi = EXT4_SB(io_end->inode->i_sb); struct workqueue_struct *wq; unsigned long flags; /* Only reserved conversions or pending IO errors will enter here. */ WARN_ON(!(io_end->flag & EXT4_IO_END_DEFER_COMPLETION)); WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN && !io_end->handle && sbi->s_journal); WARN_ON(!io_end->bio); spin_lock_irqsave(&ei->i_completed_io_lock, flags); wq = sbi->rsv_conversion_wq; if (list_empty(&ei->i_rsv_conversion_list)) queue_work(wq, &ei->i_rsv_conversion_work); list_add_tail(&io_end->list, &ei->i_rsv_conversion_list); spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); } static int ext4_do_flush_completed_IO(struct inode *inode, struct list_head *head) { ext4_io_end_t *io_end; struct list_head unwritten; unsigned long flags; struct ext4_inode_info *ei = EXT4_I(inode); int err, ret = 0; spin_lock_irqsave(&ei->i_completed_io_lock, flags); dump_completed_IO(inode, head); list_replace_init(head, &unwritten); spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); while (!list_empty(&unwritten)) { io_end = list_entry(unwritten.next, ext4_io_end_t, list); BUG_ON(!(io_end->flag & EXT4_IO_END_DEFER_COMPLETION)); list_del_init(&io_end->list); err = ext4_end_io_end(io_end); if (unlikely(!ret && err)) ret = err; } return ret; } /* * Used to convert unwritten extents to written extents upon IO completion, * or used to abort the journal upon IO errors. */ void ext4_end_io_rsv_work(struct work_struct *work) { struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info, i_rsv_conversion_work); ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list); } ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) { ext4_io_end_t *io_end = kmem_cache_zalloc(io_end_cachep, flags); if (io_end) { io_end->inode = inode; INIT_LIST_HEAD(&io_end->list); INIT_LIST_HEAD(&io_end->list_vec); refcount_set(&io_end->count, 1); } return io_end; } void ext4_put_io_end_defer(ext4_io_end_t *io_end) { if (refcount_dec_and_test(&io_end->count)) { if (ext4_io_end_defer_completion(io_end)) return ext4_add_complete_io(io_end); ext4_release_io_end(io_end); } } int ext4_put_io_end(ext4_io_end_t *io_end) { if (refcount_dec_and_test(&io_end->count)) { if (ext4_io_end_defer_completion(io_end)) return ext4_end_io_end(io_end); ext4_release_io_end(io_end); } return 0; } ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end) { refcount_inc(&io_end->count); return io_end; } /* BIO completion function for page writeback */ static void ext4_end_bio(struct bio *bio) { ext4_io_end_t *io_end = bio->bi_private; sector_t bi_sector = bio->bi_iter.bi_sector; if (WARN_ONCE(!io_end, "io_end is NULL: %pg: sector %Lu len %u err %d\n", bio->bi_bdev, (long long) bio->bi_iter.bi_sector, (unsigned) bio_sectors(bio), bio->bi_status)) { ext4_finish_bio(bio); bio_put(bio); return; } bio->bi_end_io = NULL; if (bio->bi_status) { struct inode *inode = io_end->inode; ext4_warning(inode->i_sb, "I/O error %d writing to inode %llu " "starting block %llu)", bio->bi_status, inode->i_ino, (unsigned long long) bi_sector >> (inode->i_blkbits - 9)); io_end->flag |= EXT4_IO_END_FAILED; mapping_set_error(inode->i_mapping, blk_status_to_errno(bio->bi_status)); } if (ext4_io_end_defer_completion(io_end)) { /* * Link bio into list hanging from io_end. We have to do it * atomically as bio completions can be racing against each * other. */ bio->bi_private = xchg(&io_end->bio, bio); ext4_put_io_end_defer(io_end); } else { /* * Drop io_end reference early. Inode can get freed once * we finish the bio. */ ext4_put_io_end_defer(io_end); ext4_finish_bio(bio); bio_put(bio); } } void ext4_io_submit(struct ext4_io_submit *io) { struct bio *bio = io->io_bio; if (bio) { if (io->io_wbc->sync_mode == WB_SYNC_ALL) io->io_bio->bi_opf |= REQ_SYNC; blk_crypto_submit_bio(io->io_bio); } io->io_bio = NULL; } void ext4_io_submit_init(struct ext4_io_submit *io, struct writeback_control *wbc) { io->io_wbc = wbc; io->io_bio = NULL; io->io_end = NULL; } static void io_submit_init_bio(struct ext4_io_submit *io, struct inode *inode, struct folio *folio, struct buffer_head *bh) { struct bio *bio; /* * bio_alloc will _always_ be able to allocate a bio if * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset(). */ bio = bio_alloc(bh->b_bdev, BIO_MAX_VECS, REQ_OP_WRITE, GFP_NOIO); fscrypt_set_bio_crypt_ctx(bio, inode, folio_pos(folio) + bh_offset(bh), GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_end_io = ext4_end_bio; bio->bi_private = ext4_get_io_end(io->io_end); bio->bi_write_hint = inode->i_write_hint; io->io_bio = bio; io->io_next_block = bh->b_blocknr; wbc_init_bio(io->io_wbc, bio); } static bool io_submit_need_new_bio(struct ext4_io_submit *io, struct inode *inode, struct folio *folio, struct buffer_head *bh) { if (bh->b_blocknr != io->io_next_block) return true; if (!fscrypt_mergeable_bio(io->io_bio, inode, folio_pos(folio) + bh_offset(bh))) return true; return false; } static void io_submit_add_bh(struct ext4_io_submit *io, struct inode *inode, struct folio *folio, struct folio *io_folio, struct buffer_head *bh) { if (io->io_bio && io_submit_need_new_bio(io, inode, folio, bh)) { submit_and_retry: ext4_io_submit(io); } if (io->io_bio == NULL) io_submit_init_bio(io, inode, folio, bh); if (!bio_add_folio(io->io_bio, io_folio, bh->b_size, bh_offset(bh))) goto submit_and_retry; wbc_account_cgroup_owner(io->io_wbc, folio, bh->b_size); io->io_next_block++; } int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio, size_t len) { struct folio *io_folio = folio; struct inode *inode = folio->mapping->host; unsigned block_start; struct buffer_head *bh, *head; int ret = 0; int nr_to_submit = 0; struct writeback_control *wbc = io->io_wbc; bool keep_towrite = false; BUG_ON(!folio_test_locked(folio)); BUG_ON(folio_test_writeback(folio)); /* * Comments copied from block_write_full_folio: * * The folio 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." */ if (len < folio_size(folio)) folio_zero_segment(folio, len, folio_size(folio)); /* * In the first loop we prepare and mark buffers to submit. We have to * mark all buffers in the folio before submitting so that * folio_end_writeback() cannot be called from ext4_end_bio() when IO * on the first buffer finishes and we are still working on submitting * the second buffer. */ bh = head = folio_buffers(folio); do { block_start = bh_offset(bh); if (block_start >= len) { clear_buffer_dirty(bh); set_buffer_uptodate(bh); continue; } if (!buffer_dirty(bh) || buffer_delay(bh) || !buffer_mapped(bh) || buffer_unwritten(bh)) { /* A hole? We can safely clear the dirty bit */ if (!buffer_mapped(bh)) clear_buffer_dirty(bh); /* * Keeping dirty some buffer we cannot write? Make sure * to redirty the folio and keep TOWRITE tag so that * racing WB_SYNC_ALL writeback does not skip the folio. * This happens e.g. when doing writeout for * transaction commit or when journalled data is not * yet committed. */ if (buffer_dirty(bh) || (buffer_jbd(bh) && buffer_jbddirty(bh))) { if (!folio_test_dirty(folio)) folio_redirty_for_writepage(wbc, folio); keep_towrite = true; } continue; } if (buffer_new(bh)) clear_buffer_new(bh); set_buffer_async_write(bh); clear_buffer_dirty(bh); nr_to_submit++; } while ((bh = bh->b_this_page) != head); if (!nr_to_submit) { /* * We have nothing to submit. Just cycle the folio through * writeback state to properly update xarray tags. */ __folio_start_writeback(folio, keep_towrite); folio_end_writeback(folio); return 0; } bh = head = folio_buffers(folio); /* * If any blocks are being written to an encrypted file, encrypt them * into a bounce page. For simplicity, just encrypt until the last * block which might be needed. This may cause some unneeded blocks * (e.g. holes) to be unnecessarily encrypted, but this is rare and * can't happen in the common case of blocksize == PAGE_SIZE. */ if (fscrypt_inode_uses_fs_layer_crypto(inode)) { gfp_t gfp_flags = GFP_NOFS; unsigned int enc_bytes = round_up(len, i_blocksize(inode)); struct page *bounce_page; /* * Since bounce page allocation uses a mempool, we can only use * a waiting mask (i.e. request guaranteed allocation) on the * first page of the bio. Otherwise it can deadlock. */ if (io->io_bio) gfp_flags = GFP_NOWAIT; retry_encrypt: bounce_page = fscrypt_encrypt_pagecache_blocks(folio, enc_bytes, 0, gfp_flags); if (IS_ERR(bounce_page)) { ret = PTR_ERR(bounce_page); if (ret == -ENOMEM && (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) { gfp_t new_gfp_flags = GFP_NOFS; if (io->io_bio) ext4_io_submit(io); else new_gfp_flags |= __GFP_NOFAIL; memalloc_retry_wait(gfp_flags); gfp_flags = new_gfp_flags; goto retry_encrypt; } printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret); folio_redirty_for_writepage(wbc, folio); do { if (buffer_async_write(bh)) { clear_buffer_async_write(bh); set_buffer_dirty(bh); } bh = bh->b_this_page; } while (bh != head); return ret; } io_folio = page_folio(bounce_page); } __folio_start_writeback(folio, keep_towrite); /* Now submit buffers to write */ do { if (!buffer_async_write(bh)) continue; io_submit_add_bh(io, inode, folio, io_folio, bh); } while ((bh = bh->b_this_page) != head); return 0; } |
| 3741 4514 4489 137 1968 510 2168 181 2011 168 8 702 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix - mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitrary value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += get_unaligned((u32 *)k); b += get_unaligned((u32 *)(k + 4)); c += get_unaligned((u32 *)(k + 8)); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitrary value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 13 7 9 13 13 12 13 7 9 13 13 13 13 13 13 13 181 180 181 59 2 52 6 6 6 6 6 5 6 6 7 4 7 4 5 5 5 5 5 5 2 4 4 4 4 1 4 4 4 4 4 4 36 32 5 1 9 8 7 8 2 2 2 2 3 1 9 9 9 9 9 10 10 1 1 1 1 9 9 9 9 9 9 9 10 1 1 9 9 1 8 2 7 7 9 32 32 6 6 6 6 6 6 6 4 2 6 5 4 6 2 2 2 207 7 158 39 110 152 193 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 | // SPDX-License-Identifier: GPL-2.0 /* * consolemap.c * * Mapping from internal code (such as Latin-1 or Unicode or IBM PC code) * to font positions. * * aeb, 950210 * * Support for multiple unimaps by Jakub Jelinek <jj@ultra.linux.cz>, July 1998 * * Fix bug in inverse translation. Stanislav Voronyi <stas@cnti.uanet.kharkov.ua>, Dec 1998 * * In order to prevent the following circular lock dependency: * &mm->mmap_lock --> cpu_hotplug.lock --> console_lock --> &mm->mmap_lock * * We cannot allow page fault to happen while holding the console_lock. * Therefore, all the userspace copy operations have to be done outside * the console_lock critical sections. * * As all the affected functions are all called directly from vt_ioctl(), we * can allocate some small buffers directly on stack without worrying about * stack overflow. */ #include <linux/bitfield.h> #include <linux/bits.h> #include <linux/module.h> #include <linux/kd.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/tty.h> #include <linux/uaccess.h> #include <linux/console.h> #include <linux/consolemap.h> #include <linux/vt_kern.h> #include <linux/string.h> static unsigned short translations[][E_TABSZ] = { /* 8-bit Latin-1 mapped to Unicode -- trivial mapping */ [LAT1_MAP] = { 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7, 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df, 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, 0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7, 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff }, /* VT100 graphics mapped to Unicode */ [GRAF_MAP] = { 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x2192, 0x2190, 0x2191, 0x2193, 0x002f, 0x2588, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x00a0, 0x25c6, 0x2592, 0x2409, 0x240c, 0x240d, 0x240a, 0x00b0, 0x00b1, 0x2591, 0x240b, 0x2518, 0x2510, 0x250c, 0x2514, 0x253c, 0x23ba, 0x23bb, 0x2500, 0x23bc, 0x23bd, 0x251c, 0x2524, 0x2534, 0x252c, 0x2502, 0x2264, 0x2265, 0x03c0, 0x2260, 0x00a3, 0x00b7, 0x007f, 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7, 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df, 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, 0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7, 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff }, /* IBM Codepage 437 mapped to Unicode */ [IBMPC_MAP] = { 0x0000, 0x263a, 0x263b, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022, 0x25d8, 0x25cb, 0x25d9, 0x2642, 0x2640, 0x266a, 0x266b, 0x263c, 0x25b6, 0x25c0, 0x2195, 0x203c, 0x00b6, 0x00a7, 0x25ac, 0x21a8, 0x2191, 0x2193, 0x2192, 0x2190, 0x221f, 0x2194, 0x25b2, 0x25bc, 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x2302, 0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7, 0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x00ec, 0x00c4, 0x00c5, 0x00c9, 0x00e6, 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9, 0x00ff, 0x00d6, 0x00dc, 0x00a2, 0x00a3, 0x00a5, 0x20a7, 0x0192, 0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba, 0x00bf, 0x2310, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb, 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556, 0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510, 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567, 0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b, 0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580, 0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4, 0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229, 0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248, 0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0 }, /* User mapping -- default to codes for direct font mapping */ [USER_MAP] = { 0xf000, 0xf001, 0xf002, 0xf003, 0xf004, 0xf005, 0xf006, 0xf007, 0xf008, 0xf009, 0xf00a, 0xf00b, 0xf00c, 0xf00d, 0xf00e, 0xf00f, 0xf010, 0xf011, 0xf012, 0xf013, 0xf014, 0xf015, 0xf016, 0xf017, 0xf018, 0xf019, 0xf01a, 0xf01b, 0xf01c, 0xf01d, 0xf01e, 0xf01f, 0xf020, 0xf021, 0xf022, 0xf023, 0xf024, 0xf025, 0xf026, 0xf027, 0xf028, 0xf029, 0xf02a, 0xf02b, 0xf02c, 0xf02d, 0xf02e, 0xf02f, 0xf030, 0xf031, 0xf032, 0xf033, 0xf034, 0xf035, 0xf036, 0xf037, 0xf038, 0xf039, 0xf03a, 0xf03b, 0xf03c, 0xf03d, 0xf03e, 0xf03f, 0xf040, 0xf041, 0xf042, 0xf043, 0xf044, 0xf045, 0xf046, 0xf047, 0xf048, 0xf049, 0xf04a, 0xf04b, 0xf04c, 0xf04d, 0xf04e, 0xf04f, 0xf050, 0xf051, 0xf052, 0xf053, 0xf054, 0xf055, 0xf056, 0xf057, 0xf058, 0xf059, 0xf05a, 0xf05b, 0xf05c, 0xf05d, 0xf05e, 0xf05f, 0xf060, 0xf061, 0xf062, 0xf063, 0xf064, 0xf065, 0xf066, 0xf067, 0xf068, 0xf069, 0xf06a, 0xf06b, 0xf06c, 0xf06d, 0xf06e, 0xf06f, 0xf070, 0xf071, 0xf072, 0xf073, 0xf074, 0xf075, 0xf076, 0xf077, 0xf078, 0xf079, 0xf07a, 0xf07b, 0xf07c, 0xf07d, 0xf07e, 0xf07f, 0xf080, 0xf081, 0xf082, 0xf083, 0xf084, 0xf085, 0xf086, 0xf087, 0xf088, 0xf089, 0xf08a, 0xf08b, 0xf08c, 0xf08d, 0xf08e, 0xf08f, 0xf090, 0xf091, 0xf092, 0xf093, 0xf094, 0xf095, 0xf096, 0xf097, 0xf098, 0xf099, 0xf09a, 0xf09b, 0xf09c, 0xf09d, 0xf09e, 0xf09f, 0xf0a0, 0xf0a1, 0xf0a2, 0xf0a3, 0xf0a4, 0xf0a5, 0xf0a6, 0xf0a7, 0xf0a8, 0xf0a9, 0xf0aa, 0xf0ab, 0xf0ac, 0xf0ad, 0xf0ae, 0xf0af, 0xf0b0, 0xf0b1, 0xf0b2, 0xf0b3, 0xf0b4, 0xf0b5, 0xf0b6, 0xf0b7, 0xf0b8, 0xf0b9, 0xf0ba, 0xf0bb, 0xf0bc, 0xf0bd, 0xf0be, 0xf0bf, 0xf0c0, 0xf0c1, 0xf0c2, 0xf0c3, 0xf0c4, 0xf0c5, 0xf0c6, 0xf0c7, 0xf0c8, 0xf0c9, 0xf0ca, 0xf0cb, 0xf0cc, 0xf0cd, 0xf0ce, 0xf0cf, 0xf0d0, 0xf0d1, 0xf0d2, 0xf0d3, 0xf0d4, 0xf0d5, 0xf0d6, 0xf0d7, 0xf0d8, 0xf0d9, 0xf0da, 0xf0db, 0xf0dc, 0xf0dd, 0xf0de, 0xf0df, 0xf0e0, 0xf0e1, 0xf0e2, 0xf0e3, 0xf0e4, 0xf0e5, 0xf0e6, 0xf0e7, 0xf0e8, 0xf0e9, 0xf0ea, 0xf0eb, 0xf0ec, 0xf0ed, 0xf0ee, 0xf0ef, 0xf0f0, 0xf0f1, 0xf0f2, 0xf0f3, 0xf0f4, 0xf0f5, 0xf0f6, 0xf0f7, 0xf0f8, 0xf0f9, 0xf0fa, 0xf0fb, 0xf0fc, 0xf0fd, 0xf0fe, 0xf0ff } }; /* The standard kernel character-to-font mappings are not invertible -- this is just a best effort. */ #define MAX_GLYPH 512 /* Max possible glyph value */ static enum translation_map inv_translate[MAX_NR_CONSOLES]; #define UNI_DIRS 32U #define UNI_DIR_ROWS 32U #define UNI_ROW_GLYPHS 64U #define UNI_DIR_BITS GENMASK(15, 11) #define UNI_ROW_BITS GENMASK(10, 6) #define UNI_GLYPH_BITS GENMASK( 5, 0) #define UNI_DIR(uni) FIELD_GET(UNI_DIR_BITS, (uni)) #define UNI_ROW(uni) FIELD_GET(UNI_ROW_BITS, (uni)) #define UNI_GLYPH(uni) FIELD_GET(UNI_GLYPH_BITS, (uni)) #define UNI(dir, row, glyph) (FIELD_PREP(UNI_DIR_BITS, (dir)) | \ FIELD_PREP(UNI_ROW_BITS, (row)) | \ FIELD_PREP(UNI_GLYPH_BITS, (glyph))) /** * struct uni_pagedict - unicode directory * * @uni_pgdir: 32*32*64 table with glyphs * @refcount: reference count of this structure * @sum: checksum * @inverse_translations: best-effort inverse mapping * @inverse_trans_unicode: best-effort inverse mapping to unicode */ struct uni_pagedict { u16 **uni_pgdir[UNI_DIRS]; unsigned long refcount; unsigned long sum; unsigned char *inverse_translations[LAST_MAP + 1]; u16 *inverse_trans_unicode; }; static struct uni_pagedict *dflt; static void set_inverse_transl(struct vc_data *conp, struct uni_pagedict *dict, enum translation_map m) { unsigned short *t = translations[m]; unsigned char *inv; if (!dict) return; inv = dict->inverse_translations[m]; if (!inv) { inv = dict->inverse_translations[m] = kmalloc(MAX_GLYPH, GFP_KERNEL); if (!inv) return; } memset(inv, 0, MAX_GLYPH); for (unsigned int ch = 0; ch < ARRAY_SIZE(translations[m]); ch++) { int glyph = conv_uni_to_pc(conp, t[ch]); if (glyph >= 0 && glyph < MAX_GLYPH && inv[glyph] < 32) { /* prefer '-' above SHY etc. */ inv[glyph] = ch; } } } static void set_inverse_trans_unicode(struct uni_pagedict *dict) { unsigned int d, r, g; u16 *inv; if (!dict) return; inv = dict->inverse_trans_unicode; if (!inv) { inv = dict->inverse_trans_unicode = kmalloc_array(MAX_GLYPH, sizeof(*inv), GFP_KERNEL); if (!inv) return; } memset(inv, 0, MAX_GLYPH * sizeof(*inv)); for (d = 0; d < UNI_DIRS; d++) { u16 **dir = dict->uni_pgdir[d]; if (!dir) continue; for (r = 0; r < UNI_DIR_ROWS; r++) { u16 *row = dir[r]; if (!row) continue; for (g = 0; g < UNI_ROW_GLYPHS; g++) { u16 glyph = row[g]; if (glyph < MAX_GLYPH && inv[glyph] < 32) inv[glyph] = UNI(d, r, g); } } } } unsigned short *set_translate(enum translation_map m, struct vc_data *vc) { inv_translate[vc->vc_num] = m; return translations[m]; } /* * Inverse translation is impossible for several reasons: * 1. The font<->character maps are not 1-1. * 2. The text may have been written while a different translation map * was active. * Still, it is now possible to a certain extent to cut and paste non-ASCII. */ u16 inverse_translate(const struct vc_data *conp, u16 glyph, bool use_unicode) { struct uni_pagedict *p; enum translation_map m; if (glyph >= MAX_GLYPH) return 0; p = *conp->uni_pagedict_loc; if (!p) return glyph; if (use_unicode) { if (!p->inverse_trans_unicode) return glyph; return p->inverse_trans_unicode[glyph]; } m = inv_translate[conp->vc_num]; if (!p->inverse_translations[m]) return glyph; return p->inverse_translations[m][glyph]; } EXPORT_SYMBOL_GPL(inverse_translate); static void update_user_maps(void) { int i; struct uni_pagedict *p, *q = NULL; for (i = 0; i < MAX_NR_CONSOLES; i++) { if (!vc_cons_allocated(i)) continue; p = *vc_cons[i].d->uni_pagedict_loc; if (p && p != q) { set_inverse_transl(vc_cons[i].d, p, USER_MAP); set_inverse_trans_unicode(p); q = p; } } } /* * Load customizable translation table * arg points to a 256 byte translation table. * * The "old" variants are for translation directly to font (using the * 0xf000-0xf0ff "transparent" Unicodes) whereas the "new" variants set * Unicodes explicitly. */ int con_set_trans_old(unsigned char __user * arg) { unsigned short inbuf[E_TABSZ]; unsigned int i; unsigned char ch; for (i = 0; i < ARRAY_SIZE(inbuf); i++) { if (get_user(ch, &arg[i])) return -EFAULT; inbuf[i] = UNI_DIRECT_BASE | ch; } guard(console_lock)(); memcpy(translations[USER_MAP], inbuf, sizeof(inbuf)); update_user_maps(); return 0; } int con_get_trans_old(unsigned char __user * arg) { int i, ch; unsigned short *p = translations[USER_MAP]; unsigned char outbuf[E_TABSZ]; scoped_guard(console_lock) for (i = 0; i < ARRAY_SIZE(outbuf); i++) { ch = conv_uni_to_pc(vc_cons[fg_console].d, p[i]); outbuf[i] = (ch & ~0xff) ? 0 : ch; } return copy_to_user(arg, outbuf, sizeof(outbuf)) ? -EFAULT : 0; } int con_set_trans_new(ushort __user * arg) { unsigned short inbuf[E_TABSZ]; if (copy_from_user(inbuf, arg, sizeof(inbuf))) return -EFAULT; guard(console_lock)(); memcpy(translations[USER_MAP], inbuf, sizeof(inbuf)); update_user_maps(); return 0; } int con_get_trans_new(ushort __user * arg) { unsigned short outbuf[E_TABSZ]; scoped_guard(console_lock) memcpy(outbuf, translations[USER_MAP], sizeof(outbuf)); return copy_to_user(arg, outbuf, sizeof(outbuf)) ? -EFAULT : 0; } /* * Unicode -> current font conversion * * A font has at most 512 chars, usually 256. * But one font position may represent several Unicode chars. * A hashtable is somewhat of a pain to deal with, so use a * "paged table" instead. Simulation has shown the memory cost of * this 3-level paged table scheme to be comparable to a hash table. */ extern u8 dfont_unicount[]; /* Defined in console_defmap.c */ extern u16 dfont_unitable[]; static void con_release_unimap(struct uni_pagedict *dict) { unsigned int d, r; if (dict == dflt) dflt = NULL; for (d = 0; d < UNI_DIRS; d++) { u16 **dir = dict->uni_pgdir[d]; if (dir != NULL) { for (r = 0; r < UNI_DIR_ROWS; r++) kfree(dir[r]); kfree(dir); } dict->uni_pgdir[d] = NULL; } for (r = 0; r < ARRAY_SIZE(dict->inverse_translations); r++) { kfree(dict->inverse_translations[r]); dict->inverse_translations[r] = NULL; } kfree(dict->inverse_trans_unicode); dict->inverse_trans_unicode = NULL; } /* Caller must hold the console lock */ void con_free_unimap(struct vc_data *vc) { struct uni_pagedict *p; p = *vc->uni_pagedict_loc; if (!p) return; *vc->uni_pagedict_loc = NULL; if (--p->refcount) return; con_release_unimap(p); kfree(p); } static int con_unify_unimap(struct vc_data *conp, struct uni_pagedict *dict1) { struct uni_pagedict *dict2; unsigned int cons, d, r; for (cons = 0; cons < MAX_NR_CONSOLES; cons++) { if (!vc_cons_allocated(cons)) continue; dict2 = *vc_cons[cons].d->uni_pagedict_loc; if (!dict2 || dict2 == dict1 || dict2->sum != dict1->sum) continue; for (d = 0; d < UNI_DIRS; d++) { u16 **dir1 = dict1->uni_pgdir[d]; u16 **dir2 = dict2->uni_pgdir[d]; if (!dir1 && !dir2) continue; if (!dir1 || !dir2) break; for (r = 0; r < UNI_DIR_ROWS; r++) { if (!dir1[r] && !dir2[r]) continue; if (!dir1[r] || !dir2[r]) break; if (memcmp(dir1[r], dir2[r], UNI_ROW_GLYPHS * sizeof(*dir1[r]))) break; } if (r < UNI_DIR_ROWS) break; } if (d == UNI_DIRS) { dict2->refcount++; *conp->uni_pagedict_loc = dict2; con_release_unimap(dict1); kfree(dict1); return 1; } } return 0; } static int con_insert_unipair(struct uni_pagedict *p, u_short unicode, u_short fontpos) { u16 **dir, *row; unsigned int n; n = UNI_DIR(unicode); dir = p->uni_pgdir[n]; if (!dir) { dir = p->uni_pgdir[n] = kcalloc(UNI_DIR_ROWS, sizeof(*dir), GFP_KERNEL); if (!dir) return -ENOMEM; } n = UNI_ROW(unicode); row = dir[n]; if (!row) { row = dir[n] = kmalloc_array(UNI_ROW_GLYPHS, sizeof(*row), GFP_KERNEL); if (!row) return -ENOMEM; /* No glyphs for the characters (yet) */ memset(row, 0xff, UNI_ROW_GLYPHS * sizeof(*row)); } row[UNI_GLYPH(unicode)] = fontpos; p->sum += (fontpos << 20U) + unicode; return 0; } static int con_allocate_new(struct vc_data *vc) { struct uni_pagedict *new, *old = *vc->uni_pagedict_loc; new = kzalloc_obj(*new); if (!new) return -ENOMEM; new->refcount = 1; *vc->uni_pagedict_loc = new; if (old) old->refcount--; return 0; } /* Caller must hold the lock */ static int con_do_clear_unimap(struct vc_data *vc) { struct uni_pagedict *old = *vc->uni_pagedict_loc; if (!old || old->refcount > 1) return con_allocate_new(vc); old->sum = 0; con_release_unimap(old); return 0; } int con_clear_unimap(struct vc_data *vc) { guard(console_lock)(); return con_do_clear_unimap(vc); } static struct uni_pagedict *con_unshare_unimap(struct vc_data *vc, struct uni_pagedict *old) { struct uni_pagedict *new; unsigned int d, r, g; int ret; u16 uni = 0; ret = con_allocate_new(vc); if (ret) return ERR_PTR(ret); new = *vc->uni_pagedict_loc; /* * uni_pgdir is a 32*32*64 table with rows allocated when its first * entry is added. The unicode value must still be incremented for * empty rows. We are copying entries from "old" to "new". */ for (d = 0; d < UNI_DIRS; d++) { u16 **dir = old->uni_pgdir[d]; if (!dir) { /* Account for empty table */ uni += UNI_DIR_ROWS * UNI_ROW_GLYPHS; continue; } for (r = 0; r < UNI_DIR_ROWS; r++) { u16 *row = dir[r]; if (!row) { /* Account for row of 64 empty entries */ uni += UNI_ROW_GLYPHS; continue; } for (g = 0; g < UNI_ROW_GLYPHS; g++, uni++) { if (row[g] == 0xffff) continue; /* * Found one, copy entry for unicode uni with * fontpos value row[g]. */ ret = con_insert_unipair(new, uni, row[g]); if (ret) { old->refcount++; *vc->uni_pagedict_loc = old; con_release_unimap(new); kfree(new); return ERR_PTR(ret); } } } } return new; } int con_set_unimap(struct vc_data *vc, ushort ct, struct unipair __user *list) { struct uni_pagedict *dict; struct unipair *plist; int err = 0; if (!ct) return 0; struct unipair *unilist __free(kvfree) = vmemdup_array_user(list, ct, sizeof(*unilist)); if (IS_ERR(unilist)) return PTR_ERR(unilist); guard(console_lock)(); /* Save original vc_unipagdir_loc in case we allocate a new one */ dict = *vc->uni_pagedict_loc; if (!dict) return -EINVAL; if (dict->refcount > 1) { dict = con_unshare_unimap(vc, dict); if (IS_ERR(dict)) return PTR_ERR(dict); } else if (dict == dflt) { dflt = NULL; } /* * Insert user specified unicode pairs into new table. */ for (plist = unilist; ct; ct--, plist++) { int err1 = con_insert_unipair(dict, plist->unicode, plist->fontpos); if (err1) err = err1; } /* * Merge with fontmaps of any other virtual consoles. */ if (con_unify_unimap(vc, dict)) return err; for (enum translation_map m = FIRST_MAP; m <= LAST_MAP; m++) set_inverse_transl(vc, dict, m); set_inverse_trans_unicode(dict); return err; } /** * con_set_default_unimap - set default unicode map * @vc: the console we are updating * * Loads the unimap for the hardware font, as defined in uni_hash.tbl. * The representation used was the most compact I could come up * with. This routine is executed at video setup, and when the * PIO_FONTRESET ioctl is called. * * The caller must hold the console lock */ int con_set_default_unimap(struct vc_data *vc) { struct uni_pagedict *dict; unsigned int fontpos, count; int err = 0, err1; u16 *dfont; if (dflt) { dict = *vc->uni_pagedict_loc; if (dict == dflt) return 0; dflt->refcount++; *vc->uni_pagedict_loc = dflt; if (dict && !--dict->refcount) { con_release_unimap(dict); kfree(dict); } return 0; } /* The default font is always 256 characters */ err = con_do_clear_unimap(vc); if (err) return err; dict = *vc->uni_pagedict_loc; dfont = dfont_unitable; for (fontpos = 0; fontpos < 256U; fontpos++) for (count = dfont_unicount[fontpos]; count; count--) { err1 = con_insert_unipair(dict, *(dfont++), fontpos); if (err1) err = err1; } if (con_unify_unimap(vc, dict)) { dflt = *vc->uni_pagedict_loc; return err; } for (enum translation_map m = FIRST_MAP; m <= LAST_MAP; m++) set_inverse_transl(vc, dict, m); set_inverse_trans_unicode(dict); dflt = dict; return err; } EXPORT_SYMBOL(con_set_default_unimap); /** * con_copy_unimap - copy unimap between two vts * @dst_vc: target * @src_vc: source * * The caller must hold the console lock when invoking this method */ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc) { struct uni_pagedict *src; if (!*src_vc->uni_pagedict_loc) return -EINVAL; if (*dst_vc->uni_pagedict_loc == *src_vc->uni_pagedict_loc) return 0; con_free_unimap(dst_vc); src = *src_vc->uni_pagedict_loc; src->refcount++; *dst_vc->uni_pagedict_loc = src; return 0; } EXPORT_SYMBOL(con_copy_unimap); /* * con_get_unimap - get the unicode map * * Read the console unicode data for this console. Called from the ioctl * handlers. */ int con_get_unimap(struct vc_data *vc, ushort ct, ushort __user *uct, struct unipair __user *list) { ushort ect; struct uni_pagedict *dict; unsigned int d, r, g; struct unipair *unilist __free(kvfree) = kvmalloc_array(ct, sizeof(*unilist), GFP_KERNEL); if (!unilist) return -ENOMEM; scoped_guard(console_lock) { ect = 0; dict = *vc->uni_pagedict_loc; if (!dict) break; for (d = 0; d < UNI_DIRS; d++) { u16 **dir = dict->uni_pgdir[d]; if (!dir) continue; for (r = 0; r < UNI_DIR_ROWS; r++) { u16 *row = dir[r]; if (!row) continue; for (g = 0; g < UNI_ROW_GLYPHS; g++, row++) { if (*row >= MAX_GLYPH) continue; if (ect < ct) { unilist[ect].unicode = UNI(d, r, g); unilist[ect].fontpos = *row; } ect++; } } } } if (copy_to_user(list, unilist, min(ect, ct) * sizeof(*unilist))) return -EFAULT; if (put_user(ect, uct)) return -EFAULT; if (ect > ct) return -ENOMEM; return 0; } /* * Always use USER_MAP. These functions are used by the keyboard, * which shouldn't be affected by G0/G1 switching, etc. * If the user map still contains default values, i.e. the * direct-to-font mapping, then assume user is using Latin1. * * FIXME: at some point we need to decide if we want to lock the table * update element itself via the keyboard_event_lock for consistency with the * keyboard driver as well as the consoles */ /* may be called during an interrupt */ u32 conv_8bit_to_uni(unsigned char c) { unsigned short uni = translations[USER_MAP][c]; return uni == (0xf000 | c) ? c : uni; } int conv_uni_to_8bit(u32 uni) { int c; for (c = 0; c < ARRAY_SIZE(translations[USER_MAP]); c++) if (translations[USER_MAP][c] == uni || (translations[USER_MAP][c] == (c | 0xf000) && uni == c)) return c; return -1; } int conv_uni_to_pc(struct vc_data *conp, long ucs) { struct uni_pagedict *dict; u16 **dir, *row, glyph; /* Only 16-bit codes supported at this time */ if (ucs > 0xffff) return -4; /* Not found */ else if (ucs < 0x20) return -1; /* Not a printable character */ /* * UNI_DIRECT_BASE indicates the start of the region in the User Zone * which always has a 1:1 mapping to the currently loaded font. The * UNI_DIRECT_MASK indicates the bit span of the region. */ else if ((ucs & ~UNI_DIRECT_MASK) == UNI_DIRECT_BASE) return ucs & UNI_DIRECT_MASK; dict = *conp->uni_pagedict_loc; if (!dict) return -3; dir = dict->uni_pgdir[UNI_DIR(ucs)]; if (!dir) return -4; row = dir[UNI_ROW(ucs)]; if (!row) return -4; glyph = row[UNI_GLYPH(ucs)]; if (glyph >= MAX_GLYPH) return -4; return glyph; } /* * This is called at sys_setup time, after memory and the console are * initialized. It must be possible to call kmalloc(..., GFP_KERNEL) * from this function, hence the call from sys_setup. */ void __init console_map_init(void) { int i; for (i = 0; i < MAX_NR_CONSOLES; i++) if (vc_cons_allocated(i) && !*vc_cons[i].d->uni_pagedict_loc) con_set_default_unimap(vc_cons[i].d); } |
| 100 564 476 94 309 294 402 497 465 497 476 475 476 441 401 22 36 609 576 11 31 24 21 25 8 30 361 286 16 16 3 16 14 19 19 19 19 9 19 28 28 28 28 28 12 27 24 17 7 7 3 21 24 24 24 17 7 24 24 12 17 545 567 423 371 422 421 573 566 28 19 28 24 610 604 595 447 469 238 20 503 28 410 409 401 80 5 402 351 58 410 410 410 526 526 525 238 286 525 449 526 449 449 241 447 449 449 241 39 410 410 410 410 409 448 526 526 239 286 523 526 526 525 526 125 526 401 125 526 526 116 326 84 526 649 523 164 588 587 588 586 588 473 114 115 588 587 587 587 467 466 462 467 258 259 15 259 294 62 294 475 476 117 476 221 94 190 207 187 152 221 180 308 16 293 294 294 7 7 287 169 176 38 283 217 184 222 174 158 221 459 69 453 453 453 234 210 228 453 466 466 264 323 466 466 117 446 420 208 430 430 208 205 3 205 3 460 459 460 398 160 363 232 451 299 355 207 229 451 299 358 123 206 207 207 206 574 547 33 20 95 10 85 30 2 2 30 74 42 21 21 42 41 42 450 451 299 292 451 13 13 13 12 12 1 12 42 424 28 27 13 12 451 488 488 30 392 42 42 43 307 137 573 571 100 99 573 104 514 338 241 130 109 104 489 572 100 573 573 573 47 55 260 181 1 573 299 275 571 504 2 570 504 67 571 574 574 574 341 20 425 207 383 459 575 30 371 101 286 461 212 324 574 567 574 502 206 574 574 34 571 658 655 655 654 656 655 656 656 654 655 654 655 656 656 656 654 644 12 655 1 301 354 654 655 1 1 1 1 1 1 1 654 653 26 32 32 32 32 656 655 656 656 656 655 655 620 35 656 656 656 1 1 31 1 31 31 31 31 31 31 31 31 31 31 31 21 21 21 21 21 548 7 547 2 551 551 551 550 469 259 7 546 275 275 276 241 132 551 549 469 469 469 7 462 206 33 33 33 186 33 33 26 10 27 27 10 9 27 27 24 33 574 366 206 188 189 154 46 189 140 31 10 13 13 188 87 118 188 189 185 189 188 2 7 92 118 117 583 575 137 32 26 1 3 3 138 138 138 138 138 78 78 1 1 94 584 346 353 24 93 94 94 28 94 94 214 216 216 216 216 2 78 216 213 78 409 409 156 79 123 518 241 63 63 61 7 131 132 74 94 94 19 89 28 94 132 132 131 132 131 131 161 160 161 161 160 161 132 104 104 104 104 27 104 104 102 2 104 78 79 79 79 193 99 93 93 11 93 93 93 93 79 21 93 79 21 93 835 286 695 695 93 693 94 93 94 94 94 574 478 478 475 345 363 363 314 69 216 583 584 581 584 164 1 164 164 164 477 138 164 164 7 163 164 241 252 460 252 460 482 216 584 193 193 193 192 193 193 93 100 100 607 608 549 73 57 100 73 72 3 472 471 527 584 137 574 26 336 363 7 463 193 462 584 514 89 57 529 585 314 35 300 298 300 41 258 259 259 245 14 259 259 259 2 259 332 283 73 1 332 14 332 281 74 312 7 38 294 45 4 27 234 121 121 314 8 8 9 9 17 17 11 2 9 3 1 4 8 8 8 3 8 6 3 12 12 12 20 20 20 20 1 1 2 16 16 1 13 4 13 13 1 12 12 18 22 2 21 4 16 15 7 6 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> */ /* * mballoc.c contains the multiblocks allocation routines */ #include "ext4_jbd2.h" #include "mballoc.h" #include <linux/log2.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/nospec.h> #include <linux/backing-dev.h> #include <linux/freezer.h> #include <trace/events/ext4.h> #include <kunit/static_stub.h> /* * MUSTDO: * - test ext4_ext_search_left() and ext4_ext_search_right() * - search for metadata in few groups * * TODO v4: * - normalization should take into account whether file is still open * - discard preallocations if no free space left (policy?) * - don't normalize tails * - quota * - reservation for superuser * * TODO v3: * - bitmap read-ahead (proposed by Oleg Drokin aka green) * - track min/max extents in each group for better group selection * - mb_mark_used() may allocate chunk right after splitting buddy * - tree of groups sorted by number of free blocks * - error handling */ /* * The allocation request involve request for multiple number of blocks * near to the goal(block) value specified. * * During initialization phase of the allocator we decide to use the * group preallocation or inode preallocation depending on the size of * the file. The size of the file could be the resulting file size we * would have after allocation, or the current file size, which ever * is larger. If the size is less than sbi->s_mb_stream_request we * select to use the group preallocation. The default value of * s_mb_stream_request is 16 blocks. This can also be tuned via * /sys/fs/ext4/<partition>/mb_stream_req. The value is represented in * terms of number of blocks. * * The main motivation for having small file use group preallocation is to * ensure that we have small files closer together on the disk. * * First stage the allocator looks at the inode prealloc list, * ext4_inode_info->i_prealloc_list, which contains list of prealloc * spaces for this particular inode. The inode prealloc space is * represented as: * * pa_lstart -> the logical start block for this prealloc space * pa_pstart -> the physical start block for this prealloc space * pa_len -> length for this prealloc space (in clusters) * pa_free -> free space available in this prealloc space (in clusters) * * The inode preallocation space is used looking at the _logical_ start * block. If only the logical file block falls within the range of prealloc * space we will consume the particular prealloc space. This makes sure that * we have contiguous physical blocks representing the file blocks * * The important thing to be noted in case of inode prealloc space is that * we don't modify the values associated to inode prealloc space except * pa_free. * * If we are not able to find blocks in the inode prealloc space and if we * have the group allocation flag set then we look at the locality group * prealloc space. These are per CPU prealloc list represented as * * ext4_sb_info.s_locality_groups[smp_processor_id()] * * The reason for having a per cpu locality group is to reduce the contention * between CPUs. It is possible to get scheduled at this point. * * The locality group prealloc space is used looking at whether we have * enough free space (pa_free) within the prealloc space. * * If we can't allocate blocks via inode prealloc or/and locality group * prealloc then we look at the buddy cache. The buddy cache is represented * by ext4_sb_info.s_buddy_cache (struct inode) whose file offset gets * mapped to the buddy and bitmap information regarding different * groups. The buddy information is attached to buddy cache inode so that * we can access them through the page cache. The information regarding * each group is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are stored in the * inode as: * * { folio } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. So for each group we * take up 2 blocks. A folio can contain blocks_per_folio (folio_size / * blocksize) blocks. So it can have information regarding groups_per_folio * which is blocks_per_folio/2 * * The buddy cache inode is not stored on disk. The inode is thrown * away when the filesystem is unmounted. * * We look for count number of blocks in the buddy cache. If we were able * to locate that many free blocks we return with additional information * regarding rest of the contiguous physical block available * * Before allocating blocks via buddy cache we normalize the request * blocks. This ensure we ask for more blocks that we needed. The extra * blocks that we get after allocation is added to the respective prealloc * list. In case of inode preallocation we follow a list of heuristics * based on file size. This can be found in ext4_mb_normalize_request. If * we are doing a group prealloc we try to normalize the request to * sbi->s_mb_group_prealloc. The default value of s_mb_group_prealloc is * dependent on the cluster size; for non-bigalloc file systems, it is * 512 blocks. This can be tuned via * /sys/fs/ext4/<partition>/mb_group_prealloc. The value is represented in * terms of number of blocks. If we have mounted the file system with -O * stripe=<value> option the group prealloc request is normalized to the * smallest multiple of the stripe value (sbi->s_stripe) which is * greater than the default mb_group_prealloc. * * If "mb_optimize_scan" mount option is set, we maintain in memory group info * structures in two data structures: * * 1) Array of largest free order xarrays (sbi->s_mb_largest_free_orders) * * Locking: Writers use xa_lock, readers use rcu_read_lock. * * This is an array of xarrays where the index in the array represents the * largest free order in the buddy bitmap of the participating group infos of * that xarray. So, there are exactly MB_NUM_ORDERS(sb) (which means total * number of buddy bitmap orders possible) number of xarrays. Group-infos are * placed in appropriate xarrays. * * 2) Average fragment size xarrays (sbi->s_mb_avg_fragment_size) * * Locking: Writers use xa_lock, readers use rcu_read_lock. * * This is an array of xarrays where in the i-th xarray there are groups with * average fragment size >= 2^i and < 2^(i+1). The average fragment size * is computed as ext4_group_info->bb_free / ext4_group_info->bb_fragments. * Note that we don't bother with a special xarray for completely empty * groups so we only have MB_NUM_ORDERS(sb) xarrays. Group-infos are placed * in appropriate xarrays. * * In xarray, the index is the block group number, the value is the block group * information, and a non-empty value indicates the block group is present in * the current xarray. * * When "mb_optimize_scan" mount option is set, mballoc consults the above data * structures to decide the order in which groups are to be traversed for * fulfilling an allocation request. * * At CR_POWER2_ALIGNED , we look for groups which have the largest_free_order * >= the order of the request. We directly look at the largest free order list * in the data structure (1) above where largest_free_order = order of the * request. If that list is empty, we look at remaining list in the increasing * order of largest_free_order. This allows us to perform CR_POWER2_ALIGNED * lookup in O(1) time. * * At CR_GOAL_LEN_FAST, we only consider groups where * average fragment size > request size. So, we lookup a group which has average * fragment size just above or equal to request size using our average fragment * size group lists (data structure 2) in O(1) time. * * At CR_BEST_AVAIL_LEN, we aim to optimize allocations which can't be satisfied * in CR_GOAL_LEN_FAST. The fact that we couldn't find a group in * CR_GOAL_LEN_FAST suggests that there is no BG that has avg * fragment size > goal length. So before falling to the slower * CR_GOAL_LEN_SLOW, in CR_BEST_AVAIL_LEN we proactively trim goal length and * then use the same fragment lists as CR_GOAL_LEN_FAST to find a BG with a big * enough average fragment size. This increases the chances of finding a * suitable block group in O(1) time and results in faster allocation at the * cost of reduced size of allocation. * * If "mb_optimize_scan" mount option is not set, mballoc traverses groups in * linear order which requires O(N) search time for each CR_POWER2_ALIGNED and * CR_GOAL_LEN_FAST phase. * * The regular allocator (using the buddy cache) supports a few tunables. * * /sys/fs/ext4/<partition>/mb_min_to_scan * /sys/fs/ext4/<partition>/mb_max_to_scan * /sys/fs/ext4/<partition>/mb_order2_req * /sys/fs/ext4/<partition>/mb_max_linear_groups * * The regular allocator uses buddy scan only if the request len is power of * 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The * value of s_mb_order2_reqs can be tuned via * /sys/fs/ext4/<partition>/mb_order2_req. If the request len is equal to * stripe size (sbi->s_stripe), we try to search for contiguous block in * stripe size. This should result in better allocation on RAID setups. If * not, we search in the specific group using bitmap for best extents. The * tunable min_to_scan and max_to_scan control the behaviour here. * min_to_scan indicate how long the mballoc __must__ look for a best * extent and max_to_scan indicates how long the mballoc __can__ look for a * best extent in the found extents. Searching for the blocks starts with * the group specified as the goal value in allocation context via * ac_g_ex. Each group is first checked based on the criteria whether it * can be used for allocation. ext4_mb_good_group explains how the groups are * checked. * * When "mb_optimize_scan" is turned on, as mentioned above, the groups may not * get traversed linearly. That may result in subsequent allocations being not * close to each other. And so, the underlying device may get filled up in a * non-linear fashion. While that may not matter on non-rotational devices, for * rotational devices that may result in higher seek times. "mb_max_linear_groups" * tells mballoc how many groups mballoc should search linearly before * performing consulting above data structures for more efficient lookups. For * non rotational devices, this value defaults to 0 and for rotational devices * this is set to MB_DEFAULT_LINEAR_LIMIT. * * Both the prealloc space are getting populated as above. So for the first * request we will hit the buddy cache which will result in this prealloc * space getting filled. The prealloc space is then later used for the * subsequent request. */ /* * mballoc operates on the following data: * - on-disk bitmap * - in-core buddy (actually includes buddy and bitmap) * - preallocation descriptors (PAs) * * there are two types of preallocations: * - inode * assiged to specific inode and can be used for this inode only. * it describes part of inode's space preallocated to specific * physical blocks. any block from that preallocated can be used * independent. the descriptor just tracks number of blocks left * unused. so, before taking some block from descriptor, one must * make sure corresponded logical block isn't allocated yet. this * also means that freeing any block within descriptor's range * must discard all preallocated blocks. * - locality group * assigned to specific locality group which does not translate to * permanent set of inodes: inode can join and leave group. space * from this type of preallocation can be used for any inode. thus * it's consumed from the beginning to the end. * * relation between them can be expressed as: * in-core buddy = on-disk bitmap + preallocation descriptors * * this mean blocks mballoc considers used are: * - allocated blocks (persistent) * - preallocated blocks (non-persistent) * * consistency in mballoc world means that at any time a block is either * free or used in ALL structures. notice: "any time" should not be read * literally -- time is discrete and delimited by locks. * * to keep it simple, we don't use block numbers, instead we count number of * blocks: how many blocks marked used/free in on-disk bitmap, buddy and PA. * * all operations can be expressed as: * - init buddy: buddy = on-disk + PAs * - new PA: buddy += N; PA = N * - use inode PA: on-disk += N; PA -= N * - discard inode PA buddy -= on-disk - PA; PA = 0 * - use locality group PA on-disk += N; PA -= N * - discard locality group PA buddy -= PA; PA = 0 * note: 'buddy -= on-disk - PA' is used to show that on-disk bitmap * is used in real operation because we can't know actual used * bits from PA, only from on-disk bitmap * * if we follow this strict logic, then all operations above should be atomic. * given some of them can block, we'd have to use something like semaphores * killing performance on high-end SMP hardware. let's try to relax it using * the following knowledge: * 1) if buddy is referenced, it's already initialized * 2) while block is used in buddy and the buddy is referenced, * nobody can re-allocate that block * 3) we work on bitmaps and '+' actually means 'set bits'. if on-disk has * bit set and PA claims same block, it's OK. IOW, one can set bit in * on-disk bitmap if buddy has same bit set or/and PA covers corresponded * block * * so, now we're building a concurrency table: * - init buddy vs. * - new PA * blocks for PA are allocated in the buddy, buddy must be referenced * until PA is linked to allocation group to avoid concurrent buddy init * - use inode PA * we need to make sure that either on-disk bitmap or PA has uptodate data * given (3) we care that PA-=N operation doesn't interfere with init * - discard inode PA * the simplest way would be to have buddy initialized by the discard * - use locality group PA * again PA-=N must be serialized with init * - discard locality group PA * the simplest way would be to have buddy initialized by the discard * - new PA vs. * - use inode PA * i_data_sem serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * some mutex should serialize them * - discard locality group PA * discard process must wait until PA isn't used by another process * - use inode PA * - use inode PA * i_data_sem or another mutex should serializes them * - discard inode PA * discard process must wait until PA isn't used by another process * - use locality group PA * nothing wrong here -- they're different PAs covering different blocks * - discard locality group PA * discard process must wait until PA isn't used by another process * * now we're ready to make few consequences: * - PA is referenced and while it is no discard is possible * - PA is referenced until block isn't marked in on-disk bitmap * - PA changes only after on-disk bitmap * - discard must not compete with init. either init is done before * any discard or they're serialized somehow * - buddy init as sum of on-disk bitmap and PAs is done atomically * * a special case when we've used PA to emptiness. no need to modify buddy * in this case, but we should care about concurrent init * */ /* * Logic in few words: * * - allocation: * load group * find blocks * mark bits in on-disk bitmap * release group * * - use preallocation: * find proper PA (per-inode or group) * load group * mark bits in on-disk bitmap * release group * release PA * * - free: * load group * mark bits in on-disk bitmap * release group * * - discard preallocations in group: * mark PAs deleted * move them onto local list * load on-disk bitmap * load group * remove PA from object (inode or locality group) * mark free blocks in-core * * - discard inode's preallocations: */ /* * Locking rules * * Locks: * - bitlock on a group (group) * - object (inode/locality) (object) * - per-pa lock (pa) * - cr_power2_aligned lists lock (cr_power2_aligned) * - cr_goal_len_fast lists lock (cr_goal_len_fast) * * Paths: * - new pa * object * group * * - find and use pa: * pa * * - release consumed pa: * pa * group * object * * - generate in-core bitmap: * group * pa * * - discard all for given object (inode, locality group): * object * pa * group * * - discard all for given group: * group * pa * group * object * * - allocation path (ext4_mb_regular_allocator) * group * cr_power2_aligned/cr_goal_len_fast */ static struct kmem_cache *ext4_pspace_cachep; static struct kmem_cache *ext4_ac_cachep; static struct kmem_cache *ext4_free_data_cachep; /* We create slab caches for groupinfo data structures based on the * superblock block size. There will be one per mounted filesystem for * each unique s_blocksize_bits */ #define NR_GRPINFO_CACHES 8 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES]; static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { "ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k", "ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k", "ext4_groupinfo_64k", "ext4_groupinfo_128k" }; static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); static int ext4_mb_scan_group(struct ext4_allocation_context *ac, ext4_group_t group); static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks); /* * The algorithm using this percpu seq counter goes below: * 1. We sample the percpu discard_pa_seq counter before trying for block * allocation in ext4_mb_new_blocks(). * 2. We increment this percpu discard_pa_seq counter when we either allocate * or free these blocks i.e. while marking those blocks as used/free in * mb_mark_used()/mb_free_blocks(). * 3. We also increment this percpu seq counter when we successfully identify * that the bb_prealloc_list is not empty and hence proceed for discarding * of those PAs inside ext4_mb_discard_group_preallocations(). * * Now to make sure that the regular fast path of block allocation is not * affected, as a small optimization we only sample the percpu seq counter * on that cpu. Only when the block allocation fails and when freed blocks * found were 0, that is when we sample percpu seq counter for all cpus using * below function ext4_get_discard_pa_seq_sum(). This happens after making * sure that all the PAs on grp->bb_prealloc_list got freed or if it's empty. */ static DEFINE_PER_CPU(u64, discard_pa_seq); static inline u64 ext4_get_discard_pa_seq_sum(void) { int __cpu; u64 __seq = 0; for_each_possible_cpu(__cpu) __seq += per_cpu(discard_pa_seq, __cpu); return __seq; } static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { #if BITS_PER_LONG == 64 *bit += ((unsigned long) addr & 7UL) << 3; addr = (void *) ((unsigned long) addr & ~7UL); #elif BITS_PER_LONG == 32 *bit += ((unsigned long) addr & 3UL) << 3; addr = (void *) ((unsigned long) addr & ~3UL); #else #error "how many bits you are?!" #endif return addr; } static inline int mb_test_bit(int bit, void *addr) { /* * ext4_test_bit on architecture like powerpc * needs unsigned long aligned address */ addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_bit(bit, addr); } static inline void mb_set_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_set_bit(bit, addr); } static inline void mb_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); ext4_clear_bit(bit, addr); } static inline int mb_test_and_clear_bit(int bit, void *addr) { addr = mb_correct_addr_and_bit(&bit, addr); return ext4_test_and_clear_bit(bit, addr); } static inline int mb_find_next_zero_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_zero_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static inline int mb_find_next_bit(void *addr, int max, int start) { int fix = 0, ret, tmpmax; addr = mb_correct_addr_and_bit(&fix, addr); tmpmax = max + fix; start += fix; ret = ext4_find_next_bit(addr, tmpmax, start) - fix; if (ret > max) return max; return ret; } static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max) { char *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(max == NULL); if (order > e4b->bd_blkbits + 1) { *max = 0; return NULL; } /* at order 0 we see each particular block */ if (order == 0) { *max = 1 << (e4b->bd_blkbits + 3); return e4b->bd_bitmap; } bb = e4b->bd_buddy + EXT4_SB(e4b->bd_sb)->s_mb_offsets[order]; *max = EXT4_SB(e4b->bd_sb)->s_mb_maxs[order]; return bb; } #ifdef DOUBLE_CHECK static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int i; struct super_block *sb = e4b->bd_sb; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); for (i = 0; i < count; i++) { if (!mb_test_bit(first + i, e4b->bd_info->bb_bitmap)) { ext4_fsblk_t blocknr; blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(EXT4_SB(sb), first + i); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing block already freed " "(bit %u)", first + i); } mb_clear_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { int i; if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); for (i = 0; i < count; i++) { BUG_ON(mb_test_bit(first + i, e4b->bd_info->bb_bitmap)); mb_set_bit(first + i, e4b->bd_info->bb_bitmap); } } static void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { if (unlikely(e4b->bd_info->bb_bitmap == NULL)) return; if (memcmp(e4b->bd_info->bb_bitmap, bitmap, e4b->bd_sb->s_blocksize)) { unsigned char *b1, *b2; int i; b1 = (unsigned char *) e4b->bd_info->bb_bitmap; b2 = (unsigned char *) bitmap; for (i = 0; i < e4b->bd_sb->s_blocksize; i++) { if (b1[i] != b2[i]) { ext4_msg(e4b->bd_sb, KERN_ERR, "corruption in group %u " "at byte %u(%u): %x in copy != %x " "on disk/prealloc", e4b->bd_group, i, i * 8, b1[i], b2[i]); BUG(); } } } } static void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { struct buffer_head *bh; grp->bb_bitmap = kmalloc(sb->s_blocksize, GFP_NOFS); if (!grp->bb_bitmap) return; bh = ext4_read_block_bitmap(sb, group); if (IS_ERR_OR_NULL(bh)) { kfree(grp->bb_bitmap); grp->bb_bitmap = NULL; return; } memcpy(grp->bb_bitmap, bh->b_data, sb->s_blocksize); put_bh(bh); } static void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { kfree(grp->bb_bitmap); } #else static inline void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_mark_used_double(struct ext4_buddy *e4b, int first, int count) { return; } static inline void mb_cmp_bitmaps(struct ext4_buddy *e4b, void *bitmap) { return; } static inline void mb_group_bb_bitmap_alloc(struct super_block *sb, struct ext4_group_info *grp, ext4_group_t group) { return; } static inline void mb_group_bb_bitmap_free(struct ext4_group_info *grp) { return; } #endif #ifdef AGGRESSIVE_CHECK #define MB_CHECK_ASSERT(assert) \ do { \ if (!(assert)) { \ printk(KERN_EMERG \ "Assertion failure in %s() at %s:%d: \"%s\"\n", \ function, file, line, # assert); \ BUG(); \ } \ } while (0) /* * Perform buddy integrity check with the following steps: * * 1. Top-down validation (from highest order down to order 1, excluding order-0 bitmap): * For each pair of adjacent orders, if a higher-order bit is set (indicating a free block), * at most one of the two corresponding lower-order bits may be clear (free). * * 2. Order-0 (bitmap) validation, performed on bit pairs: * - If either bit in a pair is set (1, allocated), then all corresponding higher-order bits * must not be free (0). * - If both bits in a pair are clear (0, free), then exactly one of the corresponding * higher-order bits must be free (0). * * 3. Preallocation (pa) list validation: * For each preallocated block (pa) in the group: * - Verify that pa_pstart falls within the bounds of this block group. * - Ensure the corresponding bit(s) in the order-0 bitmap are marked as allocated (1). */ static void __mb_check_buddy(struct ext4_buddy *e4b, char *file, const char *function, int line) { struct super_block *sb = e4b->bd_sb; int order = e4b->bd_blkbits + 1; int max; int max2; int i; int j; int k; int count; struct ext4_group_info *grp; int fragments = 0; int fstart; struct list_head *cur; void *buddy; void *buddy2; if (e4b->bd_info->bb_check_counter++ % 10) return; while (order > 1) { buddy = mb_find_buddy(e4b, order, &max); MB_CHECK_ASSERT(buddy); buddy2 = mb_find_buddy(e4b, order - 1, &max2); MB_CHECK_ASSERT(buddy2); MB_CHECK_ASSERT(buddy != buddy2); MB_CHECK_ASSERT(max * 2 == max2); count = 0; for (i = 0; i < max; i++) { if (mb_test_bit(i, buddy)) { /* only single bit in buddy2 may be 0 */ if (!mb_test_bit(i << 1, buddy2)) { MB_CHECK_ASSERT( mb_test_bit((i<<1)+1, buddy2)); } continue; } count++; } MB_CHECK_ASSERT(e4b->bd_info->bb_counters[order] == count); order--; } fstart = -1; buddy = mb_find_buddy(e4b, 0, &max); for (i = 0; i < max; i++) { if (!mb_test_bit(i, buddy)) { MB_CHECK_ASSERT(i >= e4b->bd_info->bb_first_free); if (fstart == -1) { fragments++; fstart = i; } } else { fstart = -1; } if (!(i & 1)) { int in_use, zero_bit_count = 0; in_use = mb_test_bit(i, buddy) || mb_test_bit(i + 1, buddy); for (j = 1; j < e4b->bd_blkbits + 2; j++) { buddy2 = mb_find_buddy(e4b, j, &max2); k = i >> j; MB_CHECK_ASSERT(k < max2); if (!mb_test_bit(k, buddy2)) zero_bit_count++; } MB_CHECK_ASSERT(zero_bit_count == !in_use); } } MB_CHECK_ASSERT(!EXT4_MB_GRP_NEED_INIT(e4b->bd_info)); MB_CHECK_ASSERT(e4b->bd_info->bb_fragments == fragments); grp = ext4_get_group_info(sb, e4b->bd_group); if (!grp) return; list_for_each(cur, &grp->bb_prealloc_list) { ext4_group_t groupnr; struct ext4_prealloc_space *pa; pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); if (!pa->pa_len) continue; ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &k); MB_CHECK_ASSERT(groupnr == e4b->bd_group); for (i = 0; i < pa->pa_len; i++) MB_CHECK_ASSERT(mb_test_bit(k + i, buddy)); } } #undef MB_CHECK_ASSERT #define mb_check_buddy(e4b) __mb_check_buddy(e4b, \ __FILE__, __func__, __LINE__) #else #define mb_check_buddy(e4b) #endif /* * Divide blocks started from @first with length @len into * smaller chunks with power of 2 blocks. * Clear the bits in bitmap which the blocks of the chunk(s) covered, * then increase bb_counters[] for corresponded chunk size. */ static void ext4_mb_mark_free_simple(struct super_block *sb, void *buddy, ext4_grpblk_t first, ext4_grpblk_t len, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t min; ext4_grpblk_t max; ext4_grpblk_t chunk; unsigned int border; BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb)); border = 2 << sb->s_blocksize_bits; while (len > 0) { /* find how many blocks can be covered since this position */ max = ffs(first | border) - 1; /* find how many blocks of power 2 we need to mark */ min = fls(len) - 1; if (max < min) min = max; chunk = 1 << min; /* mark multiblock chunks only */ grp->bb_counters[min]++; if (min > 0) mb_clear_bit(first >> min, buddy + sbi->s_mb_offsets[min]); len -= chunk; first += chunk; } } static int mb_avg_fragment_size_order(struct super_block *sb, ext4_grpblk_t len) { int order; /* * We don't bother with a special lists groups with only 1 block free * extents and for completely empty groups. */ order = fls(len) - 2; if (order < 0) return 0; if (order == MB_NUM_ORDERS(sb)) order--; if (WARN_ON_ONCE(order > MB_NUM_ORDERS(sb))) order = MB_NUM_ORDERS(sb) - 1; return order; } /* Move group to appropriate avg_fragment_size list */ static void mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); int new, old; if (!test_opt2(sb, MB_OPTIMIZE_SCAN)) return; old = grp->bb_avg_fragment_size_order; new = grp->bb_fragments == 0 ? -1 : mb_avg_fragment_size_order(sb, grp->bb_free / grp->bb_fragments); if (new == old) return; if (old >= 0) xa_erase(&sbi->s_mb_avg_fragment_size[old], grp->bb_group); grp->bb_avg_fragment_size_order = new; if (new >= 0) { /* * Cannot use __GFP_NOFAIL because we hold the group lock. * Although allocation for insertion may fails, it's not fatal * as we have linear traversal to fall back on. */ int err = xa_insert(&sbi->s_mb_avg_fragment_size[new], grp->bb_group, grp, GFP_ATOMIC); if (err) mb_debug(sb, "insert group: %u to s_mb_avg_fragment_size[%d] failed, err %d", grp->bb_group, new, err); } } static ext4_group_t ext4_get_allocation_groups_count( struct ext4_allocation_context *ac) { ext4_group_t ngroups = ext4_get_groups_count(ac->ac_sb); /* non-extent files are limited to low blocks/groups */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS))) ngroups = EXT4_SB(ac->ac_sb)->s_blockfile_groups; /* Pairs with smp_wmb() in ext4_update_super() */ smp_rmb(); return ngroups; } static int ext4_mb_scan_groups_xa_range(struct ext4_allocation_context *ac, struct xarray *xa, ext4_group_t start, ext4_group_t end) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); enum criteria cr = ac->ac_criteria; ext4_group_t ngroups = ext4_get_allocation_groups_count(ac); unsigned long group = start; struct ext4_group_info *grp; if (WARN_ON_ONCE(end > ngroups || start >= end)) return 0; xa_for_each_range(xa, group, grp, start, end - 1) { int err; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[cr]); err = ext4_mb_scan_group(ac, grp->bb_group); if (err || ac->ac_status != AC_STATUS_CONTINUE) return err; cond_resched(); } return 0; } /* * Find a suitable group of given order from the largest free orders xarray. */ static inline int ext4_mb_scan_groups_largest_free_order_range(struct ext4_allocation_context *ac, int order, ext4_group_t start, ext4_group_t end) { struct xarray *xa = &EXT4_SB(ac->ac_sb)->s_mb_largest_free_orders[order]; if (xa_empty(xa)) return 0; return ext4_mb_scan_groups_xa_range(ac, xa, start, end); } /* * Choose next group by traversing largest_free_order lists. Updates *new_cr if * cr level needs an update. */ static int ext4_mb_scan_groups_p2_aligned(struct ext4_allocation_context *ac, ext4_group_t group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int i; int ret = 0; ext4_group_t start, end; start = group; end = ext4_get_allocation_groups_count(ac); wrap_around: for (i = ac->ac_2order; i < MB_NUM_ORDERS(ac->ac_sb); i++) { ret = ext4_mb_scan_groups_largest_free_order_range(ac, i, start, end); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; } if (start) { end = start; start = 0; goto wrap_around; } if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_failed[ac->ac_criteria]); /* Increment cr and search again if no group is found */ ac->ac_criteria = CR_GOAL_LEN_FAST; return ret; } /* * Find a suitable group of given order from the average fragments xarray. */ static int ext4_mb_scan_groups_avg_frag_order_range(struct ext4_allocation_context *ac, int order, ext4_group_t start, ext4_group_t end) { struct xarray *xa = &EXT4_SB(ac->ac_sb)->s_mb_avg_fragment_size[order]; if (xa_empty(xa)) return 0; return ext4_mb_scan_groups_xa_range(ac, xa, start, end); } /* * Choose next group by traversing average fragment size list of suitable * order. Updates *new_cr if cr level needs an update. */ static int ext4_mb_scan_groups_goal_fast(struct ext4_allocation_context *ac, ext4_group_t group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int i, ret = 0; ext4_group_t start, end; start = group; end = ext4_get_allocation_groups_count(ac); wrap_around: i = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); for (; i < MB_NUM_ORDERS(ac->ac_sb); i++) { ret = ext4_mb_scan_groups_avg_frag_order_range(ac, i, start, end); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; } if (start) { end = start; start = 0; goto wrap_around; } if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_failed[ac->ac_criteria]); /* * CR_BEST_AVAIL_LEN works based on the concept that we have * a larger normalized goal len request which can be trimmed to * a smaller goal len such that it can still satisfy original * request len. However, allocation request for non-regular * files never gets normalized. * See function ext4_mb_normalize_request() (EXT4_MB_HINT_DATA). */ if (ac->ac_flags & EXT4_MB_HINT_DATA) ac->ac_criteria = CR_BEST_AVAIL_LEN; else ac->ac_criteria = CR_GOAL_LEN_SLOW; return ret; } /* * We couldn't find a group in CR_GOAL_LEN_FAST so try to find the highest free fragment * order we have and proactively trim the goal request length to that order to * find a suitable group faster. * * This optimizes allocation speed at the cost of slightly reduced * preallocations. However, we make sure that we don't trim the request too * much and fall to CR_GOAL_LEN_SLOW in that case. */ static int ext4_mb_scan_groups_best_avail(struct ext4_allocation_context *ac, ext4_group_t group) { int ret = 0; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int i, order, min_order; unsigned long num_stripe_clusters = 0; ext4_group_t start, end; /* * mb_avg_fragment_size_order() returns order in a way that makes * retrieving back the length using (1 << order) inaccurate. Hence, use * fls() instead since we need to know the actual length while modifying * goal length. */ order = fls(ac->ac_g_ex.fe_len) - 1; if (WARN_ON_ONCE(order - 1 > MB_NUM_ORDERS(ac->ac_sb))) order = MB_NUM_ORDERS(ac->ac_sb); min_order = order - sbi->s_mb_best_avail_max_trim_order; if (min_order < 0) min_order = 0; if (sbi->s_stripe > 0) { /* * We are assuming that stripe size is always a multiple of * cluster ratio otherwise __ext4_fill_super exists early. */ num_stripe_clusters = EXT4_NUM_B2C(sbi, sbi->s_stripe); if (1 << min_order < num_stripe_clusters) /* * We consider 1 order less because later we round * up the goal len to num_stripe_clusters */ min_order = fls(num_stripe_clusters) - 1; } if (1 << min_order < ac->ac_o_ex.fe_len) min_order = fls(ac->ac_o_ex.fe_len); start = group; end = ext4_get_allocation_groups_count(ac); wrap_around: for (i = order; i >= min_order; i--) { int frag_order; /* * Scale down goal len to make sure we find something * in the free fragments list. Basically, reduce * preallocations. */ ac->ac_g_ex.fe_len = 1 << i; if (num_stripe_clusters > 0) { /* * Try to round up the adjusted goal length to * stripe size (in cluster units) multiple for * efficiency. */ ac->ac_g_ex.fe_len = roundup(ac->ac_g_ex.fe_len, num_stripe_clusters); } frag_order = mb_avg_fragment_size_order(ac->ac_sb, ac->ac_g_ex.fe_len); ret = ext4_mb_scan_groups_avg_frag_order_range(ac, frag_order, start, end); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; } if (start) { end = start; start = 0; goto wrap_around; } /* Reset goal length to original goal length before falling into CR_GOAL_LEN_SLOW */ ac->ac_g_ex.fe_len = ac->ac_orig_goal_len; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_failed[ac->ac_criteria]); ac->ac_criteria = CR_GOAL_LEN_SLOW; return ret; } static inline int should_optimize_scan(struct ext4_allocation_context *ac) { if (unlikely(!test_opt2(ac->ac_sb, MB_OPTIMIZE_SCAN))) return 0; if (ac->ac_criteria >= CR_GOAL_LEN_SLOW) return 0; return 1; } /* * next linear group for allocation. */ static void next_linear_group(ext4_group_t *group, ext4_group_t ngroups) { /* * Artificially restricted ngroups for non-extent * files makes group > ngroups possible on first loop. */ *group = *group + 1 >= ngroups ? 0 : *group + 1; } static int ext4_mb_scan_groups_linear(struct ext4_allocation_context *ac, ext4_group_t ngroups, ext4_group_t *start, ext4_group_t count) { int ret, i; enum criteria cr = ac->ac_criteria; struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group = *start; for (i = 0; i < count; i++, next_linear_group(&group, ngroups)) { ret = ext4_mb_scan_group(ac, group); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; cond_resched(); } *start = group; if (count == ngroups) ac->ac_criteria++; /* Processed all groups and haven't found blocks */ if (sbi->s_mb_stats && i == ngroups) atomic64_inc(&sbi->s_bal_cX_failed[cr]); return 0; } static int ext4_mb_scan_groups(struct ext4_allocation_context *ac) { int ret = 0; ext4_group_t start; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_group_t ngroups = ext4_get_allocation_groups_count(ac); /* searching for the right group start from the goal value specified */ start = ac->ac_g_ex.fe_group; if (start >= ngroups) start = 0; ac->ac_prefetch_grp = start; ac->ac_prefetch_nr = 0; if (!should_optimize_scan(ac)) return ext4_mb_scan_groups_linear(ac, ngroups, &start, ngroups); /* * Optimized scanning can return non adjacent groups which can cause * seek overhead for rotational disks. So try few linear groups before * trying optimized scan. */ if (sbi->s_mb_max_linear_groups) ret = ext4_mb_scan_groups_linear(ac, ngroups, &start, sbi->s_mb_max_linear_groups); if (ret || ac->ac_status != AC_STATUS_CONTINUE) return ret; switch (ac->ac_criteria) { case CR_POWER2_ALIGNED: return ext4_mb_scan_groups_p2_aligned(ac, start); case CR_GOAL_LEN_FAST: return ext4_mb_scan_groups_goal_fast(ac, start); case CR_BEST_AVAIL_LEN: return ext4_mb_scan_groups_best_avail(ac, start); default: /* * TODO: For CR_GOAL_LEN_SLOW, we can arrange groups in an * rb tree sorted by bb_free. But until that happens, we should * never come here. */ WARN_ON(1); } return 0; } /* * Cache the order of the largest free extent we have available in this block * group. */ static void mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); int new, old = grp->bb_largest_free_order; for (new = MB_NUM_ORDERS(sb) - 1; new >= 0; new--) if (grp->bb_counters[new] > 0) break; /* No need to move between order lists? */ if (new == old) return; if (old >= 0) { struct xarray *xa = &sbi->s_mb_largest_free_orders[old]; if (!xa_empty(xa) && xa_load(xa, grp->bb_group)) xa_erase(xa, grp->bb_group); } grp->bb_largest_free_order = new; if (test_opt2(sb, MB_OPTIMIZE_SCAN) && new >= 0 && grp->bb_free) { /* * Cannot use __GFP_NOFAIL because we hold the group lock. * Although allocation for insertion may fails, it's not fatal * as we have linear traversal to fall back on. */ int err = xa_insert(&sbi->s_mb_largest_free_orders[new], grp->bb_group, grp, GFP_ATOMIC); if (err) mb_debug(sb, "insert group: %u to s_mb_largest_free_orders[%d] failed, err %d", grp->bb_group, new, err); } } static noinline_for_stack void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group, struct ext4_group_info *grp) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_grpblk_t first; ext4_grpblk_t len; unsigned free = 0; unsigned fragments = 0; unsigned long long period = get_cycles(); /* initialize buddy from bitmap which is aggregation * of on-disk bitmap and preallocations */ i = mb_find_next_zero_bit(bitmap, max, 0); grp->bb_first_free = i; while (i < max) { fragments++; first = i; i = mb_find_next_bit(bitmap, max, i); len = i - first; free += len; if (len > 1) ext4_mb_mark_free_simple(sb, buddy, first, len, grp); else grp->bb_counters[0]++; if (i < max) i = mb_find_next_zero_bit(bitmap, max, i); } grp->bb_fragments = fragments; if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, "block bitmap and bg descriptor " "inconsistent: %u vs %u free clusters", free, grp->bb_free); /* * If we intend to continue, we consider group descriptor * corrupt and update bb_free using bitmap value */ grp->bb_free = free; ext4_mark_group_bitmap_corrupted(sb, group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); } mb_set_largest_free_order(sb, grp); mb_update_avg_fragment_size(sb, grp); clear_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state)); period = get_cycles() - period; atomic_inc(&sbi->s_mb_buddies_generated); atomic64_add(period, &sbi->s_mb_generation_time); } static void mb_regenerate_buddy(struct ext4_buddy *e4b) { int count; int order = 1; void *buddy; while ((buddy = mb_find_buddy(e4b, order++, &count))) mb_set_bits(buddy, 0, count); e4b->bd_info->bb_fragments = 0; memset(e4b->bd_info->bb_counters, 0, sizeof(*e4b->bd_info->bb_counters) * (e4b->bd_sb->s_blocksize_bits + 2)); ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); } /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve * block bitmap and buddy information. The information are * stored in the inode as * * { folio } * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]... * * * one block each for bitmap and buddy information. * So for each group we take up 2 blocks. A folio can * contain blocks_per_folio (folio_size / blocksize) blocks. * So it can have information regarding groups_per_folio which * is blocks_per_folio/2 * * Locking note: This routine takes the block group lock of all groups * for this folio; do not hold this lock when calling this routine! */ static int ext4_mb_init_cache(struct folio *folio, char *incore, gfp_t gfp) { ext4_group_t ngroups; unsigned int blocksize; int blocks_per_folio; int groups_per_folio; int err = 0; int i; ext4_group_t first_group, group; int first_block; struct super_block *sb; struct buffer_head *bhs; struct buffer_head **bh = NULL; struct inode *inode; char *data; char *bitmap; struct ext4_group_info *grinfo; inode = folio->mapping->host; sb = inode->i_sb; ngroups = ext4_get_groups_count(sb); blocksize = i_blocksize(inode); blocks_per_folio = folio_size(folio) / blocksize; WARN_ON_ONCE(!blocks_per_folio); groups_per_folio = DIV_ROUND_UP(blocks_per_folio, 2); mb_debug(sb, "init folio %lu\n", folio->index); /* allocate buffer_heads to read bitmaps */ if (groups_per_folio > 1) { i = sizeof(struct buffer_head *) * groups_per_folio; bh = kzalloc(i, gfp); if (bh == NULL) return -ENOMEM; } else bh = &bhs; /* read all groups the folio covers into the cache */ first_group = EXT4_PG_TO_LBLK(inode, folio->index) / 2; for (i = 0, group = first_group; i < groups_per_folio; i++, group++) { if (group >= ngroups) break; grinfo = ext4_get_group_info(sb, group); if (!grinfo) continue; /* * If folio is uptodate then we came here after online resize * which added some new uninitialized group info structs, so * we must skip all initialized uptodate buddies on the folio, * which may be currently in use by an allocating task. */ if (folio_test_uptodate(folio) && !EXT4_MB_GRP_NEED_INIT(grinfo)) { bh[i] = NULL; continue; } bh[i] = ext4_read_block_bitmap_nowait(sb, group, false); if (IS_ERR(bh[i])) { err = PTR_ERR(bh[i]); bh[i] = NULL; goto out; } mb_debug(sb, "read bitmap for group %u\n", group); } /* wait for I/O completion */ for (i = 0, group = first_group; i < groups_per_folio; i++, group++) { int err2; if (!bh[i]) continue; err2 = ext4_wait_block_bitmap(sb, group, bh[i]); if (!err) err = err2; } first_block = EXT4_PG_TO_LBLK(inode, folio->index); for (i = 0; i < blocks_per_folio; i++) { group = (first_block + i) >> 1; if (group >= ngroups) break; if (!bh[group - first_group]) /* skip initialized uptodate buddy */ continue; if (!buffer_verified(bh[group - first_group])) /* Skip faulty bitmaps */ continue; err = 0; /* * data carry information regarding this * particular group in the format specified * above * */ data = folio_address(folio) + (i * blocksize); bitmap = bh[group - first_group]->b_data; /* * We place the buddy block and bitmap block * close together */ grinfo = ext4_get_group_info(sb, group); if (!grinfo) { err = -EFSCORRUPTED; goto out; } if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); mb_debug(sb, "put buddy for group %u in folio %lu/%x\n", group, folio->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * (MB_NUM_ORDERS(sb))); /* * incore got set to the group block bitmap below */ ext4_lock_group(sb, group); /* init the buddy */ memset(data, 0xff, blocksize); ext4_mb_generate_buddy(sb, data, incore, group, grinfo); ext4_unlock_group(sb, group); incore = NULL; } else { /* this is block of bitmap */ BUG_ON(incore != NULL); mb_debug(sb, "put bitmap for group %u in folio %lu/%x\n", group, folio->index, i * blocksize); trace_ext4_mb_bitmap_load(sb, group); /* see comments in ext4_mb_put_pa() */ ext4_lock_group(sb, group); memcpy(data, bitmap, blocksize); /* mark all preallocated blks used in in-core bitmap */ ext4_mb_generate_from_pa(sb, data, group); WARN_ON_ONCE(!RB_EMPTY_ROOT(&grinfo->bb_free_root)); ext4_unlock_group(sb, group); /* set incore so that the buddy information can be * generated using this */ incore = data; } } folio_mark_uptodate(folio); out: if (bh) { for (i = 0; i < groups_per_folio; i++) brelse(bh[i]); if (bh != &bhs) kfree(bh); } return err; } /* * Lock the buddy and bitmap folios. This makes sure other parallel init_group * on the same buddy folio doesn't happen while holding the buddy folio lock. * Return locked buddy and bitmap folios on e4b struct. If buddy and bitmap * are on the same folio e4b->bd_buddy_folio is NULL and return value is 0. */ static int ext4_mb_get_buddy_folio_lock(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { struct inode *inode = EXT4_SB(sb)->s_buddy_cache; int block, pnum; struct folio *folio; e4b->bd_buddy_folio = NULL; e4b->bd_bitmap_folio = NULL; /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = EXT4_LBLK_TO_PG(inode, block); folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return PTR_ERR(folio); BUG_ON(folio->mapping != inode->i_mapping); WARN_ON_ONCE(folio_size(folio) < sb->s_blocksize); e4b->bd_bitmap_folio = folio; e4b->bd_bitmap = folio_address(folio) + offset_in_folio(folio, EXT4_LBLK_TO_B(inode, block)); block++; pnum = EXT4_LBLK_TO_PG(inode, block); if (folio_contains(folio, pnum)) { /* buddy and bitmap are on the same folio */ return 0; } /* we need another folio for the buddy */ folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return PTR_ERR(folio); BUG_ON(folio->mapping != inode->i_mapping); WARN_ON_ONCE(folio_size(folio) < sb->s_blocksize); e4b->bd_buddy_folio = folio; return 0; } static void ext4_mb_put_buddy_folio_lock(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_folio) { folio_unlock(e4b->bd_bitmap_folio); folio_put(e4b->bd_bitmap_folio); } if (e4b->bd_buddy_folio) { folio_unlock(e4b->bd_buddy_folio); folio_put(e4b->bd_buddy_folio); } } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this folio; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_init_group(struct super_block *sb, ext4_group_t group, gfp_t gfp) { struct ext4_group_info *this_grp; struct ext4_buddy e4b; struct folio *folio; int ret = 0; might_sleep(); mb_debug(sb, "init group %u\n", group); this_grp = ext4_get_group_info(sb, group); if (!this_grp) return -EFSCORRUPTED; /* * This ensures that we don't reinit the buddy cache * folio which map to the group from which we are already * allocating. If we are looking at the buddy cache we would * have taken a reference using ext4_mb_load_buddy and that * would have pinned buddy folio to page cache. * The call to ext4_mb_get_buddy_folio_lock will mark the * folio accessed. */ ret = ext4_mb_get_buddy_folio_lock(sb, group, &e4b, gfp); if (ret || !EXT4_MB_GRP_NEED_INIT(this_grp)) { /* * somebody initialized the group * return without doing anything */ goto err; } folio = e4b.bd_bitmap_folio; ret = ext4_mb_init_cache(folio, NULL, gfp); if (ret) goto err; if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } if (e4b.bd_buddy_folio == NULL) { /* * If both the bitmap and buddy are in * the same folio we don't need to force * init the buddy */ ret = 0; goto err; } /* init buddy cache */ folio = e4b.bd_buddy_folio; ret = ext4_mb_init_cache(folio, e4b.bd_bitmap, gfp); if (ret) goto err; if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } err: ext4_mb_put_buddy_folio_lock(&e4b); return ret; } /* * Locking note: This routine calls ext4_mb_init_cache(), which takes the * block group lock of all groups for this folio; do not hold the BG lock when * calling this routine! */ static noinline_for_stack int ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b, gfp_t gfp) { int block; int pnum; struct folio *folio; int ret; struct ext4_group_info *grp; struct ext4_sb_info *sbi = EXT4_SB(sb); struct inode *inode = sbi->s_buddy_cache; might_sleep(); mb_debug(sb, "load group %u\n", group); grp = ext4_get_group_info(sb, group); if (!grp) return -EFSCORRUPTED; e4b->bd_blkbits = sb->s_blocksize_bits; e4b->bd_info = grp; e4b->bd_sb = sb; e4b->bd_group = group; e4b->bd_buddy_folio = NULL; e4b->bd_bitmap_folio = NULL; if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { /* * we need full data about the group * to make a good selection */ ret = ext4_mb_init_group(sb, group, gfp); if (ret) return ret; } /* * the buddy cache inode stores the block bitmap * and buddy information in consecutive blocks. * So for each group we need two blocks. */ block = group * 2; pnum = EXT4_LBLK_TO_PG(inode, block); /* Avoid locking the folio in the fast path ... */ folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0); if (IS_ERR(folio) || !folio_test_uptodate(folio) || folio_test_locked(folio)) { /* * folio_test_locked is employed to detect ongoing folio * migrations, since concurrent migrations can lead to * bitmap inconsistency. And if we are not uptodate that * implies somebody just created the folio but is yet to * initialize it. We can drop the folio reference and * try to get the folio with lock in both cases to avoid * concurrency. */ if (!IS_ERR(folio)) folio_put(folio); folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (!IS_ERR(folio)) { if (WARN_RATELIMIT(folio->mapping != inode->i_mapping, "ext4: bitmap's mapping != inode->i_mapping\n")) { /* should never happen */ folio_unlock(folio); ret = -EINVAL; goto err; } if (!folio_test_uptodate(folio)) { ret = ext4_mb_init_cache(folio, NULL, gfp); if (ret) { folio_unlock(folio); goto err; } mb_cmp_bitmaps(e4b, folio_address(folio) + offset_in_folio(folio, EXT4_LBLK_TO_B(inode, block))); } folio_unlock(folio); } } if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto err; } if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } /* Folios marked accessed already */ e4b->bd_bitmap_folio = folio; e4b->bd_bitmap = folio_address(folio) + offset_in_folio(folio, EXT4_LBLK_TO_B(inode, block)); block++; pnum = EXT4_LBLK_TO_PG(inode, block); /* buddy and bitmap are on the same folio? */ if (folio_contains(folio, pnum)) { folio_get(folio); goto update_buddy; } /* we need another folio for the buddy */ folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_ACCESSED, 0); if (IS_ERR(folio) || !folio_test_uptodate(folio) || folio_test_locked(folio)) { if (!IS_ERR(folio)) folio_put(folio); folio = __filemap_get_folio(inode->i_mapping, pnum, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (!IS_ERR(folio)) { if (WARN_RATELIMIT(folio->mapping != inode->i_mapping, "ext4: buddy bitmap's mapping != inode->i_mapping\n")) { /* should never happen */ folio_unlock(folio); ret = -EINVAL; goto err; } if (!folio_test_uptodate(folio)) { ret = ext4_mb_init_cache(folio, e4b->bd_bitmap, gfp); if (ret) { folio_unlock(folio); goto err; } } folio_unlock(folio); } } if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto err; } if (!folio_test_uptodate(folio)) { ret = -EIO; goto err; } update_buddy: /* Folios marked accessed already */ e4b->bd_buddy_folio = folio; e4b->bd_buddy = folio_address(folio) + offset_in_folio(folio, EXT4_LBLK_TO_B(inode, block)); return 0; err: if (!IS_ERR_OR_NULL(folio)) folio_put(folio); if (e4b->bd_bitmap_folio) folio_put(e4b->bd_bitmap_folio); e4b->bd_buddy = NULL; e4b->bd_bitmap = NULL; return ret; } static int ext4_mb_load_buddy(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b) { return ext4_mb_load_buddy_gfp(sb, group, e4b, GFP_NOFS); } static void ext4_mb_unload_buddy(struct ext4_buddy *e4b) { if (e4b->bd_bitmap_folio) folio_put(e4b->bd_bitmap_folio); if (e4b->bd_buddy_folio) folio_put(e4b->bd_buddy_folio); } static int mb_find_order_for_block(struct ext4_buddy *e4b, int block) { int order = 1, max; void *bb; BUG_ON(e4b->bd_bitmap == e4b->bd_buddy); BUG_ON(block >= (1 << (e4b->bd_blkbits + 3))); while (order <= e4b->bd_blkbits + 1) { bb = mb_find_buddy(e4b, order, &max); if (!mb_test_bit(block >> order, bb)) { /* this block is part of buddy of order 'order' */ return order; } order++; } return 0; } static void mb_clear_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); *addr = 0; cur += 32; continue; } mb_clear_bit(cur, bm); cur++; } } /* clear bits in given range * will return first found zero bit if any, -1 otherwise */ static int mb_test_and_clear_bits(void *bm, int cur, int len) { __u32 *addr; int zero_bit = -1; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: clear whole word at once */ addr = bm + (cur >> 3); if (*addr != (__u32)(-1) && zero_bit == -1) zero_bit = cur + mb_find_next_zero_bit(addr, 32, 0); *addr = 0; cur += 32; continue; } if (!mb_test_and_clear_bit(cur, bm) && zero_bit == -1) zero_bit = cur; cur++; } return zero_bit; } void mb_set_bits(void *bm, int cur, int len) { __u32 *addr; len = cur + len; while (cur < len) { if ((cur & 31) == 0 && (len - cur) >= 32) { /* fast path: set whole word at once */ addr = bm + (cur >> 3); *addr = 0xffffffff; cur += 32; continue; } mb_set_bit(cur, bm); cur++; } } static inline int mb_buddy_adjust_border(int* bit, void* bitmap, int side) { if (mb_test_bit(*bit + side, bitmap)) { mb_clear_bit(*bit, bitmap); (*bit) -= side; return 1; } else { (*bit) += side; mb_set_bit(*bit, bitmap); return -1; } } static void mb_buddy_mark_free(struct ext4_buddy *e4b, int first, int last) { int max; int order = 1; void *buddy = mb_find_buddy(e4b, order, &max); while (buddy) { void *buddy2; /* Bits in range [first; last] are known to be set since * corresponding blocks were allocated. Bits in range * (first; last) will stay set because they form buddies on * upper layer. We just deal with borders if they don't * align with upper layer and then go up. * Releasing entire group is all about clearing * single bit of highest order buddy. */ /* Example: * --------------------------------- * | 1 | 1 | 1 | 1 | * --------------------------------- * | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | * --------------------------------- * 0 1 2 3 4 5 6 7 * \_____________________/ * * Neither [1] nor [6] is aligned to above layer. * Left neighbour [0] is free, so mark it busy, * decrease bb_counters and extend range to * [0; 6] * Right neighbour [7] is busy. It can't be coaleasced with [6], so * mark [6] free, increase bb_counters and shrink range to * [0; 5]. * Then shift range to [0; 2], go up and do the same. */ if (first & 1) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&first, buddy, -1); if (!(last & 1)) e4b->bd_info->bb_counters[order] += mb_buddy_adjust_border(&last, buddy, 1); if (first > last) break; order++; buddy2 = mb_find_buddy(e4b, order, &max); if (!buddy2) { mb_clear_bits(buddy, first, last - first + 1); e4b->bd_info->bb_counters[order - 1] += last - first + 1; break; } first >>= 1; last >>= 1; buddy = buddy2; } } static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { int left_is_free = 0; int right_is_free = 0; int block; int last = first + count - 1; struct super_block *sb = e4b->bd_sb; if (WARN_ON(count == 0)) return; BUG_ON(last >= (sb->s_blocksize << 3)); assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group)); /* Don't bother if the block group is corrupt. */ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) return; mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ if (first != 0) left_is_free = !mb_test_bit(first - 1, e4b->bd_bitmap); block = mb_test_and_clear_bits(e4b->bd_bitmap, first, count); if (last + 1 < EXT4_SB(sb)->s_mb_maxs[0]) right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap); if (unlikely(block != -1)) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; /* * Fastcommit replay can free already freed blocks which * corrupts allocation info. Regenerate it. */ if (sbi->s_mount_state & EXT4_FC_REPLAY) { mb_regenerate_buddy(e4b); goto check; } blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, inode ? inode->i_ino : 0, blocknr, "freeing already freed block (bit %u); block bitmap corrupt.", block); return; } this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free += count; if (first < e4b->bd_info->bb_first_free) e4b->bd_info->bb_first_free = first; /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; else if (!left_is_free && !right_is_free) e4b->bd_info->bb_fragments++; /* buddy[0] == bd_bitmap is a special case, so handle * it right away and let mb_buddy_mark_free stay free of * zero order checks. * Check if neighbours are to be coaleasced, * adjust bitmap bb_counters and borders appropriately. */ if (first & 1) { first += !left_is_free; e4b->bd_info->bb_counters[0] += left_is_free ? -1 : 1; } if (!(last & 1)) { last -= !right_is_free; e4b->bd_info->bb_counters[0] += right_is_free ? -1 : 1; } if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); check: mb_check_buddy(e4b); } static int mb_find_extent(struct ext4_buddy *e4b, int block, int needed, struct ext4_free_extent *ex) { int max, order, next; void *buddy; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); buddy = mb_find_buddy(e4b, 0, &max); BUG_ON(buddy == NULL); BUG_ON(block >= max); if (mb_test_bit(block, buddy)) { ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; return 0; } /* find actual order */ order = mb_find_order_for_block(e4b, block); ex->fe_len = (1 << order) - (block & ((1 << order) - 1)); ex->fe_start = block; ex->fe_group = e4b->bd_group; block = block >> order; while (needed > ex->fe_len && mb_find_buddy(e4b, order, &max)) { if (block + 1 >= max) break; next = (block + 1) * (1 << order); if (mb_test_bit(next, e4b->bd_bitmap)) break; order = mb_find_order_for_block(e4b, next); block = next >> order; ex->fe_len += 1 << order; } if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) { /* Should never happen! (but apparently sometimes does?!?) */ WARN_ON(1); ext4_grp_locked_error(e4b->bd_sb, e4b->bd_group, 0, 0, "corruption or bug in mb_find_extent " "block=%d, order=%d needed=%d ex=%u/%d/%d@%u", block, order, needed, ex->fe_group, ex->fe_start, ex->fe_len, ex->fe_logical); ex->fe_len = 0; ex->fe_start = 0; ex->fe_group = 0; } return ex->fe_len; } static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex) { int ord; int mlen = 0; int max = 0; int start = ex->fe_start; int len = ex->fe_len; unsigned ret = 0; int len0 = len; void *buddy; int ord_start, ord_end; BUG_ON(start + len > (e4b->bd_sb->s_blocksize << 3)); BUG_ON(e4b->bd_group != ex->fe_group); assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); mb_check_buddy(e4b); mb_mark_used_double(e4b, start, len); this_cpu_inc(discard_pa_seq); e4b->bd_info->bb_free -= len; if (e4b->bd_info->bb_first_free == start) e4b->bd_info->bb_first_free += len; /* let's maintain fragments counter */ if (start != 0) mlen = !mb_test_bit(start - 1, e4b->bd_bitmap); if (start + len < EXT4_SB(e4b->bd_sb)->s_mb_maxs[0]) max = !mb_test_bit(start + len, e4b->bd_bitmap); if (mlen && max) e4b->bd_info->bb_fragments++; else if (!mlen && !max) e4b->bd_info->bb_fragments--; /* let's maintain buddy itself */ while (len) { ord = mb_find_order_for_block(e4b, start); if (((start >> ord) << ord) == start && len >= (1 << ord)) { /* the whole chunk may be allocated at once! */ mlen = 1 << ord; buddy = mb_find_buddy(e4b, ord, &max); BUG_ON((start >> ord) >= max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; start += mlen; len -= mlen; BUG_ON(len < 0); continue; } /* store for history */ if (ret == 0) ret = len | (ord << 16); BUG_ON(ord <= 0); buddy = mb_find_buddy(e4b, ord, &max); mb_set_bit(start >> ord, buddy); e4b->bd_info->bb_counters[ord]--; ord_start = (start >> ord) << ord; ord_end = ord_start + (1 << ord); /* first chunk */ if (start > ord_start) ext4_mb_mark_free_simple(e4b->bd_sb, e4b->bd_buddy, ord_start, start - ord_start, e4b->bd_info); /* last chunk */ if (start + len < ord_end) { ext4_mb_mark_free_simple(e4b->bd_sb, e4b->bd_buddy, start + len, ord_end - (start + len), e4b->bd_info); break; } len = start + len - ord_end; start = ord_end; } mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info); mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info); mb_set_bits(e4b->bd_bitmap, ex->fe_start, len0); mb_check_buddy(e4b); return ret; } /* * Must be called under group lock! */ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int ret; BUG_ON(ac->ac_b_ex.fe_group != e4b->bd_group); BUG_ON(ac->ac_status == AC_STATUS_FOUND); ac->ac_b_ex.fe_len = min(ac->ac_b_ex.fe_len, ac->ac_g_ex.fe_len); ac->ac_b_ex.fe_logical = ac->ac_g_ex.fe_logical; ret = mb_mark_used(e4b, &ac->ac_b_ex); /* preallocation can change ac_b_ex, thus we store actually * allocated blocks for history */ ac->ac_f_ex = ac->ac_b_ex; ac->ac_status = AC_STATUS_FOUND; ac->ac_tail = ret & 0xffff; ac->ac_buddy = ret >> 16; /* * take the folio reference. We want the folio to be pinned * so that we don't get a ext4_mb_init_cache_call for this * group until we update the bitmap. That would mean we * double allocate blocks. The reference is dropped * in ext4_mb_release_context */ ac->ac_bitmap_folio = e4b->bd_bitmap_folio; folio_get(ac->ac_bitmap_folio); ac->ac_buddy_folio = e4b->bd_buddy_folio; folio_get(ac->ac_buddy_folio); /* store last allocated for subsequent stream allocation */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { int hash = (unsigned int)ac->ac_inode->i_ino % sbi->s_mb_nr_global_goals; WRITE_ONCE(sbi->s_mb_last_groups[hash], ac->ac_f_ex.fe_group); } /* * As we've just preallocated more space than * user requested originally, we store allocated * space in a special descriptor. */ if (ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len) ext4_mb_new_preallocation(ac); } static void ext4_mb_check_limits(struct ext4_allocation_context *ac, struct ext4_buddy *e4b, int finish_group) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; if (ac->ac_status == AC_STATUS_FOUND) return; /* * We don't want to scan for a whole year */ if (ac->ac_found > sbi->s_mb_max_to_scan && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { ac->ac_status = AC_STATUS_BREAK; return; } /* * Haven't found good chunk so far, let's continue */ if (bex->fe_len < gex->fe_len) return; if (finish_group || ac->ac_found > sbi->s_mb_min_to_scan) ext4_mb_use_best_found(ac, e4b); } /* * The routine checks whether found extent is good enough. If it is, * then the extent gets marked used and flag is set to the context * to stop scanning. Otherwise, the extent is compared with the * previous found extent and if new one is better, then it's stored * in the context. Later, the best found extent will be used, if * mballoc can't find good enough extent. * * The algorithm used is roughly as follows: * * * If free extent found is exactly as big as goal, then * stop the scan and use it immediately * * * If free extent found is smaller than goal, then keep retrying * upto a max of sbi->s_mb_max_to_scan times (default 200). After * that stop scanning and use whatever we have. * * * If free extent found is bigger than goal, then keep retrying * upto a max of sbi->s_mb_min_to_scan times (default 10) before * stopping the scan and using the extent. * * * FIXME: real allocation policy is to be designed yet! */ static void ext4_mb_measure_extent(struct ext4_allocation_context *ac, struct ext4_free_extent *ex, struct ext4_buddy *e4b) { struct ext4_free_extent *bex = &ac->ac_b_ex; struct ext4_free_extent *gex = &ac->ac_g_ex; BUG_ON(ex->fe_len <= 0); BUG_ON(ex->fe_len > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ex->fe_start >= EXT4_CLUSTERS_PER_GROUP(ac->ac_sb)); BUG_ON(ac->ac_status != AC_STATUS_CONTINUE); ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; /* * The special case - take what you catch first */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_FIRST)) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * Let's check whether the chuck is good enough */ if (ex->fe_len == gex->fe_len) { *bex = *ex; ext4_mb_use_best_found(ac, e4b); return; } /* * If this is first found extent, just store it in the context */ if (bex->fe_len == 0) { *bex = *ex; return; } /* * If new found extent is better, store it in the context */ if (bex->fe_len < gex->fe_len) { /* if the request isn't satisfied, any found extent * larger than previous best one is better */ if (ex->fe_len > bex->fe_len) *bex = *ex; } else if (ex->fe_len > gex->fe_len) { /* if the request is satisfied, then we try to find * an extent that still satisfy the request, but is * smaller than previous one */ if (ex->fe_len < bex->fe_len) *bex = *ex; } ext4_mb_check_limits(ac, e4b, 0); } static noinline_for_stack void ext4_mb_try_best_found(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct ext4_free_extent ex = ac->ac_b_ex; ext4_group_t group = ex.fe_group; int max; int err; BUG_ON(ex.fe_len <= 0); err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return; ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) goto out; max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); } static noinline_for_stack int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { ext4_group_t group = ac->ac_g_ex.fe_group; int max; int err; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; if (!grp) return -EFSCORRUPTED; if (!(ac->ac_flags & (EXT4_MB_HINT_TRY_GOAL | EXT4_MB_HINT_GOAL_ONLY))) return 0; if (grp->bb_free == 0) return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) { if (EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info) && !(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return 0; return err; } ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) goto out; max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == EXT4_NUM_B2C(sbi, sbi->s_stripe)) { ext4_fsblk_t start; start = ext4_grp_offs_to_block(ac->ac_sb, &ex); /* use do_div to get remainder (would be 64-bit modulo) */ if (do_div(start, sbi->s_stripe) == 0) { ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } } else if (max >= ac->ac_g_ex.fe_len) { BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } else if (max > 0 && (ac->ac_flags & EXT4_MB_HINT_MERGE)) { /* Sometimes, caller may want to merge even small * number of blocks to an existing extent */ BUG_ON(ex.fe_len <= 0); BUG_ON(ex.fe_group != ac->ac_g_ex.fe_group); BUG_ON(ex.fe_start != ac->ac_g_ex.fe_start); ac->ac_found++; ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); return 0; } /* * The routine scans buddy structures (not bitmap!) from given order * to max order and tries to find big enough chunk to satisfy the req */ static noinline_for_stack void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_group_info *grp = e4b->bd_info; void *buddy; int i; int k; int max; BUG_ON(ac->ac_2order <= 0); for (i = ac->ac_2order; i < MB_NUM_ORDERS(sb); i++) { if (grp->bb_counters[i] == 0) continue; buddy = mb_find_buddy(e4b, i, &max); if (WARN_RATELIMIT(buddy == NULL, "ext4: mb_simple_scan_group: mb_find_buddy failed, (%d)\n", i)) continue; k = mb_find_next_zero_bit(buddy, max, 0); if (k >= max) { ext4_mark_group_bitmap_corrupted(ac->ac_sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, "%d free clusters of order %d. But found 0", grp->bb_counters[i], i); break; } ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; ac->ac_b_ex.fe_len = 1 << i; ac->ac_b_ex.fe_start = k << i; ac->ac_b_ex.fe_group = e4b->bd_group; ext4_mb_use_best_found(ac, e4b); BUG_ON(ac->ac_f_ex.fe_len != ac->ac_g_ex.fe_len); if (EXT4_SB(sb)->s_mb_stats) atomic_inc(&EXT4_SB(sb)->s_bal_2orders); break; } } /* * The routine scans the group and measures all found extents. * In order to optimize scanning, caller must pass number of * free blocks in the group, so the routine can know upper limit. */ static noinline_for_stack void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; int i, j, freelen; int free; free = e4b->bd_info->bb_free; if (WARN_ON(free <= 0)) return; i = e4b->bd_info->bb_first_free; while (free && ac->ac_status == AC_STATUS_CONTINUE) { i = mb_find_next_zero_bit(bitmap, EXT4_CLUSTERS_PER_GROUP(sb), i); if (i >= EXT4_CLUSTERS_PER_GROUP(sb)) { /* * IF we have corrupt bitmap, we won't find any * free blocks even though group info says we * have free blocks */ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But bitmap says 0", free); break; } if (!ext4_mb_cr_expensive(ac->ac_criteria)) { /* * In CR_GOAL_LEN_FAST and CR_BEST_AVAIL_LEN, we are * sure that this group will have a large enough * continuous free extent, so skip over the smaller free * extents */ j = mb_find_next_bit(bitmap, EXT4_CLUSTERS_PER_GROUP(sb), i); freelen = j - i; if (freelen < ac->ac_g_ex.fe_len) { i = j; free -= freelen; continue; } } mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex); if (WARN_ON(ex.fe_len <= 0)) break; if (free < ex.fe_len) { ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, "%d free clusters as per " "group info. But got %d blocks", free, ex.fe_len); /* * The number of free blocks differs. This mostly * indicate that the bitmap is corrupt. So exit * without claiming the space. */ break; } ex.fe_logical = 0xDEADC0DE; /* debug value */ ext4_mb_measure_extent(ac, &ex, e4b); i += ex.fe_len; free -= ex.fe_len; } ext4_mb_check_limits(ac, e4b, 1); } /* * This is a special case for storages like raid5 * we try to find stripe-aligned chunks for stripe-size-multiple requests */ static noinline_for_stack void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, struct ext4_buddy *e4b) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); void *bitmap = e4b->bd_bitmap; struct ext4_free_extent ex; ext4_fsblk_t first_group_block; ext4_fsblk_t a; ext4_grpblk_t i, stripe; int max; BUG_ON(sbi->s_stripe == 0); /* find first stripe-aligned block in group */ first_group_block = ext4_group_first_block_no(sb, e4b->bd_group); a = first_group_block + sbi->s_stripe - 1; do_div(a, sbi->s_stripe); i = (a * sbi->s_stripe) - first_group_block; stripe = EXT4_NUM_B2C(sbi, sbi->s_stripe); i = EXT4_B2C(sbi, i); while (i < EXT4_CLUSTERS_PER_GROUP(sb)) { if (!mb_test_bit(i, bitmap)) { max = mb_find_extent(e4b, i, stripe, &ex); if (max >= stripe) { ac->ac_found++; ac->ac_cX_found[ac->ac_criteria]++; ex.fe_logical = 0xDEADF00D; /* debug value */ ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); break; } } i += stripe; } } static void __ext4_mb_scan_group(struct ext4_allocation_context *ac) { bool is_stripe_aligned; struct ext4_sb_info *sbi; enum criteria cr = ac->ac_criteria; ac->ac_groups_scanned++; if (cr == CR_POWER2_ALIGNED) return ext4_mb_simple_scan_group(ac, ac->ac_e4b); sbi = EXT4_SB(ac->ac_sb); is_stripe_aligned = false; if ((sbi->s_stripe >= sbi->s_cluster_ratio) && !(ac->ac_g_ex.fe_len % EXT4_NUM_B2C(sbi, sbi->s_stripe))) is_stripe_aligned = true; if ((cr == CR_GOAL_LEN_FAST || cr == CR_BEST_AVAIL_LEN) && is_stripe_aligned) ext4_mb_scan_aligned(ac, ac->ac_e4b); if (ac->ac_status == AC_STATUS_CONTINUE) ext4_mb_complex_scan_group(ac, ac->ac_e4b); } /* * This is also called BEFORE we load the buddy bitmap. * Returns either 1 or 0 indicating that the group is either suitable * for the allocation or not. */ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ext4_group_t group, enum criteria cr) { ext4_grpblk_t free, fragments; int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb)); struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); BUG_ON(cr < CR_POWER2_ALIGNED || cr >= EXT4_MB_NUM_CRS); if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; free = grp->bb_free; if (free == 0) return false; fragments = grp->bb_fragments; if (fragments == 0) return false; switch (cr) { case CR_POWER2_ALIGNED: BUG_ON(ac->ac_2order == 0); /* Avoid using the first bg of a flexgroup for data files */ if ((ac->ac_flags & EXT4_MB_HINT_DATA) && (flex_size >= EXT4_FLEX_SIZE_DIR_ALLOC_SCHEME) && ((group % flex_size) == 0)) return false; if (free < ac->ac_g_ex.fe_len) return false; if (ac->ac_2order >= MB_NUM_ORDERS(ac->ac_sb)) return true; if (grp->bb_largest_free_order < ac->ac_2order) return false; return true; case CR_GOAL_LEN_FAST: case CR_BEST_AVAIL_LEN: if ((free / fragments) >= ac->ac_g_ex.fe_len) return true; break; case CR_GOAL_LEN_SLOW: if (free >= ac->ac_g_ex.fe_len) return true; break; case CR_ANY_FREE: return true; default: BUG(); } return false; } /* * This could return negative error code if something goes wrong * during ext4_mb_init_group(). This should not be called with * ext4_lock_group() held. * * Note: because we are conditionally operating with the group lock in * the EXT4_MB_STRICT_CHECK case, we need to fake out sparse in this * function using __acquire and __release. This means we need to be * super careful before messing with the error path handling via "goto * out"! */ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, ext4_group_t group, enum criteria cr) { struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; ext4_grpblk_t free; int ret = 0; if (!grp) return -EFSCORRUPTED; if (sbi->s_mb_stats) atomic64_inc(&sbi->s_bal_cX_groups_considered[ac->ac_criteria]); if (should_lock) { ext4_lock_group(sb, group); __release(ext4_group_lock_ptr(sb, group)); } free = grp->bb_free; if (free == 0) goto out; /* * In all criterias except CR_ANY_FREE we try to avoid groups that * can't possibly satisfy the full goal request due to insufficient * free blocks. */ if (cr < CR_ANY_FREE && free < ac->ac_g_ex.fe_len) goto out; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) goto out; if (should_lock) { __acquire(ext4_group_lock_ptr(sb, group)); ext4_unlock_group(sb, group); } /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); int ret; /* * CR_POWER2_ALIGNED/CR_GOAL_LEN_FAST is a very optimistic * search to find large good chunks almost for free. If buddy * data is not ready, then this optimization makes no sense. But * we never skip the first block group in a flex_bg, since this * gets used for metadata block allocation, and we want to make * sure we locate metadata blocks in the first block group in * the flex_bg if possible. */ if (!ext4_mb_cr_expensive(cr) && (!sbi->s_log_groups_per_flex || ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && !(ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) return 0; ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) return ret; } if (should_lock) { ext4_lock_group(sb, group); __release(ext4_group_lock_ptr(sb, group)); } ret = ext4_mb_good_group(ac, group, cr); out: if (should_lock) { __acquire(ext4_group_lock_ptr(sb, group)); ext4_unlock_group(sb, group); } return ret; } /* * Start prefetching @nr block bitmaps starting at @group. * Return the next group which needs to be prefetched. */ ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, unsigned int nr, int *cnt) { ext4_group_t ngroups = ext4_get_groups_count(sb); struct buffer_head *bh; struct blk_plug plug; blk_start_plug(&plug); while (nr-- > 0) { struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL); struct ext4_group_info *grp = ext4_get_group_info(sb, group); /* * Prefetch block groups with free blocks; but don't * bother if it is marked uninitialized on disk, since * it won't require I/O to read. Also only try to * prefetch once, so we avoid getblk() call, which can * be expensive. */ if (gdp && grp && !EXT4_MB_GRP_TEST_AND_SET_READ(grp) && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0 ) { bh = ext4_read_block_bitmap_nowait(sb, group, true); if (!IS_ERR_OR_NULL(bh)) { if (!buffer_uptodate(bh) && cnt) (*cnt)++; brelse(bh); } } if (++group >= ngroups) group = 0; } blk_finish_plug(&plug); return group; } /* * Batch reads of the block allocation bitmaps to get * multiple READs in flight; limit prefetching at inexpensive * CR, otherwise mballoc can spend a lot of time loading * imperfect groups */ static void ext4_mb_might_prefetch(struct ext4_allocation_context *ac, ext4_group_t group) { struct ext4_sb_info *sbi; if (ac->ac_prefetch_grp != group) return; sbi = EXT4_SB(ac->ac_sb); if (ext4_mb_cr_expensive(ac->ac_criteria) || ac->ac_prefetch_ios < sbi->s_mb_prefetch_limit) { unsigned int nr = sbi->s_mb_prefetch; if (ext4_has_feature_flex_bg(ac->ac_sb)) { nr = 1 << sbi->s_log_groups_per_flex; nr -= group & (nr - 1); nr = umin(nr, sbi->s_mb_prefetch); } ac->ac_prefetch_nr = nr; ac->ac_prefetch_grp = ext4_mb_prefetch(ac->ac_sb, group, nr, &ac->ac_prefetch_ios); } } /* * Prefetching reads the block bitmap into the buffer cache; but we * need to make sure that the buddy bitmap in the page cache has been * initialized. Note that ext4_mb_init_group() will block if the I/O * is not yet completed, or indeed if it was not initiated by * ext4_mb_prefetch did not start the I/O. * * TODO: We should actually kick off the buddy bitmap setup in a work * queue when the buffer I/O is completed, so that we don't block * waiting for the block allocation bitmap read to finish when * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator(). */ void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, unsigned int nr) { struct ext4_group_desc *gdp; struct ext4_group_info *grp; while (nr-- > 0) { if (!group) group = ext4_get_groups_count(sb); group--; gdp = ext4_get_group_desc(sb, group, NULL); grp = ext4_get_group_info(sb, group); if (grp && gdp && EXT4_MB_GRP_NEED_INIT(grp) && ext4_free_group_clusters(sb, gdp) > 0) { if (ext4_mb_init_group(sb, group, GFP_NOFS)) break; } } } static int ext4_mb_scan_group(struct ext4_allocation_context *ac, ext4_group_t group) { int ret; struct super_block *sb = ac->ac_sb; enum criteria cr = ac->ac_criteria; ext4_mb_might_prefetch(ac, group); /* prevent unnecessary buddy loading. */ if (cr < CR_ANY_FREE && spin_is_locked(ext4_group_lock_ptr(sb, group))) return 0; /* This now checks without needing the buddy folio */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { if (!ac->ac_first_err) ac->ac_first_err = ret; return 0; } ret = ext4_mb_load_buddy(sb, group, ac->ac_e4b); if (ret) return ret; /* skip busy group */ if (cr >= CR_ANY_FREE) ext4_lock_group(sb, group); else if (!ext4_try_lock_group(sb, group)) goto out_unload; /* We need to check again after locking the block group. */ if (unlikely(!ext4_mb_good_group(ac, group, cr))) goto out_unlock; __ext4_mb_scan_group(ac); out_unlock: ext4_unlock_group(sb, group); out_unload: ext4_mb_unload_buddy(ac->ac_e4b); return ret; } static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { ext4_group_t i; int err = 0; struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; BUG_ON(ac->ac_status == AC_STATUS_FOUND); /* first, try the goal */ err = ext4_mb_find_by_goal(ac, &e4b); if (err || ac->ac_status == AC_STATUS_FOUND) goto out; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) goto out; /* * ac->ac_2order is set only if the fe_len is a power of 2 * if ac->ac_2order is set we also set criteria to CR_POWER2_ALIGNED * so that we try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); ac->ac_2order = 0; /* * We search using buddy data only if the order of the request * is greater than equal to the sbi_s_mb_order2_reqs * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req * We also support searching for power-of-two requests only for * requests upto maximum buddy size we have constructed. */ if (i >= sbi->s_mb_order2_reqs && i <= MB_NUM_ORDERS(sb)) { if (is_power_of_2(ac->ac_g_ex.fe_len)) ac->ac_2order = array_index_nospec(i - 1, MB_NUM_ORDERS(sb)); } /* if stream allocation is enabled, use global goal */ if (ac->ac_flags & EXT4_MB_STREAM_ALLOC) { int hash = (unsigned int)ac->ac_inode->i_ino % sbi->s_mb_nr_global_goals; ac->ac_g_ex.fe_group = READ_ONCE(sbi->s_mb_last_groups[hash]); ac->ac_g_ex.fe_start = -1; ac->ac_flags &= ~EXT4_MB_HINT_TRY_GOAL; } /* * Let's just scan groups to find more-less suitable blocks We * start with CR_GOAL_LEN_FAST, unless it is power of 2 * aligned, in which case let's do that faster approach first. */ ac->ac_criteria = CR_GOAL_LEN_FAST; if (ac->ac_2order) ac->ac_criteria = CR_POWER2_ALIGNED; ac->ac_e4b = &e4b; ac->ac_prefetch_ios = 0; ac->ac_first_err = 0; repeat: while (ac->ac_criteria < EXT4_MB_NUM_CRS) { err = ext4_mb_scan_groups(ac); if (err) goto out; if (ac->ac_status != AC_STATUS_CONTINUE) break; } if (ac->ac_b_ex.fe_len > 0 && ac->ac_status != AC_STATUS_FOUND && !(ac->ac_flags & EXT4_MB_HINT_FIRST)) { /* * We've been searching too long. Let's try to allocate * the best chunk we've found so far */ ext4_mb_try_best_found(ac, &e4b); if (ac->ac_status != AC_STATUS_FOUND) { int lost; /* * Someone more lucky has already allocated it. * The only thing we can do is just take first * found block(s) */ lost = atomic_inc_return(&sbi->s_mb_lost_chunks); mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n", ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, lost); ac->ac_b_ex.fe_group = 0; ac->ac_b_ex.fe_start = 0; ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; ac->ac_flags |= EXT4_MB_HINT_FIRST; ac->ac_criteria = CR_ANY_FREE; goto repeat; } } if (sbi->s_mb_stats && ac->ac_status == AC_STATUS_FOUND) { atomic64_inc(&sbi->s_bal_cX_hits[ac->ac_criteria]); if (ac->ac_flags & EXT4_MB_STREAM_ALLOC && ac->ac_b_ex.fe_group == ac->ac_g_ex.fe_group) atomic_inc(&sbi->s_bal_stream_goals); } out: if (!err && ac->ac_status != AC_STATUS_FOUND && ac->ac_first_err) err = ac->ac_first_err; mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, ac->ac_flags, ac->ac_criteria, err); if (ac->ac_prefetch_nr) ext4_mb_prefetch_fini(sb, ac->ac_prefetch_grp, ac->ac_prefetch_nr); return err; } static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; ++*pos; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) return NULL; group = *pos + 1; return (void *) ((unsigned long) group); } static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i, err; char nbuf[16]; struct ext4_buddy e4b; struct ext4_group_info *grinfo; unsigned char blocksize_bits = min_t(unsigned char, sb->s_blocksize_bits, EXT4_MAX_BLOCK_LOG_SIZE); DEFINE_RAW_FLEX(struct ext4_group_info, sg, bb_counters, EXT4_MAX_BLOCK_LOG_SIZE + 2); group--; if (group == 0) seq_puts(seq, "#group: free frags first [" " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); i = (blocksize_bits + 2) * sizeof(sg->bb_counters[0]) + sizeof(struct ext4_group_info); grinfo = ext4_get_group_info(sb, group); if (!grinfo) return 0; /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { seq_printf(seq, "#%-5u: %s\n", group, ext4_decode_error(NULL, err, nbuf)); return 0; } ext4_mb_unload_buddy(&e4b); } /* * We care only about free space counters in the group info and * these are safe to access even after the buddy has been unloaded */ memcpy(sg, grinfo, i); seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg->bb_free, sg->bb_fragments, sg->bb_first_free); for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg->bb_counters[i] : 0); seq_puts(seq, " ]"); if (EXT4_MB_GRP_BBITMAP_CORRUPT(sg)) seq_puts(seq, " Block bitmap corrupted!"); seq_putc(seq, '\n'); return 0; } static void ext4_mb_seq_groups_stop(struct seq_file *seq, void *v) { } const struct seq_operations ext4_mb_seq_groups_ops = { .start = ext4_mb_seq_groups_start, .next = ext4_mb_seq_groups_next, .stop = ext4_mb_seq_groups_stop, .show = ext4_mb_seq_groups_show, }; int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) { struct super_block *sb = seq->private; struct ext4_sb_info *sbi = EXT4_SB(sb); seq_puts(seq, "mballoc:\n"); if (!sbi->s_mb_stats) { seq_puts(seq, "\tmb stats collection turned off.\n"); seq_puts( seq, "\tTo enable, please write \"1\" to sysfs file mb_stats.\n"); return 0; } seq_printf(seq, "\treqs: %u\n", atomic_read(&sbi->s_bal_reqs)); seq_printf(seq, "\tsuccess: %u\n", atomic_read(&sbi->s_bal_success)); seq_printf(seq, "\tgroups_scanned: %u\n", atomic_read(&sbi->s_bal_groups_scanned)); /* CR_POWER2_ALIGNED stats */ seq_puts(seq, "\tcr_p2_aligned_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_POWER2_ALIGNED])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_POWER2_ALIGNED])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_POWER2_ALIGNED])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_POWER2_ALIGNED])); /* CR_GOAL_LEN_FAST stats */ seq_puts(seq, "\tcr_goal_fast_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_GOAL_LEN_FAST])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_GOAL_LEN_FAST])); /* CR_BEST_AVAIL_LEN stats */ seq_puts(seq, "\tcr_best_avail_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_BEST_AVAIL_LEN])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_BEST_AVAIL_LEN])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_BEST_AVAIL_LEN])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_BEST_AVAIL_LEN])); /* CR_GOAL_LEN_SLOW stats */ seq_puts(seq, "\tcr_goal_slow_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\tgroups_considered: %llu\n", atomic64_read( &sbi->s_bal_cX_groups_considered[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_GOAL_LEN_SLOW])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_GOAL_LEN_SLOW])); /* CR_ANY_FREE stats */ seq_puts(seq, "\tcr_any_free_stats:\n"); seq_printf(seq, "\t\thits: %llu\n", atomic64_read(&sbi->s_bal_cX_hits[CR_ANY_FREE])); seq_printf( seq, "\t\tgroups_considered: %llu\n", atomic64_read(&sbi->s_bal_cX_groups_considered[CR_ANY_FREE])); seq_printf(seq, "\t\textents_scanned: %u\n", atomic_read(&sbi->s_bal_cX_ex_scanned[CR_ANY_FREE])); seq_printf(seq, "\t\tuseless_loops: %llu\n", atomic64_read(&sbi->s_bal_cX_failed[CR_ANY_FREE])); /* Aggregates */ seq_printf(seq, "\textents_scanned: %u\n", atomic_read(&sbi->s_bal_ex_scanned)); seq_printf(seq, "\t\tgoal_hits: %u\n", atomic_read(&sbi->s_bal_goals)); seq_printf(seq, "\t\tstream_goal_hits: %u\n", atomic_read(&sbi->s_bal_stream_goals)); seq_printf(seq, "\t\tlen_goal_hits: %u\n", atomic_read(&sbi->s_bal_len_goals)); seq_printf(seq, "\t\t2^n_hits: %u\n", atomic_read(&sbi->s_bal_2orders)); seq_printf(seq, "\t\tbreaks: %u\n", atomic_read(&sbi->s_bal_breaks)); seq_printf(seq, "\t\tlost: %u\n", atomic_read(&sbi->s_mb_lost_chunks)); seq_printf(seq, "\tbuddies_generated: %u/%u\n", atomic_read(&sbi->s_mb_buddies_generated), ext4_get_groups_count(sb)); seq_printf(seq, "\tbuddies_time_used: %llu\n", atomic64_read(&sbi->s_mb_generation_time)); seq_printf(seq, "\tpreallocated: %u\n", atomic_read(&sbi->s_mb_preallocated)); seq_printf(seq, "\tdiscarded: %u\n", atomic_read(&sbi->s_mb_discarded)); return 0; } static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); } static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos) { struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; ++*pos; if (*pos < 0 || *pos >= 2*MB_NUM_ORDERS(sb)) return NULL; position = *pos + 1; return (void *) ((unsigned long) position); } static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) { struct super_block *sb = pde_data(file_inode(seq->file)); struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; unsigned int count; unsigned long idx; position--; if (position >= MB_NUM_ORDERS(sb)) { position -= MB_NUM_ORDERS(sb); if (position == 0) seq_puts(seq, "avg_fragment_size_lists:\n"); count = 0; xa_for_each(&sbi->s_mb_avg_fragment_size[position], idx, grp) count++; seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); return 0; } if (position == 0) { seq_printf(seq, "optimize_scan: %d\n", test_opt2(sb, MB_OPTIMIZE_SCAN) ? 1 : 0); seq_puts(seq, "max_free_order_lists:\n"); } count = 0; xa_for_each(&sbi->s_mb_largest_free_orders[position], idx, grp) count++; seq_printf(seq, "\tlist_order_%u_groups: %u\n", (unsigned int)position, count); return 0; } static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) { } const struct seq_operations ext4_mb_seq_structs_summary_ops = { .start = ext4_mb_seq_structs_summary_start, .next = ext4_mb_seq_structs_summary_next, .stop = ext4_mb_seq_structs_summary_stop, .show = ext4_mb_seq_structs_summary_show, }; static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) { int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep = ext4_groupinfo_caches[cache_index]; BUG_ON(!cachep); return cachep; } /* * Allocate the top-level s_group_info array for the specified number * of groups */ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned size; struct ext4_group_info ***old_groupinfo, ***new_groupinfo; size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); if (size <= sbi->s_group_info_size) return 0; size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size); new_groupinfo = kvzalloc(size, GFP_KERNEL); if (!new_groupinfo) { ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); return -ENOMEM; } rcu_read_lock(); old_groupinfo = rcu_dereference(sbi->s_group_info); if (old_groupinfo) memcpy(new_groupinfo, old_groupinfo, sbi->s_group_info_size * sizeof(*sbi->s_group_info)); rcu_read_unlock(); rcu_assign_pointer(sbi->s_group_info, new_groupinfo); sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); if (old_groupinfo) ext4_kvfree_array_rcu(old_groupinfo); ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", sbi->s_group_info_size); return 0; } /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) { int i; int metalen = 0; int idx = group >> EXT4_DESC_PER_BLOCK_BITS(sb); struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_info **meta_group_info; struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); /* * First check if this group is the first of a reserved block. * If it's true, we have to allocate a new table of pointers * to ext4_group_info structures */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb); meta_group_info = kmalloc(metalen, GFP_NOFS); if (meta_group_info == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate mem " "for a buddy group"); return -ENOMEM; } rcu_read_lock(); rcu_dereference(sbi->s_group_info)[idx] = meta_group_info; rcu_read_unlock(); } meta_group_info = sbi_array_rcu_deref(sbi, s_group_info, idx); i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_NOFS); if (meta_group_info[i] == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate buddy mem"); goto exit_group_info; } set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); /* * initialize bb_free to be able to skip * empty groups without initialization */ if (ext4_has_group_desc_csum(sb) && (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { meta_group_info[i]->bb_free = ext4_free_clusters_after_init(sb, group, desc); } else { meta_group_info[i]->bb_free = ext4_free_group_clusters(sb, desc); } INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list); init_rwsem(&meta_group_info[i]->alloc_sem); meta_group_info[i]->bb_free_root = RB_ROOT; meta_group_info[i]->bb_largest_free_order = -1; /* uninit */ meta_group_info[i]->bb_avg_fragment_size_order = -1; /* uninit */ meta_group_info[i]->bb_group = group; mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group); return 0; exit_group_info: /* If a meta_group_info table has been allocated, release it now */ if (group % EXT4_DESC_PER_BLOCK(sb) == 0) { struct ext4_group_info ***group_info; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); kfree(group_info[idx]); group_info[idx] = NULL; rcu_read_unlock(); } return -ENOMEM; } /* ext4_mb_add_groupinfo */ static int ext4_mb_init_backend(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; struct ext4_sb_info *sbi = EXT4_SB(sb); int err; struct ext4_group_desc *desc; struct ext4_group_info ***group_info; struct kmem_cache *cachep; err = ext4_mb_alloc_groupinfo(sb, ngroups); if (err) return err; sbi->s_buddy_cache = new_inode(sb); if (sbi->s_buddy_cache == NULL) { ext4_msg(sb, KERN_ERR, "can't get new inode"); goto err_freesgi; } /* To avoid potentially colliding with an valid on-disk inode number, * use EXT4_BAD_INO for the buddy cache inode number. This inode is * not in the inode hash, so it should never be found by iget(), but * this will avoid confusion if it ever shows up during debugging. */ sbi->s_buddy_cache->i_ino = EXT4_BAD_INO; EXT4_I(sbi->s_buddy_cache)->i_disksize = 0; ext4_set_inode_mapping_order(sbi->s_buddy_cache); for (i = 0; i < ngroups; i++) { cond_resched(); desc = ext4_get_group_desc(sb, i, NULL); if (desc == NULL) { ext4_msg(sb, KERN_ERR, "can't read descriptor %u", i); goto err_freebuddy; } if (ext4_mb_add_groupinfo(sb, i, desc) != 0) goto err_freebuddy; } if (ext4_has_feature_flex_bg(sb)) { /* a single flex group is supposed to be read by a single IO. * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is * unsigned integer, so the maximum shift is 32. */ if (sbi->s_es->s_log_groups_per_flex >= 32) { ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group"); goto err_freebuddy; } sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex, BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { sbi->s_mb_prefetch = 32; } if (sbi->s_mb_prefetch > ext4_get_groups_count(sb)) sbi->s_mb_prefetch = ext4_get_groups_count(sb); /* * now many real IOs to prefetch within a single allocation at * CR_POWER2_ALIGNED. Given CR_POWER2_ALIGNED is an CPU-related * optimization we shouldn't try to load too many groups, at some point * we should start to use what we've got in memory. * with an average random access time 5ms, it'd take a second to get * 200 groups (* N with flex_bg), so let's make this limit 4 */ sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4; if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb)) sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb); return 0; err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); if (grp) kmem_cache_free(cachep, grp); } i = sbi->s_group_info_size; rcu_read_lock(); group_info = rcu_dereference(sbi->s_group_info); while (i-- > 0) kfree(group_info[i]); rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: kvfree(rcu_access_pointer(sbi->s_group_info)); return -ENOMEM; } static void ext4_groupinfo_destroy_slabs(void) { int i; for (i = 0; i < NR_GRPINFO_CACHES; i++) { kmem_cache_destroy(ext4_groupinfo_caches[i]); ext4_groupinfo_caches[i] = NULL; } } static int ext4_groupinfo_create_slab(size_t size) { static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex); int slab_size; int blocksize_bits = order_base_2(size); int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE; struct kmem_cache *cachep; if (cache_index >= NR_GRPINFO_CACHES) return -EINVAL; if (unlikely(cache_index < 0)) cache_index = 0; mutex_lock(&ext4_grpinfo_slab_create_mutex); if (ext4_groupinfo_caches[cache_index]) { mutex_unlock(&ext4_grpinfo_slab_create_mutex); return 0; /* Already created */ } slab_size = offsetof(struct ext4_group_info, bb_counters[blocksize_bits + 2]); cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index], slab_size, 0, SLAB_RECLAIM_ACCOUNT, NULL); ext4_groupinfo_caches[cache_index] = cachep; mutex_unlock(&ext4_grpinfo_slab_create_mutex); if (!cachep) { printk(KERN_EMERG "EXT4-fs: no memory for groupinfo slab cache\n"); return -ENOMEM; } return 0; } static void ext4_discard_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_discard_work); struct super_block *sb = sbi->s_sb; struct ext4_free_data *fd, *nfd; struct ext4_buddy e4b; LIST_HEAD(discard_list); ext4_group_t grp, load_grp; int err = 0; spin_lock(&sbi->s_md_lock); list_splice_init(&sbi->s_discard_list, &discard_list); spin_unlock(&sbi->s_md_lock); load_grp = UINT_MAX; list_for_each_entry_safe(fd, nfd, &discard_list, efd_list) { /* * If filesystem is umounting or no memory or suffering * from no space, give up the discard */ if ((sb->s_flags & SB_ACTIVE) && !err && !atomic_read(&sbi->s_retry_alloc_pending)) { grp = fd->efd_group; if (grp != load_grp) { if (load_grp != UINT_MAX) ext4_mb_unload_buddy(&e4b); err = ext4_mb_load_buddy(sb, grp, &e4b); if (err) { kmem_cache_free(ext4_free_data_cachep, fd); load_grp = UINT_MAX; continue; } else { load_grp = grp; } } ext4_lock_group(sb, grp); ext4_try_to_trim_range(sb, &e4b, fd->efd_start_cluster, fd->efd_start_cluster + fd->efd_count - 1, 1); ext4_unlock_group(sb, grp); } kmem_cache_free(ext4_free_data_cachep, fd); } if (load_grp != UINT_MAX) ext4_mb_unload_buddy(&e4b); } static inline void ext4_mb_avg_fragment_size_destroy(struct ext4_sb_info *sbi) { if (!sbi->s_mb_avg_fragment_size) return; for (int i = 0; i < MB_NUM_ORDERS(sbi->s_sb); i++) xa_destroy(&sbi->s_mb_avg_fragment_size[i]); kfree(sbi->s_mb_avg_fragment_size); sbi->s_mb_avg_fragment_size = NULL; } static inline void ext4_mb_largest_free_orders_destroy(struct ext4_sb_info *sbi) { if (!sbi->s_mb_largest_free_orders) return; for (int i = 0; i < MB_NUM_ORDERS(sbi->s_sb); i++) xa_destroy(&sbi->s_mb_largest_free_orders[i]); kfree(sbi->s_mb_largest_free_orders); sbi->s_mb_largest_free_orders = NULL; } int ext4_mb_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned i, j; unsigned offset, offset_incr; unsigned max; int ret; i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_offsets); sbi->s_mb_offsets = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_offsets == NULL) { ret = -ENOMEM; goto out; } i = MB_NUM_ORDERS(sb) * sizeof(*sbi->s_mb_maxs); sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL); if (sbi->s_mb_maxs == NULL) { ret = -ENOMEM; goto out; } ret = ext4_groupinfo_create_slab(sb->s_blocksize); if (ret < 0) goto out; /* order 0 is regular bitmap */ sbi->s_mb_maxs[0] = sb->s_blocksize << 3; sbi->s_mb_offsets[0] = 0; i = 1; offset = 0; offset_incr = 1 << (sb->s_blocksize_bits - 1); max = sb->s_blocksize << 2; do { sbi->s_mb_offsets[i] = offset; sbi->s_mb_maxs[i] = max; offset += offset_incr; offset_incr = offset_incr >> 1; max = max >> 1; i++; } while (i < MB_NUM_ORDERS(sb)); sbi->s_mb_avg_fragment_size = kmalloc_objs(struct xarray, MB_NUM_ORDERS(sb)); if (!sbi->s_mb_avg_fragment_size) { ret = -ENOMEM; goto out; } for (i = 0; i < MB_NUM_ORDERS(sb); i++) xa_init(&sbi->s_mb_avg_fragment_size[i]); sbi->s_mb_largest_free_orders = kmalloc_objs(struct xarray, MB_NUM_ORDERS(sb)); if (!sbi->s_mb_largest_free_orders) { ret = -ENOMEM; goto out; } for (i = 0; i < MB_NUM_ORDERS(sb); i++) xa_init(&sbi->s_mb_largest_free_orders[i]); spin_lock_init(&sbi->s_md_lock); atomic_set(&sbi->s_mb_free_pending, 0); INIT_LIST_HEAD(&sbi->s_freed_data_list[0]); INIT_LIST_HEAD(&sbi->s_freed_data_list[1]); INIT_LIST_HEAD(&sbi->s_discard_list); INIT_WORK(&sbi->s_discard_work, ext4_discard_work); atomic_set(&sbi->s_retry_alloc_pending, 0); sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN; sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN; sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; sbi->s_mb_best_avail_max_trim_order = MB_DEFAULT_BEST_AVAIL_TRIM_ORDER; /* * The default group preallocation is 512, which for 4k block * sizes translates to 2 megabytes. However for bigalloc file * systems, this is probably too big (i.e, if the cluster size * is 1 megabyte, then group preallocation size becomes half a * gigabyte!). As a default, we will keep a two megabyte * group pralloc size for cluster sizes up to 64k, and after * that, we will force a minimum group preallocation size of * 32 clusters. This translates to 8 megs when the cluster * size is 256k, and 32 megs when the cluster size is 1 meg, * which seems reasonable as a default. */ sbi->s_mb_group_prealloc = max(MB_DEFAULT_GROUP_PREALLOC >> sbi->s_cluster_bits, 32); /* * If there is a s_stripe > 1, then we set the s_mb_group_prealloc * to the lowest multiple of s_stripe which is bigger than * the s_mb_group_prealloc as determined above. We want * the preallocation size to be an exact multiple of the * RAID stripe size so that preallocations don't fragment * the stripes. */ if (sbi->s_stripe > 1) { sbi->s_mb_group_prealloc = roundup( sbi->s_mb_group_prealloc, EXT4_NUM_B2C(sbi, sbi->s_stripe)); } sbi->s_mb_nr_global_goals = umin(num_possible_cpus(), DIV_ROUND_UP(sbi->s_groups_count, 4)); sbi->s_mb_last_groups = kzalloc_objs(ext4_group_t, sbi->s_mb_nr_global_goals); if (sbi->s_mb_last_groups == NULL) { ret = -ENOMEM; goto out; } sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group); if (sbi->s_locality_groups == NULL) { ret = -ENOMEM; goto out_free_last_groups; } for_each_possible_cpu(i) { struct ext4_locality_group *lg; lg = per_cpu_ptr(sbi->s_locality_groups, i); mutex_init(&lg->lg_mutex); for (j = 0; j < PREALLOC_TB_SIZE; j++) INIT_LIST_HEAD(&lg->lg_prealloc_list[j]); spin_lock_init(&lg->lg_prealloc_lock); } if (!bdev_rot(sb->s_bdev)) sbi->s_mb_max_linear_groups = 0; else sbi->s_mb_max_linear_groups = MB_DEFAULT_LINEAR_LIMIT; /* init file for buddy data */ ret = ext4_mb_init_backend(sb); if (ret != 0) goto out_free_locality_groups; return 0; out_free_locality_groups: free_percpu(sbi->s_locality_groups); sbi->s_locality_groups = NULL; out_free_last_groups: kfree(sbi->s_mb_last_groups); sbi->s_mb_last_groups = NULL; out: ext4_mb_avg_fragment_size_destroy(sbi); ext4_mb_largest_free_orders_destroy(sbi); kfree(sbi->s_mb_offsets); sbi->s_mb_offsets = NULL; kfree(sbi->s_mb_maxs); sbi->s_mb_maxs = NULL; return ret; } /* need to called with the ext4 group lock held */ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp) { struct ext4_prealloc_space *pa; struct list_head *cur, *tmp; int count = 0; list_for_each_safe(cur, tmp, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); list_del(&pa->pa_group_list); count++; kmem_cache_free(ext4_pspace_cachep, pa); } return count; } void ext4_mb_release(struct super_block *sb) { ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; int num_meta_group_infos; struct ext4_group_info *grinfo, ***group_info; struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); int count; /* * wait the discard work to drain all of ext4_free_data */ flush_work(&sbi->s_discard_work); WARN_ON_ONCE(!list_empty(&sbi->s_discard_list)); group_info = rcu_access_pointer(sbi->s_group_info); if (group_info) { for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); if (!grinfo) continue; mb_group_bb_bitmap_free(grinfo); ext4_lock_group(sb, i); count = ext4_mb_cleanup_pa(grinfo); if (count) mb_debug(sb, "mballoc: %d PAs left\n", count); ext4_unlock_group(sb, i); kmem_cache_free(cachep, grinfo); } num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); for (i = 0; i < num_meta_group_infos; i++) kfree(group_info[i]); kvfree(group_info); } ext4_mb_avg_fragment_size_destroy(sbi); ext4_mb_largest_free_orders_destroy(sbi); kfree(sbi->s_mb_offsets); kfree(sbi->s_mb_maxs); iput(sbi->s_buddy_cache); if (sbi->s_mb_stats) { ext4_msg(sb, KERN_INFO, "mballoc: %u blocks %u reqs (%u success)", atomic_read(&sbi->s_bal_allocated), atomic_read(&sbi->s_bal_reqs), atomic_read(&sbi->s_bal_success)); ext4_msg(sb, KERN_INFO, "mballoc: %u extents scanned, %u groups scanned, %u goal hits, " "%u 2^N hits, %u breaks, %u lost", atomic_read(&sbi->s_bal_ex_scanned), atomic_read(&sbi->s_bal_groups_scanned), atomic_read(&sbi->s_bal_goals), atomic_read(&sbi->s_bal_2orders), atomic_read(&sbi->s_bal_breaks), atomic_read(&sbi->s_mb_lost_chunks)); ext4_msg(sb, KERN_INFO, "mballoc: %u generated and it took %llu", atomic_read(&sbi->s_mb_buddies_generated), atomic64_read(&sbi->s_mb_generation_time)); ext4_msg(sb, KERN_INFO, "mballoc: %u preallocated, %u discarded", atomic_read(&sbi->s_mb_preallocated), atomic_read(&sbi->s_mb_discarded)); } free_percpu(sbi->s_locality_groups); kfree(sbi->s_mb_last_groups); } static inline int ext4_issue_discard(struct super_block *sb, ext4_group_t block_group, ext4_grpblk_t cluster, int count) { ext4_fsblk_t discard_block; discard_block = (EXT4_C2B(EXT4_SB(sb), cluster) + ext4_group_first_block_no(sb, block_group)); count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } static void ext4_free_data_in_buddy(struct super_block *sb, struct ext4_free_data *entry) { struct ext4_buddy e4b; struct ext4_group_info *db; int err, count = 0; mb_debug(sb, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ BUG_ON(err != 0); atomic_sub(entry->efd_count, &EXT4_SB(sb)->s_mb_free_pending); db = e4b.bd_info; /* there are blocks to put in buddy to make them really free */ count += entry->efd_count; ext4_lock_group(sb, entry->efd_group); /* Take it out of per group rb tree */ rb_erase(&entry->efd_node, &(db->bb_free_root)); mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count); /* * Clear the trimmed flag for the group so that the next * ext4_trim_fs can trim it. */ EXT4_MB_GRP_CLEAR_TRIMMED(db); if (!db->bb_free_root.rb_node) { /* No more items in the per group rb tree * balance refcounts from ext4_mb_free_metadata() */ folio_put(e4b.bd_buddy_folio); folio_put(e4b.bd_bitmap_folio); } ext4_unlock_group(sb, entry->efd_group); ext4_mb_unload_buddy(&e4b); mb_debug(sb, "freed %d blocks in 1 structures\n", count); } /* * This function is called by the jbd2 layer once the commit has finished, * so we know we can free the blocks that were released with that commit. */ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_free_data *entry, *tmp; LIST_HEAD(freed_data_list); struct list_head *s_freed_head = &sbi->s_freed_data_list[commit_tid & 1]; bool wake; list_replace_init(s_freed_head, &freed_data_list); list_for_each_entry(entry, &freed_data_list, efd_list) ext4_free_data_in_buddy(sb, entry); if (test_opt(sb, DISCARD)) { spin_lock(&sbi->s_md_lock); wake = list_empty(&sbi->s_discard_list); list_splice_tail(&freed_data_list, &sbi->s_discard_list); spin_unlock(&sbi->s_md_lock); if (wake) queue_work(system_dfl_wq, &sbi->s_discard_work); } else { list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list) kmem_cache_free(ext4_free_data_cachep, entry); } } int __init ext4_init_mballoc(void) { ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, SLAB_RECLAIM_ACCOUNT); if (ext4_pspace_cachep == NULL) goto out; ext4_ac_cachep = KMEM_CACHE(ext4_allocation_context, SLAB_RECLAIM_ACCOUNT); if (ext4_ac_cachep == NULL) goto out_pa_free; ext4_free_data_cachep = KMEM_CACHE(ext4_free_data, SLAB_RECLAIM_ACCOUNT); if (ext4_free_data_cachep == NULL) goto out_ac_free; return 0; out_ac_free: kmem_cache_destroy(ext4_ac_cachep); out_pa_free: kmem_cache_destroy(ext4_pspace_cachep); out: return -ENOMEM; } void ext4_exit_mballoc(void) { /* * Wait for completion of call_rcu()'s on ext4_pspace_cachep * before destroying the slab cache. */ rcu_barrier(); kmem_cache_destroy(ext4_pspace_cachep); kmem_cache_destroy(ext4_ac_cachep); kmem_cache_destroy(ext4_free_data_cachep); ext4_groupinfo_destroy_slabs(); } #define EXT4_MB_BITMAP_MARKED_CHECK 0x0001 #define EXT4_MB_SYNC_UPDATE 0x0002 int ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state, ext4_group_t group, ext4_grpblk_t blkoff, ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bitmap_bh = NULL; struct ext4_group_desc *gdp; struct buffer_head *gdp_bh; int err; unsigned int i, already, changed = len; KUNIT_STATIC_STUB_REDIRECT(ext4_mb_mark_context, handle, sb, state, group, blkoff, len, flags, ret_changed); if (ret_changed) *ret_changed = 0; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) return PTR_ERR(bitmap_bh); if (handle) { BUFFER_TRACE(bitmap_bh, "getting write access"); err = ext4_journal_get_write_access(handle, sb, bitmap_bh, EXT4_JTR_NONE); if (err) goto out_err; } err = -EIO; gdp = ext4_get_group_desc(sb, group, &gdp_bh); if (!gdp) goto out_err; if (handle) { BUFFER_TRACE(gdp_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, gdp_bh, EXT4_JTR_NONE); if (err) goto out_err; } ext4_lock_group(sb, group); if (ext4_has_group_desc_csum(sb) && (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); } if (flags & EXT4_MB_BITMAP_MARKED_CHECK) { already = 0; for (i = 0; i < len; i++) if (mb_test_bit(blkoff + i, bitmap_bh->b_data) == state) already++; changed = len - already; } if (state) { mb_set_bits(bitmap_bh->b_data, blkoff, len); ext4_free_group_clusters_set(sb, gdp, ext4_free_group_clusters(sb, gdp) - changed); } else { mb_clear_bits(bitmap_bh->b_data, blkoff, len); ext4_free_group_clusters_set(sb, gdp, ext4_free_group_clusters(sb, gdp) + changed); } ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh); ext4_group_desc_csum_set(sb, group, gdp); ext4_unlock_group(sb, group); if (ret_changed) *ret_changed = changed; if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, group); struct flex_groups *fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group); if (state) atomic64_sub(changed, &fg->free_clusters); else atomic64_add(changed, &fg->free_clusters); } err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); if (err) goto out_err; err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh); if (err) goto out_err; if (flags & EXT4_MB_SYNC_UPDATE) { sync_dirty_buffer(bitmap_bh); sync_dirty_buffer(gdp_bh); } out_err: brelse(bitmap_bh); return err; } /* * Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps * Returns 0 if success or error code */ static noinline_for_stack int ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, handle_t *handle) { struct ext4_group_desc *gdp; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block; int err, len; int flags = 0; ext4_grpblk_t changed; BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(ac->ac_b_ex.fe_len <= 0); sb = ac->ac_sb; sbi = EXT4_SB(sb); gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, NULL); if (!gdp) return -EIO; ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group, ext4_free_group_clusters(sb, gdp)); block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error * Fix the bitmap and return EFSCORRUPTED * We leak some of the blocks here. */ err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, 0, NULL); if (!err) err = -EFSCORRUPTED; return err; } #ifdef AGGRESSIVE_CHECK flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len, flags, &changed); if (err && changed == 0) return err; #ifdef AGGRESSIVE_CHECK BUG_ON(changed != ac->ac_b_ex.fe_len); #endif percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); return err; } /* * Idempotent helper for Ext4 fast commit replay path to set the state of * blocks in bitmaps and update counters. */ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, int len, bool state) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group; ext4_grpblk_t blkoff; int err = 0; unsigned int clen, thisgrp_len; while (len > 0) { ext4_get_group_no_and_offset(sb, block, &group, &blkoff); /* * Check to see if we are freeing blocks across a group * boundary. * In case of flex_bg, this can happen that (block, len) may * span across more than one group. In that case we need to * get the corresponding group metadata to work with. * For this we have goto again loop. */ thisgrp_len = min(len, EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff)); clen = EXT4_NUM_B2C(sbi, thisgrp_len); if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) { ext4_error(sb, "Marking blocks in system zone - " "Block = %llu, len = %u", block, thisgrp_len); break; } err = ext4_mb_mark_context(NULL, sb, state, group, blkoff, clen, EXT4_MB_BITMAP_MARKED_CHECK | EXT4_MB_SYNC_UPDATE, NULL); if (err) break; block += thisgrp_len; len -= thisgrp_len; BUG_ON(len < 0); } } /* * here we normalize request for locality group * Group request are normalized to s_mb_group_prealloc, which goes to * s_strip if we set the same via mount option. * s_mb_group_prealloc can be configured via * /sys/fs/ext4/<partition>/mb_group_prealloc * * XXX: should we try to preallocate more than the group has now? */ static void ext4_mb_normalize_group_request(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; BUG_ON(lg == NULL); ac->ac_g_ex.fe_len = EXT4_SB(sb)->s_mb_group_prealloc; mb_debug(sb, "goal %u blocks for locality group\n", ac->ac_g_ex.fe_len); } /* * This function returns the next element to look at during inode * PA rbtree walk. We assume that we have held the inode PA rbtree lock * (ei->i_prealloc_lock) * * new_start The start of the range we want to compare * cur_start The existing start that we are comparing against * node The node of the rb_tree */ static inline struct rb_node* ext4_mb_pa_rb_next_iter(ext4_lblk_t new_start, ext4_lblk_t cur_start, struct rb_node *node) { if (new_start < cur_start) return node->rb_left; else return node->rb_right; } static inline void ext4_mb_pa_assert_overlap(struct ext4_allocation_context *ac, ext4_lblk_t start, loff_t end) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_prealloc_space *tmp_pa; ext4_lblk_t tmp_pa_start; loff_t tmp_pa_end; struct rb_node *iter; read_lock(&ei->i_prealloc_lock); for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(start, tmp_pa_start, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); tmp_pa_start = tmp_pa->pa_lstart; tmp_pa_end = pa_logical_end(sbi, tmp_pa); spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) BUG_ON(!(start >= tmp_pa_end || end <= tmp_pa_start)); spin_unlock(&tmp_pa->pa_lock); } read_unlock(&ei->i_prealloc_lock); } /* * Given an allocation context "ac" and a range "start", "end", check * and adjust boundaries if the range overlaps with any of the existing * preallocatoins stored in the corresponding inode of the allocation context. * * Parameters: * ac allocation context * start start of the new range * end end of the new range */ static inline void ext4_mb_pa_adjust_overlap(struct ext4_allocation_context *ac, ext4_lblk_t *start, loff_t *end) { struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *tmp_pa = NULL, *left_pa = NULL, *right_pa = NULL; struct rb_node *iter; ext4_lblk_t new_start, tmp_pa_start, right_pa_start = -1; loff_t new_end, tmp_pa_end, left_pa_end = -1; new_start = *start; new_end = *end; /* * Adjust the normalized range so that it doesn't overlap with any * existing preallocated blocks(PAs). Make sure to hold the rbtree lock * so it doesn't change underneath us. */ read_lock(&ei->i_prealloc_lock); /* Step 1: find any one immediate neighboring PA of the normalized range */ for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical, tmp_pa_start, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); tmp_pa_start = tmp_pa->pa_lstart; tmp_pa_end = pa_logical_end(sbi, tmp_pa); /* PA must not overlap original request */ spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) BUG_ON(!(ac->ac_o_ex.fe_logical >= tmp_pa_end || ac->ac_o_ex.fe_logical < tmp_pa_start)); spin_unlock(&tmp_pa->pa_lock); } /* * Step 2: check if the found PA is left or right neighbor and * get the other neighbor */ if (tmp_pa) { if (tmp_pa->pa_lstart < ac->ac_o_ex.fe_logical) { struct rb_node *tmp; left_pa = tmp_pa; tmp = rb_next(&left_pa->pa_node.inode_node); if (tmp) { right_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } } else { struct rb_node *tmp; right_pa = tmp_pa; tmp = rb_prev(&right_pa->pa_node.inode_node); if (tmp) { left_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } } } /* Step 3: get the non deleted neighbors */ if (left_pa) { for (iter = &left_pa->pa_node.inode_node;; iter = rb_prev(iter)) { if (!iter) { left_pa = NULL; break; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); left_pa = tmp_pa; spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { spin_unlock(&tmp_pa->pa_lock); break; } spin_unlock(&tmp_pa->pa_lock); } } if (right_pa) { for (iter = &right_pa->pa_node.inode_node;; iter = rb_next(iter)) { if (!iter) { right_pa = NULL; break; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); right_pa = tmp_pa; spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { spin_unlock(&tmp_pa->pa_lock); break; } spin_unlock(&tmp_pa->pa_lock); } } if (left_pa) { left_pa_end = pa_logical_end(sbi, left_pa); BUG_ON(left_pa_end > ac->ac_o_ex.fe_logical); } if (right_pa) { right_pa_start = right_pa->pa_lstart; BUG_ON(right_pa_start <= ac->ac_o_ex.fe_logical); } /* Step 4: trim our normalized range to not overlap with the neighbors */ if (left_pa) { if (left_pa_end > new_start) new_start = left_pa_end; } if (right_pa) { if (right_pa_start < new_end) new_end = right_pa_start; } read_unlock(&ei->i_prealloc_lock); /* XXX: extra loop to check we really don't overlap preallocations */ ext4_mb_pa_assert_overlap(ac, new_start, new_end); *start = new_start; *end = new_end; } /* * Normalization means making request better in terms of * size and alignment */ static noinline_for_stack void ext4_mb_normalize_request(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_super_block *es = sbi->s_es; int bsbits, max; loff_t size, start_off, end; loff_t orig_size __maybe_unused; ext4_lblk_t start; /* do normalize only data requests, metadata requests do not need preallocation */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; /* sometime caller may want exact blocks */ if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; /* caller may indicate that preallocation isn't * required (it's a tail, for example) */ if (ac->ac_flags & EXT4_MB_HINT_NOPREALLOC) return; if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) { ext4_mb_normalize_group_request(ac); return ; } bsbits = ac->ac_sb->s_blocksize_bits; /* first, let's learn actual file size * given current request is allocated */ size = extent_logical_end(sbi, &ac->ac_o_ex); size = size << bsbits; if (size < i_size_read(ac->ac_inode)) size = i_size_read(ac->ac_inode); orig_size = size; /* max size of free chunks */ max = 2 << bsbits; #define NRL_CHECK_SIZE(req, size, max, chunk_size) \ (req <= (size) || max <= (chunk_size)) /* first, try to predict filesize */ start_off = 0; if (size <= SZ_1M) { /* * For files up to 1MB, round up the preallocation size to * the next power of two, with a minimum of 16KB. */ if (size <= (unsigned long)SZ_16K) size = SZ_16K; else size = roundup_pow_of_two(size); } else if (NRL_CHECK_SIZE(size, 4 * 1024 * 1024, max, 2 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (21 - bsbits)) << 21; size = 2 * 1024 * 1024; } else if (NRL_CHECK_SIZE(size, 8 * 1024 * 1024, max, 4 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (22 - bsbits)) << 22; size = 4 * 1024 * 1024; } else if (NRL_CHECK_SIZE(EXT4_C2B(sbi, ac->ac_o_ex.fe_len), (8<<20)>>bsbits, max, 8 * 1024)) { start_off = ((loff_t)ac->ac_o_ex.fe_logical >> (23 - bsbits)) << 23; size = 8 * 1024 * 1024; } else { start_off = (loff_t) ac->ac_o_ex.fe_logical << bsbits; size = (loff_t) EXT4_C2B(sbi, ac->ac_o_ex.fe_len) << bsbits; } size = size >> bsbits; start = start_off >> bsbits; /* * For tiny groups (smaller than 8MB) the chosen allocation * alignment may be larger than group size. Make sure the * alignment does not move allocation to a different group which * makes mballoc fail assertions later. */ start = max(start, rounddown(ac->ac_o_ex.fe_logical, (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); /* avoid unnecessary preallocation that may trigger assertions */ if (start + size > EXT_MAX_BLOCKS) size = EXT_MAX_BLOCKS - start; /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; start = ar->lleft + 1; } if (ar->pright && start + size - 1 >= ar->lright) size -= start + size - ar->lright; /* * Trim allocation request for filesystems with artificially small * groups. */ if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)) size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb); end = start + size; ext4_mb_pa_adjust_overlap(ac, &start, &end); size = end - start; /* * In this function "start" and "size" are normalized for better * alignment and length such that we could preallocate more blocks. * This normalization is done such that original request of * ac->ac_o_ex.fe_logical & fe_len should always lie within "start" and * "size" boundaries. * (Note fe_len can be relaxed since FS block allocation API does not * provide gurantee on number of contiguous blocks allocation since that * depends upon free space left, etc). * In case of inode pa, later we use the allocated blocks * [pa_pstart + fe_logical - pa_lstart, fe_len/size] from the preallocated * range of goal/best blocks [start, size] to put it at the * ac_o_ex.fe_logical extent of this inode. * (See ext4_mb_use_inode_pa() for more details) */ if (start + size <= ac->ac_o_ex.fe_logical || start > ac->ac_o_ex.fe_logical) { ext4_msg(ac->ac_sb, KERN_ERR, "start %lu, size %lu, fe_logical %lu", (unsigned long) start, (unsigned long) size, (unsigned long) ac->ac_o_ex.fe_logical); BUG(); } BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb)); /* now prepare goal request */ /* XXX: is it better to align blocks WRT to logical * placement or satisfy big request as is */ ac->ac_g_ex.fe_logical = start; ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size); ac->ac_orig_goal_len = ac->ac_g_ex.fe_len; /* define goal start in order to merge */ if (ar->pright && (ar->lright == (start + size)) && ar->pright >= size && ar->pright - size >= le32_to_cpu(es->s_first_data_block)) { /* merge to the right */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size, &ac->ac_g_ex.fe_group, &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } if (ar->pleft && (ar->lleft + 1 == start) && ar->pleft + 1 < ext4_blocks_count(es)) { /* merge to the left */ ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1, &ac->ac_g_ex.fe_group, &ac->ac_g_ex.fe_start); ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL; } mb_debug(ac->ac_sb, "goal: %lld(was %lld) blocks at %u\n", size, orig_size, start); } static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); if (sbi->s_mb_stats && ac->ac_g_ex.fe_len >= 1) { atomic_inc(&sbi->s_bal_reqs); atomic_add(ac->ac_b_ex.fe_len, &sbi->s_bal_allocated); if (ac->ac_b_ex.fe_len >= ac->ac_o_ex.fe_len) atomic_inc(&sbi->s_bal_success); atomic_add(ac->ac_found, &sbi->s_bal_ex_scanned); for (int i=0; i<EXT4_MB_NUM_CRS; i++) { atomic_add(ac->ac_cX_found[i], &sbi->s_bal_cX_ex_scanned[i]); } atomic_add(ac->ac_groups_scanned, &sbi->s_bal_groups_scanned); if (ac->ac_g_ex.fe_start == ac->ac_b_ex.fe_start && ac->ac_g_ex.fe_group == ac->ac_b_ex.fe_group) atomic_inc(&sbi->s_bal_goals); /* did we allocate as much as normalizer originally wanted? */ if (ac->ac_f_ex.fe_len == ac->ac_orig_goal_len) atomic_inc(&sbi->s_bal_len_goals); if (ac->ac_found > sbi->s_mb_max_to_scan) atomic_inc(&sbi->s_bal_breaks); } if (ac->ac_op == EXT4_MB_HISTORY_ALLOC) trace_ext4_mballoc_alloc(ac); else trace_ext4_mballoc_prealloc(ac); } /* * Called on failure; free up any blocks from the inode PA for this * context. We don't need this for MB_GROUP_PA because we only change * pa_free in ext4_mb_release_context(), but on failure, we've already * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed. */ static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; struct ext4_buddy e4b; int err; if (pa == NULL) { if (ac->ac_f_ex.fe_len == 0) return; err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b); if (WARN_RATELIMIT(err, "ext4: mb_load_buddy failed (%d)", err)) /* * This should never happen since we pin the * folios in the ext4_allocation_context so * ext4_mb_load_buddy() should never fail. */ return; ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group); mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start, ac->ac_f_ex.fe_len); ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group); ext4_mb_unload_buddy(&e4b); return; } if (pa->pa_type == MB_INODE_PA) { spin_lock(&pa->pa_lock); pa->pa_free += ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); } } /* * use blocks preallocated to inode */ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_fsblk_t start; ext4_fsblk_t end; int len; /* found preallocated blocks, use them */ start = pa->pa_pstart + (ac->ac_o_ex.fe_logical - pa->pa_lstart); end = min(pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len), start + EXT4_C2B(sbi, ac->ac_o_ex.fe_len)); len = EXT4_NUM_B2C(sbi, end - start); ext4_get_group_no_and_offset(ac->ac_sb, start, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; BUG_ON(start < pa->pa_pstart); BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len)); BUG_ON(pa->pa_free < len); BUG_ON(ac->ac_b_ex.fe_len <= 0); pa->pa_free -= len; mb_debug(ac->ac_sb, "use %llu/%d from inode pa %p\n", start, len, pa); } /* * use blocks preallocated to locality group */ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { unsigned int len = ac->ac_o_ex.fe_len; ext4_get_group_no_and_offset(ac->ac_sb, pa->pa_pstart, &ac->ac_b_ex.fe_group, &ac->ac_b_ex.fe_start); ac->ac_b_ex.fe_len = len; ac->ac_status = AC_STATUS_FOUND; ac->ac_pa = pa; /* we don't correct pa_pstart or pa_len here to avoid * possible race when the group is being loaded concurrently * instead we correct pa later, after blocks are marked * in on-disk bitmap -- see ext4_mb_release_context() * Other CPUs are prevented from allocating from this pa by lg_mutex */ mb_debug(ac->ac_sb, "use %u/%u from group pa %p\n", pa->pa_lstart, len, pa); } /* * Return the prealloc space that have minimal distance * from the goal block. @cpa is the prealloc * space that is having currently known minimal distance * from the goal block. */ static struct ext4_prealloc_space * ext4_mb_check_group_pa(ext4_fsblk_t goal_block, struct ext4_prealloc_space *pa, struct ext4_prealloc_space *cpa) { ext4_fsblk_t cur_distance, new_distance; if (cpa == NULL) { atomic_inc(&pa->pa_count); return pa; } cur_distance = abs(goal_block - cpa->pa_pstart); new_distance = abs(goal_block - pa->pa_pstart); if (cur_distance <= new_distance) return cpa; /* drop the previous reference */ atomic_dec(&cpa->pa_count); atomic_inc(&pa->pa_count); return pa; } /* * check if found pa meets EXT4_MB_HINT_GOAL_ONLY */ static bool ext4_mb_pa_goal_check(struct ext4_allocation_context *ac, struct ext4_prealloc_space *pa) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); ext4_fsblk_t start; if (likely(!(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))) return true; /* * If EXT4_MB_HINT_GOAL_ONLY is set, ac_g_ex will not be adjusted * in ext4_mb_normalize_request and will keep same with ac_o_ex * from ext4_mb_initialize_context. Choose ac_g_ex here to keep * consistent with ext4_mb_find_by_goal. */ start = pa->pa_pstart + (ac->ac_g_ex.fe_logical - pa->pa_lstart); if (ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex) != start) return false; if (ac->ac_g_ex.fe_len > pa->pa_len - EXT4_B2C(sbi, ac->ac_g_ex.fe_logical - pa->pa_lstart)) return false; return true; } /* * search goal blocks in preallocated space */ static noinline_for_stack bool ext4_mb_use_preallocated(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int order, i; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); struct ext4_locality_group *lg; struct ext4_prealloc_space *tmp_pa = NULL, *cpa = NULL; struct rb_node *iter; ext4_fsblk_t goal_block; /* only data can be preallocated */ if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return false; /* * first, try per-file preallocation by searching the inode pa rbtree. * * Here, we can't do a direct traversal of the tree because * ext4_mb_discard_group_preallocation() can paralelly mark the pa * deleted and that can cause direct traversal to skip some entries. */ read_lock(&ei->i_prealloc_lock); if (RB_EMPTY_ROOT(&ei->i_prealloc_node)) { goto try_group_pa; } /* * Step 1: Find a pa with logical start immediately adjacent to the * original logical start. This could be on the left or right. * * (tmp_pa->pa_lstart never changes so we can skip locking for it). */ for (iter = ei->i_prealloc_node.rb_node; iter; iter = ext4_mb_pa_rb_next_iter(ac->ac_o_ex.fe_logical, tmp_pa->pa_lstart, iter)) { tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); } /* * Step 2: The adjacent pa might be to the right of logical start, find * the left adjacent pa. After this step we'd have a valid tmp_pa whose * logical start is towards the left of original request's logical start */ if (tmp_pa->pa_lstart > ac->ac_o_ex.fe_logical) { struct rb_node *tmp; tmp = rb_prev(&tmp_pa->pa_node.inode_node); if (tmp) { tmp_pa = rb_entry(tmp, struct ext4_prealloc_space, pa_node.inode_node); } else { /* * If there is no adjacent pa to the left then finding * an overlapping pa is not possible hence stop searching * inode pa tree */ goto try_group_pa; } } BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical)); /* * Step 3: If the left adjacent pa is deleted, keep moving left to find * the first non deleted adjacent pa. After this step we should have a * valid tmp_pa which is guaranteed to be non deleted. */ for (iter = &tmp_pa->pa_node.inode_node;; iter = rb_prev(iter)) { if (!iter) { /* * no non deleted left adjacent pa, so stop searching * inode pa tree */ goto try_group_pa; } tmp_pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0) { /* * We will keep holding the pa_lock from * this point on because we don't want group discard * to delete this pa underneath us. Since group * discard is anyways an ENOSPC operation it * should be okay for it to wait a few more cycles. */ break; } else { spin_unlock(&tmp_pa->pa_lock); } } BUG_ON(!(tmp_pa && tmp_pa->pa_lstart <= ac->ac_o_ex.fe_logical)); BUG_ON(tmp_pa->pa_deleted == 1); /* * Step 4: We now have the non deleted left adjacent pa. Only this * pa can possibly satisfy the request hence check if it overlaps * original logical start and stop searching if it doesn't. */ if (ac->ac_o_ex.fe_logical >= pa_logical_end(sbi, tmp_pa)) { spin_unlock(&tmp_pa->pa_lock); goto try_group_pa; } /* non-extent files can't have physical blocks past 2^32 */ if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)) && (tmp_pa->pa_pstart + EXT4_C2B(sbi, tmp_pa->pa_len) > EXT4_MAX_BLOCK_FILE_PHYS)) { /* * Since PAs don't overlap, we won't find any other PA to * satisfy this. */ spin_unlock(&tmp_pa->pa_lock); goto try_group_pa; } if (tmp_pa->pa_free && likely(ext4_mb_pa_goal_check(ac, tmp_pa))) { atomic_inc(&tmp_pa->pa_count); ext4_mb_use_inode_pa(ac, tmp_pa); spin_unlock(&tmp_pa->pa_lock); read_unlock(&ei->i_prealloc_lock); return true; } else { /* * We found a valid overlapping pa but couldn't use it because * it had no free blocks. This should ideally never happen * because: * * 1. When a new inode pa is added to rbtree it must have * pa_free > 0 since otherwise we won't actually need * preallocation. * * 2. An inode pa that is in the rbtree can only have it's * pa_free become zero when another thread calls: * ext4_mb_new_blocks * ext4_mb_use_preallocated * ext4_mb_use_inode_pa * * 3. Further, after the above calls make pa_free == 0, we will * immediately remove it from the rbtree in: * ext4_mb_new_blocks * ext4_mb_release_context * ext4_mb_put_pa * * 4. Since the pa_free becoming 0 and pa_free getting removed * from tree both happen in ext4_mb_new_blocks, which is always * called with i_data_sem held for data allocations, we can be * sure that another process will never see a pa in rbtree with * pa_free == 0. */ WARN_ON_ONCE(tmp_pa->pa_free == 0); } spin_unlock(&tmp_pa->pa_lock); try_group_pa: read_unlock(&ei->i_prealloc_lock); /* can we use group allocation? */ if (!(ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)) return false; /* inode may have no locality group for some reason */ lg = ac->ac_lg; if (lg == NULL) return false; order = fls(ac->ac_o_ex.fe_len) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; goal_block = ext4_grp_offs_to_block(ac->ac_sb, &ac->ac_g_ex); /* * search for the prealloc space that is having * minimal distance from the goal block. */ for (i = order; i < PREALLOC_TB_SIZE; i++) { rcu_read_lock(); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[i], pa_node.lg_list) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted == 0 && tmp_pa->pa_free >= ac->ac_o_ex.fe_len) { cpa = ext4_mb_check_group_pa(goal_block, tmp_pa, cpa); } spin_unlock(&tmp_pa->pa_lock); } rcu_read_unlock(); } if (cpa) { ext4_mb_use_group_pa(ac, cpa); return true; } return false; } /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap * Need to be called with ext4 group lock held */ static noinline_for_stack void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct ext4_prealloc_space *pa; struct list_head *cur; ext4_group_t groupnr; ext4_grpblk_t start; int preallocated = 0; int len; if (!grp) return; /* all form of preallocation discards first load group, * so the only competing code is preallocation use. * we don't need any locking here * notice we do NOT ignore preallocations with pa_deleted * otherwise we could leave used blocks available for * allocation in buddy when concurrent ext4_mb_put_pa() * is dropping preallocation */ list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &groupnr, &start); len = pa->pa_len; spin_unlock(&pa->pa_lock); if (unlikely(len == 0)) continue; BUG_ON(groupnr != group); mb_set_bits(bitmap, start, len); preallocated += len; } mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } static void ext4_mb_mark_pa_deleted(struct super_block *sb, struct ext4_prealloc_space *pa) { struct ext4_inode_info *ei; if (pa->pa_deleted) { ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n", pa->pa_type, pa->pa_pstart, pa->pa_lstart, pa->pa_len); return; } pa->pa_deleted = 1; if (pa->pa_type == MB_INODE_PA) { ei = EXT4_I(pa->pa_inode); atomic_dec(&ei->i_prealloc_active); } } static inline void ext4_mb_pa_free(struct ext4_prealloc_space *pa) { BUG_ON(!pa); BUG_ON(atomic_read(&pa->pa_count)); BUG_ON(pa->pa_deleted == 0); kmem_cache_free(ext4_pspace_cachep, pa); } static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu); ext4_mb_pa_free(pa); } /* * drops a reference to preallocated space descriptor * if this was the last reference and the space is consumed */ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, struct super_block *sb, struct ext4_prealloc_space *pa) { ext4_group_t grp; ext4_fsblk_t grp_blk; struct ext4_inode_info *ei = EXT4_I(ac->ac_inode); /* in this short window concurrent discard can set pa_deleted */ spin_lock(&pa->pa_lock); if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) { spin_unlock(&pa->pa_lock); return; } if (pa->pa_deleted == 1) { spin_unlock(&pa->pa_lock); return; } ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); grp_blk = pa->pa_pstart; /* * If doing group-based preallocation, pa_pstart may be in the * next group when pa is used up */ if (pa->pa_type == MB_GROUP_PA) grp_blk--; grp = ext4_get_group_number(sb, grp_blk); /* * possible race: * * P1 (buddy init) P2 (regular allocation) * find block B in PA * copy on-disk bitmap to buddy * mark B in on-disk bitmap * drop PA from group * mark all PAs in buddy * * thus, P1 initializes buddy with B available. to prevent this * we make "copy" and "mark all PAs" atomic and serialize "drop PA" * against that pair */ ext4_lock_group(sb, grp); list_del(&pa->pa_group_list); ext4_unlock_group(sb, grp); if (pa->pa_type == MB_INODE_PA) { write_lock(pa->pa_node_lock.inode_lock); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); write_unlock(pa->pa_node_lock.inode_lock); ext4_mb_pa_free(pa); } else { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } static void ext4_mb_pa_rb_insert(struct rb_root *root, struct rb_node *new) { struct rb_node **iter = &root->rb_node, *parent = NULL; struct ext4_prealloc_space *iter_pa, *new_pa; ext4_lblk_t iter_start, new_start; while (*iter) { iter_pa = rb_entry(*iter, struct ext4_prealloc_space, pa_node.inode_node); new_pa = rb_entry(new, struct ext4_prealloc_space, pa_node.inode_node); iter_start = iter_pa->pa_lstart; new_start = new_pa->pa_lstart; parent = *iter; if (new_start < iter_start) iter = &((*iter)->rb_left); else iter = &((*iter)->rb_right); } rb_link_node(new, parent, iter); rb_insert_color(new, root); } /* * creates new preallocated space for given inode */ static noinline_for_stack void ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_prealloc_space *pa; struct ext4_group_info *grp; struct ext4_inode_info *ei; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; if (ac->ac_b_ex.fe_len < ac->ac_orig_goal_len) { struct ext4_free_extent ex = { .fe_logical = ac->ac_g_ex.fe_logical, .fe_len = ac->ac_orig_goal_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); /* * We can't allocate as much as normalizer wants, so we try * to get proper lstart to cover the original request, except * when the goal doesn't cover the original request as below: * * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 * best_ex:0/200(200) -> adjusted: 1848/2048(200) */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); /* * Use the below logic for adjusting best extent as it keeps * fragmentation in check while ensuring logical range of best * extent doesn't overflow out of goal extent: * * 1. Check if best ex can be kept at end of goal (before * cr_best_avail trimmed it) and still cover original start * 2. Else, check if best ex can be kept at start of goal and * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; ex.fe_logical = orig_goal_end - EXT4_C2B(sbi, ex.fe_len); if (ac->ac_o_ex.fe_logical >= ex.fe_logical) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } pa->pa_lstart = ac->ac_b_ex.fe_logical; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_INODE_PA; mb_debug(sb, "new inode pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_inode_pa(ac, pa); atomic_add(pa->pa_free, &sbi->s_mb_preallocated); ext4_mb_use_inode_pa(ac, pa); ei = EXT4_I(ac->ac_inode); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); if (!grp) return; pa->pa_node_lock.inode_lock = &ei->i_prealloc_lock; pa->pa_inode = ac->ac_inode; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); write_lock(pa->pa_node_lock.inode_lock); ext4_mb_pa_rb_insert(&ei->i_prealloc_node, &pa->pa_node.inode_node); write_unlock(pa->pa_node_lock.inode_lock); atomic_inc(&ei->i_prealloc_active); } /* * creates new preallocated space for locality group inodes belongs to */ static noinline_for_stack void ext4_mb_new_group_pa(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg; struct ext4_prealloc_space *pa; struct ext4_group_info *grp; /* preallocate only when found space is larger then requested */ BUG_ON(ac->ac_o_ex.fe_len >= ac->ac_b_ex.fe_len); BUG_ON(ac->ac_status != AC_STATUS_FOUND); BUG_ON(!S_ISREG(ac->ac_inode->i_mode)); BUG_ON(ac->ac_pa == NULL); pa = ac->ac_pa; pa->pa_pstart = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); pa->pa_lstart = pa->pa_pstart; pa->pa_len = ac->ac_b_ex.fe_len; pa->pa_free = pa->pa_len; spin_lock_init(&pa->pa_lock); INIT_LIST_HEAD(&pa->pa_node.lg_list); INIT_LIST_HEAD(&pa->pa_group_list); pa->pa_deleted = 0; pa->pa_type = MB_GROUP_PA; mb_debug(sb, "new group pa %p: %llu/%d for %u\n", pa, pa->pa_pstart, pa->pa_len, pa->pa_lstart); trace_ext4_mb_new_group_pa(ac, pa); ext4_mb_use_group_pa(ac, pa); atomic_add(pa->pa_free, &EXT4_SB(sb)->s_mb_preallocated); grp = ext4_get_group_info(sb, ac->ac_b_ex.fe_group); if (!grp) return; lg = ac->ac_lg; BUG_ON(lg == NULL); pa->pa_node_lock.lg_lock = &lg->lg_prealloc_lock; pa->pa_inode = NULL; list_add(&pa->pa_group_list, &grp->bb_prealloc_list); /* * We will later add the new pa to the right bucket * after updating the pa_free in ext4_mb_release_context */ } static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac) { if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) ext4_mb_new_group_pa(ac); else ext4_mb_new_inode_pa(ac); } /* * finds all unused blocks in on-disk bitmap, frees them in * in-core bitmap and buddy. * @pa must be unlinked from inode and group lists, so that * nobody else can find/use it. * the caller MUST hold group/inode locks. * TODO: optimize the case when there are no in-core structures yet */ static noinline_for_stack void ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned int end; unsigned int next; ext4_group_t group; ext4_grpblk_t bit; unsigned long long grp_blk_start; int free = 0; BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); grp_blk_start = pa->pa_pstart - EXT4_C2B(sbi, bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); end = bit + pa->pa_len; while (bit < end) { bit = mb_find_next_zero_bit(bitmap_bh->b_data, end, bit); if (bit >= end) break; next = mb_find_next_bit(bitmap_bh->b_data, end, bit); mb_debug(sb, "free preallocated %u/%u in group %u\n", (unsigned) ext4_group_first_block_no(sb, group) + bit, (unsigned) next - bit, (unsigned) group); free += next - bit; trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit); trace_ext4_mb_release_inode_pa(pa, (grp_blk_start + EXT4_C2B(sbi, bit)), next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } if (free != pa->pa_free) { ext4_msg(e4b->bd_sb, KERN_CRIT, "pa %p: logic %lu, phys. %lu, len %d", pa, (unsigned long) pa->pa_lstart, (unsigned long) pa->pa_pstart, pa->pa_len); ext4_grp_locked_error(sb, group, 0, 0, "free %u, pa_free %u", free, pa->pa_free); /* * pa is already deleted so we use the value obtained * from the bitmap and continue. */ } atomic_add(free, &sbi->s_mb_discarded); } static noinline_for_stack void ext4_mb_release_group_pa(struct ext4_buddy *e4b, struct ext4_prealloc_space *pa) { struct super_block *sb = e4b->bd_sb; ext4_group_t group; ext4_grpblk_t bit; trace_ext4_mb_release_group_pa(sb, pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) { ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu", e4b->bd_group, group, pa->pa_pstart); return; } mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len); atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded); trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len); } /* * releases all preallocations in given group * * first, we need to decide discard policy: * - when do we discard * 1) ENOSPC * - how many do we discard * 1) how many requested */ static noinline_for_stack int ext4_mb_discard_group_preallocations(struct super_block *sb, ext4_group_t group, int *busy) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; LIST_HEAD(list); struct ext4_buddy e4b; struct ext4_inode_info *ei; int err; int free = 0; if (!grp) return 0; mb_debug(sb, "discard preallocation for group %u\n", group); if (list_empty(&grp->bb_prealloc_list)) goto out_dbg; bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); goto out_dbg; } err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { ext4_warning(sb, "Error %d loading buddy information for %u", err, group); put_bh(bitmap_bh); goto out_dbg; } ext4_lock_group(sb, group); list_for_each_entry_safe(pa, tmp, &grp->bb_prealloc_list, pa_group_list) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { spin_unlock(&pa->pa_lock); *busy = 1; continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); if (!free) this_cpu_inc(discard_pa_seq); /* we can trust pa_free ... */ free += pa->pa_free; spin_unlock(&pa->pa_lock); list_del(&pa->pa_group_list); list_add(&pa->u.pa_tmp_list, &list); } /* now free all selected PAs */ list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { /* remove from object (inode or locality group) */ if (pa->pa_type == MB_GROUP_PA) { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); } else { write_lock(pa->pa_node_lock.inode_lock); ei = EXT4_I(pa->pa_inode); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); write_unlock(pa->pa_node_lock.inode_lock); } list_del(&pa->u.pa_tmp_list); if (pa->pa_type == MB_GROUP_PA) { ext4_mb_release_group_pa(&e4b, pa); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } else { ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_mb_pa_free(pa); } } ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); out_dbg: mb_debug(sb, "discarded (%d) blocks preallocated for group %u bb_free (%d)\n", free, group, grp->bb_free); return free; } /* * releases all non-used preallocated blocks for given inode * * It's important to discard preallocations under i_data_sem * We don't want another block to be served from the prealloc * space when we are discarding the inode prealloc space. * * FIXME!! Make sure it is valid at all the call sites */ void ext4_discard_preallocations(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; struct buffer_head *bitmap_bh = NULL; struct ext4_prealloc_space *pa, *tmp; ext4_group_t group = 0; LIST_HEAD(list); struct ext4_buddy e4b; struct rb_node *iter; int err; if (!S_ISREG(inode->i_mode)) return; if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) return; mb_debug(sb, "discard preallocation for inode %llu\n", inode->i_ino); trace_ext4_discard_preallocations(inode, atomic_read(&ei->i_prealloc_active)); repeat: /* first, collect all pa's in the inode */ write_lock(&ei->i_prealloc_lock); for (iter = rb_first(&ei->i_prealloc_node); iter; iter = rb_next(iter)) { pa = rb_entry(iter, struct ext4_prealloc_space, pa_node.inode_node); BUG_ON(pa->pa_node_lock.inode_lock != &ei->i_prealloc_lock); spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* this shouldn't happen often - nobody should * use preallocation while we're discarding it */ spin_unlock(&pa->pa_lock); write_unlock(&ei->i_prealloc_lock); ext4_msg(sb, KERN_ERR, "uh-oh! used pa while discarding"); WARN_ON(1); schedule_timeout_uninterruptible(HZ); goto repeat; } if (pa->pa_deleted == 0) { ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node); list_add(&pa->u.pa_tmp_list, &list); continue; } /* someone is deleting pa right now */ spin_unlock(&pa->pa_lock); write_unlock(&ei->i_prealloc_lock); /* we have to wait here because pa_deleted * doesn't mean pa is already unlinked from * the list. as we might be called from * ->clear_inode() the inode will get freed * and concurrent thread which is unlinking * pa from inode's list may access already * freed memory, bad-bad-bad */ /* XXX: if this happens too often, we can * add a flag to force wait only in case * of ->clear_inode(), but not in case of * regular truncate */ schedule_timeout_uninterruptible(HZ); goto repeat; } write_unlock(&ei->i_prealloc_lock); list_for_each_entry_safe(pa, tmp, &list, u.pa_tmp_list) { BUG_ON(pa->pa_type != MB_INODE_PA); group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { err = PTR_ERR(bitmap_bh); ext4_error_err(sb, -err, "Error %d reading block bitmap for %u", err, group); ext4_mb_unload_buddy(&e4b); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); put_bh(bitmap_bh); list_del(&pa->u.pa_tmp_list); ext4_mb_pa_free(pa); } } static int ext4_mb_pa_alloc(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa; BUG_ON(ext4_pspace_cachep == NULL); pa = kmem_cache_zalloc(ext4_pspace_cachep, GFP_NOFS); if (!pa) return -ENOMEM; atomic_set(&pa->pa_count, 1); ac->ac_pa = pa; return 0; } static void ext4_mb_pa_put_free(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; BUG_ON(!pa); ac->ac_pa = NULL; WARN_ON(!atomic_dec_and_test(&pa->pa_count)); /* * current function is only called due to an error or due to * len of found blocks < len of requested blocks hence the PA has not * been added to grp->bb_prealloc_list. So we don't need to lock it */ pa->pa_deleted = 1; ext4_mb_pa_free(pa); } #ifdef CONFIG_EXT4_DEBUG static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; if (ext4_emergency_state(sb)) return; ngroups = ext4_get_groups_count(sb); mb_debug(sb, "groups: "); for (i = 0; i < ngroups; i++) { struct ext4_group_info *grp = ext4_get_group_info(sb, i); struct ext4_prealloc_space *pa; ext4_grpblk_t start; struct list_head *cur; if (!grp) continue; ext4_lock_group(sb, i); list_for_each(cur, &grp->bb_prealloc_list) { pa = list_entry(cur, struct ext4_prealloc_space, pa_group_list); spin_lock(&pa->pa_lock); ext4_get_group_no_and_offset(sb, pa->pa_pstart, NULL, &start); spin_unlock(&pa->pa_lock); mb_debug(sb, "PA:%u:%d:%d\n", i, start, pa->pa_len); } ext4_unlock_group(sb, i); mb_debug(sb, "%u: %d/%d\n", i, grp->bb_free, grp->bb_fragments); } } static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; if (ext4_emergency_state(sb)) return; mb_debug(sb, "Can't allocate:" " Allocation context details:"); mb_debug(sb, "status %u flags 0x%x", ac->ac_status, ac->ac_flags); mb_debug(sb, "orig %lu/%lu/%lu@%lu, " "goal %lu/%lu/%lu@%lu, " "best %lu/%lu/%lu@%lu cr %d", (unsigned long)ac->ac_o_ex.fe_group, (unsigned long)ac->ac_o_ex.fe_start, (unsigned long)ac->ac_o_ex.fe_len, (unsigned long)ac->ac_o_ex.fe_logical, (unsigned long)ac->ac_g_ex.fe_group, (unsigned long)ac->ac_g_ex.fe_start, (unsigned long)ac->ac_g_ex.fe_len, (unsigned long)ac->ac_g_ex.fe_logical, (unsigned long)ac->ac_b_ex.fe_group, (unsigned long)ac->ac_b_ex.fe_start, (unsigned long)ac->ac_b_ex.fe_len, (unsigned long)ac->ac_b_ex.fe_logical, (int)ac->ac_criteria); mb_debug(sb, "%u found", ac->ac_found); mb_debug(sb, "used pa: %s, ", str_yes_no(ac->ac_pa)); if (ac->ac_pa) mb_debug(sb, "pa_type %s\n", ac->ac_pa->pa_type == MB_GROUP_PA ? "group pa" : "inode pa"); ext4_mb_show_pa(sb); } #else static inline void ext4_mb_show_pa(struct super_block *sb) { } static inline void ext4_mb_show_ac(struct ext4_allocation_context *ac) { ext4_mb_show_pa(ac->ac_sb); } #endif /* * We use locality group preallocation for small size file. The size of the * file is determined by the current size or the resulting size after * allocation which ever is larger * * One can tune this size via /sys/fs/ext4/<partition>/mb_stream_req */ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); int bsbits = ac->ac_sb->s_blocksize_bits; loff_t size, isize; bool inode_pa_eligible, group_pa_eligible; if (!(ac->ac_flags & EXT4_MB_HINT_DATA)) return; if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) return; group_pa_eligible = sbi->s_mb_group_prealloc > 0; inode_pa_eligible = true; size = extent_logical_end(sbi, &ac->ac_o_ex); isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1) >> bsbits; /* No point in using inode preallocation for closed files */ if ((size == isize) && !ext4_fs_is_busy(sbi) && !inode_is_open_for_write(ac->ac_inode)) inode_pa_eligible = false; size = max(size, isize); /* Don't use group allocation for large files */ if (size > sbi->s_mb_stream_request) group_pa_eligible = false; if (!group_pa_eligible) { if (inode_pa_eligible) ac->ac_flags |= EXT4_MB_STREAM_ALLOC; else ac->ac_flags |= EXT4_MB_HINT_NOPREALLOC; return; } BUG_ON(ac->ac_lg != NULL); /* * locality group prealloc space are per cpu. The reason for having * per cpu locality group is to reduce the contention between block * request from multiple CPUs. */ ac->ac_lg = raw_cpu_ptr(sbi->s_locality_groups); /* we're going to use group allocation */ ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC; /* serialize all allocations in the group */ mutex_lock(&ac->ac_lg->lg_mutex); } static noinline_for_stack void ext4_mb_initialize_context(struct ext4_allocation_context *ac, struct ext4_allocation_request *ar) { struct super_block *sb = ar->inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; ext4_group_t group; unsigned int len; ext4_fsblk_t goal; ext4_grpblk_t block; /* we can't allocate > group size */ len = ar->len; /* just a dirty hack to filter too big requests */ if (len >= EXT4_CLUSTERS_PER_GROUP(sb)) len = EXT4_CLUSTERS_PER_GROUP(sb); /* start searching from the goal */ goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; ac->ac_inode = ar->inode; ac->ac_o_ex.fe_logical = ac->ac_b_ex.fe_logical; ac->ac_o_ex.fe_group = group; ac->ac_o_ex.fe_start = block; ac->ac_o_ex.fe_len = len; ac->ac_g_ex = ac->ac_o_ex; ac->ac_orig_goal_len = ac->ac_g_ex.fe_len; ac->ac_flags = ar->flags; /* we have to define context: we'll work with a file or * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); mb_debug(sb, "init ac: %u blocks @ %u, goal %u, flags 0x%x, 2^%d, " "left: %u/%u, right %u/%u to %swritable\n", (unsigned) ar->len, (unsigned) ar->logical, (unsigned) ar->goal, ac->ac_flags, ac->ac_2order, (unsigned) ar->lleft, (unsigned) ar->pleft, (unsigned) ar->lright, (unsigned) ar->pright, inode_is_open_for_write(ar->inode) ? "" : "non-"); } static noinline_for_stack void ext4_mb_discard_lg_preallocations(struct super_block *sb, struct ext4_locality_group *lg, int order, int total_entries) { ext4_group_t group = 0; struct ext4_buddy e4b; LIST_HEAD(discard_list); struct ext4_prealloc_space *pa, *tmp; mb_debug(sb, "discard locality group preallocation\n"); spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(pa, &lg->lg_prealloc_list[order], pa_node.lg_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&pa->pa_lock); if (atomic_read(&pa->pa_count)) { /* * This is the pa that we just used * for block allocation. So don't * free that */ spin_unlock(&pa->pa_lock); continue; } if (pa->pa_deleted) { spin_unlock(&pa->pa_lock); continue; } /* only lg prealloc space */ BUG_ON(pa->pa_type != MB_GROUP_PA); /* seems this one can be freed ... */ ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_node.lg_list); list_add(&pa->u.pa_tmp_list, &discard_list); total_entries--; if (total_entries <= 5) { /* * we want to keep only 5 entries * allowing it to grow to 8. This * mak sure we don't call discard * soon for this list. */ break; } } spin_unlock(&lg->lg_prealloc_lock); list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) { int err; group = ext4_get_group_number(sb, pa->pa_pstart); err = ext4_mb_load_buddy_gfp(sb, group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) { ext4_error_err(sb, -err, "Error %d loading buddy information for %u", err, group); continue; } ext4_lock_group(sb, group); list_del(&pa->pa_group_list); ext4_mb_release_group_pa(&e4b, pa); ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); list_del(&pa->u.pa_tmp_list); call_rcu(&(pa)->u.pa_rcu, ext4_mb_pa_callback); } } /* * We have incremented pa_count. So it cannot be freed at this * point. Also we hold lg_mutex. So no parallel allocation is * possible from this lg. That means pa_free cannot be updated. * * A parallel ext4_mb_discard_group_preallocations is possible. * which can cause the lg_prealloc_list to be updated. */ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) { int order, added = 0, lg_prealloc_count = 1; struct super_block *sb = ac->ac_sb; struct ext4_locality_group *lg = ac->ac_lg; struct ext4_prealloc_space *tmp_pa, *pa = ac->ac_pa; order = fls(pa->pa_free) - 1; if (order > PREALLOC_TB_SIZE - 1) /* The max size of hash table is PREALLOC_TB_SIZE */ order = PREALLOC_TB_SIZE - 1; /* Add the prealloc space to lg */ spin_lock(&lg->lg_prealloc_lock); list_for_each_entry_rcu(tmp_pa, &lg->lg_prealloc_list[order], pa_node.lg_list, lockdep_is_held(&lg->lg_prealloc_lock)) { spin_lock(&tmp_pa->pa_lock); if (tmp_pa->pa_deleted) { spin_unlock(&tmp_pa->pa_lock); continue; } if (!added && pa->pa_free < tmp_pa->pa_free) { /* Add to the tail of the previous entry */ list_add_tail_rcu(&pa->pa_node.lg_list, &tmp_pa->pa_node.lg_list); added = 1; /* * we want to count the total * number of entries in the list */ } spin_unlock(&tmp_pa->pa_lock); lg_prealloc_count++; } if (!added) list_add_tail_rcu(&pa->pa_node.lg_list, &lg->lg_prealloc_list[order]); spin_unlock(&lg->lg_prealloc_lock); /* Now trim the list to be not more than 8 elements */ if (lg_prealloc_count > 8) ext4_mb_discard_lg_preallocations(sb, lg, order, lg_prealloc_count); } /* * release all resource we used in allocation */ static void ext4_mb_release_context(struct ext4_allocation_context *ac) { struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; if (pa) { if (pa->pa_type == MB_GROUP_PA) { /* see comment in ext4_mb_use_group_pa() */ spin_lock(&pa->pa_lock); pa->pa_pstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_lstart += EXT4_C2B(sbi, ac->ac_b_ex.fe_len); pa->pa_free -= ac->ac_b_ex.fe_len; pa->pa_len -= ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); /* * We want to add the pa to the right bucket. * Remove it from the list and while adding * make sure the list to which we are adding * doesn't grow big. */ if (likely(pa->pa_free)) { spin_lock(pa->pa_node_lock.lg_lock); list_del_rcu(&pa->pa_node.lg_list); spin_unlock(pa->pa_node_lock.lg_lock); ext4_mb_add_n_trim(ac); } } ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_folio) folio_put(ac->ac_bitmap_folio); if (ac->ac_buddy_folio) folio_put(ac->ac_buddy_folio); if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); } static int ext4_mb_discard_preallocations(struct super_block *sb, int needed) { ext4_group_t i, ngroups = ext4_get_groups_count(sb); int ret; int freed = 0, busy = 0; int retry = 0; trace_ext4_mb_discard_preallocations(sb, needed); if (needed == 0) needed = EXT4_CLUSTERS_PER_GROUP(sb) + 1; repeat: for (i = 0; i < ngroups && needed > 0; i++) { ret = ext4_mb_discard_group_preallocations(sb, i, &busy); freed += ret; needed -= ret; cond_resched(); } if (needed > 0 && busy && ++retry < 3) { busy = 0; goto repeat; } return freed; } static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb, struct ext4_allocation_context *ac, u64 *seq) { int freed; u64 seq_retry = 0; bool ret = false; freed = ext4_mb_discard_preallocations(sb, ac->ac_o_ex.fe_len); if (freed) { ret = true; goto out_dbg; } seq_retry = ext4_get_discard_pa_seq_sum(); if (!(ac->ac_flags & EXT4_MB_STRICT_CHECK) || seq_retry != *seq) { ac->ac_flags |= EXT4_MB_STRICT_CHECK; *seq = seq_retry; ret = true; } out_dbg: mb_debug(sb, "freed %d, retry ? %s\n", freed, str_yes_no(ret)); return ret; } /* * Simple allocator for Ext4 fast commit replay path. It searches for blocks * linearly starting at the goal block and also excludes the blocks which * are going to be in use after fast commit replay. */ static ext4_fsblk_t ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp) { struct buffer_head *bitmap_bh; struct super_block *sb = ar->inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_group_t group, nr; ext4_grpblk_t blkoff; ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_fsblk_t goal, block; struct ext4_super_block *es = sbi->s_es; goal = ar->goal; if (goal < le32_to_cpu(es->s_first_data_block) || goal >= ext4_blocks_count(es)) goal = le32_to_cpu(es->s_first_data_block); ar->len = 0; ext4_get_group_no_and_offset(sb, goal, &group, &blkoff); for (nr = ext4_get_groups_count(sb); nr > 0; nr--) { bitmap_bh = ext4_read_block_bitmap(sb, group); if (IS_ERR(bitmap_bh)) { *errp = PTR_ERR(bitmap_bh); pr_warn("Failed to read block bitmap\n"); return 0; } while (1) { i = mb_find_next_zero_bit(bitmap_bh->b_data, max, blkoff); if (i >= max) break; if (ext4_fc_replay_check_excluded(sb, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i))) { blkoff = i + 1; } else break; } brelse(bitmap_bh); if (i < max) break; if (++group >= ext4_get_groups_count(sb)) group = 0; blkoff = 0; } if (i >= max) { *errp = -ENOSPC; return 0; } block = ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i); ext4_mb_mark_bb(sb, block, 1, true); ar->len = 1; *errp = 0; return block; } /* * Main entry point into mballoc to allocate blocks * it tries to use preallocation first, then falls back * to usual allocation */ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, struct ext4_allocation_request *ar, int *errp) { struct ext4_allocation_context *ac = NULL; struct ext4_sb_info *sbi; struct super_block *sb; ext4_fsblk_t block = 0; unsigned int inquota = 0; unsigned int reserv_clstrs = 0; int retries = 0; u64 seq; might_sleep(); sb = ar->inode->i_sb; sbi = EXT4_SB(sb); trace_ext4_request_blocks(ar); if (sbi->s_mount_state & EXT4_FC_REPLAY) return ext4_mb_new_blocks_simple(ar, errp); /* Allow to use superuser reservation for quota file */ if (ext4_is_quota_file(ar->inode)) ar->flags |= EXT4_MB_USE_ROOT_BLOCKS; if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) { /* Without delayed allocation we need to verify * there is enough free blocks to do block allocation * and verify allocation doesn't exceed the quota limits. */ while (ar->len && ext4_claim_free_clusters(sbi, ar->len, ar->flags)) { /* let others to free the space */ cond_resched(); ar->len = ar->len >> 1; } if (!ar->len) { ext4_mb_show_pa(sb); *errp = -ENOSPC; return 0; } reserv_clstrs = ar->len; if (ar->flags & EXT4_MB_USE_ROOT_BLOCKS) { dquot_alloc_block_nofail(ar->inode, EXT4_C2B(sbi, ar->len)); } else { while (ar->len && dquot_alloc_block(ar->inode, EXT4_C2B(sbi, ar->len))) { ar->flags |= EXT4_MB_HINT_NOPREALLOC; ar->len--; } } inquota = ar->len; if (ar->len == 0) { *errp = -EDQUOT; goto out; } } ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS); if (!ac) { ar->len = 0; *errp = -ENOMEM; goto out; } ext4_mb_initialize_context(ac, ar); ac->ac_op = EXT4_MB_HISTORY_PREALLOC; seq = this_cpu_read(discard_pa_seq); if (!ext4_mb_use_preallocated(ac)) { ac->ac_op = EXT4_MB_HISTORY_ALLOC; ext4_mb_normalize_request(ac, ar); *errp = ext4_mb_pa_alloc(ac); if (*errp) goto errout; repeat: /* allocate space in core */ *errp = ext4_mb_regular_allocator(ac); /* * pa allocated above is added to grp->bb_prealloc_list only * when we were able to allocate some block i.e. when * ac->ac_status == AC_STATUS_FOUND. * And error from above mean ac->ac_status != AC_STATUS_FOUND * So we have to free this pa here itself. */ if (*errp) { ext4_mb_pa_put_free(ac); ext4_discard_allocated_blocks(ac); goto errout; } if (ac->ac_status == AC_STATUS_FOUND && ac->ac_o_ex.fe_len >= ac->ac_f_ex.fe_len) ext4_mb_pa_put_free(ac); } if (likely(ac->ac_status == AC_STATUS_FOUND)) { *errp = ext4_mb_mark_diskspace_used(ac, handle); if (*errp) { ext4_discard_allocated_blocks(ac); goto errout; } else { block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); ar->len = ac->ac_b_ex.fe_len; } } else { if (++retries < 3 && ext4_mb_discard_preallocations_should_retry(sb, ac, &seq)) goto repeat; /* * If block allocation fails then the pa allocated above * needs to be freed here itself. */ ext4_mb_pa_put_free(ac); *errp = -ENOSPC; } if (*errp) { errout: ac->ac_b_ex.fe_len = 0; ar->len = 0; ext4_mb_show_ac(ac); } ext4_mb_release_context(ac); kmem_cache_free(ext4_ac_cachep, ac); out: if (inquota && ar->len < inquota) dquot_free_block(ar->inode, EXT4_C2B(sbi, inquota - ar->len)); /* release any reserved blocks */ if (reserv_clstrs) percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); trace_ext4_allocate_blocks(ar, (unsigned long long)block); return block; } /* * We can merge two free data extents only if the physical blocks * are contiguous, AND the extents were freed by the same transaction, * AND the blocks are associated with the same group. */ static inline bool ext4_freed_extents_can_be_merged(struct ext4_free_data *entry1, struct ext4_free_data *entry2) { if (entry1->efd_tid != entry2->efd_tid) return false; if (entry1->efd_start_cluster + entry1->efd_count != entry2->efd_start_cluster) return false; if (WARN_ON_ONCE(entry1->efd_group != entry2->efd_group)) return false; return true; } static inline void ext4_merge_freed_extents(struct ext4_sb_info *sbi, struct rb_root *root, struct ext4_free_data *entry1, struct ext4_free_data *entry2) { entry1->efd_count += entry2->efd_count; spin_lock(&sbi->s_md_lock); list_del(&entry2->efd_list); spin_unlock(&sbi->s_md_lock); rb_erase(&entry2->efd_node, root); kmem_cache_free(ext4_free_data_cachep, entry2); } static inline void ext4_try_merge_freed_extent_prev(struct ext4_sb_info *sbi, struct rb_root *root, struct ext4_free_data *entry) { struct ext4_free_data *prev; struct rb_node *node; node = rb_prev(&entry->efd_node); if (!node) return; prev = rb_entry(node, struct ext4_free_data, efd_node); if (ext4_freed_extents_can_be_merged(prev, entry)) ext4_merge_freed_extents(sbi, root, prev, entry); } static inline void ext4_try_merge_freed_extent_next(struct ext4_sb_info *sbi, struct rb_root *root, struct ext4_free_data *entry) { struct ext4_free_data *next; struct rb_node *node; node = rb_next(&entry->efd_node); if (!node) return; next = rb_entry(node, struct ext4_free_data, efd_node); if (ext4_freed_extents_can_be_merged(entry, next)) ext4_merge_freed_extents(sbi, root, entry, next); } static noinline_for_stack void ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, struct ext4_free_data *new_entry) { ext4_group_t group = e4b->bd_group; ext4_grpblk_t cluster; ext4_grpblk_t clusters = new_entry->efd_count; struct ext4_free_data *entry = NULL; struct ext4_group_info *db = e4b->bd_info; struct super_block *sb = e4b->bd_sb; struct ext4_sb_info *sbi = EXT4_SB(sb); struct rb_root *root = &db->bb_free_root; struct rb_node **n = &root->rb_node; struct rb_node *parent = NULL, *new_node; BUG_ON(!ext4_handle_valid(handle)); BUG_ON(e4b->bd_bitmap_folio == NULL); BUG_ON(e4b->bd_buddy_folio == NULL); new_node = &new_entry->efd_node; cluster = new_entry->efd_start_cluster; if (!*n) { /* first free block exent. We need to protect buddy cache from being freed, * otherwise we'll refresh it from * on-disk bitmap and lose not-yet-available * blocks */ folio_get(e4b->bd_buddy_folio); folio_get(e4b->bd_bitmap_folio); } while (*n) { parent = *n; entry = rb_entry(parent, struct ext4_free_data, efd_node); if (cluster < entry->efd_start_cluster) n = &(*n)->rb_left; else if (cluster >= (entry->efd_start_cluster + entry->efd_count)) n = &(*n)->rb_right; else { ext4_grp_locked_error(sb, group, 0, ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, cluster), "Block already on to-be-freed list"); kmem_cache_free(ext4_free_data_cachep, new_entry); return; } } atomic_add(clusters, &sbi->s_mb_free_pending); if (!entry) goto insert; /* Now try to see the extent can be merged to prev and next */ if (ext4_freed_extents_can_be_merged(new_entry, entry)) { entry->efd_start_cluster = cluster; entry->efd_count += new_entry->efd_count; kmem_cache_free(ext4_free_data_cachep, new_entry); ext4_try_merge_freed_extent_prev(sbi, root, entry); return; } if (ext4_freed_extents_can_be_merged(entry, new_entry)) { entry->efd_count += new_entry->efd_count; kmem_cache_free(ext4_free_data_cachep, new_entry); ext4_try_merge_freed_extent_next(sbi, root, entry); return; } insert: rb_link_node(new_node, parent, n); rb_insert_color(new_node, root); spin_lock(&sbi->s_md_lock); list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list[new_entry->efd_tid & 1]); spin_unlock(&sbi->s_md_lock); } static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block, unsigned long count) { struct super_block *sb = inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; ext4_get_group_no_and_offset(sb, block, &group, &blkoff); ext4_mb_mark_context(NULL, sb, false, group, blkoff, count, EXT4_MB_BITMAP_MARKED_CHECK | EXT4_MB_SYNC_UPDATE, NULL); } /** * ext4_mb_clear_bb() -- helper function for freeing blocks. * Used by ext4_free_blocks() * @handle: handle for this transaction * @inode: inode * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, ext4_fsblk_t block, unsigned long count, int flags) { struct super_block *sb = inode->i_sb; struct ext4_group_info *grp; unsigned int overflow; ext4_grpblk_t bit; ext4_group_t block_group; struct ext4_sb_info *sbi; struct ext4_buddy e4b; unsigned int count_clusters; int err = 0; int mark_flags = 0; ext4_grpblk_t changed; sbi = EXT4_SB(sb); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_out; } flags |= EXT4_FREE_BLOCKS_VALIDATED; do_more: overflow = 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); grp = ext4_get_group_info(sb, block_group); if (unlikely(!grp || EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return; /* * Check to see if we are freeing blocks across a group * boundary. */ if (EXT4_C2B(sbi, bit) + count > EXT4_BLOCKS_PER_GROUP(sb)) { overflow = EXT4_C2B(sbi, bit) + count - EXT4_BLOCKS_PER_GROUP(sb); count -= overflow; /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } count_clusters = EXT4_NUM_B2C(sbi, count); trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters); /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */ err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b, GFP_NOFS|__GFP_NOFAIL); if (err) goto error_out; if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks in system zone - " "Block = %llu, count = %lu", block, count); /* err = 0. ext4_std_error should be a no op */ goto error_clean; } #ifdef AGGRESSIVE_CHECK mark_flags |= EXT4_MB_BITMAP_MARKED_CHECK; #endif err = ext4_mb_mark_context(handle, sb, false, block_group, bit, count_clusters, mark_flags, &changed); if (err && changed == 0) goto error_clean; #ifdef AGGRESSIVE_CHECK BUG_ON(changed != count_clusters); #endif /* * We need to make sure we don't reuse the freed block until after the * transaction is committed. We make an exception if the inode is to be * written in writeback mode since writeback mode has weak data * consistency guarantees. */ if (ext4_handle_valid(handle) && ((flags & EXT4_FREE_BLOCKS_METADATA) || !ext4_should_writeback_data(inode))) { struct ext4_free_data *new_entry; /* * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed * to fail. */ new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS|__GFP_NOFAIL); new_entry->efd_start_cluster = bit; new_entry->efd_group = block_group; new_entry->efd_count = count_clusters; new_entry->efd_tid = handle->h_transaction->t_tid; ext4_lock_group(sb, block_group); ext4_mb_free_metadata(handle, &e4b, new_entry); } else { if (test_opt(sb, DISCARD)) { err = ext4_issue_discard(sb, block_group, bit, count_clusters); /* * Ignore EOPNOTSUPP error. This is consistent with * what happens when using journal. */ if (err == -EOPNOTSUPP) err = 0; if (err) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%u block:%d count:%lu failed" " with %d", block_group, bit, count, err); } EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info); ext4_lock_group(sb, block_group); mb_free_blocks(inode, &e4b, bit, count_clusters); } ext4_unlock_group(sb, block_group); /* * on a bigalloc file system, defer the s_freeclusters_counter * update to the caller (ext4_remove_space and friends) so they * can determine if a cluster freed here should be rereserved */ if (!(flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER)) { if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); } if (overflow && !err) { block += count; count = overflow; ext4_mb_unload_buddy(&e4b); /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; goto do_more; } error_clean: ext4_mb_unload_buddy(&e4b); error_out: ext4_std_error(sb, err); } /** * ext4_free_blocks() -- Free given blocks and update quota * @handle: handle for this transaction * @inode: inode * @bh: optional buffer of the block to be freed * @block: starting physical block to be freed * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags) { struct super_block *sb = inode->i_sb; unsigned int overflow; struct ext4_sb_info *sbi; sbi = EXT4_SB(sb); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); else block = bh->b_blocknr; } if (sbi->s_mount_state & EXT4_FC_REPLAY) { ext4_free_blocks_simple(inode, block, EXT4_NUM_B2C(sbi, count)); return; } might_sleep(); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); return; } flags |= EXT4_FREE_BLOCKS_VALIDATED; ext4_debug("freeing block %llu\n", block); trace_ext4_free_blocks(inode, block, count, flags); if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { BUG_ON(count > 1); ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA, inode, bh, block); } /* * If the extent to be freed does not begin on a cluster * boundary, we need to deal with partial clusters at the * beginning and end of the extent. Normally we will free * blocks at the beginning or the end unless we are explicitly * requested to avoid doing so. */ overflow = EXT4_PBLK_COFF(sbi, block); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { overflow = sbi->s_cluster_ratio - overflow; block += overflow; if (count > overflow) count -= overflow; else return; } else { block -= overflow; count += overflow; } /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { if (count > overflow) count -= overflow; else return; } else count += sbi->s_cluster_ratio - overflow; /* The range changed so it's no longer validated */ flags &= ~EXT4_FREE_BLOCKS_VALIDATED; } if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) { int i; int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA; for (i = 0; i < count; i++) { cond_resched(); if (is_metadata) bh = sb_find_get_block_nonatomic(inode->i_sb, block + i); ext4_forget(handle, is_metadata, inode, bh, block + i); } } ext4_mb_clear_bb(handle, inode, block, count, flags); } /** * ext4_group_add_blocks() -- Add given blocks to an existing group * @handle: handle to this transaction * @sb: super block * @block: start physical block to add to the block group * @count: number of blocks to free * * This marks the blocks as free in the bitmap and buddy. */ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count) { ext4_group_t block_group; ext4_grpblk_t bit; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_buddy e4b; int err = 0; ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block); ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1); unsigned long cluster_count = last_cluster - first_cluster + 1; ext4_grpblk_t changed; ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1); if (cluster_count == 0) return 0; ext4_get_group_no_and_offset(sb, block, &block_group, &bit); /* * Check to see if we are freeing blocks across a group * boundary. */ if (bit + cluster_count > EXT4_CLUSTERS_PER_GROUP(sb)) { ext4_warning(sb, "too many blocks added to group %u", block_group); err = -EINVAL; goto error_out; } err = ext4_mb_load_buddy(sb, block_group, &e4b); if (err) goto error_out; if (!ext4_sb_block_valid(sb, NULL, block, count)) { ext4_error(sb, "Adding blocks in system zones - " "Block = %llu, count = %lu", block, count); err = -EINVAL; goto error_clean; } err = ext4_mb_mark_context(handle, sb, false, block_group, bit, cluster_count, EXT4_MB_BITMAP_MARKED_CHECK, &changed); if (err && changed == 0) goto error_clean; if (changed != cluster_count) ext4_error(sb, "bit already cleared in group %u", block_group); ext4_lock_group(sb, block_group); mb_free_blocks(NULL, &e4b, bit, cluster_count); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, changed); error_clean: ext4_mb_unload_buddy(&e4b); error_out: ext4_std_error(sb, err); return err; } /** * ext4_trim_extent -- function to TRIM one single free extent in the group * @sb: super block for the file system * @start: starting block of the free extent in the alloc. group * @count: number of blocks to TRIM * @e4b: ext4 buddy for the group * * Trim "count" blocks starting at "start" in the "group". To assure that no * one will allocate those blocks, mark it as used in buddy bitmap. This must * be called with under the group lock. */ static int ext4_trim_extent(struct super_block *sb, int start, int count, struct ext4_buddy *e4b) __releases(bitlock) __acquires(bitlock) { struct ext4_free_extent ex; ext4_group_t group = e4b->bd_group; int ret = 0; trace_ext4_trim_extent(sb, group, start, count); assert_spin_locked(ext4_group_lock_ptr(sb, group)); ex.fe_start = start; ex.fe_group = group; ex.fe_len = count; /* * Mark blocks used, so no one can reuse them while * being trimmed. */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); ret = ext4_issue_discard(sb, group, start, count); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); return ret; } static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb, ext4_group_t grp) { unsigned long nr_clusters_in_group; if (grp < (ext4_get_groups_count(sb) - 1)) nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb); else nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) - ext4_group_first_block_no(sb, grp)) >> EXT4_CLUSTER_BITS(sb); return nr_clusters_in_group - 1; } static bool ext4_trim_interrupted(void) { return fatal_signal_pending(current) || freezing(current); } static int ext4_try_to_trim_range(struct super_block *sb, struct ext4_buddy *e4b, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) __acquires(ext4_group_lock_ptr(sb, e4b->bd_group)) __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) { ext4_grpblk_t next, count, free_count, last, origin_start; bool set_trimmed = false; void *bitmap; if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) return 0; last = ext4_last_grp_cluster(sb, e4b->bd_group); bitmap = e4b->bd_bitmap; if (start == 0 && max >= last) set_trimmed = true; origin_start = start; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; while (start <= max) { start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; next = mb_find_next_bit(bitmap, last + 1, start); if (origin_start == 0 && next >= last) set_trimmed = true; if ((next - start) >= minblocks) { int ret = ext4_trim_extent(sb, start, next - start, e4b); if (ret && ret != -EOPNOTSUPP) return count; count += next - start; } free_count += next - start; start = next + 1; if (ext4_trim_interrupted()) return count; if (need_resched()) { ext4_unlock_group(sb, e4b->bd_group); cond_resched(); ext4_lock_group(sb, e4b->bd_group); } if ((e4b->bd_info->bb_free - free_count) < minblocks) break; } if (set_trimmed) EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info); return count; } /** * ext4_trim_all_free -- function to trim all free space in alloc. group * @sb: super block for file system * @group: group to be trimmed * @start: first group block to examine * @max: last group block to examine * @minblocks: minimum extent block count * * ext4_trim_all_free walks through group's block bitmap searching for free * extents. When the free extent is found, mark it as used in group buddy * bitmap. Then issue a TRIM command on this extent and free the extent in * the group buddy bitmap. */ static ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks) { struct ext4_buddy e4b; int ret; trace_ext4_trim_all_free(sb, group, start, max); ret = ext4_mb_load_buddy(sb, group, &e4b); if (ret) { ext4_warning(sb, "Error %d loading buddy information for %u", ret, group); return ret; } ext4_lock_group(sb, group); if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) || minblocks < EXT4_SB(sb)->s_last_trim_minblks) ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks); else ret = 0; ext4_unlock_group(sb, group); ext4_mb_unload_buddy(&e4b); ext4_debug("trimmed %d blocks in the group %d\n", ret, group); return ret; } /** * ext4_trim_fs() -- trim ioctl handle function * @sb: superblock for filesystem * @range: fstrim_range structure * * start: First Byte to trim * len: number of Bytes to trim from start * minlen: minimum extent length in Bytes * ext4_trim_fs goes through all allocation groups containing Bytes from * start to start+len. For each such a group ext4_trim_all_free function * is invoked to trim all free space. */ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) { unsigned int discard_granularity = bdev_discard_granularity(sb->s_bdev); struct ext4_group_info *grp; ext4_group_t group, first_group, last_group; ext4_grpblk_t cnt = 0, first_cluster, last_cluster; uint64_t start, end, minlen, trimmed = 0; ext4_fsblk_t first_data_blk = le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block); ext4_fsblk_t max_blks = ext4_blocks_count(EXT4_SB(sb)->s_es); int ret = 0; start = range->start >> sb->s_blocksize_bits; end = start + (range->len >> sb->s_blocksize_bits) - 1; minlen = EXT4_NUM_B2C(EXT4_SB(sb), range->minlen >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb) || start >= max_blks || range->len < sb->s_blocksize) return -EINVAL; /* No point to try to trim less than discard granularity */ if (range->minlen < discard_granularity) { minlen = EXT4_NUM_B2C(EXT4_SB(sb), discard_granularity >> sb->s_blocksize_bits); if (minlen > EXT4_CLUSTERS_PER_GROUP(sb)) goto out; } if (end >= max_blks - 1) end = max_blks - 1; if (end <= first_data_blk) goto out; if (start < first_data_blk) start = first_data_blk; /* Determine first and last group to examine based on start and end */ ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start, &first_group, &first_cluster); ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) end, &last_group, &last_cluster); /* end now represents the last cluster to discard in this group */ end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; for (group = first_group; group <= last_group; group++) { if (ext4_trim_interrupted()) break; grp = ext4_get_group_info(sb, group); if (!grp) continue; /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) break; } /* * For all the groups except the last one, last cluster will * always be EXT4_CLUSTERS_PER_GROUP(sb)-1, so we only need to * change it for the last group, note that last_cluster is * already computed earlier by ext4_get_group_no_and_offset() */ if (group == last_group) end = last_cluster; if (grp->bb_free >= minlen) { cnt = ext4_trim_all_free(sb, group, first_cluster, end, minlen); if (cnt < 0) { ret = cnt; break; } trimmed += cnt; } /* * For every group except the first one, we are sure * that the first cluster to discard will be cluster #0. */ first_cluster = 0; } if (!ret) EXT4_SB(sb)->s_last_trim_minblks = minlen; out: range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; return ret; } /* Iterate all the free extents in the group. */ int ext4_mballoc_query_range( struct super_block *sb, ext4_group_t group, ext4_grpblk_t first, ext4_grpblk_t end, ext4_mballoc_query_range_fn meta_formatter, ext4_mballoc_query_range_fn formatter, void *priv) { void *bitmap; ext4_grpblk_t start, next; struct ext4_buddy e4b; int error; error = ext4_mb_load_buddy(sb, group, &e4b); if (error) return error; bitmap = e4b.bd_bitmap; ext4_lock_group(sb, group); start = max(e4b.bd_info->bb_first_free, first); if (end >= EXT4_CLUSTERS_PER_GROUP(sb)) end = EXT4_CLUSTERS_PER_GROUP(sb) - 1; if (meta_formatter && start != first) { if (start > end) start = end; ext4_unlock_group(sb, group); error = meta_formatter(sb, group, first, start - first, priv); if (error) goto out_unload; ext4_lock_group(sb, group); } while (start <= end) { start = mb_find_next_zero_bit(bitmap, end + 1, start); if (start > end) break; next = mb_find_next_bit(bitmap, end + 1, start); ext4_unlock_group(sb, group); error = formatter(sb, group, start, next - start, priv); if (error) goto out_unload; ext4_lock_group(sb, group); start = next + 1; } ext4_unlock_group(sb, group); out_unload: ext4_mb_unload_buddy(&e4b); return error; } #if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) void mb_clear_bits_test(void *bm, int cur, int len) { mb_clear_bits(bm, cur, len); } EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bits_test); ext4_fsblk_t ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar, int *errp) { return ext4_mb_new_blocks_simple(ar, errp); } EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_new_blocks_simple_test); int mb_find_next_zero_bit_test(void *addr, int max, int start) { return mb_find_next_zero_bit(addr, max, start); } EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_zero_bit_test); int mb_find_next_bit_test(void *addr, int max, int start) { return mb_find_next_bit(addr, max, start); } EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_bit_test); void mb_clear_bit_test(int bit, void *addr) { mb_clear_bit(bit, addr); } EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bit_test); int mb_test_bit_test(int bit, void *addr) { return mb_test_bit(bit, addr); } EXPORT_SYMBOL_FOR_EXT4_TEST(mb_test_bit_test); int ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac, handle_t *handle) { return ext4_mb_mark_diskspace_used(ac, handle); } EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_diskspace_used_test); int mb_mark_used_test(struct ext4_buddy *e4b, struct ext4_free_extent *ex) { return mb_mark_used(e4b, ex); } EXPORT_SYMBOL_FOR_EXT4_TEST(mb_mark_used_test); void ext4_mb_generate_buddy_test(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group, struct ext4_group_info *grp) { ext4_mb_generate_buddy(sb, buddy, bitmap, group, grp); } EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_generate_buddy_test); int ext4_mb_load_buddy_test(struct super_block *sb, ext4_group_t group, struct ext4_buddy *e4b) { return ext4_mb_load_buddy(sb, group, e4b); } EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_load_buddy_test); void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b) { ext4_mb_unload_buddy(e4b); } EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_unload_buddy_test); void mb_free_blocks_test(struct inode *inode, struct ext4_buddy *e4b, int first, int count) { mb_free_blocks(inode, e4b, first, count); } EXPORT_SYMBOL_FOR_EXT4_TEST(mb_free_blocks_test); void ext4_free_blocks_simple_test(struct inode *inode, ext4_fsblk_t block, unsigned long count) { return ext4_free_blocks_simple(inode, block, count); } EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_blocks_simple_test); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_wait_block_bitmap); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_init); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_desc); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_count_free_clusters); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_info); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_group_clusters_set); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_release); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_read_block_bitmap_nowait); EXPORT_SYMBOL_FOR_EXT4_TEST(mb_set_bits); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_fc_init_inode); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_context); #endif |
| 14541 14542 12 1 4 6 1 1 6 2 3 3 3 6 1 2 3 3 4 1 1 2 2 2 4 4 4 4 1191 394 24 416 1990 1979 1086 216 415 416 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 | // SPDX-License-Identifier: GPL-2.0-or-later /* * xfrm_device.c - IPsec device offloading code. * * Copyright (c) 2015 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/errno.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/dst.h> #include <net/gso.h> #include <net/xfrm.h> #include <linux/notifier.h> #ifdef CONFIG_XFRM_OFFLOAD static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); skb_reset_mac_len(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header -= x->props.header_len; pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len); } static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); pskb_pull(skb, skb->mac_len + x->props.header_len - x->props.enc_hdr_len); } static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb, unsigned int hsize) { struct xfrm_offload *xo = xfrm_offload(skb); int phlen = 0; if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header = skb->network_header + hsize; skb_reset_mac_len(skb); if (x->sel.family != AF_INET6) { phlen = IPV4_BEET_PHMAXLEN; if (x->outer_mode.family == AF_INET6) phlen += sizeof(struct ipv6hdr) - sizeof(struct iphdr); } pskb_pull(skb, skb->mac_len + hsize + (x->props.header_len - phlen)); } /* Adjust pointers into the packet when IPsec is done at layer2 */ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) { switch (x->outer_mode.encap) { case XFRM_MODE_IPTFS: case XFRM_MODE_TUNNEL: if (x->outer_mode.family == AF_INET) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_tunnel_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_TRANSPORT: if (x->outer_mode.family == AF_INET) return __xfrm_transport_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_transport_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_BEET: if (x->outer_mode.family == AF_INET) return __xfrm_mode_beet_prep(x, skb, sizeof(struct iphdr)); if (x->outer_mode.family == AF_INET6) return __xfrm_mode_beet_prep(x, skb, sizeof(struct ipv6hdr)); break; case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: break; } } static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) { struct xfrm_offload *xo = xfrm_offload(skb); __u32 seq = xo->seq.low; seq += skb_shinfo(skb)->gso_segs; if (unlikely(seq < xo->seq.low)) return true; return false; } struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; unsigned long flags; struct xfrm_state *x; struct softnet_data *sd; struct sk_buff *skb2, *nskb, *pskb = NULL; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct net_device *dev = skb->dev; struct sec_path *sp; if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; if (xo->flags & XFRM_GRO || x->xso.dir == XFRM_DEV_OFFLOAD_IN) return skb; /* The packet was sent to HW IPsec packet offload engine, * but to wrong device. Drop the packet, so it won't skip * XFRM stack. */ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->xso.dev != dev) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); err = !skb_queue_empty(&sd->xfrm_backlog); local_irq_restore(flags); if (err) { *again = true; return skb; } if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ esp_features = esp_features & ~(NETIF_F_HW_ESP | NETIF_F_GSO_ESP); segs = skb_gso_segment(skb, esp_features); if (IS_ERR(segs)) { kfree_skb(skb); dev_core_stats_tx_dropped_inc(dev); return NULL; } else { consume_skb(skb); skb = segs; } } if (!skb->next) { esp_features |= skb->dev->gso_partial_features; xfrm_outer_mode_prep(x, skb); xo->flags |= XFRM_DEV_RESUME; err = x->type_offload->xmit(x, skb, esp_features); if (err) { if (err == -EINPROGRESS) return NULL; XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); kfree_skb(skb); return NULL; } skb_push(skb, skb->data - skb_mac_header(skb)); return skb; } skb_list_walk_safe(skb, skb2, nskb) { esp_features |= skb->dev->gso_partial_features; skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; xfrm_outer_mode_prep(x, skb2); err = x->type_offload->xmit(x, skb2, esp_features); if (!err) { skb2->next = nskb; } else if (err != -EINPROGRESS) { XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR); skb2->next = nskb; kfree_skb_list(skb2); return NULL; } else { if (skb == skb2) skb = nskb; else pskb->next = nskb; continue; } skb_push(skb2, skb2->data - skb_mac_header(skb2)); pskb = skb2; } return skb; } EXPORT_SYMBOL_GPL(validate_xmit_xfrm); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack) { int err; struct dst_entry *dst; struct net_device *dev; struct xfrm_dev_offload *xso = &x->xso; xfrm_address_t *saddr; xfrm_address_t *daddr; bool is_packet_offload; if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) { NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } if ((xuo->flags & XFRM_OFFLOAD_INBOUND && x->dir == XFRM_SA_DIR_OUT) || (!(xuo->flags & XFRM_OFFLOAD_INBOUND) && x->dir == XFRM_SA_DIR_IN)) { NL_SET_ERR_MSG(extack, "Mismatched SA and offload direction"); return -EINVAL; } if (xuo->flags & XFRM_OFFLOAD_INBOUND && x->if_id) { NL_SET_ERR_MSG(extack, "XFRM if_id is not supported in RX path"); return -EINVAL; } is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; /* We don't yet support TFC padding. */ if (x->tfcpad) { NL_SET_ERR_MSG(extack, "TFC padding can't be offloaded"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { struct xfrm_dst_lookup_params params; if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { saddr = &x->props.saddr; daddr = &x->id.daddr; } else { saddr = &x->id.daddr; daddr = &x->props.saddr; } memset(¶ms, 0, sizeof(params)); params.net = net; params.saddr = saddr; params.daddr = daddr; params.mark = xfrm_smark_get(0, x); dst = __xfrm_dst_lookup(x->props.family, ¶ms); if (IS_ERR(dst)) return (is_packet_offload) ? -EINVAL : 0; dev = dst->dev; dev_hold(dev); dst_release(dst); } if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) { xso->dev = NULL; dev_put(dev); return (is_packet_offload) ? -EINVAL : 0; } if (!is_packet_offload && x->props.flags & XFRM_STATE_ESN && !dev->xfrmdev_ops->xdo_dev_state_advance_esn) { NL_SET_ERR_MSG(extack, "Device doesn't support offload with ESN"); xso->dev = NULL; dev_put(dev); return -EINVAL; } if (!x->type_offload) { NL_SET_ERR_MSG(extack, "Type doesn't support offload"); dev_put(dev); return -EINVAL; } xso->dev = dev; netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); if (xuo->flags & XFRM_OFFLOAD_INBOUND) xso->dir = XFRM_DEV_OFFLOAD_IN; else xso->dir = XFRM_DEV_OFFLOAD_OUT; if (is_packet_offload) xso->type = XFRM_DEV_OFFLOAD_PACKET; else xso->type = XFRM_DEV_OFFLOAD_CRYPTO; err = dev->xfrmdev_ops->xdo_dev_state_add(dev, x, extack); if (err) { xso->dev = NULL; xso->dir = 0; netdev_put(dev, &xso->dev_tracker); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xfrm_unset_type_offload(x); /* User explicitly requested packet offload mode and configured * policy in addition to the XFRM state. So be civil to users, * and return an error instead of taking fallback path. */ if ((err != -EOPNOTSUPP && !is_packet_offload) || is_packet_offload) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state"); return err; } } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_state_add); int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, struct xfrm_user_offload *xuo, u8 dir, struct netlink_ext_ack *extack) { struct xfrm_dev_offload *xdo = &xp->xdo; struct net_device *dev; int err; if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) { /* We support only packet offload mode and it means * that user must set XFRM_OFFLOAD_PACKET bit. */ NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); return -EINVAL; } dev = dev_get_by_index(net, xuo->ifindex); if (!dev) return -EINVAL; if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) { xdo->dev = NULL; dev_put(dev); NL_SET_ERR_MSG(extack, "Policy offload is not supported"); return -EINVAL; } xdo->dev = dev; netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC); xdo->type = XFRM_DEV_OFFLOAD_PACKET; switch (dir) { case XFRM_POLICY_IN: xdo->dir = XFRM_DEV_OFFLOAD_IN; break; case XFRM_POLICY_OUT: xdo->dir = XFRM_DEV_OFFLOAD_OUT; break; case XFRM_POLICY_FWD: xdo->dir = XFRM_DEV_OFFLOAD_FWD; break; default: xdo->dev = NULL; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG(extack, "Unrecognized offload direction"); return -EINVAL; } err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack); if (err) { xdo->dev = NULL; xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; xdo->dir = 0; netdev_put(dev, &xdo->dev_tracker); NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this policy"); return err; } return 0; } EXPORT_SYMBOL_GPL(xfrm_dev_policy_add); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { int mtu; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; bool check_tunnel_size; if (!x->type_offload || (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; if ((!dev || dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) goto ok; } return false; ok: if (!dev) return true; check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; switch (skb_dst(skb)->ops->family) { case AF_INET: /* Check for IPv4 options */ if (ip_hdr(skb)->ihl != 5) return false; if (check_tunnel_size && xfrm4_tunnel_check_size(skb)) return false; break; case AF_INET6: /* Check for IPv6 extensions */ if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) return false; if (check_tunnel_size && xfrm6_tunnel_check_size(skb)) return false; break; default: break; } if (dev->xfrmdev_ops->xdo_dev_offload_ok) return dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x); return true; } EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok); void xfrm_dev_resume(struct sk_buff *skb) { struct net_device *dev = skb->dev; int ret = NETDEV_TX_BUSY; struct netdev_queue *txq; struct softnet_data *sd; unsigned long flags; rcu_read_lock(); txq = netdev_core_pick_tx(dev, skb, NULL); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); HARD_TX_UNLOCK(dev, txq); if (!dev_xmit_complete(ret)) { local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); skb_queue_tail(&sd->xfrm_backlog, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(xfrm_dev_resume); void xfrm_dev_backlog(struct softnet_data *sd) { struct sk_buff_head *xfrm_backlog = &sd->xfrm_backlog; struct sk_buff_head list; struct sk_buff *skb; if (skb_queue_empty(xfrm_backlog)) return; __skb_queue_head_init(&list); spin_lock(&xfrm_backlog->lock); skb_queue_splice_init(xfrm_backlog, &list); spin_unlock(&xfrm_backlog->lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); xfrm_dev_resume(skb); } } #endif static int xfrm_api_check(struct net_device *dev) { #ifdef CONFIG_XFRM_OFFLOAD if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) && !(dev->features & NETIF_F_HW_ESP)) return NOTIFY_BAD; if ((dev->features & NETIF_F_HW_ESP) && (!(dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_state_add && dev->xfrmdev_ops->xdo_dev_state_delete))) return NOTIFY_BAD; #else if (dev->features & (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM)) return NOTIFY_BAD; #endif return NOTIFY_DONE; } static int xfrm_dev_down(struct net_device *dev) { if (dev->features & NETIF_F_HW_ESP) { xfrm_dev_state_flush(dev_net(dev), dev, true); xfrm_dev_policy_flush(dev_net(dev), dev, true); } return NOTIFY_DONE; } static int xfrm_dev_unregister(struct net_device *dev) { xfrm_dev_state_flush(dev_net(dev), dev, true); xfrm_dev_policy_flush(dev_net(dev), dev, true); return NOTIFY_DONE; } static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_REGISTER: return xfrm_api_check(dev); case NETDEV_FEAT_CHANGE: return xfrm_api_check(dev); case NETDEV_DOWN: return xfrm_dev_down(dev); case NETDEV_UNREGISTER: return xfrm_dev_unregister(dev); } return NOTIFY_DONE; } static struct notifier_block xfrm_dev_notifier = { .notifier_call = xfrm_dev_event, }; void __init xfrm_dev_init(void) { register_netdevice_notifier(&xfrm_dev_notifier); } |
| 274 8128 5723 3529 3532 4978 51 773 77 77 738 6762 3722 3723 6095 409 3 3 2 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NS_COMMON_H #define _LINUX_NS_COMMON_H #include <linux/ns/ns_common_types.h> #include <linux/refcount.h> #include <linux/vfsdebug.h> #include <uapi/linux/sched.h> #include <uapi/linux/nsfs.h> bool is_current_namespace(struct ns_common *ns); int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum); void __ns_common_free(struct ns_common *ns); struct ns_common *__must_check ns_owner(struct ns_common *ns); static __always_inline bool is_ns_init_inum(const struct ns_common *ns) { VFS_WARN_ON_ONCE(ns->inum == 0); return unlikely(in_range(ns->inum, MNT_NS_INIT_INO, IPC_NS_INIT_INO - MNT_NS_INIT_INO + 1)); } static __always_inline bool is_ns_init_id(const struct ns_common *ns) { VFS_WARN_ON_ONCE(ns->ns_id == 0); return ns->ns_id <= NS_LAST_INIT_ID; } #define NS_COMMON_INIT(nsname) \ { \ .ns_type = ns_common_type(&nsname), \ .ns_id = ns_init_id(&nsname), \ .inum = ns_init_inum(&nsname), \ .ops = to_ns_operations(&nsname), \ .stashed = NULL, \ .__ns_ref = REFCOUNT_INIT(1), \ .__ns_ref_active = ATOMIC_INIT(1), \ .ns_unified_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_unified_node.ns_list_entry), \ .ns_tree_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_tree_node.ns_list_entry), \ .ns_owner_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_owner_node.ns_list_entry), \ .ns_owner_root.ns_list_head = LIST_HEAD_INIT(nsname.ns.ns_owner_root.ns_list_head), \ } #define ns_common_init(__ns) \ __ns_common_init(to_ns_common(__ns), \ ns_common_type(__ns), \ to_ns_operations(__ns), \ (((__ns) == ns_init_ns(__ns)) ? ns_init_inum(__ns) : 0)) #define ns_common_init_inum(__ns, __inum) \ __ns_common_init(to_ns_common(__ns), \ ns_common_type(__ns), \ to_ns_operations(__ns), \ __inum) #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) bool may_see_all_namespaces(void); static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) { return atomic_read(&ns->__ns_ref_active); } static __always_inline __must_check int __ns_ref_read(const struct ns_common *ns) { return refcount_read(&ns->__ns_ref); } static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns) { if (is_ns_init_id(ns)) { VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); return false; } if (refcount_dec_and_test(&ns->__ns_ref)) { VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); return true; } return false; } static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns) { if (is_ns_init_id(ns)) { VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); return true; } if (refcount_inc_not_zero(&ns->__ns_ref)) return true; VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); return false; } static __always_inline void __ns_ref_inc(struct ns_common *ns) { if (is_ns_init_id(ns)) { VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); return; } refcount_inc(&ns->__ns_ref); } static __always_inline __must_check bool __ns_ref_dec_and_lock(struct ns_common *ns, spinlock_t *ns_lock) { if (is_ns_init_id(ns)) { VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); return false; } return refcount_dec_and_lock(&ns->__ns_ref, ns_lock); } #define ns_ref_read(__ns) __ns_ref_read(to_ns_common((__ns))) #define ns_ref_inc(__ns) \ do { if (__ns) __ns_ref_inc(to_ns_common((__ns))); } while (0) #define ns_ref_get(__ns) \ ((__ns) ? __ns_ref_get(to_ns_common((__ns))) : false) #define ns_ref_put(__ns) \ ((__ns) ? __ns_ref_put(to_ns_common((__ns))) : false) #define ns_ref_put_and_lock(__ns, __ns_lock) \ ((__ns) ? __ns_ref_dec_and_lock(to_ns_common((__ns)), __ns_lock) : false) #define ns_ref_active_read(__ns) \ ((__ns) ? __ns_ref_active_read(to_ns_common(__ns)) : 0) void __ns_ref_active_put(struct ns_common *ns); #define ns_ref_active_put(__ns) \ do { if (__ns) __ns_ref_active_put(to_ns_common(__ns)); } while (0) static __always_inline struct ns_common *__must_check ns_get_unless_inactive(struct ns_common *ns) { if (!__ns_ref_active_read(ns)) { VFS_WARN_ON_ONCE(is_ns_init_id(ns)); return NULL; } if (!__ns_ref_get(ns)) return NULL; return ns; } void __ns_ref_active_get(struct ns_common *ns); #define ns_ref_active_get(__ns) \ do { if (__ns) __ns_ref_active_get(to_ns_common(__ns)); } while (0) #endif |
| 2 6632 18 69 2902 1243 1992 57 811 2032 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILELOCK_H #define _LINUX_FILELOCK_H #include <linux/fs.h> #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 struct file_lock; struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lease_manager_operations { bool (*lm_break)(struct file_lease *); int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); int (*lm_open_conflict)(struct file *, int); bool (*lm_breaker_timedout)(struct file_lease *fl); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* * struct file_lock has a union that some filesystems use to track * their own private info. The NFS side of things is defined here: */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock_core { struct file_lock_core *flc_blocker; /* The lock that is blocking us */ struct list_head flc_list; /* link into file_lock_context */ struct hlist_node flc_link; /* node in global lists */ struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t flc_owner; unsigned int flc_flags; unsigned char flc_type; pid_t flc_pid; int flc_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t flc_wait; struct file *flc_file; }; struct file_lock { struct file_lock_core c; loff_t fl_start; loff_t fl_end; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; struct { struct inode *inode; } ceph; } fl_u; } __randomize_layout; struct file_lease { struct file_lock_core c; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; #ifdef CONFIG_FILE_LOCKING int fcntl_getlk(struct file *, unsigned int, struct flock *); int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg); int fcntl_getdeleg(struct file *filp, struct delegation *deleg); static inline bool lock_is_unlock(struct file_lock *fl) { return fl->c.flc_type == F_UNLCK; } static inline bool lock_is_read(struct file_lock *fl) { return fl->c.flc_type == F_RDLCK; } static inline bool lock_is_write(struct file_lock *fl) { return fl->c.flc_type == F_WRLCK; } static inline void locks_wake_up_waiter(struct file_lock_core *flc) { wake_up(&flc->flc_wait); } static inline void locks_wake_up(struct file_lock *fl) { locks_wake_up_waiter(&fl->c); } static inline bool locks_can_async_lock(const struct file_operations *fops) { return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; } /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); void locks_remove_file(struct file *); void locks_release_private(struct file_lock *); void posix_test_lock(struct file *, struct file_lock *); int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); int locks_delete_block(struct file_lock *); int vfs_test_lock(struct file *, struct file_lock *); int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); #define LEASE_BREAK_LEASE BIT(0) // break leases and delegations #define LEASE_BREAK_DELEG BIT(1) // break delegations only #define LEASE_BREAK_LAYOUT BIT(2) // break layouts only #define LEASE_BREAK_NONBLOCK BIT(3) // non-blocking break #define LEASE_BREAK_OPEN_RDONLY BIT(4) // readonly open event int __break_lease(struct inode *inode, unsigned int flags); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); int vfs_setlease(struct file *, int, struct file_lease **, void **); int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); void lease_unregister_notifier(struct notifier_block *); struct files_struct; void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { /* * Paired with smp_store_release in locks_get_lock_context(). * * Ensures ->i_flctx will be visible if we spotted the flag. */ if (likely(!(smp_load_acquire(&inode->i_opflags) & IOP_FLCTX))) return NULL; return READ_ONCE(inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg) { return -EINVAL; } static inline int fcntl_getdeleg(struct file *filp, struct delegation *deleg) { return -EINVAL; } static inline bool lock_is_unlock(struct file_lock *fl) { return false; } static inline bool lock_is_read(struct file_lock *fl) { return false; } static inline bool lock_is_write(struct file_lock *fl) { return false; } static inline void locks_wake_up(struct file_lock *fl) { } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_init_lease(struct file_lease *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int flags) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } static inline int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ /* for walking lists of file_locks linked by fl_list */ #define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); } #ifdef CONFIG_FILE_LOCKING static inline unsigned int openmode_to_lease_flags(unsigned int mode) { unsigned int flags = 0; if ((mode & O_ACCMODE) == O_RDONLY) flags |= LEASE_BREAK_OPEN_RDONLY; if (mode & O_NONBLOCK) flags |= LEASE_BREAK_NONBLOCK; return flags; } static inline int break_lease(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = locks_inode_context(inode); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) return __break_lease(inode, LEASE_BREAK_LEASE | openmode_to_lease_flags(mode)); return 0; } static inline int break_deleg(struct inode *inode, unsigned int flags) { struct file_lock_context *flctx; /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ flctx = locks_inode_context(inode); if (!flctx) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) { flags |= LEASE_BREAK_DELEG; return __break_lease(inode, flags); } return 0; } struct delegated_inode { struct inode *di_inode; }; static inline bool is_delegated(struct delegated_inode *di) { return di->di_inode; } static inline int try_break_deleg(struct inode *inode, struct delegated_inode *di) { int ret; ret = break_deleg(inode, LEASE_BREAK_NONBLOCK); if (ret == -EWOULDBLOCK && di) { di->di_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct delegated_inode *di) { int ret; ret = break_deleg(di->di_inode, 0); iput(di->di_inode); di->di_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { struct file_lock_context *flctx; smp_mb(); flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_lease)) { unsigned int flags = LEASE_BREAK_LAYOUT; if (!wait) flags |= LEASE_BREAK_NONBLOCK; return __break_lease(inode, flags); } return 0; } #else /* !CONFIG_FILE_LOCKING */ struct delegated_inode { }; static inline bool is_delegated(struct delegated_inode *di) { return false; } static inline int break_lease(struct inode *inode, bool wait) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int flags) { return 0; } static inline int try_break_deleg(struct inode *inode, struct delegated_inode *delegated_inode) { return 0; } static inline int break_deleg_wait(struct delegated_inode *delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ #endif /* _LINUX_FILELOCK_H */ |
| 38 26 35 35 5 9 9 2 7 7 3 30 1 24 6 3 1 8 2 8 2 10 10 33 25 9 9 8 8 5 3 3 2 2 2 1 1 33 33 18 3 16 1 13 18 1 6 10 4 4 1 13 5 3 3 4 2 2 4 4 4 4 39 12 13 16 29 2 29 13 22 7 22 1 12 10 2 10 10 10 9 1 10 10 10 3 4 3 1 2 1 2 2 2 4 1 1 1 1 1 5 1 21 1 2 18 18 34 34 6 6 3 3 3 3 1 5 5 10 2 2 2 2 25 12 12 26 32 31 1 31 30 2 31 38 2 28 9 2 2 26 26 2 3 3 2 28 2 1 31 1 26 4 27 3 23 7 22 6 2 3 5 20 4 1 2 16 2 18 12 6 6 6 26 5 2 2 2 2 8 2 1 2 3 3 2 5 1 1 2 2 2 1 1 1 1 1 1 2 3 3 2 5 1 4 2 2 1 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Network block device - make block devices work over TCP * * Note that you can not swap over this thing, yet. Seems to work but * deadlocks sometimes - you can not swap over TCP in general. * * Copyright 1997-2000, 2008 Pavel Machek <pavel@ucw.cz> * Parts copyright 2001 Steven Whitehouse <steve@chygwyn.com> * * (part of code stolen from loop.c) */ #define pr_fmt(fmt) "nbd: " fmt #include <linux/major.h> #include <linux/blkdev.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/fs.h> #include <linux/bio.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/ioctl.h> #include <linux/mutex.h> #include <linux/compiler.h> #include <linux/completion.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/slab.h> #include <net/sock.h> #include <linux/net.h> #include <linux/kthread.h> #include <linux/types.h> #include <linux/debugfs.h> #include <linux/blk-mq.h> #include <linux/uaccess.h> #include <asm/types.h> #include <linux/nbd.h> #include <linux/nbd-netlink.h> #include <net/genetlink.h> #define CREATE_TRACE_POINTS #include <trace/events/nbd.h> static DEFINE_IDR(nbd_index_idr); static DEFINE_MUTEX(nbd_index_mutex); static struct workqueue_struct *nbd_del_wq; static int nbd_total_devices = 0; struct nbd_sock { struct socket *sock; struct mutex tx_lock; struct request *pending; int sent; bool dead; int fallback_index; int cookie; struct work_struct work; }; struct recv_thread_args { struct work_struct work; struct nbd_device *nbd; struct nbd_sock *nsock; int index; }; struct link_dead_args { struct work_struct work; int index; }; #define NBD_RT_TIMEDOUT 0 #define NBD_RT_DISCONNECT_REQUESTED 1 #define NBD_RT_DISCONNECTED 2 #define NBD_RT_HAS_PID_FILE 3 #define NBD_RT_HAS_CONFIG_REF 4 #define NBD_RT_BOUND 5 #define NBD_RT_DISCONNECT_ON_CLOSE 6 #define NBD_RT_HAS_BACKEND_FILE 7 #define NBD_DESTROY_ON_DISCONNECT 0 #define NBD_DISCONNECT_REQUESTED 1 struct nbd_config { u32 flags; unsigned long runtime_flags; u64 dead_conn_timeout; struct nbd_sock **socks; int num_connections; atomic_t live_connections; wait_queue_head_t conn_wait; atomic_t recv_threads; wait_queue_head_t recv_wq; unsigned int blksize_bits; loff_t bytesize; #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbg_dir; #endif }; static inline unsigned int nbd_blksize(struct nbd_config *config) { return 1u << config->blksize_bits; } struct nbd_device { struct blk_mq_tag_set tag_set; int index; refcount_t config_refs; refcount_t refs; struct nbd_config *config; struct mutex config_lock; struct gendisk *disk; struct workqueue_struct *recv_workq; struct work_struct remove_work; struct list_head list; struct task_struct *task_setup; unsigned long flags; pid_t pid; /* pid of nbd-client, if attached */ char *backend; }; #define NBD_CMD_REQUEUED 1 /* * This flag will be set if nbd_queue_rq() succeed, and will be checked and * cleared in completion. Both setting and clearing of the flag are protected * by cmd->lock. */ #define NBD_CMD_INFLIGHT 2 /* Just part of request header or data payload is sent successfully */ #define NBD_CMD_PARTIAL_SEND 3 struct nbd_cmd { struct nbd_device *nbd; struct mutex lock; int index; int cookie; int retries; blk_status_t status; unsigned long flags; u32 cmd_cookie; }; #if IS_ENABLED(CONFIG_DEBUG_FS) static struct dentry *nbd_dbg_dir; #endif #define nbd_name(nbd) ((nbd)->disk->disk_name) #define NBD_DEF_BLKSIZE_BITS 10 static unsigned int nbds_max = 16; static int max_part = 16; static int part_shift; static int nbd_dev_dbg_init(struct nbd_device *nbd); static void nbd_dev_dbg_close(struct nbd_device *nbd); static void nbd_config_put(struct nbd_device *nbd); static void nbd_connect_reply(struct genl_info *info, int index); static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info); static void nbd_dead_link_work(struct work_struct *work); static void nbd_disconnect_and_put(struct nbd_device *nbd); static inline struct device *nbd_to_dev(struct nbd_device *nbd) { return disk_to_dev(nbd->disk); } static void nbd_requeue_cmd(struct nbd_cmd *cmd) { struct request *req = blk_mq_rq_from_pdu(cmd); lockdep_assert_held(&cmd->lock); /* * Clear INFLIGHT flag so that this cmd won't be completed in * normal completion path * * INFLIGHT flag will be set when the cmd is queued to nbd next * time. */ __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) blk_mq_requeue_request(req, true); } #define NBD_COOKIE_BITS 32 static u64 nbd_cmd_handle(struct nbd_cmd *cmd) { struct request *req = blk_mq_rq_from_pdu(cmd); u32 tag = blk_mq_unique_tag(req); u64 cookie = cmd->cmd_cookie; return (cookie << NBD_COOKIE_BITS) | tag; } static u32 nbd_handle_to_tag(u64 handle) { return (u32)handle; } static u32 nbd_handle_to_cookie(u64 handle) { return (u32)(handle >> NBD_COOKIE_BITS); } static const char *nbdcmd_to_ascii(int cmd) { switch (cmd) { case NBD_CMD_READ: return "read"; case NBD_CMD_WRITE: return "write"; case NBD_CMD_DISC: return "disconnect"; case NBD_CMD_FLUSH: return "flush"; case NBD_CMD_TRIM: return "trim/discard"; } return "invalid"; } static ssize_t pid_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); struct nbd_device *nbd = disk->private_data; return sprintf(buf, "%d\n", nbd->pid); } static const struct device_attribute pid_attr = { .attr = { .name = "pid", .mode = 0444}, .show = pid_show, }; static ssize_t backend_show(struct device *dev, struct device_attribute *attr, char *buf) { struct gendisk *disk = dev_to_disk(dev); struct nbd_device *nbd = disk->private_data; return sprintf(buf, "%s\n", nbd->backend ?: ""); } static const struct device_attribute backend_attr = { .attr = { .name = "backend", .mode = 0444}, .show = backend_show, }; static void nbd_dev_remove(struct nbd_device *nbd) { struct gendisk *disk = nbd->disk; del_gendisk(disk); blk_mq_free_tag_set(&nbd->tag_set); /* * Remove from idr after del_gendisk() completes, so if the same ID is * reused, the following add_disk() will succeed. */ mutex_lock(&nbd_index_mutex); idr_remove(&nbd_index_idr, nbd->index); mutex_unlock(&nbd_index_mutex); destroy_workqueue(nbd->recv_workq); put_disk(disk); } static void nbd_dev_remove_work(struct work_struct *work) { nbd_dev_remove(container_of(work, struct nbd_device, remove_work)); } static void nbd_put(struct nbd_device *nbd) { if (!refcount_dec_and_test(&nbd->refs)) return; /* Call del_gendisk() asynchrounously to prevent deadlock */ if (test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) queue_work(nbd_del_wq, &nbd->remove_work); else nbd_dev_remove(nbd); } static int nbd_disconnected(struct nbd_config *config) { return test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags) || test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags); } static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock, int notify) { if (!nsock->dead && notify && !nbd_disconnected(nbd->config)) { struct link_dead_args *args; args = kmalloc_obj(struct link_dead_args, GFP_NOIO); if (args) { INIT_WORK(&args->work, nbd_dead_link_work); args->index = nbd->index; queue_work(system_percpu_wq, &args->work); } } if (!nsock->dead) { kernel_sock_shutdown(nsock->sock, SHUT_RDWR); if (atomic_dec_return(&nbd->config->live_connections) == 0) { if (test_and_clear_bit(NBD_RT_DISCONNECT_REQUESTED, &nbd->config->runtime_flags)) { set_bit(NBD_RT_DISCONNECTED, &nbd->config->runtime_flags); dev_info(nbd_to_dev(nbd), "Disconnected due to user request.\n"); } } } nsock->dead = true; nsock->pending = NULL; nsock->sent = 0; } static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, loff_t blksize) { struct queue_limits lim; int error; if (!blksize) blksize = 1u << NBD_DEF_BLKSIZE_BITS; if (blk_validate_block_size(blksize)) return -EINVAL; if (bytesize < 0) return -EINVAL; nbd->config->bytesize = bytesize; nbd->config->blksize_bits = __ffs(blksize); if (!nbd->pid) return 0; lim = queue_limits_start_update(nbd->disk->queue); if (nbd->config->flags & NBD_FLAG_SEND_TRIM) lim.max_hw_discard_sectors = UINT_MAX >> SECTOR_SHIFT; else lim.max_hw_discard_sectors = 0; if (!(nbd->config->flags & NBD_FLAG_SEND_FLUSH)) { lim.features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); } else if (nbd->config->flags & NBD_FLAG_SEND_FUA) { lim.features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; } else { lim.features |= BLK_FEAT_WRITE_CACHE; lim.features &= ~BLK_FEAT_FUA; } if (nbd->config->flags & NBD_FLAG_ROTATIONAL) lim.features |= BLK_FEAT_ROTATIONAL; if (nbd->config->flags & NBD_FLAG_SEND_WRITE_ZEROES) lim.max_write_zeroes_sectors = UINT_MAX >> SECTOR_SHIFT; lim.logical_block_size = blksize; lim.physical_block_size = blksize; error = queue_limits_commit_update_frozen(nbd->disk->queue, &lim); if (error) return error; if (max_part) set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); if (!set_capacity_and_notify(nbd->disk, bytesize >> 9)) kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); return 0; } static void nbd_complete_rq(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", req, cmd->status ? "failed" : "done"); blk_mq_end_request(req, cmd->status); } /* * Forcibly shutdown the socket causing all listeners to error */ static void sock_shutdown(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int i; if (config->num_connections == 0) return; if (test_and_set_bit(NBD_RT_DISCONNECTED, &config->runtime_flags)) return; for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; mutex_lock(&nsock->tx_lock); nbd_mark_nsock_dead(nbd, nsock, 0); mutex_unlock(&nsock->tx_lock); } dev_warn(disk_to_dev(nbd->disk), "shutting down sockets\n"); } static u32 req_to_nbd_cmd_type(struct request *req) { switch (req_op(req)) { case REQ_OP_DISCARD: return NBD_CMD_TRIM; case REQ_OP_FLUSH: return NBD_CMD_FLUSH; case REQ_OP_WRITE: return NBD_CMD_WRITE; case REQ_OP_READ: return NBD_CMD_READ; case REQ_OP_WRITE_ZEROES: return NBD_CMD_WRITE_ZEROES; default: return U32_MAX; } } static struct nbd_config *nbd_get_config_unlocked(struct nbd_device *nbd) { if (refcount_inc_not_zero(&nbd->config_refs)) { /* * Add smp_mb__after_atomic to ensure that reading nbd->config_refs * and reading nbd->config is ordered. The pair is the barrier in * nbd_alloc_and_init_config(), avoid nbd->config_refs is set * before nbd->config. */ smp_mb__after_atomic(); return nbd->config; } return NULL; } static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); struct nbd_device *nbd = cmd->nbd; struct nbd_config *config; if (!mutex_trylock(&cmd->lock)) return BLK_EH_RESET_TIMER; /* partial send is handled in nbd_sock's work function */ if (test_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags)) { mutex_unlock(&cmd->lock); return BLK_EH_RESET_TIMER; } if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { mutex_unlock(&cmd->lock); return BLK_EH_DONE; } config = nbd_get_config_unlocked(nbd); if (!config) { cmd->status = BLK_STS_TIMEOUT; __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); mutex_unlock(&cmd->lock); goto done; } if (config->num_connections > 1 || (config->num_connections == 1 && nbd->tag_set.timeout)) { dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out, retrying (%d/%d alive)\n", atomic_read(&config->live_connections), config->num_connections); /* * Hooray we have more connections, requeue this IO, the submit * path will put it on a real connection. Or if only one * connection is configured, the submit path will wait util * a new connection is reconfigured or util dead timeout. */ if (config->socks) { if (cmd->index < config->num_connections) { struct nbd_sock *nsock = config->socks[cmd->index]; mutex_lock(&nsock->tx_lock); /* We can have multiple outstanding requests, so * we don't want to mark the nsock dead if we've * already reconnected with a new socket, so * only mark it dead if its the same socket we * were sent out on. */ if (cmd->cookie == nsock->cookie) nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } nbd_requeue_cmd(cmd); mutex_unlock(&cmd->lock); nbd_config_put(nbd); return BLK_EH_DONE; } } if (!nbd->tag_set.timeout) { /* * Userspace sets timeout=0 to disable socket disconnection, * so just warn and reset the timer. */ struct nbd_sock *nsock = config->socks[cmd->index]; cmd->retries++; dev_info(nbd_to_dev(nbd), "Possible stuck request %p: control (%s@%llu,%uB). Runtime %u seconds\n", req, nbdcmd_to_ascii(req_to_nbd_cmd_type(req)), (unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req), (req->timeout / HZ) * cmd->retries); mutex_lock(&nsock->tx_lock); if (cmd->cookie != nsock->cookie) { nbd_requeue_cmd(cmd); mutex_unlock(&nsock->tx_lock); mutex_unlock(&cmd->lock); nbd_config_put(nbd); return BLK_EH_DONE; } mutex_unlock(&nsock->tx_lock); mutex_unlock(&cmd->lock); nbd_config_put(nbd); return BLK_EH_RESET_TIMER; } dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out\n"); set_bit(NBD_RT_TIMEDOUT, &config->runtime_flags); cmd->status = BLK_STS_IOERR; __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); mutex_unlock(&cmd->lock); sock_shutdown(nbd); nbd_config_put(nbd); done: blk_mq_complete_request(req); return BLK_EH_DONE; } static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, struct iov_iter *iter, int msg_flags, int *sent) { int result; struct msghdr msg = {} ; unsigned int noreclaim_flag; if (unlikely(!sock)) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Attempted %s on closed socket in sock_xmit\n", (send ? "send" : "recv")); return -EINVAL; } msg.msg_iter = *iter; noreclaim_flag = memalloc_noreclaim_save(); scoped_with_kernel_creds() { do { sock->sk->sk_allocation = GFP_NOIO | __GFP_MEMALLOC; sock->sk->sk_use_task_frag = false; msg.msg_flags = msg_flags | MSG_NOSIGNAL; if (send) result = sock_sendmsg(sock, &msg); else result = sock_recvmsg(sock, &msg, msg.msg_flags); if (result <= 0) { if (result == 0) result = -EPIPE; /* short read */ break; } if (sent) *sent += result; } while (msg_data_left(&msg)); } memalloc_noreclaim_restore(noreclaim_flag); return result; } /* * Send or receive packet. Return a positive value on success and * negtive value on failure, and never return 0. */ static int sock_xmit(struct nbd_device *nbd, int index, int send, struct iov_iter *iter, int msg_flags, int *sent) { struct nbd_config *config = nbd->config; struct socket *sock = config->socks[index]->sock; return __sock_xmit(nbd, sock, send, iter, msg_flags, sent); } /* * Different settings for sk->sk_sndtimeo can result in different return values * if there is a signal pending when we enter sendmsg, because reasons? */ static inline int was_interrupted(int result) { return result == -ERESTARTSYS || result == -EINTR; } /* * We've already sent header or part of data payload, have no choice but * to set pending and schedule it in work. * * And we have to return BLK_STS_OK to block core, otherwise this same * request may be re-dispatched with different tag, but our header has * been sent out with old tag, and this way does confuse reply handling. */ static void nbd_sched_pending_work(struct nbd_device *nbd, struct nbd_sock *nsock, struct nbd_cmd *cmd, int sent) { struct request *req = blk_mq_rq_from_pdu(cmd); /* pending work should be scheduled only once */ WARN_ON_ONCE(test_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags)); nsock->pending = req; nsock->sent = sent; set_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags); refcount_inc(&nbd->config_refs); schedule_work(&nsock->work); } /* * Returns BLK_STS_RESOURCE if the caller should retry after a delay. * Returns BLK_STS_IOERR if sending failed. */ static blk_status_t nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_config *config = nbd->config; struct nbd_sock *nsock = config->socks[index]; int result; struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)}; struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)}; struct iov_iter from; struct bio *bio; u64 handle; u32 type; u32 nbd_cmd_flags = 0; int sent = nsock->sent, skip = 0; lockdep_assert_held(&cmd->lock); lockdep_assert_held(&nsock->tx_lock); iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request)); type = req_to_nbd_cmd_type(req); if (type == U32_MAX) return BLK_STS_IOERR; if (rq_data_dir(req) == WRITE && (config->flags & NBD_FLAG_READ_ONLY)) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Write on read-only\n"); return BLK_STS_IOERR; } if (req->cmd_flags & REQ_FUA) nbd_cmd_flags |= NBD_CMD_FLAG_FUA; if ((req->cmd_flags & REQ_NOUNMAP) && (type == NBD_CMD_WRITE_ZEROES)) nbd_cmd_flags |= NBD_CMD_FLAG_NO_HOLE; /* We did a partial send previously, and we at least sent the whole * request struct, so just go and send the rest of the pages in the * request. */ if (sent) { if (sent >= sizeof(request)) { skip = sent - sizeof(request); /* initialize handle for tracing purposes */ handle = nbd_cmd_handle(cmd); goto send_pages; } iov_iter_advance(&from, sent); } else { cmd->cmd_cookie++; } cmd->index = index; cmd->cookie = nsock->cookie; cmd->retries = 0; request.type = htonl(type | nbd_cmd_flags); if (type != NBD_CMD_FLUSH) { request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(blk_rq_bytes(req)); } handle = nbd_cmd_handle(cmd); request.cookie = cpu_to_be64(handle); trace_nbd_send_request(&request, nbd->index, blk_mq_rq_from_pdu(cmd)); dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", req, nbdcmd_to_ascii(type), (unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req)); result = sock_xmit(nbd, index, 1, &from, (type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent); trace_nbd_header_sent(req, handle); if (result < 0) { if (was_interrupted(result)) { /* If we haven't sent anything we can just return BUSY, * however if we have sent something we need to make * sure we only allow this req to be sent until we are * completely done. */ if (sent) { nbd_sched_pending_work(nbd, nsock, cmd, sent); return BLK_STS_OK; } set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), "Send control failed (result %d)\n", result); goto requeue; } send_pages: if (type != NBD_CMD_WRITE) goto out; bio = req->bio; while (bio) { struct bio *next = bio->bi_next; struct bvec_iter iter; struct bio_vec bvec; bio_for_each_segment(bvec, bio, iter) { bool is_last = !next && bio_iter_last(bvec, iter); int flags = is_last ? 0 : MSG_MORE; dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n", req, bvec.bv_len); iov_iter_bvec(&from, ITER_SOURCE, &bvec, 1, bvec.bv_len); if (skip) { if (skip >= iov_iter_count(&from)) { skip -= iov_iter_count(&from); continue; } iov_iter_advance(&from, skip); skip = 0; } result = sock_xmit(nbd, index, 1, &from, flags, &sent); if (result < 0) { if (was_interrupted(result)) { nbd_sched_pending_work(nbd, nsock, cmd, sent); return BLK_STS_OK; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", result); goto requeue; } /* * The completion might already have come in, * so break for the last one instead of letting * the iterator do it. This prevents use-after-free * of the bio. */ if (is_last) break; } bio = next; } out: trace_nbd_payload_sent(req, handle); nsock->pending = NULL; nsock->sent = 0; __set_bit(NBD_CMD_INFLIGHT, &cmd->flags); return BLK_STS_OK; requeue: /* * Can't requeue in case we are dealing with partial send * * We must run from pending work function. * */ if (test_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags)) return BLK_STS_OK; /* retry on a different socket */ dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); nbd_requeue_cmd(cmd); return BLK_STS_OK; } /* handle partial sending */ static void nbd_pending_cmd_work(struct work_struct *work) { struct nbd_sock *nsock = container_of(work, struct nbd_sock, work); struct request *req = nsock->pending; struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); struct nbd_device *nbd = cmd->nbd; unsigned long deadline = READ_ONCE(req->deadline); unsigned int wait_ms = 2; mutex_lock(&cmd->lock); WARN_ON_ONCE(test_bit(NBD_CMD_REQUEUED, &cmd->flags)); if (WARN_ON_ONCE(!test_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags))) goto out; mutex_lock(&nsock->tx_lock); while (true) { nbd_send_cmd(nbd, cmd, cmd->index); if (!nsock->pending) break; /* don't bother timeout handler for partial sending */ if (READ_ONCE(jiffies) + msecs_to_jiffies(wait_ms) >= deadline) { cmd->status = BLK_STS_IOERR; blk_mq_complete_request(req); break; } msleep(wait_ms); wait_ms *= 2; } mutex_unlock(&nsock->tx_lock); clear_bit(NBD_CMD_PARTIAL_SEND, &cmd->flags); out: mutex_unlock(&cmd->lock); nbd_config_put(nbd); } static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock, struct nbd_reply *reply) { struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)}; struct iov_iter to; int result; reply->magic = 0; iov_iter_kvec(&to, ITER_DEST, &iov, 1, sizeof(*reply)); result = __sock_xmit(nbd, sock, 0, &to, MSG_WAITALL, NULL); if (result < 0) { if (!nbd_disconnected(nbd->config)) dev_err(disk_to_dev(nbd->disk), "Receive control failed (result %d)\n", result); return result; } if (ntohl(reply->magic) != NBD_REPLY_MAGIC) { dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n", (unsigned long)ntohl(reply->magic)); return -EPROTO; } return 0; } /* NULL returned = something went wrong, inform userspace */ static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index, struct nbd_reply *reply) { int result; struct nbd_cmd *cmd; struct request *req = NULL; u64 handle; u16 hwq; u32 tag; int ret = 0; handle = be64_to_cpu(reply->cookie); tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq], blk_mq_unique_tag_to_tag(tag)); if (!req || !blk_mq_request_started(req)) { dev_err(disk_to_dev(nbd->disk), "Unexpected reply (%d) %p\n", tag, req); return ERR_PTR(-ENOENT); } trace_nbd_header_received(req, handle); cmd = blk_mq_rq_to_pdu(req); mutex_lock(&cmd->lock); if (!test_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)", tag, cmd->status, cmd->flags); ret = -ENOENT; goto out; } if (cmd->index != index) { dev_err(disk_to_dev(nbd->disk), "Unexpected reply %d from different sock %d (expected %d)", tag, index, cmd->index); ret = -ENOENT; goto out; } if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); ret = -ENOENT; goto out; } if (cmd->status != BLK_STS_OK) { dev_err(disk_to_dev(nbd->disk), "Command already handled %p\n", req); ret = -ENOENT; goto out; } if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) { dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n", req); ret = -ENOENT; goto out; } if (ntohl(reply->error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply->error)); cmd->status = BLK_STS_IOERR; goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req); if (rq_data_dir(req) != WRITE) { struct req_iterator iter; struct bio_vec bvec; struct iov_iter to; rq_for_each_segment(bvec, req, iter) { iov_iter_bvec(&to, ITER_DEST, &bvec, 1, bvec.bv_len); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); if (result < 0) { dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n", result); /* * If we've disconnected, we need to make sure we * complete this request, otherwise error out * and let the timeout stuff handle resubmitting * this request onto another connection. */ if (nbd_disconnected(nbd->config)) { cmd->status = BLK_STS_IOERR; goto out; } ret = -EIO; goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n", req, bvec.bv_len); } } out: trace_nbd_payload_received(req, handle); mutex_unlock(&cmd->lock); return ret ? ERR_PTR(ret) : cmd; } static void recv_work(struct work_struct *work) { struct recv_thread_args *args = container_of(work, struct recv_thread_args, work); struct nbd_device *nbd = args->nbd; struct nbd_config *config = nbd->config; struct request_queue *q = nbd->disk->queue; struct nbd_sock *nsock = args->nsock; struct nbd_cmd *cmd; struct request *rq; while (1) { struct nbd_reply reply; if (nbd_read_reply(nbd, nsock->sock, &reply)) break; /* * Grab .q_usage_counter so request pool won't go away, then no * request use-after-free is possible during nbd_handle_reply(). * If queue is frozen, there won't be any inflight requests, we * needn't to handle the incoming garbage message. */ if (!percpu_ref_tryget(&q->q_usage_counter)) { dev_err(disk_to_dev(nbd->disk), "%s: no io inflight\n", __func__); break; } cmd = nbd_handle_reply(nbd, args->index, &reply); if (IS_ERR(cmd)) { percpu_ref_put(&q->q_usage_counter); break; } rq = blk_mq_rq_from_pdu(cmd); if (likely(!blk_should_fake_timeout(rq->q))) { bool complete; mutex_lock(&cmd->lock); complete = __test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); mutex_unlock(&cmd->lock); if (complete) blk_mq_complete_request(rq); } percpu_ref_put(&q->q_usage_counter); } mutex_lock(&nsock->tx_lock); nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); atomic_dec(&config->recv_threads); wake_up(&config->recv_wq); nbd_config_put(nbd); kfree(args); } static bool nbd_clear_req(struct request *req, void *data) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); /* don't abort one completed request */ if (blk_mq_request_completed(req)) return true; mutex_lock(&cmd->lock); if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { mutex_unlock(&cmd->lock); return true; } cmd->status = BLK_STS_IOERR; mutex_unlock(&cmd->lock); blk_mq_complete_request(req); return true; } static void nbd_clear_que(struct nbd_device *nbd) { blk_mq_quiesce_queue(nbd->disk->queue); blk_mq_tagset_busy_iter(&nbd->tag_set, nbd_clear_req, NULL); blk_mq_unquiesce_queue(nbd->disk->queue); dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n"); } static int find_fallback(struct nbd_device *nbd, int index) { struct nbd_config *config = nbd->config; int new_index = -1; struct nbd_sock *nsock = config->socks[index]; int fallback = nsock->fallback_index; if (test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags)) return new_index; if (config->num_connections <= 1) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Dead connection, failed to find a fallback\n"); return new_index; } if (fallback >= 0 && fallback < config->num_connections && !config->socks[fallback]->dead) return fallback; if (nsock->fallback_index < 0 || nsock->fallback_index >= config->num_connections || config->socks[nsock->fallback_index]->dead) { int i; for (i = 0; i < config->num_connections; i++) { if (i == index) continue; if (!config->socks[i]->dead) { new_index = i; break; } } nsock->fallback_index = new_index; if (new_index < 0) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Dead connection, failed to find a fallback\n"); return new_index; } } new_index = nsock->fallback_index; return new_index; } static int wait_for_reconnect(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; if (!config->dead_conn_timeout) return 0; if (!wait_event_timeout(config->conn_wait, test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags) || atomic_read(&config->live_connections) > 0, config->dead_conn_timeout)) return 0; return !test_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); } static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_device *nbd = cmd->nbd; struct nbd_config *config; struct nbd_sock *nsock; blk_status_t ret; lockdep_assert_held(&cmd->lock); config = nbd_get_config_unlocked(nbd); if (!config) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Socks array is empty\n"); return BLK_STS_IOERR; } if (index >= config->num_connections) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Attempted send on invalid socket\n"); nbd_config_put(nbd); return BLK_STS_IOERR; } cmd->status = BLK_STS_OK; again: nsock = config->socks[index]; mutex_lock(&nsock->tx_lock); if (nsock->dead) { int old_index = index; index = find_fallback(nbd, index); mutex_unlock(&nsock->tx_lock); if (index < 0) { if (wait_for_reconnect(nbd)) { index = old_index; goto again; } /* All the sockets should already be down at this point, * we just want to make sure that DISCONNECTED is set so * any requests that come in that were queue'ed waiting * for the reconnect timer don't trigger the timer again * and instead just error out. */ sock_shutdown(nbd); nbd_config_put(nbd); return BLK_STS_IOERR; } goto again; } /* Handle the case that we have a pending request that was partially * transmitted that _has_ to be serviced first. We need to call requeue * here so that it gets put _after_ the request that is already on the * dispatch list. */ blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { nbd_requeue_cmd(cmd); ret = BLK_STS_OK; goto out; } ret = nbd_send_cmd(nbd, cmd, index); out: mutex_unlock(&nsock->tx_lock); nbd_config_put(nbd); return ret; } static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); blk_status_t ret; /* * Since we look at the bio's to send the request over the network we * need to make sure the completion work doesn't mark this request done * before we are done doing our send. This keeps us from dereferencing * freed data if we have particularly fast completions (ie we get the * completion before we exit sock_xmit on the last bvec) or in the case * that the server is misbehaving (or there was an error) before we're * done sending everything over the wire. */ mutex_lock(&cmd->lock); clear_bit(NBD_CMD_REQUEUED, &cmd->flags); /* We can be called directly from the user space process, which means we * could possibly have signals pending so our sendmsg will fail. In * this case we need to return that we are busy, otherwise error out as * appropriate. */ ret = nbd_handle_cmd(cmd, hctx->queue_num); mutex_unlock(&cmd->lock); return ret; } static struct socket *nbd_get_socket(struct nbd_device *nbd, unsigned long fd, int *err) { struct socket *sock; *err = 0; sock = sockfd_lookup(fd, err); if (!sock) return NULL; if (!sk_is_tcp(sock->sk) && !sk_is_stream_unix(sock->sk)) { dev_err(disk_to_dev(nbd->disk), "Unsupported socket: should be TCP or UNIX.\n"); *err = -EINVAL; sockfd_put(sock); return NULL; } if (sock->ops->shutdown == sock_no_shutdown) { dev_err(disk_to_dev(nbd->disk), "Unsupported socket: shutdown callout must be supported.\n"); *err = -EINVAL; sockfd_put(sock); return NULL; } return sock; } static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, bool netlink) { struct nbd_config *config = nbd->config; struct socket *sock; struct nbd_sock **socks; struct nbd_sock *nsock; unsigned int memflags; int err; /* Arg will be cast to int, check it to avoid overflow */ if (arg > INT_MAX) return -EINVAL; sock = nbd_get_socket(nbd, arg, &err); if (!sock) return err; /* * We need to make sure we don't get any errant requests while we're * reallocating the ->socks array. */ memflags = blk_mq_freeze_queue(nbd->disk->queue); if (!netlink && !nbd->task_setup && !test_bit(NBD_RT_BOUND, &config->runtime_flags)) nbd->task_setup = current; if (!netlink && (nbd->task_setup != current || test_bit(NBD_RT_BOUND, &config->runtime_flags))) { dev_err(disk_to_dev(nbd->disk), "Device being setup by another task"); err = -EBUSY; goto put_socket; } nsock = kzalloc_obj(*nsock); if (!nsock) { err = -ENOMEM; goto put_socket; } socks = krealloc(config->socks, (config->num_connections + 1) * sizeof(struct nbd_sock *), GFP_KERNEL); if (!socks) { kfree(nsock); err = -ENOMEM; goto put_socket; } config->socks = socks; nsock->fallback_index = -1; nsock->dead = false; mutex_init(&nsock->tx_lock); nsock->sock = sock; nsock->pending = NULL; nsock->sent = 0; nsock->cookie = 0; INIT_WORK(&nsock->work, nbd_pending_cmd_work); socks[config->num_connections++] = nsock; atomic_inc(&config->live_connections); blk_mq_unfreeze_queue(nbd->disk->queue, memflags); return 0; put_socket: blk_mq_unfreeze_queue(nbd->disk->queue, memflags); sockfd_put(sock); return err; } static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) { struct nbd_config *config = nbd->config; struct socket *sock, *old; struct recv_thread_args *args; int i; int err; sock = nbd_get_socket(nbd, arg, &err); if (!sock) return err; args = kzalloc_obj(*args); if (!args) { sockfd_put(sock); return -ENOMEM; } for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; if (!nsock->dead) continue; mutex_lock(&nsock->tx_lock); if (!nsock->dead) { mutex_unlock(&nsock->tx_lock); continue; } sk_set_memalloc(sock->sk); if (nbd->tag_set.timeout) sock->sk->sk_sndtimeo = nbd->tag_set.timeout; atomic_inc(&config->recv_threads); refcount_inc(&nbd->config_refs); old = nsock->sock; nsock->fallback_index = -1; nsock->sock = sock; nsock->dead = false; INIT_WORK(&args->work, recv_work); args->index = i; args->nbd = nbd; args->nsock = nsock; nsock->cookie++; mutex_unlock(&nsock->tx_lock); sockfd_put(old); clear_bit(NBD_RT_DISCONNECTED, &config->runtime_flags); /* We take the tx_mutex in an error path in the recv_work, so we * need to queue_work outside of the tx_mutex. */ queue_work(nbd->recv_workq, &args->work); atomic_inc(&config->live_connections); wake_up(&config->conn_wait); return 0; } sockfd_put(sock); kfree(args); return -ENOSPC; } static void nbd_bdev_reset(struct nbd_device *nbd) { if (disk_openers(nbd->disk) > 1) return; set_capacity(nbd->disk, 0); } static void nbd_parse_flags(struct nbd_device *nbd) { if (nbd->config->flags & NBD_FLAG_READ_ONLY) set_disk_ro(nbd->disk, true); else set_disk_ro(nbd->disk, false); } static void send_disconnects(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; struct nbd_request request = { .magic = htonl(NBD_REQUEST_MAGIC), .type = htonl(NBD_CMD_DISC), }; struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)}; struct iov_iter from; int i, ret; for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; iov_iter_kvec(&from, ITER_SOURCE, &iov, 1, sizeof(request)); mutex_lock(&nsock->tx_lock); ret = sock_xmit(nbd, i, 1, &from, 0, NULL); if (ret < 0) dev_err(disk_to_dev(nbd->disk), "Send disconnect failed %d\n", ret); mutex_unlock(&nsock->tx_lock); } } static int nbd_disconnect(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n"); set_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags); set_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags); send_disconnects(nbd); return 0; } static void nbd_clear_sock(struct nbd_device *nbd) { sock_shutdown(nbd); nbd_clear_que(nbd); nbd->task_setup = NULL; } static void nbd_config_put(struct nbd_device *nbd) { if (refcount_dec_and_mutex_lock(&nbd->config_refs, &nbd->config_lock)) { struct nbd_config *config = nbd->config; nbd_dev_dbg_close(nbd); invalidate_disk(nbd->disk); if (nbd->config->bytesize) kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); if (test_and_clear_bit(NBD_RT_HAS_PID_FILE, &config->runtime_flags)) device_remove_file(disk_to_dev(nbd->disk), &pid_attr); nbd->pid = 0; if (test_and_clear_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags)) { device_remove_file(disk_to_dev(nbd->disk), &backend_attr); kfree(nbd->backend); nbd->backend = NULL; } nbd_clear_sock(nbd); if (config->num_connections) { int i; for (i = 0; i < config->num_connections; i++) { sockfd_put(config->socks[i]->sock); kfree(config->socks[i]); } kfree(config->socks); } kfree(nbd->config); nbd->config = NULL; nbd->tag_set.timeout = 0; mutex_unlock(&nbd->config_lock); nbd_put(nbd); module_put(THIS_MODULE); } } static int nbd_start_device(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int num_connections = config->num_connections; int error = 0, i; if (nbd->pid) return -EBUSY; if (!config->socks) return -EINVAL; if (num_connections > 1 && !(config->flags & NBD_FLAG_CAN_MULTI_CONN)) { dev_err(disk_to_dev(nbd->disk), "server does not support multiple connections per device.\n"); return -EINVAL; } retry: mutex_unlock(&nbd->config_lock); blk_mq_update_nr_hw_queues(&nbd->tag_set, num_connections); mutex_lock(&nbd->config_lock); /* if another code path updated nr_hw_queues, retry until succeed */ if (num_connections != config->num_connections) { num_connections = config->num_connections; goto retry; } nbd->pid = task_pid_nr(current); nbd_parse_flags(nbd); error = device_create_file(disk_to_dev(nbd->disk), &pid_attr); if (error) { dev_err(disk_to_dev(nbd->disk), "device_create_file failed for pid!\n"); return error; } set_bit(NBD_RT_HAS_PID_FILE, &config->runtime_flags); nbd_dev_dbg_init(nbd); for (i = 0; i < num_connections; i++) { struct recv_thread_args *args; args = kzalloc_obj(*args); if (!args) { sock_shutdown(nbd); /* * If num_connections is m (2 < m), * and NO.1 ~ NO.n(1 < n < m) kzallocs are successful. * But NO.(n + 1) failed. We still have n recv threads. * So, add flush_workqueue here to prevent recv threads * dropping the last config_refs and trying to destroy * the workqueue from inside the workqueue. */ if (i) flush_workqueue(nbd->recv_workq); return -ENOMEM; } sk_set_memalloc(config->socks[i]->sock->sk); if (nbd->tag_set.timeout) config->socks[i]->sock->sk->sk_sndtimeo = nbd->tag_set.timeout; atomic_inc(&config->recv_threads); refcount_inc(&nbd->config_refs); INIT_WORK(&args->work, recv_work); args->nbd = nbd; args->nsock = config->socks[i]; args->index = i; queue_work(nbd->recv_workq, &args->work); } return nbd_set_size(nbd, config->bytesize, nbd_blksize(config)); } static int nbd_start_device_ioctl(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; int ret; ret = nbd_start_device(nbd); if (ret) return ret; if (max_part) set_bit(GD_NEED_PART_SCAN, &nbd->disk->state); mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); if (ret) { sock_shutdown(nbd); nbd_clear_que(nbd); } flush_workqueue(nbd->recv_workq); mutex_lock(&nbd->config_lock); nbd_bdev_reset(nbd); /* user requested, ignore socket errors */ if (test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags)) ret = 0; if (test_bit(NBD_RT_TIMEDOUT, &config->runtime_flags)) ret = -ETIMEDOUT; return ret; } static void nbd_clear_sock_ioctl(struct nbd_device *nbd) { nbd_clear_sock(nbd); disk_force_media_change(nbd->disk); nbd_bdev_reset(nbd); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); } static void nbd_set_cmd_timeout(struct nbd_device *nbd, u64 timeout) { nbd->tag_set.timeout = timeout * HZ; if (timeout) blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ); else blk_queue_rq_timeout(nbd->disk->queue, 30 * HZ); } /* Must be called with config_lock held */ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, unsigned int cmd, unsigned long arg) { struct nbd_config *config = nbd->config; loff_t bytesize; switch (cmd) { case NBD_DISCONNECT: return nbd_disconnect(nbd); case NBD_CLEAR_SOCK: nbd_clear_sock_ioctl(nbd); return 0; case NBD_SET_SOCK: return nbd_add_socket(nbd, arg, false); case NBD_SET_BLKSIZE: return nbd_set_size(nbd, config->bytesize, arg); case NBD_SET_SIZE: return nbd_set_size(nbd, arg, nbd_blksize(config)); case NBD_SET_SIZE_BLOCKS: if (check_shl_overflow(arg, config->blksize_bits, &bytesize)) return -EINVAL; return nbd_set_size(nbd, bytesize, nbd_blksize(config)); case NBD_SET_TIMEOUT: nbd_set_cmd_timeout(nbd, arg); return 0; case NBD_SET_FLAGS: config->flags = arg; return 0; case NBD_DO_IT: return nbd_start_device_ioctl(nbd); case NBD_CLEAR_QUE: /* * This is for compatibility only. The queue is always cleared * by NBD_DO_IT or NBD_CLEAR_SOCK. */ return 0; case NBD_PRINT_DEBUG: /* * For compatibility only, we no longer keep a list of * outstanding requests. */ return 0; } return -ENOTTY; } static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct nbd_device *nbd = bdev->bd_disk->private_data; struct nbd_config *config = nbd->config; int error = -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* The block layer will pass back some non-nbd ioctls in case we have * special handling for them, but we don't so just return an error. */ if (_IOC_TYPE(cmd) != 0xab) return -EINVAL; mutex_lock(&nbd->config_lock); /* Don't allow ioctl operations on a nbd device that was created with * netlink, unless it's DISCONNECT or CLEAR_SOCK, which are fine. */ if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) || (cmd == NBD_DISCONNECT || cmd == NBD_CLEAR_SOCK)) error = __nbd_ioctl(bdev, nbd, cmd, arg); else dev_err(nbd_to_dev(nbd), "Cannot use ioctl interface on a netlink controlled device.\n"); mutex_unlock(&nbd->config_lock); return error; } static int nbd_alloc_and_init_config(struct nbd_device *nbd) { struct nbd_config *config; if (WARN_ON(nbd->config)) return -EINVAL; if (!try_module_get(THIS_MODULE)) return -ENODEV; config = kzalloc_obj(struct nbd_config, GFP_NOFS); if (!config) { module_put(THIS_MODULE); return -ENOMEM; } atomic_set(&config->recv_threads, 0); init_waitqueue_head(&config->recv_wq); init_waitqueue_head(&config->conn_wait); config->blksize_bits = NBD_DEF_BLKSIZE_BITS; atomic_set(&config->live_connections, 0); nbd->config = config; /* * Order refcount_set(&nbd->config_refs, 1) and nbd->config assignment, * its pair is the barrier in nbd_get_config_unlocked(). * So nbd_get_config_unlocked() won't see nbd->config as null after * refcount_inc_not_zero() succeed. */ smp_mb__before_atomic(); refcount_set(&nbd->config_refs, 1); return 0; } static int nbd_open(struct gendisk *disk, blk_mode_t mode) { struct nbd_device *nbd; struct nbd_config *config; int ret = 0; mutex_lock(&nbd_index_mutex); nbd = disk->private_data; if (!nbd) { ret = -ENXIO; goto out; } if (!refcount_inc_not_zero(&nbd->refs)) { ret = -ENXIO; goto out; } config = nbd_get_config_unlocked(nbd); if (!config) { mutex_lock(&nbd->config_lock); if (refcount_inc_not_zero(&nbd->config_refs)) { mutex_unlock(&nbd->config_lock); goto out; } ret = nbd_alloc_and_init_config(nbd); if (ret) { mutex_unlock(&nbd->config_lock); goto out; } refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); if (max_part) set_bit(GD_NEED_PART_SCAN, &disk->state); } else if (nbd_disconnected(config)) { if (max_part) set_bit(GD_NEED_PART_SCAN, &disk->state); } out: mutex_unlock(&nbd_index_mutex); return ret; } static void nbd_release(struct gendisk *disk) { struct nbd_device *nbd = disk->private_data; if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && disk_openers(disk) == 0) nbd_disconnect_and_put(nbd); nbd_config_put(nbd); nbd_put(nbd); } static void nbd_free_disk(struct gendisk *disk) { struct nbd_device *nbd = disk->private_data; kfree(nbd); } static const struct block_device_operations nbd_fops = { .owner = THIS_MODULE, .open = nbd_open, .release = nbd_release, .ioctl = nbd_ioctl, .compat_ioctl = nbd_ioctl, .free_disk = nbd_free_disk, }; #if IS_ENABLED(CONFIG_DEBUG_FS) static int nbd_dbg_tasks_show(struct seq_file *s, void *unused) { struct nbd_device *nbd = s->private; if (nbd->pid) seq_printf(s, "recv: %d\n", nbd->pid); return 0; } DEFINE_SHOW_ATTRIBUTE(nbd_dbg_tasks); static int nbd_dbg_flags_show(struct seq_file *s, void *unused) { struct nbd_device *nbd = s->private; u32 flags = nbd->config->flags; seq_printf(s, "Hex: 0x%08x\n\n", flags); seq_puts(s, "Known flags:\n"); if (flags & NBD_FLAG_HAS_FLAGS) seq_puts(s, "NBD_FLAG_HAS_FLAGS\n"); if (flags & NBD_FLAG_READ_ONLY) seq_puts(s, "NBD_FLAG_READ_ONLY\n"); if (flags & NBD_FLAG_SEND_FLUSH) seq_puts(s, "NBD_FLAG_SEND_FLUSH\n"); if (flags & NBD_FLAG_SEND_FUA) seq_puts(s, "NBD_FLAG_SEND_FUA\n"); if (flags & NBD_FLAG_SEND_TRIM) seq_puts(s, "NBD_FLAG_SEND_TRIM\n"); if (flags & NBD_FLAG_SEND_WRITE_ZEROES) seq_puts(s, "NBD_FLAG_SEND_WRITE_ZEROES\n"); if (flags & NBD_FLAG_ROTATIONAL) seq_puts(s, "NBD_FLAG_ROTATIONAL\n"); return 0; } DEFINE_SHOW_ATTRIBUTE(nbd_dbg_flags); static int nbd_dev_dbg_init(struct nbd_device *nbd) { struct dentry *dir; struct nbd_config *config = nbd->config; if (!nbd_dbg_dir) return -EIO; dir = debugfs_create_dir(nbd_name(nbd), nbd_dbg_dir); if (IS_ERR(dir)) { dev_err(nbd_to_dev(nbd), "Failed to create debugfs dir for '%s'\n", nbd_name(nbd)); return -EIO; } config->dbg_dir = dir; debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_fops); debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize); debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout); debugfs_create_u32("blocksize_bits", 0444, dir, &config->blksize_bits); debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_fops); return 0; } static void nbd_dev_dbg_close(struct nbd_device *nbd) { debugfs_remove_recursive(nbd->config->dbg_dir); } static int nbd_dbg_init(void) { struct dentry *dbg_dir; dbg_dir = debugfs_create_dir("nbd", NULL); if (IS_ERR(dbg_dir)) return -EIO; nbd_dbg_dir = dbg_dir; return 0; } static void nbd_dbg_close(void) { debugfs_remove_recursive(nbd_dbg_dir); } #else /* IS_ENABLED(CONFIG_DEBUG_FS) */ static int nbd_dev_dbg_init(struct nbd_device *nbd) { return 0; } static void nbd_dev_dbg_close(struct nbd_device *nbd) { } static int nbd_dbg_init(void) { return 0; } static void nbd_dbg_close(void) { } #endif static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, unsigned int numa_node) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq); cmd->nbd = set->driver_data; cmd->flags = 0; mutex_init(&cmd->lock); return 0; } static const struct blk_mq_ops nbd_mq_ops = { .queue_rq = nbd_queue_rq, .complete = nbd_complete_rq, .init_request = nbd_init_request, .timeout = nbd_xmit_timeout, }; static struct nbd_device *nbd_dev_add(int index, unsigned int refs) { struct queue_limits lim = { .max_hw_sectors = 65536, .io_opt = 256 << SECTOR_SHIFT, .max_segments = USHRT_MAX, .max_segment_size = UINT_MAX, }; struct nbd_device *nbd; struct gendisk *disk; int err = -ENOMEM; nbd = kzalloc_obj(struct nbd_device); if (!nbd) goto out; nbd->tag_set.ops = &nbd_mq_ops; nbd->tag_set.nr_hw_queues = 1; nbd->tag_set.queue_depth = 128; nbd->tag_set.numa_node = NUMA_NO_NODE; nbd->tag_set.cmd_size = sizeof(struct nbd_cmd); nbd->tag_set.flags = BLK_MQ_F_BLOCKING; nbd->tag_set.driver_data = nbd; INIT_WORK(&nbd->remove_work, nbd_dev_remove_work); nbd->backend = NULL; err = blk_mq_alloc_tag_set(&nbd->tag_set); if (err) goto out_free_nbd; mutex_lock(&nbd_index_mutex); if (index >= 0) { err = idr_alloc(&nbd_index_idr, nbd, index, index + 1, GFP_KERNEL); if (err == -ENOSPC) err = -EEXIST; } else { err = idr_alloc(&nbd_index_idr, nbd, 0, (MINORMASK >> part_shift) + 1, GFP_KERNEL); if (err >= 0) index = err; } nbd->index = index; mutex_unlock(&nbd_index_mutex); if (err < 0) goto out_free_tags; disk = blk_mq_alloc_disk(&nbd->tag_set, &lim, NULL); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_free_idr; } nbd->disk = disk; nbd->recv_workq = alloc_workqueue("nbd%d-recv", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 0, nbd->index); if (!nbd->recv_workq) { dev_err(disk_to_dev(nbd->disk), "Could not allocate knbd recv work queue.\n"); err = -ENOMEM; goto out_err_disk; } mutex_init(&nbd->config_lock); refcount_set(&nbd->config_refs, 0); /* * Start out with a zero references to keep other threads from using * this device until it is fully initialized. */ refcount_set(&nbd->refs, 0); INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; disk->first_minor = index << part_shift; disk->minors = 1 << part_shift; disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); err = add_disk(disk); if (err) goto out_free_work; /* * Now publish the device. */ refcount_set(&nbd->refs, refs); nbd_total_devices++; return nbd; out_free_work: destroy_workqueue(nbd->recv_workq); out_err_disk: put_disk(disk); out_free_idr: mutex_lock(&nbd_index_mutex); idr_remove(&nbd_index_idr, index); mutex_unlock(&nbd_index_mutex); out_free_tags: blk_mq_free_tag_set(&nbd->tag_set); out_free_nbd: kfree(nbd); out: return ERR_PTR(err); } static struct nbd_device *nbd_find_get_unused(void) { struct nbd_device *nbd; int id; lockdep_assert_held(&nbd_index_mutex); idr_for_each_entry(&nbd_index_idr, nbd, id) { if (refcount_read(&nbd->config_refs) || test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) continue; if (refcount_inc_not_zero(&nbd->refs)) return nbd; } return NULL; } /* Netlink interface. */ static const struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = { [NBD_ATTR_INDEX] = { .type = NLA_U32 }, [NBD_ATTR_SIZE_BYTES] = { .type = NLA_U64 }, [NBD_ATTR_BLOCK_SIZE_BYTES] = { .type = NLA_U64 }, [NBD_ATTR_TIMEOUT] = { .type = NLA_U64 }, [NBD_ATTR_SERVER_FLAGS] = { .type = NLA_U64 }, [NBD_ATTR_CLIENT_FLAGS] = { .type = NLA_U64 }, [NBD_ATTR_SOCKETS] = { .type = NLA_NESTED}, [NBD_ATTR_DEAD_CONN_TIMEOUT] = { .type = NLA_U64 }, [NBD_ATTR_DEVICE_LIST] = { .type = NLA_NESTED}, [NBD_ATTR_BACKEND_IDENTIFIER] = { .type = NLA_STRING}, }; static const struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = { [NBD_SOCK_FD] = { .type = NLA_U32 }, }; /* We don't use this right now since we don't parse the incoming list, but we * still want it here so userspace knows what to expect. */ static const struct nla_policy __attribute__((unused)) nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = { [NBD_DEVICE_INDEX] = { .type = NLA_U32 }, [NBD_DEVICE_CONNECTED] = { .type = NLA_U8 }, }; static int nbd_genl_size_set(struct genl_info *info, struct nbd_device *nbd) { struct nbd_config *config = nbd->config; u64 bsize = nbd_blksize(config); u64 bytes = config->bytesize; if (info->attrs[NBD_ATTR_SIZE_BYTES]) bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]); if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) bsize = nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]); if (bytes != config->bytesize || bsize != nbd_blksize(config)) return nbd_set_size(nbd, bytes, bsize); return 0; } static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) { struct nbd_device *nbd; struct nbd_config *config; int index = -1; int ret; bool put_dev = false; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; if (info->attrs[NBD_ATTR_INDEX]) { index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); /* * Too big first_minor can cause duplicate creation of * sysfs files/links, since index << part_shift might overflow, or * MKDEV() expect that the max bits of first_minor is 20. */ if (index < 0 || index > MINORMASK >> part_shift) { pr_err("illegal input index %d\n", index); return -EINVAL; } } if (GENL_REQ_ATTR_CHECK(info, NBD_ATTR_SOCKETS)) { pr_err("must specify at least one socket\n"); return -EINVAL; } if (GENL_REQ_ATTR_CHECK(info, NBD_ATTR_SIZE_BYTES)) { pr_err("must specify a size in bytes for the device\n"); return -EINVAL; } again: mutex_lock(&nbd_index_mutex); if (index == -1) { nbd = nbd_find_get_unused(); } else { nbd = idr_find(&nbd_index_idr, index); if (nbd) { if ((test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags) && test_bit(NBD_DISCONNECT_REQUESTED, &nbd->flags)) || !refcount_inc_not_zero(&nbd->refs)) { mutex_unlock(&nbd_index_mutex); pr_err("device at index %d is going down\n", index); return -EINVAL; } } } mutex_unlock(&nbd_index_mutex); if (!nbd) { nbd = nbd_dev_add(index, 2); if (IS_ERR(nbd)) { pr_err("failed to add new device\n"); return PTR_ERR(nbd); } } mutex_lock(&nbd->config_lock); if (refcount_read(&nbd->config_refs)) { mutex_unlock(&nbd->config_lock); nbd_put(nbd); if (index == -1) goto again; pr_err("nbd%d already in use\n", index); return -EBUSY; } ret = nbd_alloc_and_init_config(nbd); if (ret) { mutex_unlock(&nbd->config_lock); nbd_put(nbd); pr_err("couldn't allocate config\n"); return ret; } config = nbd->config; set_bit(NBD_RT_BOUND, &config->runtime_flags); ret = nbd_genl_size_set(info, nbd); if (ret) goto out; if (info->attrs[NBD_ATTR_TIMEOUT]) nbd_set_cmd_timeout(nbd, nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT])); if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) { config->dead_conn_timeout = nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]); config->dead_conn_timeout *= HZ; } if (info->attrs[NBD_ATTR_SERVER_FLAGS]) config->flags = nla_get_u64(info->attrs[NBD_ATTR_SERVER_FLAGS]); if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) { u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]); if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) { /* * We have 1 ref to keep the device around, and then 1 * ref for our current operation here, which will be * inherited by the config. If we already have * DESTROY_ON_DISCONNECT set then we know we don't have * that extra ref already held so we don't need the * put_dev. */ if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) put_dev = true; } else { if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) refcount_inc(&nbd->refs); } if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { set_bit(NBD_RT_DISCONNECT_ON_CLOSE, &config->runtime_flags); } } if (info->attrs[NBD_ATTR_SOCKETS]) { struct nlattr *attr; int rem, fd; nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS], rem) { struct nlattr *socks[NBD_SOCK_MAX+1]; if (nla_type(attr) != NBD_SOCK_ITEM) { pr_err("socks must be embedded in a SOCK_ITEM attr\n"); ret = -EINVAL; goto out; } ret = nla_parse_nested_deprecated(socks, NBD_SOCK_MAX, attr, nbd_sock_policy, info->extack); if (ret != 0) { pr_err("error processing sock list\n"); ret = -EINVAL; goto out; } if (!socks[NBD_SOCK_FD]) continue; fd = (int)nla_get_u32(socks[NBD_SOCK_FD]); ret = nbd_add_socket(nbd, fd, true); if (ret) goto out; } } if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) { nbd->backend = nla_strdup(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER], GFP_KERNEL); if (!nbd->backend) { ret = -ENOMEM; goto out; } } ret = device_create_file(disk_to_dev(nbd->disk), &backend_attr); if (ret) { dev_err(disk_to_dev(nbd->disk), "device_create_file failed for backend!\n"); goto out; } set_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags); ret = nbd_start_device(nbd); out: if (!ret) { set_bit(NBD_RT_HAS_CONFIG_REF, &config->runtime_flags); refcount_inc(&nbd->config_refs); nbd_connect_reply(info, nbd->index); } mutex_unlock(&nbd->config_lock); nbd_config_put(nbd); if (put_dev) nbd_put(nbd); return ret; } static void nbd_disconnect_and_put(struct nbd_device *nbd) { mutex_lock(&nbd->config_lock); nbd_disconnect(nbd); sock_shutdown(nbd); wake_up(&nbd->config->conn_wait); /* * Make sure recv thread has finished, we can safely call nbd_clear_que() * to cancel the inflight I/Os. */ flush_workqueue(nbd->recv_workq); nbd_clear_que(nbd); nbd->task_setup = NULL; clear_bit(NBD_RT_BOUND, &nbd->config->runtime_flags); mutex_unlock(&nbd->config_lock); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); } static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info) { struct nbd_device *nbd; int index; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; if (GENL_REQ_ATTR_CHECK(info, NBD_ATTR_INDEX)) { pr_err("must specify an index to disconnect\n"); return -EINVAL; } index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); mutex_lock(&nbd_index_mutex); nbd = idr_find(&nbd_index_idr, index); if (!nbd) { mutex_unlock(&nbd_index_mutex); pr_err("couldn't find device at index %d\n", index); return -EINVAL; } if (!refcount_inc_not_zero(&nbd->refs)) { mutex_unlock(&nbd_index_mutex); pr_err("device at index %d is going down\n", index); return -EINVAL; } mutex_unlock(&nbd_index_mutex); if (!refcount_inc_not_zero(&nbd->config_refs)) goto put_nbd; nbd_disconnect_and_put(nbd); nbd_config_put(nbd); put_nbd: nbd_put(nbd); return 0; } static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) { struct nbd_device *nbd = NULL; struct nbd_config *config; int index; int ret = 0; bool put_dev = false; if (!netlink_capable(skb, CAP_SYS_ADMIN)) return -EPERM; if (GENL_REQ_ATTR_CHECK(info, NBD_ATTR_INDEX)) { pr_err("must specify a device to reconfigure\n"); return -EINVAL; } index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); mutex_lock(&nbd_index_mutex); nbd = idr_find(&nbd_index_idr, index); if (!nbd) { mutex_unlock(&nbd_index_mutex); pr_err("couldn't find a device at index %d\n", index); return -EINVAL; } if (nbd->backend) { if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) { if (nla_strcmp(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER], nbd->backend)) { mutex_unlock(&nbd_index_mutex); dev_err(nbd_to_dev(nbd), "backend image doesn't match with %s\n", nbd->backend); return -EINVAL; } } else { mutex_unlock(&nbd_index_mutex); dev_err(nbd_to_dev(nbd), "must specify backend\n"); return -EINVAL; } } if (!refcount_inc_not_zero(&nbd->refs)) { mutex_unlock(&nbd_index_mutex); pr_err("device at index %d is going down\n", index); return -EINVAL; } mutex_unlock(&nbd_index_mutex); config = nbd_get_config_unlocked(nbd); if (!config) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); nbd_put(nbd); return -EINVAL; } mutex_lock(&nbd->config_lock); if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) || !nbd->pid) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); ret = -EINVAL; goto out; } ret = nbd_genl_size_set(info, nbd); if (ret) goto out; if (info->attrs[NBD_ATTR_TIMEOUT]) nbd_set_cmd_timeout(nbd, nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT])); if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) { config->dead_conn_timeout = nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]); config->dead_conn_timeout *= HZ; } if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) { u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]); if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) { if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) put_dev = true; } else { if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags)) refcount_inc(&nbd->refs); } if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { set_bit(NBD_RT_DISCONNECT_ON_CLOSE, &config->runtime_flags); } else { clear_bit(NBD_RT_DISCONNECT_ON_CLOSE, &config->runtime_flags); } } if (info->attrs[NBD_ATTR_SOCKETS]) { struct nlattr *attr; int rem, fd; nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS], rem) { struct nlattr *socks[NBD_SOCK_MAX+1]; if (nla_type(attr) != NBD_SOCK_ITEM) { pr_err("socks must be embedded in a SOCK_ITEM attr\n"); ret = -EINVAL; goto out; } ret = nla_parse_nested_deprecated(socks, NBD_SOCK_MAX, attr, nbd_sock_policy, info->extack); if (ret != 0) { pr_err("error processing sock list\n"); ret = -EINVAL; goto out; } if (!socks[NBD_SOCK_FD]) continue; fd = (int)nla_get_u32(socks[NBD_SOCK_FD]); ret = nbd_reconnect_socket(nbd, fd); if (ret) { if (ret == -ENOSPC) ret = 0; goto out; } dev_info(nbd_to_dev(nbd), "reconnected socket\n"); } } out: mutex_unlock(&nbd->config_lock); nbd_config_put(nbd); nbd_put(nbd); if (put_dev) nbd_put(nbd); return ret; } static const struct genl_small_ops nbd_connect_genl_ops[] = { { .cmd = NBD_CMD_CONNECT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nbd_genl_connect, }, { .cmd = NBD_CMD_DISCONNECT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nbd_genl_disconnect, }, { .cmd = NBD_CMD_RECONFIGURE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nbd_genl_reconfigure, }, { .cmd = NBD_CMD_STATUS, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nbd_genl_status, }, }; static const struct genl_multicast_group nbd_mcast_grps[] = { { .name = NBD_GENL_MCAST_GROUP_NAME, }, }; static struct genl_family nbd_genl_family __ro_after_init = { .hdrsize = 0, .name = NBD_GENL_FAMILY_NAME, .version = NBD_GENL_VERSION, .module = THIS_MODULE, .small_ops = nbd_connect_genl_ops, .n_small_ops = ARRAY_SIZE(nbd_connect_genl_ops), .resv_start_op = NBD_CMD_STATUS + 1, .maxattr = NBD_ATTR_MAX, .netnsok = 1, .policy = nbd_attr_policy, .mcgrps = nbd_mcast_grps, .n_mcgrps = ARRAY_SIZE(nbd_mcast_grps), }; MODULE_ALIAS_GENL_FAMILY(NBD_GENL_FAMILY_NAME); static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply) { struct nlattr *dev_opt; u8 connected = 0; int ret; /* This is a little racey, but for status it's ok. The * reason we don't take a ref here is because we can't * take a ref in the index == -1 case as we would need * to put under the nbd_index_mutex, which could * deadlock if we are configured to remove ourselves * once we're disconnected. */ if (refcount_read(&nbd->config_refs)) connected = 1; dev_opt = nla_nest_start_noflag(reply, NBD_DEVICE_ITEM); if (!dev_opt) return -EMSGSIZE; ret = nla_put_u32(reply, NBD_DEVICE_INDEX, nbd->index); if (ret) return -EMSGSIZE; ret = nla_put_u8(reply, NBD_DEVICE_CONNECTED, connected); if (ret) return -EMSGSIZE; nla_nest_end(reply, dev_opt); return 0; } static int status_cb(int id, void *ptr, void *data) { struct nbd_device *nbd = ptr; return populate_nbd_status(nbd, (struct sk_buff *)data); } static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) { struct nlattr *dev_list; struct sk_buff *reply; void *reply_head; size_t msg_size; int index = -1; int ret = -ENOMEM; if (info->attrs[NBD_ATTR_INDEX]) index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]); mutex_lock(&nbd_index_mutex); msg_size = nla_total_size(nla_attr_size(sizeof(u32)) + nla_attr_size(sizeof(u8))); msg_size *= (index == -1) ? nbd_total_devices : 1; reply = genlmsg_new(msg_size, GFP_KERNEL); if (!reply) goto out; reply_head = genlmsg_put_reply(reply, info, &nbd_genl_family, 0, NBD_CMD_STATUS); if (!reply_head) { nlmsg_free(reply); goto out; } dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); if (!dev_list) { nlmsg_free(reply); ret = -EMSGSIZE; goto out; } if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { nlmsg_free(reply); goto out; } } else { struct nbd_device *nbd; nbd = idr_find(&nbd_index_idr, index); if (nbd) { ret = populate_nbd_status(nbd, reply); if (ret) { nlmsg_free(reply); goto out; } } } nla_nest_end(reply, dev_list); genlmsg_end(reply, reply_head); ret = genlmsg_reply(reply, info); out: mutex_unlock(&nbd_index_mutex); return ret; } static void nbd_connect_reply(struct genl_info *info, int index) { struct sk_buff *skb; void *msg_head; int ret; skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL); if (!skb) return; msg_head = genlmsg_put_reply(skb, info, &nbd_genl_family, 0, NBD_CMD_CONNECT); if (!msg_head) { nlmsg_free(skb); return; } ret = nla_put_u32(skb, NBD_ATTR_INDEX, index); if (ret) { nlmsg_free(skb); return; } genlmsg_end(skb, msg_head); genlmsg_reply(skb, info); } static void nbd_mcast_index(int index) { struct sk_buff *skb; void *msg_head; int ret; skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL); if (!skb) return; msg_head = genlmsg_put(skb, 0, 0, &nbd_genl_family, 0, NBD_CMD_LINK_DEAD); if (!msg_head) { nlmsg_free(skb); return; } ret = nla_put_u32(skb, NBD_ATTR_INDEX, index); if (ret) { nlmsg_free(skb); return; } genlmsg_end(skb, msg_head); genlmsg_multicast(&nbd_genl_family, skb, 0, 0, GFP_KERNEL); } static void nbd_dead_link_work(struct work_struct *work) { struct link_dead_args *args = container_of(work, struct link_dead_args, work); nbd_mcast_index(args->index); kfree(args); } static int __init nbd_init(void) { int i; BUILD_BUG_ON(sizeof(struct nbd_request) != 28); if (max_part < 0) { pr_err("max_part must be >= 0\n"); return -EINVAL; } part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); /* * Adjust max_part according to part_shift as it is exported * to user space so that user can know the max number of * partition kernel should be able to manage. * * Note that -1 is required because partition 0 is reserved * for the whole disk. */ max_part = (1UL << part_shift) - 1; } if ((1UL << part_shift) > DISK_MAX_PARTS) return -EINVAL; if (nbds_max > 1UL << (MINORBITS - part_shift)) return -EINVAL; if (register_blkdev(NBD_MAJOR, "nbd")) return -EIO; nbd_del_wq = alloc_workqueue("nbd-del", WQ_UNBOUND, 0); if (!nbd_del_wq) { unregister_blkdev(NBD_MAJOR, "nbd"); return -ENOMEM; } if (genl_register_family(&nbd_genl_family)) { destroy_workqueue(nbd_del_wq); unregister_blkdev(NBD_MAJOR, "nbd"); return -EINVAL; } nbd_dbg_init(); for (i = 0; i < nbds_max; i++) nbd_dev_add(i, 1); return 0; } static int nbd_exit_cb(int id, void *ptr, void *data) { struct list_head *list = (struct list_head *)data; struct nbd_device *nbd = ptr; /* Skip nbd that is being removed asynchronously */ if (refcount_read(&nbd->refs)) list_add_tail(&nbd->list, list); return 0; } static void __exit nbd_cleanup(void) { struct nbd_device *nbd; LIST_HEAD(del_list); /* * Unregister netlink interface prior to waiting * for the completion of netlink commands. */ genl_unregister_family(&nbd_genl_family); nbd_dbg_close(); mutex_lock(&nbd_index_mutex); idr_for_each(&nbd_index_idr, &nbd_exit_cb, &del_list); mutex_unlock(&nbd_index_mutex); while (!list_empty(&del_list)) { nbd = list_first_entry(&del_list, struct nbd_device, list); list_del_init(&nbd->list); if (refcount_read(&nbd->config_refs)) pr_err("possibly leaking nbd_config (ref %d)\n", refcount_read(&nbd->config_refs)); if (refcount_read(&nbd->refs) != 1) pr_err("possibly leaking a device\n"); nbd_put(nbd); } /* Also wait for nbd_dev_remove_work() completes */ destroy_workqueue(nbd_del_wq); idr_destroy(&nbd_index_idr); unregister_blkdev(NBD_MAJOR, "nbd"); } module_init(nbd_init); module_exit(nbd_cleanup); MODULE_DESCRIPTION("Network Block Device"); MODULE_LICENSE("GPL"); module_param(nbds_max, int, 0444); MODULE_PARM_DESC(nbds_max, "number of network block devices to initialize (default: 16)"); module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "number of partitions per device (default: 16)"); |
| 6 6 3 1 4 205 196 6 4 206 206 9 199 175 168 1 2 2 4 6 1 5 9 9 195 192 6 175 3 17 2 9 4 9 202 6 6 4 6 6 8 208 5 170 20 3 3 208 5 4 202 8 209 208 209 208 27 27 195 208 36 186 3 186 187 187 187 186 187 169 170 4 28 28 51 27 27 6 7 5 6 10 1 6 4 9 23 9 22 1 10 29 27 11 40 36 40 6 1 6 5 1 1 1 6 6 2 6 5 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> * (C) 2011 Patrick McHardy <kaber@trash.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/skbuff.h> #include <linux/gfp.h> #include <net/xfrm.h> #include <linux/siphash.h> #include <linux/rtnetlink.h> #include <net/netfilter/nf_conntrack_bpf.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #include <uapi/linux/netfilter/nf_nat.h> #include "nf_internals.h" #define NF_NAT_MAX_ATTEMPTS 128 #define NF_NAT_HARDER_THRESH (NF_NAT_MAX_ATTEMPTS / 4) static spinlock_t nf_nat_locks[CONNTRACK_LOCKS]; static DEFINE_MUTEX(nf_nat_proto_mutex); static unsigned int nat_net_id __read_mostly; static struct hlist_head *nf_nat_bysource __read_mostly; static unsigned int nf_nat_htable_size __read_mostly; static siphash_aligned_key_t nf_nat_hash_rnd; struct nf_nat_lookup_hook_priv { struct nf_hook_entries __rcu *entries; struct rcu_head rcu_head; }; struct nf_nat_hooks_net { struct nf_hook_ops *nat_hook_ops; unsigned int users; }; struct nat_net { struct nf_nat_hooks_net nat_proto_net[NFPROTO_NUMPROTO]; }; #ifdef CONFIG_XFRM static void nf_nat_ipv4_decode_session(struct sk_buff *skb, const struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned long statusbit, struct flowi *fl) { const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; struct flowi4 *fl4 = &fl->u.ip4; if (ct->status & statusbit) { fl4->daddr = t->dst.u3.ip; if (t->dst.protonum == IPPROTO_TCP || t->dst.protonum == IPPROTO_UDP || t->dst.protonum == IPPROTO_SCTP) fl4->fl4_dport = t->dst.u.all; } statusbit ^= IPS_NAT_MASK; if (ct->status & statusbit) { fl4->saddr = t->src.u3.ip; if (t->dst.protonum == IPPROTO_TCP || t->dst.protonum == IPPROTO_UDP || t->dst.protonum == IPPROTO_SCTP) fl4->fl4_sport = t->src.u.all; } } static void nf_nat_ipv6_decode_session(struct sk_buff *skb, const struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned long statusbit, struct flowi *fl) { #if IS_ENABLED(CONFIG_IPV6) const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; struct flowi6 *fl6 = &fl->u.ip6; if (ct->status & statusbit) { fl6->daddr = t->dst.u3.in6; if (t->dst.protonum == IPPROTO_TCP || t->dst.protonum == IPPROTO_UDP || t->dst.protonum == IPPROTO_SCTP) fl6->fl6_dport = t->dst.u.all; } statusbit ^= IPS_NAT_MASK; if (ct->status & statusbit) { fl6->saddr = t->src.u3.in6; if (t->dst.protonum == IPPROTO_TCP || t->dst.protonum == IPPROTO_UDP || t->dst.protonum == IPPROTO_SCTP) fl6->fl6_sport = t->src.u.all; } #endif } static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; unsigned long statusbit; u8 family; ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) return; family = nf_ct_l3num(ct); dir = CTINFO2DIR(ctinfo); if (dir == IP_CT_DIR_ORIGINAL) statusbit = IPS_DST_NAT; else statusbit = IPS_SRC_NAT; switch (family) { case NFPROTO_IPV4: nf_nat_ipv4_decode_session(skb, ct, dir, statusbit, fl); return; case NFPROTO_IPV6: nf_nat_ipv6_decode_session(skb, ct, dir, statusbit, fl); return; } } #endif /* CONFIG_XFRM */ /* We keep an extra hash for each conntrack, for fast searching. */ static unsigned int hash_by_src(const struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { unsigned int hash; struct { struct nf_conntrack_man src; u32 net_mix; u32 protonum; u32 zone; } __aligned(SIPHASH_ALIGNMENT) combined; get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd)); memset(&combined, 0, sizeof(combined)); /* Original src, to ensure we map it consistently if poss. */ combined.src = tuple->src; combined.net_mix = net_hash_mix(net); combined.protonum = tuple->dst.protonum; /* Zone ID can be used provided its valid for both directions */ if (zone->dir == NF_CT_DEFAULT_ZONE_DIR) combined.zone = zone->id; hash = siphash(&combined, sizeof(combined), &nf_nat_hash_rnd); return reciprocal_scale(hash, nf_nat_htable_size); } /** * nf_nat_used_tuple - check if proposed nat tuple clashes with existing entry * @tuple: proposed NAT binding * @ignored_conntrack: our (unconfirmed) conntrack entry * * A conntrack entry can be inserted to the connection tracking table * if there is no existing entry with an identical tuple in either direction. * * Example: * INITIATOR -> NAT/PAT -> RESPONDER * * INITIATOR passes through NAT/PAT ("us") and SNAT is done (saddr rewrite). * Then, later, NAT/PAT itself also connects to RESPONDER. * * This will not work if the SNAT done earlier has same IP:PORT source pair. * * Conntrack table has: * ORIGINAL: $IP_INITIATOR:$SPORT -> $IP_RESPONDER:$DPORT * REPLY: $IP_RESPONDER:$DPORT -> $IP_NAT:$SPORT * * and new locally originating connection wants: * ORIGINAL: $IP_NAT:$SPORT -> $IP_RESPONDER:$DPORT * REPLY: $IP_RESPONDER:$DPORT -> $IP_NAT:$SPORT * * ... which would mean incoming packets cannot be distinguished between * the existing and the newly added entry (identical IP_CT_DIR_REPLY tuple). * * @return: true if the proposed NAT mapping collides with an existing entry. */ static int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack) { /* Conntrack tracking doesn't keep track of outgoing tuples; only * incoming ones. NAT means they don't have a fixed mapping, * so we invert the tuple and look for the incoming reply. * * We could keep a separate hash if this proves too slow. */ struct nf_conntrack_tuple reply; nf_ct_invert_tuple(&reply, tuple); return nf_conntrack_tuple_taken(&reply, ignored_conntrack); } static bool nf_nat_allow_clash(const struct nf_conn *ct) { return nf_ct_l4proto_find(nf_ct_protonum(ct))->allow_clash; } /** * nf_nat_used_tuple_new - check if to-be-inserted conntrack collides with existing entry * @tuple: proposed NAT binding * @ignored_ct: our (unconfirmed) conntrack entry * * Same as nf_nat_used_tuple, but also check for rare clash in reverse * direction. Should be called only when @tuple has not been altered, i.e. * @ignored_conntrack will not be subject to NAT. * * @return: true if the proposed NAT mapping collides with existing entry. */ static noinline bool nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_ct) { static const unsigned long uses_nat = IPS_NAT_MASK | IPS_SEQ_ADJUST; const struct nf_conntrack_tuple_hash *thash; const struct nf_conntrack_zone *zone; struct nf_conn *ct; bool taken = true; struct net *net; if (!nf_nat_used_tuple(tuple, ignored_ct)) return false; if (!nf_nat_allow_clash(ignored_ct)) return true; /* Initial choice clashes with existing conntrack. * Check for (rare) reverse collision. * * This can happen when new packets are received in both directions * at the exact same time on different CPUs. * * Without SMP, first packet creates new conntrack entry and second * packet is resolved as established reply packet. * * With parallel processing, both packets could be picked up as * new and both get their own ct entry allocated. * * If ignored_conntrack and colliding ct are not subject to NAT then * pretend the tuple is available and let later clash resolution * handle this at insertion time. * * Without it, the 'reply' packet has its source port rewritten * by nat engine. */ if (READ_ONCE(ignored_ct->status) & uses_nat) return true; net = nf_ct_net(ignored_ct); zone = nf_ct_zone(ignored_ct); thash = nf_conntrack_find_get(net, zone, tuple); if (unlikely(!thash)) { struct nf_conntrack_tuple reply; nf_ct_invert_tuple(&reply, tuple); thash = nf_conntrack_find_get(net, zone, &reply); if (!thash) /* clashing entry went away */ return false; } ct = nf_ct_tuplehash_to_ctrack(thash); /* clashing connection subject to NAT? Retry with new tuple. */ if (READ_ONCE(ct->status) & uses_nat) goto out; if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, &ignored_ct->tuplehash[IP_CT_DIR_REPLY].tuple)) taken = false; out: nf_ct_put(ct); return taken; } static bool nf_nat_may_kill(struct nf_conn *ct, unsigned long flags) { static const unsigned long flags_refuse = IPS_FIXED_TIMEOUT | IPS_DYING; static const unsigned long flags_needed = IPS_SRC_NAT; enum tcp_conntrack old_state; old_state = READ_ONCE(ct->proto.tcp.state); if (old_state < TCP_CONNTRACK_TIME_WAIT) return false; if (flags & flags_refuse) return false; return (flags & flags_needed) == flags_needed; } /* reverse direction will send packets to new source, so * make sure such packets are invalid. */ static bool nf_seq_has_advanced(const struct nf_conn *old, const struct nf_conn *new) { return (__s32)(new->proto.tcp.seen[0].td_end - old->proto.tcp.seen[0].td_end) > 0; } static int nf_nat_used_tuple_harder(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack, unsigned int attempts_left) { static const unsigned long flags_offload = IPS_OFFLOAD | IPS_HW_OFFLOAD; struct nf_conntrack_tuple_hash *thash; const struct nf_conntrack_zone *zone; struct nf_conntrack_tuple reply; unsigned long flags; struct nf_conn *ct; bool taken = true; struct net *net; nf_ct_invert_tuple(&reply, tuple); if (attempts_left > NF_NAT_HARDER_THRESH || tuple->dst.protonum != IPPROTO_TCP || ignored_conntrack->proto.tcp.state != TCP_CONNTRACK_SYN_SENT) return nf_conntrack_tuple_taken(&reply, ignored_conntrack); /* :ast few attempts to find a free tcp port. Destructive * action: evict colliding if its in timewait state and the * tcp sequence number has advanced past the one used by the * old entry. */ net = nf_ct_net(ignored_conntrack); zone = nf_ct_zone(ignored_conntrack); thash = nf_conntrack_find_get(net, zone, &reply); if (!thash) return false; ct = nf_ct_tuplehash_to_ctrack(thash); if (thash->tuple.dst.dir == IP_CT_DIR_ORIGINAL) goto out; if (WARN_ON_ONCE(ct == ignored_conntrack)) goto out; flags = READ_ONCE(ct->status); if (!nf_nat_may_kill(ct, flags)) goto out; if (!nf_seq_has_advanced(ct, ignored_conntrack)) goto out; /* Even if we can evict do not reuse if entry is offloaded. */ if (nf_ct_kill(ct)) taken = flags & flags_offload; out: nf_ct_put(ct); return taken; } static bool nf_nat_inet_in_range(const struct nf_conntrack_tuple *t, const struct nf_nat_range2 *range) { if (t->src.l3num == NFPROTO_IPV4) return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) && ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip); return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 && ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0; } /* Is the manipable part of the tuple between min and max incl? */ static bool l4proto_in_range(const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype, const union nf_conntrack_man_proto *min, const union nf_conntrack_man_proto *max) { __be16 port; switch (tuple->dst.protonum) { case IPPROTO_ICMP: case IPPROTO_ICMPV6: return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) && ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id); case IPPROTO_GRE: /* all fall though */ case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_SCTP: if (maniptype == NF_NAT_MANIP_SRC) port = tuple->src.u.all; else port = tuple->dst.u.all; return ntohs(port) >= ntohs(min->all) && ntohs(port) <= ntohs(max->all); default: return true; } } /* If we source map this tuple so reply looks like reply_tuple, will * that meet the constraints of range. */ static int nf_in_range(const struct nf_conntrack_tuple *tuple, const struct nf_nat_range2 *range) { /* If we are supposed to map IPs, then we must be in the * range specified, otherwise let this drag us onto a new src IP. */ if (range->flags & NF_NAT_RANGE_MAP_IPS && !nf_nat_inet_in_range(tuple, range)) return 0; if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) return 1; return l4proto_in_range(tuple, NF_NAT_MANIP_SRC, &range->min_proto, &range->max_proto); } static inline int same_src(const struct nf_conn *ct, const struct nf_conntrack_tuple *tuple) { const struct nf_conntrack_tuple *t; t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; return (t->dst.protonum == tuple->dst.protonum && nf_inet_addr_cmp(&t->src.u3, &tuple->src.u3) && t->src.u.all == tuple->src.u.all); } /* Only called for SRC manip */ static int find_appropriate_src(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *result, const struct nf_nat_range2 *range) { unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn *ct; hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) { if (same_src(ct, tuple) && net_eq(net, nf_ct_net(ct)) && nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) { /* Copy source part from reply tuple. */ nf_ct_invert_tuple(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); result->dst = tuple->dst; if (nf_in_range(result, range)) return 1; } } return 0; } /* For [FUTURE] fragmentation handling, we want the least-used * src-ip/dst-ip/proto triple. Fairness doesn't come into it. Thus * if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports * 1-65535, we don't do pro-rata allocation based on ports; we choose * the ip with the lowest src-ip/dst-ip/proto usage. */ static void find_best_ips_proto(const struct nf_conntrack_zone *zone, struct nf_conntrack_tuple *tuple, const struct nf_nat_range2 *range, const struct nf_conn *ct, enum nf_nat_manip_type maniptype) { union nf_inet_addr *var_ipp; unsigned int i, max; /* Host order */ u32 minip, maxip, j, dist; bool full_range; /* No IP mapping? Do nothing. */ if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) return; if (maniptype == NF_NAT_MANIP_SRC) var_ipp = &tuple->src.u3; else var_ipp = &tuple->dst.u3; /* Fast path: only one choice. */ if (nf_inet_addr_cmp(&range->min_addr, &range->max_addr)) { *var_ipp = range->min_addr; return; } if (nf_ct_l3num(ct) == NFPROTO_IPV4) max = sizeof(var_ipp->ip) / sizeof(u32) - 1; else max = sizeof(var_ipp->ip6) / sizeof(u32) - 1; /* Hashing source and destination IPs gives a fairly even * spread in practice (if there are a small number of IPs * involved, there usually aren't that many connections * anyway). The consistency means that servers see the same * client coming from the same IP (some Internet Banking sites * like this), even across reboots. */ j = jhash2((u32 *)&tuple->src.u3, sizeof(tuple->src.u3) / sizeof(u32), range->flags & NF_NAT_RANGE_PERSISTENT ? 0 : (__force u32)tuple->dst.u3.all[max] ^ zone->id); full_range = false; for (i = 0; i <= max; i++) { /* If first bytes of the address are at the maximum, use the * distance. Otherwise use the full range. */ if (!full_range) { minip = ntohl((__force __be32)range->min_addr.all[i]); maxip = ntohl((__force __be32)range->max_addr.all[i]); dist = maxip - minip + 1; } else { minip = 0; dist = ~0; } var_ipp->all[i] = (__force __u32) htonl(minip + reciprocal_scale(j, dist)); if (var_ipp->all[i] != range->max_addr.all[i]) full_range = true; if (!(range->flags & NF_NAT_RANGE_PERSISTENT)) j ^= (__force u32)tuple->dst.u3.all[i]; } } /* Alter the per-proto part of the tuple (depending on maniptype), to * give a unique tuple in the given range if possible. * * Per-protocol part of tuple is initialized to the incoming packet. */ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { unsigned int range_size, min, max, i, attempts; __be16 *keyptr; u16 off; switch (tuple->dst.protonum) { case IPPROTO_ICMP: case IPPROTO_ICMPV6: /* id is same for either direction... */ keyptr = &tuple->src.u.icmp.id; if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { min = 0; range_size = 65536; } else { min = ntohs(range->min_proto.icmp.id); range_size = ntohs(range->max_proto.icmp.id) - ntohs(range->min_proto.icmp.id) + 1; } goto find_free_id; #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) case IPPROTO_GRE: /* If there is no master conntrack we are not PPTP, do not change tuples */ if (!ct->master) return; if (maniptype == NF_NAT_MANIP_SRC) keyptr = &tuple->src.u.gre.key; else keyptr = &tuple->dst.u.gre.key; if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { min = 1; range_size = 65535; } else { min = ntohs(range->min_proto.gre.key); range_size = ntohs(range->max_proto.gre.key) - min + 1; } goto find_free_id; #endif case IPPROTO_UDP: case IPPROTO_TCP: case IPPROTO_SCTP: if (maniptype == NF_NAT_MANIP_SRC) keyptr = &tuple->src.u.all; else keyptr = &tuple->dst.u.all; break; default: return; } /* If no range specified... */ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { /* If it's dst rewrite, can't change port */ if (maniptype == NF_NAT_MANIP_DST) return; if (ntohs(*keyptr) < 1024) { /* Loose convention: >> 512 is credential passing */ if (ntohs(*keyptr) < 512) { min = 1; range_size = 511 - min + 1; } else { min = 600; range_size = 1023 - min + 1; } } else { min = 1024; range_size = 65535 - 1024 + 1; } } else { min = ntohs(range->min_proto.all); max = ntohs(range->max_proto.all); if (unlikely(max < min)) swap(max, min); range_size = max - min + 1; } find_free_id: if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) off = (ntohs(*keyptr) - ntohs(range->base_proto.all)); else if ((range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL) || maniptype != NF_NAT_MANIP_DST) off = get_random_u16(); else off = 0; attempts = range_size; if (attempts > NF_NAT_MAX_ATTEMPTS) attempts = NF_NAT_MAX_ATTEMPTS; /* We are in softirq; doing a search of the entire range risks * soft lockup when all tuples are already used. * * If we can't find any free port from first offset, pick a new * one and try again, with ever smaller search window. */ another_round: for (i = 0; i < attempts; i++, off++) { *keyptr = htons(min + off % range_size); if (!nf_nat_used_tuple_harder(tuple, ct, attempts - i)) return; } if (attempts >= range_size || attempts < 16) return; attempts /= 2; off = get_random_u16(); goto another_round; } /* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING, * we change the source to map into the range. For NF_INET_PRE_ROUTING * and NF_INET_LOCAL_OUT, we change the destination to map into the * range. It might not be possible to get a unique tuple, but we try. * At worst (or if we race), we will end up with a final duplicate in * __nf_conntrack_confirm and drop the packet. */ static void get_unique_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig_tuple, const struct nf_nat_range2 *range, struct nf_conn *ct, enum nf_nat_manip_type maniptype) { const struct nf_conntrack_zone *zone; struct net *net = nf_ct_net(ct); zone = nf_ct_zone(ct); /* 1) If this srcip/proto/src-proto-part is currently mapped, * and that same mapping gives a unique tuple within the given * range, use that. * * This is only required for source (ie. NAT/masq) mappings. * So far, we don't do local source mappings, so multiple * manips not an issue. */ if (maniptype == NF_NAT_MANIP_SRC && !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { /* try the original tuple first */ if (nf_in_range(orig_tuple, range)) { if (!nf_nat_used_tuple_new(orig_tuple, ct)) { *tuple = *orig_tuple; return; } } else if (find_appropriate_src(net, zone, orig_tuple, tuple, range)) { pr_debug("get_unique_tuple: Found current src map\n"); if (!nf_nat_used_tuple(tuple, ct)) return; } } /* 2) Select the least-used IP/proto combination in the given range */ *tuple = *orig_tuple; find_best_ips_proto(zone, tuple, range, ct, maniptype); /* 3) The per-protocol part of the manip is made to map into * the range to make a unique tuple. */ /* Only bother mapping if it's not already in range and unique */ if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { if (!(range->flags & NF_NAT_RANGE_PROTO_OFFSET) && l4proto_in_range(tuple, maniptype, &range->min_proto, &range->max_proto) && (range->min_proto.all == range->max_proto.all || !nf_nat_used_tuple(tuple, ct))) return; } else if (!nf_nat_used_tuple(tuple, ct)) { return; } } /* Last chance: get protocol to try to obtain unique tuple. */ nf_nat_l4proto_unique_tuple(tuple, range, maniptype, ct); } struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct) { struct nf_conn_nat *nat = nfct_nat(ct); if (nat) return nat; if (!nf_ct_is_confirmed(ct)) nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); return nat; } EXPORT_SYMBOL_GPL(nf_ct_nat_ext_add); unsigned int nf_nat_setup_info(struct nf_conn *ct, const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { struct net *net = nf_ct_net(ct); struct nf_conntrack_tuple curr_tuple, new_tuple; /* Can't setup nat info for confirmed ct. */ if (nf_ct_is_confirmed(ct)) return NF_ACCEPT; WARN_ON(maniptype != NF_NAT_MANIP_SRC && maniptype != NF_NAT_MANIP_DST); if (WARN_ON(nf_nat_initialized(ct, maniptype))) return NF_DROP; /* What we've got will look like inverse of reply. Normally * this is what is in the conntrack, except for prior * manipulations (future optimization: if num_manips == 0, * orig_tp = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple) */ nf_ct_invert_tuple(&curr_tuple, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype); if (!nf_ct_tuple_equal(&new_tuple, &curr_tuple)) { struct nf_conntrack_tuple reply; /* Alter conntrack table so will recognize replies. */ nf_ct_invert_tuple(&reply, &new_tuple); nf_conntrack_alter_reply(ct, &reply); /* Non-atomic: we own this at the moment. */ if (maniptype == NF_NAT_MANIP_SRC) ct->status |= IPS_SRC_NAT; else ct->status |= IPS_DST_NAT; if (nfct_help(ct) && !nfct_seqadj(ct)) if (!nfct_seqadj_ext_add(ct)) return NF_DROP; } if (maniptype == NF_NAT_MANIP_SRC) { unsigned int srchash; spinlock_t *lock; srchash = hash_by_src(net, nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS]; spin_lock_bh(lock); hlist_add_head_rcu(&ct->nat_bysource, &nf_nat_bysource[srchash]); spin_unlock_bh(lock); } /* It's done. */ if (maniptype == NF_NAT_MANIP_DST) ct->status |= IPS_DST_NAT_DONE; else ct->status |= IPS_SRC_NAT_DONE; return NF_ACCEPT; } EXPORT_SYMBOL(nf_nat_setup_info); static unsigned int __nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip) { /* Force range to this IP; let proto decide mapping for * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). * Use reply in case it's already been mangled (eg local packet). */ union nf_inet_addr ip = (manip == NF_NAT_MANIP_SRC ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3); struct nf_nat_range2 range = { .flags = NF_NAT_RANGE_MAP_IPS, .min_addr = ip, .max_addr = ip, }; return nf_nat_setup_info(ct, &range, manip); } unsigned int nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) { return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum)); } EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding); /* Do packet manipulations according to nf_nat_setup_info. */ unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, struct sk_buff *skb) { enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned int verdict = NF_ACCEPT; unsigned long statusbit; if (mtype == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; /* Invert if this is reply dir. */ if (dir == IP_CT_DIR_REPLY) statusbit ^= IPS_NAT_MASK; /* Non-atomic: these bits don't change. */ if (ct->status & statusbit) verdict = nf_nat_manip_pkt(skb, ct, mtype, dir); return verdict; } EXPORT_SYMBOL_GPL(nf_nat_packet); static bool in_vrf_postrouting(const struct nf_hook_state *state) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (state->hook == NF_INET_POST_ROUTING && netif_is_l3_master(state->out)) return true; #endif return false; } unsigned int nf_nat_inet_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; /* maniptype == SRC for postrouting. */ enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook); ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would * have dropped it. Hence it's the user's responsibilty to * packet filter it out, or implement conntrack/NAT for that * protocol. 8) --RR */ if (!ct || in_vrf_postrouting(state)) return NF_ACCEPT; nat = nfct_nat(ct); switch (ctinfo) { case IP_CT_RELATED: case IP_CT_RELATED_REPLY: /* Only ICMPs can be IP_CT_IS_REPLY. Fallthrough */ case IP_CT_NEW: /* Seen it before? This can happen for loopback, retrans, * or local packets. */ if (!nf_nat_initialized(ct, maniptype)) { struct nf_nat_lookup_hook_priv *lpriv = priv; struct nf_hook_entries *e = rcu_dereference(lpriv->entries); unsigned int ret; int i; if (!e) goto null_bind; for (i = 0; i < e->num_hook_entries; i++) { ret = e->hooks[i].hook(e->hooks[i].priv, skb, state); if (ret != NF_ACCEPT) return ret; if (nf_nat_initialized(ct, maniptype)) goto do_nat; } null_bind: ret = nf_nat_alloc_null_binding(ct, state->hook); if (ret != NF_ACCEPT) return ret; } else { pr_debug("Already setup manip %s for ct %p (status bits 0x%lx)\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct, ct->status); if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) goto oif_changed; } break; default: /* ESTABLISHED */ WARN_ON(ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY); if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) goto oif_changed; } do_nat: return nf_nat_packet(ct, ctinfo, state->hook, skb); oif_changed: nf_ct_kill_acct(ct, ctinfo, skb); return NF_DROP; } EXPORT_SYMBOL_GPL(nf_nat_inet_fn); struct nf_nat_proto_clean { u8 l3proto; u8 l4proto; }; /* kill conntracks with affected NAT section */ static int nf_nat_proto_remove(struct nf_conn *i, void *data) { const struct nf_nat_proto_clean *clean = data; if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) || (clean->l4proto && nf_ct_protonum(i) != clean->l4proto)) return 0; return i->status & IPS_NAT_MASK ? 1 : 0; } static void nf_nat_cleanup_conntrack(struct nf_conn *ct) { unsigned int h; h = hash_by_src(nf_ct_net(ct), nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); hlist_del_rcu(&ct->nat_bysource); spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]); } static int nf_nat_proto_clean(struct nf_conn *ct, void *data) { if (nf_nat_proto_remove(ct, data)) return 1; /* This module is being removed and conntrack has nat null binding. * Remove it from bysource hash, as the table will be freed soon. * * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack() * will delete entry from already-freed table. */ if (test_and_clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status)) nf_nat_cleanup_conntrack(ct); /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. */ return 0; } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 }, [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 }, }; static int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], struct nf_nat_range2 *range) { if (tb[CTA_PROTONAT_PORT_MIN]) { range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]); range->max_proto.all = range->min_proto.all; range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } if (tb[CTA_PROTONAT_PORT_MAX]) { range->max_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]); range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } return 0; } static int nfnetlink_parse_nat_proto(struct nlattr *attr, const struct nf_conn *ct, struct nf_nat_range2 *range) { struct nlattr *tb[CTA_PROTONAT_MAX+1]; int err; err = nla_parse_nested_deprecated(tb, CTA_PROTONAT_MAX, attr, protonat_nla_policy, NULL); if (err < 0) return err; return nf_nat_l4proto_nlattr_to_range(tb, range); } static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { [CTA_NAT_V4_MINIP] = { .type = NLA_U32 }, [CTA_NAT_V4_MAXIP] = { .type = NLA_U32 }, [CTA_NAT_V6_MINIP] = { .len = sizeof(struct in6_addr) }, [CTA_NAT_V6_MAXIP] = { .len = sizeof(struct in6_addr) }, [CTA_NAT_PROTO] = { .type = NLA_NESTED }, }; static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], struct nf_nat_range2 *range) { if (tb[CTA_NAT_V4_MINIP]) { range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]); range->flags |= NF_NAT_RANGE_MAP_IPS; } range->max_addr.ip = nla_get_be32_default(tb[CTA_NAT_V4_MAXIP], range->min_addr.ip); return 0; } static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], struct nf_nat_range2 *range) { if (tb[CTA_NAT_V6_MINIP]) { nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP], sizeof(struct in6_addr)); range->flags |= NF_NAT_RANGE_MAP_IPS; } if (tb[CTA_NAT_V6_MAXIP]) nla_memcpy(&range->max_addr.ip6, tb[CTA_NAT_V6_MAXIP], sizeof(struct in6_addr)); else range->max_addr = range->min_addr; return 0; } static int nfnetlink_parse_nat(const struct nlattr *nat, const struct nf_conn *ct, struct nf_nat_range2 *range) { struct nlattr *tb[CTA_NAT_MAX+1]; int err; memset(range, 0, sizeof(*range)); err = nla_parse_nested_deprecated(tb, CTA_NAT_MAX, nat, nat_nla_policy, NULL); if (err < 0) return err; switch (nf_ct_l3num(ct)) { case NFPROTO_IPV4: err = nf_nat_ipv4_nlattr_to_range(tb, range); break; case NFPROTO_IPV6: err = nf_nat_ipv6_nlattr_to_range(tb, range); break; default: err = -EPROTONOSUPPORT; break; } if (err) return err; if (!tb[CTA_NAT_PROTO]) return 0; return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); } /* This function is called under rcu_read_lock() */ static int nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { struct nf_nat_range2 range; int err; /* Should not happen, restricted to creating new conntracks * via ctnetlink. */ if (WARN_ON_ONCE(nf_nat_initialized(ct, manip))) return -EEXIST; /* No NAT information has been passed, allocate the null-binding */ if (attr == NULL) return __nf_nat_alloc_null_binding(ct, manip) == NF_DROP ? -ENOMEM : 0; err = nfnetlink_parse_nat(attr, ct, &range); if (err < 0) return err; return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0; } #else static int nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { return -EOPNOTSUPP; } #endif static struct nf_ct_helper_expectfn follow_master_nat = { .name = "nat-follow-master", .expectfn = nf_nat_follow_master, }; int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, const struct nf_hook_ops *orig_nat_ops, unsigned int ops_count) { struct nat_net *nat_net = net_generic(net, nat_net_id); struct nf_nat_hooks_net *nat_proto_net; struct nf_nat_lookup_hook_priv *priv; unsigned int hooknum = ops->hooknum; struct nf_hook_ops *nat_ops; int i, ret; if (WARN_ON_ONCE(pf >= ARRAY_SIZE(nat_net->nat_proto_net))) return -EINVAL; nat_proto_net = &nat_net->nat_proto_net[pf]; for (i = 0; i < ops_count; i++) { if (orig_nat_ops[i].hooknum == hooknum) { hooknum = i; break; } } if (WARN_ON_ONCE(i == ops_count)) return -EINVAL; mutex_lock(&nf_nat_proto_mutex); if (!nat_proto_net->nat_hook_ops) { WARN_ON(nat_proto_net->users != 0); nat_ops = kmemdup_array(orig_nat_ops, ops_count, sizeof(*orig_nat_ops), GFP_KERNEL); if (!nat_ops) { mutex_unlock(&nf_nat_proto_mutex); return -ENOMEM; } for (i = 0; i < ops_count; i++) { priv = kzalloc_obj(*priv); if (priv) { nat_ops[i].priv = priv; continue; } mutex_unlock(&nf_nat_proto_mutex); while (i) kfree(nat_ops[--i].priv); kfree(nat_ops); return -ENOMEM; } ret = nf_register_net_hooks(net, nat_ops, ops_count); if (ret < 0) { mutex_unlock(&nf_nat_proto_mutex); for (i = 0; i < ops_count; i++) { priv = nat_ops[i].priv; kfree_rcu(priv, rcu_head); } kfree_rcu(nat_ops, rcu); return ret; } nat_proto_net->nat_hook_ops = nat_ops; } nat_ops = nat_proto_net->nat_hook_ops; priv = nat_ops[hooknum].priv; if (WARN_ON_ONCE(!priv)) { mutex_unlock(&nf_nat_proto_mutex); return -EOPNOTSUPP; } ret = nf_hook_entries_insert_raw(&priv->entries, ops); if (ret == 0) nat_proto_net->users++; mutex_unlock(&nf_nat_proto_mutex); return ret; } void nf_nat_unregister_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, unsigned int ops_count) { struct nat_net *nat_net = net_generic(net, nat_net_id); struct nf_nat_hooks_net *nat_proto_net; struct nf_nat_lookup_hook_priv *priv; struct nf_hook_ops *nat_ops; int hooknum = ops->hooknum; int i; if (pf >= ARRAY_SIZE(nat_net->nat_proto_net)) return; nat_proto_net = &nat_net->nat_proto_net[pf]; mutex_lock(&nf_nat_proto_mutex); if (WARN_ON(nat_proto_net->users == 0)) goto unlock; nat_proto_net->users--; nat_ops = nat_proto_net->nat_hook_ops; for (i = 0; i < ops_count; i++) { if (nat_ops[i].hooknum == hooknum) { hooknum = i; break; } } if (WARN_ON_ONCE(i == ops_count)) goto unlock; priv = nat_ops[hooknum].priv; nf_hook_entries_delete_raw(&priv->entries, ops); if (nat_proto_net->users == 0) { nf_unregister_net_hooks(net, nat_ops, ops_count); for (i = 0; i < ops_count; i++) { priv = nat_ops[i].priv; kfree_rcu(priv, rcu_head); } nat_proto_net->nat_hook_ops = NULL; kfree_rcu(nat_ops, rcu); } unlock: mutex_unlock(&nf_nat_proto_mutex); } static struct pernet_operations nat_net_ops = { .id = &nat_net_id, .size = sizeof(struct nat_net), }; static const struct nf_nat_hook nat_hook = { .parse_nat_setup = nfnetlink_parse_nat_setup, #ifdef CONFIG_XFRM .decode_session = __nf_nat_decode_session, #endif .remove_nat_bysrc = nf_nat_cleanup_conntrack, }; static int __init nf_nat_init(void) { int ret, i; /* Leave them the same for the moment. */ nf_nat_htable_size = nf_conntrack_htable_size; if (nf_nat_htable_size < CONNTRACK_LOCKS) nf_nat_htable_size = CONNTRACK_LOCKS; nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0); if (!nf_nat_bysource) return -ENOMEM; for (i = 0; i < CONNTRACK_LOCKS; i++) spin_lock_init(&nf_nat_locks[i]); ret = register_pernet_subsys(&nat_net_ops); if (ret < 0) { kvfree(nf_nat_bysource); return ret; } nf_ct_helper_expectfn_register(&follow_master_nat); WARN_ON(nf_nat_hook != NULL); RCU_INIT_POINTER(nf_nat_hook, &nat_hook); ret = register_nf_nat_bpf(); if (ret < 0) { RCU_INIT_POINTER(nf_nat_hook, NULL); nf_ct_helper_expectfn_unregister(&follow_master_nat); synchronize_net(); unregister_pernet_subsys(&nat_net_ops); kvfree(nf_nat_bysource); } return ret; } static void __exit nf_nat_cleanup(void) { struct nf_nat_proto_clean clean = {}; nf_ct_iterate_destroy(nf_nat_proto_clean, &clean); nf_ct_helper_expectfn_unregister(&follow_master_nat); RCU_INIT_POINTER(nf_nat_hook, NULL); synchronize_net(); kvfree(nf_nat_bysource); unregister_pernet_subsys(&nat_net_ops); } MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Network address translation core"); module_init(nf_nat_init); module_exit(nf_nat_cleanup); |
| 48 2 46 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2010 * Phillip Lougher <phillip@squashfs.org.uk> * * xattr.h */ #ifdef CONFIG_SQUASHFS_XATTR extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, u64 *, unsigned int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_xattr_id_table *id_table; id_table = squashfs_read_table(sb, start, sizeof(*id_table)); if (IS_ERR(id_table)) return (__le64 *) id_table; *xattr_table_start = le64_to_cpu(id_table->xattr_table_start); kfree(id_table); ERROR("Xattrs in filesystem, these will be ignored\n"); return ERR_PTR(-ENOTSUPP); } static inline int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, int *count, unsigned int *size, unsigned long long *xattr) { return 0; } #define squashfs_listxattr NULL #define squashfs_xattr_handlers NULL #endif |
| 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 | #ifndef LLC_C_EV_H #define LLC_C_EV_H /* * Copyright (c) 1997 by Procom Technology,Inc. * 2001 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <net/sock.h> /* Connection component state transition event qualifiers */ /* Types of events (possible values in 'ev->type') */ #define LLC_CONN_EV_TYPE_SIMPLE 1 #define LLC_CONN_EV_TYPE_CONDITION 2 #define LLC_CONN_EV_TYPE_PRIM 3 #define LLC_CONN_EV_TYPE_PDU 4 /* command/response PDU */ #define LLC_CONN_EV_TYPE_ACK_TMR 5 #define LLC_CONN_EV_TYPE_P_TMR 6 #define LLC_CONN_EV_TYPE_REJ_TMR 7 #define LLC_CONN_EV_TYPE_BUSY_TMR 8 #define LLC_CONN_EV_TYPE_RPT_STATUS 9 #define LLC_CONN_EV_TYPE_SENDACK_TMR 10 #define NBR_CONN_EV 5 /* Connection events which cause state transitions when fully qualified */ #define LLC_CONN_EV_CONN_REQ 1 #define LLC_CONN_EV_CONN_RESP 2 #define LLC_CONN_EV_DATA_REQ 3 #define LLC_CONN_EV_DISC_REQ 4 #define LLC_CONN_EV_RESET_REQ 5 #define LLC_CONN_EV_RESET_RESP 6 #define LLC_CONN_EV_LOCAL_BUSY_DETECTED 7 #define LLC_CONN_EV_LOCAL_BUSY_CLEARED 8 #define LLC_CONN_EV_RX_BAD_PDU 9 #define LLC_CONN_EV_RX_DISC_CMD_Pbit_SET_X 10 #define LLC_CONN_EV_RX_DM_RSP_Fbit_SET_X 11 #define LLC_CONN_EV_RX_FRMR_RSP_Fbit_SET_X 12 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X 13 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_UNEXPD_Ns 14 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_X_INVAL_Ns 15 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X 16 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_UNEXPD_Ns 17 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_X_INVAL_Ns 18 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_X 19 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_X 20 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_X 21 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_X 22 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_X 23 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_X 24 #define LLC_CONN_EV_RX_SABME_CMD_Pbit_SET_X 25 #define LLC_CONN_EV_RX_UA_RSP_Fbit_SET_X 26 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_X 27 #define LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_X 28 #define LLC_CONN_EV_RX_XXX_YYY 29 #define LLC_CONN_EV_RX_ZZZ_CMD_Pbit_SET_X_INVAL_Nr 30 #define LLC_CONN_EV_RX_ZZZ_RSP_Fbit_SET_X_INVAL_Nr 31 #define LLC_CONN_EV_P_TMR_EXP 32 #define LLC_CONN_EV_ACK_TMR_EXP 33 #define LLC_CONN_EV_REJ_TMR_EXP 34 #define LLC_CONN_EV_BUSY_TMR_EXP 35 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_1 36 #define LLC_CONN_EV_RX_XXX_CMD_Pbit_SET_0 37 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_0_UNEXPD_Ns 38 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_0_UNEXPD_Ns 39 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_1_UNEXPD_Ns 40 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_1_UNEXPD_Ns 41 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_0 42 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_0 43 #define LLC_CONN_EV_RX_I_CMD_Pbit_SET_1 44 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_0 45 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_0 46 #define LLC_CONN_EV_RX_RR_RSP_Fbit_SET_1 47 #define LLC_CONN_EV_RX_RR_CMD_Pbit_SET_1 48 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_0 49 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_0 50 #define LLC_CONN_EV_RX_RNR_RSP_Fbit_SET_1 51 #define LLC_CONN_EV_RX_RNR_CMD_Pbit_SET_1 52 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_0 53 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_0 54 #define LLC_CONN_EV_RX_REJ_CMD_Pbit_SET_1 55 #define LLC_CONN_EV_RX_I_RSP_Fbit_SET_1 56 #define LLC_CONN_EV_RX_REJ_RSP_Fbit_SET_1 57 #define LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_1 58 #define LLC_CONN_EV_TX_BUFF_FULL 59 #define LLC_CONN_EV_INIT_P_F_CYCLE 100 /* * Connection event qualifiers; for some events a certain combination of * these qualifiers must be TRUE before event recognized valid for state; * these constants act as indexes into the Event Qualifier function * table */ #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_1 1 #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_0 2 #define LLC_CONN_EV_QFY_DATA_FLAG_EQ_2 3 #define LLC_CONN_EV_QFY_P_FLAG_EQ_1 4 #define LLC_CONN_EV_QFY_P_FLAG_EQ_0 5 #define LLC_CONN_EV_QFY_P_FLAG_EQ_Fbit 6 #define LLC_CONN_EV_QFY_REMOTE_BUSY_EQ_0 7 #define LLC_CONN_EV_QFY_RETRY_CNT_LT_N2 8 #define LLC_CONN_EV_QFY_RETRY_CNT_GTE_N2 9 #define LLC_CONN_EV_QFY_S_FLAG_EQ_1 10 #define LLC_CONN_EV_QFY_S_FLAG_EQ_0 11 #define LLC_CONN_EV_QFY_INIT_P_F_CYCLE 12 struct llc_conn_state_ev { u8 type; u8 prim; u8 prim_type; u8 reason; u8 status; u8 ind_prim; u8 cfm_prim; }; static __inline__ struct llc_conn_state_ev *llc_conn_ev(struct sk_buff *skb) { return (struct llc_conn_state_ev *)skb->cb; } typedef int (*llc_conn_ev_t)(struct sock *sk, struct sk_buff *skb); typedef int (*llc_conn_ev_qfyr_t)(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_conn_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_data_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_disc_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rst_req(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_local_busy_detected(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_local_busy_cleared(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_bad_pdu(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_disc_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_dm_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_frmr_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_x_inval_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_sabme_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_ua_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_cmd_pbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_x(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_zzz_cmd_pbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_zzz_rsp_fbit_set_x_inval_nr(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_p_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_ack_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rej_tmr_exp(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_busy_tmr_exp(struct sock *sk, struct sk_buff *skb); /* NOT_USED functions and their variations */ int llc_conn_ev_rx_xxx_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_xxx_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_i_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rnr_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_cmd_pbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_cmd_pbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_rej_rsp_fbit_set_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_rx_any_frame(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_tx_buffer_full(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_init_p_f_cycle(struct sock *sk, struct sk_buff *skb); /* Available connection action qualifiers */ int llc_conn_ev_qlfy_data_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_data_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_data_flag_eq_2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_last_frame_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_last_frame_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_p_flag_eq_f(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_remote_busy_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_remote_busy_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_retry_cnt_lt_n2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_retry_cnt_gte_n2(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_s_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_s_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_cause_flag_eq_1(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_cause_flag_eq_0(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_conn(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_disc(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_failed(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_remote_busy(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_refuse(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_conflict(struct sock *sk, struct sk_buff *skb); int llc_conn_ev_qlfy_set_status_rst_done(struct sock *sk, struct sk_buff *skb); static __inline__ int llc_conn_space(struct sock *sk, struct sk_buff *skb) { return atomic_read(&sk->sk_rmem_alloc) + skb->truesize < (unsigned int)sk->sk_rcvbuf; } #endif /* LLC_C_EV_H */ |
| 13 9 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/spinlock.h> #include <linux/atomic.h> /* * This is an implementation of the notion of "decrement a * reference count, and return locked if it decremented to zero". * * NOTE NOTE NOTE! This is _not_ equivalent to * * if (atomic_dec_and_test(&atomic)) { * spin_lock(&lock); * return 1; * } * return 0; * * because the spin-lock and the decrement must be * "atomic". */ int atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; spin_unlock(lock); return 0; } EXPORT_SYMBOL(atomic_dec_and_lock); int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); int atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ raw_spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; raw_spin_unlock(lock); return 0; } EXPORT_SYMBOL(atomic_dec_and_raw_lock); int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ raw_spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; raw_spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave); |
| 12498 12541 1 1 133 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <net/net_namespace.h> #include <linux/if_arp.h> #include <net/rtnetlink.h> static netdev_tx_t nlmon_xmit(struct sk_buff *skb, struct net_device *dev) { dev_lstats_add(dev, skb->len); dev_kfree_skb(skb); return NETDEV_TX_OK; } struct nlmon { struct netlink_tap nt; }; static int nlmon_open(struct net_device *dev) { struct nlmon *nlmon = netdev_priv(dev); nlmon->nt.dev = dev; nlmon->nt.module = THIS_MODULE; return netlink_add_tap(&nlmon->nt); } static int nlmon_close(struct net_device *dev) { struct nlmon *nlmon = netdev_priv(dev); return netlink_remove_tap(&nlmon->nt); } static void nlmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { dev_lstats_read(dev, &stats->rx_packets, &stats->rx_bytes); } static u32 always_on(struct net_device *dev) { return 1; } static const struct ethtool_ops nlmon_ethtool_ops = { .get_link = always_on, }; static const struct net_device_ops nlmon_ops = { .ndo_open = nlmon_open, .ndo_stop = nlmon_close, .ndo_start_xmit = nlmon_xmit, .ndo_get_stats64 = nlmon_get_stats64, }; static void nlmon_setup(struct net_device *dev) { dev->type = ARPHRD_NETLINK; dev->priv_flags |= IFF_NO_QUEUE; dev->lltx = true; dev->netdev_ops = &nlmon_ops; dev->ethtool_ops = &nlmon_ethtool_ops; dev->needs_free_netdev = true; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA; dev->flags = IFF_NOARP; dev->pcpu_stat_type = NETDEV_PCPU_STAT_LSTATS; /* That's rather a softlimit here, which, of course, * can be altered. Not a real MTU, but what is to be * expected in most cases. */ dev->mtu = NLMSG_GOODSIZE; dev->min_mtu = sizeof(struct nlmsghdr); } static int nlmon_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) return -EINVAL; return 0; } static struct rtnl_link_ops nlmon_link_ops __read_mostly = { .kind = "nlmon", .priv_size = sizeof(struct nlmon), .setup = nlmon_setup, .validate = nlmon_validate, }; static __init int nlmon_register(void) { return rtnl_link_register(&nlmon_link_ops); } static __exit void nlmon_unregister(void) { rtnl_link_unregister(&nlmon_link_ops); } module_init(nlmon_register); module_exit(nlmon_unregister); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); MODULE_AUTHOR("Mathieu Geli <geli@enseirb.fr>"); MODULE_DESCRIPTION("Netlink monitoring device"); MODULE_ALIAS_RTNL_LINK("nlmon"); |
| 2 35 35 35 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/netfilter.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/percpu.h> #include <linux/netdevice.h> #include <linux/security.h> #include <net/net_namespace.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/netfilter/nf_log.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <linux/rculist_nulls.h> static bool enable_hooks __read_mostly; MODULE_PARM_DESC(enable_hooks, "Always enable conntrack hooks"); module_param(enable_hooks, bool, 0000); unsigned int nf_conntrack_net_id __read_mostly; #ifdef CONFIG_NF_CONNTRACK_PROCFS void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *l4proto) { switch (tuple->src.l3num) { case NFPROTO_IPV4: seq_printf(s, "src=%pI4 dst=%pI4 ", &tuple->src.u3.ip, &tuple->dst.u3.ip); break; case NFPROTO_IPV6: seq_printf(s, "src=%pI6 dst=%pI6 ", tuple->src.u3.ip6, tuple->dst.u3.ip6); break; default: break; } switch (l4proto->l4proto) { case IPPROTO_ICMP: seq_printf(s, "type=%u code=%u id=%u ", tuple->dst.u.icmp.type, tuple->dst.u.icmp.code, ntohs(tuple->src.u.icmp.id)); break; case IPPROTO_TCP: seq_printf(s, "sport=%hu dport=%hu ", ntohs(tuple->src.u.tcp.port), ntohs(tuple->dst.u.tcp.port)); break; case IPPROTO_UDP: seq_printf(s, "sport=%hu dport=%hu ", ntohs(tuple->src.u.udp.port), ntohs(tuple->dst.u.udp.port)); break; case IPPROTO_SCTP: seq_printf(s, "sport=%hu dport=%hu ", ntohs(tuple->src.u.sctp.port), ntohs(tuple->dst.u.sctp.port)); break; case IPPROTO_ICMPV6: seq_printf(s, "type=%u code=%u id=%u ", tuple->dst.u.icmp.type, tuple->dst.u.icmp.code, ntohs(tuple->src.u.icmp.id)); break; case IPPROTO_GRE: seq_printf(s, "srckey=0x%x dstkey=0x%x ", ntohs(tuple->src.u.gre.key), ntohs(tuple->dst.u.gre.key)); break; default: break; } } EXPORT_SYMBOL_GPL(print_tuple); struct ct_iter_state { struct seq_net_private p; struct hlist_nulls_head *hash; unsigned int htable_size; unsigned int skip_elems; unsigned int bucket; u_int64_t time_now; }; static struct nf_conntrack_tuple_hash *ct_get_next(const struct net *net, struct ct_iter_state *st) { struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; unsigned int i; for (i = st->bucket; i < st->htable_size; i++) { unsigned int skip = 0; restart: hlist_nulls_for_each_entry_rcu(h, n, &st->hash[i], hnnode) { struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); struct hlist_nulls_node *tmp = n; if (!net_eq(net, nf_ct_net(ct))) continue; if (++skip <= st->skip_elems) continue; /* h should be returned, skip to nulls marker. */ while (!is_a_nulls(tmp)) tmp = rcu_dereference(hlist_nulls_next_rcu(tmp)); /* check if h is still linked to hash[i] */ if (get_nulls_value(tmp) != i) { skip = 0; goto restart; } st->skip_elems = skip; st->bucket = i; return h; } skip = 0; if (get_nulls_value(n) != i) goto restart; st->skip_elems = 0; } st->bucket = i; return NULL; } static void *ct_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct ct_iter_state *st = seq->private; struct net *net = seq_file_net(seq); st->time_now = ktime_get_real_ns(); rcu_read_lock(); nf_conntrack_get_ht(&st->hash, &st->htable_size); if (*pos == 0) { st->skip_elems = 0; st->bucket = 0; } else if (st->skip_elems) { /* resume from last dumped entry */ st->skip_elems--; } return ct_get_next(net, st); } static void *ct_seq_next(struct seq_file *s, void *v, loff_t *pos) { struct ct_iter_state *st = s->private; struct net *net = seq_file_net(s); (*pos)++; return ct_get_next(net, st); } static void ct_seq_stop(struct seq_file *s, void *v) __releases(RCU) { rcu_read_unlock(); } #ifdef CONFIG_NF_CONNTRACK_SECMARK static void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { struct lsm_context ctx; int ret; ret = security_secid_to_secctx(ct->secmark, &ctx); if (ret < 0) return; seq_printf(s, "secctx=%s ", ctx.context); security_release_secctx(&ctx); } #else static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { } #endif #ifdef CONFIG_NF_CONNTRACK_ZONES static void ct_show_zone(struct seq_file *s, const struct nf_conn *ct, int dir) { const struct nf_conntrack_zone *zone = nf_ct_zone(ct); if (zone->dir != dir) return; switch (zone->dir) { case NF_CT_DEFAULT_ZONE_DIR: seq_printf(s, "zone=%u ", zone->id); break; case NF_CT_ZONE_DIR_ORIG: seq_printf(s, "zone-orig=%u ", zone->id); break; case NF_CT_ZONE_DIR_REPL: seq_printf(s, "zone-reply=%u ", zone->id); break; default: break; } } #else static inline void ct_show_zone(struct seq_file *s, const struct nf_conn *ct, int dir) { } #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP static void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) { struct ct_iter_state *st = s->private; struct nf_conn_tstamp *tstamp; s64 delta_time; tstamp = nf_conn_tstamp_find(ct); if (tstamp) { delta_time = st->time_now - tstamp->start; if (delta_time > 0) delta_time = div_s64(delta_time, NSEC_PER_SEC); else delta_time = 0; seq_printf(s, "delta-time=%llu ", (unsigned long long)delta_time); } return; } #else static inline void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) { } #endif static const char* l3proto_name(u16 proto) { switch (proto) { case AF_INET: return "ipv4"; case AF_INET6: return "ipv6"; } return "unknown"; } static const char* l4proto_name(u16 proto) { switch (proto) { case IPPROTO_ICMP: return "icmp"; case IPPROTO_TCP: return "tcp"; case IPPROTO_UDP: return "udp"; case IPPROTO_GRE: return "gre"; case IPPROTO_SCTP: return "sctp"; case IPPROTO_ICMPV6: return "icmpv6"; } return "unknown"; } static void seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir) { struct nf_conn_acct *acct; struct nf_conn_counter *counter; acct = nf_conn_acct_find(ct); if (!acct) return; counter = acct->counter; seq_printf(s, "packets=%llu bytes=%llu ", (unsigned long long)atomic64_read(&counter[dir].packets), (unsigned long long)atomic64_read(&counter[dir].bytes)); } /* return 0 on success, 1 in case of error */ static int ct_seq_show(struct seq_file *s, void *v) { struct nf_conntrack_tuple_hash *hash = v; struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l4proto *l4proto; struct net *net = seq_file_net(s); int ret = 0; WARN_ON(!ct); if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use))) return 0; /* load ->status after refcount increase */ smp_acquire__after_ctrl_dep(); if (nf_ct_should_gc(ct)) { struct ct_iter_state *st = s->private; st->skip_elems--; nf_ct_kill(ct); goto release; } /* we only want to print DIR_ORIGINAL */ if (NF_CT_DIRECTION(hash)) goto release; if (!net_eq(nf_ct_net(ct), net)) goto release; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); ret = -ENOSPC; seq_printf(s, "%-8s %u %-8s %u ", l3proto_name(nf_ct_l3num(ct)), nf_ct_l3num(ct), l4proto_name(l4proto->l4proto), nf_ct_protonum(ct)); if (!test_bit(IPS_OFFLOAD_BIT, &ct->status)) seq_printf(s, "%ld ", nf_ct_expires(ct) / HZ); if (l4proto->print_conntrack) l4proto->print_conntrack(s, ct); print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, l4proto); ct_show_zone(s, ct, NF_CT_ZONE_DIR_ORIG); if (seq_has_overflowed(s)) goto release; seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL); if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) seq_puts(s, "[UNREPLIED] "); print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l4proto); ct_show_zone(s, ct, NF_CT_ZONE_DIR_REPL); seq_print_acct(s, ct, IP_CT_DIR_REPLY); if (test_bit(IPS_HW_OFFLOAD_BIT, &ct->status)) seq_puts(s, "[HW_OFFLOAD] "); else if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) seq_puts(s, "[OFFLOAD] "); else if (test_bit(IPS_ASSURED_BIT, &ct->status)) seq_puts(s, "[ASSURED] "); if (seq_has_overflowed(s)) goto release; #if defined(CONFIG_NF_CONNTRACK_MARK) seq_printf(s, "mark=%u ", READ_ONCE(ct->mark)); #endif ct_show_secctx(s, ct); ct_show_zone(s, ct, NF_CT_DEFAULT_ZONE_DIR); ct_show_delta_time(s, ct); seq_printf(s, "use=%u\n", refcount_read(&ct->ct_general.use)); if (seq_has_overflowed(s)) goto release; ret = 0; release: nf_ct_put(ct); return ret; } static const struct seq_operations ct_seq_ops = { .start = ct_seq_start, .next = ct_seq_next, .stop = ct_seq_stop, .show = ct_seq_show }; static void *ct_cpu_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu + 1; return per_cpu_ptr(net->ct.stat, cpu); } return NULL; } static void *ct_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu + 1; return per_cpu_ptr(net->ct.stat, cpu); } (*pos)++; return NULL; } static void ct_cpu_seq_stop(struct seq_file *seq, void *v) { } static int ct_cpu_seq_show(struct seq_file *seq, void *v) { struct net *net = seq_file_net(seq); const struct ip_conntrack_stat *st = v; unsigned int nr_conntracks; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries clashres found new invalid ignore delete chainlength insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); return 0; } nr_conntracks = nf_conntrack_count(net); seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", nr_conntracks, st->clash_resolve, st->found, 0, st->invalid, 0, 0, st->chaintoolong, st->insert, st->insert_failed, st->drop, st->early_drop, st->error, st->expect_new, st->expect_create, st->expect_delete, st->search_restart ); return 0; } static const struct seq_operations ct_cpu_seq_ops = { .start = ct_cpu_seq_start, .next = ct_cpu_seq_next, .stop = ct_cpu_seq_stop, .show = ct_cpu_seq_show, }; static int nf_conntrack_standalone_init_proc(struct net *net) { struct proc_dir_entry *pde; kuid_t root_uid; kgid_t root_gid; pde = proc_create_net("nf_conntrack", 0440, net->proc_net, &ct_seq_ops, sizeof(struct ct_iter_state)); if (!pde) goto out_nf_conntrack; root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(pde, root_uid, root_gid); pde = proc_create_net("nf_conntrack", 0444, net->proc_net_stat, &ct_cpu_seq_ops, sizeof(struct seq_net_private)); if (!pde) goto out_stat_nf_conntrack; return 0; out_stat_nf_conntrack: remove_proc_entry("nf_conntrack", net->proc_net); out_nf_conntrack: return -ENOMEM; } static void nf_conntrack_standalone_fini_proc(struct net *net) { remove_proc_entry("nf_conntrack", net->proc_net_stat); remove_proc_entry("nf_conntrack", net->proc_net); } #else static int nf_conntrack_standalone_init_proc(struct net *net) { return 0; } static void nf_conntrack_standalone_fini_proc(struct net *net) { } #endif /* CONFIG_NF_CONNTRACK_PROCFS */ u32 nf_conntrack_count(const struct net *net) { const struct nf_conntrack_net *cnet = nf_ct_pernet(net); return atomic_read(&cnet->count); } EXPORT_SYMBOL_GPL(nf_conntrack_count); /* Sysctl support */ #ifdef CONFIG_SYSCTL /* size the user *wants to set */ static unsigned int nf_conntrack_htable_size_user __read_mostly; static int nf_conntrack_hash_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; /* module_param hashsize could have changed value */ nf_conntrack_htable_size_user = nf_conntrack_htable_size; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret < 0 || !write) return ret; /* update ret, we might not be able to satisfy request */ ret = nf_conntrack_hash_resize(nf_conntrack_htable_size_user); /* update it to the actual value used by conntrack */ nf_conntrack_htable_size_user = nf_conntrack_htable_size; return ret; } static int nf_conntrack_log_invalid_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, i; ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (ret < 0 || !write) return ret; if (*(u8 *)table->data == 0) return 0; /* Load nf_log_syslog only if no logger is currently registered */ for (i = 0; i < NFPROTO_NUMPROTO; i++) { if (nf_log_is_registered(i)) return 0; } request_module("%s", "nf_log_syslog"); return 0; } static struct ctl_table_header *nf_ct_netfilter_header; enum nf_ct_sysctl_index { NF_SYSCTL_CT_MAX, NF_SYSCTL_CT_COUNT, NF_SYSCTL_CT_BUCKETS, NF_SYSCTL_CT_CHECKSUM, NF_SYSCTL_CT_LOG_INVALID, NF_SYSCTL_CT_EXPECT_MAX, NF_SYSCTL_CT_ACCT, #ifdef CONFIG_NF_CONNTRACK_EVENTS NF_SYSCTL_CT_EVENTS, #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP NF_SYSCTL_CT_TIMESTAMP, #endif NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_RECV, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ESTABLISHED, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_FIN_WAIT, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE_WAIT, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_LAST_ACK, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_TIME_WAIT, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD, #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST, NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD, #endif NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, #ifdef CONFIG_NF_CT_PROTO_SCTP NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_CLOSED, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_WAIT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_ECHOED, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ESTABLISHED, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, #endif #ifdef CONFIG_NF_CT_PROTO_GRE NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif NF_SYSCTL_CT_LAST_SYSCTL, }; static struct ctl_table nf_ct_sysctl_table[] = { [NF_SYSCTL_CT_MAX] = { .procname = "nf_conntrack_max", .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_COUNT] = { .procname = "nf_conntrack_count", .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, [NF_SYSCTL_CT_BUCKETS] = { .procname = "nf_conntrack_buckets", .data = &nf_conntrack_htable_size_user, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = nf_conntrack_hash_sysctl, }, [NF_SYSCTL_CT_CHECKSUM] = { .procname = "nf_conntrack_checksum", .data = &init_net.ct.sysctl_checksum, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_LOG_INVALID] = { .procname = "nf_conntrack_log_invalid", .data = &init_net.ct.sysctl_log_invalid, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = nf_conntrack_log_invalid_sysctl, }, [NF_SYSCTL_CT_EXPECT_MAX] = { .procname = "nf_conntrack_expect_max", .data = &nf_ct_expect_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_ACCT] = { .procname = "nf_conntrack_acct", .data = &init_net.ct.sysctl_acct, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #ifdef CONFIG_NF_CONNTRACK_EVENTS [NF_SYSCTL_CT_EVENTS] = { .procname = "nf_conntrack_events", .data = &init_net.ct.sysctl_events, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP [NF_SYSCTL_CT_TIMESTAMP] = { .procname = "nf_conntrack_timestamp", .data = &init_net.ct.sysctl_tstamp, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC] = { .procname = "nf_conntrack_generic_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_SENT] = { .procname = "nf_conntrack_tcp_timeout_syn_sent", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_RECV] = { .procname = "nf_conntrack_tcp_timeout_syn_recv", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ESTABLISHED] = { .procname = "nf_conntrack_tcp_timeout_established", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_FIN_WAIT] = { .procname = "nf_conntrack_tcp_timeout_fin_wait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE_WAIT] = { .procname = "nf_conntrack_tcp_timeout_close_wait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_LAST_ACK] = { .procname = "nf_conntrack_tcp_timeout_last_ack", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_TIME_WAIT] = { .procname = "nf_conntrack_tcp_timeout_time_wait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE] = { .procname = "nf_conntrack_tcp_timeout_close", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS] = { .procname = "nf_conntrack_tcp_timeout_max_retrans", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK] = { .procname = "nf_conntrack_tcp_timeout_unacknowledged", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD] = { .procname = "nf_flowtable_tcp_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #endif [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_LIBERAL] = { .procname = "nf_conntrack_tcp_be_liberal", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST] = { .procname = "nf_conntrack_tcp_ignore_invalid_rst", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = { .procname = "nf_conntrack_tcp_max_retrans", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP] = { .procname = "nf_conntrack_udp_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM] = { .procname = "nf_conntrack_udp_timeout_stream", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = { .procname = "nf_flowtable_udp_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { .procname = "nf_conntrack_icmp_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6] = { .procname = "nf_conntrack_icmpv6_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #ifdef CONFIG_NF_CT_PROTO_SCTP [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_CLOSED] = { .procname = "nf_conntrack_sctp_timeout_closed", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_WAIT] = { .procname = "nf_conntrack_sctp_timeout_cookie_wait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_ECHOED] = { .procname = "nf_conntrack_sctp_timeout_cookie_echoed", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ESTABLISHED] = { .procname = "nf_conntrack_sctp_timeout_established", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_SENT] = { .procname = "nf_conntrack_sctp_timeout_shutdown_sent", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD] = { .procname = "nf_conntrack_sctp_timeout_shutdown_recd", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .procname = "nf_conntrack_sctp_timeout_shutdown_ack_sent", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .procname = "nf_conntrack_sctp_timeout_heartbeat_sent", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #endif #ifdef CONFIG_NF_CT_PROTO_GRE [NF_SYSCTL_CT_PROTO_TIMEOUT_GRE] = { .procname = "nf_conntrack_gre_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM] = { .procname = "nf_conntrack_gre_timeout_stream", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #endif }; static struct ctl_table nf_ct_netfilter_table[] = { { .procname = "nf_conntrack_max", .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, }; static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, struct ctl_table *table) { struct nf_tcp_net *tn = nf_tcp_pernet(net); #define XASSIGN(XNAME, tn) \ table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ ## XNAME].data = \ &(tn)->timeouts[TCP_CONNTRACK_ ## XNAME] XASSIGN(SYN_SENT, tn); XASSIGN(SYN_RECV, tn); XASSIGN(ESTABLISHED, tn); XASSIGN(FIN_WAIT, tn); XASSIGN(CLOSE_WAIT, tn); XASSIGN(LAST_ACK, tn); XASSIGN(TIME_WAIT, tn); XASSIGN(CLOSE, tn); XASSIGN(RETRANS, tn); XASSIGN(UNACK, tn); #undef XASSIGN #define XASSIGN(XNAME, rval) \ table[NF_SYSCTL_CT_PROTO_TCP_ ## XNAME].data = (rval) XASSIGN(LOOSE, &tn->tcp_loose); XASSIGN(LIBERAL, &tn->tcp_be_liberal); XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans); XASSIGN(IGNORE_INVALID_RST, &tn->tcp_ignore_invalid_rst); #undef XASSIGN #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout; #endif } static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, struct ctl_table *table) { #ifdef CONFIG_NF_CT_PROTO_SCTP struct nf_sctp_net *sn = nf_sctp_pernet(net); #define XASSIGN(XNAME, sn) \ table[NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ ## XNAME].data = \ &(sn)->timeouts[SCTP_CONNTRACK_ ## XNAME] XASSIGN(CLOSED, sn); XASSIGN(COOKIE_WAIT, sn); XASSIGN(COOKIE_ECHOED, sn); XASSIGN(ESTABLISHED, sn); XASSIGN(SHUTDOWN_SENT, sn); XASSIGN(SHUTDOWN_RECD, sn); XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); #undef XASSIGN #endif } static void nf_conntrack_standalone_init_gre_sysctl(struct net *net, struct ctl_table *table) { #ifdef CONFIG_NF_CT_PROTO_GRE struct nf_gre_net *gn = nf_gre_pernet(net); table[NF_SYSCTL_CT_PROTO_TIMEOUT_GRE].data = &gn->timeouts[GRE_CT_UNREPLIED]; table[NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM].data = &gn->timeouts[GRE_CT_REPLIED]; #endif } static int nf_conntrack_standalone_init_sysctl(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_udp_net *un = nf_udp_pernet(net); struct ctl_table *table; BUILD_BUG_ON(ARRAY_SIZE(nf_ct_sysctl_table) != NF_SYSCTL_CT_LAST_SYSCTL); table = kmemdup(nf_ct_sysctl_table, sizeof(nf_ct_sysctl_table), GFP_KERNEL); if (!table) return -ENOMEM; table[NF_SYSCTL_CT_COUNT].data = &cnet->count; table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum; table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid; table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct; #ifdef CONFIG_NF_CONNTRACK_EVENTS table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events; #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP table[NF_SYSCTL_CT_TIMESTAMP].data = &net->ct.sysctl_tstamp; #endif table[NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC].data = &nf_generic_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP].data = &nf_icmp_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP].data = &un->timeouts[UDP_CT_UNREPLIED]; table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout; #endif nf_conntrack_standalone_init_tcp_sysctl(net, table); nf_conntrack_standalone_init_sctp_sysctl(net, table); nf_conntrack_standalone_init_gre_sysctl(net, table); /* Don't allow non-init_net ns to alter global sysctls */ if (!net_eq(&init_net, net)) { table[NF_SYSCTL_CT_MAX].mode = 0444; table[NF_SYSCTL_CT_EXPECT_MAX].mode = 0444; table[NF_SYSCTL_CT_BUCKETS].mode = 0444; } cnet->sysctl_header = register_net_sysctl_sz(net, "net/netfilter", table, ARRAY_SIZE(nf_ct_sysctl_table)); if (!cnet->sysctl_header) goto out_unregister_netfilter; return 0; out_unregister_netfilter: kfree(table); return -ENOMEM; } static void nf_conntrack_standalone_fini_sysctl(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); const struct ctl_table *table; table = cnet->sysctl_header->ctl_table_arg; unregister_net_sysctl_table(cnet->sysctl_header); kfree(table); } #else static int nf_conntrack_standalone_init_sysctl(struct net *net) { return 0; } static void nf_conntrack_standalone_fini_sysctl(struct net *net) { } #endif /* CONFIG_SYSCTL */ static void nf_conntrack_fini_net(struct net *net) { if (enable_hooks) nf_ct_netns_put(net, NFPROTO_INET); nf_conntrack_standalone_fini_proc(net); nf_conntrack_standalone_fini_sysctl(net); } static int nf_conntrack_pernet_init(struct net *net) { int ret; net->ct.sysctl_checksum = 1; ret = nf_conntrack_standalone_init_sysctl(net); if (ret < 0) return ret; ret = nf_conntrack_standalone_init_proc(net); if (ret < 0) goto out_proc; ret = nf_conntrack_init_net(net); if (ret < 0) goto out_init_net; if (enable_hooks) { ret = nf_ct_netns_get(net, NFPROTO_INET); if (ret < 0) goto out_hooks; } return 0; out_hooks: nf_conntrack_cleanup_net(net); out_init_net: nf_conntrack_standalone_fini_proc(net); out_proc: nf_conntrack_standalone_fini_sysctl(net); return ret; } static void nf_conntrack_pernet_exit(struct list_head *net_exit_list) { struct net *net; list_for_each_entry(net, net_exit_list, exit_list) nf_conntrack_fini_net(net); nf_conntrack_cleanup_net_list(net_exit_list); } static struct pernet_operations nf_conntrack_net_ops = { .init = nf_conntrack_pernet_init, .exit_batch = nf_conntrack_pernet_exit, .id = &nf_conntrack_net_id, .size = sizeof(struct nf_conntrack_net), }; static int __init nf_conntrack_standalone_init(void) { int ret = nf_conntrack_init_start(); if (ret < 0) goto out_start; BUILD_BUG_ON(NFCT_INFOMASK <= IP_CT_NUMBER); #ifdef CONFIG_SYSCTL nf_ct_netfilter_header = register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); if (!nf_ct_netfilter_header) { pr_err("nf_conntrack: can't register to sysctl.\n"); ret = -ENOMEM; goto out_sysctl; } nf_conntrack_htable_size_user = nf_conntrack_htable_size; #endif nf_conntrack_init_end(); ret = register_pernet_subsys(&nf_conntrack_net_ops); if (ret < 0) goto out_pernet; return 0; out_pernet: #ifdef CONFIG_SYSCTL unregister_net_sysctl_table(nf_ct_netfilter_header); out_sysctl: #endif nf_conntrack_cleanup_end(); out_start: return ret; } static void __exit nf_conntrack_standalone_fini(void) { nf_conntrack_cleanup_start(); unregister_pernet_subsys(&nf_conntrack_net_ops); #ifdef CONFIG_SYSCTL unregister_net_sysctl_table(nf_ct_netfilter_header); #endif nf_conntrack_cleanup_end(); } module_init(nf_conntrack_standalone_init); module_exit(nf_conntrack_standalone_fini); |
| 7 3 2 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "../fs/internal.h" #include "io_uring.h" #include "statx.h" struct io_statx { struct file *file; int dfd; unsigned int mask; unsigned int flags; struct delayed_filename filename; struct statx __user *buffer; }; int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_statx *sx = io_kiocb_to_cmd(req, struct io_statx); const char __user *path; int ret; if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (req->flags & REQ_F_FIXED_FILE) return -EBADF; sx->dfd = READ_ONCE(sqe->fd); sx->mask = READ_ONCE(sqe->len); path = u64_to_user_ptr(READ_ONCE(sqe->addr)); sx->buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2)); sx->flags = READ_ONCE(sqe->statx_flags); ret = delayed_getname_uflags(&sx->filename, path, sx->flags); if (unlikely(ret)) return ret; req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_statx(struct io_kiocb *req, unsigned int issue_flags) { struct io_statx *sx = io_kiocb_to_cmd(req, struct io_statx); CLASS(filename_complete_delayed, name)(&sx->filename); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = do_statx(sx->dfd, name, sx->flags, sx->mask, sx->buffer); io_req_set_res(req, ret, 0); return IOU_COMPLETE; } void io_statx_cleanup(struct io_kiocb *req) { struct io_statx *sx = io_kiocb_to_cmd(req, struct io_statx); dismiss_delayed_filename(&sx->filename); } |
| 6 9 8 73 32 73 73 73 59 10 14 68 6 34 104 42 4 2 2 4 1 3 4 46 2 3 3 18 169 7 7 126 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_PKT_CLS_H #define __NET_PKT_CLS_H #include <linux/pkt_cls.h> #include <linux/workqueue.h> #include <net/sch_generic.h> #include <net/act_api.h> #include <net/net_namespace.h> /* TC action not accessible from user space */ #define TC_ACT_CONSUMED (TC_ACT_VALUE_MAX + 1) /* Basic packet classifier frontend definitions. */ struct tcf_walker { int stop; int skip; int count; bool nonempty; unsigned long cookie; int (*fn)(struct tcf_proto *, void *node, struct tcf_walker *); }; int register_tcf_proto_ops(struct tcf_proto_ops *ops); void unregister_tcf_proto_ops(struct tcf_proto_ops *ops); #define NET_CLS_ALIAS_PREFIX "net-cls-" #define MODULE_ALIAS_NET_CLS(kind) MODULE_ALIAS(NET_CLS_ALIAS_PREFIX kind) struct tcf_block_ext_info { enum flow_block_binder_type binder_type; tcf_chain_head_change_t *chain_head_change; void *chain_head_change_priv; u32 block_index; }; struct tcf_qevent { struct tcf_block *block; struct tcf_block_ext_info info; struct tcf_proto __rcu *filter_chain; }; struct tcf_block_cb; bool tcf_queue_work(struct rcu_work *rwork, work_func_t func); #ifdef CONFIG_NET_CLS struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index); void tcf_chain_put_by_act(struct tcf_chain *chain); struct tcf_chain *tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain); struct tcf_proto *tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp); void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, struct netlink_ext_ack *extack); int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack); void tcf_block_put(struct tcf_block *block); void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei); int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action, int police, struct tcf_proto *tp, u32 handle, bool used_action_miss); static inline bool tcf_block_shared(struct tcf_block *block) { return block->index; } static inline bool tcf_block_non_null_shared(struct tcf_block *block) { return block && block->index; } #ifdef CONFIG_NET_CLS_ACT DECLARE_STATIC_KEY_FALSE(tcf_sw_enabled_key); static inline bool tcf_block_bypass_sw(struct tcf_block *block) { return block && !atomic_read(&block->useswcnt); } #endif static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { WARN_ON(tcf_block_shared(block)); return block->q; } int tcf_classify(struct sk_buff *skb, const struct tcf_block *block, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); static inline bool tc_cls_stats_dump(struct tcf_proto *tp, struct tcf_walker *arg, void *filter) { if (arg->count >= arg->skip && arg->fn(tp, filter, arg) < 0) { arg->stop = 1; return false; } arg->count++; return true; } #else static inline bool tcf_block_shared(struct tcf_block *block) { return false; } static inline bool tcf_block_non_null_shared(struct tcf_block *block) { return false; } static inline int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, struct netlink_ext_ack *extack) { return 0; } static inline int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) { return 0; } static inline void tcf_block_put(struct tcf_block *block) { } static inline void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, struct tcf_block_ext_info *ei) { } static inline struct Qdisc *tcf_block_q(struct tcf_block *block) { return NULL; } static inline int tcf_classify(struct sk_buff *skb, const struct tcf_block *block, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { return TC_ACT_UNSPEC; } #endif static inline unsigned long __cls_set_class(unsigned long *clp, unsigned long cl) { return xchg(clp, cl); } static inline void __tcf_bind_filter(struct Qdisc *q, struct tcf_result *r, unsigned long base) { unsigned long cl; cl = q->ops->cl_ops->bind_tcf(q, base, r->classid); cl = __cls_set_class(&r->class, cl); if (cl) q->ops->cl_ops->unbind_tcf(q, cl); } static inline void tcf_bind_filter(struct tcf_proto *tp, struct tcf_result *r, unsigned long base) { struct Qdisc *q = tp->chain->block->q; /* Check q as it is not set for shared blocks. In that case, * setting class is not supported. */ if (!q) return; sch_tree_lock(q); __tcf_bind_filter(q, r, base); sch_tree_unlock(q); } static inline void __tcf_unbind_filter(struct Qdisc *q, struct tcf_result *r) { unsigned long cl; if ((cl = __cls_set_class(&r->class, 0)) != 0) q->ops->cl_ops->unbind_tcf(q, cl); } static inline void tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) { struct Qdisc *q = tp->chain->block->q; if (!q) return; __tcf_unbind_filter(q, r); } static inline void tc_cls_bind_class(u32 classid, unsigned long cl, void *q, struct tcf_result *res, unsigned long base) { if (res->classid == classid) { if (cl) __tcf_bind_filter(q, res, base); else __tcf_unbind_filter(q, res); } } struct tcf_exts { #ifdef CONFIG_NET_CLS_ACT __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ int nr_actions; struct tc_action **actions; struct net *net; netns_tracker ns_tracker; struct tcf_exts_miss_cookie_node *miss_cookie_node; #endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. */ int action; int police; }; static inline int tcf_exts_init(struct tcf_exts *exts, struct net *net, int action, int police) { #ifdef CONFIG_NET_CLS return tcf_exts_init_ex(exts, net, action, police, NULL, 0, false); #else return -EOPNOTSUPP; #endif } /* Return false if the netns is being destroyed in cleanup_net(). Callers * need to do cleanup synchronously in this case, otherwise may race with * tc_action_net_exit(). Return true for other cases. */ static inline bool tcf_exts_get_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT exts->net = maybe_get_net(exts->net); if (exts->net) netns_tracker_alloc(exts->net, &exts->ns_tracker, GFP_KERNEL); return exts->net != NULL; #else return true; #endif } static inline void tcf_exts_put_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT if (exts->net) put_net_track(exts->net, &exts->ns_tracker); #endif } #ifdef CONFIG_NET_CLS_ACT #define tcf_exts_for_each_action(i, a, exts) \ for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = (exts)->actions[i]); i++) #else #define tcf_exts_for_each_action(i, a, exts) \ for (; 0; (void)(i), (void)(a), (void)(exts)) #endif #define tcf_act_for_each_action(i, a, actions) \ for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = actions[i]); i++) static inline bool tc_act_in_hw(struct tc_action *act) { return !!act->in_hw_count; } static inline void tcf_exts_hw_stats_update(const struct tcf_exts *exts, struct flow_stats *stats, bool use_act_stats) { #ifdef CONFIG_NET_CLS_ACT int i; for (i = 0; i < exts->nr_actions; i++) { struct tc_action *a = exts->actions[i]; if (use_act_stats || tc_act_in_hw(a)) { if (!tcf_action_update_hw_stats(a)) continue; } preempt_disable(); tcf_action_stats_update(a, stats->bytes, stats->pkts, stats->drops, stats->lastused, true); preempt_enable(); a->used_hw_stats = stats->used_hw_stats; a->used_hw_stats_valid = stats->used_hw_stats_valid; } #endif } /** * tcf_exts_has_actions - check if at least one action is present * @exts: tc filter extensions handle * * Returns: true if at least one action is present. */ static inline bool tcf_exts_has_actions(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT return exts->nr_actions; #else return false; #endif } /** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer * @exts: tc filter extensions handle * @res: desired result * * Executes all configured extensions. Returns TC_ACT_OK on a normal execution, * a negative number if the filter must be considered unmatched or * a positive action code (TC_ACT_*) which must be returned to the * underlying layer. */ static inline int tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, struct tcf_result *res) { #ifdef CONFIG_NET_CLS_ACT return tcf_action_exec(skb, exts->actions, exts->nr_actions, res); #endif return TC_ACT_OK; } static inline int tcf_exts_exec_ex(struct sk_buff *skb, struct tcf_exts *exts, int act_index, struct tcf_result *res) { #ifdef CONFIG_NET_CLS_ACT return tcf_action_exec(skb, exts->actions + act_index, exts->nr_actions - act_index, res); #else return TC_ACT_OK; #endif } int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags, struct netlink_ext_ack *extack); int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack); void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_terse_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); /** * struct tcf_pkt_info - packet information * * @ptr: start of the pkt data * @nexthdr: offset of the next header */ struct tcf_pkt_info { unsigned char * ptr; int nexthdr; }; #ifdef CONFIG_NET_EMATCH struct tcf_ematch_ops; /** * struct tcf_ematch - extended match (ematch) * * @matchid: identifier to allow userspace to reidentify a match * @flags: flags specifying attributes and the relation to other matches * @ops: the operations lookup table of the corresponding ematch module * @datalen: length of the ematch specific configuration data * @data: ematch specific data * @net: the network namespace */ struct tcf_ematch { struct tcf_ematch_ops * ops; unsigned long data; unsigned int datalen; u16 matchid; u16 flags; struct net *net; }; static inline int tcf_em_is_container(struct tcf_ematch *em) { return !em->ops; } static inline int tcf_em_is_simple(struct tcf_ematch *em) { return em->flags & TCF_EM_SIMPLE; } static inline int tcf_em_is_inverted(struct tcf_ematch *em) { return em->flags & TCF_EM_INVERT; } static inline int tcf_em_last_match(struct tcf_ematch *em) { return (em->flags & TCF_EM_REL_MASK) == TCF_EM_REL_END; } static inline int tcf_em_early_end(struct tcf_ematch *em, int result) { if (tcf_em_last_match(em)) return 1; if (result == 0 && em->flags & TCF_EM_REL_AND) return 1; if (result != 0 && em->flags & TCF_EM_REL_OR) return 1; return 0; } /** * struct tcf_ematch_tree - ematch tree handle * * @hdr: ematch tree header supplied by userspace * @matches: array of ematches */ struct tcf_ematch_tree { struct tcf_ematch_tree_hdr hdr; struct tcf_ematch * matches; }; /** * struct tcf_ematch_ops - ematch module operations * * @kind: identifier (kind) of this ematch module * @datalen: length of expected configuration data (optional) * @change: called during validation (optional) * @match: called during ematch tree evaluation, must return 1/0 * @destroy: called during destroyage (optional) * @dump: called during dumping process (optional) * @owner: owner, must be set to THIS_MODULE * @link: link to previous/next ematch module (internal use) */ struct tcf_ematch_ops { int kind; int datalen; int (*change)(struct net *net, void *, int, struct tcf_ematch *); int (*match)(struct sk_buff *, struct tcf_ematch *, struct tcf_pkt_info *); void (*destroy)(struct tcf_ematch *); int (*dump)(struct sk_buff *, struct tcf_ematch *); struct module *owner; struct list_head link; }; int tcf_em_register(struct tcf_ematch_ops *); void tcf_em_unregister(struct tcf_ematch_ops *); int tcf_em_tree_validate(struct tcf_proto *, struct nlattr *, struct tcf_ematch_tree *); void tcf_em_tree_destroy(struct tcf_ematch_tree *); int tcf_em_tree_dump(struct sk_buff *, struct tcf_ematch_tree *, int); int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** * tcf_em_tree_match - evaluate an ematch tree * * @skb: socket buffer of the packet in question * @tree: ematch tree to be used for evaluation * @info: packet information examined by classifier * * This function matches @skb against the ematch tree in @tree by going * through all ematches respecting their logic relations returning * as soon as the result is obvious. * * Returns: 1 if the ematch tree as-one matches, no ematches are configured * or ematch is not enabled in the kernel, otherwise 0 is returned. */ static inline int tcf_em_tree_match(struct sk_buff *skb, struct tcf_ematch_tree *tree, struct tcf_pkt_info *info) { if (tree->hdr.nmatches) return __tcf_em_tree_match(skb, tree, info); else return 1; } #define MODULE_ALIAS_TCF_EMATCH(kind) MODULE_ALIAS("ematch-kind-" __stringify(kind)) #else /* CONFIG_NET_EMATCH */ struct tcf_ematch_tree { }; #define tcf_em_tree_validate(tp, tb, t) ((void)(t), 0) #define tcf_em_tree_destroy(t) do { (void)(t); } while(0) #define tcf_em_tree_dump(skb, t, tlv) (0) #define tcf_em_tree_match(skb, t, info) ((void)(info), 1) #endif /* CONFIG_NET_EMATCH */ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) { switch (layer) { case TCF_LAYER_LINK: return skb_mac_header(skb); case TCF_LAYER_NETWORK: return skb_network_header(skb); case TCF_LAYER_TRANSPORT: if (!skb_transport_header_was_set(skb)) break; return skb_transport_header(skb); } return NULL; } static inline int tcf_valid_offset(const struct sk_buff *skb, const unsigned char *ptr, const int len) { return likely((ptr + len) <= skb_tail_pointer(skb) && ptr >= skb->head && (ptr <= (ptr + len))); } static inline int tcf_change_indev(struct net *net, struct nlattr *indev_tlv, struct netlink_ext_ack *extack) { char indev[IFNAMSIZ]; struct net_device *dev; if (nla_strscpy(indev, indev_tlv, IFNAMSIZ) < 0) { NL_SET_ERR_MSG_ATTR(extack, indev_tlv, "Interface name too long"); return -EINVAL; } dev = __dev_get_by_name(net, indev); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, indev_tlv, "Network device not found"); return -ENODEV; } return dev->ifindex; } static inline bool tcf_match_indev(struct sk_buff *skb, int ifindex) { if (!ifindex) return true; if (!skb->skb_iif) return false; return ifindex == skb->skb_iif; } int tc_setup_offload_action(struct flow_action *flow_action, const struct tcf_exts *exts, struct netlink_ext_ack *extack); void tc_cleanup_offload_action(struct flow_action *flow_action); int tc_setup_action(struct flow_action *flow_action, struct tc_action *actions[], u32 miss_cookie_base, struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop, bool rtnl_held); int tc_setup_cb_add(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *flags, unsigned int *in_hw_count, bool rtnl_held); int tc_setup_cb_replace(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *old_flags, unsigned int *old_in_hw_count, u32 *new_flags, unsigned int *new_in_hw_count, bool rtnl_held); int tc_setup_cb_destroy(struct tcf_block *block, struct tcf_proto *tp, enum tc_setup_type type, void *type_data, bool err_stop, u32 *flags, unsigned int *in_hw_count, bool rtnl_held); int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, enum tc_setup_type type, void *type_data, void *cb_priv, u32 *flags, unsigned int *in_hw_count); unsigned int tcf_exts_num_actions(struct tcf_exts *exts); #ifdef CONFIG_NET_CLS_ACT int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, enum flow_block_binder_type binder_type, struct nlattr *block_index_attr, struct netlink_ext_ack *extack); void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch); int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, struct netlink_ext_ack *extack); struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, struct sk_buff **to_free, int *ret); int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe); #else static inline int tcf_qevent_init(struct tcf_qevent *qe, struct Qdisc *sch, enum flow_block_binder_type binder_type, struct nlattr *block_index_attr, struct netlink_ext_ack *extack) { return 0; } static inline void tcf_qevent_destroy(struct tcf_qevent *qe, struct Qdisc *sch) { } static inline int tcf_qevent_validate_change(struct tcf_qevent *qe, struct nlattr *block_index_attr, struct netlink_ext_ack *extack) { return 0; } static inline struct sk_buff * tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struct sk_buff *skb, struct sk_buff **to_free, int *ret) { return skb; } static inline int tcf_qevent_dump(struct sk_buff *skb, int attr_name, struct tcf_qevent *qe) { return 0; } #endif struct tc_cls_u32_knode { struct tcf_exts *exts; struct tcf_result *res; struct tc_u32_sel *sel; u32 handle; u32 val; u32 mask; u32 link_handle; u8 fshift; }; struct tc_cls_u32_hnode { u32 handle; u32 prio; unsigned int divisor; }; enum tc_clsu32_command { TC_CLSU32_NEW_KNODE, TC_CLSU32_REPLACE_KNODE, TC_CLSU32_DELETE_KNODE, TC_CLSU32_NEW_HNODE, TC_CLSU32_REPLACE_HNODE, TC_CLSU32_DELETE_HNODE, }; struct tc_cls_u32_offload { struct flow_cls_common_offload common; /* knode values */ enum tc_clsu32_command command; union { struct tc_cls_u32_knode knode; struct tc_cls_u32_hnode hnode; }; }; static inline bool tc_can_offload(const struct net_device *dev) { return dev->features & NETIF_F_HW_TC; } static inline bool tc_can_offload_extack(const struct net_device *dev, struct netlink_ext_ack *extack) { bool can = tc_can_offload(dev); if (!can) NL_SET_ERR_MSG(extack, "TC offload is disabled on net device"); return can; } static inline bool tc_cls_can_offload_and_chain0(const struct net_device *dev, struct flow_cls_common_offload *common) { if (!tc_can_offload_extack(dev, common->extack)) return false; if (common->chain_index) { NL_SET_ERR_MSG(common->extack, "Driver supports only offload of chain 0"); return false; } return true; } static inline bool tc_skip_hw(u32 flags) { return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false; } static inline bool tc_skip_sw(u32 flags) { return (flags & TCA_CLS_FLAGS_SKIP_SW) ? true : false; } /* SKIP_HW and SKIP_SW are mutually exclusive flags. */ static inline bool tc_flags_valid(u32 flags) { if (flags & ~(TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW | TCA_CLS_FLAGS_VERBOSE)) return false; flags &= TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW; if (!(flags ^ (TCA_CLS_FLAGS_SKIP_HW | TCA_CLS_FLAGS_SKIP_SW))) return false; return true; } static inline bool tc_in_hw(u32 flags) { return (flags & TCA_CLS_FLAGS_IN_HW) ? true : false; } static inline void tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common, const struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { cls_common->chain_index = tp->chain->index; cls_common->protocol = tp->protocol; cls_common->prio = tp->prio >> 16; cls_common->skip_sw = tc_skip_sw(flags); if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE) cls_common->extack = extack; } static inline void tcf_proto_update_usesw(struct tcf_proto *tp, u32 flags) { if (tp->usesw) return; if (tc_skip_sw(flags) && tc_in_hw(flags)) return; tp->usesw = true; } #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) static inline struct tc_skb_ext *tc_skb_ext_alloc(struct sk_buff *skb) { struct tc_skb_ext *tc_skb_ext = skb_ext_add(skb, TC_SKB_EXT); if (tc_skb_ext) memset(tc_skb_ext, 0, sizeof(*tc_skb_ext)); return tc_skb_ext; } #endif enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, TC_CLSMATCHALL_STATS, }; struct tc_cls_matchall_offload { struct flow_cls_common_offload common; enum tc_matchall_command command; struct flow_rule *rule; struct flow_stats stats; bool use_act_stats; unsigned long cookie; }; enum tc_clsbpf_command { TC_CLSBPF_OFFLOAD, TC_CLSBPF_STATS, }; struct tc_cls_bpf_offload { struct flow_cls_common_offload common; enum tc_clsbpf_command command; struct tcf_exts *exts; struct bpf_prog *prog; struct bpf_prog *oldprog; const char *name; bool exts_integrated; }; /* This structure holds cookie structure that is passed from user * to the kernel for actions and classifiers */ struct tc_cookie { u8 *data; u32 len; struct rcu_head rcu; }; struct tc_qopt_offload_stats { struct gnet_stats_basic_sync *bstats; struct gnet_stats_queue *qstats; }; enum tc_mq_command { TC_MQ_CREATE, TC_MQ_DESTROY, TC_MQ_STATS, TC_MQ_GRAFT, }; struct tc_mq_opt_offload_graft_params { unsigned long queue; u32 child_handle; }; struct tc_mq_qopt_offload { enum tc_mq_command command; u32 handle; union { struct tc_qopt_offload_stats stats; struct tc_mq_opt_offload_graft_params graft_params; }; }; enum tc_htb_command { /* Root */ TC_HTB_CREATE, /* Initialize HTB offload. */ TC_HTB_DESTROY, /* Destroy HTB offload. */ /* Classes */ /* Allocate qid and create leaf. */ TC_HTB_LEAF_ALLOC_QUEUE, /* Convert leaf to inner, preserve and return qid, create new leaf. */ TC_HTB_LEAF_TO_INNER, /* Delete leaf, while siblings remain. */ TC_HTB_LEAF_DEL, /* Delete leaf, convert parent to leaf, preserving qid. */ TC_HTB_LEAF_DEL_LAST, /* TC_HTB_LEAF_DEL_LAST, but delete driver data on hardware errors. */ TC_HTB_LEAF_DEL_LAST_FORCE, /* Modify parameters of a node. */ TC_HTB_NODE_MODIFY, /* Class qdisc */ TC_HTB_LEAF_QUERY_QUEUE, /* Query qid by classid. */ }; struct tc_htb_qopt_offload { struct netlink_ext_ack *extack; enum tc_htb_command command; u32 parent_classid; u16 classid; u16 qid; u32 quantum; u64 rate; u64 ceil; u8 prio; }; #define TC_HTB_CLASSID_ROOT U32_MAX enum tc_red_command { TC_RED_REPLACE, TC_RED_DESTROY, TC_RED_STATS, TC_RED_XSTATS, TC_RED_GRAFT, }; struct tc_red_qopt_offload_params { u32 min; u32 max; u32 probability; u32 limit; bool is_ecn; bool is_harddrop; bool is_nodrop; struct gnet_stats_queue *qstats; }; struct tc_red_qopt_offload { enum tc_red_command command; u32 handle; u32 parent; union { struct tc_red_qopt_offload_params set; struct tc_qopt_offload_stats stats; struct red_stats *xstats; u32 child_handle; }; }; enum tc_gred_command { TC_GRED_REPLACE, TC_GRED_DESTROY, TC_GRED_STATS, }; struct tc_gred_vq_qopt_offload_params { bool present; u32 limit; u32 prio; u32 min; u32 max; bool is_ecn; bool is_harddrop; u32 probability; /* Only need backlog, see struct tc_prio_qopt_offload_params */ u32 *backlog; }; struct tc_gred_qopt_offload_params { bool grio_on; bool wred_on; unsigned int dp_cnt; unsigned int dp_def; struct gnet_stats_queue *qstats; struct tc_gred_vq_qopt_offload_params tab[MAX_DPs]; }; struct tc_gred_qopt_offload_stats { struct gnet_stats_basic_sync bstats[MAX_DPs]; struct gnet_stats_queue qstats[MAX_DPs]; struct red_stats *xstats[MAX_DPs]; }; struct tc_gred_qopt_offload { enum tc_gred_command command; u32 handle; u32 parent; union { struct tc_gred_qopt_offload_params set; struct tc_gred_qopt_offload_stats stats; }; }; enum tc_prio_command { TC_PRIO_REPLACE, TC_PRIO_DESTROY, TC_PRIO_STATS, TC_PRIO_GRAFT, }; struct tc_prio_qopt_offload_params { int bands; u8 priomap[TC_PRIO_MAX + 1]; /* At the point of un-offloading the Qdisc, the reported backlog and * qlen need to be reduced by the portion that is in HW. */ struct gnet_stats_queue *qstats; }; struct tc_prio_qopt_offload_graft_params { u8 band; u32 child_handle; }; struct tc_prio_qopt_offload { enum tc_prio_command command; u32 handle; u32 parent; union { struct tc_prio_qopt_offload_params replace_params; struct tc_qopt_offload_stats stats; struct tc_prio_qopt_offload_graft_params graft_params; }; }; enum tc_root_command { TC_ROOT_GRAFT, }; struct tc_root_qopt_offload { enum tc_root_command command; u32 handle; bool ingress; }; enum tc_ets_command { TC_ETS_REPLACE, TC_ETS_DESTROY, TC_ETS_STATS, TC_ETS_GRAFT, }; struct tc_ets_qopt_offload_replace_params { unsigned int bands; u8 priomap[TC_PRIO_MAX + 1]; unsigned int quanta[TCQ_ETS_MAX_BANDS]; /* 0 for strict bands. */ unsigned int weights[TCQ_ETS_MAX_BANDS]; struct gnet_stats_queue *qstats; }; struct tc_ets_qopt_offload_graft_params { u8 band; u32 child_handle; }; struct tc_ets_qopt_offload { enum tc_ets_command command; u32 handle; u32 parent; union { struct tc_ets_qopt_offload_replace_params replace_params; struct tc_qopt_offload_stats stats; struct tc_ets_qopt_offload_graft_params graft_params; }; }; enum tc_tbf_command { TC_TBF_REPLACE, TC_TBF_DESTROY, TC_TBF_STATS, TC_TBF_GRAFT, }; struct tc_tbf_qopt_offload_replace_params { struct psched_ratecfg rate; u32 max_size; struct gnet_stats_queue *qstats; }; struct tc_tbf_qopt_offload { enum tc_tbf_command command; u32 handle; u32 parent; union { struct tc_tbf_qopt_offload_replace_params replace_params; struct tc_qopt_offload_stats stats; u32 child_handle; }; }; enum tc_fifo_command { TC_FIFO_REPLACE, TC_FIFO_DESTROY, TC_FIFO_STATS, }; struct tc_fifo_qopt_offload { enum tc_fifo_command command; u32 handle; u32 parent; union { struct tc_qopt_offload_stats stats; }; }; #ifdef CONFIG_NET_CLS_ACT DECLARE_STATIC_KEY_FALSE(tc_skb_ext_tc); void tc_skb_ext_tc_enable(void); void tc_skb_ext_tc_disable(void); #define tc_skb_ext_tc_enabled() static_branch_unlikely(&tc_skb_ext_tc) #else /* CONFIG_NET_CLS_ACT */ static inline void tc_skb_ext_tc_enable(void) { } static inline void tc_skb_ext_tc_disable(void) { } #define tc_skb_ext_tc_enabled() false #endif #endif |
| 251 3 3 158 18 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 | /* 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. * * Authors: Lotsa people, from code originally in tcp */ #ifndef _INET6_HASHTABLES_H #define _INET6_HASHTABLES_H #if IS_ENABLED(CONFIG_IPV6) #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/types.h> #include <linux/jhash.h> #include <net/inet_sock.h> #include <net/ipv6.h> #include <net/netns/hash.h> struct inet_hashinfo; void inet6_init_ehash_secret(void); static inline unsigned int __inet6_ehashfn(const u32 lhash, const u16 lport, const u32 fhash, const __be16 fport, const u32 initval) { const u32 ports = (((u32)lport) << 16) | (__force u32)fport; return jhash_3words(lhash, fhash, ports, initval); } /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM * * The sockhash lock must be held as a reader here. */ struct sock *__inet6_lookup_established(const struct net *net, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif); typedef u32 (inet6_ehashfn_t)(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport); inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, inet6_ehashfn_t *ehashfn); struct sock *inet6_lookup_listener(const struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif); struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); static inline struct sock *__inet6_lookup(const struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif, bool *refcounted) { struct sock *sk = __inet6_lookup_established(net, saddr, sport, daddr, hnum, dif, sdif); *refcounted = true; if (sk) return sk; *refcounted = false; return inet6_lookup_listener(net, skb, doff, saddr, sport, daddr, hnum, dif, sdif); } static inline struct sock *inet6_steal_sock(struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, bool *refcounted, inet6_ehashfn_t *ehashfn) { struct sock *sk, *reuse_sk; bool prefetched; sk = skb_steal_sock(skb, refcounted, &prefetched); if (!sk) return NULL; if (!prefetched || !sk_fullsock(sk)) return sk; if (sk->sk_protocol == IPPROTO_TCP) { if (sk->sk_state != TCP_LISTEN) return sk; } else if (sk->sk_protocol == IPPROTO_UDP) { if (sk->sk_state != TCP_CLOSE) return sk; } else { return sk; } reuse_sk = inet6_lookup_reuseport(net, sk, skb, doff, saddr, sport, daddr, ntohs(dport), ehashfn); if (!reuse_sk) return sk; /* We've chosen a new reuseport sock which is never refcounted. This * implies that sk also isn't refcounted. */ WARN_ON_ONCE(*refcounted); return reuse_sk; } static inline struct sock *__inet6_lookup_skb(struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, int iif, int sdif, bool *refcounted) { struct net *net = skb_dst_dev_net_rcu(skb); const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct sock *sk; sk = inet6_steal_sock(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, dport, refcounted, inet6_ehashfn); if (IS_ERR(sk)) return NULL; if (sk) return sk; return __inet6_lookup(net, skb, doff, &ip6h->saddr, sport, &ip6h->daddr, ntohs(dport), iif, sdif, refcounted); } struct sock *inet6_lookup(const struct net *net, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif); static inline bool inet6_match(const struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, const int dif, const int sdif) { if (!net_eq(sock_net(sk), net) || sk->sk_family != AF_INET6 || READ_ONCE(sk->sk_portpair) != ports || !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return false; /* READ_ONCE() paired with WRITE_ONCE() in sock_bindtoindex_locked() */ return inet_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif); } #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _INET6_HASHTABLES_H */ |
| 4 4 4 4 1 3 4 1 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * BlueZ - Bluetooth protocol stack for Linux * * Copyright (C) 2022 Intel Corporation * Copyright 2023-2024 NXP */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/sched/signal.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/iso.h> #include "eir.h" static const struct proto_ops iso_sock_ops; static struct bt_sock_list iso_sk_list = { .lock = __RW_LOCK_UNLOCKED(iso_sk_list.lock) }; /* ---- ISO connections ---- */ struct iso_conn { struct hci_conn *hcon; /* @lock: spinlock protecting changes to iso_conn fields */ spinlock_t lock; struct sock *sk; struct delayed_work timeout_work; struct sk_buff *rx_skb; __u32 rx_len; __u16 tx_sn; struct kref ref; }; #define iso_conn_lock(c) spin_lock(&(c)->lock) #define iso_conn_unlock(c) spin_unlock(&(c)->lock) static void iso_sock_close(struct sock *sk); static void iso_sock_kill(struct sock *sk); /* ----- ISO socket info ----- */ #define iso_pi(sk) ((struct iso_pinfo *)sk) #define EIR_SERVICE_DATA_LENGTH 4 #define BASE_MAX_LENGTH (HCI_MAX_PER_AD_LENGTH - EIR_SERVICE_DATA_LENGTH) #define EIR_BAA_SERVICE_UUID 0x1851 /* iso_pinfo flags values */ enum { BT_SK_BIG_SYNC, BT_SK_PA_SYNC, }; struct iso_pinfo { struct bt_sock bt; bdaddr_t src; __u8 src_type; bdaddr_t dst; __u8 dst_type; __u8 bc_sid; __u8 bc_num_bis; __u8 bc_bis[ISO_MAX_NUM_BIS]; __u16 sync_handle; unsigned long flags; struct bt_iso_qos qos; bool qos_user_set; __u8 base_len; __u8 base[BASE_MAX_LENGTH]; struct iso_conn *conn; }; static struct bt_iso_qos default_qos; static bool check_ucast_qos(struct bt_iso_qos *qos); static bool check_bcast_qos(struct bt_iso_qos *qos); static bool iso_match_sid(struct sock *sk, void *data); static bool iso_match_sid_past(struct sock *sk, void *data); static bool iso_match_sync_handle(struct sock *sk, void *data); static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data); static void iso_sock_disconn(struct sock *sk); typedef bool (*iso_sock_match_t)(struct sock *sk, void *data); static struct sock *iso_get_sock(struct hci_dev *hdev, bdaddr_t *src, bdaddr_t *dst, enum bt_sock_state state, iso_sock_match_t match, void *data); /* ---- ISO timers ---- */ #define ISO_CONN_TIMEOUT secs_to_jiffies(20) #define ISO_DISCONN_TIMEOUT secs_to_jiffies(2) static void iso_conn_free(struct kref *ref) { struct iso_conn *conn = container_of(ref, struct iso_conn, ref); BT_DBG("conn %p", conn); if (conn->sk) iso_pi(conn->sk)->conn = NULL; if (conn->hcon) { conn->hcon->iso_data = NULL; hci_conn_drop(conn->hcon); } /* Ensure no more work items will run since hci_conn has been dropped */ disable_delayed_work_sync(&conn->timeout_work); kfree_skb(conn->rx_skb); kfree(conn); } static void iso_conn_put(struct iso_conn *conn) { if (!conn) return; BT_DBG("conn %p refcnt %d", conn, kref_read(&conn->ref)); kref_put(&conn->ref, iso_conn_free); } static struct iso_conn *iso_conn_hold_unless_zero(struct iso_conn *conn) { if (!conn) return NULL; BT_DBG("conn %p refcnt %u", conn, kref_read(&conn->ref)); if (!kref_get_unless_zero(&conn->ref)) return NULL; return conn; } static struct sock *iso_sock_hold(struct iso_conn *conn) { if (!conn || !bt_sock_linked(&iso_sk_list, conn->sk)) return NULL; sock_hold(conn->sk); return conn->sk; } static void iso_sock_timeout(struct work_struct *work) { struct iso_conn *conn = container_of(work, struct iso_conn, timeout_work.work); struct sock *sk; conn = iso_conn_hold_unless_zero(conn); if (!conn) return; iso_conn_lock(conn); sk = iso_sock_hold(conn); iso_conn_unlock(conn); iso_conn_put(conn); if (!sk) return; BT_DBG("sock %p state %d", sk, sk->sk_state); lock_sock(sk); sk->sk_err = ETIMEDOUT; sk->sk_state_change(sk); release_sock(sk); sock_put(sk); } static void iso_sock_set_timer(struct sock *sk, long timeout) { if (!iso_pi(sk)->conn) return; BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); cancel_delayed_work(&iso_pi(sk)->conn->timeout_work); schedule_delayed_work(&iso_pi(sk)->conn->timeout_work, timeout); } static void iso_sock_clear_timer(struct sock *sk) { if (!iso_pi(sk)->conn) return; BT_DBG("sock %p state %d", sk, sk->sk_state); cancel_delayed_work(&iso_pi(sk)->conn->timeout_work); } /* ---- ISO connections ---- */ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) { struct iso_conn *conn = hcon->iso_data; conn = iso_conn_hold_unless_zero(conn); if (conn) { if (!conn->hcon) { iso_conn_lock(conn); conn->hcon = hcon; iso_conn_unlock(conn); } iso_conn_put(conn); return conn; } conn = kzalloc_obj(*conn); if (!conn) return NULL; kref_init(&conn->ref); spin_lock_init(&conn->lock); INIT_DELAYED_WORK(&conn->timeout_work, iso_sock_timeout); hcon->iso_data = conn; conn->hcon = hcon; conn->tx_sn = 0; BT_DBG("hcon %p conn %p", hcon, conn); return conn; } /* Delete channel. Must be called on the locked socket. */ static void iso_chan_del(struct sock *sk, int err) { struct iso_conn *conn; struct sock *parent; conn = iso_pi(sk)->conn; iso_pi(sk)->conn = NULL; BT_DBG("sk %p, conn %p, err %d", sk, conn, err); if (conn) { iso_conn_lock(conn); conn->sk = NULL; iso_conn_unlock(conn); iso_conn_put(conn); } sk->sk_state = BT_CLOSED; sk->sk_err = err; parent = bt_sk(sk)->parent; if (parent) { bt_accept_unlink(sk); parent->sk_data_ready(parent); } else { sk->sk_state_change(sk); } sock_set_flag(sk, SOCK_ZAPPED); } static void iso_conn_del(struct hci_conn *hcon, int err) { struct iso_conn *conn = hcon->iso_data; struct sock *sk; conn = iso_conn_hold_unless_zero(conn); if (!conn) return; BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); /* Kill socket */ iso_conn_lock(conn); sk = iso_sock_hold(conn); iso_conn_unlock(conn); iso_conn_put(conn); if (!sk) { iso_conn_put(conn); return; } lock_sock(sk); iso_sock_clear_timer(sk); iso_chan_del(sk, err); release_sock(sk); sock_put(sk); } static int __iso_chan_add(struct iso_conn *conn, struct sock *sk, struct sock *parent) { BT_DBG("conn %p", conn); if (iso_pi(sk)->conn == conn && conn->sk == sk) return 0; if (conn->sk) { BT_ERR("conn->sk already set"); return -EBUSY; } iso_pi(sk)->conn = conn; conn->sk = sk; if (parent) bt_accept_enqueue(parent, sk, true); return 0; } static int iso_chan_add(struct iso_conn *conn, struct sock *sk, struct sock *parent) { int err; iso_conn_lock(conn); err = __iso_chan_add(conn, sk, parent); iso_conn_unlock(conn); return err; } static inline u8 le_addr_type(u8 bdaddr_type) { if (bdaddr_type == BDADDR_LE_PUBLIC) return ADDR_LE_DEV_PUBLIC; else return ADDR_LE_DEV_RANDOM; } static int iso_connect_bis(struct sock *sk) { struct iso_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; bdaddr_t src, dst; u8 src_type, bc_sid; int err; lock_sock(sk); bacpy(&src, &iso_pi(sk)->src); bacpy(&dst, &iso_pi(sk)->dst); src_type = iso_pi(sk)->src_type; bc_sid = iso_pi(sk)->bc_sid; release_sock(sk); BT_DBG("%pMR (SID 0x%2.2x)", &src, bc_sid); hdev = hci_get_route(&dst, &src, src_type); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); lock_sock(sk); if (!bis_capable(hdev)) { err = -EOPNOTSUPP; goto unlock; } /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; err = -EINVAL; goto unlock; } /* Fail if out PHYs are marked as disabled */ if (!iso_pi(sk)->qos.bcast.out.phys) { err = -EINVAL; goto unlock; } /* Just bind if DEFER_SETUP has been set */ if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { hcon = hci_bind_bis(hdev, &iso_pi(sk)->dst, iso_pi(sk)->bc_sid, &iso_pi(sk)->qos, iso_pi(sk)->base_len, iso_pi(sk)->base, READ_ONCE(sk->sk_sndtimeo)); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } } else { hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), iso_pi(sk)->bc_sid, &iso_pi(sk)->qos, iso_pi(sk)->base_len, iso_pi(sk)->base, READ_ONCE(sk->sk_sndtimeo)); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } /* Update SID if it was not set */ if (iso_pi(sk)->bc_sid == HCI_SID_INVALID) iso_pi(sk)->bc_sid = hcon->sid; } conn = iso_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } err = iso_chan_add(conn, sk, NULL); if (err) goto unlock; /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); if (hcon->state == BT_CONNECTED) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; } else if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECT; } else { sk->sk_state = BT_CONNECT; iso_sock_set_timer(sk, READ_ONCE(sk->sk_sndtimeo)); } unlock: release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static int iso_connect_cis(struct sock *sk) { struct iso_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; bdaddr_t src, dst; u8 src_type; int err; lock_sock(sk); bacpy(&src, &iso_pi(sk)->src); bacpy(&dst, &iso_pi(sk)->dst); src_type = iso_pi(sk)->src_type; release_sock(sk); BT_DBG("%pMR -> %pMR", &src, &dst); hdev = hci_get_route(&dst, &src, src_type); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); lock_sock(sk); if (!cis_central_capable(hdev)) { err = -EOPNOTSUPP; goto unlock; } /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_ucast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; err = -EINVAL; goto unlock; } /* Fail if either PHYs are marked as disabled */ if (!iso_pi(sk)->qos.ucast.in.phys && !iso_pi(sk)->qos.ucast.out.phys) { err = -EINVAL; goto unlock; } /* Check if there are available buffers for output/TX. */ if (iso_pi(sk)->qos.ucast.out.sdu && !hci_iso_count(hdev) && (hdev->iso_pkts && !hdev->iso_cnt)) { err = -ENOBUFS; goto unlock; } /* Just bind if DEFER_SETUP has been set */ if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { hcon = hci_bind_cis(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), &iso_pi(sk)->qos, READ_ONCE(sk->sk_sndtimeo)); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } } else { hcon = hci_connect_cis(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), &iso_pi(sk)->qos, READ_ONCE(sk->sk_sndtimeo)); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } } conn = iso_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } err = iso_chan_add(conn, sk, NULL); if (err) goto unlock; /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); if (hcon->state == BT_CONNECTED) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; } else if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECT; } else { sk->sk_state = BT_CONNECT; iso_sock_set_timer(sk, READ_ONCE(sk->sk_sndtimeo)); } unlock: release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static struct bt_iso_qos *iso_sock_get_qos(struct sock *sk) { if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONNECT2) return &iso_pi(sk)->conn->hcon->iso_qos; return &iso_pi(sk)->qos; } static int iso_send_frame(struct sock *sk, struct sk_buff *skb, const struct sockcm_cookie *sockc) { struct iso_conn *conn = iso_pi(sk)->conn; struct bt_iso_qos *qos = iso_sock_get_qos(sk); struct hci_iso_data_hdr *hdr; int len = 0; BT_DBG("sk %p len %d", sk, skb->len); if (skb->len > qos->ucast.out.sdu) return -EMSGSIZE; len = skb->len; /* Push ISO data header */ hdr = skb_push(skb, HCI_ISO_DATA_HDR_SIZE); hdr->sn = cpu_to_le16(conn->tx_sn++); hdr->slen = cpu_to_le16(hci_iso_data_len_pack(len, HCI_ISO_STATUS_VALID)); if (sk->sk_state == BT_CONNECTED) { hci_setup_tx_timestamp(skb, 1, sockc); hci_send_iso(conn->hcon, skb); } else { len = -ENOTCONN; } return len; } static void iso_recv_frame(struct iso_conn *conn, struct sk_buff *skb) { struct sock *sk; iso_conn_lock(conn); sk = iso_sock_hold(conn); iso_conn_unlock(conn); if (!sk) goto drop; BT_DBG("sk %p len %d", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop_put; if (!sock_queue_rcv_skb(sk, skb)) { sock_put(sk); return; } drop_put: sock_put(sk); drop: kfree_skb(skb); } /* -------- Socket interface ---------- */ static struct sock *__iso_get_sock_listen_by_addr(bdaddr_t *src, bdaddr_t *dst) { struct sock *sk; sk_for_each(sk, &iso_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (bacmp(&iso_pi(sk)->dst, dst)) continue; if (!bacmp(&iso_pi(sk)->src, src)) return sk; } return NULL; } static struct sock *__iso_get_sock_listen_by_sid(bdaddr_t *ba, bdaddr_t *bc, __u8 sid) { struct sock *sk; sk_for_each(sk, &iso_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (bacmp(&iso_pi(sk)->src, ba)) continue; if (bacmp(&iso_pi(sk)->dst, bc)) continue; if (iso_pi(sk)->bc_sid == sid) return sk; } return NULL; } /* Find socket in given state: * source bdaddr (Unicast) * destination bdaddr (Broadcast only) * match func - pass NULL to ignore * match func data - pass -1 to ignore * Returns closest match. */ static struct sock *iso_get_sock(struct hci_dev *hdev, bdaddr_t *src, bdaddr_t *dst, enum bt_sock_state state, iso_sock_match_t match, void *data) { struct sock *sk = NULL, *sk1 = NULL; read_lock(&iso_sk_list.lock); sk_for_each(sk, &iso_sk_list.head) { if (sk->sk_state != state) continue; /* Match Broadcast destination */ if (bacmp(dst, BDADDR_ANY) && bacmp(&iso_pi(sk)->dst, dst)) { struct smp_irk *irk1, *irk2; /* Check if destination is an RPA that we can resolve */ irk1 = hci_find_irk_by_rpa(hdev, dst); if (!irk1) continue; /* Match with identity address */ if (bacmp(&iso_pi(sk)->dst, &irk1->bdaddr)) { /* Check if socket destination address is also * an RPA and if the IRK matches. */ irk2 = hci_find_irk_by_rpa(hdev, &iso_pi(sk)->dst); if (!irk2 || irk1 != irk2) continue; } } /* Use Match function if provided */ if (match && !match(sk, data)) continue; /* Exact match. */ if (!bacmp(&iso_pi(sk)->src, src)) { sock_hold(sk); break; } /* Closest match */ if (!bacmp(&iso_pi(sk)->src, BDADDR_ANY)) { if (sk1) sock_put(sk1); sk1 = sk; sock_hold(sk1); } } if (sk && sk1) sock_put(sk1); read_unlock(&iso_sk_list.lock); return sk ? sk : sk1; } static struct sock *iso_get_sock_big(struct sock *match_sk, bdaddr_t *src, bdaddr_t *dst, uint8_t big) { struct sock *sk = NULL; read_lock(&iso_sk_list.lock); sk_for_each(sk, &iso_sk_list.head) { if (match_sk == sk) continue; /* Look for sockets that have already been * connected to the BIG */ if (sk->sk_state != BT_CONNECTED && sk->sk_state != BT_CONNECT) continue; /* Match Broadcast destination */ if (bacmp(&iso_pi(sk)->dst, dst)) continue; /* Match BIG handle */ if (iso_pi(sk)->qos.bcast.big != big) continue; /* Match source address */ if (bacmp(&iso_pi(sk)->src, src)) continue; sock_hold(sk); break; } read_unlock(&iso_sk_list.lock); return sk; } static void iso_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); iso_conn_put(iso_pi(sk)->conn); skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&sk->sk_error_queue); } static void iso_sock_cleanup_listen(struct sock *parent) { struct sock *sk; BT_DBG("parent %p", parent); /* Close not yet accepted channels */ while ((sk = bt_accept_dequeue(parent, NULL))) { iso_sock_close(sk); iso_sock_kill(sk); /* Drop the reference handed back by bt_accept_dequeue(). */ sock_put(sk); } /* If listening socket has a hcon, properly disconnect it */ if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon) { iso_sock_disconn(parent); return; } parent->sk_state = BT_CLOSED; sock_set_flag(parent, SOCK_ZAPPED); } /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket. */ static void iso_sock_kill(struct sock *sk) { if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket || sock_flag(sk, SOCK_DEAD)) return; BT_DBG("sk %p state %d", sk, sk->sk_state); /* Sock is dead, so set conn->sk to NULL to avoid possible UAF */ if (iso_pi(sk)->conn) { iso_conn_lock(iso_pi(sk)->conn); iso_pi(sk)->conn->sk = NULL; iso_conn_unlock(iso_pi(sk)->conn); } /* Kill poor orphan */ bt_sock_unlink(&iso_sk_list, sk); sock_set_flag(sk, SOCK_DEAD); sock_put(sk); } static void iso_sock_disconn(struct sock *sk) { struct sock *bis_sk; struct hci_conn *hcon = iso_pi(sk)->conn->hcon; if (test_bit(HCI_CONN_BIG_CREATED, &hcon->flags)) { bis_sk = iso_get_sock_big(sk, &iso_pi(sk)->src, &iso_pi(sk)->dst, iso_pi(sk)->qos.bcast.big); /* If there are any other connected sockets for the * same BIG, just delete the sk and leave the bis * hcon active, in case later rebinding is needed. */ if (bis_sk) { hcon->state = BT_OPEN; hcon->iso_data = NULL; iso_pi(sk)->conn->hcon = NULL; iso_sock_clear_timer(sk); iso_chan_del(sk, bt_to_errno(hcon->abort_reason)); sock_put(bis_sk); return; } } sk->sk_state = BT_DISCONN; iso_conn_lock(iso_pi(sk)->conn); hci_conn_drop(iso_pi(sk)->conn->hcon); iso_pi(sk)->conn->hcon = NULL; iso_conn_unlock(iso_pi(sk)->conn); } static void __iso_sock_close(struct sock *sk) { BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); switch (sk->sk_state) { case BT_LISTEN: iso_sock_cleanup_listen(sk); break; case BT_CONNECT: case BT_CONNECTED: case BT_CONFIG: if (iso_pi(sk)->conn->hcon) iso_sock_disconn(sk); else iso_chan_del(sk, ECONNRESET); break; case BT_CONNECT2: if (iso_pi(sk)->conn->hcon && (test_bit(HCI_CONN_PA_SYNC, &iso_pi(sk)->conn->hcon->flags) || test_bit(HCI_CONN_PA_SYNC_FAILED, &iso_pi(sk)->conn->hcon->flags))) iso_sock_disconn(sk); else iso_chan_del(sk, ECONNRESET); break; case BT_DISCONN: iso_chan_del(sk, ECONNRESET); break; default: sock_set_flag(sk, SOCK_ZAPPED); break; } } /* Must be called on unlocked socket. */ static void iso_sock_close(struct sock *sk) { lock_sock(sk); iso_sock_clear_timer(sk); __iso_sock_close(sk); release_sock(sk); iso_sock_kill(sk); } static void iso_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); if (parent) { sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); } } static struct proto iso_proto = { .name = "ISO", .owner = THIS_MODULE, .obj_size = sizeof(struct iso_pinfo) }; #define DEFAULT_IO_QOS \ { \ .interval = 10000u, \ .latency = 10u, \ .sdu = 40u, \ .phys = BT_ISO_PHY_2M, \ .rtn = 2u, \ } static struct bt_iso_qos default_qos = { .bcast = { .big = BT_ISO_QOS_BIG_UNSET, .bis = BT_ISO_QOS_BIS_UNSET, .sync_factor = 0x01, .packing = 0x00, .framing = 0x00, .in = DEFAULT_IO_QOS, .out = DEFAULT_IO_QOS, .encryption = 0x00, .bcode = {0x00}, .options = 0x00, .skip = 0x0000, .sync_timeout = BT_ISO_SYNC_TIMEOUT, .sync_cte_type = 0x00, .mse = 0x00, .timeout = BT_ISO_SYNC_TIMEOUT, }, }; static struct sock *iso_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) { struct sock *sk; sk = bt_sock_alloc(net, sock, &iso_proto, proto, prio, kern); if (!sk) return NULL; sk->sk_destruct = iso_sock_destruct; sk->sk_sndtimeo = ISO_CONN_TIMEOUT; /* Set address type as public as default src address is BDADDR_ANY */ iso_pi(sk)->src_type = BDADDR_LE_PUBLIC; iso_pi(sk)->qos = default_qos; iso_pi(sk)->sync_handle = -1; bt_sock_link(&iso_sk_list, sk); return sk; } static int iso_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; BT_DBG("sock %p", sock); sock->state = SS_UNCONNECTED; if (sock->type != SOCK_SEQPACKET) return -ESOCKTNOSUPPORT; sock->ops = &iso_sock_ops; sk = iso_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; iso_sock_init(sk, NULL); return 0; } static int iso_sock_bind_bc(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; struct sock *sk = sock->sk; int i; BT_DBG("sk %p bc_sid %u bc_num_bis %u", sk, sa->iso_bc->bc_sid, sa->iso_bc->bc_num_bis); if (addr_len != sizeof(*sa) + sizeof(*sa->iso_bc)) return -EINVAL; bacpy(&iso_pi(sk)->dst, &sa->iso_bc->bc_bdaddr); /* Check if the address type is of LE type */ if (!bdaddr_type_is_le(sa->iso_bc->bc_bdaddr_type)) return -EINVAL; iso_pi(sk)->dst_type = sa->iso_bc->bc_bdaddr_type; if (sa->iso_bc->bc_sid > 0x0f && sa->iso_bc->bc_sid != HCI_SID_INVALID) return -EINVAL; iso_pi(sk)->bc_sid = sa->iso_bc->bc_sid; if (sa->iso_bc->bc_num_bis > ISO_MAX_NUM_BIS) return -EINVAL; iso_pi(sk)->bc_num_bis = sa->iso_bc->bc_num_bis; for (i = 0; i < iso_pi(sk)->bc_num_bis; i++) if (sa->iso_bc->bc_bis[i] < 0x01 || sa->iso_bc->bc_bis[i] > 0x1f) return -EINVAL; memcpy(iso_pi(sk)->bc_bis, sa->iso_bc->bc_bis, iso_pi(sk)->bc_num_bis); return 0; } /* Must be called on the locked socket. */ static int iso_sock_rebind_bis(struct sock *sk, struct sockaddr_iso *sa, int addr_len) { int err = 0; if (!test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) return -EBADFD; if (sa->iso_bc->bc_num_bis > ISO_MAX_NUM_BIS) { err = -EINVAL; goto done; } iso_pi(sk)->bc_num_bis = sa->iso_bc->bc_num_bis; for (int i = 0; i < iso_pi(sk)->bc_num_bis; i++) if (sa->iso_bc->bc_bis[i] < 0x01 || sa->iso_bc->bc_bis[i] > 0x1f) { err = -EINVAL; goto done; } memcpy(iso_pi(sk)->bc_bis, sa->iso_bc->bc_bis, iso_pi(sk)->bc_num_bis); done: return err; } static struct hci_dev *iso_conn_get_hdev(struct iso_conn *conn) { struct hci_dev *hdev = NULL; iso_conn_lock(conn); if (conn->hcon) hdev = hci_dev_hold(conn->hcon->hdev); iso_conn_unlock(conn); return hdev; } /* Must be called on the locked socket. */ static int iso_sock_rebind_bc(struct sock *sk, struct sockaddr_iso *sa, int addr_len) { struct hci_dev *hdev; struct hci_conn *bis; int err; if (sk->sk_type != SOCK_SEQPACKET || !iso_pi(sk)->conn) return -EINVAL; /* Check if it is really a Broadcast address being requested */ if (addr_len != sizeof(*sa) + sizeof(*sa->iso_bc)) return -EINVAL; /* Check if the address hasn't changed then perhaps only the number of * bis has changed. */ if (!bacmp(&iso_pi(sk)->dst, &sa->iso_bc->bc_bdaddr) || !bacmp(&sa->iso_bc->bc_bdaddr, BDADDR_ANY)) return iso_sock_rebind_bis(sk, sa, addr_len); /* Check if the address type is of LE type */ if (!bdaddr_type_is_le(sa->iso_bc->bc_bdaddr_type)) return -EINVAL; hdev = iso_conn_get_hdev(iso_pi(sk)->conn); if (!hdev) return -EINVAL; bis = iso_pi(sk)->conn->hcon; /* Release the socket before lookups since that requires hci_dev_lock * which shall not be acquired while holding sock_lock for proper * ordering. */ release_sock(sk); hci_dev_lock(hdev); lock_sock(sk); if (!iso_pi(sk)->conn || iso_pi(sk)->conn->hcon != bis) { /* raced with iso_conn_del() or iso_disconn_sock() */ err = -ENOTCONN; goto unlock; } BT_DBG("sk %p %pMR type %u", sk, &sa->iso_bc->bc_bdaddr, sa->iso_bc->bc_bdaddr_type); err = hci_past_bis(bis, &sa->iso_bc->bc_bdaddr, le_addr_type(sa->iso_bc->bc_bdaddr_type)); unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static int iso_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; struct sock *sk = sock->sk; int err = 0; BT_DBG("sk %p %pMR type %u", sk, &sa->iso_bdaddr, sa->iso_bdaddr_type); if (!addr || addr_len < sizeof(struct sockaddr_iso) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; lock_sock(sk); if ((sk->sk_state == BT_CONNECT2 || sk->sk_state == BT_CONNECTED) && addr_len > sizeof(*sa)) { /* Allow the user to rebind to a different address using * PAST procedures. */ err = iso_sock_rebind_bc(sk, sa, addr_len); goto done; } if (sk->sk_state != BT_OPEN) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } /* Check if the address type is of LE type */ if (!bdaddr_type_is_le(sa->iso_bdaddr_type)) { err = -EINVAL; goto done; } bacpy(&iso_pi(sk)->src, &sa->iso_bdaddr); iso_pi(sk)->src_type = sa->iso_bdaddr_type; /* Check for Broadcast address */ if (addr_len > sizeof(*sa)) { err = iso_sock_bind_bc(sock, addr, addr_len); if (err) goto done; } sk->sk_state = BT_BOUND; done: release_sock(sk); return err; } static int iso_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; struct sock *sk = sock->sk; int err; BT_DBG("sk %p", sk); if (alen < sizeof(struct sockaddr_iso) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) return -EBADFD; if (sk->sk_type != SOCK_SEQPACKET) return -EINVAL; /* Check if the address type is of LE type */ if (!bdaddr_type_is_le(sa->iso_bdaddr_type)) return -EINVAL; lock_sock(sk); bacpy(&iso_pi(sk)->dst, &sa->iso_bdaddr); iso_pi(sk)->dst_type = sa->iso_bdaddr_type; release_sock(sk); if (bacmp(&sa->iso_bdaddr, BDADDR_ANY)) err = iso_connect_cis(sk); else err = iso_connect_bis(sk); if (err) return err; lock_sock(sk); if (!test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); } release_sock(sk); return err; } static int iso_listen_bis(struct sock *sk) { struct iso_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; bdaddr_t src, dst; u8 src_type, bc_sid; int err = 0; lock_sock(sk); bacpy(&src, &iso_pi(sk)->src); bacpy(&dst, &iso_pi(sk)->dst); src_type = iso_pi(sk)->src_type; bc_sid = iso_pi(sk)->bc_sid; release_sock(sk); BT_DBG("%pMR -> %pMR (SID 0x%2.2x)", &src, &dst, bc_sid); write_lock(&iso_sk_list.lock); if (__iso_get_sock_listen_by_sid(&src, &dst, bc_sid)) err = -EADDRINUSE; write_unlock(&iso_sk_list.lock); if (err) return err; hdev = hci_get_route(&dst, &src, src_type); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); lock_sock(sk); /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; err = -EINVAL; goto unlock; } hcon = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), iso_pi(sk)->bc_sid, &iso_pi(sk)->qos); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } conn = iso_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } err = iso_chan_add(conn, sk, NULL); if (err) { hci_conn_drop(hcon); goto unlock; } unlock: release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static int iso_listen_cis(struct sock *sk) { int err = 0; BT_DBG("%pMR", &iso_pi(sk)->src); write_lock(&iso_sk_list.lock); if (__iso_get_sock_listen_by_addr(&iso_pi(sk)->src, &iso_pi(sk)->dst)) err = -EADDRINUSE; write_unlock(&iso_sk_list.lock); return err; } static int iso_sock_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sk %p backlog %d", sk, backlog); sock_hold(sk); lock_sock(sk); if (sk->sk_state != BT_BOUND) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } if (!bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) { err = iso_listen_cis(sk); } else { /* Drop sock lock to avoid potential * deadlock with the hdev lock. */ release_sock(sk); err = iso_listen_bis(sk); lock_sock(sk); } if (err) goto done; sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = BT_LISTEN; done: release_sock(sk); sock_put(sk); return err; } static int iso_sock_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; long timeo; int err = 0; /* Use explicit nested locking to avoid lockdep warnings generated * because the parent socket and the child socket are locked on the * same thread. */ lock_sock_nested(sk, SINGLE_DEPTH_NESTING); timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; } ch = bt_accept_dequeue(sk, newsock); if (ch) { /* Drop the bridging ref from bt_accept_dequeue(); * the grafted socket keeps ch alive from here. */ sock_put(ch); break; } if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); } remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; newsock->state = SS_CONNECTED; BT_DBG("new socket %p", ch); /* A Broadcast Sink might require BIG sync to be terminated * and re-established multiple times, while keeping the same * PA sync handle active. To allow this, once all BIS * connections have been accepted on a PA sync parent socket, * "reset" socket state, to allow future BIG re-sync procedures. */ if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { /* Iterate through the list of bound BIS indices * and clear each BIS as they are accepted by the * user space, one by one. */ for (int i = 0; i < iso_pi(sk)->bc_num_bis; i++) { if (iso_pi(sk)->bc_bis[i] > 0) { iso_pi(sk)->bc_bis[i] = 0; iso_pi(sk)->bc_num_bis--; break; } } if (iso_pi(sk)->bc_num_bis == 0) { /* Once the last BIS was accepted, reset parent * socket parameters to mark that the listening * process for BIS connections has been completed: * * 1. Reset the DEFER setup flag on the parent sk. * 2. Clear the flag marking that the BIG create * sync command is pending. * 3. Transition socket state from BT_LISTEN to * BT_CONNECTED. */ set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); clear_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags); sk->sk_state = BT_CONNECTED; } } done: release_sock(sk); return err; } static int iso_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; struct sock *sk = sock->sk; int len = sizeof(struct sockaddr_iso); BT_DBG("sock %p, sk %p", sock, sk); addr->sa_family = AF_BLUETOOTH; if (peer) { struct hci_conn *hcon = iso_pi(sk)->conn ? iso_pi(sk)->conn->hcon : NULL; bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst); sa->iso_bdaddr_type = iso_pi(sk)->dst_type; if (hcon && (hcon->type == BIS_LINK || hcon->type == PA_LINK)) { sa->iso_bc->bc_sid = iso_pi(sk)->bc_sid; sa->iso_bc->bc_num_bis = iso_pi(sk)->bc_num_bis; memcpy(sa->iso_bc->bc_bis, iso_pi(sk)->bc_bis, ISO_MAX_NUM_BIS); len += sizeof(struct sockaddr_iso_bc); } } else { bacpy(&sa->iso_bdaddr, &iso_pi(sk)->src); sa->iso_bdaddr_type = iso_pi(sk)->src_type; } return len; } static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb, **frag; struct sockcm_cookie sockc; size_t mtu; int err; BT_DBG("sock %p, sk %p", sock, sk); err = sock_error(sk); if (err) return err; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; hci_sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (err) return err; } lock_sock(sk); if (sk->sk_state != BT_CONNECTED) { release_sock(sk); return -ENOTCONN; } mtu = iso_pi(sk)->conn->hcon->mtu; release_sock(sk); skb = bt_skb_sendmsg(sk, msg, len, mtu, HCI_ISO_DATA_HDR_SIZE, 0); if (IS_ERR(skb)) return PTR_ERR(skb); len -= skb->len; BT_DBG("skb %p len %d", sk, skb->len); /* Continuation fragments */ frag = &skb_shinfo(skb)->frag_list; while (len) { struct sk_buff *tmp; tmp = bt_skb_sendmsg(sk, msg, len, mtu, 0, 0); if (IS_ERR(tmp)) { kfree_skb(skb); return PTR_ERR(tmp); } *frag = tmp; len -= tmp->len; skb->len += tmp->len; skb->data_len += tmp->len; BT_DBG("frag %p len %d", *frag, tmp->len); frag = &(*frag)->next; } lock_sock(sk); if (sk->sk_state == BT_CONNECTED) err = iso_send_frame(sk, skb, &sockc); else err = -ENOTCONN; release_sock(sk); if (err < 0) kfree_skb(skb); return err; } static void iso_conn_defer_accept(struct hci_conn *conn) { struct hci_cp_le_accept_cis cp; struct hci_dev *hdev = conn->hdev; BT_DBG("conn %p", conn); conn->state = BT_CONFIG; cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_LE_ACCEPT_CIS, sizeof(cp), &cp); } static void iso_conn_big_sync(struct sock *sk) { int err; struct hci_dev *hdev; bdaddr_t src, dst; u8 src_type; lock_sock(sk); bacpy(&src, &iso_pi(sk)->src); bacpy(&dst, &iso_pi(sk)->dst); src_type = iso_pi(sk)->src_type; release_sock(sk); hdev = hci_get_route(&dst, &src, src_type); if (!hdev) return; /* hci_le_big_create_sync requires hdev lock to be held, since * it enqueues the HCI LE BIG Create Sync command via * hci_cmd_sync_queue_once, which checks hdev flags that might * change. */ hci_dev_lock(hdev); lock_sock(sk); if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { err = hci_conn_big_create_sync(hdev, iso_pi(sk)->conn->hcon, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, iso_pi(sk)->bc_bis); if (err) bt_dev_err(hdev, "hci_big_create_sync: %d", err); } release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); } static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct iso_pinfo *pi = iso_pi(sk); bool early_ret = false; int err = 0; BT_DBG("sk %p", sk); if (unlikely(flags & MSG_ERRQUEUE)) return sock_recv_errqueue(sk, msg, len, SOL_BLUETOOTH, BT_SCM_ERROR); if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { sock_hold(sk); lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: if (test_bit(BT_SK_PA_SYNC, &pi->flags)) { release_sock(sk); iso_conn_big_sync(sk); lock_sock(sk); sk->sk_state = BT_LISTEN; } else { iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; } early_ret = true; break; case BT_CONNECTED: if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { release_sock(sk); iso_conn_big_sync(sk); lock_sock(sk); sk->sk_state = BT_LISTEN; early_ret = true; } break; case BT_CONNECT: release_sock(sk); err = iso_connect_cis(sk); lock_sock(sk); early_ret = true; break; default: break; } release_sock(sk); sock_put(sk); if (early_ret) return err; } return bt_sock_recvmsg(sock, msg, len, flags); } static bool check_io_qos(struct bt_iso_io_qos *qos) { /* If no PHY is enable SDU must be 0 */ if (!qos->phys && qos->sdu) return false; if (qos->interval && (qos->interval < 0xff || qos->interval > 0xfffff)) return false; if (qos->latency && (qos->latency < 0x05 || qos->latency > 0xfa0)) return false; if (qos->phys > BT_ISO_PHY_ANY) return false; return true; } static bool check_ucast_qos(struct bt_iso_qos *qos) { if (qos->ucast.cig > 0xef && qos->ucast.cig != BT_ISO_QOS_CIG_UNSET) return false; if (qos->ucast.cis > 0xef && qos->ucast.cis != BT_ISO_QOS_CIS_UNSET) return false; if (qos->ucast.sca > 0x07) return false; if (qos->ucast.packing > 0x01) return false; if (qos->ucast.framing > 0x01) return false; if (!check_io_qos(&qos->ucast.in)) return false; if (!check_io_qos(&qos->ucast.out)) return false; return true; } static bool check_bcast_qos(struct bt_iso_qos *qos) { if (!qos->bcast.sync_factor) qos->bcast.sync_factor = 0x01; if (qos->bcast.packing > 0x01) return false; if (qos->bcast.framing > 0x01) return false; if (!check_io_qos(&qos->bcast.in)) return false; if (!check_io_qos(&qos->bcast.out)) return false; if (qos->bcast.encryption > 0x01) return false; if (qos->bcast.options > 0x07) return false; if (qos->bcast.skip > 0x01f3) return false; if (!qos->bcast.sync_timeout) qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; if (qos->bcast.sync_timeout < 0x000a || qos->bcast.sync_timeout > 0x4000) return false; if (qos->bcast.sync_cte_type > 0x1f) return false; if (qos->bcast.mse > 0x1f) return false; if (!qos->bcast.timeout) qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT; if (qos->bcast.timeout < 0x000a || qos->bcast.timeout > 0x4000) return false; return true; } static int iso_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; struct bt_iso_qos qos = default_qos; u32 opt; BT_DBG("sk %p", sk); lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); else clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); break; case BT_PKT_STATUS: err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); else clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); break; case BT_PKT_SEQNUM: err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_PKT_SEQNUM, &bt_sk(sk)->flags); else clear_bit(BT_SK_PKT_SEQNUM, &bt_sk(sk)->flags); break; case BT_ISO_QOS: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2 && (!test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags) || sk->sk_state != BT_CONNECTED)) { err = -EINVAL; break; } err = copy_safe_from_sockptr(&qos, sizeof(qos), optval, optlen); if (err) break; iso_pi(sk)->qos = qos; iso_pi(sk)->qos_user_set = true; break; case BT_ISO_BASE: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } if (optlen > sizeof(iso_pi(sk)->base)) { err = -EINVAL; break; } err = copy_safe_from_sockptr(iso_pi(sk)->base, optlen, optval, optlen); if (err) break; iso_pi(sk)->base_len = optlen; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int iso_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int len, err = 0; struct bt_iso_qos *qos; u8 base_len; u8 *base; BT_DBG("sk %p", sk); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state == BT_CONNECTED) { err = -EINVAL; break; } if (put_user(test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags), (u32 __user *)optval)) err = -EFAULT; break; case BT_PKT_STATUS: if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags), (int __user *)optval)) err = -EFAULT; break; case BT_ISO_QOS: qos = iso_sock_get_qos(sk); len = min_t(unsigned int, len, sizeof(*qos)); if (copy_to_user(optval, qos, len)) err = -EFAULT; break; case BT_ISO_BASE: if (sk->sk_state == BT_CONNECTED && !bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) { base_len = iso_pi(sk)->conn->hcon->le_per_adv_data_len; base = iso_pi(sk)->conn->hcon->le_per_adv_data; } else { base_len = iso_pi(sk)->base_len; base = iso_pi(sk)->base; } len = min_t(unsigned int, len, base_len); if (copy_to_user(optval, base, len)) err = -EFAULT; if (put_user(len, optlen)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int iso_sock_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p, how %d", sock, sk, how); if (!sk) return 0; sock_hold(sk); lock_sock(sk); switch (how) { case SHUT_RD: if (sk->sk_shutdown & RCV_SHUTDOWN) goto unlock; sk->sk_shutdown |= RCV_SHUTDOWN; break; case SHUT_WR: if (sk->sk_shutdown & SEND_SHUTDOWN) goto unlock; sk->sk_shutdown |= SEND_SHUTDOWN; break; case SHUT_RDWR: if (sk->sk_shutdown & SHUTDOWN_MASK) goto unlock; sk->sk_shutdown |= SHUTDOWN_MASK; break; } iso_sock_clear_timer(sk); __iso_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); unlock: release_sock(sk); sock_put(sk); return err; } static int iso_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; iso_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) && !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); } sock_orphan(sk); iso_sock_kill(sk); return err; } static void iso_sock_ready(struct sock *sk) { BT_DBG("sk %p", sk); if (!sk) return; lock_sock(sk); iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; sk->sk_state_change(sk); release_sock(sk); } static bool iso_match_big(struct sock *sk, void *data) { struct hci_evt_le_big_sync_established *ev = data; return ev->handle == iso_pi(sk)->qos.bcast.big; } static bool iso_match_big_hcon(struct sock *sk, void *data) { struct hci_conn *hcon = data; return hcon->iso_qos.bcast.big == iso_pi(sk)->qos.bcast.big; } static bool iso_match_pa_sync_flag(struct sock *sk, void *data) { return test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); } static bool iso_match_dst(struct sock *sk, void *data) { return !bacmp(&iso_pi(sk)->dst, (bdaddr_t *)data); } static void iso_conn_ready(struct iso_conn *conn) { struct sock *parent = NULL; struct sock *sk = conn->sk; struct hci_ev_le_big_sync_established *ev = NULL; struct hci_ev_le_pa_sync_established *ev2 = NULL; struct hci_ev_le_per_adv_report *ev3 = NULL; struct hci_conn *hcon; struct hci_dev *hdev; BT_DBG("conn %p", conn); if (sk) { /* Attempt to update source address in case of BIS Sender if * the advertisement is using a random address. */ if (conn->hcon->type == BIS_LINK && conn->hcon->role == HCI_ROLE_MASTER && !bacmp(&conn->hcon->dst, BDADDR_ANY)) { struct hci_conn *bis = conn->hcon; struct adv_info *adv; adv = hci_find_adv_instance(bis->hdev, bis->iso_qos.bcast.bis); if (adv && bacmp(&adv->random_addr, BDADDR_ANY)) { lock_sock(sk); iso_pi(sk)->src_type = BDADDR_LE_RANDOM; bacpy(&iso_pi(sk)->src, &adv->random_addr); release_sock(sk); } } iso_sock_ready(conn->sk); } else { hcon = conn->hcon; if (!hcon) return; hdev = hcon->hdev; if (test_bit(HCI_CONN_BIG_SYNC, &hcon->flags)) { /* A BIS slave hcon is notified to the ISO layer * after the Command Complete for the LE Setup * ISO Data Path command is received. Get the * parent socket that matches the hcon BIG handle. */ parent = iso_get_sock(hdev, &hcon->src, &hcon->dst, BT_LISTEN, iso_match_big_hcon, hcon); } else if (test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags)) { ev = hci_recv_event_data(hcon->hdev, HCI_EVT_LE_BIG_SYNC_ESTABLISHED); /* Get reference to PA sync parent socket, if it exists */ parent = iso_get_sock(hdev, &hcon->src, &hcon->dst, BT_LISTEN, iso_match_pa_sync_flag, NULL); if (!parent && ev) parent = iso_get_sock(hdev, &hcon->src, &hcon->dst, BT_LISTEN, iso_match_big, ev); } else if (test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { ev2 = hci_recv_event_data(hcon->hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev2) parent = iso_get_sock(hdev, &hcon->src, &hcon->dst, BT_LISTEN, iso_match_sid, ev2); } else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags)) { ev3 = hci_recv_event_data(hcon->hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) parent = iso_get_sock(hdev, &hcon->src, &hcon->dst, BT_LISTEN, iso_match_sync_handle_pa_report, ev3); } if (!parent) parent = iso_get_sock(hdev, &hcon->src, BDADDR_ANY, BT_LISTEN, iso_match_dst, BDADDR_ANY); if (!parent) return; lock_sock(parent); sk = iso_sock_alloc(sock_net(parent), NULL, BTPROTO_ISO, GFP_ATOMIC, 0); if (!sk) { release_sock(parent); return; } iso_sock_init(sk, parent); bacpy(&iso_pi(sk)->src, &hcon->src); /* Convert from HCI to three-value type */ if (hcon->src_type == ADDR_LE_DEV_PUBLIC) iso_pi(sk)->src_type = BDADDR_LE_PUBLIC; else iso_pi(sk)->src_type = BDADDR_LE_RANDOM; /* If hcon has no destination address (BDADDR_ANY) it means it * was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED or * HCI_EV_LE_PA_SYNC_ESTABLISHED so we need to initialize using * the parent socket destination address. */ if (!bacmp(&hcon->dst, BDADDR_ANY)) { bacpy(&hcon->dst, &iso_pi(parent)->dst); hcon->dst_type = le_addr_type(iso_pi(parent)->dst_type); } if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags)) { iso_pi(sk)->qos = iso_pi(parent)->qos; hcon->iso_qos = iso_pi(sk)->qos; iso_pi(sk)->bc_sid = iso_pi(parent)->bc_sid; iso_pi(sk)->bc_num_bis = iso_pi(parent)->bc_num_bis; memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis, ISO_MAX_NUM_BIS); set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); } bacpy(&iso_pi(sk)->dst, &hcon->dst); /* Convert from HCI to three-value type */ if (hcon->dst_type == ADDR_LE_DEV_PUBLIC) iso_pi(sk)->dst_type = BDADDR_LE_PUBLIC; else iso_pi(sk)->dst_type = BDADDR_LE_RANDOM; iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle; memcpy(iso_pi(sk)->base, iso_pi(parent)->base, iso_pi(parent)->base_len); iso_pi(sk)->base_len = iso_pi(parent)->base_len; hci_conn_hold(hcon); iso_chan_add(conn, sk, parent); if ((ev && ((struct hci_evt_le_big_sync_established *)ev)->status) || (ev2 && ev2->status)) { /* Trigger error signal on child socket */ sk->sk_err = ECONNREFUSED; sk->sk_error_report(sk); } if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; else sk->sk_state = BT_CONNECTED; /* Wake up parent */ parent->sk_data_ready(parent); release_sock(parent); sock_put(parent); } } static bool iso_match_sid(struct sock *sk, void *data) { struct hci_ev_le_pa_sync_established *ev = data; if (iso_pi(sk)->bc_sid == HCI_SID_INVALID) return true; return ev->sid == iso_pi(sk)->bc_sid; } static bool iso_match_sid_past(struct sock *sk, void *data) { struct hci_ev_le_past_received *ev = data; if (iso_pi(sk)->bc_sid == HCI_SID_INVALID) return true; return ev->sid == iso_pi(sk)->bc_sid; } static bool iso_match_sync_handle(struct sock *sk, void *data) { struct hci_evt_le_big_info_adv_report *ev = data; return le16_to_cpu(ev->sync_handle) == iso_pi(sk)->sync_handle; } static bool iso_match_sync_handle_pa_report(struct sock *sk, void *data) { struct hci_ev_le_per_adv_report *ev = data; return le16_to_cpu(ev->sync_handle) == iso_pi(sk)->sync_handle; } /* ----- ISO interface with lower layer (HCI) ----- */ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct hci_ev_le_pa_sync_established *ev1; struct hci_ev_le_past_received *ev1a; struct hci_evt_le_big_info_adv_report *ev2; struct hci_ev_le_per_adv_report *ev3; struct sock *sk; bt_dev_dbg(hdev, "bdaddr %pMR", bdaddr); /* Broadcast receiver requires handling of some events before it can * proceed to establishing a BIG sync: * * 1. HCI_EV_LE_PA_SYNC_ESTABLISHED: The socket may specify a specific * SID to listen to and once sync is established its handle needs to * be stored in iso_pi(sk)->sync_handle so it can be matched once * receiving the BIG Info. * 1a. HCI_EV_LE_PAST_RECEIVED: alternative to 1. * 2. HCI_EVT_LE_BIG_INFO_ADV_REPORT: When connect_ind is triggered by a * a BIG Info it attempts to check if there any listening socket with * the same sync_handle and if it does then attempt to create a sync. * 3. HCI_EV_LE_PER_ADV_REPORT: When a PA report is received, it is stored * in iso_pi(sk)->base so it can be passed up to user, in the case of a * broadcast sink. */ ev1 = hci_recv_event_data(hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev1) { sk = iso_get_sock(hdev, &hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sid, ev1); if (sk && !ev1->status) { lock_sock(sk); iso_pi(sk)->sync_handle = le16_to_cpu(ev1->handle); iso_pi(sk)->bc_sid = ev1->sid; release_sock(sk); } goto done; } ev1a = hci_recv_event_data(hdev, HCI_EV_LE_PAST_RECEIVED); if (ev1a) { sk = iso_get_sock(hdev, &hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sid_past, ev1a); if (sk && !ev1a->status) { lock_sock(sk); iso_pi(sk)->sync_handle = le16_to_cpu(ev1a->sync_handle); iso_pi(sk)->bc_sid = ev1a->sid; release_sock(sk); } goto done; } ev2 = hci_recv_event_data(hdev, HCI_EVT_LE_BIG_INFO_ADV_REPORT); if (ev2) { /* Check if BIGInfo report has already been handled */ sk = iso_get_sock(hdev, &hdev->bdaddr, bdaddr, BT_CONNECTED, iso_match_sync_handle, ev2); if (sk) { sock_put(sk); sk = NULL; goto done; } /* Try to get PA sync socket, if it exists */ sk = iso_get_sock(hdev, &hdev->bdaddr, bdaddr, BT_CONNECT2, iso_match_sync_handle, ev2); if (!sk) sk = iso_get_sock(hdev, &hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sync_handle, ev2); if (sk) { int err = 0; bool big_sync; struct hci_conn *hcon; lock_sock(sk); hcon = iso_pi(sk)->conn->hcon; iso_pi(sk)->qos.bcast.encryption = ev2->encryption; if (ev2->num_bis < iso_pi(sk)->bc_num_bis) iso_pi(sk)->bc_num_bis = ev2->num_bis; big_sync = !test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags) && !test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags); if (big_sync) err = hci_conn_big_create_sync(hdev, hcon, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, iso_pi(sk)->bc_bis); release_sock(sk); if (big_sync && err) { bt_dev_err(hdev, "hci_le_big_create_sync: %d", err); sock_put(sk); sk = NULL; } } goto done; } ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) { size_t base_len = 0; u8 *base; struct hci_conn *hcon; sk = iso_get_sock(hdev, &hdev->bdaddr, bdaddr, BT_LISTEN, iso_match_sync_handle_pa_report, ev3); if (!sk) goto done; hcon = iso_pi(sk)->conn->hcon; if (!hcon) goto done; if (ev3->data_status == LE_PA_DATA_TRUNCATED) { /* The controller was unable to retrieve PA data. */ memset(hcon->le_per_adv_data, 0, HCI_MAX_PER_AD_TOT_LEN); hcon->le_per_adv_data_len = 0; hcon->le_per_adv_data_offset = 0; goto done; } if (hcon->le_per_adv_data_offset + ev3->length > HCI_MAX_PER_AD_TOT_LEN) goto done; memcpy(hcon->le_per_adv_data + hcon->le_per_adv_data_offset, ev3->data, ev3->length); hcon->le_per_adv_data_offset += ev3->length; if (ev3->data_status == LE_PA_DATA_COMPLETE) { /* All PA data has been received. */ hcon->le_per_adv_data_len = hcon->le_per_adv_data_offset; hcon->le_per_adv_data_offset = 0; /* Extract BASE */ base = eir_get_service_data(hcon->le_per_adv_data, hcon->le_per_adv_data_len, EIR_BAA_SERVICE_UUID, &base_len); if (!base || base_len > BASE_MAX_LENGTH) goto done; lock_sock(sk); memcpy(iso_pi(sk)->base, base, base_len); iso_pi(sk)->base_len = base_len; release_sock(sk); } else { /* This is a PA data fragment. Keep pa_data_len set to 0 * until all data has been reassembled. */ hcon->le_per_adv_data_len = 0; } } else { sk = iso_get_sock(hdev, &hdev->bdaddr, BDADDR_ANY, BT_LISTEN, iso_match_dst, BDADDR_ANY); } done: if (!sk) return 0; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; sock_put(sk); return HCI_LM_ACCEPT; } static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) { if (hcon->type != CIS_LINK && hcon->type != BIS_LINK && hcon->type != PA_LINK) { if (hcon->type != LE_LINK) return; /* Check if LE link has failed */ if (status) { struct hci_link *link, *t; list_for_each_entry_safe(link, t, &hcon->link_list, list) iso_conn_del(link->conn, bt_to_errno(status)); return; } /* Create CIS if pending */ hci_le_create_cis_pending(hcon->hdev); return; } BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); /* Similar to the success case, if HCI_CONN_BIG_SYNC_FAILED or * HCI_CONN_PA_SYNC_FAILED is set, queue the failed connection * into the accept queue of the listening socket and wake up * userspace, to inform the user about the event. */ if (!status || test_bit(HCI_CONN_BIG_SYNC_FAILED, &hcon->flags) || test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { struct iso_conn *conn; conn = iso_conn_add(hcon); if (conn) iso_conn_ready(conn); } else { iso_conn_del(hcon, bt_to_errno(status)); } } static void iso_disconn_cfm(struct hci_conn *hcon, __u8 reason) { if (hcon->type != CIS_LINK && hcon->type != BIS_LINK && hcon->type != PA_LINK) return; BT_DBG("hcon %p reason %d", hcon, reason); iso_conn_del(hcon, bt_to_errno(reason)); } int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) { struct hci_conn *hcon; struct iso_conn *conn; struct skb_shared_hwtstamps *hwts; __u16 pb, ts, len, sn; hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_handle(hdev, handle); if (!hcon) { hci_dev_unlock(hdev); kfree_skb(skb); return -ENOENT; } conn = iso_conn_hold_unless_zero(hcon->iso_data); hcon = NULL; hci_dev_unlock(hdev); if (!conn) { kfree_skb(skb); return -EINVAL; } pb = hci_iso_flags_pb(flags); ts = hci_iso_flags_ts(flags); BT_DBG("conn %p len %d pb 0x%x ts 0x%x", conn, skb->len, pb, ts); switch (pb) { case ISO_START: case ISO_SINGLE: if (conn->rx_len) { BT_ERR("Unexpected start frame (len %d)", skb->len); kfree_skb(conn->rx_skb); conn->rx_skb = NULL; conn->rx_len = 0; } if (ts) { struct hci_iso_ts_data_hdr *hdr; hdr = skb_pull_data(skb, HCI_ISO_TS_DATA_HDR_SIZE); if (!hdr) { BT_ERR("Frame is too short (len %d)", skb->len); goto drop; } /* Record the timestamp to skb */ hwts = skb_hwtstamps(skb); hwts->hwtstamp = us_to_ktime(le32_to_cpu(hdr->ts)); sn = __le16_to_cpu(hdr->sn); len = __le16_to_cpu(hdr->slen); } else { struct hci_iso_data_hdr *hdr; hdr = skb_pull_data(skb, HCI_ISO_DATA_HDR_SIZE); if (!hdr) { BT_ERR("Frame is too short (len %d)", skb->len); goto drop; } sn = __le16_to_cpu(hdr->sn); len = __le16_to_cpu(hdr->slen); } flags = hci_iso_data_flags(len); len = hci_iso_data_len(len); BT_DBG("Start: total len %d, frag len %d flags 0x%4.4x sn %d", len, skb->len, flags, sn); if (len == skb->len) { /* Complete frame received */ hci_skb_pkt_status(skb) = flags & 0x03; hci_skb_pkt_seqnum(skb) = sn; iso_recv_frame(conn, skb); goto done; } if (pb == ISO_SINGLE) { BT_ERR("Frame malformed (len %d, expected len %d)", skb->len, len); goto drop; } if (skb->len > len) { BT_ERR("Frame is too long (len %d, expected len %d)", skb->len, len); goto drop; } /* Allocate skb for the complete frame (with header) */ conn->rx_skb = bt_skb_alloc(len, GFP_KERNEL); if (!conn->rx_skb) goto drop; hci_skb_pkt_status(conn->rx_skb) = flags & 0x03; hci_skb_pkt_seqnum(conn->rx_skb) = sn; skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len = len - skb->len; /* Copy hw timestamp from skb to rx_skb if present */ if (ts) { hwts = skb_hwtstamps(conn->rx_skb); hwts->hwtstamp = skb_hwtstamps(skb)->hwtstamp; } break; case ISO_CONT: BT_DBG("Cont: frag len %d (expecting %d)", skb->len, conn->rx_len); if (!conn->rx_len) { BT_ERR("Unexpected continuation frame (len %d)", skb->len); goto drop; } if (skb->len > conn->rx_len) { BT_ERR("Fragment is too long (len %d, expected %d)", skb->len, conn->rx_len); kfree_skb(conn->rx_skb); conn->rx_skb = NULL; conn->rx_len = 0; goto drop; } skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len -= skb->len; break; case ISO_END: if (!conn->rx_len) { BT_ERR("Unexpected end frame (len %d)", skb->len); goto drop; } skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len -= skb->len; if (!conn->rx_len) { struct sk_buff *rx_skb = conn->rx_skb; /* Complete frame received. iso_recv_frame * takes ownership of the skb so set the global * rx_skb pointer to NULL first. */ conn->rx_skb = NULL; iso_recv_frame(conn, rx_skb); } break; } drop: kfree_skb(skb); done: iso_conn_put(conn); return 0; } static struct hci_cb iso_cb = { .name = "ISO", .connect_cfm = iso_connect_cfm, .disconn_cfm = iso_disconn_cfm, }; static int iso_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; read_lock(&iso_sk_list.lock); sk_for_each(sk, &iso_sk_list.head) { seq_printf(f, "%pMR %pMR %d\n", &iso_pi(sk)->src, &iso_pi(sk)->dst, sk->sk_state); } read_unlock(&iso_sk_list.lock); return 0; } DEFINE_SHOW_ATTRIBUTE(iso_debugfs); static struct dentry *iso_debugfs; static const struct proto_ops iso_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = iso_sock_release, .bind = iso_sock_bind, .connect = iso_sock_connect, .listen = iso_sock_listen, .accept = iso_sock_accept, .getname = iso_sock_getname, .sendmsg = iso_sock_sendmsg, .recvmsg = iso_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = iso_sock_shutdown, .setsockopt = iso_sock_setsockopt, .getsockopt = iso_sock_getsockopt }; static const struct net_proto_family iso_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = iso_sock_create, }; static bool inited; bool iso_inited(void) { return inited; } int iso_init(void) { int err; BUILD_BUG_ON(sizeof(struct sockaddr_iso) > sizeof(struct sockaddr)); if (inited) return -EALREADY; err = proto_register(&iso_proto, 0); if (err < 0) return err; err = bt_sock_register(BTPROTO_ISO, &iso_sock_family_ops); if (err < 0) { BT_ERR("ISO socket registration failed"); goto error; } err = bt_procfs_init(&init_net, "iso", &iso_sk_list, NULL); if (err < 0) { BT_ERR("Failed to create ISO proc file"); bt_sock_unregister(BTPROTO_ISO); goto error; } BT_INFO("ISO socket layer initialized"); hci_register_cb(&iso_cb); if (!IS_ERR_OR_NULL(bt_debugfs)) iso_debugfs = debugfs_create_file("iso", 0444, bt_debugfs, NULL, &iso_debugfs_fops); inited = true; return 0; error: proto_unregister(&iso_proto); return err; } int iso_exit(void) { if (!inited) return -EALREADY; bt_procfs_cleanup(&init_net, "iso"); debugfs_remove(iso_debugfs); iso_debugfs = NULL; hci_unregister_cb(&iso_cb); bt_sock_unregister(BTPROTO_ISO); proto_unregister(&iso_proto); inited = false; return 0; } |
| 11 5 11 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 | /* * linux/fs/nls/nls_cp855.c * * Charset cp855 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0452, 0x0402, 0x0453, 0x0403, 0x0451, 0x0401, 0x0454, 0x0404, 0x0455, 0x0405, 0x0456, 0x0406, 0x0457, 0x0407, 0x0458, 0x0408, /* 0x90*/ 0x0459, 0x0409, 0x045a, 0x040a, 0x045b, 0x040b, 0x045c, 0x040c, 0x045e, 0x040e, 0x045f, 0x040f, 0x044e, 0x042e, 0x044a, 0x042a, /* 0xa0*/ 0x0430, 0x0410, 0x0431, 0x0411, 0x0446, 0x0426, 0x0434, 0x0414, 0x0435, 0x0415, 0x0444, 0x0424, 0x0433, 0x0413, 0x00ab, 0x00bb, /* 0xb0*/ 0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x0445, 0x0425, 0x0438, 0x0418, 0x2563, 0x2551, 0x2557, 0x255d, 0x0439, 0x0419, 0x2510, /* 0xc0*/ 0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x043a, 0x041a, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x00a4, /* 0xd0*/ 0x043b, 0x041b, 0x043c, 0x041c, 0x043d, 0x041d, 0x043e, 0x041e, 0x043f, 0x2518, 0x250c, 0x2588, 0x2584, 0x041f, 0x044f, 0x2580, /* 0xe0*/ 0x042f, 0x0440, 0x0420, 0x0441, 0x0421, 0x0442, 0x0422, 0x0443, 0x0423, 0x0436, 0x0416, 0x0432, 0x0412, 0x044c, 0x042c, 0x2116, /* 0xf0*/ 0x00ad, 0x044b, 0x042b, 0x0437, 0x0417, 0x0448, 0x0428, 0x044d, 0x042d, 0x0449, 0x0429, 0x0447, 0x0427, 0x00a7, 0x25a0, 0x00a0, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xff, 0x00, 0x00, 0x00, 0xcf, 0x00, 0x00, 0xfd, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0xae, 0x00, 0xf0, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xaf, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ }; static const unsigned char page04[256] = { 0x00, 0x85, 0x81, 0x83, 0x87, 0x89, 0x8b, 0x8d, /* 0x00-0x07 */ 0x8f, 0x91, 0x93, 0x95, 0x97, 0x00, 0x99, 0x9b, /* 0x08-0x0f */ 0xa1, 0xa3, 0xec, 0xad, 0xa7, 0xa9, 0xea, 0xf4, /* 0x10-0x17 */ 0xb8, 0xbe, 0xc7, 0xd1, 0xd3, 0xd5, 0xd7, 0xdd, /* 0x18-0x1f */ 0xe2, 0xe4, 0xe6, 0xe8, 0xab, 0xb6, 0xa5, 0xfc, /* 0x20-0x27 */ 0xf6, 0xfa, 0x9f, 0xf2, 0xee, 0xf8, 0x9d, 0xe0, /* 0x28-0x2f */ 0xa0, 0xa2, 0xeb, 0xac, 0xa6, 0xa8, 0xe9, 0xf3, /* 0x30-0x37 */ 0xb7, 0xbd, 0xc6, 0xd0, 0xd2, 0xd4, 0xd6, 0xd8, /* 0x38-0x3f */ 0xe1, 0xe3, 0xe5, 0xe7, 0xaa, 0xb5, 0xa4, 0xfb, /* 0x40-0x47 */ 0xf5, 0xf9, 0x9e, 0xf1, 0xed, 0xf7, 0x9c, 0xde, /* 0x48-0x4f */ 0x00, 0x84, 0x80, 0x82, 0x86, 0x88, 0x8a, 0x8c, /* 0x50-0x57 */ 0x8e, 0x90, 0x92, 0x94, 0x96, 0x00, 0x98, 0x9a, /* 0x58-0x5f */ }; static const unsigned char page21[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xef, 0x00, /* 0x10-0x17 */ }; static const unsigned char page25[256] = { 0xc4, 0x00, 0xb3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0xbf, 0x00, 0x00, 0x00, 0xc0, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd9, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0xb4, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0xc2, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0xc1, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0xc5, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0xcd, 0xba, 0x00, 0x00, 0xc9, 0x00, 0x00, 0xbb, /* 0x50-0x57 */ 0x00, 0x00, 0xc8, 0x00, 0x00, 0xbc, 0x00, 0x00, /* 0x58-0x5f */ 0xcc, 0x00, 0x00, 0xb9, 0x00, 0x00, 0xcb, 0x00, /* 0x60-0x67 */ 0x00, 0xca, 0x00, 0x00, 0xce, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0xdf, 0x00, 0x00, 0x00, 0xdc, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0xdb, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0xb0, 0xb1, 0xb2, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xfe, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, page04, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page21, NULL, NULL, NULL, page25, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x80, 0x82, 0x82, 0x84, 0x84, 0x86, 0x86, /* 0x80-0x87 */ 0x88, 0x88, 0x8a, 0x8a, 0x8c, 0x8c, 0x8e, 0x8e, /* 0x88-0x8f */ 0x90, 0x90, 0x92, 0x92, 0x94, 0x94, 0x96, 0x96, /* 0x90-0x97 */ 0x98, 0x98, 0x9a, 0x9a, 0x9c, 0x9c, 0x9e, 0x9e, /* 0x98-0x9f */ 0xa0, 0xa0, 0xa2, 0xa2, 0xa4, 0xa4, 0xa6, 0xa6, /* 0xa0-0xa7 */ 0xa8, 0xa8, 0xaa, 0xaa, 0xac, 0xac, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb5, 0xb7, /* 0xb0-0xb7 */ 0xb7, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbd, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc6, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd0, 0xd2, 0xd2, 0xd4, 0xd4, 0xd6, 0xd6, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xd8, 0xde, 0xdf, /* 0xd8-0xdf */ 0xde, 0xe1, 0xe1, 0xe3, 0xe3, 0xe5, 0xe5, 0xe7, /* 0xe0-0xe7 */ 0xe7, 0xe9, 0xe9, 0xeb, 0xeb, 0xed, 0xed, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf1, 0xf3, 0xf3, 0xf5, 0xf5, 0xf7, /* 0xf0-0xf7 */ 0xf7, 0xf9, 0xf9, 0xfb, 0xfb, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x81, 0x81, 0x83, 0x83, 0x85, 0x85, 0x87, 0x87, /* 0x80-0x87 */ 0x89, 0x89, 0x8b, 0x8b, 0x8d, 0x8d, 0x8f, 0x8f, /* 0x88-0x8f */ 0x91, 0x91, 0x93, 0x93, 0x95, 0x95, 0x97, 0x97, /* 0x90-0x97 */ 0x99, 0x99, 0x9b, 0x9b, 0x9d, 0x9d, 0x9f, 0x9f, /* 0x98-0x9f */ 0xa1, 0xa1, 0xa3, 0xa3, 0xa5, 0xa5, 0xa7, 0xa7, /* 0xa0-0xa7 */ 0xa9, 0xa9, 0xab, 0xab, 0xad, 0xad, 0xae, 0xaf, /* 0xa8-0xaf */ 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb6, 0xb6, 0xb8, /* 0xb0-0xb7 */ 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbe, 0xbe, 0xbf, /* 0xb8-0xbf */ 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc7, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd1, 0xd1, 0xd3, 0xd3, 0xd5, 0xd5, 0xd7, 0xd7, /* 0xd0-0xd7 */ 0xdd, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xe0, 0xdf, /* 0xd8-0xdf */ 0xe0, 0xe2, 0xe2, 0xe4, 0xe4, 0xe6, 0xe6, 0xe8, /* 0xe0-0xe7 */ 0xe8, 0xea, 0xea, 0xec, 0xec, 0xee, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf2, 0xf2, 0xf4, 0xf4, 0xf6, 0xf6, 0xf8, /* 0xf0-0xf7 */ 0xf8, 0xfa, 0xfa, 0xfc, 0xfc, 0xfd, 0xfe, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "cp855", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_cp855(void) { return register_nls(&table); } static void __exit exit_nls_cp855(void) { unregister_nls(&table); } module_init(init_nls_cp855) module_exit(exit_nls_cp855) MODULE_DESCRIPTION("NLS Codepage 855 (Cyrillic)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 2 2 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 | // SPDX-License-Identifier: GPL-2.0-only /* * IPV4 GSO/GRO offload support * Linux INET implementation * * Copyright (C) 2016 secunet Security Networks AG * Author: Steffen Klassert <steffen.klassert@secunet.com> * * ESP GRO support */ #include <linux/skbuff.h> #include <linux/init.h> #include <net/protocol.h> #include <crypto/aead.h> #include <crypto/authenc.h> #include <linux/err.h> #include <linux/module.h> #include <net/gro.h> #include <net/gso.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/esp.h> #include <linux/scatterlist.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/udp.h> static struct sk_buff *esp4_gro_receive(struct list_head *head, struct sk_buff *skb) { int offset = skb_gro_offset(skb); struct xfrm_offload *xo; struct xfrm_state *x; int encap_type = 0; __be32 seq; __be32 spi; if (!pskb_pull(skb, offset)) return NULL; if (xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq) != 0) goto out; xo = xfrm_offload(skb); if (!xo || !(xo->flags & CRYPTO_DONE)) { struct sec_path *sp = secpath_set(skb); if (!sp) goto out; if (sp->len == XFRM_MAX_DEPTH) goto out_reset; x = xfrm_input_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ip_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET); if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) { /* non-offload path will record the error and audit log */ xfrm_state_put(x); x = NULL; } if (!x) goto out_reset; skb->mark = xfrm_smark_get(skb->mark, x); sp->xvec[sp->len++] = x; sp->olen++; xo = xfrm_offload(skb); if (!xo) goto out_reset; } xo->flags |= XFRM_GRO; if (NAPI_GRO_CB(skb)->proto == IPPROTO_UDP) encap_type = UDP_ENCAP_ESPINUDP; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); XFRM_SPI_SKB_CB(skb)->seq = seq; /* We don't need to handle errors from xfrm_input, it does all * the error handling and frees the resources on error. */ xfrm_input(skb, IPPROTO_ESP, spi, encap_type); return ERR_PTR(-EINPROGRESS); out_reset: secpath_reset(skb); out: skb_push(skb, offset); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 1; return NULL; } static void esp4_gso_encap(struct xfrm_state *x, struct sk_buff *skb) { struct ip_esp_hdr *esph; struct iphdr *iph = ip_hdr(skb); struct xfrm_offload *xo = xfrm_offload(skb); int proto = iph->protocol; skb_push(skb, -skb_network_offset(skb)); esph = ip_esp_hdr(skb); *skb_mac_header(skb) = IPPROTO_ESP; esph->spi = x->id.spi; esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); xo->proto = proto; } static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { struct xfrm_offload *xo = xfrm_offload(skb); const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, xo->proto); __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6) : htons(ETH_P_IP); return skb_eth_gso_segment(skb, features, type); } static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct xfrm_offload *xo = xfrm_offload(skb); skb->transport_header += x->props.header_len; ops = rcu_dereference(inet_offloads[xo->proto]); if (likely(ops && ops->callbacks.gso_segment)) segs = ops->callbacks.gso_segment(skb, features); return segs; } static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { struct xfrm_offload *xo = xfrm_offload(skb); struct sk_buff *segs = ERR_PTR(-EINVAL); const struct net_offload *ops; u8 proto = xo->proto; skb->transport_header += x->props.header_len; if (x->sel.family != AF_INET6) { if (proto == IPPROTO_BEETPH) { struct ip_beet_phdr *ph = (struct ip_beet_phdr *)skb->data; skb->transport_header += ph->hdrlen * 8; proto = ph->nexthdr; } else { skb->transport_header -= IPV4_BEET_PHMAXLEN; } } else { __be16 frag; skb->transport_header += ipv6_skip_exthdr(skb, 0, &proto, &frag); if (proto == IPPROTO_TCP) skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; } if (proto == IPPROTO_IPV6) skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; __skb_pull(skb, skb_transport_offset(skb)); ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) segs = ops->callbacks.gso_segment(skb, features); return segs; } static struct sk_buff *xfrm4_outer_mode_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { switch (x->outer_mode.encap) { case XFRM_MODE_TUNNEL: return xfrm4_tunnel_gso_segment(x, skb, features); case XFRM_MODE_TRANSPORT: return xfrm4_transport_gso_segment(x, skb, features); case XFRM_MODE_BEET: return xfrm4_beet_gso_segment(x, skb, features); } return ERR_PTR(-EOPNOTSUPP); } static struct sk_buff *esp4_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct xfrm_state *x; struct ip_esp_hdr *esph; struct crypto_aead *aead; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; if (!xo) return ERR_PTR(-EINVAL); if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP)) return ERR_PTR(-EINVAL); sp = skb_sec_path(skb); x = sp->xvec[sp->len - 1]; aead = x->data; esph = ip_esp_hdr(skb); if (esph->spi != x->id.spi) return ERR_PTR(-EINVAL); if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead))) return ERR_PTR(-EINVAL); __skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)); skb->encap_hdr_csum = 1; if ((!(skb->dev->gso_partial_features & NETIF_F_HW_ESP) && !(features & NETIF_F_HW_ESP)) || x->xso.dev != skb->dev) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC); else if (!(features & NETIF_F_HW_ESP_TX_CSUM) && !(skb->dev->gso_partial_features & NETIF_F_HW_ESP_TX_CSUM)) esp_features = features & ~(NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC); xo->flags |= XFRM_GSO_SEGMENT; return xfrm4_outer_mode_gso_segment(x, skb, esp_features); } static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb) { struct crypto_aead *aead = x->data; struct xfrm_offload *xo = xfrm_offload(skb); if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead))) return -EINVAL; if (!(xo->flags & CRYPTO_DONE)) skb->ip_summed = CHECKSUM_NONE; return esp_input_done2(skb, 0); } static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { int err; int alen; int blksize; struct xfrm_offload *xo; struct ip_esp_hdr *esph; struct crypto_aead *aead; struct esp_info esp; bool hw_offload = true; __u32 seq; int encap_type = 0; esp.inplace = true; xo = xfrm_offload(skb); if (!xo) return -EINVAL; if ((!(features & NETIF_F_HW_ESP) && !(skb->dev->gso_partial_features & NETIF_F_HW_ESP)) || x->xso.dev != skb->dev) { xo->flags |= CRYPTO_FALLBACK; hw_offload = false; } esp.proto = xo->proto; /* skb is pure payload to encrypt */ aead = x->data; alen = crypto_aead_authsize(aead); esp.tfclen = 0; /* XXX: Add support for tfc padding here. */ blksize = ALIGN(crypto_aead_blocksize(aead), 4); esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize); esp.plen = esp.clen - skb->len - esp.tfclen; esp.tailen = esp.tfclen + esp.plen + alen; esp.esph = ip_esp_hdr(skb); if (x->encap) encap_type = x->encap->encap_type; if (!hw_offload || !skb_is_gso(skb) || (hw_offload && encap_type == UDP_ENCAP_ESPINUDP)) { esp.nfrags = esp_output_head(x, skb, &esp); if (esp.nfrags < 0) return esp.nfrags; } seq = xo->seq.low; esph = esp.esph; esph->spi = x->id.spi; skb_push(skb, -skb_network_offset(skb)); if (xo->flags & XFRM_GSO_SEGMENT) { esph->seq_no = htonl(seq); if (!skb_is_gso(skb)) xo->seq.low++; else xo->seq.low += skb_shinfo(skb)->gso_segs; } if (xo->seq.low < seq) xo->seq.hi++; esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); if (hw_offload && encap_type == UDP_ENCAP_ESPINUDP) { /* In the XFRM stack, the encapsulation protocol is set to iphdr->protocol by * setting *skb_mac_header(skb) (see esp_output_udp_encap()) where skb->mac_header * points to iphdr->protocol (see xfrm4_tunnel_encap_add()). * However, in esp_xmit(), skb->mac_header doesn't point to iphdr->protocol. * Therefore, the protocol field needs to be corrected. */ ip_hdr(skb)->protocol = IPPROTO_UDP; esph->seq_no = htonl(seq); } ip_hdr(skb)->tot_len = htons(skb->len); ip_send_check(ip_hdr(skb)); if (hw_offload) { if (!skb_ext_add(skb, SKB_EXT_SEC_PATH)) return -ENOMEM; xo = xfrm_offload(skb); if (!xo) return -EINVAL; xo->flags |= XFRM_XMIT; return 0; } err = esp_output_tail(x, skb, &esp); if (err) return err; secpath_reset(skb); if (skb_needs_linearize(skb, skb->dev->features) && __skb_linearize(skb)) return -ENOMEM; return 0; } static const struct net_offload esp4_offload = { .callbacks = { .gro_receive = esp4_gro_receive, .gso_segment = esp4_gso_segment, }, }; static const struct xfrm_type_offload esp_type_offload = { .owner = THIS_MODULE, .proto = IPPROTO_ESP, .input_tail = esp_input_tail, .xmit = esp_xmit, .encap = esp4_gso_encap, }; static int __init esp4_offload_init(void) { if (xfrm_register_type_offload(&esp_type_offload, AF_INET) < 0) { pr_info("%s: can't add xfrm type offload\n", __func__); return -EAGAIN; } return inet_add_offload(&esp4_offload, IPPROTO_ESP); } static void __exit esp4_offload_exit(void) { xfrm_unregister_type_offload(&esp_type_offload, AF_INET); inet_del_offload(&esp4_offload, IPPROTO_ESP); } module_init(esp4_offload_init); module_exit(esp4_offload_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>"); MODULE_ALIAS_XFRM_OFFLOAD_TYPE(AF_INET, XFRM_PROTO_ESP); MODULE_DESCRIPTION("IPV4 GSO/GRO offload support"); |
| 910 908 904 908 1422 1423 1420 697 8 1125 2 1420 1420 908 910 1300 1300 1 1302 722 722 888 887 26 885 887 887 886 2 887 886 888 887 887 887 1761 1763 1755 8 6 1160 1156 928 334 4 22 24 77 1 1 1 1153 213 1120 109 217 213 202 6 6 6 16 16 15 4 16 1687 962 1542 24 24 211 204 11 211 210 210 182 32 2360 2364 2359 2356 2363 2357 2354 2359 2357 59 4 17 17 3 17 2356 10 2363 59 2359 2358 2360 2357 59 59 2359 2349 17 2358 2355 2359 103 5 79 26 1 1 101 115 115 115 191 414 574 220 377 6 575 573 569 553 38 576 569 412 187 187 564 6 3 3 3 3 3 3 3 3 3 216 1 4748 4757 109 229 229 229 7 2 2 2 78 78 78 78 2 77 1 78 78 78 78 140 1 1 1 23 18 9 81 3 81 80 3799 3803 3067 47 3030 3033 3801 2962 2383 2672 1347 1347 2420 593 263 2739 264 2167 2014 2011 333 1884 2013 6 9 1 8 2001 9 2865 6 266 1177 1831 5 1566 63 1477 1478 1477 44 1469 44 42 2 1475 1554 1553 1556 1348 26 15 1335 4 1327 13 2 12 1327 104 1554 266 9 9 9 8 8 1 8 9 8 8 9 1252 1250 1254 374 21 1251 17 170 169 146 54 145 144 78 23 112 170 304 2 305 10 184 172 273 6 17 14 6 27 9 3 72 75 1 30 47 2 43 40 1 23 24 24 170 170 102 113 4 114 2 110 4 89 25 145 141 24 114 10 75 137 8 19 10 37 83 12 83 1 2 2 105 1 104 102 10 9 86 86 82 86 85 86 15 69 18 86 86 86 86 86 94 86 16 70 85 1 84 68 120 4 93 2 24 15 10 15 134 134 134 134 134 81 1 80 39 1 32 74 73 1 65 33 80 80 21 13 4 6 6 6 4 3 6 2 20 29 6 25 25 2 21 21 12 7 6 1 1 6 24 7 18 132 35 34 1 91 1 3 74 3 11 10 11 38 36 74 17 11 78 26 66 33 91 59 24 14 14 14 150 49 134 36 96 70 50 91 2 89 89 132 1 132 1 81 46 4 48 49 2 11 120 30 113 120 896 20 17 5 861 153 1273 1254 11 1163 18 66 1150 1149 76 85 78 77 56 56 3 78 42 10 72 72 4 34 4 1107 952 240 1273 1271 338 1150 912 10 1144 1110 78 809 1146 1147 1270 25 25 25 25 25 1 1 50 50 6 6 5 219 219 190 190 1 204 15 7 183 7 7 219 32 33 17 1 4 14 788 789 72 763 763 97 745 19 762 127 127 219 754 754 50 679 75 11 5 61 77 2 27 42 1162 1163 800 256 17 17 5 1 1 2 2 5 2 5 5 17 12 6 33 31 2 25 3 17 17 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/syscalls.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/folio_batch.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include <linux/migrate.h> #include <linux/pipe_fs_i.h> #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <linux/sched/mm.h> #include <linux/sysctl.h> #include <linux/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> #include "swap.h" /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->block_dirty_folio) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_rwsem * ->invalidate_lock (acquired by fs in truncate path) * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->invalidate_lock (filemap_fault) * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_merge) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->lruvec->lru_lock (follow_page_mask->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->folio_isolate_lru) * ->private_lock (folio_remove_rmap_pte->set_page_dirty) * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) */ static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { XA_STATE(xas, &mapping->i_pages, folio->index); long nr = 1; mapping_set_update(&xas, mapping); xas_set_order(&xas, folio->index, folio_order(folio)); nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies upon it */ mapping->nrpages -= nr; } static void filemap_unaccount_folio(struct address_space *mapping, struct folio *folio) { long nr; VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, folio_pfn(folio)); dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); if (mapping_exiting(mapping) && !folio_test_large(folio)) { int mapcount = folio_mapcount(folio); if (folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped * and we'd rather not leak it: if we're wrong, * another bad page check should catch it later. */ atomic_set(&folio->_mapcount, -1); folio_ref_sub(folio, mapcount); } } } /* hugetlb folios do not participate in page cache accounting. */ if (folio_test_hugetlb(folio)) return; nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); if (folio_test_swapbacked(folio)) { lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); if (folio_test_pmd_mappable(folio)) lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) { lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } if (test_bit(AS_KERNEL_FILE, &folio->mapping->flags)) mod_node_page_state(folio_pgdat(folio), NR_KERNEL_FILE_PAGES, -nr); /* * At this point folio must be either written or cleaned by * truncate. Dirty folio here signals a bug and loss of * unwritten data - on ordinary filesystems. * * But it's harmless on in-memory filesystems like tmpfs; and can * occur when a driver which did get_user_pages() sets page dirty * before putting it, while the inode is being finally evicted. * * Below fixes dirty accounting after removing the folio entirely * but leaves the dirty flag set: it has no effect for truncated * folio and anyway will be cleared before returning folio to * buddy allocator. */ if (WARN_ON_ONCE(folio_test_dirty(folio) && mapping_can_writeback(mapping))) folio_account_cleaned(folio, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __filemap_remove_folio(struct folio *folio, void *shadow) { struct address_space *mapping = folio->mapping; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } static void filemap_free_folio(const struct address_space *mapping, struct folio *folio) { void (*free_folio)(struct folio *); free_folio = mapping->a_ops->free_folio; if (free_folio) free_folio(folio); folio_put_refs(folio, folio_nr_pages(folio)); } /** * filemap_remove_folio - Remove folio from page cache. * @folio: The folio. * * This must be called only on folios that are locked and have been * verified to be in the page cache. It will never put the folio into * the free list because the caller has a reference on the page. */ void filemap_remove_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_lru_list_add(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); } /* * page_cache_delete_batch - delete several folios from page cache * @mapping: the mapping to which folios belong * @fbatch: batch of folios to delete * * The function walks over mapping->i_pages and removes folios passed in * @fbatch from the mapping. The function expects @fbatch to be sorted * by page index and is optimised for it to be dense. * It tolerates holes in @fbatch (mapping entries at those indices are not * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); long total_pages = 0; int i = 0; struct folio *folio; mapping_set_update(&xas, mapping); xas_for_each(&xas, folio, ULONG_MAX) { if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (folio != fbatch->folios[i]) { VM_BUG_ON_FOLIO(folio->index > fbatch->folios[i]->index, folio); continue; } WARN_ON_ONCE(!folio_test_locked(folio)); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies on it */ i++; xas_store(&xas, NULL); total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch) { int i; if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); } page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_lru_list_add(mapping->host); spin_unlock(&mapping->host->i_lock); for (i = 0; i < folio_batch_count(fbatch); i++) filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } static int filemap_writeback(struct address_space *mapping, loff_t start, loff_t end, enum writeback_sync_modes sync_mode, long *nr_to_write) { struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = nr_to_write ? *nr_to_write : LONG_MAX, .range_start = start, .range_end = end, }; int ret; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); wbc_detach_inode(&wbc); if (!ret && nr_to_write) *nr_to_write = wbc.nr_to_write; return ret; } /** * filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * This is a data integrity operation that waits upon dirty or in writeback * pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return filemap_writeback(mapping, start, end, WB_SYNC_ALL, NULL); } EXPORT_SYMBOL(filemap_fdatawrite_range); int filemap_fdatawrite(struct address_space *mapping) { return filemap_fdatawrite_range(mapping, 0, LLONG_MAX); } EXPORT_SYMBOL(filemap_fdatawrite); /** * filemap_flush_range - start writeback on a range * @mapping: target address_space * @start: index to start writeback on * @end: last (inclusive) index for writeback * * This is a non-integrity writeback helper, to start writing back folios * for the indicated range. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush_range(struct address_space *mapping, loff_t start, loff_t end) { return filemap_writeback(mapping, start, end, WB_SYNC_NONE, NULL); } EXPORT_SYMBOL_GPL(filemap_flush_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return filemap_flush_range(mapping, 0, LLONG_MAX); } EXPORT_SYMBOL(filemap_flush); /* * Start writeback on @nr_to_write pages from @mapping. No one but the existing * btrfs caller should be using this. Talk to linux-mm if you think adding a * new caller is a good idea. */ int filemap_flush_nr(struct address_space *mapping, long *nr_to_write) { return filemap_writeback(mapping, 0, LLONG_MAX, WB_SYNC_NONE, nr_to_write); } EXPORT_SYMBOL_FOR_MODULES(filemap_flush_nr, "btrfs"); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct folio *folio; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { folio = xas_find(&xas, max); if (xas_retry(&xas, folio)) continue; /* Shadow entries don't count */ if (xa_is_value(folio)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct folio_batch fbatch; unsigned nr_folios; folio_batch_init(&fbatch); while (index <= end) { unsigned i; nr_folios = filemap_get_folios_tag(mapping, &index, end, PAGECACHE_TAG_WRITEBACK, &fbatch); if (!nr_folios) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; folio_wait_writeback(folio); } folio_batch_release(&fbatch); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { return mapping->nrpages; } bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; struct folio *folio; if (end_byte < start_byte) return false; rcu_read_lock(); xas_for_each(&xas, folio, max) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_dirty(folio) || folio_test_locked(folio) || folio_test_writeback(folio)) break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL_GPL(filemap_range_has_writeback); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0, err2; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = filemap_fdatawrite_range(mapping, lstart, lend); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = filemap_check_errors(mapping); if (!err) err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = filemap_fdatawrite_range(mapping, lstart, lend); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_folio - replace a pagecache folio with a new one * @old: folio to be replaced * @new: folio to replace with * * This function replaces a folio in the pagecache with a new one. On * success it acquires the pagecache reference for the new folio and * drops it for the old folio. Both the old and new folios must be * locked. This function does not add the new folio to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. */ void replace_page_cache_folio(struct folio *old, struct folio *new) { struct address_space *mapping = old->mapping; void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); VM_BUG_ON_FOLIO(!folio_test_locked(old), old); VM_BUG_ON_FOLIO(!folio_test_locked(new), new); VM_BUG_ON_FOLIO(new->mapping, new); folio_get(new); new->mapping = mapping; new->index = offset; mem_cgroup_replace_folio(old, new); xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!folio_test_hugetlb(old)) lruvec_stat_sub_folio(old, NR_FILE_PAGES); if (!folio_test_hugetlb(new)) lruvec_stat_add_folio(new, NR_FILE_PAGES); if (folio_test_swapbacked(old)) lruvec_stat_sub_folio(old, NR_SHMEM); if (folio_test_swapbacked(new)) lruvec_stat_add_folio(new, NR_SHMEM); xas_unlock_irq(&xas); if (free_folio) free_folio(old); folio_put(old); } EXPORT_SYMBOL_GPL(replace_page_cache_folio); noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); bool huge; long nr; unsigned int forder = folio_order(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping), folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = xas.xa_index; for (;;) { int order = -1; void *entry, *old = NULL; xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } /* * If a larger entry exists, * it will be the first and only entry iterated. */ if (order == -1) order = xas_get_order(&xas); } if (old) { if (order > 0 && order > forder) { unsigned int split_order = max(forder, xas_try_split_min_order(order)); /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); while (order > forder) { xas_set_order(&xas, index, split_order); xas_try_split(&xas, old, order); if (xas_error(&xas)) goto unlock; order = split_order; split_order = max(xas_try_split_min_order( split_order), forder); } xas_reset(&xas); } if (shadowp) *shadowp = old; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; mapping->nrpages += nr; /* hugetlb pages do not participate in page cache accounting */ if (!huge) { lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); if (folio_test_pmd_mappable(folio)) lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } unlock: xas_unlock_irq(&xas); if (!xas_nomem(&xas, gfp)) break; } if (xas_error(&xas)) goto error; trace_mm_filemap_add_to_page_cache(folio); return 0; error: folio->mapping = NULL; /* Leave folio->index set: truncation relies upon it */ folio_put_refs(folio, nr); return xas_error(&xas); } ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; struct mem_cgroup *tmp; bool kernel_file = test_bit(AS_KERNEL_FILE, &mapping->flags); if (kernel_file) tmp = set_active_memcg(root_mem_cgroup); ret = mem_cgroup_charge(folio, NULL, gfp); if (kernel_file) set_active_memcg(tmp); if (ret) return ret; __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) { mem_cgroup_uncharge(folio); __folio_clear_locked(folio); } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed folio. * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(folio_test_active(folio)); if (!(gfp & __GFP_WRITE) && shadow) workingset_refault(folio, shadow); folio_add_lru(folio); if (kernel_file) mod_node_page_state(folio_pgdat(folio), NR_KERNEL_FILE_PAGES, folio_nr_pages(folio)); } return ret; } EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, struct mempolicy *policy) { int n; struct folio *folio; if (policy) return folio_alloc_mpol_noprof(gfp, order, policy, NO_INTERLEAVE_INDEX, numa_node_id()); if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); return folio; } return folio_alloc_noprof(gfp, order); } EXPORT_SYMBOL(filemap_alloc_folio_noprof); #endif /* * filemap_invalidate_lock_two - lock invalidate_lock for two mappings * * Lock exclusively invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to lock * @mapping2: the second mapping to lock */ void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1 > mapping2) swap(mapping1, mapping2); if (mapping1) down_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) down_write_nested(&mapping2->invalidate_lock, 1); } EXPORT_SYMBOL(filemap_invalidate_lock_two); /* * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings * * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to unlock * @mapping2: the second mapping to unlock */ void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1) up_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) up_write(&mapping2->invalidate_lock); } EXPORT_SYMBOL(filemap_invalidate_unlock_two); /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *folio_waitqueue(struct folio *folio) { return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } /* How many times do we accept lock stealing from under a waiter? */ static int sysctl_page_lock_unfairness = 5; static const struct ctl_table filemap_sysctl_table[] = { { .procname = "page_lock_unfairness", .data = &sysctl_page_lock_unfairness, .maxlen = sizeof(sysctl_page_lock_unfairness), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, } }; void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); register_sysctl_init("vm", filemap_sysctl_table); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->folio->flags.f)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->folio->flags.f)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void folio_wake_bit(struct folio *folio, int bit_nr) { wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key(q, TASK_NORMAL, &key); /* * It's possible to miss clearing waiters here, when we woke our page * waiters, but the hashed waitqueue has waiters for other pages on it. * That's okay, it's a rare case. The next waker will clear it. * * Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE, * other), the flag may be cleared in the course of freeing the page; * but that is not required for correctness. */ if (!waitqueue_active(q) || !key.page_match) folio_clear_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } /* * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like folio_put_wait_locked() on PG_locked. */ }; /* * Attempt to check (or get) the folio flag, and mark us done * if successful. */ static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &folio->flags.f)) return false; } else if (test_bit(bit_nr, &folio->flags.f)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, int state, enum behavior behavior) { wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; if (bit_nr == PG_locked && !folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the folio. */ if (behavior == DROP) folio_put(folio); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } #ifdef CONFIG_MIGRATION /** * softleaf_entry_wait_on_locked - Wait for a migration entry or * device_private entry to be removed. * @entry: migration or device_private swap entry. * @ptl: already locked ptl. This function will drop the lock. * * Wait for a migration entry referencing the given page, or device_private * entry referencing a dvice_private page to be unlocked. This is * equivalent to folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE) except * this can be called without taking a reference on the page. Instead this * should be called while holding the ptl for @entry referencing * the page. * * Returns after unlocking the ptl. * * This follows the same logic as folio_wait_bit_common() so see the comments * there. */ void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) __releases(ptl) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; wait_queue_head_t *q; struct folio *folio = softleaf_to_folio(entry); q = folio_waitqueue(folio); if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = PG_locked; wait->flags = 0; spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, PG_locked, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * If a migration entry exists for the page the migration path must hold * a valid reference to the page, and it must take the ptl to remove the * migration entry. So the page is valid until the ptl is dropped. * Similarly any path attempting to drop the last reference to a * device-private page needs to grab the ptl to remove the device-private * entry. */ spin_unlock(ptl); for (;;) { unsigned int flags; set_current_state(TASK_UNINTERRUPTIBLE); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) break; io_schedule(); continue; } break; } finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } } #endif void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit); int folio_wait_bit_killable(struct folio *folio, int bit_nr) { return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit_killable); /** * folio_put_wait_locked - Drop a reference and wait for it to be unlocked * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not * dereference @folio. * * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ static int folio_put_wait_locked(struct folio *folio, int state) { return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** * folio_unlock - Unlock a locked folio. * @folio: The folio. * * Unlocks the folio and wakes up any thread sleeping on the page lock. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_unlock(struct folio *folio) { /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); BUILD_BUG_ON(PG_locked > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_unlock); /** * folio_end_read - End read on a folio. * @folio: The folio. * @success: True if all reads completed successfully. * * When all reads against a folio have completed, filesystems should * call this function to let the pagecache know that no more reads * are outstanding. This will unlock the folio and wake up any thread * sleeping on the lock. The folio will also be marked uptodate if all * reads succeeded. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_end_read(struct folio *folio, bool success) { unsigned long mask = 1 << PG_locked; /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; if (folio_xor_flags_has_waiters(folio, mask)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_end_read); /** * folio_end_private_2 - Clear PG_private_2 and wake any waiters. * @folio: The folio. * * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for * it. The folio reference held for PG_private_2 being set is released. * * This is, for example, used when a netfs folio is being written to a local * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ void folio_end_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); folio_wake_bit(folio, PG_private_2); folio_put(folio); } EXPORT_SYMBOL(folio_end_private_2); /** * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio. */ void folio_wait_private_2(struct folio *folio) { while (folio_test_private_2(folio)) folio_wait_bit(folio, PG_private_2); } EXPORT_SYMBOL(folio_wait_private_2); /** * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is * received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; while (folio_test_private_2(folio)) { ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } EXPORT_SYMBOL(folio_wait_private_2_killable); static void filemap_end_dropbehind(struct folio *folio) { struct address_space *mapping = folio->mapping; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) return; if (!folio_test_clear_dropbehind(folio)) return; if (mapping) folio_unmap_invalidate(mapping, folio, 0); } /* * If folio was marked as dropbehind, then pages should be dropped when writeback * completes. Do that now. If we fail, it's likely because of a big folio - * just reset dropbehind for that case and latter completions should invalidate. */ void folio_end_dropbehind(struct folio *folio) { if (!folio_test_dropbehind(folio)) return; /* * Hitting !in_task() should not happen off RWF_DONTCACHE writeback, * but can happen if normal writeback just happens to find dirty folios * that were created as part of uncached writeback, and that writeback * would otherwise not need non-IRQ handling. Just skip the * invalidation in that case. */ if (in_task() && folio_trylock(folio)) { filemap_end_dropbehind(folio); folio_unlock(folio); } } EXPORT_SYMBOL_GPL(folio_end_dropbehind); /** * folio_end_writeback_no_dropbehind - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * This call is intended for filesystems that need to defer dropbehind. * * Context: May be called from process or interrupt context. */ void folio_end_writeback_no_dropbehind(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * folio_test_clear_reclaim() could be used here but it is an * atomic operation and overkill in this particular case. Failing * to shuffle a folio marked for immediate reclaim is too mild * a gain to justify taking an atomic operation penalty at the * end of every folio writeback. */ if (folio_test_reclaim(folio)) { folio_clear_reclaim(folio); folio_rotate_reclaimable(folio); } if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); } EXPORT_SYMBOL_GPL(folio_end_writeback_no_dropbehind); /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * * Context: May be called from process or interrupt context. */ void folio_end_writeback(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the folio is not freed and * reused before the folio_wake_bit(). */ folio_get(folio); folio_end_writeback_no_dropbehind(folio); folio_end_dropbehind(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); /** * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. * @folio: The folio to lock */ void __folio_lock(struct folio *folio) { folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__folio_lock); int __folio_lock_killable(struct folio *folio) { return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { struct wait_queue_head *q = folio_waitqueue(folio); int ret; wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); folio_set_waiters(folio); ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } /* * Return values: * 0 - folio is locked. * non-zero - folio is not locked. * mmap_lock or per-VMA lock has been released (mmap_read_unlock() or * vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 0 * with the folio locked and the mmap_lock/per-VMA lock is left unperturbed. */ vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { unsigned int flags = vmf->flags; if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock/per-VMA lock is not * released even though returning VM_FAULT_RETRY. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return VM_FAULT_RETRY; release_fault_lock(vmf); if (flags & FAULT_FLAG_KILLABLE) folio_wait_locked_killable(folio); else folio_wait_locked(folio); return VM_FAULT_RETRY; } if (flags & FAULT_FLAG_KILLABLE) { bool ret; ret = __folio_lock_killable(folio); if (ret) { release_fault_lock(vmf); return VM_FAULT_RETRY; } } else { __folio_lock(folio); } return 0; } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); unsigned long nr = max_scan; while (nr--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; if (xas.xa_index == 0) return 0; } return index + max_scan; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /* * Lockless page cache protocol: * On the lookup side: * 1. Load the folio from i_pages * 2. Increment the refcount if it's not zero * 3. If the folio is not found by xas_reload(), put the refcount and retry * * On the removal side: * A. Freeze the page (by zeroing the refcount if nobody else has a reference) * B. Remove the page from i_pages * C. Return the page to the page allocator * * This means that any page may have its reference count temporarily * increased by a speculative page cache (or GUP-fast) lookup as it can * be allocated by another user before the RCU grace period expires. * Because the refcount temporarily acquired here may end up being the * last refcount on the page, any page allocation must be freeable by * folio_put(). */ /* * filemap_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache entry at @mapping & @index. If it is a folio, * it is returned with an increased refcount. If it is a shadow entry * of a previously evicted folio, or a swap entry from shmem/tmpfs, * it is returned without further action. * * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); folio = xas_load(&xas); if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!folio || xa_is_value(folio)) goto out; if (!folio_try_get(folio)) goto repeat; if (unlikely(folio != xas_reload(&xas))) { folio_put(folio); goto repeat; } out: rcu_read_unlock(); return folio; } /** * __filemap_get_folio_mpol - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the folio is returned. * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * @policy: NUMA memory allocation policy to follow. * * Looks up the page cache entry at @mapping & @index. * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If this function returns a folio, it is returned with an increased refcount. * * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio_mpol(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp, struct mempolicy *policy) { struct folio *folio; repeat: folio = filemap_get_entry(mapping, index); if (xa_is_value(folio)) folio = NULL; if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EAGAIN); } } else { folio_lock(folio); } /* Has the page been truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (folio_test_idle(folio)) folio_clear_idle(folio); } if (fgp_flags & FGP_STABLE) folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { unsigned int min_order = mapping_min_folio_order(mapping); unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags)); int err; index = mapping_align_index(mapping, index); if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp &= ~__GFP_FS; if (fgp_flags & FGP_NOWAIT) { gfp &= ~GFP_KERNEL; gfp |= GFP_NOWAIT; } if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; if (order > mapping_max_folio_order(mapping)) order = mapping_max_folio_order(mapping); /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); do { gfp_t alloc_gfp = gfp; err = -ENOMEM; if (order > min_order) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order, policy); if (!folio) continue; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); if (fgp_flags & FGP_DONTCACHE) __folio_set_dropbehind(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) break; folio_put(folio); folio = NULL; } while (order-- > min_order); if (err == -EEXIST) goto repeat; if (err) { /* * When NOWAIT I/O fails to allocate folios this could * be due to a nonblocking memory allocation and not * because the system actually is out of memory. * Return -EAGAIN so that there caller retries in a * blocking fashion instead of propagating -ENOMEM * to the application. */ if ((fgp_flags & FGP_NOWAIT) && err == -ENOMEM) err = -EAGAIN; return ERR_PTR(err); } /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. */ if (folio && (fgp_flags & FGP_FOR_MMAP)) folio_unlock(folio); } if (!folio) return ERR_PTR(-ENOENT); /* not an uncached lookup, clear uncached if set */ if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE)) folio_clear_dropbehind(folio); return folio; } EXPORT_SYMBOL(__filemap_get_folio_mpol); static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) { struct folio *folio; retry: if (mark == XA_PRESENT) folio = xas_find(xas, max); else folio = xas_find_marked(xas, max, mark); if (xas_retry(xas, folio)) goto retry; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (!folio || xa_is_value(folio)) return folio; if (!folio_try_get(folio)) goto reset; if (unlikely(folio != xas_reload(xas))) { folio_put(folio); goto reset; } return folio; reset: xas_reset(xas); goto retry; } /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in * the mapping. The entries are placed in @fbatch. find_get_entries() * takes a reference on any actual folios it returns. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries or large folios. * * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; } if (folio_batch_count(fbatch)) { unsigned long nr; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); else nr = 1 << xa_get_order(&mapping->i_pages, indices[idx]); *start = round_down(indices[idx] + nr, nr); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * find_lock_entries - Find a batch of pagecache entries. * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. * Swap, shadow and DAX entries are included. Folios are returned * locked and with an incremented refcount. Folios which are locked * by somebody else or under writeback are skipped. Folios which are * partially outside the range are not returned. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries, large folios, folios which could not be * locked or folios under writeback. * * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { unsigned long base; unsigned long nr; if (!xa_is_value(folio)) { nr = folio_nr_pages(folio); base = folio->index; /* Omit large folio which begins before the start */ if (base < *start) goto put; /* Omit large folio which extends beyond the end */ if (base + nr - 1 > end) goto put; if (!folio_trylock(folio)) goto put; if (folio->mapping != mapping || folio_test_writeback(folio)) goto unlock; VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), folio); } else { nr = 1 << xas_get_order(&xas); base = xas.xa_index & ~(nr - 1); /* Omit order>0 value which begins before the start */ if (base < *start) continue; /* Omit order>0 value which extends beyond the end */ if (base + nr - 1 > end) break; } /* Update start now so that last update is correct on return */ *start = base + nr; indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; continue; unlock: folio_unlock(folio); put: folio_put(folio); } rcu_read_unlock(); return folio_batch_count(fbatch); } /** * filemap_get_folios - Get a batch of folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill. * * Search for and return a batch of folios in the mapping starting at * index @start and up to index @end (inclusive). The folios are returned * in @fbatch with an elevated reference count. * * Return: The number of folios which were found. * We also update @start to index the next folio for the traversal. */ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch); } EXPORT_SYMBOL(filemap_get_folios); /** * filemap_get_folios_contig - Get a batch of contiguous folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_contig() works exactly like filemap_get_folios(), * except the returned folios are guaranteed to be contiguous. This may * not return all contiguous folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); unsigned long nr; struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio && xas.xa_index <= end; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(folio)) goto update_start; /* If we landed in the middle of a THP, continue at its end. */ if (xa_is_sibling(folio)) goto update_start; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) { nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } update_start: nr = folio_batch_count(fbatch); if (nr) { folio = fbatch->folios[nr - 1]; *start = folio_next_index(folio); } out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_contig); /** * filemap_get_folios_tag - Get a batch of folios matching @tag * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @tag: The tag index * @fbatch: The batch to fill * * The first folio may start before @start; if it does, it will contain * @start. The final folio may extend beyond @end; if it does, it will * contain @end. The folios have ascending indices. There may be gaps * between the folios if there are indices which have no folio in the * page cache. If folios are added to or removed from the page cache * while this is running, they may or may not be found by this call. * Only returns folios that are tagged with @tag. * * Return: The number of folios found. * Also update @start to index the next folio for traversal. */ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, tag)) != NULL) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(folio)) continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_tag); /** * filemap_get_folios_dirty - Get a batch of dirty folios * @mapping: The address_space to search * @start: The starting folio index * @end: The final folio index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_dirty() works exactly like filemap_get_folios(), except * the returned folios are presumed to be dirty or undergoing writeback. Dirty * state is presumed because we don't block on folio lock nor want to miss * folios. Callers that need to can recheck state upon locking the folio. * * This may not return all dirty folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_dirty(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { if (xa_is_value(folio)) continue; if (folio_trylock(folio)) { bool clean = !folio_test_dirty(folio) && !folio_test_writeback(folio); folio_unlock(folio); if (clean) { folio_put(folio); continue; } } if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } } /* * We come here when there is no folio beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a folio at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /* * filemap_get_read_batch - Get a batch of folios for read * * Get a batch of folios which represent a contiguous range of bytes in * the file. No exceptional entries will be returned. If @index is in * the middle of a folio, the entire folio will be returned. The last * folio in the batch may have the readahead flag set or the uptodate flag * clear so that the caller can take the appropriate action. */ static void filemap_get_read_batch(struct address_space *mapping, pgoff_t index, pgoff_t max, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; if (xas.xa_index > max || xa_is_value(folio)) break; if (xa_is_sibling(folio)) break; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) break; if (!folio_test_uptodate(folio)) break; if (folio_test_readahead(folio)) break; xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } rcu_read_unlock(); } static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { bool workingset = folio_test_workingset(folio); unsigned long pflags; int error; /* Start the actual read. The read will unlock the page. */ if (unlikely(workingset)) psi_memstall_enter(&pflags); error = filler(file, folio); if (unlikely(workingset)) psi_memstall_leave(&pflags); if (error) return error; error = folio_wait_locked_killable(folio); if (error) return error; if (folio_test_uptodate(folio)) return 0; if (file) shrink_readahead_size_eio(&file->f_ra); return -EIO; } static bool filemap_range_uptodate(struct address_space *mapping, loff_t pos, size_t count, struct folio *folio, bool need_uptodate) { if (folio_test_uptodate(folio)) return true; /* pipes can't handle partially uptodate pages */ if (need_uptodate) return false; if (!mapping->a_ops->is_partially_uptodate) return false; if (mapping->host->i_blkbits >= folio_shift(folio)) return false; if (folio_pos(folio) > pos) { count -= folio_pos(folio) - pos; pos = 0; } else { pos -= folio_pos(folio); } if (pos == 0 && count >= folio_size(folio)) return false; return mapping->a_ops->is_partially_uptodate(folio, pos, count); } static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, size_t count, struct folio *folio, bool need_uptodate) { int error; if (iocb->ki_flags & IOCB_NOWAIT) { if (!filemap_invalidate_trylock_shared(mapping)) return -EAGAIN; } else { filemap_invalidate_lock_shared(mapping); } if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); /* * This is where we usually end up waiting for a * previously submitted readahead to finish. */ folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; if (!folio->mapping) goto unlock; error = 0; if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio, need_uptodate)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); goto unlock_mapping; unlock: folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) folio_put(folio); return error; } static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct folio *folio; int error; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t index; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order, NULL); if (!folio) return -ENOMEM; if (iocb->ki_flags & IOCB_DONTCACHE) __folio_set_dropbehind(folio); /* * Protect against truncate / hole punch. Grabbing invalidate_lock * here assures we cannot instantiate and bring uptodate new * pagecache folios after evicting page cache during truncate * and before actually freeing blocks. Note that we could * release invalidate_lock after inserting the folio into * the page cache as the locked folio would then be enough to * synchronize with hole punching. But there are code paths * such as filemap_update_page() filling in partially uptodate * pages or ->readahead() that need to hold invalidate_lock * while mapping blocks for IO so let's hold the lock here as * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) error = AOP_TRUNCATED_PAGE; if (error) goto error; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); if (error) goto error; filemap_invalidate_unlock_shared(mapping); folio_batch_add(fbatch, folio); return 0; error: filemap_invalidate_unlock_shared(mapping); folio_put(folio); return error; } static int filemap_readahead(struct kiocb *iocb, struct file *file, struct address_space *mapping, struct folio *folio, pgoff_t last_index) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_DONTCACHE) ractl.dropbehind = 1; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } static int filemap_get_pages(struct kiocb *iocb, size_t count, struct folio_batch *fbatch, bool need_uptodate) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; unsigned int flags; int err = 0; /* "last_index" is the index of the folio beyond the end of the read */ last_index = round_up(iocb->ki_pos + count, mapping_min_folio_nrbytes(mapping)) >> PAGE_SHIFT; retry: if (fatal_signal_pending(current)) return -EINTR; filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); if (iocb->ki_flags & IOCB_DONTCACHE) ractl.dropbehind = 1; page_cache_sync_ra(&ractl, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { err = filemap_create_folio(iocb, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } folio = fbatch->folios[folio_batch_count(fbatch) - 1]; if (folio_test_readahead(folio)) { err = filemap_readahead(iocb, filp, mapping, folio, last_index); if (err) goto err; } if (!folio_test_uptodate(folio)) { if (folio_batch_count(fbatch) > 1) { err = -EAGAIN; goto err; } err = filemap_update_page(iocb, mapping, count, folio, need_uptodate); if (err) goto err; } trace_mm_filemap_get_pages(mapping, index, last_index - 1); return 0; err: if (err < 0) folio_put(folio); if (likely(--fbatch->nr)) return 0; if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) { unsigned int shift = folio_shift(folio); return (pos1 >> shift == pos2 >> shift); } static void filemap_end_dropbehind_read(struct folio *folio) { if (!folio_test_dropbehind(folio)) return; if (folio_test_writeback(folio) || folio_test_dirty(folio)) return; if (folio_trylock(folio)) { filemap_end_dropbehind(folio); folio_unlock(folio); } } /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. * @iter: Destination for the data. * @already_read: Number of bytes already read by the caller. * * Copies data from the page cache. If the data is not currently present, * uses the readahead and read_folio address_space operations to fetch it. * * Return: Total number of bytes copied, including those already read by * the caller. If an error happens before any bytes are copied, returns * a negative error number. */ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t already_read) { struct file *filp = iocb->ki_filp; struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct folio_batch fbatch; int i, error = 0; bool writably_mapped; loff_t isize, end_offset; loff_t last_pos = ra->prev_pos; if (unlikely(iocb->ki_pos < 0)) return -EINVAL; if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes - iocb->ki_pos); folio_batch_init(&fbatch); do { cond_resched(); /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(mapping); /* * When a read accesses the same folio several times, only * mark it as accessed the first time. */ if (!pos_same_folio(iocb->ki_pos, last_pos - 1, fbatch.folios[0])) folio_mark_accessed(fbatch.folios[0]); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t fsize = folio_size(folio); size_t offset = iocb->ki_pos & (fsize - 1); size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); size_t copied; if (end_offset < folio_pos(folio)) break; if (i > 0) folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); copied = copy_folio_to_iter(folio, offset, bytes, iter); already_read += copied; iocb->ki_pos += copied; last_pos = iocb->ki_pos; if (copied < bytes) { error = -EFAULT; break; } } put_folios: for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; filemap_end_dropbehind_read(folio); folio_put(folio); } folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); ra->prev_pos = last_pos; return already_read ? already_read : error; } EXPORT_SYMBOL_GPL(filemap_read); int kiocb_write_and_wait(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, pos, end)) return -EAGAIN; return 0; } return filemap_write_and_wait_range(mapping, pos, end); } EXPORT_SYMBOL_GPL(kiocb_write_and_wait); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait) { int ret; if (nowait) { /* we could block if there are any pages in the range */ if (filemap_range_has_page(mapping, pos, end)) return -EAGAIN; } else { ret = filemap_write_and_wait_range(mapping, pos, end); if (ret) return ret; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; return filemap_invalidate_pages(mapping, iocb->ki_pos, iocb->ki_pos + count - 1, iocb->ki_flags & IOCB_NOWAIT); } EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) return 0; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; retval = kiocb_write_and_wait(iocb, count); if (retval < 0) return retval; file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } if (retval != -EIOCBQUEUED) iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || IS_DAX(inode)) return retval; if (iocb->ki_pos >= i_size_read(inode)) return retval; } return filemap_read(iocb, iter, retval); } EXPORT_SYMBOL(generic_file_read_iter); /* * Splice subpages from a folio into a pipe. */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size) { struct page *page; size_t spliced = 0, offset = offset_in_folio(folio, fpos); page = folio_page(folio, offset / PAGE_SIZE); size = min(size, folio_size(folio) - offset); offset %= PAGE_SIZE; while (spliced < size && !pipe_is_full(pipe)) { struct pipe_buffer *buf = pipe_head_buf(pipe); size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); *buf = (struct pipe_buffer) { .ops = &page_cache_pipe_buf_ops, .page = page, .offset = offset, .len = part, }; folio_get(folio); pipe->head++; page++; spliced += part; offset = 0; } return spliced; } /** * filemap_splice_read - Splice data from a file's pagecache into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function gets folios from a file's pagecache and splices them into the * pipe. Readahead will be called as necessary to fill more folios. This may * be used for blockdevs also. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct folio_batch fbatch; struct kiocb iocb; size_t total_spliced = 0, used, npages; loff_t isize, end_offset; bool writably_mapped; int i, error = 0; if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) return 0; init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; /* Work out how much data we can actually add into the pipe */ used = pipe_buf_usage(pipe); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); folio_batch_init(&fbatch); do { cond_resched(); if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; error = filemap_get_pages(&iocb, len, &fbatch, true); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(in->f_mapping); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t n; if (folio_pos(folio) >= end_offset) goto out; folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); n = min_t(loff_t, len, isize - *ppos); n = splice_folio_into_pipe(pipe, folio, *ppos, n); if (!n) goto out; len -= n; total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; if (pipe_is_full(pipe)) goto out; } folio_batch_release(&fbatch); } while (len); out: folio_batch_release(&fbatch); file_accessed(in); return total_spliced ? total_spliced : error; } EXPORT_SYMBOL(filemap_splice_read); static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) { const struct address_space_operations *ops = mapping->a_ops; size_t offset, bsz = i_blocksize(mapping->host); if (xa_is_value(folio) || folio_test_uptodate(folio)) return seek_data ? start : end; if (!ops->is_partially_uptodate) return seek_data ? end : start; xas_pause(xas); rcu_read_unlock(); folio_lock(folio); if (unlikely(folio->mapping != mapping)) goto unlock; offset = offset_in_folio(folio, start) & ~(bsz - 1); do { if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; start = (start + bsz) & ~((u64)bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: folio_unlock(folio); rcu_read_lock(); return start; } static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) { if (xa_is_value(folio)) return PAGE_SIZE << xas_get_order(xas); return folio_size(folio); } /** * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. * @mapping: Address space to search. * @start: First byte to consider. * @end: Limit of search (exclusive). * @whence: Either SEEK_HOLE or SEEK_DATA. * * If the page cache knows which blocks contain holes and which blocks * contain data, your filesystem can use this function to implement * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are * entirely memory-based such as tmpfs, and filesystems which support * unwritten extents. * * Return: The requested offset on success, or -ENXIO if @whence specifies * SEEK_DATA and there is no data after @start. There is an implicit hole * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start * and @end contain data. */ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, loff_t end, int whence) { XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); struct folio *folio; if (end <= start) return -ENXIO; rcu_read_lock(); while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; size_t seek_size; if (start < pos) { if (!seek_data) goto unlock; start = pos; } seek_size = seek_folio_size(&xas, folio); pos = round_up((u64)pos + 1, seek_size); start = folio_seek_hole_data(&xas, mapping, folio, start, pos, seek_data); if (start < pos) goto unlock; if (start >= end) break; if (seek_size > PAGE_SIZE) xas_set(&xas, pos >> PAGE_SHIFT); if (!xa_is_value(folio)) folio_put(folio); } if (seek_data) start = -ENXIO; unlock: rcu_read_unlock(); if (folio && !xa_is_value(folio)) folio_put(folio); if (start > end) return end; return start; } #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_folio_or_retry in that it can drop the * mmap_lock. It differs in that it actually returns the folio locked * if it returns 1 and 0 if it couldn't lock the folio. If we did have * to drop the mmap_lock then fpin will point to the pinned file and * needs to be fput()'ed at a later point. */ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { if (folio_trylock(folio)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the * fault lock, but all fault_handlers only check * for fatal signals if we return VM_FAULT_RETRY, * so we need to drop the fault lock here and * return 0 if we don't have a fpin. */ if (*fpin == NULL) release_fault_lock(vmf); return 0; } } else __folio_lock(folio); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff); struct file *fpin = NULL; vm_flags_t vm_flags = vmf->vma->vm_flags; bool force_thp_readahead = false; unsigned short mmap_miss; /* Use the readahead code, even if readahead is disabled */ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && (vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) force_thp_readahead = true; if (!force_thp_readahead) { /* * If we don't want any read-ahead, don't bother. * VM_EXEC case below is already intended for random access. */ if ((vm_flags & (VM_RAND_READ | VM_EXEC)) == VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra->ra_pages); return fpin; } } if (!(vm_flags & VM_SEQ_READ)) { /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; } if (force_thp_readahead) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); ra->size = HPAGE_PMD_NR; /* * Fetch two PMD folios, so we get the chance to actually * readahead, unless we've been told not to. */ if (!(vm_flags & VM_RAND_READ)) ra->size *= 2; ra->async_size = HPAGE_PMD_NR; ra->order = HPAGE_PMD_ORDER; page_cache_ra_order(&ractl, ra); return fpin; } if (vm_flags & VM_EXEC) { /* * Allow arch to request a preferred minimum folio order for * executable memory. This can often be beneficial to * performance if (e.g.) arm64 can contpte-map the folio. * Executable memory rarely benefits from readahead, due to its * random access nature, so set async_size to 0. * * Limit to the boundaries of the VMA to avoid reading in any * pad that might exist between sections, which would be a waste * of memory. */ struct vm_area_struct *vma = vmf->vma; unsigned long start = vma->vm_pgoff; unsigned long end = start + vma_pages(vma); unsigned long ra_end; ra->order = exec_folio_order(); ra->start = round_down(vmf->pgoff, 1UL << ra->order); ra->start = max(ra->start, start); ra_end = round_up(ra->start + ra->ra_pages, 1UL << ra->order); ra_end = min(ra_end, end); ra->size = ra_end - ra->start; ra->async_size = 0; } else { /* * mmap read-around */ ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ra->order = 0; } fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index = ra->start; page_cache_ra_order(&ractl, ra); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; unsigned short mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; /* * If the folio is locked, we're likely racing against another fault. * Don't touch the mmap_miss counter to avoid decreasing it multiple * times for a single folio and break the balance with mmap_miss * increase in do_sync_mmap_readahead(). */ if (likely(!folio_test_locked(folio))) { mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); } if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; pte_t *ptep; /* * We might have COW'ed a pagecache folio and might now have an mlocked * anon folio mapped. The original pagecache folio is not mlocked and * might have been evicted. During a read+clear/modify/write update of * the PTE, such as done in do_numa_page()/change_pte_range(), we * temporarily clear the PTE under PT lock and might detect it here as * "none" when not holding the PT lock. * * Not rechecking the PTE under PT lock could result in an unexpected * major fault in an mlock'ed region. Recheck only for this special * scenario while holding the PT lock, to not degrade non-mlocked * scenarios. Recheck the PTE without PT lock firstly, thereby reducing * the number of times we hold PT lock. */ if (!(vma->vm_flags & VM_LOCKED)) return 0; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; ptep = pte_offset_map_ro_nolock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; if (unlikely(!pte_none(ptep_get_lockless(ptep)))) { ret = VM_FAULT_NOPAGE; } else { spin_lock(vmf->ptl); if (unlikely(!pte_none(ptep_get(ptep)))) ret = VM_FAULT_NOPAGE; spin_unlock(vmf->ptl); } pte_unmap(ptep); return ret; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t max_idx, index = vmf->pgoff; struct folio *folio; vm_fault_t ret = 0; bool mapping_locked = false; max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; trace_mm_filemap_fault(mapping, index); /* * Do we have something in the page cache already? */ folio = filemap_get_folio(mapping, index); if (likely(!IS_ERR(folio))) { /* * We found the page, so try async readahead before waiting for * the lock. */ if (!(vmf->flags & FAULT_FLAG_TRIED)) fpin = do_async_mmap_readahead(vmf, folio); if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } } else { ret = filemap_fault_recheck_pte_none(vmf); if (unlikely(ret)) return ret; /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: /* * See comment in filemap_create_folio() why we need * invalidate_lock */ if (!mapping_locked) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (IS_ERR(folio)) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_OOM; } } if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto retry_find; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked folio in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error, * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop * everything, get the invalidate lock and try again. */ if (!mapping_locked) { folio_unlock(folio); folio_put(folio); goto retry_find; } /* * OK, the folio is really not uptodate. This can be because the * VMA has the VM_RAND_READ flag set, or because an error * arose. Let's read it in directly. */ goto page_not_uptodate; } /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { folio_unlock(folio); goto out_retry; } if (mapping_locked) filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) { folio_unlock(folio); folio_put(folio); return VM_FAULT_SIGBUS; } vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (fpin) goto out_retry; folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, pgoff_t start) { struct mm_struct *mm = vmf->vma->vm_mm; /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) { folio_unlock(folio); folio_put(folio); return true; } if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) { struct page *page = folio_file_page(folio, start); vm_fault_t ret = do_set_pmd(vmf, folio, page); if (!ret) { /* The page is mapped successfully, reference consumed. */ folio_unlock(folio); return true; } } if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); return false; } static struct folio *next_uptodate_folio(struct xa_state *xas, struct address_space *mapping, pgoff_t end_pgoff) { struct folio *folio = xas_next_entry(xas, end_pgoff); unsigned long max_idx; do { if (!folio) return NULL; if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) continue; if (!folio_try_get(folio)) continue; if (folio_test_locked(folio)) goto skip; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) goto skip; if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; if (!folio_trylock(folio)) goto skip; if (folio->mapping != mapping) goto unlock; if (!folio_test_uptodate(folio)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; return folio; unlock: folio_unlock(folio); skip: folio_put(folio); } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } /* * Map page range [start_page, start_page + nr_pages) of folio. * start_page is gotten from start by folio_page(folio, start) */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, unsigned long *rss, unsigned short *mmap_miss, pgoff_t file_end) { struct address_space *mapping = folio->mapping; unsigned int ref_from_caller = 1; vm_fault_t ret = 0; struct page *page = folio_page(folio, start); unsigned int count = 0; pte_t *old_ptep = vmf->pte; unsigned long addr0; /* * Map the large folio fully where possible: * * - The folio is fully within size of the file or belong * to shmem/tmpfs; * - The folio doesn't cross VMA boundary; * - The folio doesn't cross page table boundary; */ addr0 = addr - start * PAGE_SIZE; if ((file_end >= folio_next_index(folio) || shmem_mapping(mapping)) && folio_within_vma(folio, vmf->vma) && (addr0 & PMD_MASK) == ((addr0 + folio_size(folio) - 1) & PMD_MASK)) { vmf->pte -= start; page -= start; addr = addr0; nr_pages = folio_nr_pages(folio); } do { if (PageHWPoison(page + count)) goto skip; /* * If there are too many folios that are recently evicted * in a file, they will probably continue to be evicted. * In such situation, read-ahead is only a waste of IO. * Don't decrease mmap_miss in this scenario to make sure * we can stop read-ahead. */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; continue; skip: if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count - ref_from_caller); ref_from_caller = 0; if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } count++; page += count; vmf->pte += count; addr += count * PAGE_SIZE; count = 0; } while (--nr_pages > 0); if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count - ref_from_caller); ref_from_caller = 0; if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } vmf->pte = old_ptep; if (ref_from_caller) /* Locked folios cannot get truncated. */ folio_ref_dec(folio); return ret; } static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, struct folio *folio, unsigned long addr, unsigned long *rss, unsigned short *mmap_miss) { vm_fault_t ret = 0; struct page *page = &folio->page; if (PageHWPoison(page)) goto out; /* See comment of filemap_map_folio_range() */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit * the fault-around logic. */ if (!pte_none(ptep_get(vmf->pte))) goto out; if (vmf->address == addr) ret = VM_FAULT_NOPAGE; set_pte_range(vmf, folio, page, 1, addr); (*rss)++; return ret; out: /* Locked folios cannot get truncated. */ folio_ref_dec(folio); return ret; } vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t file_end, last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; unsigned long rss = 0; unsigned int nr_pages = 0, folio_type; unsigned short mmap_miss = 0, mmap_miss_saved; /* * Recalculate end_pgoff based on file_end before calling * next_uptodate_folio() to avoid races with concurrent * truncation. */ file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1; end_pgoff = min(end_pgoff, file_end); rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; /* * Do not allow to map with PMD across i_size to preserve * SIGBUS semantics. * * Make an exception for shmem/tmpfs that for long time * intentionally mapped with PMDs across i_size. */ if ((file_end >= folio_next_index(folio) || shmem_mapping(mapping)) && filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) { folio_unlock(folio); folio_put(folio); goto out; } folio_type = mm_counter_file(folio); do { unsigned long end; addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) ret |= filemap_map_order0_folio(vmf, folio, addr, &rss, &mmap_miss); else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, nr_pages, &rss, &mmap_miss, file_end); folio_unlock(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); add_mm_counter(vma->vm_mm, folio_type, rss); pte_unmap_unlock(vmf->pte, vmf->ptl); trace_mm_filemap_map_pages(mapping, start_pgoff, end_pgoff); out: rcu_read_unlock(); mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss); if (mmap_miss >= mmap_miss_saved) WRITE_ONCE(file->f_ra.mmap_miss, 0); else WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss); return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct folio *folio = page_folio(vmf->page); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(mapping->host->i_sb); file_update_time(vmf->vma->vm_file); folio_lock(folio); if (folio->mapping != mapping) { folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the folio dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty folio and writeprotect it again. */ folio_mark_dirty(folio); folio_wait_stable(folio); out: sb_end_pagefault(mapping->host->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } int generic_file_mmap_prepare(struct vm_area_desc *desc) { struct file *file = desc->file; struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); desc->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc) { if (is_shared_maywrite(&desc->vma_flags)) return -EINVAL; return generic_file_mmap_prepare(desc); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } int generic_file_mmap_prepare(struct vm_area_desc *desc) { return -ENOSYS; } int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_mmap_prepare); EXPORT_SYMBOL(generic_file_readonly_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap_prepare); static struct folio *do_read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file, gfp_t gfp) { struct folio *folio; int err; if (!filler) filler = mapping->a_ops->read_folio; repeat: folio = filemap_get_folio(mapping, index); if (IS_ERR(folio)) { folio = filemap_alloc_folio(gfp, mapping_min_folio_order(mapping), NULL); if (!folio) return ERR_PTR(-ENOMEM); index = mapping_align_index(mapping, index); err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } goto filler; } if (folio_test_uptodate(folio)) goto out; if (!folio_trylock(folio)) { folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); goto repeat; } /* Folio was truncated from mapping */ if (!folio->mapping) { folio_unlock(folio); folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (folio_test_uptodate(folio)) { folio_unlock(folio); goto out; } filler: err = filemap_read_folio(file, filler, folio); if (err) { folio_put(folio); if (err == AOP_TRUNCATED_PAGE) goto repeat; return ERR_PTR(err); } out: folio_mark_accessed(folio); return folio; } /** * read_cache_folio - Read into page cache, fill it if needed. * @mapping: The address_space to read from. * @index: The index to read. * @filler: Function to perform the read, or NULL to use aops->read_folio(). * @file: Passed to filler function, may be NULL if not required. * * Read one page into the page cache. If it succeeds, the folio returned * will contain @index, but it may not be the first page of the folio. * * If the filler function returns an error, it will be returned to the * caller. * * Context: May sleep. Expects mapping->invalidate_lock to be held. * Return: An uptodate folio on success, ERR_PTR() on failure. */ struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file) { return do_read_cache_folio(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_folio); /** * mapping_read_folio_gfp - Read into page cache, using specified allocation flags. * @mapping: The address_space for the folio. * @index: The index that the allocated folio will contain. * @gfp: The page allocator flags to use if allocating. * * This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with * any new memory allocations done using the specified allocation flags. * * The most likely error from this function is EIO, but ENOMEM is * possible and so is EINTR. If ->read_folio returns another error, * that will be returned to the caller. * * The function expects mapping->invalidate_lock to be already held. * * Return: Uptodate folio on success, ERR_PTR() on failure. */ struct folio *mapping_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_folio(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(mapping_read_folio_gfp); static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp) { struct folio *folio; folio = do_read_cache_folio(mapping, index, filler, file, gfp); if (IS_ERR(folio)) return &folio->page; return folio_file_page(folio, index); } struct page *read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file) { return do_read_cache_page(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * The function expects mapping->invalidate_lock to be already held. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); /* * Warn about a page cache invalidation failure during a direct I/O write. */ static void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; char *path; errseq_set(&filp->f_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; if (mapping->nrpages && invalidate_inode_pages2_range(mapping, iocb->ki_pos >> PAGE_SHIFT, (iocb->ki_pos + count - 1) >> PAGE_SHIFT)) dio_warn_stale_pagecache(iocb->ki_filp); } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct address_space *mapping = iocb->ki_filp->f_mapping; size_t write_len = iov_iter_count(from); ssize_t written; /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ written = kiocb_invalidate_pages(iocb, write_len); if (written) { if (written == -EBUSY) return 0; return written; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0) { struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; kiocb_invalidate_post_direct_write(iocb, written); pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } if (written != -EIOCBQUEUED) iov_iter_revert(from, write_len - iov_iter_count(from)); return written; } EXPORT_SYMBOL(generic_file_direct_write); ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) { struct file *file = iocb->ki_filp; loff_t pos = iocb->ki_pos; struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; size_t chunk = mapping_max_folio_size(mapping); long status = 0; ssize_t written = 0; do { struct folio *folio; size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ void *fsdata = NULL; bytes = iov_iter_count(i); retry: offset = pos & (chunk - 1); bytes = min(chunk - offset, bytes); balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(iocb, mapping, pos, bytes, &folio, &fsdata); if (unlikely(status < 0)) break; offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); /* * Faults here on mmap()s can recurse into arbitrary * filesystem code. Lots of locks are held that can * deadlock. Use an atomic copy to avoid deadlocking * in page fault handling. */ copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); flush_dcache_folio(folio); status = a_ops->write_end(iocb, mapping, pos, bytes, copied, folio, fsdata); if (unlikely(status != copied)) { iov_iter_revert(i, copied - max(status, 0L)); if (unlikely(status < 0)) break; } cond_resched(); if (unlikely(status == 0)) { /* * A short copy made ->write_end() reject the * thing entirely. Might be memory poisoning * halfway through, might be a race with munmap, * might be severe memory pressure. */ if (chunk > PAGE_SIZE) chunk /= 2; if (copied) { bytes = copied; goto retry; } /* * 'folio' is now unlocked and faults on it can be * handled. Ensure forward progress by trying to * fault it in now. */ if (fault_in_iov_iter_readable(i, bytes) == bytes) { status = -EFAULT; break; } } else { pos += status; written += status; } } while (iov_iter_count(i)); if (!written) return status; iocb->ki_pos += written; return written; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_rwsem to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_rwsem. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; ret = file_remove_privs(file); if (ret) return ret; ret = file_update_time(file); if (ret) return ret; if (iocb->ki_flags & IOCB_DIRECT) { ret = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (ret < 0 || !iov_iter_count(from) || IS_DAX(inode)) return ret; return direct_write_fallback(iocb, from, ret, generic_perform_write(iocb, from)); } return generic_perform_write(iocb, from); } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_rwsem as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * filemap_release_folio() - Release fs-specific metadata on a folio. * @folio: The folio which the kernel is trying to free. * @gfp: Memory allocation flags (and I/O mode). * * The address_space is trying to release any data attached to a folio * (presumably at folio->private). * * This will also be called if the private_2 flag is set on a page, * indicating that the folio has other metadata associated with it. * * The @gfp argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block * (__GFP_RECLAIM & __GFP_FS). * * Return: %true if the release was successful, otherwise %false. */ bool filemap_release_folio(struct folio *folio, gfp_t gfp) { struct address_space * const mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); if (!folio_needs_release(folio)) return true; if (folio_test_writeback(folio)) return false; if (mapping && mapping->a_ops->release_folio) return mapping->a_ops->release_folio(folio, gfp); return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); /** * filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache * @inode: The inode to flush * @flush: Set to write back rather than simply invalidate. * @start: First byte to in range. * @end: Last byte in range (inclusive), or LLONG_MAX for everything from start * onwards. * * Invalidate all the folios on an inode that contribute to the specified * range, possibly writing them back first. Whilst the operation is * undertaken, the invalidate lock is held to prevent new folios from being * installed. */ int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end) { struct address_space *mapping = inode->i_mapping; pgoff_t first = start >> PAGE_SHIFT; pgoff_t last = end >> PAGE_SHIFT; pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1; if (!mapping || !mapping->nrpages || end < start) goto out; /* Prevent new folios from being added to the inode. */ filemap_invalidate_lock(mapping); if (!mapping->nrpages) goto unlock; unmap_mapping_pages(mapping, first, nr, false); /* Write back the data if we're asked to. */ if (flush) filemap_fdatawrite_range(mapping, start, end); /* Wait for writeback to complete on all folios and discard. */ invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE); unlock: filemap_invalidate_unlock(mapping); out: return filemap_check_errors(mapping); } EXPORT_SYMBOL_GPL(filemap_invalidate_inode); #ifdef CONFIG_CACHESTAT_SYSCALL /** * filemap_cachestat() - compute the page cache statistics of a mapping * @mapping: The mapping to compute the statistics for. * @first_index: The starting page cache index. * @last_index: The final page index (inclusive). * @cs: the cachestat struct to write the result to. * * This will query the page cache statistics of a mapping in the * page range of [first_index, last_index] (inclusive). The statistics * queried include: number of dirty pages, number of pages marked for * writeback, and the number of (recently) evicted pages. */ static void filemap_cachestat(struct address_space *mapping, pgoff_t first_index, pgoff_t last_index, struct cachestat *cs) { XA_STATE(xas, &mapping->i_pages, first_index); struct folio *folio; /* Flush stats (and potentially sleep) outside the RCU read section. */ mem_cgroup_flush_stats_ratelimited(NULL); rcu_read_lock(); xas_for_each(&xas, folio, last_index) { int order; unsigned long nr_pages; pgoff_t folio_first_index, folio_last_index; /* * Don't deref the folio. It is not pinned, and might * get freed (and reused) underneath us. * * We *could* pin it, but that would be expensive for * what should be a fast and lightweight syscall. * * Instead, derive all information of interest from * the rcu-protected xarray. */ if (xas_retry(&xas, folio)) continue; order = xas_get_order(&xas); nr_pages = 1 << order; folio_first_index = round_down(xas.xa_index, 1 << order); folio_last_index = folio_first_index + nr_pages - 1; /* Folios might straddle the range boundaries, only count covered pages */ if (folio_first_index < first_index) nr_pages -= first_index - folio_first_index; if (folio_last_index > last_index) nr_pages -= folio_last_index - last_index; if (xa_is_value(folio)) { /* page is evicted */ void *shadow = (void *)folio; bool workingset; /* not used */ cs->nr_evicted += nr_pages; #ifdef CONFIG_SWAP /* implies CONFIG_MMU */ if (shmem_mapping(mapping)) { /* shmem file - in swap cache */ swp_entry_t swp = radix_to_swp_entry(folio); /* swapin error results in poisoned entry */ if (!softleaf_is_swap(swp)) goto resched; /* * Getting a swap entry from the shmem * inode means we beat * shmem_unuse(). rcu_read_lock() * ensures swapoff waits for us before * freeing the swapper space. However, * we can race with swapping and * invalidation, so there might not be * a shadow in the swapcache (yet). */ shadow = swap_cache_get_shadow(swp); if (!shadow) goto resched; } #endif if (workingset_test_recent(shadow, true, &workingset, false)) cs->nr_recently_evicted += nr_pages; goto resched; } /* page is in cache */ cs->nr_cache += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY)) cs->nr_dirty += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK)) cs->nr_writeback += nr_pages; resched: if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); } /* * See mincore: reveal pagecache information only for files * that the calling process has write access to, or could (if * tried) open for writing. */ static inline bool can_do_cachestat(struct file *f) { if (f->f_mode & FMODE_WRITE) return true; if (inode_owner_or_capable(file_mnt_idmap(f), file_inode(f))) return true; return file_permission(f, MAY_WRITE) == 0; } /* * The cachestat(2) system call. * * cachestat() returns the page cache statistics of a file in the * bytes range specified by `off` and `len`: number of cached pages, * number of dirty pages, number of pages marked for writeback, * number of evicted pages, and number of recently evicted pages. * * An evicted page is a page that is previously in the page cache * but has been evicted since. A page is recently evicted if its last * eviction was recent enough that its reentry to the cache would * indicate that it is actively being used by the system, and that * there is memory pressure on the system. * * `off` and `len` must be non-negative integers. If `len` > 0, * the queried range is [`off`, `off` + `len`]. If `len` == 0, * we will query in the range from `off` to the end of the file. * * The `flags` argument is unused for now, but is included for future * extensibility. User should pass 0 (i.e no flag specified). * * Currently, hugetlbfs is not supported. * * Because the status of a page can change after cachestat() checks it * but before it returns to the application, the returned values may * contain stale information. * * return values: * zero - success * -EFAULT - cstat or cstat_range points to an illegal address * -EINVAL - invalid flags * -EBADF - invalid file descriptor * -EOPNOTSUPP - file descriptor is of a hugetlbfs file */ SYSCALL_DEFINE4(cachestat, unsigned int, fd, struct cachestat_range __user *, cstat_range, struct cachestat __user *, cstat, unsigned int, flags) { CLASS(fd, f)(fd); struct address_space *mapping; struct cachestat_range csr; struct cachestat cs; pgoff_t first_index, last_index; if (fd_empty(f)) return -EBADF; if (copy_from_user(&csr, cstat_range, sizeof(struct cachestat_range))) return -EFAULT; /* hugetlbfs is not supported */ if (is_file_hugepages(fd_file(f))) return -EOPNOTSUPP; if (!can_do_cachestat(fd_file(f))) return -EPERM; if (flags != 0) return -EINVAL; first_index = csr.off >> PAGE_SHIFT; last_index = csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT; memset(&cs, 0, sizeof(struct cachestat)); mapping = fd_file(f)->f_mapping; filemap_cachestat(mapping, first_index, last_index, &cs); if (copy_to_user(cstat, &cs, sizeof(struct cachestat))) return -EFAULT; return 0; } #endif /* CONFIG_CACHESTAT_SYSCALL */ |
| 1368 1365 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 | // SPDX-License-Identifier: GPL-2.0 /* * Dynamic byte queue limits. See include/linux/dynamic_queue_limits.h * * Copyright (c) 2011, Tom Herbert <therbert@google.com> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/dynamic_queue_limits.h> #include <linux/compiler.h> #include <linux/export.h> #include <trace/events/napi.h> #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) static void dql_check_stall(struct dql *dql, unsigned short stall_thrs) { unsigned long now; if (!stall_thrs) return; now = jiffies; /* Check for a potential stall */ if (time_after_eq(now, dql->last_reap + stall_thrs)) { unsigned long hist_head, t, start, end; /* We are trying to detect a period of at least @stall_thrs * jiffies without any Tx completions, but during first half * of which some Tx was posted. */ dqs_again: hist_head = READ_ONCE(dql->history_head); /* pairs with smp_wmb() in dql_queued() */ smp_rmb(); /* Get the previous entry in the ring buffer, which is the * oldest sample. */ start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG; /* Advance start to continue from the last reap time */ if (time_before(start, dql->last_reap + 1)) start = dql->last_reap + 1; /* Newest sample we should have already seen a completion for */ end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1); /* Shrink the search space to [start, (now - start_thrs/2)] if * `end` is beyond the stall zone */ if (time_before(now, end + stall_thrs / 2)) end = now - stall_thrs / 2; /* Search for the queued time in [t, end] */ for (t = start; time_before_eq(t, end); t++) if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG), dql->history)) break; /* Variable t contains the time of the queue */ if (!time_before_eq(t, end)) goto no_stall; /* The ring buffer was modified in the meantime, retry */ if (hist_head != READ_ONCE(dql->history_head)) goto dqs_again; dql->stall_cnt++; dql->stall_max = max_t(unsigned short, dql->stall_max, now - t); trace_dql_stall_detected(dql->stall_thrs, now - t, dql->last_reap, dql->history_head, now, dql->history); } no_stall: dql->last_reap = now; } /* Records completed count and recalculates the queue limit */ void dql_completed(struct dql *dql, unsigned int count) { unsigned int inprogress, prev_inprogress, limit; unsigned int ovlimit, completed, num_queued; unsigned short stall_thrs; bool all_prev_completed; num_queued = READ_ONCE(dql->num_queued); /* Read stall_thrs in advance since it belongs to the same (first) * cache line as ->num_queued. This way, dql_check_stall() does not * need to touch the first cache line again later, reducing the window * of possible false sharing. */ stall_thrs = READ_ONCE(dql->stall_thrs); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); completed = dql->num_completed + count; limit = dql->limit; ovlimit = POSDIFF(num_queued - dql->num_completed, limit); inprogress = num_queued - completed; prev_inprogress = dql->prev_num_queued - dql->num_completed; all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued); if ((ovlimit && !inprogress) || (dql->prev_ovlimit && all_prev_completed)) { /* * Queue considered starved if: * - The queue was over-limit in the last interval, * and there is no more data in the queue. * OR * - The queue was over-limit in the previous interval and * when enqueuing it was possible that all queued data * had been consumed. This covers the case when queue * may have becomes starved between completion processing * running and next time enqueue was scheduled. * * When queue is starved increase the limit by the amount * of bytes both sent and completed in the last interval, * plus any previous over-limit. */ limit += POSDIFF(completed, dql->prev_num_queued) + dql->prev_ovlimit; dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } else if (inprogress && prev_inprogress && !all_prev_completed) { /* * Queue was not starved, check if the limit can be decreased. * A decrease is only considered if the queue has been busy in * the whole interval (the check above). * * If there is slack, the amount of excess data queued above * the amount needed to prevent starvation, the queue limit * can be decreased. To avoid hysteresis we consider the * minimum amount of slack found over several iterations of the * completion routine. */ unsigned int slack, slack_last_objs; /* * Slack is the maximum of * - The queue limit plus previous over-limit minus twice * the number of objects completed. Note that two times * number of completed bytes is a basis for an upper bound * of the limit. * - Portion of objects in the last queuing operation that * was not part of non-zero previous over-limit. That is * "round down" by non-overlimit portion of the last * queueing operation. */ slack = POSDIFF(limit + dql->prev_ovlimit, 2 * (completed - dql->num_completed)); slack_last_objs = dql->prev_ovlimit ? POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0; slack = max(slack, slack_last_objs); if (slack < dql->lowest_slack) dql->lowest_slack = slack; if (time_after(jiffies, dql->slack_start_time + dql->slack_hold_time)) { limit = POSDIFF(limit, dql->lowest_slack); dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } } /* Enforce bounds on limit */ limit = clamp(limit, dql->min_limit, dql->max_limit); if (limit != dql->limit) { dql->limit = limit; ovlimit = 0; } dql->adj_limit = limit + completed; dql->prev_ovlimit = ovlimit; dql->prev_last_obj_cnt = READ_ONCE(dql->last_obj_cnt); dql->num_completed = completed; dql->prev_num_queued = num_queued; dql_check_stall(dql, stall_thrs); } EXPORT_SYMBOL(dql_completed); void dql_reset(struct dql *dql) { /* Reset all dynamic values */ dql->limit = dql->min_limit; dql->num_queued = 0; dql->num_completed = 0; dql->last_obj_cnt = 0; dql->prev_num_queued = 0; dql->prev_last_obj_cnt = 0; dql->prev_ovlimit = 0; dql->lowest_slack = UINT_MAX; dql->slack_start_time = jiffies; dql->last_reap = jiffies; dql->history_head = jiffies / BITS_PER_LONG; memset(dql->history, 0, sizeof(dql->history)); } EXPORT_SYMBOL(dql_reset); void dql_init(struct dql *dql, unsigned int hold_time) { dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; dql->stall_thrs = 0; dql_reset(dql); } EXPORT_SYMBOL(dql_init); |
| 3128 3128 3131 1536 3132 3129 3130 3127 3131 1535 1534 154 3155 3154 3393 289 3111 3 3083 3109 1335 1335 1096 1098 1098 1095 798 1012 1210 30 1185 3154 78 3155 3158 3158 1136 1098 1091 1098 3130 3130 3134 1098 1098 705 705 1535 157 1535 1535 157 1536 704 704 1 705 670 3 3 3 421 420 182 179 182 182 179 45 28 159 26 26 16 15 15 15 182 420 421 117 421 421 170 419 421 43 421 421 421 421 149 149 5 15 140 139 3123 3129 17 3127 168 3122 3119 188 3117 3117 3121 3119 3118 153 3117 3114 1 159 3115 4 154 154 17 3 3 17 3126 3129 118 3118 3127 17 177 150 4 51 68 3129 3126 3127 23 6 231 232 195 44 10 185 52 890 20 845 890 844 118 118 111 4 1 6 2 4 827 28 778 12 32 32 5 27 1 88 38 387 386 47 7 387 379 38 57 57 2716 420 421 12 145 421 21 421 2525 1112 1581 468 1235 485 891 1 6 1160 33 232 657 3131 1460 1317 118 1315 1 37 2070 1251 78 828 1216 1 78 36 9 65 37 45 340 38 244 245 572 571 254 1013 1012 1115 49 28 3 1115 1115 11 11 11 3128 1420 9 138 1147 384 1589 1108 1107 1 1110 1576 5 1459 165 1407 1219 629 26 602 7 7 7 2 16 3129 2714 421 313 421 370 374 360 139 139 135 139 138 18 139 3128 3129 3133 3130 3131 3129 3125 3 3129 2710 420 3124 3128 3134 3132 3134 3134 3128 3131 3134 3131 1109 3131 1460 3133 226 3133 210 3131 3130 3127 3125 237 3129 3134 3134 3131 1396 16 14 2 2 211 3 2 1 3129 3134 3130 3130 3132 3129 2713 421 3133 3130 3132 37 2071 1420 384 1154 9 39 8 94 19 1648 1255 19 313 3125 358 1311 925 3132 3134 3134 3134 3124 3134 3134 3134 3134 2714 421 38 419 420 416 420 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/hashtable.h> #include <linux/jhash.h> #include <linux/slab.h> #include <linux/sort.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) struct per_frame_masks { spis_t may_read; /* stack slots that may be read by this instruction */ spis_t must_write; /* stack slots written by this instruction */ spis_t live_before; /* stack slots that may be read by this insn and its successors */ }; /* * A function instance keyed by (callsite, depth). * Encapsulates read and write marks for each instruction in the function. * Marks are tracked for each frame up to @depth. */ struct func_instance { struct hlist_node hl_node; u32 callsite; /* call insn that invoked this subprog (subprog_start for depth 0) */ u32 depth; /* call depth (0 = entry subprog) */ u32 subprog; /* subprog index */ u32 subprog_start; /* cached env->subprog_info[subprog].start */ u32 insn_cnt; /* cached number of insns in the function */ /* Per frame, per instruction masks, frames allocated lazily. */ struct per_frame_masks *frames[MAX_CALL_FRAMES]; bool must_write_initialized; }; struct live_stack_query { struct func_instance *instances[MAX_CALL_FRAMES]; /* valid in range [0..curframe] */ u32 callsites[MAX_CALL_FRAMES]; /* callsite[i] = insn calling frame i+1 */ u32 curframe; u32 insn_idx; }; struct bpf_liveness { DECLARE_HASHTABLE(func_instances, 8); /* maps (depth, callsite) to func_instance */ struct live_stack_query live_stack_query; /* cache to avoid repetitive ht lookups */ u32 subprog_calls; /* analyze_subprog() invocations */ }; /* * Hash/compare key for func_instance: (depth, callsite). * For depth == 0 (entry subprog), @callsite is the subprog start insn. * For depth > 0, @callsite is the call instruction index that invoked the subprog. */ static u32 instance_hash(u32 callsite, u32 depth) { u32 key[2] = { depth, callsite }; return jhash2(key, 2, 0); } static struct func_instance *find_instance(struct bpf_verifier_env *env, u32 callsite, u32 depth) { struct bpf_liveness *liveness = env->liveness; struct func_instance *f; u32 key = instance_hash(callsite, depth); hash_for_each_possible(liveness->func_instances, f, hl_node, key) if (f->depth == depth && f->callsite == callsite) return f; return NULL; } static struct func_instance *call_instance(struct bpf_verifier_env *env, struct func_instance *caller, u32 callsite, int subprog) { u32 depth = caller ? caller->depth + 1 : 0; u32 subprog_start = env->subprog_info[subprog].start; u32 lookup_key = depth > 0 ? callsite : subprog_start; struct func_instance *f; u32 hash; f = find_instance(env, lookup_key, depth); if (f) return f; f = kvzalloc(sizeof(*f), GFP_KERNEL_ACCOUNT); if (!f) return ERR_PTR(-ENOMEM); f->callsite = lookup_key; f->depth = depth; f->subprog = subprog; f->subprog_start = subprog_start; f->insn_cnt = (env->subprog_info + subprog + 1)->start - subprog_start; hash = instance_hash(lookup_key, depth); hash_add(env->liveness->func_instances, &f->hl_node, hash); return f; } static struct func_instance *lookup_instance(struct bpf_verifier_env *env, struct bpf_verifier_state *st, u32 frameno) { u32 callsite, subprog_start; struct func_instance *f; u32 key, depth; subprog_start = env->subprog_info[st->frame[frameno]->subprogno].start; callsite = frameno > 0 ? st->frame[frameno]->callsite : subprog_start; for (depth = frameno; ; depth--) { key = depth > 0 ? callsite : subprog_start; f = find_instance(env, key, depth); if (f || depth == 0) return f; } } int bpf_stack_liveness_init(struct bpf_verifier_env *env) { env->liveness = kvzalloc_obj(*env->liveness, GFP_KERNEL_ACCOUNT); if (!env->liveness) return -ENOMEM; hash_init(env->liveness->func_instances); return 0; } void bpf_stack_liveness_free(struct bpf_verifier_env *env) { struct func_instance *instance; struct hlist_node *tmp; int bkt, i; if (!env->liveness) return; hash_for_each_safe(env->liveness->func_instances, bkt, tmp, instance, hl_node) { for (i = 0; i <= instance->depth; i++) kvfree(instance->frames[i]); kvfree(instance); } kvfree(env->liveness); } /* * Convert absolute instruction index @insn_idx to an index relative * to start of the function corresponding to @instance. */ static int relative_idx(struct func_instance *instance, u32 insn_idx) { return insn_idx - instance->subprog_start; } static struct per_frame_masks *get_frame_masks(struct func_instance *instance, u32 frame, u32 insn_idx) { if (!instance->frames[frame]) return NULL; return &instance->frames[frame][relative_idx(instance, insn_idx)]; } static struct per_frame_masks *alloc_frame_masks(struct func_instance *instance, u32 frame, u32 insn_idx) { struct per_frame_masks *arr; if (!instance->frames[frame]) { arr = kvzalloc_objs(*arr, instance->insn_cnt, GFP_KERNEL_ACCOUNT); instance->frames[frame] = arr; if (!arr) return ERR_PTR(-ENOMEM); } return get_frame_masks(instance, frame, insn_idx); } /* Accumulate may_read masks for @frame at @insn_idx */ static int mark_stack_read(struct func_instance *instance, u32 frame, u32 insn_idx, spis_t mask) { struct per_frame_masks *masks; masks = alloc_frame_masks(instance, frame, insn_idx); if (IS_ERR(masks)) return PTR_ERR(masks); masks->may_read = spis_or(masks->may_read, mask); return 0; } static int mark_stack_write(struct func_instance *instance, u32 frame, u32 insn_idx, spis_t mask) { struct per_frame_masks *masks; masks = alloc_frame_masks(instance, frame, insn_idx); if (IS_ERR(masks)) return PTR_ERR(masks); masks->must_write = spis_or(masks->must_write, mask); return 0; } int bpf_jmp_offset(struct bpf_insn *insn) { u8 code = insn->code; if (code == (BPF_JMP32 | BPF_JA)) return insn->imm; return insn->off; } __diag_push(); __diag_ignore_all("-Woverride-init", "Allow field initialization overrides for opcode_info_tbl"); /* * Returns an array of instructions succ, with succ->items[0], ..., * succ->items[n-1] with successor instructions, where n=succ->cnt */ inline struct bpf_iarray * bpf_insn_successors(struct bpf_verifier_env *env, u32 idx) { static const struct opcode_info { bool can_jump; bool can_fallthrough; } opcode_info_tbl[256] = { [0 ... 255] = {.can_jump = false, .can_fallthrough = true}, #define _J(code, ...) \ [BPF_JMP | code] = __VA_ARGS__, \ [BPF_JMP32 | code] = __VA_ARGS__ _J(BPF_EXIT, {.can_jump = false, .can_fallthrough = false}), _J(BPF_JA, {.can_jump = true, .can_fallthrough = false}), _J(BPF_JEQ, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JNE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JLT, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JLE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JGT, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JGE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSGT, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSGE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSLT, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSLE, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JCOND, {.can_jump = true, .can_fallthrough = true}), _J(BPF_JSET, {.can_jump = true, .can_fallthrough = true}), #undef _J }; struct bpf_prog *prog = env->prog; struct bpf_insn *insn = &prog->insnsi[idx]; const struct opcode_info *opcode_info; struct bpf_iarray *succ, *jt; int insn_sz; jt = env->insn_aux_data[idx].jt; if (unlikely(jt)) return jt; /* pre-allocated array of size up to 2; reset cnt, as it may have been used already */ succ = env->succ; succ->cnt = 0; opcode_info = &opcode_info_tbl[BPF_CLASS(insn->code) | BPF_OP(insn->code)]; insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; if (opcode_info->can_fallthrough) succ->items[succ->cnt++] = idx + insn_sz; if (opcode_info->can_jump) succ->items[succ->cnt++] = idx + bpf_jmp_offset(insn) + 1; return succ; } __diag_pop(); static inline bool update_insn(struct bpf_verifier_env *env, struct func_instance *instance, u32 frame, u32 insn_idx) { spis_t new_before, new_after; struct per_frame_masks *insn, *succ_insn; struct bpf_iarray *succ; u32 s; bool changed; succ = bpf_insn_successors(env, insn_idx); if (succ->cnt == 0) return false; changed = false; insn = get_frame_masks(instance, frame, insn_idx); new_before = SPIS_ZERO; new_after = SPIS_ZERO; for (s = 0; s < succ->cnt; ++s) { succ_insn = get_frame_masks(instance, frame, succ->items[s]); new_after = spis_or(new_after, succ_insn->live_before); } /* * New "live_before" is a union of all "live_before" of successors * minus slots written by instruction plus slots read by instruction. * new_before = (new_after & ~insn->must_write) | insn->may_read */ new_before = spis_or(spis_and(new_after, spis_not(insn->must_write)), insn->may_read); changed |= !spis_equal(new_before, insn->live_before); insn->live_before = new_before; return changed; } /* Fixed-point computation of @live_before marks */ static void update_instance(struct bpf_verifier_env *env, struct func_instance *instance) { u32 i, frame, po_start, po_end; int *insn_postorder = env->cfg.insn_postorder; struct bpf_subprog_info *subprog; bool changed; instance->must_write_initialized = true; subprog = &env->subprog_info[instance->subprog]; po_start = subprog->postorder_start; po_end = (subprog + 1)->postorder_start; /* repeat until fixed point is reached */ do { changed = false; for (frame = 0; frame <= instance->depth; frame++) { if (!instance->frames[frame]) continue; for (i = po_start; i < po_end; i++) changed |= update_insn(env, instance, frame, insn_postorder[i]); } } while (changed); } static bool is_live_before(struct func_instance *instance, u32 insn_idx, u32 frameno, u32 half_spi) { struct per_frame_masks *masks; masks = get_frame_masks(instance, frameno, insn_idx); return masks && spis_test_bit(masks->live_before, half_spi); } int bpf_live_stack_query_init(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { struct live_stack_query *q = &env->liveness->live_stack_query; struct func_instance *instance; u32 frame; memset(q, 0, sizeof(*q)); for (frame = 0; frame <= st->curframe; frame++) { instance = lookup_instance(env, st, frame); if (IS_ERR_OR_NULL(instance)) q->instances[frame] = NULL; else q->instances[frame] = instance; if (frame < st->curframe) q->callsites[frame] = st->frame[frame + 1]->callsite; } q->curframe = st->curframe; q->insn_idx = st->insn_idx; return 0; } bool bpf_stack_slot_alive(struct bpf_verifier_env *env, u32 frameno, u32 half_spi) { /* * Slot is alive if it is read before q->insn_idx in current func instance, * or if for some outer func instance: * - alive before callsite if callsite calls callback, otherwise * - alive after callsite */ struct live_stack_query *q = &env->liveness->live_stack_query; struct func_instance *instance, *curframe_instance; u32 i, callsite, rel; int cur_delta, delta; bool alive = false; curframe_instance = q->instances[q->curframe]; if (!curframe_instance) return true; cur_delta = (int)curframe_instance->depth - (int)q->curframe; rel = frameno + cur_delta; if (rel <= curframe_instance->depth) alive = is_live_before(curframe_instance, q->insn_idx, rel, half_spi); if (alive) return true; for (i = frameno; i < q->curframe; i++) { instance = q->instances[i]; if (!instance) return true; /* Map actual frameno to frame index within this instance */ delta = (int)instance->depth - (int)i; rel = frameno + delta; if (rel > instance->depth) return true; /* Get callsite from verifier state, not from instance callchain */ callsite = q->callsites[i]; alive = bpf_calls_callback(env, callsite) ? is_live_before(instance, callsite, rel, half_spi) : is_live_before(instance, callsite + 1, rel, half_spi); if (alive) return true; } return false; } static char *fmt_subprog(struct bpf_verifier_env *env, int subprog) { const char *name = env->subprog_info[subprog].name; snprintf(env->tmp_str_buf, sizeof(env->tmp_str_buf), "subprog#%d%s%s", subprog, name ? " " : "", name ? name : ""); return env->tmp_str_buf; } static char *fmt_instance(struct bpf_verifier_env *env, struct func_instance *instance) { snprintf(env->tmp_str_buf, sizeof(env->tmp_str_buf), "(d%d,cs%d)", instance->depth, instance->callsite); return env->tmp_str_buf; } static int spi_off(int spi) { return -(spi + 1) * BPF_REG_SIZE; } /* * When both halves of an 8-byte SPI are set, print as "-8","-16",... * When only one half is set, print as "-4h","-8h",... * Runs of 3+ consecutive fully-set SPIs are collapsed: "fp0-8..-24" */ static char *fmt_spis_mask(struct bpf_verifier_env *env, int frame, bool first, spis_t spis) { int buf_sz = sizeof(env->tmp_str_buf); char *buf = env->tmp_str_buf; int spi, n, run_start; buf[0] = '\0'; for (spi = 0; spi < STACK_SLOTS / 2 && buf_sz > 0; spi++) { bool lo = spis_test_bit(spis, spi * 2); bool hi = spis_test_bit(spis, spi * 2 + 1); const char *space = first ? "" : " "; if (!lo && !hi) continue; if (!lo || !hi) { /* half-spi */ n = scnprintf(buf, buf_sz, "%sfp%d%d%s", space, frame, spi_off(spi) + (lo ? STACK_SLOT_SZ : 0), "h"); } else if (spi + 2 < STACK_SLOTS / 2 && spis_test_bit(spis, spi * 2 + 2) && spis_test_bit(spis, spi * 2 + 3) && spis_test_bit(spis, spi * 2 + 4) && spis_test_bit(spis, spi * 2 + 5)) { /* 3+ consecutive full spis */ run_start = spi; while (spi + 1 < STACK_SLOTS / 2 && spis_test_bit(spis, (spi + 1) * 2) && spis_test_bit(spis, (spi + 1) * 2 + 1)) spi++; n = scnprintf(buf, buf_sz, "%sfp%d%d..%d", space, frame, spi_off(run_start), spi_off(spi)); } else { /* just a full spi */ n = scnprintf(buf, buf_sz, "%sfp%d%d", space, frame, spi_off(spi)); } first = false; buf += n; buf_sz -= n; } return env->tmp_str_buf; } static void print_instance(struct bpf_verifier_env *env, struct func_instance *instance) { int start = env->subprog_info[instance->subprog].start; struct bpf_insn *insns = env->prog->insnsi; struct per_frame_masks *masks; int len = instance->insn_cnt; int insn_idx, frame, i; bool has_use, has_def; u64 pos, insn_pos; if (!(env->log.level & BPF_LOG_LEVEL2)) return; verbose(env, "stack use/def %s ", fmt_subprog(env, instance->subprog)); verbose(env, "%s:\n", fmt_instance(env, instance)); for (i = 0; i < len; i++) { insn_idx = start + i; has_use = false; has_def = false; pos = env->log.end_pos; verbose(env, "%3d: ", insn_idx); bpf_verbose_insn(env, &insns[insn_idx]); bpf_vlog_reset(&env->log, env->log.end_pos - 1); /* remove \n */ insn_pos = env->log.end_pos; verbose(env, "%*c;", bpf_vlog_alignment(insn_pos - pos), ' '); pos = env->log.end_pos; verbose(env, " use: "); for (frame = instance->depth; frame >= 0; --frame) { masks = get_frame_masks(instance, frame, insn_idx); if (!masks || spis_is_zero(masks->may_read)) continue; verbose(env, "%s", fmt_spis_mask(env, frame, !has_use, masks->may_read)); has_use = true; } if (!has_use) bpf_vlog_reset(&env->log, pos); pos = env->log.end_pos; verbose(env, " def: "); for (frame = instance->depth; frame >= 0; --frame) { masks = get_frame_masks(instance, frame, insn_idx); if (!masks || spis_is_zero(masks->must_write)) continue; verbose(env, "%s", fmt_spis_mask(env, frame, !has_def, masks->must_write)); has_def = true; } if (!has_def) bpf_vlog_reset(&env->log, has_use ? pos : insn_pos); verbose(env, "\n"); if (bpf_is_ldimm64(&insns[insn_idx])) i++; } } static int cmp_instances(const void *pa, const void *pb) { struct func_instance *a = *(struct func_instance **)pa; struct func_instance *b = *(struct func_instance **)pb; int dcallsite = (int)a->callsite - b->callsite; int ddepth = (int)a->depth - b->depth; if (dcallsite) return dcallsite; if (ddepth) return ddepth; return 0; } /* print use/def slots for all instances ordered by callsite first, then by depth */ static int print_instances(struct bpf_verifier_env *env) { struct func_instance *instance, **sorted_instances; struct bpf_liveness *liveness = env->liveness; int i, bkt, cnt; cnt = 0; hash_for_each(liveness->func_instances, bkt, instance, hl_node) cnt++; sorted_instances = kvmalloc_objs(*sorted_instances, cnt, GFP_KERNEL_ACCOUNT); if (!sorted_instances) return -ENOMEM; cnt = 0; hash_for_each(liveness->func_instances, bkt, instance, hl_node) sorted_instances[cnt++] = instance; sort(sorted_instances, cnt, sizeof(*sorted_instances), cmp_instances, NULL); for (i = 0; i < cnt; i++) print_instance(env, sorted_instances[i]); kvfree(sorted_instances); return 0; } /* * Per-register tracking state for compute_subprog_args(). * Tracks which frame's FP a value is derived from * and the byte offset from that frame's FP. * * The .frame field forms a lattice with three levels of precision: * * precise {frame=N, off=V} -- known absolute frame index and byte offset * | * offset-imprecise {frame=N, cnt=0} * | -- known frame identity, unknown offset * fully-imprecise {frame=ARG_IMPRECISE, mask=bitmask} * -- unknown frame identity; .mask is a * bitmask of which frame indices might be * involved * * At CFG merge points, arg_track_join() moves down the lattice: * - same frame + same offset -> precise * - same frame + different offset -> offset-imprecise * - different frames -> fully-imprecise (bitmask OR) * * At memory access sites (LDX/STX/ST), offset-imprecise marks only * the known frame's access mask as SPIS_ALL, while fully-imprecise * iterates bits in the bitmask and routes each frame to its target. */ #define MAX_ARG_OFFSETS 4 struct arg_track { union { s16 off[MAX_ARG_OFFSETS]; /* byte offsets; off_cnt says how many */ u16 mask; /* arg bitmask when arg == ARG_IMPRECISE */ }; s8 frame; /* absolute frame index, or enum arg_track_state */ s8 off_cnt; /* 0 = offset-imprecise, 1-4 = # of precise offsets */ }; enum arg_track_state { ARG_NONE = -1, /* not derived from any argument */ ARG_UNVISITED = -2, /* not yet reached by dataflow */ ARG_IMPRECISE = -3, /* lost identity; .mask is arg bitmask */ }; /* Track callee stack slots fp-8 through fp-512 (64 slots of 8 bytes each) */ #define MAX_ARG_SPILL_SLOTS 64 static bool arg_is_visited(const struct arg_track *at) { return at->frame != ARG_UNVISITED; } static bool arg_is_fp(const struct arg_track *at) { return at->frame >= 0 || at->frame == ARG_IMPRECISE; } static void verbose_arg_track(struct bpf_verifier_env *env, struct arg_track *at) { int i; switch (at->frame) { case ARG_NONE: verbose(env, "_"); break; case ARG_UNVISITED: verbose(env, "?"); break; case ARG_IMPRECISE: verbose(env, "IMP%x", at->mask); break; default: /* frame >= 0: absolute frame index */ if (at->off_cnt == 0) { verbose(env, "fp%d ?", at->frame); } else { for (i = 0; i < at->off_cnt; i++) { if (i) verbose(env, "|"); verbose(env, "fp%d%+d", at->frame, at->off[i]); } } break; } } static bool arg_track_eq(const struct arg_track *a, const struct arg_track *b) { int i; if (a->frame != b->frame) return false; if (a->frame == ARG_IMPRECISE) return a->mask == b->mask; if (a->frame < 0) return true; if (a->off_cnt != b->off_cnt) return false; for (i = 0; i < a->off_cnt; i++) if (a->off[i] != b->off[i]) return false; return true; } static struct arg_track arg_single(s8 arg, s16 off) { struct arg_track at = {}; at.frame = arg; at.off[0] = off; at.off_cnt = 1; return at; } /* * Merge two sorted offset arrays, deduplicate. * Returns off_cnt=0 if the result exceeds MAX_ARG_OFFSETS. * Both args must have the same frame and off_cnt > 0. */ static struct arg_track arg_merge_offsets(struct arg_track a, struct arg_track b) { struct arg_track result = { .frame = a.frame }; struct arg_track imp = { .frame = a.frame }; int i = 0, j = 0, k = 0; while (i < a.off_cnt && j < b.off_cnt) { s16 v; if (a.off[i] <= b.off[j]) { v = a.off[i++]; if (v == b.off[j]) j++; } else { v = b.off[j++]; } if (k > 0 && result.off[k - 1] == v) continue; if (k >= MAX_ARG_OFFSETS) return imp; result.off[k++] = v; } while (i < a.off_cnt) { if (k >= MAX_ARG_OFFSETS) return imp; result.off[k++] = a.off[i++]; } while (j < b.off_cnt) { if (k >= MAX_ARG_OFFSETS) return imp; result.off[k++] = b.off[j++]; } result.off_cnt = k; return result; } /* * Merge two arg_tracks into ARG_IMPRECISE, collecting the frame * bits from both operands. Precise frame indices (frame >= 0) * contribute a single bit; existing ARG_IMPRECISE values * contribute their full bitmask. */ static struct arg_track arg_join_imprecise(struct arg_track a, struct arg_track b) { u32 m = 0; if (a.frame >= 0) m |= BIT(a.frame); else if (a.frame == ARG_IMPRECISE) m |= a.mask; if (b.frame >= 0) m |= BIT(b.frame); else if (b.frame == ARG_IMPRECISE) m |= b.mask; return (struct arg_track){ .mask = m, .frame = ARG_IMPRECISE }; } /* Join two arg_track values at merge points */ static struct arg_track __arg_track_join(struct arg_track a, struct arg_track b) { if (!arg_is_visited(&b)) return a; if (!arg_is_visited(&a)) return b; if (a.frame == b.frame && a.frame >= 0) { /* Both offset-imprecise: stay imprecise */ if (a.off_cnt == 0 || b.off_cnt == 0) return (struct arg_track){ .frame = a.frame }; /* Merge offset sets; falls back to off_cnt=0 if >4 */ return arg_merge_offsets(a, b); } /* * args are different, but one of them is known * arg + none -> arg * none + arg -> arg * * none + none -> none */ if (a.frame == ARG_NONE && b.frame == ARG_NONE) return a; if (a.frame >= 0 && b.frame == ARG_NONE) { /* * When joining single fp-N add fake fp+0 to * keep stack_use and prevent stack_def */ if (a.off_cnt == 1) return arg_merge_offsets(a, arg_single(a.frame, 0)); return a; } if (b.frame >= 0 && a.frame == ARG_NONE) { if (b.off_cnt == 1) return arg_merge_offsets(b, arg_single(b.frame, 0)); return b; } return arg_join_imprecise(a, b); } static bool arg_track_join(struct bpf_verifier_env *env, int idx, int target, int r, struct arg_track *in, struct arg_track out) { struct arg_track old = *in; struct arg_track new_val = __arg_track_join(old, out); if (arg_track_eq(&new_val, &old)) return false; *in = new_val; if (!(env->log.level & BPF_LOG_LEVEL2) || !arg_is_visited(&old)) return true; verbose(env, "arg JOIN insn %d -> %d ", idx, target); if (r >= 0) verbose(env, "r%d: ", r); else verbose(env, "fp%+d: ", r * 8); verbose_arg_track(env, &old); verbose(env, " + "); verbose_arg_track(env, &out); verbose(env, " => "); verbose_arg_track(env, &new_val); verbose(env, "\n"); return true; } /* * Compute the result when an ALU op destroys offset precision. * If a single arg is identifiable, preserve it with OFF_IMPRECISE. * If two different args are involved or one is already ARG_IMPRECISE, * the result is fully ARG_IMPRECISE. */ static void arg_track_alu64(struct arg_track *dst, const struct arg_track *src) { WARN_ON_ONCE(!arg_is_visited(dst)); WARN_ON_ONCE(!arg_is_visited(src)); if (dst->frame >= 0 && (src->frame == ARG_NONE || src->frame == dst->frame)) { /* * rX += rY where rY is not arg derived * rX += rX */ dst->off_cnt = 0; return; } if (src->frame >= 0 && dst->frame == ARG_NONE) { /* * rX += rY where rX is not arg derived * rY identity leaks into rX */ dst->off_cnt = 0; dst->frame = src->frame; return; } if (dst->frame == ARG_NONE && src->frame == ARG_NONE) return; *dst = arg_join_imprecise(*dst, *src); } static bool arg_add(s16 off, s64 delta, s16 *out) { s16 d = delta; if (d != delta) return true; return check_add_overflow(off, d, out); } static void arg_padd(struct arg_track *at, s64 delta) { int i; if (at->off_cnt == 0) return; for (i = 0; i < at->off_cnt; i++) { s16 new_off; if (arg_add(at->off[i], delta, &new_off)) { at->off_cnt = 0; return; } at->off[i] = new_off; } } /* * Convert a byte offset from FP to a callee stack slot index. * Returns -1 if out of range or not 8-byte aligned. * Slot 0 = fp-8, slot 1 = fp-16, ..., slot 7 = fp-64, .... */ static int fp_off_to_slot(s16 off) { if (off >= 0 || off < -(int)(MAX_ARG_SPILL_SLOTS * 8)) return -1; if (off % 8) return -1; return (-off) / 8 - 1; } static struct arg_track fill_from_stack(struct bpf_insn *insn, struct arg_track *at_out, int reg, struct arg_track *at_stack_out, int depth) { struct arg_track imp = { .mask = (1u << (depth + 1)) - 1, .frame = ARG_IMPRECISE }; struct arg_track result = { .frame = ARG_NONE }; int cnt, i; if (reg == BPF_REG_FP) { int slot = fp_off_to_slot(insn->off); return slot >= 0 ? at_stack_out[slot] : imp; } cnt = at_out[reg].off_cnt; if (cnt == 0) return imp; for (i = 0; i < cnt; i++) { s16 fp_off, slot; if (arg_add(at_out[reg].off[i], insn->off, &fp_off)) return imp; slot = fp_off_to_slot(fp_off); if (slot < 0) return imp; result = __arg_track_join(result, at_stack_out[slot]); } return result; } /* * Spill @val to all possible stack slots indicated by the FP offsets in @reg. * For an 8-byte store, single candidate slot gets @val. multi-slots are joined. * sub-8-byte store joins with ARG_NONE. * When exact offset is unknown conservatively add reg values to all slots in at_stack_out. */ static void spill_to_stack(struct bpf_insn *insn, struct arg_track *at_out, int reg, struct arg_track *at_stack_out, struct arg_track *val, u32 sz) { struct arg_track none = { .frame = ARG_NONE }; struct arg_track new_val = sz == 8 ? *val : none; int cnt, i; if (reg == BPF_REG_FP) { int slot = fp_off_to_slot(insn->off); if (slot >= 0) at_stack_out[slot] = new_val; return; } cnt = at_out[reg].off_cnt; if (cnt == 0) { for (int slot = 0; slot < MAX_ARG_SPILL_SLOTS; slot++) at_stack_out[slot] = __arg_track_join(at_stack_out[slot], new_val); return; } for (i = 0; i < cnt; i++) { s16 fp_off; int slot; if (arg_add(at_out[reg].off[i], insn->off, &fp_off)) continue; slot = fp_off_to_slot(fp_off); if (slot < 0) continue; if (cnt == 1) at_stack_out[slot] = new_val; else at_stack_out[slot] = __arg_track_join(at_stack_out[slot], new_val); } } /* * Clear all tracked callee stack slots overlapping the byte range * [off, off+sz-1] where off is a negative FP-relative offset. */ static void clear_overlapping_stack_slots(struct arg_track *at_stack, s16 off, u32 sz, int cnt) { struct arg_track none = { .frame = ARG_NONE }; if (cnt == 0) { for (int i = 0; i < MAX_ARG_SPILL_SLOTS; i++) at_stack[i] = __arg_track_join(at_stack[i], none); return; } for (int i = 0; i < MAX_ARG_SPILL_SLOTS; i++) { int slot_start = -((i + 1) * 8); int slot_end = slot_start + 8; if (slot_start < off + (int)sz && slot_end > off) { if (cnt == 1) at_stack[i] = none; else at_stack[i] = __arg_track_join(at_stack[i], none); } } } /* * Clear stack slots overlapping all possible FP offsets in @reg. */ static void clear_stack_for_all_offs(struct bpf_insn *insn, struct arg_track *at_out, int reg, struct arg_track *at_stack_out, u32 sz) { int cnt, i; if (reg == BPF_REG_FP) { clear_overlapping_stack_slots(at_stack_out, insn->off, sz, 1); return; } cnt = at_out[reg].off_cnt; if (cnt == 0) { clear_overlapping_stack_slots(at_stack_out, 0, sz, cnt); return; } for (i = 0; i < cnt; i++) { s16 fp_off; if (arg_add(at_out[reg].off[i], insn->off, &fp_off)) { clear_overlapping_stack_slots(at_stack_out, 0, sz, 0); break; } clear_overlapping_stack_slots(at_stack_out, fp_off, sz, cnt); } } static void arg_track_log(struct bpf_verifier_env *env, struct bpf_insn *insn, int idx, struct arg_track *at_in, struct arg_track *at_stack_in, struct arg_track *at_out, struct arg_track *at_stack_out) { bool printed = false; int i; if (!(env->log.level & BPF_LOG_LEVEL2)) return; for (i = 0; i < MAX_BPF_REG; i++) { if (arg_track_eq(&at_out[i], &at_in[i])) continue; if (!printed) { verbose(env, "%3d: ", idx); bpf_verbose_insn(env, insn); bpf_vlog_reset(&env->log, env->log.end_pos - 1); printed = true; } verbose(env, "\tr%d: ", i); verbose_arg_track(env, &at_in[i]); verbose(env, " -> "); verbose_arg_track(env, &at_out[i]); } for (i = 0; i < MAX_ARG_SPILL_SLOTS; i++) { if (arg_track_eq(&at_stack_out[i], &at_stack_in[i])) continue; if (!printed) { verbose(env, "%3d: ", idx); bpf_verbose_insn(env, insn); bpf_vlog_reset(&env->log, env->log.end_pos - 1); printed = true; } verbose(env, "\tfp%+d: ", -(i + 1) * 8); verbose_arg_track(env, &at_stack_in[i]); verbose(env, " -> "); verbose_arg_track(env, &at_stack_out[i]); } if (printed) verbose(env, "\n"); } static bool can_be_local_fp(int depth, int regno, struct arg_track *at) { return regno == BPF_REG_FP || at->frame == depth || (at->frame == ARG_IMPRECISE && (at->mask & BIT(depth))); } /* * Pure dataflow transfer function for arg_track state. * Updates at_out[] based on how the instruction modifies registers. * Tracks spill/fill, but not other memory accesses. */ static void arg_track_xfer(struct bpf_verifier_env *env, struct bpf_insn *insn, int insn_idx, struct arg_track *at_out, struct arg_track *at_stack_out, struct func_instance *instance, u32 *callsites) { int depth = instance->depth; u8 class = BPF_CLASS(insn->code); u8 code = BPF_OP(insn->code); struct arg_track *dst = &at_out[insn->dst_reg]; struct arg_track *src = &at_out[insn->src_reg]; struct arg_track none = { .frame = ARG_NONE }; int r; if (class == BPF_ALU64 && BPF_SRC(insn->code) == BPF_K) { if (code == BPF_MOV) { *dst = none; } else if (dst->frame >= 0) { if (code == BPF_ADD) arg_padd(dst, insn->imm); else if (code == BPF_SUB) arg_padd(dst, -(s64)insn->imm); else /* Any other 64-bit alu on the pointer makes it imprecise */ dst->off_cnt = 0; } /* else if dst->frame is imprecise it stays so */ } else if (class == BPF_ALU64 && BPF_SRC(insn->code) == BPF_X) { if (code == BPF_MOV) { if (insn->off == 0) { *dst = *src; } else { /* addr_space_cast destroys a pointer */ *dst = none; } } else { arg_track_alu64(dst, src); } } else if (class == BPF_ALU) { /* * 32-bit alu destroys the pointer. * If src was a pointer it cannot leak into dst */ *dst = none; } else if (class == BPF_JMP && code == BPF_CALL) { /* * at_stack_out[slot] is not cleared by the helper and subprog calls. * The fill_from_stack() may return the stale spill — which is an FP-derived arg_track * (the value that was originally spilled there). The loaded register then carries * a phantom FP-derived identity that doesn't correspond to what's actually in the slot. * This phantom FP pointer propagates forward, and wherever it's subsequently used * (as a helper argument, another store, etc.), it sets stack liveness bits. * Those bits correspond to stack accesses that don't actually happen. * So the effect is over-reporting stack liveness — marking slots as live that aren't * actually accessed. The verifier preserves more state than necessary across calls, * which is conservative. * * helpers can scratch stack slots, but they won't make a valid pointer out of it. * subprogs are allowed to write into parent slots, but they cannot write * _any_ FP-derived pointer into it (either their own or parent's FP). */ for (r = BPF_REG_0; r <= BPF_REG_5; r++) at_out[r] = none; } else if (class == BPF_LDX) { u32 sz = bpf_size_to_bytes(BPF_SIZE(insn->code)); bool src_is_local_fp = can_be_local_fp(depth, insn->src_reg, src); /* * Reload from callee stack: if src is current-frame FP-derived * and the load is an 8-byte BPF_MEM, try to restore the spill * identity. For imprecise sources fill_from_stack() returns * ARG_IMPRECISE (off_cnt == 0). */ if (src_is_local_fp && BPF_MODE(insn->code) == BPF_MEM && sz == 8) { *dst = fill_from_stack(insn, at_out, insn->src_reg, at_stack_out, depth); } else if (src->frame >= 0 && src->frame < depth && BPF_MODE(insn->code) == BPF_MEM && sz == 8) { struct arg_track *parent_stack = env->callsite_at_stack[callsites[src->frame]]; *dst = fill_from_stack(insn, at_out, insn->src_reg, parent_stack, src->frame); } else if (src->frame == ARG_IMPRECISE && !(src->mask & BIT(depth)) && src->mask && BPF_MODE(insn->code) == BPF_MEM && sz == 8) { /* * Imprecise src with only parent-frame bits: * conservative fallback. */ *dst = *src; } else { *dst = none; } } else if (class == BPF_LD && BPF_MODE(insn->code) == BPF_IMM) { *dst = none; } else if (class == BPF_STX) { u32 sz = bpf_size_to_bytes(BPF_SIZE(insn->code)); bool dst_is_local_fp; /* Track spills to current-frame FP-derived callee stack */ dst_is_local_fp = can_be_local_fp(depth, insn->dst_reg, dst); if (dst_is_local_fp && BPF_MODE(insn->code) == BPF_MEM) spill_to_stack(insn, at_out, insn->dst_reg, at_stack_out, src, sz); if (BPF_MODE(insn->code) == BPF_ATOMIC) { if (dst_is_local_fp && insn->imm != BPF_LOAD_ACQ) clear_stack_for_all_offs(insn, at_out, insn->dst_reg, at_stack_out, sz); if (insn->imm == BPF_CMPXCHG) at_out[BPF_REG_0] = none; else if (insn->imm == BPF_LOAD_ACQ) *dst = none; else if (insn->imm & BPF_FETCH) *src = none; } } else if (class == BPF_ST && BPF_MODE(insn->code) == BPF_MEM) { u32 sz = bpf_size_to_bytes(BPF_SIZE(insn->code)); bool dst_is_local_fp = can_be_local_fp(depth, insn->dst_reg, dst); /* BPF_ST to FP-derived dst: clear overlapping stack slots */ if (dst_is_local_fp) clear_stack_for_all_offs(insn, at_out, insn->dst_reg, at_stack_out, sz); } } /* * Record access_bytes from helper/kfunc or load/store insn. * access_bytes > 0: stack read * access_bytes < 0: stack write * access_bytes == S64_MIN: unknown — conservative, mark [0..slot] as read * access_bytes == 0: no access * */ static int record_stack_access_off(struct func_instance *instance, s64 fp_off, s64 access_bytes, u32 frame, u32 insn_idx) { s32 slot_hi, slot_lo; spis_t mask; if (fp_off >= 0) /* * out of bounds stack access doesn't contribute * into actual stack liveness. It will be rejected * by the main verifier pass later. */ return 0; if (access_bytes == S64_MIN) { /* helper/kfunc read unknown amount of bytes from fp_off until fp+0 */ slot_hi = (-fp_off - 1) / STACK_SLOT_SZ; mask = SPIS_ZERO; spis_or_range(&mask, 0, slot_hi); return mark_stack_read(instance, frame, insn_idx, mask); } if (access_bytes > 0) { /* Mark any touched slot as use */ slot_hi = (-fp_off - 1) / STACK_SLOT_SZ; slot_lo = max_t(s32, (-fp_off - access_bytes) / STACK_SLOT_SZ, 0); mask = SPIS_ZERO; spis_or_range(&mask, slot_lo, slot_hi); return mark_stack_read(instance, frame, insn_idx, mask); } else if (access_bytes < 0) { /* Mark only fully covered slots as def */ access_bytes = -access_bytes; slot_hi = (-fp_off) / STACK_SLOT_SZ - 1; slot_lo = max_t(s32, (-fp_off - access_bytes + STACK_SLOT_SZ - 1) / STACK_SLOT_SZ, 0); if (slot_lo <= slot_hi) { mask = SPIS_ZERO; spis_or_range(&mask, slot_lo, slot_hi); return mark_stack_write(instance, frame, insn_idx, mask); } } return 0; } /* * 'arg' is FP-derived argument to helper/kfunc or load/store that * reads (positive) or writes (negative) 'access_bytes' into 'use' or 'def'. */ static int record_stack_access(struct func_instance *instance, const struct arg_track *arg, s64 access_bytes, u32 frame, u32 insn_idx) { int i, err; if (access_bytes == 0) return 0; if (arg->off_cnt == 0) { if (access_bytes > 0 || access_bytes == S64_MIN) return mark_stack_read(instance, frame, insn_idx, SPIS_ALL); return 0; } if (access_bytes != S64_MIN && access_bytes < 0 && arg->off_cnt != 1) /* multi-offset write cannot set stack_def */ return 0; for (i = 0; i < arg->off_cnt; i++) { err = record_stack_access_off(instance, arg->off[i], access_bytes, frame, insn_idx); if (err) return err; } return 0; } /* * When a pointer is ARG_IMPRECISE, conservatively mark every frame in * the bitmask as fully used. */ static int record_imprecise(struct func_instance *instance, u32 mask, u32 insn_idx) { int depth = instance->depth; int f, err; for (f = 0; mask; f++, mask >>= 1) { if (!(mask & 1)) continue; if (f <= depth) { err = mark_stack_read(instance, f, insn_idx, SPIS_ALL); if (err) return err; } } return 0; } /* Record load/store access for a given 'at' state of 'insn'. */ static int record_load_store_access(struct bpf_verifier_env *env, struct func_instance *instance, struct arg_track *at, int insn_idx) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int depth = instance->depth; s32 sz = bpf_size_to_bytes(BPF_SIZE(insn->code)); u8 class = BPF_CLASS(insn->code); struct arg_track resolved, *ptr; int oi; switch (class) { case BPF_LDX: ptr = &at[insn->src_reg]; break; case BPF_STX: if (BPF_MODE(insn->code) == BPF_ATOMIC) { if (insn->imm == BPF_STORE_REL) sz = -sz; if (insn->imm == BPF_LOAD_ACQ) ptr = &at[insn->src_reg]; else ptr = &at[insn->dst_reg]; } else { ptr = &at[insn->dst_reg]; sz = -sz; } break; case BPF_ST: ptr = &at[insn->dst_reg]; sz = -sz; break; default: return 0; } /* Resolve offsets: fold insn->off into arg_track */ if (ptr->off_cnt > 0) { resolved.off_cnt = ptr->off_cnt; resolved.frame = ptr->frame; for (oi = 0; oi < ptr->off_cnt; oi++) { if (arg_add(ptr->off[oi], insn->off, &resolved.off[oi])) { resolved.off_cnt = 0; break; } } ptr = &resolved; } if (ptr->frame >= 0 && ptr->frame <= depth) return record_stack_access(instance, ptr, sz, ptr->frame, insn_idx); if (ptr->frame == ARG_IMPRECISE) return record_imprecise(instance, ptr->mask, insn_idx); /* ARG_NONE: not derived from any frame pointer, skip */ return 0; } /* Record stack access for a given 'at' state of helper/kfunc 'insn' */ static int record_call_access(struct bpf_verifier_env *env, struct func_instance *instance, struct arg_track *at, int insn_idx) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int depth = instance->depth; struct bpf_call_summary cs; int r, err = 0, num_params = 5; if (bpf_pseudo_call(insn)) return 0; if (bpf_get_call_summary(env, insn, &cs)) num_params = cs.num_params; for (r = BPF_REG_1; r < BPF_REG_1 + num_params; r++) { int frame = at[r].frame; s64 bytes; if (!arg_is_fp(&at[r])) continue; if (bpf_helper_call(insn)) { bytes = bpf_helper_stack_access_bytes(env, insn, r - 1, insn_idx); } else if (bpf_pseudo_kfunc_call(insn)) { bytes = bpf_kfunc_stack_access_bytes(env, insn, r - 1, insn_idx); } else { for (int f = 0; f <= depth; f++) { err = mark_stack_read(instance, f, insn_idx, SPIS_ALL); if (err) return err; } return 0; } if (bytes == 0) continue; if (frame >= 0 && frame <= depth) err = record_stack_access(instance, &at[r], bytes, frame, insn_idx); else if (frame == ARG_IMPRECISE) err = record_imprecise(instance, at[r].mask, insn_idx); if (err) return err; } return 0; } /* * For a calls_callback helper, find the callback subprog and determine * which caller register maps to which callback register for FP passthrough. */ static int find_callback_subprog(struct bpf_verifier_env *env, struct bpf_insn *insn, int insn_idx, int *caller_reg, int *callee_reg) { struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; int cb_reg = -1; *caller_reg = -1; *callee_reg = -1; if (!bpf_helper_call(insn)) return -1; switch (insn->imm) { case BPF_FUNC_loop: /* bpf_loop(nr, cb, ctx, flags): cb=R2, R3->cb R2 */ cb_reg = BPF_REG_2; *caller_reg = BPF_REG_3; *callee_reg = BPF_REG_2; break; case BPF_FUNC_for_each_map_elem: /* for_each_map_elem(map, cb, ctx, flags): cb=R2, R3->cb R4 */ cb_reg = BPF_REG_2; *caller_reg = BPF_REG_3; *callee_reg = BPF_REG_4; break; case BPF_FUNC_find_vma: /* find_vma(task, addr, cb, ctx, flags): cb=R3, R4->cb R3 */ cb_reg = BPF_REG_3; *caller_reg = BPF_REG_4; *callee_reg = BPF_REG_3; break; case BPF_FUNC_user_ringbuf_drain: /* user_ringbuf_drain(map, cb, ctx, flags): cb=R2, R3->cb R2 */ cb_reg = BPF_REG_2; *caller_reg = BPF_REG_3; *callee_reg = BPF_REG_2; break; default: return -1; } if (!(aux->const_reg_subprog_mask & BIT(cb_reg))) return -2; return aux->const_reg_vals[cb_reg]; } /* Per-subprog intermediate state kept alive across analysis phases */ struct subprog_at_info { struct arg_track (*at_in)[MAX_BPF_REG]; int len; }; static void print_subprog_arg_access(struct bpf_verifier_env *env, int subprog, struct subprog_at_info *info, struct arg_track (*at_stack_in)[MAX_ARG_SPILL_SLOTS]) { struct bpf_insn *insns = env->prog->insnsi; int start = env->subprog_info[subprog].start; int len = info->len; int i, r; if (!(env->log.level & BPF_LOG_LEVEL2)) return; verbose(env, "%s:\n", fmt_subprog(env, subprog)); for (i = 0; i < len; i++) { int idx = start + i; bool has_extra = false; u8 cls = BPF_CLASS(insns[idx].code); bool is_ldx_stx_call = cls == BPF_LDX || cls == BPF_STX || insns[idx].code == (BPF_JMP | BPF_CALL); verbose(env, "%3d: ", idx); bpf_verbose_insn(env, &insns[idx]); /* Collect what needs printing */ if (is_ldx_stx_call && arg_is_visited(&info->at_in[i][0])) { for (r = 0; r < MAX_BPF_REG - 1; r++) if (arg_is_fp(&info->at_in[i][r])) has_extra = true; } if (is_ldx_stx_call) { for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) if (arg_is_fp(&at_stack_in[i][r])) has_extra = true; } if (!has_extra) { if (bpf_is_ldimm64(&insns[idx])) i++; continue; } bpf_vlog_reset(&env->log, env->log.end_pos - 1); verbose(env, " //"); if (is_ldx_stx_call && info->at_in && arg_is_visited(&info->at_in[i][0])) { for (r = 0; r < MAX_BPF_REG - 1; r++) { if (!arg_is_fp(&info->at_in[i][r])) continue; verbose(env, " r%d=", r); verbose_arg_track(env, &info->at_in[i][r]); } } if (is_ldx_stx_call) { for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) { if (!arg_is_fp(&at_stack_in[i][r])) continue; verbose(env, " fp%+d=", -(r + 1) * 8); verbose_arg_track(env, &at_stack_in[i][r]); } } verbose(env, "\n"); if (bpf_is_ldimm64(&insns[idx])) i++; } } /* * Compute arg tracking dataflow for a single subprog. * Runs forward fixed-point with arg_track_xfer(), then records * memory accesses in a single linear pass over converged state. * * @callee_entry: pre-populated entry state for R1-R5 * NULL for main (subprog 0). * @info: stores at_in, len for debug printing. */ static int compute_subprog_args(struct bpf_verifier_env *env, struct subprog_at_info *info, struct arg_track *callee_entry, struct func_instance *instance, u32 *callsites) { int subprog = instance->subprog; struct bpf_insn *insns = env->prog->insnsi; int depth = instance->depth; int start = env->subprog_info[subprog].start; int po_start = env->subprog_info[subprog].postorder_start; int end = env->subprog_info[subprog + 1].start; int po_end = env->subprog_info[subprog + 1].postorder_start; int len = end - start; struct arg_track (*at_in)[MAX_BPF_REG] = NULL; struct arg_track at_out[MAX_BPF_REG]; struct arg_track (*at_stack_in)[MAX_ARG_SPILL_SLOTS] = NULL; struct arg_track *at_stack_out = NULL; struct arg_track unvisited = { .frame = ARG_UNVISITED }; struct arg_track none = { .frame = ARG_NONE }; bool changed; int i, p, r, err = -ENOMEM; at_in = kvmalloc_objs(*at_in, len, GFP_KERNEL_ACCOUNT); if (!at_in) goto err_free; at_stack_in = kvmalloc_objs(*at_stack_in, len, GFP_KERNEL_ACCOUNT); if (!at_stack_in) goto err_free; at_stack_out = kvmalloc_objs(*at_stack_out, MAX_ARG_SPILL_SLOTS, GFP_KERNEL_ACCOUNT); if (!at_stack_out) goto err_free; for (i = 0; i < len; i++) { for (r = 0; r < MAX_BPF_REG; r++) at_in[i][r] = unvisited; for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) at_stack_in[i][r] = unvisited; } for (r = 0; r < MAX_BPF_REG; r++) at_in[0][r] = none; /* Entry: R10 is always precisely the current frame's FP */ at_in[0][BPF_REG_FP] = arg_single(depth, 0); /* R1-R5: from caller or ARG_NONE for main */ if (callee_entry) { for (r = BPF_REG_1; r <= BPF_REG_5; r++) at_in[0][r] = callee_entry[r]; } /* Entry: all stack slots are ARG_NONE */ for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) at_stack_in[0][r] = none; if (env->log.level & BPF_LOG_LEVEL2) verbose(env, "subprog#%d: analyzing (depth %d)...\n", subprog, depth); /* Forward fixed-point iteration in reverse post order */ redo: changed = false; for (p = po_end - 1; p >= po_start; p--) { int idx = env->cfg.insn_postorder[p]; int i = idx - start; struct bpf_insn *insn = &insns[idx]; struct bpf_iarray *succ; if (!arg_is_visited(&at_in[i][0]) && !arg_is_visited(&at_in[i][1])) continue; memcpy(at_out, at_in[i], sizeof(at_out)); memcpy(at_stack_out, at_stack_in[i], MAX_ARG_SPILL_SLOTS * sizeof(*at_stack_out)); arg_track_xfer(env, insn, idx, at_out, at_stack_out, instance, callsites); arg_track_log(env, insn, idx, at_in[i], at_stack_in[i], at_out, at_stack_out); /* Propagate to successors within this subprogram */ succ = bpf_insn_successors(env, idx); for (int s = 0; s < succ->cnt; s++) { int target = succ->items[s]; int ti; /* Filter: stay within the subprogram's range */ if (target < start || target >= end) continue; ti = target - start; for (r = 0; r < MAX_BPF_REG; r++) changed |= arg_track_join(env, idx, target, r, &at_in[ti][r], at_out[r]); for (r = 0; r < MAX_ARG_SPILL_SLOTS; r++) changed |= arg_track_join(env, idx, target, -r - 1, &at_stack_in[ti][r], at_stack_out[r]); } } if (changed) goto redo; /* Record memory accesses using converged at_in (RPO skips dead code) */ for (p = po_end - 1; p >= po_start; p--) { int idx = env->cfg.insn_postorder[p]; int i = idx - start; struct bpf_insn *insn = &insns[idx]; err = record_load_store_access(env, instance, at_in[i], idx); if (err) goto err_free; if (insn->code == (BPF_JMP | BPF_CALL)) { err = record_call_access(env, instance, at_in[i], idx); if (err) goto err_free; } if (bpf_pseudo_call(insn) || bpf_calls_callback(env, idx)) { kvfree(env->callsite_at_stack[idx]); env->callsite_at_stack[idx] = kvmalloc_objs(*env->callsite_at_stack[idx], MAX_ARG_SPILL_SLOTS, GFP_KERNEL_ACCOUNT); if (!env->callsite_at_stack[idx]) { err = -ENOMEM; goto err_free; } memcpy(env->callsite_at_stack[idx], at_stack_in[i], sizeof(struct arg_track) * MAX_ARG_SPILL_SLOTS); } } info->at_in = at_in; at_in = NULL; info->len = len; print_subprog_arg_access(env, subprog, info, at_stack_in); err = 0; err_free: kvfree(at_stack_out); kvfree(at_stack_in); kvfree(at_in); return err; } /* Return true if any of R1-R5 is derived from a frame pointer. */ static bool has_fp_args(struct arg_track *args) { for (int r = BPF_REG_1; r <= BPF_REG_5; r++) if (args[r].frame != ARG_NONE) return true; return false; } /* * Merge a freshly analyzed instance into the original. * may_read: union (any pass might read the slot). * must_write: intersection (only slots written on ALL passes are guaranteed). * live_before is recomputed by a subsequent update_instance() on @dst. */ static void merge_instances(struct func_instance *dst, struct func_instance *src) { int f, i; for (f = 0; f <= dst->depth; f++) { if (!src->frames[f]) { /* This pass didn't touch frame f — must_write intersects with empty. */ if (dst->frames[f]) for (i = 0; i < dst->insn_cnt; i++) dst->frames[f][i].must_write = SPIS_ZERO; continue; } if (!dst->frames[f]) { /* Previous pass didn't touch frame f — take src, zero must_write. */ dst->frames[f] = src->frames[f]; src->frames[f] = NULL; for (i = 0; i < dst->insn_cnt; i++) dst->frames[f][i].must_write = SPIS_ZERO; continue; } for (i = 0; i < dst->insn_cnt; i++) { dst->frames[f][i].may_read = spis_or(dst->frames[f][i].may_read, src->frames[f][i].may_read); dst->frames[f][i].must_write = spis_and(dst->frames[f][i].must_write, src->frames[f][i].must_write); } } } static struct func_instance *fresh_instance(struct func_instance *src) { struct func_instance *f; f = kvzalloc_obj(*f, GFP_KERNEL_ACCOUNT); if (!f) return ERR_PTR(-ENOMEM); f->callsite = src->callsite; f->depth = src->depth; f->subprog = src->subprog; f->subprog_start = src->subprog_start; f->insn_cnt = src->insn_cnt; return f; } static void free_instance(struct func_instance *instance) { int i; for (i = 0; i <= instance->depth; i++) kvfree(instance->frames[i]); kvfree(instance); } /* * Recursively analyze a subprog with specific 'entry_args'. * Each callee is analyzed with the exact args from its call site. * * Args are recomputed for each call because the dataflow result at_in[] * depends on the entry args and frame depth. Consider: A->C->D and B->C->D * Callsites in A and B pass different args into C, so C is recomputed. * Then within C the same callsite passes different args into D. */ static int analyze_subprog(struct bpf_verifier_env *env, struct arg_track *entry_args, struct subprog_at_info *info, struct func_instance *instance, u32 *callsites) { int subprog = instance->subprog; int depth = instance->depth; struct bpf_insn *insns = env->prog->insnsi; int start = env->subprog_info[subprog].start; int po_start = env->subprog_info[subprog].postorder_start; int po_end = env->subprog_info[subprog + 1].postorder_start; struct func_instance *prev_instance = NULL; int j, err; if (++env->liveness->subprog_calls > 10000) { verbose(env, "liveness analysis exceeded complexity limit (%d calls)\n", env->liveness->subprog_calls); return -E2BIG; } if (need_resched()) cond_resched(); /* * When an instance is reused (must_write_initialized == true), * record into a fresh instance and merge afterward. This avoids * stale must_write marks for instructions not reached in this pass. */ if (instance->must_write_initialized) { struct func_instance *fresh = fresh_instance(instance); if (IS_ERR(fresh)) return PTR_ERR(fresh); prev_instance = instance; instance = fresh; } /* Free prior analysis if this subprog was already visited */ kvfree(info[subprog].at_in); info[subprog].at_in = NULL; err = compute_subprog_args(env, &info[subprog], entry_args, instance, callsites); if (err) goto out_free; /* For each reachable call site in the subprog, recurse into callees */ for (int p = po_start; p < po_end; p++) { int idx = env->cfg.insn_postorder[p]; struct arg_track callee_args[BPF_REG_5 + 1]; struct arg_track none = { .frame = ARG_NONE }; struct bpf_insn *insn = &insns[idx]; struct func_instance *callee_instance; int callee, target; int caller_reg, cb_callee_reg; j = idx - start; /* relative index within this subprog */ if (bpf_pseudo_call(insn)) { target = idx + insn->imm + 1; callee = bpf_find_subprog(env, target); if (callee < 0) continue; /* Build entry args: R1-R5 from at_in at call site */ for (int r = BPF_REG_1; r <= BPF_REG_5; r++) callee_args[r] = info[subprog].at_in[j][r]; } else if (bpf_calls_callback(env, idx)) { callee = find_callback_subprog(env, insn, idx, &caller_reg, &cb_callee_reg); if (callee == -2) { /* * same bpf_loop() calls two different callbacks and passes * stack pointer to them */ if (info[subprog].at_in[j][caller_reg].frame == ARG_NONE) continue; for (int f = 0; f <= depth; f++) { err = mark_stack_read(instance, f, idx, SPIS_ALL); if (err) goto out_free; } continue; } if (callee < 0) continue; for (int r = BPF_REG_1; r <= BPF_REG_5; r++) callee_args[r] = none; callee_args[cb_callee_reg] = info[subprog].at_in[j][caller_reg]; } else { continue; } if (!has_fp_args(callee_args)) continue; if (depth == MAX_CALL_FRAMES - 1) { err = -EINVAL; goto out_free; } callee_instance = call_instance(env, instance, idx, callee); if (IS_ERR(callee_instance)) { err = PTR_ERR(callee_instance); goto out_free; } callsites[depth] = idx; err = analyze_subprog(env, callee_args, info, callee_instance, callsites); if (err) goto out_free; /* Pull callee's entry liveness back to caller's callsite */ { u32 callee_start = callee_instance->subprog_start; struct per_frame_masks *entry; for (int f = 0; f < callee_instance->depth; f++) { entry = get_frame_masks(callee_instance, f, callee_start); if (!entry) continue; err = mark_stack_read(instance, f, idx, entry->live_before); if (err) goto out_free; } } } if (prev_instance) { merge_instances(prev_instance, instance); free_instance(instance); instance = prev_instance; } update_instance(env, instance); return 0; out_free: if (prev_instance) free_instance(instance); return err; } int bpf_compute_subprog_arg_access(struct bpf_verifier_env *env) { u32 callsites[MAX_CALL_FRAMES] = {}; int insn_cnt = env->prog->len; struct func_instance *instance; struct subprog_at_info *info; int k, err = 0; info = kvzalloc_objs(*info, env->subprog_cnt, GFP_KERNEL_ACCOUNT); if (!info) return -ENOMEM; env->callsite_at_stack = kvzalloc_objs(*env->callsite_at_stack, insn_cnt, GFP_KERNEL_ACCOUNT); if (!env->callsite_at_stack) { kvfree(info); return -ENOMEM; } /* * Analyze every subprog in reverse topological order (callers * before callees) so that each subprog is analyzed before its * callees, allowing the recursive walk inside analyze_subprog() * to naturally reach callees that receive FP-derived args. * * Subprogs and callbacks that don't receive FP-derived arguments * cannot access ancestor stack frames are analyzed independently. * Async callbacks (timer, workqueue) are handled the same way. */ for (k = env->subprog_cnt - 1; k >= 0; k--) { int sub = env->subprog_topo_order[k]; if (info[sub].at_in && !bpf_subprog_is_global(env, sub)) continue; instance = call_instance(env, NULL, 0, sub); if (IS_ERR(instance)) { err = PTR_ERR(instance); goto out; } err = analyze_subprog(env, NULL, info, instance, callsites); if (err) goto out; } if (env->log.level & BPF_LOG_LEVEL2) err = print_instances(env); out: for (k = 0; k < insn_cnt; k++) kvfree(env->callsite_at_stack[k]); kvfree(env->callsite_at_stack); env->callsite_at_stack = NULL; for (k = 0; k < env->subprog_cnt; k++) kvfree(info[k].at_in); kvfree(info); return err; } /* Each field is a register bitmask */ struct insn_live_regs { u16 use; /* registers read by instruction */ u16 def; /* registers written by instruction */ u16 in; /* registers that may be alive before instruction */ u16 out; /* registers that may be alive after instruction */ }; /* Bitmask with 1s for all caller saved registers */ #define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1) /* Compute info->{use,def} fields for the instruction */ static void compute_insn_live_regs(struct bpf_verifier_env *env, struct bpf_insn *insn, struct insn_live_regs *info) { struct bpf_call_summary cs; u8 class = BPF_CLASS(insn->code); u8 code = BPF_OP(insn->code); u8 mode = BPF_MODE(insn->code); u16 src = BIT(insn->src_reg); u16 dst = BIT(insn->dst_reg); u16 r0 = BIT(0); u16 def = 0; u16 use = 0xffff; switch (class) { case BPF_LD: switch (mode) { case BPF_IMM: if (BPF_SIZE(insn->code) == BPF_DW) { def = dst; use = 0; } break; case BPF_LD | BPF_ABS: case BPF_LD | BPF_IND: /* stick with defaults */ break; } break; case BPF_LDX: switch (mode) { case BPF_MEM: case BPF_MEMSX: def = dst; use = src; break; } break; case BPF_ST: switch (mode) { case BPF_MEM: def = 0; use = dst; break; } break; case BPF_STX: switch (mode) { case BPF_MEM: def = 0; use = dst | src; break; case BPF_ATOMIC: switch (insn->imm) { case BPF_CMPXCHG: use = r0 | dst | src; def = r0; break; case BPF_LOAD_ACQ: def = dst; use = src; break; case BPF_STORE_REL: def = 0; use = dst | src; break; default: use = dst | src; if (insn->imm & BPF_FETCH) def = src; else def = 0; } break; } break; case BPF_ALU: case BPF_ALU64: switch (code) { case BPF_END: use = dst; def = dst; break; case BPF_MOV: def = dst; if (BPF_SRC(insn->code) == BPF_K) use = 0; else use = src; break; default: def = dst; if (BPF_SRC(insn->code) == BPF_K) use = dst; else use = dst | src; } break; case BPF_JMP: case BPF_JMP32: switch (code) { case BPF_JA: def = 0; if (BPF_SRC(insn->code) == BPF_X) use = dst; else use = 0; break; case BPF_JCOND: def = 0; use = 0; break; case BPF_EXIT: def = 0; use = r0; break; case BPF_CALL: def = ALL_CALLER_SAVED_REGS; use = def & ~BIT(BPF_REG_0); if (bpf_get_call_summary(env, insn, &cs)) use = GENMASK(cs.num_params, 1); break; default: def = 0; if (BPF_SRC(insn->code) == BPF_K) use = dst; else use = dst | src; } break; } info->def = def; info->use = use; } /* Compute may-live registers after each instruction in the program. * The register is live after the instruction I if it is read by some * instruction S following I during program execution and is not * overwritten between I and S. * * Store result in env->insn_aux_data[i].live_regs. */ int bpf_compute_live_registers(struct bpf_verifier_env *env) { struct bpf_insn_aux_data *insn_aux = env->insn_aux_data; struct bpf_insn *insns = env->prog->insnsi; struct insn_live_regs *state; int insn_cnt = env->prog->len; int err = 0, i, j; bool changed; /* Use the following algorithm: * - define the following: * - I.use : a set of all registers read by instruction I; * - I.def : a set of all registers written by instruction I; * - I.in : a set of all registers that may be alive before I execution; * - I.out : a set of all registers that may be alive after I execution; * - insn_successors(I): a set of instructions S that might immediately * follow I for some program execution; * - associate separate empty sets 'I.in' and 'I.out' with each instruction; * - visit each instruction in a postorder and update * state[i].in, state[i].out as follows: * * state[i].out = U [state[s].in for S in insn_successors(i)] * state[i].in = (state[i].out / state[i].def) U state[i].use * * (where U stands for set union, / stands for set difference) * - repeat the computation while {in,out} fields changes for * any instruction. */ state = kvzalloc_objs(*state, insn_cnt, GFP_KERNEL_ACCOUNT); if (!state) { err = -ENOMEM; goto out; } for (i = 0; i < insn_cnt; ++i) compute_insn_live_regs(env, &insns[i], &state[i]); /* Forward pass: resolve stack access through FP-derived pointers */ err = bpf_compute_subprog_arg_access(env); if (err) goto out; changed = true; while (changed) { changed = false; for (i = 0; i < env->cfg.cur_postorder; ++i) { int insn_idx = env->cfg.insn_postorder[i]; struct insn_live_regs *live = &state[insn_idx]; struct bpf_iarray *succ; u16 new_out = 0; u16 new_in = 0; succ = bpf_insn_successors(env, insn_idx); for (int s = 0; s < succ->cnt; ++s) new_out |= state[succ->items[s]].in; new_in = (new_out & ~live->def) | live->use; if (new_out != live->out || new_in != live->in) { live->in = new_in; live->out = new_out; changed = true; } } } for (i = 0; i < insn_cnt; ++i) insn_aux[i].live_regs_before = state[i].in; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "Live regs before insn:\n"); for (i = 0; i < insn_cnt; ++i) { if (env->insn_aux_data[i].scc) verbose(env, "%3d ", env->insn_aux_data[i].scc); else verbose(env, " "); verbose(env, "%3d: ", i); for (j = BPF_REG_0; j < BPF_REG_10; ++j) if (insn_aux[i].live_regs_before & BIT(j)) verbose(env, "%d", j); else verbose(env, "."); verbose(env, " "); bpf_verbose_insn(env, &insns[i]); if (bpf_is_ldimm64(&insns[i])) i++; } } out: kvfree(state); return err; } |
| 4 70 3 537 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_INTERNAL_H #define __CGROUP_INTERNAL_H #include <linux/cgroup.h> #include <linux/kernfs.h> #include <linux/workqueue.h> #include <linux/list.h> #include <linux/refcount.h> #include <linux/fs_parser.h> #define TRACE_CGROUP_PATH_LEN 1024 extern spinlock_t trace_cgroup_path_lock; extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; extern void __init enable_debug_cgroup(void); /* * cgroup_path() takes a spin lock. It is good practice not to take * spin locks within trace point handlers, as they are mostly hidden * from normal view. As cgroup_path() can take the kernfs_rename_lock * spin lock, it is best to not call that function from the trace event * handler. * * Note: trace_cgroup_##type##_enabled() is a static branch that will only * be set when the trace event is enabled. */ #define TRACE_CGROUP_PATH(type, cgrp, ...) \ do { \ if (trace_cgroup_##type##_enabled()) { \ unsigned long flags; \ spin_lock_irqsave(&trace_cgroup_path_lock, \ flags); \ cgroup_path(cgrp, trace_cgroup_path, \ TRACE_CGROUP_PATH_LEN); \ trace_cgroup_##type(cgrp, trace_cgroup_path, \ ##__VA_ARGS__); \ spin_unlock_irqrestore(&trace_cgroup_path_lock, \ flags); \ } \ } while (0) /* * The cgroup filesystem superblock creation/mount context. */ struct cgroup_fs_context { struct kernfs_fs_context kfc; struct cgroup_root *root; struct cgroup_namespace *ns; unsigned int flags; /* CGRP_ROOT_* flags */ /* cgroup1 bits */ bool cpuset_clone_children; bool none; /* User explicitly requested empty subsystem */ bool all_ss; /* Seen 'all' option */ u32 subsys_mask; /* Selected subsystems */ char *name; /* Hierarchy name */ char *release_agent; /* Path for release notifications */ }; static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) { struct kernfs_fs_context *kfc = fc->fs_private; return container_of(kfc, struct cgroup_fs_context, kfc); } struct cgroup_pidlist; struct cgroup_file_ctx { struct cgroup_namespace *ns; struct { void *trigger; } psi; struct { bool started; struct css_task_iter iter; } procs; struct { struct cgroup_pidlist *pidlist; } procs1; struct cgroup_of_peak peak; }; /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other * direction, a css_set is naturally associated with multiple cgroups. * This M:N relationship is represented by the following link structure * which exists for each association and allows traversing the associations * from both sides. */ struct cgrp_cset_link { /* the cgroup and css_set this link associates */ struct cgroup *cgrp; struct css_set *cset; /* list of cgrp_cset_links anchored at cgrp->cset_links */ struct list_head cset_link; /* list of cgrp_cset_links anchored at css_set->cgrp_links */ struct list_head cgrp_link; }; /* used to track tasks and csets during migration */ struct cgroup_taskset { /* the src and dst cset list running through cset->mg_node */ struct list_head src_csets; struct list_head dst_csets; /* the number of tasks in the set */ int nr_tasks; /* the subsys currently being processed */ int ssid; /* * Fields for cgroup_taskset_*() iteration. * * Before migration is committed, the target migration tasks are on * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of * the csets on ->dst_csets. ->csets point to either ->src_csets * or ->dst_csets depending on whether migration is committed. * * ->cur_csets and ->cur_task point to the current task position * during iteration. */ struct list_head *csets; struct css_set *cur_cset; struct task_struct *cur_task; }; /* migration context also tracks preloading */ struct cgroup_mgctx { /* * Preloaded source and destination csets. Used to guarantee * atomic success or failure on actual migration. */ struct list_head preloaded_src_csets; struct list_head preloaded_dst_csets; /* tasks and csets to migrate */ struct cgroup_taskset tset; /* subsystems affected by migration */ u32 ss_mask; }; #define CGROUP_TASKSET_INIT(tset) \ { \ .src_csets = LIST_HEAD_INIT(tset.src_csets), \ .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ .csets = &tset.src_csets, \ } #define CGROUP_MGCTX_INIT(name) \ { \ LIST_HEAD_INIT(name.preloaded_src_csets), \ LIST_HEAD_INIT(name.preloaded_dst_csets), \ CGROUP_TASKSET_INIT(name.tset), \ } #define DEFINE_CGROUP_MGCTX(name) \ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; extern bool cgrp_dfl_visible; /* iterate across the hierarchies */ #define for_each_root(root) \ list_for_each_entry_rcu((root), &cgroup_roots, root_list, \ lockdep_is_held(&cgroup_mutex)) /** * for_each_subsys - iterate all enabled cgroup subsystems * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end */ #define for_each_subsys(ss, ssid) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) static inline bool notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } void put_css_set_locked(struct css_set *cset); static inline void put_css_set(struct css_set *cset) { unsigned long flags; /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an * rwlock */ if (refcount_dec_not_one(&cset->refcount)) return; spin_lock_irqsave(&css_set_lock, flags); put_css_set_locked(cset); spin_unlock_irqrestore(&css_set_lock, flags); } /* * refcounted get/put for css_set objects */ static inline void get_css_set(struct css_set *cset) { refcount_inc(&cset->refcount); } bool cgroup_ssid_enabled(int ssid); struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root); struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root); struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline); void cgroup_kn_unlock(struct kernfs_node *kn); int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); void cgroup_favor_dynmods(struct cgroup_root *root, bool favor); void cgroup_free_root(struct cgroup_root *root); void init_cgroup_root(struct cgroup_fs_context *ctx); int cgroup_setup_root(struct cgroup_root *root, u32 ss_mask); int rebind_subsystems(struct cgroup_root *dst_root, u32 ss_mask); int cgroup_do_get_tree(struct fs_context *fc); int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp); void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx); int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx); int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx); int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup); void cgroup_attach_lock(enum cgroup_attach_lock_mode lock_mode, struct task_struct *tsk); void cgroup_attach_unlock(enum cgroup_attach_lock_mode lock_mode, struct task_struct *tsk); struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, enum cgroup_attach_lock_mode *lock_mode) __acquires(&cgroup_threadgroup_rwsem); void cgroup_procs_write_finish(struct task_struct *task, enum cgroup_attach_lock_mode lock_mode) __releases(&cgroup_threadgroup_rwsem); void cgroup_lock_and_drain_offline(struct cgroup *cgrp); int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode); int cgroup_rmdir(struct kernfs_node *kn); int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root); int __cgroup_task_count(const struct cgroup *cgrp); int cgroup_task_count(const struct cgroup *cgrp); /* * rstat.c */ int css_rstat_init(struct cgroup_subsys_state *css); void css_rstat_exit(struct cgroup_subsys_state *css); int ss_rstat_init(struct cgroup_subsys *ss); void cgroup_base_stat_cputime_show(struct seq_file *seq); /* * namespace.c */ extern const struct proc_ns_operations cgroupns_operations; /* * cgroup-v1.c */ extern struct cftype cgroup1_base_files[]; extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; extern const struct fs_parameter_spec cgroup1_fs_parameters[]; int proc_cgroupstats_show(struct seq_file *m, void *v); bool cgroup1_ssid_disabled(int ssid); void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); void cgroup1_release_agent(struct work_struct *work); void cgroup1_check_for_release(struct cgroup *cgrp); int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param); int cgroup1_get_tree(struct fs_context *fc); int cgroup1_reconfigure(struct fs_context *ctx); #endif /* __CGROUP_INTERNAL_H */ |
| 5 91 1 1 1 1 1 1 1 1 1 1 15 7 1 38 38 34 29 5 4 30 1 3 31 7 5 5 5 3 2 2 3 19 20 7 13 15 5 11 3 4 3 17 9 2 2 7 6 4 13 13 7 4 1 1 2 2 1 8 11 7 2 5 13 13 2 2 9 7 1 2 5 7 20 4 3 3 1 3 5 1 6 3 2 1 2 1 1 7 7 1 2 2 3 3 7 4 3 3 3 7 2 3 2 2 2 17 17 4 13 5 10 10 10 10 5 10 9 9 4 2 4 7 3 4 3 1 4 4 2 4 2 2 8 18 18 18 17 12 5 7 1 1 5 4 4 4 3 1 1 1 4 1 38 19 10 9 29 9 2 2 40 38 39 39 10 38 19 9 10 10 28 19 10 9 19 10 9 19 10 9 38 10 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 | // SPDX-License-Identifier: GPL-2.0-only /* * A virtual codec example device. * * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved. * * This is a virtual codec device driver for testing the codec framework. * It simulates a device that uses memory buffers for both source and * destination and encodes or decodes the data. */ #include <linux/module.h> #include <linux/delay.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/platform_device.h> #include <media/v4l2-mem2mem.h> #include <media/v4l2-device.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-event.h> #include <media/videobuf2-vmalloc.h> #include "codec-v4l2-fwht.h" MODULE_DESCRIPTION("Virtual codec device"); MODULE_AUTHOR("Hans Verkuil <hverkuil@kernel.org>"); MODULE_LICENSE("GPL v2"); static bool multiplanar; module_param(multiplanar, bool, 0444); MODULE_PARM_DESC(multiplanar, " use multi-planar API instead of single-planar API"); static unsigned int debug; module_param(debug, uint, 0644); MODULE_PARM_DESC(debug, " activates debug info"); #define VICODEC_NAME "vicodec" #define MAX_WIDTH 4096U #define MIN_WIDTH 640U #define MAX_HEIGHT 2160U #define MIN_HEIGHT 360U /* Recommended number of buffers for the stateful codecs */ #define VICODEC_REC_BUFS 2 #define dprintk(dev, fmt, arg...) \ v4l2_dbg(1, debug, &dev->v4l2_dev, "%s: " fmt, __func__, ## arg) struct pixfmt_info { u32 id; unsigned int bytesperline_mult; unsigned int sizeimage_mult; unsigned int sizeimage_div; unsigned int luma_step; unsigned int chroma_step; /* Chroma plane subsampling */ unsigned int width_div; unsigned int height_div; }; static const struct v4l2_fwht_pixfmt_info pixfmt_fwht = { V4L2_PIX_FMT_FWHT, 0, 3, 1, 1, 1, 1, 1, 0, 1 }; static const struct v4l2_fwht_pixfmt_info pixfmt_stateless_fwht = { V4L2_PIX_FMT_FWHT_STATELESS, 0, 3, 1, 1, 1, 1, 1, 0, 1 }; static void vicodec_dev_release(struct device *dev) { } static struct platform_device vicodec_pdev = { .name = VICODEC_NAME, .dev.release = vicodec_dev_release, }; /* Per-queue, driver-specific private data */ struct vicodec_q_data { unsigned int coded_width; unsigned int coded_height; unsigned int visible_width; unsigned int visible_height; unsigned int sizeimage; unsigned int vb2_sizeimage; unsigned int sequence; const struct v4l2_fwht_pixfmt_info *info; }; enum { V4L2_M2M_SRC = 0, V4L2_M2M_DST = 1, }; struct vicodec_dev_instance { struct video_device vfd; struct mutex mutex; spinlock_t lock; struct v4l2_m2m_dev *m2m_dev; }; struct vicodec_dev { struct v4l2_device v4l2_dev; struct vicodec_dev_instance stateful_enc; struct vicodec_dev_instance stateful_dec; struct vicodec_dev_instance stateless_dec; #ifdef CONFIG_MEDIA_CONTROLLER struct media_device mdev; #endif }; struct vicodec_ctx { struct v4l2_fh fh; struct vicodec_dev *dev; bool is_enc; bool is_stateless; spinlock_t *lock; struct v4l2_ctrl_handler hdl; /* Source and destination queue data */ struct vicodec_q_data q_data[2]; struct v4l2_fwht_state state; u32 cur_buf_offset; u32 comp_max_size; u32 comp_size; u32 header_size; u32 comp_magic_cnt; bool comp_has_frame; bool comp_has_next_frame; bool first_source_change_sent; bool source_changed; }; static const struct v4l2_event vicodec_eos_event = { .type = V4L2_EVENT_EOS }; static inline struct vicodec_ctx *file2ctx(struct file *file) { return container_of(file_to_v4l2_fh(file), struct vicodec_ctx, fh); } static struct vicodec_q_data *get_q_data(struct vicodec_ctx *ctx, enum v4l2_buf_type type) { switch (type) { case V4L2_BUF_TYPE_VIDEO_OUTPUT: case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: return &ctx->q_data[V4L2_M2M_SRC]; case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: return &ctx->q_data[V4L2_M2M_DST]; default: break; } return NULL; } static void copy_cap_to_ref(const u8 *cap, const struct v4l2_fwht_pixfmt_info *info, struct v4l2_fwht_state *state) { int plane_idx; u8 *p_ref = state->ref_frame.buf; unsigned int cap_stride = state->stride; unsigned int ref_stride = state->ref_stride; for (plane_idx = 0; plane_idx < info->planes_num; plane_idx++) { int i; unsigned int h_div = (plane_idx == 1 || plane_idx == 2) ? info->height_div : 1; const u8 *row_cap = cap; u8 *row_ref = p_ref; if (info->planes_num == 3 && plane_idx == 1) { cap_stride /= 2; ref_stride /= 2; } if (plane_idx == 1 && (info->id == V4L2_PIX_FMT_NV24 || info->id == V4L2_PIX_FMT_NV42)) { cap_stride *= 2; ref_stride *= 2; } for (i = 0; i < state->visible_height / h_div; i++) { memcpy(row_ref, row_cap, ref_stride); row_ref += ref_stride; row_cap += cap_stride; } cap += cap_stride * (state->coded_height / h_div); p_ref += ref_stride * (state->coded_height / h_div); } } static bool validate_by_version(unsigned int flags, unsigned int version) { if (!version || version > V4L2_FWHT_VERSION) return false; if (version >= 2) { unsigned int components_num = 1 + ((flags & V4L2_FWHT_FL_COMPONENTS_NUM_MSK) >> V4L2_FWHT_FL_COMPONENTS_NUM_OFFSET); unsigned int pixenc = flags & V4L2_FWHT_FL_PIXENC_MSK; if (components_num == 0 || components_num > 4 || !pixenc) return false; } return true; } static bool validate_stateless_params_flags(const struct v4l2_ctrl_fwht_params *params, const struct v4l2_fwht_pixfmt_info *cur_info) { unsigned int width_div = (params->flags & V4L2_FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2; unsigned int height_div = (params->flags & V4L2_FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2; unsigned int components_num = 3; unsigned int pixenc = 0; if (params->version < 3) return false; components_num = 1 + ((params->flags & V4L2_FWHT_FL_COMPONENTS_NUM_MSK) >> V4L2_FWHT_FL_COMPONENTS_NUM_OFFSET); pixenc = (params->flags & V4L2_FWHT_FL_PIXENC_MSK); if (v4l2_fwht_validate_fmt(cur_info, width_div, height_div, components_num, pixenc)) return true; return false; } static void update_state_from_header(struct vicodec_ctx *ctx) { const struct fwht_cframe_hdr *p_hdr = &ctx->state.header; ctx->state.visible_width = ntohl(p_hdr->width); ctx->state.visible_height = ntohl(p_hdr->height); ctx->state.colorspace = ntohl(p_hdr->colorspace); ctx->state.xfer_func = ntohl(p_hdr->xfer_func); ctx->state.ycbcr_enc = ntohl(p_hdr->ycbcr_enc); ctx->state.quantization = ntohl(p_hdr->quantization); } static int device_process(struct vicodec_ctx *ctx, struct vb2_v4l2_buffer *src_vb, struct vb2_v4l2_buffer *dst_vb) { struct vicodec_dev *dev = ctx->dev; struct v4l2_fwht_state *state = &ctx->state; u8 *p_src, *p_dst; int ret = 0; if (ctx->is_enc || ctx->is_stateless) p_src = vb2_plane_vaddr(&src_vb->vb2_buf, 0); else p_src = state->compressed_frame; if (ctx->is_stateless) { struct media_request *src_req = src_vb->vb2_buf.req_obj.req; ret = v4l2_ctrl_request_setup(src_req, &ctx->hdl); if (ret) return ret; update_state_from_header(ctx); ctx->state.header.size = htonl(vb2_get_plane_payload(&src_vb->vb2_buf, 0)); /* * set the reference buffer from the reference timestamp * only if this is a P-frame */ if (!(ntohl(ctx->state.header.flags) & V4L2_FWHT_FL_I_FRAME)) { struct vb2_buffer *ref_vb2_buf; struct vb2_queue *vq_cap = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); ref_vb2_buf = vb2_find_buffer(vq_cap, ctx->state.ref_frame_ts); if (!ref_vb2_buf) return -EINVAL; if (ref_vb2_buf->state == VB2_BUF_STATE_ERROR) ret = -EINVAL; ctx->state.ref_frame.buf = vb2_plane_vaddr(ref_vb2_buf, 0); } else { ctx->state.ref_frame.buf = NULL; } } p_dst = vb2_plane_vaddr(&dst_vb->vb2_buf, 0); if (!p_src || !p_dst) { v4l2_err(&dev->v4l2_dev, "Acquiring kernel pointers to buffers failed\n"); return -EFAULT; } if (ctx->is_enc) { struct vicodec_q_data *q_src; int comp_sz_or_errcode; q_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); state->info = q_src->info; comp_sz_or_errcode = v4l2_fwht_encode(state, p_src, p_dst); if (comp_sz_or_errcode < 0) return comp_sz_or_errcode; vb2_set_plane_payload(&dst_vb->vb2_buf, 0, comp_sz_or_errcode); } else { struct vicodec_q_data *q_dst; unsigned int comp_frame_size = ntohl(ctx->state.header.size); q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); if (comp_frame_size > ctx->comp_max_size) return -EINVAL; state->info = q_dst->info; ret = v4l2_fwht_decode(state, p_src, p_dst); if (ret < 0) return ret; if (!ctx->is_stateless) copy_cap_to_ref(p_dst, ctx->state.info, &ctx->state); vb2_set_plane_payload(&dst_vb->vb2_buf, 0, q_dst->sizeimage); if (ntohl(ctx->state.header.flags) & V4L2_FWHT_FL_I_FRAME) dst_vb->flags |= V4L2_BUF_FLAG_KEYFRAME; else dst_vb->flags |= V4L2_BUF_FLAG_PFRAME; } return ret; } /* * mem2mem callbacks */ static enum vb2_buffer_state get_next_header(struct vicodec_ctx *ctx, u8 **pp, u32 sz) { static const u8 magic[] = { 0x4f, 0x4f, 0x4f, 0x4f, 0xff, 0xff, 0xff, 0xff }; u8 *p = *pp; u32 state; u8 *header = (u8 *)&ctx->state.header; state = VB2_BUF_STATE_DONE; if (!ctx->header_size) { state = VB2_BUF_STATE_ERROR; for (; p < *pp + sz; p++) { u32 copy; p = memchr(p, magic[ctx->comp_magic_cnt], *pp + sz - p); if (!p) { ctx->comp_magic_cnt = 0; p = *pp + sz; break; } copy = sizeof(magic) - ctx->comp_magic_cnt; if (*pp + sz - p < copy) copy = *pp + sz - p; memcpy(header + ctx->comp_magic_cnt, p, copy); ctx->comp_magic_cnt += copy; if (!memcmp(header, magic, ctx->comp_magic_cnt)) { p += copy; state = VB2_BUF_STATE_DONE; break; } ctx->comp_magic_cnt = 0; } if (ctx->comp_magic_cnt < sizeof(magic)) { *pp = p; return state; } ctx->header_size = sizeof(magic); } if (ctx->header_size < sizeof(struct fwht_cframe_hdr)) { u32 copy = sizeof(struct fwht_cframe_hdr) - ctx->header_size; if (*pp + sz - p < copy) copy = *pp + sz - p; memcpy(header + ctx->header_size, p, copy); p += copy; ctx->header_size += copy; } *pp = p; return state; } /* device_run() - prepares and starts the device */ static void device_run(void *priv) { struct vicodec_ctx *ctx = priv; struct vicodec_dev *dev = ctx->dev; struct vb2_v4l2_buffer *src_buf, *dst_buf; struct vicodec_q_data *q_src, *q_dst; u32 state; struct media_request *src_req; src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx); src_req = src_buf->vb2_buf.req_obj.req; q_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); state = VB2_BUF_STATE_DONE; if (device_process(ctx, src_buf, dst_buf)) state = VB2_BUF_STATE_ERROR; else dst_buf->sequence = q_dst->sequence++; dst_buf->flags &= ~V4L2_BUF_FLAG_LAST; v4l2_m2m_buf_copy_metadata(src_buf, dst_buf); spin_lock(ctx->lock); if (!ctx->comp_has_next_frame && v4l2_m2m_is_last_draining_src_buf(ctx->fh.m2m_ctx, src_buf)) { dst_buf->flags |= V4L2_BUF_FLAG_LAST; v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); v4l2_m2m_mark_stopped(ctx->fh.m2m_ctx); } if (ctx->is_enc || ctx->is_stateless) { src_buf->sequence = q_src->sequence++; src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); v4l2_m2m_buf_done(src_buf, state); } else if (vb2_get_plane_payload(&src_buf->vb2_buf, 0) == ctx->cur_buf_offset) { src_buf->sequence = q_src->sequence++; src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); v4l2_m2m_buf_done(src_buf, state); ctx->cur_buf_offset = 0; ctx->comp_has_next_frame = false; } v4l2_m2m_buf_done(dst_buf, state); ctx->comp_size = 0; ctx->header_size = 0; ctx->comp_magic_cnt = 0; ctx->comp_has_frame = false; spin_unlock(ctx->lock); if (ctx->is_stateless && src_req) { v4l2_ctrl_request_complete(src_req, &ctx->hdl); media_request_manual_complete(src_req); } if (ctx->is_enc) v4l2_m2m_job_finish(dev->stateful_enc.m2m_dev, ctx->fh.m2m_ctx); else if (ctx->is_stateless) v4l2_m2m_job_finish(dev->stateless_dec.m2m_dev, ctx->fh.m2m_ctx); else v4l2_m2m_job_finish(dev->stateful_dec.m2m_dev, ctx->fh.m2m_ctx); } static void job_remove_src_buf(struct vicodec_ctx *ctx, u32 state) { struct vb2_v4l2_buffer *src_buf; struct vicodec_q_data *q_src; q_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); spin_lock(ctx->lock); src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); src_buf->sequence = q_src->sequence++; v4l2_m2m_buf_done(src_buf, state); ctx->cur_buf_offset = 0; spin_unlock(ctx->lock); } static const struct v4l2_fwht_pixfmt_info * info_from_header(const struct fwht_cframe_hdr *p_hdr) { unsigned int flags = ntohl(p_hdr->flags); unsigned int width_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2; unsigned int height_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2; unsigned int components_num = 3; unsigned int pixenc = 0; unsigned int version = ntohl(p_hdr->version); if (version >= 2) { components_num = 1 + ((flags & V4L2_FWHT_FL_COMPONENTS_NUM_MSK) >> V4L2_FWHT_FL_COMPONENTS_NUM_OFFSET); pixenc = (flags & V4L2_FWHT_FL_PIXENC_MSK); } return v4l2_fwht_find_nth_fmt(width_div, height_div, components_num, pixenc, 0); } static bool is_header_valid(const struct fwht_cframe_hdr *p_hdr) { const struct v4l2_fwht_pixfmt_info *info; unsigned int w = ntohl(p_hdr->width); unsigned int h = ntohl(p_hdr->height); unsigned int version = ntohl(p_hdr->version); unsigned int flags = ntohl(p_hdr->flags); if (w < MIN_WIDTH || w > MAX_WIDTH || h < MIN_HEIGHT || h > MAX_HEIGHT) return false; if (!validate_by_version(flags, version)) return false; info = info_from_header(p_hdr); if (!info) return false; return true; } static void update_capture_data_from_header(struct vicodec_ctx *ctx) { struct vicodec_q_data *q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); const struct fwht_cframe_hdr *p_hdr = &ctx->state.header; const struct v4l2_fwht_pixfmt_info *info = info_from_header(p_hdr); unsigned int flags = ntohl(p_hdr->flags); unsigned int hdr_width_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2; unsigned int hdr_height_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2; /* * This function should not be used by a stateless codec since * it changes values in q_data that are not request specific */ WARN_ON(ctx->is_stateless); q_dst->info = info; q_dst->visible_width = ntohl(p_hdr->width); q_dst->visible_height = ntohl(p_hdr->height); q_dst->coded_width = vic_round_dim(q_dst->visible_width, hdr_width_div); q_dst->coded_height = vic_round_dim(q_dst->visible_height, hdr_height_div); q_dst->sizeimage = q_dst->coded_width * q_dst->coded_height * q_dst->info->sizeimage_mult / q_dst->info->sizeimage_div; ctx->state.colorspace = ntohl(p_hdr->colorspace); ctx->state.xfer_func = ntohl(p_hdr->xfer_func); ctx->state.ycbcr_enc = ntohl(p_hdr->ycbcr_enc); ctx->state.quantization = ntohl(p_hdr->quantization); } static void set_last_buffer(struct vb2_v4l2_buffer *dst_buf, const struct vb2_v4l2_buffer *src_buf, struct vicodec_ctx *ctx) { struct vicodec_q_data *q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); vb2_set_plane_payload(&dst_buf->vb2_buf, 0, 0); dst_buf->sequence = q_dst->sequence++; v4l2_m2m_buf_copy_metadata(src_buf, dst_buf); dst_buf->flags |= V4L2_BUF_FLAG_LAST; v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_DONE); } static int job_ready(void *priv) { static const u8 magic[] = { 0x4f, 0x4f, 0x4f, 0x4f, 0xff, 0xff, 0xff, 0xff }; struct vicodec_ctx *ctx = priv; struct vb2_v4l2_buffer *src_buf; u8 *p_src; u8 *p; u32 sz; u32 state; struct vicodec_q_data *q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); unsigned int flags; unsigned int hdr_width_div; unsigned int hdr_height_div; unsigned int max_to_copy; unsigned int comp_frame_size; if (ctx->source_changed) return 0; if (ctx->is_stateless || ctx->is_enc || ctx->comp_has_frame) return 1; restart: ctx->comp_has_next_frame = false; src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx); if (!src_buf) return 0; p_src = vb2_plane_vaddr(&src_buf->vb2_buf, 0); sz = vb2_get_plane_payload(&src_buf->vb2_buf, 0); p = p_src + ctx->cur_buf_offset; state = VB2_BUF_STATE_DONE; if (ctx->header_size < sizeof(struct fwht_cframe_hdr)) { state = get_next_header(ctx, &p, p_src + sz - p); if (ctx->header_size < sizeof(struct fwht_cframe_hdr)) { if (v4l2_m2m_is_last_draining_src_buf(ctx->fh.m2m_ctx, src_buf)) return 1; job_remove_src_buf(ctx, state); goto restart; } } comp_frame_size = ntohl(ctx->state.header.size); /* * The current scanned frame might be the first frame of a new * resolution so its size might be larger than ctx->comp_max_size. * In that case it is copied up to the current buffer capacity and * the copy will continue after allocating new large enough buffer * when restreaming */ max_to_copy = min(comp_frame_size, ctx->comp_max_size); if (ctx->comp_size < max_to_copy) { u32 copy = max_to_copy - ctx->comp_size; if (copy > p_src + sz - p) copy = p_src + sz - p; memcpy(ctx->state.compressed_frame + ctx->comp_size, p, copy); p += copy; ctx->comp_size += copy; if (ctx->comp_size < max_to_copy) { if (v4l2_m2m_is_last_draining_src_buf(ctx->fh.m2m_ctx, src_buf)) return 1; job_remove_src_buf(ctx, state); goto restart; } } ctx->cur_buf_offset = p - p_src; if (ctx->comp_size == comp_frame_size) ctx->comp_has_frame = true; ctx->comp_has_next_frame = false; if (ctx->comp_has_frame && sz - ctx->cur_buf_offset >= sizeof(struct fwht_cframe_hdr)) { struct fwht_cframe_hdr *p_hdr = (struct fwht_cframe_hdr *)p; u32 frame_size = ntohl(p_hdr->size); u32 remaining = sz - ctx->cur_buf_offset - sizeof(*p_hdr); if (!memcmp(p, magic, sizeof(magic))) ctx->comp_has_next_frame = remaining >= frame_size; } /* * if the header is invalid the device_run will just drop the frame * with an error */ if (!is_header_valid(&ctx->state.header) && ctx->comp_has_frame) return 1; flags = ntohl(ctx->state.header.flags); hdr_width_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2; hdr_height_div = (flags & V4L2_FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2; if (ntohl(ctx->state.header.width) != q_dst->visible_width || ntohl(ctx->state.header.height) != q_dst->visible_height || !q_dst->info || hdr_width_div != q_dst->info->width_div || hdr_height_div != q_dst->info->height_div) { static const struct v4l2_event rs_event = { .type = V4L2_EVENT_SOURCE_CHANGE, .u.src_change.changes = V4L2_EVENT_SRC_CH_RESOLUTION, }; struct vb2_v4l2_buffer *dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx); update_capture_data_from_header(ctx); v4l2_event_queue_fh(&ctx->fh, &rs_event); set_last_buffer(dst_buf, src_buf, ctx); ctx->source_changed = true; return 0; } return 1; } /* * video ioctls */ static const struct v4l2_fwht_pixfmt_info *find_fmt(u32 fmt) { const struct v4l2_fwht_pixfmt_info *info = v4l2_fwht_find_pixfmt(fmt); if (!info) info = v4l2_fwht_get_pixfmt(0); return info; } static int vidioc_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { strscpy(cap->driver, VICODEC_NAME, sizeof(cap->driver)); strscpy(cap->card, VICODEC_NAME, sizeof(cap->card)); snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s", VICODEC_NAME); return 0; } static int enum_fmt(struct v4l2_fmtdesc *f, struct vicodec_ctx *ctx, bool is_out) { bool is_uncomp = (ctx->is_enc && is_out) || (!ctx->is_enc && !is_out); if (V4L2_TYPE_IS_MULTIPLANAR(f->type) && !multiplanar) return -EINVAL; if (!V4L2_TYPE_IS_MULTIPLANAR(f->type) && multiplanar) return -EINVAL; if (is_uncomp) { const struct v4l2_fwht_pixfmt_info *info = get_q_data(ctx, f->type)->info; if (ctx->is_enc || !vb2_is_streaming(&ctx->fh.m2m_ctx->cap_q_ctx.q)) info = v4l2_fwht_get_pixfmt(f->index); else info = v4l2_fwht_find_nth_fmt(info->width_div, info->height_div, info->components_num, info->pixenc, f->index); if (!info) return -EINVAL; f->pixelformat = info->id; } else { if (f->index) return -EINVAL; f->pixelformat = ctx->is_stateless ? V4L2_PIX_FMT_FWHT_STATELESS : V4L2_PIX_FMT_FWHT; if (!ctx->is_enc && !ctx->is_stateless) f->flags = V4L2_FMT_FLAG_DYN_RESOLUTION | V4L2_FMT_FLAG_CONTINUOUS_BYTESTREAM; } return 0; } static int vidioc_enum_fmt_vid_cap(struct file *file, void *priv, struct v4l2_fmtdesc *f) { struct vicodec_ctx *ctx = file2ctx(file); return enum_fmt(f, ctx, false); } static int vidioc_enum_fmt_vid_out(struct file *file, void *priv, struct v4l2_fmtdesc *f) { struct vicodec_ctx *ctx = file2ctx(file); return enum_fmt(f, ctx, true); } static int vidioc_g_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f) { struct vicodec_q_data *q_data; struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; const struct v4l2_fwht_pixfmt_info *info; q_data = get_q_data(ctx, f->type); info = q_data->info; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_OUTPUT: if (multiplanar) return -EINVAL; pix = &f->fmt.pix; pix->width = q_data->coded_width; pix->height = q_data->coded_height; pix->field = V4L2_FIELD_NONE; pix->pixelformat = info->id; pix->bytesperline = q_data->coded_width * info->bytesperline_mult; pix->sizeimage = q_data->sizeimage; pix->colorspace = ctx->state.colorspace; pix->xfer_func = ctx->state.xfer_func; pix->ycbcr_enc = ctx->state.ycbcr_enc; pix->quantization = ctx->state.quantization; break; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: if (!multiplanar) return -EINVAL; pix_mp = &f->fmt.pix_mp; pix_mp->width = q_data->coded_width; pix_mp->height = q_data->coded_height; pix_mp->field = V4L2_FIELD_NONE; pix_mp->pixelformat = info->id; pix_mp->num_planes = 1; pix_mp->plane_fmt[0].bytesperline = q_data->coded_width * info->bytesperline_mult; pix_mp->plane_fmt[0].sizeimage = q_data->sizeimage; pix_mp->colorspace = ctx->state.colorspace; pix_mp->xfer_func = ctx->state.xfer_func; pix_mp->ycbcr_enc = ctx->state.ycbcr_enc; pix_mp->quantization = ctx->state.quantization; break; default: return -EINVAL; } return 0; } static int vidioc_g_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f) { return vidioc_g_fmt(file2ctx(file), f); } static int vidioc_g_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { return vidioc_g_fmt(file2ctx(file), f); } static int vidioc_try_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f) { struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; struct v4l2_plane_pix_format *plane; const struct v4l2_fwht_pixfmt_info *info = ctx->is_stateless ? &pixfmt_stateless_fwht : &pixfmt_fwht; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_OUTPUT: pix = &f->fmt.pix; if (pix->pixelformat != V4L2_PIX_FMT_FWHT && pix->pixelformat != V4L2_PIX_FMT_FWHT_STATELESS) info = find_fmt(pix->pixelformat); pix->width = clamp(pix->width, MIN_WIDTH, MAX_WIDTH); pix->width = vic_round_dim(pix->width, info->width_div); pix->height = clamp(pix->height, MIN_HEIGHT, MAX_HEIGHT); pix->height = vic_round_dim(pix->height, info->height_div); pix->field = V4L2_FIELD_NONE; pix->bytesperline = pix->width * info->bytesperline_mult; pix->sizeimage = pix->width * pix->height * info->sizeimage_mult / info->sizeimage_div; if (pix->pixelformat == V4L2_PIX_FMT_FWHT) pix->sizeimage += sizeof(struct fwht_cframe_hdr); break; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: pix_mp = &f->fmt.pix_mp; plane = pix_mp->plane_fmt; if (pix_mp->pixelformat != V4L2_PIX_FMT_FWHT && pix_mp->pixelformat != V4L2_PIX_FMT_FWHT_STATELESS) info = find_fmt(pix_mp->pixelformat); pix_mp->num_planes = 1; pix_mp->width = clamp(pix_mp->width, MIN_WIDTH, MAX_WIDTH); pix_mp->width = vic_round_dim(pix_mp->width, info->width_div); pix_mp->height = clamp(pix_mp->height, MIN_HEIGHT, MAX_HEIGHT); pix_mp->height = vic_round_dim(pix_mp->height, info->height_div); pix_mp->field = V4L2_FIELD_NONE; plane->bytesperline = pix_mp->width * info->bytesperline_mult; plane->sizeimage = pix_mp->width * pix_mp->height * info->sizeimage_mult / info->sizeimage_div; if (pix_mp->pixelformat == V4L2_PIX_FMT_FWHT) plane->sizeimage += sizeof(struct fwht_cframe_hdr); break; default: return -EINVAL; } return 0; } static int vidioc_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { struct vicodec_ctx *ctx = file2ctx(file); struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: if (multiplanar) return -EINVAL; pix = &f->fmt.pix; pix->pixelformat = ctx->is_enc ? V4L2_PIX_FMT_FWHT : find_fmt(f->fmt.pix.pixelformat)->id; pix->colorspace = ctx->state.colorspace; pix->xfer_func = ctx->state.xfer_func; pix->ycbcr_enc = ctx->state.ycbcr_enc; pix->quantization = ctx->state.quantization; break; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: if (!multiplanar) return -EINVAL; pix_mp = &f->fmt.pix_mp; pix_mp->pixelformat = ctx->is_enc ? V4L2_PIX_FMT_FWHT : find_fmt(pix_mp->pixelformat)->id; pix_mp->colorspace = ctx->state.colorspace; pix_mp->xfer_func = ctx->state.xfer_func; pix_mp->ycbcr_enc = ctx->state.ycbcr_enc; pix_mp->quantization = ctx->state.quantization; break; default: return -EINVAL; } return vidioc_try_fmt(ctx, f); } static int vidioc_try_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f) { struct vicodec_ctx *ctx = file2ctx(file); struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_OUTPUT: if (multiplanar) return -EINVAL; pix = &f->fmt.pix; if (ctx->is_enc) pix->pixelformat = find_fmt(pix->pixelformat)->id; else if (ctx->is_stateless) pix->pixelformat = V4L2_PIX_FMT_FWHT_STATELESS; else pix->pixelformat = V4L2_PIX_FMT_FWHT; if (!pix->colorspace) pix->colorspace = V4L2_COLORSPACE_REC709; break; case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: if (!multiplanar) return -EINVAL; pix_mp = &f->fmt.pix_mp; if (ctx->is_enc) pix_mp->pixelformat = find_fmt(pix_mp->pixelformat)->id; else if (ctx->is_stateless) pix_mp->pixelformat = V4L2_PIX_FMT_FWHT_STATELESS; else pix_mp->pixelformat = V4L2_PIX_FMT_FWHT; if (!pix_mp->colorspace) pix_mp->colorspace = V4L2_COLORSPACE_REC709; break; default: return -EINVAL; } return vidioc_try_fmt(ctx, f); } static int vidioc_s_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f) { struct vicodec_q_data *q_data; struct vb2_queue *vq; bool fmt_changed = true; struct v4l2_pix_format_mplane *pix_mp; struct v4l2_pix_format *pix; vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type); q_data = get_q_data(ctx, f->type); if (!q_data) return -EINVAL; switch (f->type) { case V4L2_BUF_TYPE_VIDEO_CAPTURE: case V4L2_BUF_TYPE_VIDEO_OUTPUT: pix = &f->fmt.pix; if (ctx->is_enc && V4L2_TYPE_IS_OUTPUT(f->type)) fmt_changed = !q_data->info || q_data->info->id != pix->pixelformat || q_data->coded_width != pix->width || q_data->coded_height != pix->height; if (vb2_is_busy(vq) && fmt_changed) return -EBUSY; if (pix->pixelformat == V4L2_PIX_FMT_FWHT) q_data->info = &pixfmt_fwht; else if (pix->pixelformat == V4L2_PIX_FMT_FWHT_STATELESS) q_data->info = &pixfmt_stateless_fwht; else q_data->info = find_fmt(pix->pixelformat); q_data->coded_width = pix->width; q_data->coded_height = pix->height; q_data->sizeimage = pix->sizeimage; break; case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE: case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: pix_mp = &f->fmt.pix_mp; if (ctx->is_enc && V4L2_TYPE_IS_OUTPUT(f->type)) fmt_changed = !q_data->info || q_data->info->id != pix_mp->pixelformat || q_data->coded_width != pix_mp->width || q_data->coded_height != pix_mp->height; if (vb2_is_busy(vq) && fmt_changed) return -EBUSY; if (pix_mp->pixelformat == V4L2_PIX_FMT_FWHT) q_data->info = &pixfmt_fwht; else if (pix_mp->pixelformat == V4L2_PIX_FMT_FWHT_STATELESS) q_data->info = &pixfmt_stateless_fwht; else q_data->info = find_fmt(pix_mp->pixelformat); q_data->coded_width = pix_mp->width; q_data->coded_height = pix_mp->height; q_data->sizeimage = pix_mp->plane_fmt[0].sizeimage; break; default: return -EINVAL; } dprintk(ctx->dev, "Setting format for type %d, coded wxh: %dx%d, fourcc: 0x%08x\n", f->type, q_data->coded_width, q_data->coded_height, q_data->info->id); return 0; } static int vidioc_s_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { int ret; ret = vidioc_try_fmt_vid_cap(file, priv, f); if (ret) return ret; return vidioc_s_fmt(file2ctx(file), f); } static int vidioc_s_fmt_vid_out(struct file *file, void *priv, struct v4l2_format *f) { struct vicodec_ctx *ctx = file2ctx(file); struct vicodec_q_data *q_data; struct vicodec_q_data *q_data_cap; struct v4l2_pix_format *pix; struct v4l2_pix_format_mplane *pix_mp; u32 coded_w = 0, coded_h = 0; unsigned int size = 0; int ret; q_data = get_q_data(ctx, f->type); q_data_cap = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); ret = vidioc_try_fmt_vid_out(file, priv, f); if (ret) return ret; if (ctx->is_enc) { struct vb2_queue *vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type); struct vb2_queue *vq_cap = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); const struct v4l2_fwht_pixfmt_info *info = ctx->is_stateless ? &pixfmt_stateless_fwht : &pixfmt_fwht; if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) { coded_w = f->fmt.pix.width; coded_h = f->fmt.pix.height; } else { coded_w = f->fmt.pix_mp.width; coded_h = f->fmt.pix_mp.height; } if (vb2_is_busy(vq) && (coded_w != q_data->coded_width || coded_h != q_data->coded_height)) return -EBUSY; size = coded_w * coded_h * info->sizeimage_mult / info->sizeimage_div; if (!ctx->is_stateless) size += sizeof(struct fwht_cframe_hdr); if (vb2_is_busy(vq_cap) && size > q_data_cap->sizeimage) return -EBUSY; } ret = vidioc_s_fmt(file2ctx(file), f); if (!ret) { if (ctx->is_enc) { q_data->visible_width = coded_w; q_data->visible_height = coded_h; q_data_cap->coded_width = coded_w; q_data_cap->coded_height = coded_h; q_data_cap->sizeimage = size; } switch (f->type) { case V4L2_BUF_TYPE_VIDEO_OUTPUT: pix = &f->fmt.pix; ctx->state.colorspace = pix->colorspace; ctx->state.xfer_func = pix->xfer_func; ctx->state.ycbcr_enc = pix->ycbcr_enc; ctx->state.quantization = pix->quantization; break; case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE: pix_mp = &f->fmt.pix_mp; ctx->state.colorspace = pix_mp->colorspace; ctx->state.xfer_func = pix_mp->xfer_func; ctx->state.ycbcr_enc = pix_mp->ycbcr_enc; ctx->state.quantization = pix_mp->quantization; break; default: break; } } return ret; } static int vidioc_g_selection(struct file *file, void *priv, struct v4l2_selection *s) { struct vicodec_ctx *ctx = file2ctx(file); struct vicodec_q_data *q_data; q_data = get_q_data(ctx, s->type); if (!q_data) return -EINVAL; /* * encoder supports only cropping on the OUTPUT buffer * decoder supports only composing on the CAPTURE buffer */ if (ctx->is_enc && s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT) { switch (s->target) { case V4L2_SEL_TGT_CROP: s->r.left = 0; s->r.top = 0; s->r.width = q_data->visible_width; s->r.height = q_data->visible_height; return 0; case V4L2_SEL_TGT_CROP_DEFAULT: case V4L2_SEL_TGT_CROP_BOUNDS: s->r.left = 0; s->r.top = 0; s->r.width = q_data->coded_width; s->r.height = q_data->coded_height; return 0; } } else if (!ctx->is_enc && s->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) { switch (s->target) { case V4L2_SEL_TGT_COMPOSE: s->r.left = 0; s->r.top = 0; s->r.width = q_data->visible_width; s->r.height = q_data->visible_height; return 0; case V4L2_SEL_TGT_COMPOSE_DEFAULT: case V4L2_SEL_TGT_COMPOSE_BOUNDS: s->r.left = 0; s->r.top = 0; s->r.width = q_data->coded_width; s->r.height = q_data->coded_height; return 0; } } return -EINVAL; } static int vidioc_s_selection(struct file *file, void *priv, struct v4l2_selection *s) { struct vicodec_ctx *ctx = file2ctx(file); struct vicodec_q_data *q_data; if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT) return -EINVAL; q_data = get_q_data(ctx, s->type); if (!q_data) return -EINVAL; if (!ctx->is_enc || s->target != V4L2_SEL_TGT_CROP) return -EINVAL; s->r.left = 0; s->r.top = 0; q_data->visible_width = clamp(s->r.width, MIN_WIDTH, q_data->coded_width); s->r.width = q_data->visible_width; q_data->visible_height = clamp(s->r.height, MIN_HEIGHT, q_data->coded_height); s->r.height = q_data->visible_height; return 0; } static int vicodec_encoder_cmd(struct file *file, void *priv, struct v4l2_encoder_cmd *ec) { struct vicodec_ctx *ctx = file2ctx(file); int ret; ret = v4l2_m2m_ioctl_try_encoder_cmd(file, priv, ec); if (ret < 0) return ret; if (!vb2_is_streaming(&ctx->fh.m2m_ctx->out_q_ctx.q)) return 0; ret = v4l2_m2m_ioctl_encoder_cmd(file, priv, ec); if (ret < 0) return ret; if (ec->cmd == V4L2_ENC_CMD_STOP && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); if (ec->cmd == V4L2_ENC_CMD_START && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) vb2_clear_last_buffer_dequeued(&ctx->fh.m2m_ctx->cap_q_ctx.q); return 0; } static int vicodec_decoder_cmd(struct file *file, void *priv, struct v4l2_decoder_cmd *dc) { struct vicodec_ctx *ctx = file2ctx(file); int ret; /* * This ioctl should not be used with a stateless codec that doesn't * support holding buffers and the associated flush command. */ WARN_ON(ctx->is_stateless); ret = v4l2_m2m_ioctl_try_decoder_cmd(file, priv, dc); if (ret < 0) return ret; if (!vb2_is_streaming(&ctx->fh.m2m_ctx->out_q_ctx.q)) return 0; ret = v4l2_m2m_ioctl_decoder_cmd(file, priv, dc); if (ret < 0) return ret; if (dc->cmd == V4L2_DEC_CMD_STOP && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); if (dc->cmd == V4L2_DEC_CMD_START && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) vb2_clear_last_buffer_dequeued(&ctx->fh.m2m_ctx->cap_q_ctx.q); return 0; } static int vicodec_enum_framesizes(struct file *file, void *priv, struct v4l2_frmsizeenum *fsize) { switch (fsize->pixel_format) { case V4L2_PIX_FMT_FWHT_STATELESS: break; case V4L2_PIX_FMT_FWHT: break; default: if (find_fmt(fsize->pixel_format)->id == fsize->pixel_format) break; return -EINVAL; } if (fsize->index) return -EINVAL; fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE; fsize->stepwise.min_width = MIN_WIDTH; fsize->stepwise.max_width = MAX_WIDTH; fsize->stepwise.step_width = 8; fsize->stepwise.min_height = MIN_HEIGHT; fsize->stepwise.max_height = MAX_HEIGHT; fsize->stepwise.step_height = 8; return 0; } static int vicodec_subscribe_event(struct v4l2_fh *fh, const struct v4l2_event_subscription *sub) { struct vicodec_ctx *ctx = container_of(fh, struct vicodec_ctx, fh); switch (sub->type) { case V4L2_EVENT_SOURCE_CHANGE: if (ctx->is_enc) return -EINVAL; fallthrough; case V4L2_EVENT_EOS: if (ctx->is_stateless) return -EINVAL; return v4l2_event_subscribe(fh, sub, 0, NULL); default: return v4l2_ctrl_subscribe_event(fh, sub); } } static const struct v4l2_ioctl_ops vicodec_ioctl_ops = { .vidioc_querycap = vidioc_querycap, .vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap, .vidioc_g_fmt_vid_cap = vidioc_g_fmt_vid_cap, .vidioc_try_fmt_vid_cap = vidioc_try_fmt_vid_cap, .vidioc_s_fmt_vid_cap = vidioc_s_fmt_vid_cap, .vidioc_g_fmt_vid_cap_mplane = vidioc_g_fmt_vid_cap, .vidioc_try_fmt_vid_cap_mplane = vidioc_try_fmt_vid_cap, .vidioc_s_fmt_vid_cap_mplane = vidioc_s_fmt_vid_cap, .vidioc_enum_fmt_vid_out = vidioc_enum_fmt_vid_out, .vidioc_g_fmt_vid_out = vidioc_g_fmt_vid_out, .vidioc_try_fmt_vid_out = vidioc_try_fmt_vid_out, .vidioc_s_fmt_vid_out = vidioc_s_fmt_vid_out, .vidioc_g_fmt_vid_out_mplane = vidioc_g_fmt_vid_out, .vidioc_try_fmt_vid_out_mplane = vidioc_try_fmt_vid_out, .vidioc_s_fmt_vid_out_mplane = vidioc_s_fmt_vid_out, .vidioc_reqbufs = v4l2_m2m_ioctl_reqbufs, .vidioc_querybuf = v4l2_m2m_ioctl_querybuf, .vidioc_qbuf = v4l2_m2m_ioctl_qbuf, .vidioc_dqbuf = v4l2_m2m_ioctl_dqbuf, .vidioc_prepare_buf = v4l2_m2m_ioctl_prepare_buf, .vidioc_create_bufs = v4l2_m2m_ioctl_create_bufs, .vidioc_expbuf = v4l2_m2m_ioctl_expbuf, .vidioc_remove_bufs = v4l2_m2m_ioctl_remove_bufs, .vidioc_streamon = v4l2_m2m_ioctl_streamon, .vidioc_streamoff = v4l2_m2m_ioctl_streamoff, .vidioc_g_selection = vidioc_g_selection, .vidioc_s_selection = vidioc_s_selection, .vidioc_try_encoder_cmd = v4l2_m2m_ioctl_try_encoder_cmd, .vidioc_encoder_cmd = vicodec_encoder_cmd, .vidioc_try_decoder_cmd = v4l2_m2m_ioctl_try_decoder_cmd, .vidioc_decoder_cmd = vicodec_decoder_cmd, .vidioc_enum_framesizes = vicodec_enum_framesizes, .vidioc_subscribe_event = vicodec_subscribe_event, .vidioc_unsubscribe_event = v4l2_event_unsubscribe, }; /* * Queue operations */ static int vicodec_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct vicodec_ctx *ctx = vb2_get_drv_priv(vq); struct vicodec_q_data *q_data = get_q_data(ctx, vq->type); unsigned int size = q_data->sizeimage; if (*nplanes) return sizes[0] < size ? -EINVAL : 0; *nplanes = 1; sizes[0] = size; q_data->vb2_sizeimage = size; return 0; } static int vicodec_buf_out_validate(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); vbuf->field = V4L2_FIELD_NONE; return 0; } static int vicodec_buf_prepare(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); struct vicodec_q_data *q_data; dprintk(ctx->dev, "type: %d\n", vb->vb2_queue->type); q_data = get_q_data(ctx, vb->vb2_queue->type); if (V4L2_TYPE_IS_OUTPUT(vb->vb2_queue->type)) { if (vbuf->field == V4L2_FIELD_ANY) vbuf->field = V4L2_FIELD_NONE; if (vbuf->field != V4L2_FIELD_NONE) { dprintk(ctx->dev, "%s field isn't supported\n", __func__); return -EINVAL; } } if (vb2_plane_size(vb, 0) < q_data->vb2_sizeimage) { dprintk(ctx->dev, "%s data will not fit into plane (%lu < %lu)\n", __func__, vb2_plane_size(vb, 0), (long)q_data->vb2_sizeimage); return -EINVAL; } return 0; } static void vicodec_buf_queue(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); unsigned int sz = vb2_get_plane_payload(&vbuf->vb2_buf, 0); u8 *p_src = vb2_plane_vaddr(&vbuf->vb2_buf, 0); u8 *p = p_src; struct vb2_queue *vq_out = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT); struct vb2_queue *vq_cap = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); bool header_valid = false; static const struct v4l2_event rs_event = { .type = V4L2_EVENT_SOURCE_CHANGE, .u.src_change.changes = V4L2_EVENT_SRC_CH_RESOLUTION, }; if (V4L2_TYPE_IS_CAPTURE(vb->vb2_queue->type) && vb2_is_streaming(vb->vb2_queue) && v4l2_m2m_dst_buf_is_last(ctx->fh.m2m_ctx)) { unsigned int i; for (i = 0; i < vb->num_planes; i++) vb2_set_plane_payload(vb, i, 0); vbuf->field = V4L2_FIELD_NONE; vbuf->sequence = get_q_data(ctx, vb->vb2_queue->type)->sequence++; v4l2_m2m_last_buffer_done(ctx->fh.m2m_ctx, vbuf); v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); return; } /* buf_queue handles only the first source change event */ if (ctx->first_source_change_sent) { v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); return; } /* * if both queues are streaming, the source change event is * handled in job_ready */ if (vb2_is_streaming(vq_cap) && vb2_is_streaming(vq_out)) { v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); return; } /* * source change event is relevant only for the stateful decoder * in the compressed stream */ if (ctx->is_stateless || ctx->is_enc || V4L2_TYPE_IS_CAPTURE(vb->vb2_queue->type)) { v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); return; } do { enum vb2_buffer_state state = get_next_header(ctx, &p, p_src + sz - p); if (ctx->header_size < sizeof(struct fwht_cframe_hdr)) { v4l2_m2m_buf_done(vbuf, state); return; } header_valid = is_header_valid(&ctx->state.header); /* * p points right after the end of the header in the * buffer. If the header is invalid we set p to point * to the next byte after the start of the header */ if (!header_valid) { p = p - sizeof(struct fwht_cframe_hdr) + 1; if (p < p_src) p = p_src; ctx->header_size = 0; ctx->comp_magic_cnt = 0; } } while (!header_valid); ctx->cur_buf_offset = p - p_src; update_capture_data_from_header(ctx); ctx->first_source_change_sent = true; v4l2_event_queue_fh(&ctx->fh, &rs_event); v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf); } static void vicodec_return_bufs(struct vb2_queue *q, u32 state) { struct vicodec_ctx *ctx = vb2_get_drv_priv(q); struct vb2_v4l2_buffer *vbuf; for (;;) { if (V4L2_TYPE_IS_OUTPUT(q->type)) vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx); else vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx); if (vbuf == NULL) return; if (ctx->is_stateless && V4L2_TYPE_IS_OUTPUT(q->type)) { struct media_request *req = vbuf->vb2_buf.req_obj.req; v4l2_ctrl_request_complete(req, &ctx->hdl); media_request_manual_complete(req); } spin_lock(ctx->lock); v4l2_m2m_buf_done(vbuf, state); spin_unlock(ctx->lock); } } static unsigned int total_frame_size(struct vicodec_q_data *q_data) { unsigned int size; unsigned int chroma_div; if (!q_data->info) { WARN_ON(1); return 0; } size = q_data->coded_width * q_data->coded_height; chroma_div = q_data->info->width_div * q_data->info->height_div; if (q_data->info->components_num == 4) return 2 * size + 2 * (size / chroma_div); else if (q_data->info->components_num == 3) return size + 2 * (size / chroma_div); return size; } static int vicodec_start_streaming(struct vb2_queue *q, unsigned int count) { struct vicodec_ctx *ctx = vb2_get_drv_priv(q); struct vicodec_q_data *q_data = get_q_data(ctx, q->type); struct v4l2_fwht_state *state = &ctx->state; const struct v4l2_fwht_pixfmt_info *info = q_data->info; unsigned int size = q_data->coded_width * q_data->coded_height; unsigned int chroma_div; unsigned int total_planes_size; u8 *new_comp_frame = NULL; chroma_div = info->width_div * info->height_div; q_data->sequence = 0; v4l2_m2m_update_start_streaming_state(ctx->fh.m2m_ctx, q); state->gop_cnt = 0; if ((V4L2_TYPE_IS_OUTPUT(q->type) && !ctx->is_enc) || (V4L2_TYPE_IS_CAPTURE(q->type) && ctx->is_enc)) return 0; if (info->id == V4L2_PIX_FMT_FWHT || info->id == V4L2_PIX_FMT_FWHT_STATELESS) { vicodec_return_bufs(q, VB2_BUF_STATE_QUEUED); return -EINVAL; } total_planes_size = total_frame_size(q_data); ctx->comp_max_size = total_planes_size; state->visible_width = q_data->visible_width; state->visible_height = q_data->visible_height; state->coded_width = q_data->coded_width; state->coded_height = q_data->coded_height; state->stride = q_data->coded_width * info->bytesperline_mult; if (ctx->is_stateless) { state->ref_stride = state->stride; return 0; } state->ref_stride = q_data->coded_width * info->luma_alpha_step; state->ref_frame.buf = kvmalloc(total_planes_size, GFP_KERNEL); state->ref_frame.luma = state->ref_frame.buf; new_comp_frame = kvmalloc(ctx->comp_max_size, GFP_KERNEL); if (!state->ref_frame.luma || !new_comp_frame) { kvfree(state->ref_frame.luma); kvfree(new_comp_frame); vicodec_return_bufs(q, VB2_BUF_STATE_QUEUED); return -ENOMEM; } /* * if state->compressed_frame was already allocated then * it contain data of the first frame of the new resolution */ if (state->compressed_frame) { if (ctx->comp_size > ctx->comp_max_size) ctx->comp_size = ctx->comp_max_size; memcpy(new_comp_frame, state->compressed_frame, ctx->comp_size); } kvfree(state->compressed_frame); state->compressed_frame = new_comp_frame; if (info->components_num < 3) { state->ref_frame.cb = NULL; state->ref_frame.cr = NULL; state->ref_frame.alpha = NULL; return 0; } state->ref_frame.cb = state->ref_frame.luma + size; state->ref_frame.cr = state->ref_frame.cb + size / chroma_div; if (info->components_num == 4) state->ref_frame.alpha = state->ref_frame.cr + size / chroma_div; else state->ref_frame.alpha = NULL; return 0; } static void vicodec_stop_streaming(struct vb2_queue *q) { struct vicodec_ctx *ctx = vb2_get_drv_priv(q); vicodec_return_bufs(q, VB2_BUF_STATE_ERROR); v4l2_m2m_update_stop_streaming_state(ctx->fh.m2m_ctx, q); if (V4L2_TYPE_IS_OUTPUT(q->type) && v4l2_m2m_has_stopped(ctx->fh.m2m_ctx)) v4l2_event_queue_fh(&ctx->fh, &vicodec_eos_event); if (!ctx->is_enc && V4L2_TYPE_IS_OUTPUT(q->type)) ctx->first_source_change_sent = false; if ((!V4L2_TYPE_IS_OUTPUT(q->type) && !ctx->is_enc) || (V4L2_TYPE_IS_OUTPUT(q->type) && ctx->is_enc)) { if (!ctx->is_stateless) kvfree(ctx->state.ref_frame.buf); ctx->state.ref_frame.buf = NULL; ctx->state.ref_frame.luma = NULL; ctx->comp_max_size = 0; ctx->source_changed = false; } if (V4L2_TYPE_IS_OUTPUT(q->type) && !ctx->is_enc) { ctx->cur_buf_offset = 0; ctx->comp_size = 0; ctx->header_size = 0; ctx->comp_magic_cnt = 0; ctx->comp_has_frame = false; ctx->comp_has_next_frame = false; } } static void vicodec_buf_request_complete(struct vb2_buffer *vb) { struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue); v4l2_ctrl_request_complete(vb->req_obj.req, &ctx->hdl); media_request_manual_complete(vb->req_obj.req); } static const struct vb2_ops vicodec_qops = { .queue_setup = vicodec_queue_setup, .buf_out_validate = vicodec_buf_out_validate, .buf_prepare = vicodec_buf_prepare, .buf_queue = vicodec_buf_queue, .buf_request_complete = vicodec_buf_request_complete, .start_streaming = vicodec_start_streaming, .stop_streaming = vicodec_stop_streaming, }; static int queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_queue *dst_vq) { struct vicodec_ctx *ctx = priv; int ret; src_vq->type = (multiplanar ? V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE : V4L2_BUF_TYPE_VIDEO_OUTPUT); src_vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF; src_vq->drv_priv = ctx; src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer); src_vq->ops = &vicodec_qops; src_vq->mem_ops = &vb2_vmalloc_memops; src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY; if (ctx->is_enc) { src_vq->lock = &ctx->dev->stateful_enc.mutex; src_vq->min_reqbufs_allocation = VICODEC_REC_BUFS; } else if (ctx->is_stateless) { src_vq->lock = &ctx->dev->stateless_dec.mutex; } else { src_vq->lock = &ctx->dev->stateful_dec.mutex; } src_vq->supports_requests = ctx->is_stateless; src_vq->requires_requests = ctx->is_stateless; ret = vb2_queue_init(src_vq); if (ret) return ret; dst_vq->type = (multiplanar ? V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE : V4L2_BUF_TYPE_VIDEO_CAPTURE); dst_vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF; dst_vq->max_num_buffers = 64; dst_vq->drv_priv = ctx; dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer); dst_vq->ops = &vicodec_qops; dst_vq->mem_ops = &vb2_vmalloc_memops; dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY; dst_vq->lock = src_vq->lock; if (!ctx->is_stateless && !ctx->is_enc) dst_vq->min_reqbufs_allocation = VICODEC_REC_BUFS; return vb2_queue_init(dst_vq); } static int vicodec_try_ctrl(struct v4l2_ctrl *ctrl) { struct vicodec_ctx *ctx = container_of(ctrl->handler, struct vicodec_ctx, hdl); const struct v4l2_ctrl_fwht_params *params; struct vicodec_q_data *q_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE); switch (ctrl->id) { case V4L2_CID_STATELESS_FWHT_PARAMS: if (!q_dst->info) return -EINVAL; params = ctrl->p_new.p_fwht_params; if (params->width > q_dst->coded_width || params->width < MIN_WIDTH || params->height > q_dst->coded_height || params->height < MIN_HEIGHT) return -EINVAL; if (!validate_by_version(params->flags, params->version)) return -EINVAL; if (!validate_stateless_params_flags(params, q_dst->info)) return -EINVAL; return 0; default: return 0; } return 0; } static void update_header_from_stateless_params(struct vicodec_ctx *ctx, const struct v4l2_ctrl_fwht_params *params) { struct fwht_cframe_hdr *p_hdr = &ctx->state.header; p_hdr->magic1 = FWHT_MAGIC1; p_hdr->magic2 = FWHT_MAGIC2; p_hdr->version = htonl(params->version); p_hdr->width = htonl(params->width); p_hdr->height = htonl(params->height); p_hdr->flags = htonl(params->flags); p_hdr->colorspace = htonl(params->colorspace); p_hdr->xfer_func = htonl(params->xfer_func); p_hdr->ycbcr_enc = htonl(params->ycbcr_enc); p_hdr->quantization = htonl(params->quantization); } static int vicodec_s_ctrl(struct v4l2_ctrl *ctrl) { struct vicodec_ctx *ctx = container_of(ctrl->handler, struct vicodec_ctx, hdl); const struct v4l2_ctrl_fwht_params *params; switch (ctrl->id) { case V4L2_CID_MPEG_VIDEO_GOP_SIZE: ctx->state.gop_size = ctrl->val; return 0; case V4L2_CID_FWHT_I_FRAME_QP: ctx->state.i_frame_qp = ctrl->val; return 0; case V4L2_CID_FWHT_P_FRAME_QP: ctx->state.p_frame_qp = ctrl->val; return 0; case V4L2_CID_STATELESS_FWHT_PARAMS: params = ctrl->p_new.p_fwht_params; update_header_from_stateless_params(ctx, params); ctx->state.ref_frame_ts = params->backward_ref_ts; return 0; } return -EINVAL; } static const struct v4l2_ctrl_ops vicodec_ctrl_ops = { .s_ctrl = vicodec_s_ctrl, .try_ctrl = vicodec_try_ctrl, }; static const struct v4l2_ctrl_config vicodec_ctrl_stateless_state = { .ops = &vicodec_ctrl_ops, .id = V4L2_CID_STATELESS_FWHT_PARAMS, .elem_size = sizeof(struct v4l2_ctrl_fwht_params), }; /* * File operations */ static int vicodec_open(struct file *file) { const struct v4l2_fwht_pixfmt_info *info = v4l2_fwht_get_pixfmt(0); struct video_device *vfd = video_devdata(file); struct vicodec_dev *dev = video_drvdata(file); struct vicodec_ctx *ctx = NULL; struct v4l2_ctrl_handler *hdl; unsigned int raw_size; unsigned int comp_size; int rc = 0; if (mutex_lock_interruptible(vfd->lock)) return -ERESTARTSYS; ctx = kzalloc_obj(*ctx); if (!ctx) { rc = -ENOMEM; goto open_unlock; } if (vfd == &dev->stateful_enc.vfd) ctx->is_enc = true; else if (vfd == &dev->stateless_dec.vfd) ctx->is_stateless = true; v4l2_fh_init(&ctx->fh, video_devdata(file)); ctx->dev = dev; hdl = &ctx->hdl; v4l2_ctrl_handler_init(hdl, 5); v4l2_ctrl_new_std(hdl, &vicodec_ctrl_ops, V4L2_CID_MPEG_VIDEO_GOP_SIZE, 1, 16, 1, 10); v4l2_ctrl_new_std(hdl, &vicodec_ctrl_ops, V4L2_CID_FWHT_I_FRAME_QP, 1, 31, 1, 20); v4l2_ctrl_new_std(hdl, &vicodec_ctrl_ops, V4L2_CID_FWHT_P_FRAME_QP, 1, 31, 1, 20); if (ctx->is_stateless) v4l2_ctrl_new_custom(hdl, &vicodec_ctrl_stateless_state, NULL); else v4l2_ctrl_new_std(hdl, &vicodec_ctrl_ops, ctx->is_enc ? V4L2_CID_MIN_BUFFERS_FOR_OUTPUT : V4L2_CID_MIN_BUFFERS_FOR_CAPTURE, VICODEC_REC_BUFS, VICODEC_REC_BUFS, 1, VICODEC_REC_BUFS); if (hdl->error) { rc = hdl->error; v4l2_ctrl_handler_free(hdl); kfree(ctx); goto open_unlock; } ctx->fh.ctrl_handler = hdl; v4l2_ctrl_handler_setup(hdl); if (ctx->is_enc) ctx->q_data[V4L2_M2M_SRC].info = info; else if (ctx->is_stateless) ctx->q_data[V4L2_M2M_SRC].info = &pixfmt_stateless_fwht; else ctx->q_data[V4L2_M2M_SRC].info = &pixfmt_fwht; ctx->q_data[V4L2_M2M_SRC].coded_width = 1280; ctx->q_data[V4L2_M2M_SRC].coded_height = 720; ctx->q_data[V4L2_M2M_SRC].visible_width = 1280; ctx->q_data[V4L2_M2M_SRC].visible_height = 720; raw_size = 1280 * 720 * info->sizeimage_mult / info->sizeimage_div; comp_size = 1280 * 720 * pixfmt_fwht.sizeimage_mult / pixfmt_fwht.sizeimage_div; if (ctx->is_enc) ctx->q_data[V4L2_M2M_SRC].sizeimage = raw_size; else if (ctx->is_stateless) ctx->q_data[V4L2_M2M_SRC].sizeimage = comp_size; else ctx->q_data[V4L2_M2M_SRC].sizeimage = comp_size + sizeof(struct fwht_cframe_hdr); ctx->q_data[V4L2_M2M_DST] = ctx->q_data[V4L2_M2M_SRC]; if (ctx->is_enc) { ctx->q_data[V4L2_M2M_DST].info = &pixfmt_fwht; ctx->q_data[V4L2_M2M_DST].sizeimage = comp_size + sizeof(struct fwht_cframe_hdr); } else { ctx->q_data[V4L2_M2M_DST].info = info; ctx->q_data[V4L2_M2M_DST].sizeimage = raw_size; } ctx->state.colorspace = V4L2_COLORSPACE_REC709; if (ctx->is_enc) { ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->stateful_enc.m2m_dev, ctx, &queue_init); ctx->lock = &dev->stateful_enc.lock; } else if (ctx->is_stateless) { ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->stateless_dec.m2m_dev, ctx, &queue_init); ctx->lock = &dev->stateless_dec.lock; } else { ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->stateful_dec.m2m_dev, ctx, &queue_init); ctx->lock = &dev->stateful_dec.lock; } if (IS_ERR(ctx->fh.m2m_ctx)) { rc = PTR_ERR(ctx->fh.m2m_ctx); v4l2_ctrl_handler_free(hdl); v4l2_fh_exit(&ctx->fh); kfree(ctx); goto open_unlock; } v4l2_fh_add(&ctx->fh, file); open_unlock: mutex_unlock(vfd->lock); return rc; } static int vicodec_release(struct file *file) { struct video_device *vfd = video_devdata(file); struct vicodec_ctx *ctx = file2ctx(file); mutex_lock(vfd->lock); v4l2_m2m_ctx_release(ctx->fh.m2m_ctx); mutex_unlock(vfd->lock); v4l2_fh_del(&ctx->fh, file); v4l2_fh_exit(&ctx->fh); v4l2_ctrl_handler_free(&ctx->hdl); kvfree(ctx->state.compressed_frame); kfree(ctx); return 0; } static int vicodec_request_validate(struct media_request *req) { struct media_request_object *obj; struct v4l2_ctrl_handler *parent_hdl, *hdl; struct vicodec_ctx *ctx = NULL; struct v4l2_ctrl *ctrl; unsigned int count; list_for_each_entry(obj, &req->objects, list) { struct vb2_buffer *vb; if (vb2_request_object_is_buffer(obj)) { vb = container_of(obj, struct vb2_buffer, req_obj); ctx = vb2_get_drv_priv(vb->vb2_queue); break; } } if (!ctx) { pr_err("No buffer was provided with the request\n"); return -ENOENT; } count = vb2_request_buffer_cnt(req); if (!count) { v4l2_info(&ctx->dev->v4l2_dev, "No buffer was provided with the request\n"); return -ENOENT; } else if (count > 1) { v4l2_info(&ctx->dev->v4l2_dev, "More than one buffer was provided with the request\n"); return -EINVAL; } parent_hdl = &ctx->hdl; hdl = v4l2_ctrl_request_hdl_find(req, parent_hdl); if (!hdl) { v4l2_info(&ctx->dev->v4l2_dev, "Missing codec control\n"); return -ENOENT; } ctrl = v4l2_ctrl_request_hdl_ctrl_find(hdl, vicodec_ctrl_stateless_state.id); v4l2_ctrl_request_hdl_put(hdl); if (!ctrl) { v4l2_info(&ctx->dev->v4l2_dev, "Missing required codec control\n"); return -ENOENT; } return vb2_request_validate(req); } static void vicodec_request_queue(struct media_request *req) { media_request_mark_manual_completion(req); v4l2_m2m_request_queue(req); } static const struct v4l2_file_operations vicodec_fops = { .owner = THIS_MODULE, .open = vicodec_open, .release = vicodec_release, .poll = v4l2_m2m_fop_poll, .unlocked_ioctl = video_ioctl2, .mmap = v4l2_m2m_fop_mmap, }; static const struct video_device vicodec_videodev = { .name = VICODEC_NAME, .vfl_dir = VFL_DIR_M2M, .fops = &vicodec_fops, .ioctl_ops = &vicodec_ioctl_ops, .minor = -1, .release = video_device_release_empty, }; static const struct media_device_ops vicodec_m2m_media_ops = { .req_validate = vicodec_request_validate, .req_queue = vicodec_request_queue, }; static const struct v4l2_m2m_ops m2m_ops = { .device_run = device_run, .job_ready = job_ready, }; static int register_instance(struct vicodec_dev *dev, struct vicodec_dev_instance *dev_instance, const char *name, bool is_enc, bool is_stateless) { struct video_device *vfd; int ret; spin_lock_init(&dev_instance->lock); mutex_init(&dev_instance->mutex); dev_instance->m2m_dev = v4l2_m2m_init(&m2m_ops); if (IS_ERR(dev_instance->m2m_dev)) { v4l2_err(&dev->v4l2_dev, "Failed to init vicodec enc device\n"); return PTR_ERR(dev_instance->m2m_dev); } dev_instance->vfd = vicodec_videodev; vfd = &dev_instance->vfd; vfd->lock = &dev_instance->mutex; vfd->v4l2_dev = &dev->v4l2_dev; strscpy(vfd->name, name, sizeof(vfd->name)); vfd->device_caps = V4L2_CAP_STREAMING | (multiplanar ? V4L2_CAP_VIDEO_M2M_MPLANE : V4L2_CAP_VIDEO_M2M); if (is_enc || is_stateless) { v4l2_disable_ioctl(vfd, VIDIOC_DECODER_CMD); v4l2_disable_ioctl(vfd, VIDIOC_TRY_DECODER_CMD); } if (!is_enc) { v4l2_disable_ioctl(vfd, VIDIOC_ENCODER_CMD); v4l2_disable_ioctl(vfd, VIDIOC_TRY_ENCODER_CMD); } video_set_drvdata(vfd, dev); ret = video_register_device(vfd, VFL_TYPE_VIDEO, 0); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to register video device '%s'\n", name); v4l2_m2m_release(dev_instance->m2m_dev); return ret; } v4l2_info(&dev->v4l2_dev, "Device '%s' registered as /dev/video%d\n", name, vfd->num); return 0; } static void vicodec_v4l2_dev_release(struct v4l2_device *v4l2_dev) { struct vicodec_dev *dev = container_of(v4l2_dev, struct vicodec_dev, v4l2_dev); v4l2_device_unregister(&dev->v4l2_dev); v4l2_m2m_release(dev->stateful_enc.m2m_dev); v4l2_m2m_release(dev->stateful_dec.m2m_dev); v4l2_m2m_release(dev->stateless_dec.m2m_dev); #ifdef CONFIG_MEDIA_CONTROLLER media_device_cleanup(&dev->mdev); #endif kfree(dev); } static int vicodec_probe(struct platform_device *pdev) { struct vicodec_dev *dev; int ret; dev = kzalloc_obj(*dev); if (!dev) return -ENOMEM; ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev); if (ret) goto free_dev; dev->v4l2_dev.release = vicodec_v4l2_dev_release; #ifdef CONFIG_MEDIA_CONTROLLER dev->mdev.dev = &pdev->dev; strscpy(dev->mdev.model, "vicodec", sizeof(dev->mdev.model)); strscpy(dev->mdev.bus_info, "platform:vicodec", sizeof(dev->mdev.bus_info)); media_device_init(&dev->mdev); dev->mdev.ops = &vicodec_m2m_media_ops; dev->v4l2_dev.mdev = &dev->mdev; #endif platform_set_drvdata(pdev, dev); ret = register_instance(dev, &dev->stateful_enc, "stateful-encoder", true, false); if (ret) goto unreg_dev; ret = register_instance(dev, &dev->stateful_dec, "stateful-decoder", false, false); if (ret) goto unreg_sf_enc; ret = register_instance(dev, &dev->stateless_dec, "stateless-decoder", false, true); if (ret) goto unreg_sf_dec; #ifdef CONFIG_MEDIA_CONTROLLER ret = v4l2_m2m_register_media_controller(dev->stateful_enc.m2m_dev, &dev->stateful_enc.vfd, MEDIA_ENT_F_PROC_VIDEO_ENCODER); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller for enc\n"); goto unreg_m2m; } ret = v4l2_m2m_register_media_controller(dev->stateful_dec.m2m_dev, &dev->stateful_dec.vfd, MEDIA_ENT_F_PROC_VIDEO_DECODER); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller for dec\n"); goto unreg_m2m_sf_enc_mc; } ret = v4l2_m2m_register_media_controller(dev->stateless_dec.m2m_dev, &dev->stateless_dec.vfd, MEDIA_ENT_F_PROC_VIDEO_DECODER); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller for stateless dec\n"); goto unreg_m2m_sf_dec_mc; } ret = media_device_register(&dev->mdev); if (ret) { v4l2_err(&dev->v4l2_dev, "Failed to register mem2mem media device\n"); goto unreg_m2m_sl_dec_mc; } #endif return 0; #ifdef CONFIG_MEDIA_CONTROLLER unreg_m2m_sl_dec_mc: v4l2_m2m_unregister_media_controller(dev->stateless_dec.m2m_dev); unreg_m2m_sf_dec_mc: v4l2_m2m_unregister_media_controller(dev->stateful_dec.m2m_dev); unreg_m2m_sf_enc_mc: v4l2_m2m_unregister_media_controller(dev->stateful_enc.m2m_dev); unreg_m2m: video_unregister_device(&dev->stateless_dec.vfd); v4l2_m2m_release(dev->stateless_dec.m2m_dev); #endif unreg_sf_dec: video_unregister_device(&dev->stateful_dec.vfd); v4l2_m2m_release(dev->stateful_dec.m2m_dev); unreg_sf_enc: video_unregister_device(&dev->stateful_enc.vfd); v4l2_m2m_release(dev->stateful_enc.m2m_dev); unreg_dev: v4l2_device_unregister(&dev->v4l2_dev); free_dev: kfree(dev); return ret; } static void vicodec_remove(struct platform_device *pdev) { struct vicodec_dev *dev = platform_get_drvdata(pdev); v4l2_info(&dev->v4l2_dev, "Removing " VICODEC_NAME); #ifdef CONFIG_MEDIA_CONTROLLER media_device_unregister(&dev->mdev); v4l2_m2m_unregister_media_controller(dev->stateful_enc.m2m_dev); v4l2_m2m_unregister_media_controller(dev->stateful_dec.m2m_dev); v4l2_m2m_unregister_media_controller(dev->stateless_dec.m2m_dev); #endif video_unregister_device(&dev->stateful_enc.vfd); video_unregister_device(&dev->stateful_dec.vfd); video_unregister_device(&dev->stateless_dec.vfd); v4l2_device_put(&dev->v4l2_dev); } static struct platform_driver vicodec_pdrv = { .probe = vicodec_probe, .remove = vicodec_remove, .driver = { .name = VICODEC_NAME, }, }; static void __exit vicodec_exit(void) { platform_driver_unregister(&vicodec_pdrv); platform_device_unregister(&vicodec_pdev); } static int __init vicodec_init(void) { int ret; ret = platform_device_register(&vicodec_pdev); if (ret) return ret; ret = platform_driver_register(&vicodec_pdrv); if (ret) platform_device_unregister(&vicodec_pdev); return ret; } module_init(vicodec_init); module_exit(vicodec_exit); |
| 2 2 6 5 5 5 3 8 8 6 5 6 7 7 4 6 3 9 9 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Binary Increase Congestion control for TCP * Home page: * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of BICTCP in * Lison-Xu, Kahaled Harfoush, and Injong Rhee. * "Binary Increase Congestion Control for Fast, Long Distance * Networks" in InfoComm 2004 * Available from: * http://netsrv.csc.ncsu.edu/export/bitcp.pdf * * Unless BIC is enabled and congestion window is large * this behaves the same as the original Reno. */ #include <linux/mm.h> #include <linux/module.h> #include <net/tcp.h> #define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation * max_cwnd = snd_cwnd * beta */ #define BICTCP_B 4 /* * In binary search, * go to point (max+min)/N */ static int fast_convergence = 1; static int max_increment = 16; static int low_window = 14; static int beta = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */ static int initial_ssthresh; static int smooth_part = 20; module_param(fast_convergence, int, 0644); MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence"); module_param(max_increment, int, 0644); MODULE_PARM_DESC(max_increment, "Limit on increment allowed during binary search"); module_param(low_window, int, 0644); MODULE_PARM_DESC(low_window, "lower bound on congestion window (for TCP friendliness)"); 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(smooth_part, int, 0644); MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wmax-B to Wmax"); /* 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 epoch_start; /* beginning of an epoch */ #define ACK_RATIO_SHIFT 4 u32 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ }; static inline void bictcp_reset(struct bictcp *ca) { ca->cnt = 0; ca->last_max_cwnd = 0; ca->last_cwnd = 0; ca->last_time = 0; ca->epoch_start = 0; ca->delayed_ack = 2 << ACK_RATIO_SHIFT; } static void bictcp_init(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); if (initial_ssthresh) WRITE_ONCE(tcp_sk(sk)->snd_ssthresh, initial_ssthresh); } /* * Compute congestion window to use. */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { if (ca->last_cwnd == cwnd && (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; ca->last_cwnd = cwnd; ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) /* record the beginning of an epoch */ ca->epoch_start = tcp_jiffies32; /* start off normal */ if (cwnd <= low_window) { ca->cnt = cwnd; return; } /* binary increase */ if (cwnd < ca->last_max_cwnd) { __u32 dist = (ca->last_max_cwnd - cwnd) / BICTCP_B; if (dist > max_increment) /* linear increase */ ca->cnt = cwnd / max_increment; else if (dist <= 1U) /* binary search increase */ ca->cnt = (cwnd * smooth_part) / BICTCP_B; else /* binary search increase */ ca->cnt = cwnd / dist; } else { /* slow start AMD linear increase */ if (cwnd < ca->last_max_cwnd + BICTCP_B) /* slow start */ ca->cnt = (cwnd * smooth_part) / BICTCP_B; else if (cwnd < ca->last_max_cwnd + max_increment*(BICTCP_B-1)) /* slow start */ ca->cnt = (cwnd * (BICTCP_B-1)) / (cwnd - ca->last_max_cwnd); else /* linear increase */ ca->cnt = cwnd / max_increment; } /* if in slow start or link utilization is very low */ if (ca->last_max_cwnd == 0) { if (ca->cnt > 20) /* increase cwnd 5% per RTT */ ca->cnt = 20; } ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack; if (ca->cnt == 0) /* cannot be zero */ ca->cnt = 1; } static void bictcp_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)); tcp_cong_avoid_ai(tp, ca->cnt, acked); } /* * behave like Reno until low_window is reached, * then increase congestion window slowly */ static u32 bictcp_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); if (tcp_snd_cwnd(tp) <= low_window) return max(tcp_snd_cwnd(tp) >> 1U, 2U); else return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); } static void bictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) bictcp_reset(inet_csk_ca(sk)); } /* Track delayed acknowledgment ratio using sliding window * ratio = (15*ratio + sample) / 16 */ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_state == TCP_CA_Open) { struct bictcp *ca = inet_csk_ca(sk); ca->delayed_ack += sample->pkts_acked - (ca->delayed_ack >> ACK_RATIO_SHIFT); } } static struct tcp_congestion_ops bictcp __read_mostly = { .init = bictcp_init, .ssthresh = bictcp_recalc_ssthresh, .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, .undo_cwnd = tcp_reno_undo_cwnd, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, .name = "bic", }; static int __init bictcp_register(void) { BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&bictcp); } static void __exit bictcp_unregister(void) { tcp_unregister_congestion_control(&bictcp); } module_init(bictcp_register); module_exit(bictcp_unregister); MODULE_AUTHOR("Stephen Hemminger"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("BIC TCP"); |
| 1430 1430 1375 1375 1429 1427 1429 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Functions for initializing, allocating, freeing and duplicating VMAs. Shared * between CONFIG_MMU and non-CONFIG_MMU kernel configurations. */ #include "vma_internal.h" #include "vma.h" /* SLAB cache for vm_area_struct structures */ static struct kmem_cache *vm_area_cachep; void __init vma_state_init(void) { struct kmem_cache_args args = { .use_freeptr_offset = true, .freeptr_offset = offsetof(struct vm_area_struct, vm_freeptr), .sheaf_capacity = 32, }; vm_area_cachep = kmem_cache_create("vm_area_struct", sizeof(struct vm_area_struct), &args, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT); } 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) return NULL; vma_init(vma, mm); return vma; } static void vm_area_init_from(const struct vm_area_struct *src, struct vm_area_struct *dest) { dest->vm_mm = src->vm_mm; dest->vm_ops = src->vm_ops; dest->vm_start = src->vm_start; dest->vm_end = src->vm_end; dest->anon_vma = src->anon_vma; dest->vm_pgoff = src->vm_pgoff; dest->vm_file = src->vm_file; dest->vm_private_data = src->vm_private_data; vm_flags_init(dest, src->vm_flags); memcpy(&dest->vm_page_prot, &src->vm_page_prot, sizeof(dest->vm_page_prot)); /* * src->shared.rb may be modified concurrently when called from * dup_mmap(), but the clone will reinitialize it. */ data_race(memcpy(&dest->shared, &src->shared, sizeof(dest->shared))); memcpy(&dest->vm_userfaultfd_ctx, &src->vm_userfaultfd_ctx, sizeof(dest->vm_userfaultfd_ctx)); #ifdef CONFIG_ANON_VMA_NAME dest->anon_name = src->anon_name; #endif #ifdef CONFIG_SWAP memcpy(&dest->swap_readahead_info, &src->swap_readahead_info, sizeof(dest->swap_readahead_info)); #endif #ifndef CONFIG_MMU dest->vm_region = src->vm_region; #endif #ifdef CONFIG_NUMA dest->vm_policy = src->vm_policy; #endif #ifdef __HAVE_PFNMAP_TRACKING dest->pfnmap_track_ctx = NULL; #endif } #ifdef __HAVE_PFNMAP_TRACKING static inline int vma_pfnmap_track_ctx_dup(struct vm_area_struct *orig, struct vm_area_struct *new) { struct pfnmap_track_ctx *ctx = orig->pfnmap_track_ctx; if (likely(!ctx)) return 0; /* * We don't expect to ever hit this. If ever required, we would have * to duplicate the tracking. */ if (unlikely(kref_read(&ctx->kref) >= REFCOUNT_MAX)) return -ENOMEM; kref_get(&ctx->kref); new->pfnmap_track_ctx = ctx; return 0; } static inline void vma_pfnmap_track_ctx_release(struct vm_area_struct *vma) { struct pfnmap_track_ctx *ctx = vma->pfnmap_track_ctx; if (likely(!ctx)) return; kref_put(&ctx->kref, pfnmap_track_ctx_release); vma->pfnmap_track_ctx = NULL; } #else static inline int vma_pfnmap_track_ctx_dup(struct vm_area_struct *orig, struct vm_area_struct *new) { return 0; } static inline void vma_pfnmap_track_ctx_release(struct vm_area_struct *vma) { } #endif 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) return NULL; ASSERT_EXCLUSIVE_WRITER(orig->vm_flags); ASSERT_EXCLUSIVE_WRITER(orig->vm_file); vm_area_init_from(orig, new); if (vma_pfnmap_track_ctx_dup(orig, new)) { kmem_cache_free(vm_area_cachep, new); return NULL; } vma_lock_init(new, true); INIT_LIST_HEAD(&new->anon_vma_chain); vma_numab_state_init(new); dup_anon_vma_name(orig, new); return new; } void vm_area_free(struct vm_area_struct *vma) { /* The vma should be detached while being destroyed. */ vma_assert_detached(vma); vma_numab_state_free(vma); free_anon_vma_name(vma); vma_pfnmap_track_ctx_release(vma); kmem_cache_free(vm_area_cachep, vma); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2008, 2009 open80211s Ltd. * Copyright (C) 2023-2024 Intel Corporation * Authors: Luis Carlos Cobo <luisca@cozybit.com> * Javier Cardona <javier@cozybit.com> */ #ifndef IEEE80211S_H #define IEEE80211S_H #include <linux/types.h> #include <linux/jhash.h> #include "ieee80211_i.h" /* Data structures */ /** * enum mesh_path_flags - mac80211 mesh path flags * * @MESH_PATH_ACTIVE: the mesh path can be used for forwarding * @MESH_PATH_RESOLVING: the discovery process is running for this mesh path * @MESH_PATH_SN_VALID: the mesh path contains a valid destination sequence * number * @MESH_PATH_FIXED: the mesh path has been manually set and should not be * modified * @MESH_PATH_RESOLVED: the mesh path can has been resolved * @MESH_PATH_REQ_QUEUED: there is an unsent path request for this destination * already queued up, waiting for the discovery process to start. * @MESH_PATH_DELETED: the mesh path has been deleted and should no longer * be used * * MESH_PATH_RESOLVED is used by the mesh path timer to * decide when to stop or cancel the mesh path discovery. */ enum mesh_path_flags { MESH_PATH_ACTIVE = BIT(0), MESH_PATH_RESOLVING = BIT(1), MESH_PATH_SN_VALID = BIT(2), MESH_PATH_FIXED = BIT(3), MESH_PATH_RESOLVED = BIT(4), MESH_PATH_REQ_QUEUED = BIT(5), MESH_PATH_DELETED = BIT(6), }; /** * enum mesh_deferred_task_flags - mac80211 mesh deferred tasks * * * * @MESH_WORK_HOUSEKEEPING: run the periodic mesh housekeeping tasks * @MESH_WORK_ROOT: the mesh root station needs to send a frame * @MESH_WORK_DRIFT_ADJUST: time to compensate for clock drift relative to other * mesh nodes * @MESH_WORK_MBSS_CHANGED: rebuild beacon and notify driver of BSS changes */ enum mesh_deferred_task_flags { MESH_WORK_HOUSEKEEPING, MESH_WORK_ROOT, MESH_WORK_DRIFT_ADJUST, MESH_WORK_MBSS_CHANGED, }; /** * struct mesh_path - mac80211 mesh path structure * * @dst: mesh path destination mac address * @mpp: mesh proxy mac address * @rhash: rhashtable list pointer * @walk_list: linked list containing all mesh_path objects. * @gate_list: list pointer for known gates list * @sdata: mesh subif * @next_hop: mesh neighbor to which frames for this destination will be * forwarded * @timer: mesh path discovery timer * @frame_queue: pending queue for frames sent to this destination while the * path is unresolved * @rcu: rcu head for freeing mesh path * @sn: target sequence number * @metric: current metric to this destination * @hop_count: hops to destination * @exp_time: in jiffies, when the path will expire or when it expired * @discovery_timeout: timeout (lapse in jiffies) used for the last discovery * retry * @discovery_retries: number of discovery retries * @flags: mesh path flags, as specified on &enum mesh_path_flags * @state_lock: mesh path state lock used to protect changes to the * mpath itself. No need to take this lock when adding or removing * an mpath to a hash bucket on a path table. * @rann_snd_addr: the RANN sender address * @rann_metric: the aggregated path metric towards the root node * @last_preq_to_root: Timestamp of last PREQ sent to root * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate * @path_change_count: the number of path changes to destination * @fast_tx_check: timestamp of last fast-xmit enable attempt * * * The dst address is unique in the mesh path table. Since the mesh_path is * protected by RCU, deleting the next_hop STA must remove / substitute the * mesh_path structure and wait until that is no longer reachable before * destroying the STA completely. */ struct mesh_path { u8 dst[ETH_ALEN]; u8 mpp[ETH_ALEN]; /* used for MPP or MAP */ struct rhash_head rhash; struct hlist_node walk_list; struct hlist_node gate_list; struct ieee80211_sub_if_data *sdata; struct sta_info __rcu *next_hop; struct timer_list timer; struct sk_buff_head frame_queue; struct rcu_head rcu; u32 sn; u32 metric; u8 hop_count; unsigned long exp_time; u32 discovery_timeout; u8 discovery_retries; enum mesh_path_flags flags; spinlock_t state_lock; u8 rann_snd_addr[ETH_ALEN]; u32 rann_metric; unsigned long last_preq_to_root; unsigned long fast_tx_check; bool is_root; bool is_gate; u32 path_change_count; }; #define MESH_FAST_TX_CACHE_MAX_SIZE 512 #define MESH_FAST_TX_CACHE_THRESHOLD_SIZE 384 #define MESH_FAST_TX_CACHE_TIMEOUT 8000 /* msecs */ /** * enum ieee80211_mesh_fast_tx_type - cached mesh fast tx entry type * * @MESH_FAST_TX_TYPE_LOCAL: tx from the local vif address as SA * @MESH_FAST_TX_TYPE_PROXIED: local tx with a different SA (e.g. bridged) * @MESH_FAST_TX_TYPE_FORWARDED: forwarded from a different mesh point * @NUM_MESH_FAST_TX_TYPE: number of entry types */ enum ieee80211_mesh_fast_tx_type { MESH_FAST_TX_TYPE_LOCAL, MESH_FAST_TX_TYPE_PROXIED, MESH_FAST_TX_TYPE_FORWARDED, /* must be last */ NUM_MESH_FAST_TX_TYPE }; /** * struct ieee80211_mesh_fast_tx_key - cached mesh fast tx entry key * * @addr: The Ethernet DA for this entry * @type: cache entry type */ struct ieee80211_mesh_fast_tx_key { u8 addr[ETH_ALEN] __aligned(2); u16 type; }; /** * struct ieee80211_mesh_fast_tx - cached mesh fast tx entry * @rhash: rhashtable pointer * @key: the lookup key for this cache entry * @fast_tx: base fast_tx data * @hdr: cached mesh and rfc1042 headers * @hdrlen: length of mesh + rfc1042 * @walk_list: list containing all the fast tx entries * @mpath: mesh path corresponding to the Mesh DA * @mppath: MPP entry corresponding to this DA * @timestamp: Last used time of this entry */ struct ieee80211_mesh_fast_tx { struct rhash_head rhash; struct ieee80211_mesh_fast_tx_key key; struct ieee80211_fast_tx fast_tx; u8 hdr[sizeof(struct ieee80211s_hdr) + sizeof(rfc1042_header)]; u16 hdrlen; struct mesh_path *mpath, *mppath; struct hlist_node walk_list; unsigned long timestamp; }; /* Recent multicast cache */ /* RMC_BUCKETS must be a power of 2, maximum 256 */ #define RMC_BUCKETS 256 #define RMC_QUEUE_MAX_LEN 4 #define RMC_TIMEOUT (3 * HZ) /** * struct rmc_entry - entry in the Recent Multicast Cache * * @seqnum: mesh sequence number of the frame * @exp_time: expiration time of the entry, in jiffies * @sa: source address of the frame * @list: hashtable list pointer * * The Recent Multicast Cache keeps track of the latest multicast frames that * have been received by a mesh interface and discards received multicast frames * that are found in the cache. */ struct rmc_entry { struct hlist_node list; unsigned long exp_time; u32 seqnum; u8 sa[ETH_ALEN]; }; struct mesh_rmc { struct hlist_head bucket[RMC_BUCKETS]; u32 idx_mask; }; #define IEEE80211_MESH_HOUSEKEEPING_INTERVAL (60 * HZ) #define MESH_PATH_EXPIRE (600 * HZ) /* Default maximum number of plinks per interface */ #define MESH_MAX_PLINKS 256 /* Maximum number of paths per interface */ #define MESH_MAX_MPATHS 1024 /* Number of frames buffered per destination for unresolved destinations */ #define MESH_FRAME_QUEUE_LEN 10 /* Public interfaces */ /* Various */ int ieee80211_fill_mesh_addresses(struct ieee80211_hdr *hdr, __le16 *fc, const u8 *da, const u8 *sa); unsigned int ieee80211_new_mesh_header(struct ieee80211_sub_if_data *sdata, struct ieee80211s_hdr *meshhdr, const char *addr4or5, const char *addr6); int mesh_rmc_check(struct ieee80211_sub_if_data *sdata, const u8 *addr, struct ieee80211s_hdr *mesh_hdr); bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *ie); int mesh_add_meshconf_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_meshid_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_rsn_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_ht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_ht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_vht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_he_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u8 ie_len); int mesh_add_he_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_he_6ghz_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_add_eht_cap_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u8 ie_len); int mesh_add_eht_oper_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_rmc_free(struct ieee80211_sub_if_data *sdata); int mesh_rmc_init(struct ieee80211_sub_if_data *sdata); void ieee80211s_init(void); void ieee80211s_update_metric(struct ieee80211_local *local, struct sta_info *sta, struct ieee80211_tx_status *st); void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata); int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata); void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh); const struct ieee80211_mesh_sync_ops *ieee80211_mesh_sync_ops_get(u8 method); /* wrapper for ieee80211_bss_info_change_notify() */ void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata, u64 changed); /* mesh power save */ u64 ieee80211_mps_local_status_update(struct ieee80211_sub_if_data *sdata); u64 ieee80211_mps_set_sta_local_pm(struct sta_info *sta, enum nl80211_mesh_power_mode pm); void ieee80211_mps_set_frame_flags(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_hdr *hdr); void ieee80211_mps_sta_status_update(struct sta_info *sta); void ieee80211_mps_rx_h_sta_process(struct sta_info *sta, struct ieee80211_hdr *hdr); void ieee80211_mpsp_trigger_process(u8 *qc, struct sta_info *sta, bool tx, bool acked); void ieee80211_mps_frame_release(struct sta_info *sta, struct ieee802_11_elems *elems); /* Mesh paths */ int mesh_nexthop_lookup(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata); struct mesh_path *mesh_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst); struct mesh_path *mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst); int mpp_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst, const u8 *mpp); struct mesh_path * mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx); struct mesh_path * mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx); void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop); void mesh_path_expire(struct ieee80211_sub_if_data *sdata); void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len); struct mesh_path * mesh_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst); int mesh_path_add_gate(struct mesh_path *mpath); int mesh_path_send_to_gates(struct mesh_path *mpath); int mesh_gate_num(struct ieee80211_sub_if_data *sdata); u32 airtime_link_metric_get(struct ieee80211_local *local, struct sta_info *sta); /* Mesh plinks */ void mesh_neighbour_update(struct ieee80211_sub_if_data *sdata, u8 *hw_addr, struct ieee802_11_elems *ie, struct ieee80211_rx_status *rx_status); bool mesh_peer_accepts_plinks(struct ieee802_11_elems *ie); u64 mesh_accept_plinks_update(struct ieee80211_sub_if_data *sdata); void mesh_plink_timer(struct timer_list *t); void mesh_plink_broken(struct sta_info *sta); u64 mesh_plink_deactivate(struct sta_info *sta); u64 mesh_plink_open(struct sta_info *sta); u64 mesh_plink_block(struct sta_info *sta); void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status); void mesh_sta_cleanup(struct sta_info *sta); /* Private interfaces */ /* Mesh paths */ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, u8 ttl, const u8 *target, u32 target_sn, u16 target_rcode, const u8 *ra); void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta); void mesh_path_flush_pending(struct mesh_path *mpath); void mesh_path_tx_pending(struct mesh_path *mpath); void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata); int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_path_timer(struct timer_list *t); void mesh_path_flush_by_nexthop(struct sta_info *sta); void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb); void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata); bool mesh_action_is_path_sel(struct ieee80211_mgmt *mgmt); struct ieee80211_mesh_fast_tx * mesh_fast_tx_get(struct ieee80211_sub_if_data *sdata, struct ieee80211_mesh_fast_tx_key *key); bool ieee80211_mesh_xmit_fast(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 ctrl_flags); void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, struct mesh_path *mpath); void mesh_fast_tx_gc(struct ieee80211_sub_if_data *sdata); void mesh_fast_tx_flush_addr(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_fast_tx_flush_mpath(struct mesh_path *mpath); void mesh_fast_tx_flush_sta(struct ieee80211_sub_if_data *sdata, struct sta_info *sta); void mesh_path_refresh(struct ieee80211_sub_if_data *sdata, struct mesh_path *mpath, const u8 *addr); #ifdef CONFIG_MAC80211_MESH static inline u64 mesh_plink_inc_estab_count(struct ieee80211_sub_if_data *sdata) { atomic_inc(&sdata->u.mesh.estab_plinks); return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON; } static inline u64 mesh_plink_dec_estab_count(struct ieee80211_sub_if_data *sdata) { atomic_dec(&sdata->u.mesh.estab_plinks); return mesh_accept_plinks_update(sdata) | BSS_CHANGED_BEACON; } static inline int mesh_plink_free_count(struct ieee80211_sub_if_data *sdata) { return sdata->u.mesh.mshcfg.dot11MeshMaxPeerLinks - atomic_read(&sdata->u.mesh.estab_plinks); } static inline bool mesh_plink_availables(struct ieee80211_sub_if_data *sdata) { return (min_t(long, mesh_plink_free_count(sdata), MESH_MAX_PLINKS - sdata->local->num_sta)) > 0; } static inline void mesh_path_activate(struct mesh_path *mpath) { mpath->flags |= MESH_PATH_ACTIVE | MESH_PATH_RESOLVED; } static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP; } void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_sync_adjust_tsf(struct ieee80211_sub_if_data *sdata); void ieee80211s_stop(void); #else static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) {} static inline void ieee80211s_stop(void) {} #endif #endif /* IEEE80211S_H */ |
| 7 1 2 1 2 3 1 7 2 1 2 2 1 6 1 3 2 1 5 1 1 1 1 1 6 1 1 1 2 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/io_uring.h> #include <uapi/linux/io_uring.h> #include "../fs/internal.h" #include "io_uring.h" #include "fs.h" struct io_rename { struct file *file; int old_dfd; int new_dfd; struct delayed_filename oldpath; struct delayed_filename newpath; int flags; }; struct io_unlink { struct file *file; int dfd; int flags; struct delayed_filename filename; }; struct io_mkdir { struct file *file; int dfd; umode_t mode; struct delayed_filename filename; }; struct io_link { struct file *file; int old_dfd; int new_dfd; struct delayed_filename oldpath; struct delayed_filename newpath; int flags; }; int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_rename *ren = io_kiocb_to_cmd(req, struct io_rename); const char __user *oldf, *newf; int err; if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; ren->old_dfd = READ_ONCE(sqe->fd); oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); ren->new_dfd = READ_ONCE(sqe->len); ren->flags = READ_ONCE(sqe->rename_flags); err = delayed_getname(&ren->oldpath, oldf); if (unlikely(err)) return err; err = delayed_getname(&ren->newpath, newf); if (unlikely(err)) { dismiss_delayed_filename(&ren->oldpath); return err; } req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_renameat(struct io_kiocb *req, unsigned int issue_flags) { struct io_rename *ren = io_kiocb_to_cmd(req, struct io_rename); CLASS(filename_complete_delayed, old)(&ren->oldpath); CLASS(filename_complete_delayed, new)(&ren->newpath); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = filename_renameat2(ren->old_dfd, old, ren->new_dfd, new, ren->flags); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_COMPLETE; } void io_renameat_cleanup(struct io_kiocb *req) { struct io_rename *ren = io_kiocb_to_cmd(req, struct io_rename); dismiss_delayed_filename(&ren->oldpath); dismiss_delayed_filename(&ren->newpath); } int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_unlink *un = io_kiocb_to_cmd(req, struct io_unlink); const char __user *fname; int err; if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; un->dfd = READ_ONCE(sqe->fd); un->flags = READ_ONCE(sqe->unlink_flags); if (un->flags & ~AT_REMOVEDIR) return -EINVAL; fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); err = delayed_getname(&un->filename, fname); if (unlikely(err)) return err; req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_unlink *un = io_kiocb_to_cmd(req, struct io_unlink); CLASS(filename_complete_delayed, name)(&un->filename); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); if (un->flags & AT_REMOVEDIR) ret = filename_rmdir(un->dfd, name); else ret = filename_unlinkat(un->dfd, name); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_COMPLETE; } void io_unlinkat_cleanup(struct io_kiocb *req) { struct io_unlink *ul = io_kiocb_to_cmd(req, struct io_unlink); dismiss_delayed_filename(&ul->filename); } int io_mkdirat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_mkdir *mkd = io_kiocb_to_cmd(req, struct io_mkdir); const char __user *fname; int err; if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; mkd->dfd = READ_ONCE(sqe->fd); mkd->mode = READ_ONCE(sqe->len); fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); err = delayed_getname(&mkd->filename, fname); if (unlikely(err)) return err; req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags) { struct io_mkdir *mkd = io_kiocb_to_cmd(req, struct io_mkdir); CLASS(filename_complete_delayed, name)(&mkd->filename); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = filename_mkdirat(mkd->dfd, name, mkd->mode); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_COMPLETE; } void io_mkdirat_cleanup(struct io_kiocb *req) { struct io_mkdir *md = io_kiocb_to_cmd(req, struct io_mkdir); dismiss_delayed_filename(&md->filename); } int io_symlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_link *sl = io_kiocb_to_cmd(req, struct io_link); const char __user *oldpath, *newpath; int err; if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; sl->new_dfd = READ_ONCE(sqe->fd); oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr)); newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2)); err = delayed_getname(&sl->oldpath, oldpath); if (unlikely(err)) return err; err = delayed_getname(&sl->newpath, newpath); if (unlikely(err)) { dismiss_delayed_filename(&sl->oldpath); return err; } req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_link *sl = io_kiocb_to_cmd(req, struct io_link); CLASS(filename_complete_delayed, old)(&sl->oldpath); CLASS(filename_complete_delayed, new)(&sl->newpath); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = filename_symlinkat(old, sl->new_dfd, new); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_COMPLETE; } int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link); const char __user *oldf, *newf; int err; if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; lnk->old_dfd = READ_ONCE(sqe->fd); lnk->new_dfd = READ_ONCE(sqe->len); oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); lnk->flags = READ_ONCE(sqe->hardlink_flags); err = delayed_getname_uflags(&lnk->oldpath, oldf, lnk->flags); if (unlikely(err)) return err; err = delayed_getname(&lnk->newpath, newf); if (unlikely(err)) { dismiss_delayed_filename(&lnk->oldpath); return err; } req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_linkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link); CLASS(filename_complete_delayed, old)(&lnk->oldpath); CLASS(filename_complete_delayed, new)(&lnk->newpath); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = filename_linkat(lnk->old_dfd, old, lnk->new_dfd, new, lnk->flags); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_COMPLETE; } void io_link_cleanup(struct io_kiocb *req) { struct io_link *sl = io_kiocb_to_cmd(req, struct io_link); dismiss_delayed_filename(&sl->oldpath); dismiss_delayed_filename(&sl->newpath); } |
| 15 15 13 2 2 13 3 10 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0 /* * xfrm4_policy.c * * Changes: * Kazunori MIYAZAWA @USAGI * YOSHIFUJI Hideaki @USAGI * Split up af-specific portion * */ #include <linux/err.h> #include <linux/kernel.h> #include <linux/inetdevice.h> #include <net/dst.h> #include <net/xfrm.h> #include <net/flow.h> #include <net/ip.h> #include <net/l3mdev.h> static struct dst_entry *__xfrm4_dst_lookup(struct flowi4 *fl4, const struct xfrm_dst_lookup_params *params) { struct rtable *rt; memset(fl4, 0, sizeof(*fl4)); fl4->daddr = params->daddr->a4; fl4->flowi4_dscp = params->dscp; fl4->flowi4_l3mdev = l3mdev_master_ifindex_by_index(params->net, params->oif); fl4->flowi4_mark = params->mark; if (params->saddr) fl4->saddr = params->saddr->a4; fl4->flowi4_proto = params->ipproto; fl4->uli = params->uli; rt = __ip_route_output_key(params->net, fl4); if (!IS_ERR(rt)) return &rt->dst; return ERR_CAST(rt); } static struct dst_entry *xfrm4_dst_lookup(const struct xfrm_dst_lookup_params *params) { struct flowi4 fl4; return __xfrm4_dst_lookup(&fl4, params); } static int xfrm4_get_saddr(xfrm_address_t *saddr, const struct xfrm_dst_lookup_params *params) { struct dst_entry *dst; struct flowi4 fl4; dst = __xfrm4_dst_lookup(&fl4, params); if (IS_ERR(dst)) return -EHOSTUNREACH; saddr->a4 = fl4.saddr; dst_release(dst); return 0; } static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { struct rtable *rt = dst_rtable(xdst->route); const struct flowi4 *fl4 = &fl->u.ip4; xdst->u.rt.rt_iif = fl4->flowi4_iif; xdst->u.dst.dev = dev; netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt.rt_is_input = rt->rt_is_input; xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL); xdst->u.rt.rt_type = rt->rt_type; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) xdst->u.rt.rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) xdst->u.rt.rt_gw6 = rt->rt_gw6; xdst->u.rt.rt_pmtu = rt->rt_pmtu; xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; rt_add_uncached_list(&xdst->u.rt); return 0; } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->redirect(path, sk, skb); } static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } static struct dst_ops xfrm4_dst_ops_template = { .family = AF_INET, .update_pmtu = xfrm4_update_pmtu, .redirect = xfrm4_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm_dst_ifdown, .local_out = __ip_local_out, .gc_thresh = 32768, }; static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .dst_ops = &xfrm4_dst_ops_template, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, .fill_dst = xfrm4_fill_dst, .blackhole_route = ipv4_blackhole_route, }; #ifdef CONFIG_SYSCTL static struct ctl_table xfrm4_policy_table[] = { { .procname = "xfrm4_gc_thresh", .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static __net_init int xfrm4_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; table = xfrm4_policy_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL); if (!table) goto err_alloc; table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh; } hdr = register_net_sysctl_sz(net, "net/ipv4", table, ARRAY_SIZE(xfrm4_policy_table)); if (!hdr) goto err_reg; net->ipv4.xfrm4_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static __net_exit void xfrm4_net_sysctl_exit(struct net *net) { const struct ctl_table *table; if (!net->ipv4.xfrm4_hdr) return; table = net->ipv4.xfrm4_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.xfrm4_hdr); if (!net_eq(net, &init_net)) kfree(table); } #else /* CONFIG_SYSCTL */ static inline int xfrm4_net_sysctl_init(struct net *net) { return 0; } static inline void xfrm4_net_sysctl_exit(struct net *net) { } #endif static int __net_init xfrm4_net_init(struct net *net) { int ret; memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template, sizeof(xfrm4_dst_ops_template)); ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops); if (ret) return ret; ret = xfrm4_net_sysctl_init(net); if (ret) dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); return ret; } static void __net_exit xfrm4_net_exit(struct net *net) { xfrm4_net_sysctl_exit(net); dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); } static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, }; static void __init xfrm4_policy_init(void) { xfrm_policy_register_afinfo(&xfrm4_policy_afinfo, AF_INET); } void __init xfrm4_init(void) { xfrm4_state_init(); xfrm4_policy_init(); xfrm4_protocol_init(); register_pernet_subsys(&xfrm4_net_ops); } |
| 6 6 7 6 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 ARM Ltd. * Author: Catalin Marinas <catalin.marinas@arm.com> */ #include <linux/gfp.h> #include <linux/cache.h> #include <linux/dma-map-ops.h> #include <xen/xen.h> #include <asm/cacheflush.h> #include <asm/xen/xen-ops.h> void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { unsigned long start = (unsigned long)phys_to_virt(paddr); dcache_clean_poc_nosync(start, start + size); } void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, enum dma_data_direction dir) { unsigned long start = (unsigned long)phys_to_virt(paddr); if (dir == DMA_TO_DEVICE) return; dcache_inval_poc_nosync(start, start + size); } void arch_dma_prep_coherent(struct page *page, size_t size) { unsigned long start = (unsigned long)page_address(page); dcache_clean_poc(start, start + size); } void arch_setup_dma_ops(struct device *dev, bool coherent) { int cls = cache_line_size_of_cpu(); WARN_TAINT(!coherent && cls > ARCH_DMA_MINALIGN, TAINT_CPU_OUT_OF_SPEC, "%s %s: ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)", dev_driver_string(dev), dev_name(dev), ARCH_DMA_MINALIGN, cls); dev->dma_coherent = coherent; xen_setup_dma_ops(dev); } |
| 252 98 158 13 245 328 6 10 553 1142 5 5 178 256 19 78 43 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 | // SPDX-License-Identifier: GPL-2.0+ /* * ext4_jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 * * Copyright 1998--1999 Red Hat corp --- All Rights Reserved * * Ext4-specific journaling extensions. */ #ifndef _EXT4_JBD2_H #define _EXT4_JBD2_H #include <linux/fs.h> #include <linux/jbd2.h> #include "ext4.h" #define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) /* Define the number of blocks we need to account to a transaction to * modify one block of data. * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to * 5 levels of tree, data block (for each of these we need bitmap + group * summaries), root which is stored in the inode, sb */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (ext4_has_feature_extents(sb) ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode * and the superblock, which are already accounted for. */ #define EXT4_XATTR_TRANS_BLOCKS 6U /* Define the minimum size for a transaction which modifies data. This * needs to take into account the fact that we may end up modifying two * quota files too (one for the group, one for the user quota). The * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ EXT4_XATTR_TRANS_BLOCKS - 2 + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* * Define the number of metadata blocks we need to account to modify data. * * This include super block, inode block, quota blocks and xattr blocks */ #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* Define an arbitrary limit for the amount of data we will anticipate * writing to any given transaction. For unbounded transactions such as * write(2) and truncate(2) we can write more than this, but we always * start off at the maximum transaction size and grow the transaction * optimistically as we go. */ #define EXT4_MAX_TRANS_DATA 64U /* We break up a large truncate or write transaction once the handle's * buffer credits gets this low, we need either to extend the * transaction or to start a new one. Reserve enough space here for * inode, bitmap, superblock, group and indirection updates for at least * one block, plus two quota updates. Quota allocations are not * needed. */ #define EXT4_RESERVE_TRANS_BLOCKS 12U /* * Number of credits needed if we need to insert an entry into a * directory. For each new index block, we need 4 blocks (old index * block, new index block, bitmap block, bg summary). For normal * htree directories there are 2 levels; if the largedir feature * enabled it's 3 levels. */ #define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ #define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 #endif #define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) /* * Ext4 handle operation types -- for logging purposes */ #define EXT4_HT_MISC 0 #define EXT4_HT_INODE 1 #define EXT4_HT_WRITE_PAGE 2 #define EXT4_HT_MAP_BLOCKS 3 #define EXT4_HT_DIR 4 #define EXT4_HT_TRUNCATE 5 #define EXT4_HT_QUOTA 6 #define EXT4_HT_RESIZE 7 #define EXT4_HT_MIGRATE 8 #define EXT4_HT_MOVE_EXTENTS 9 #define EXT4_HT_XATTR 10 #define EXT4_HT_EXT_CONVERT 11 #define EXT4_HT_MAX 12 int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); #define ext4_mark_inode_dirty(__h, __i) \ __ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__) int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line); int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc); /* * Wrapper functions with which ext4 calls into JBD. */ int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); #define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ __ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \ (bh), (block_nr)) #define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) /* Note: Do not use this for NULL handles. This is only to determine if * a properly allocated handle is using a journal or not. */ static inline int ext4_handle_valid(handle_t *handle) { if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT) return 0; return 1; } static inline void ext4_handle_sync(handle_t *handle) { if (ext4_handle_valid(handle)) handle->h_sync = 1; } static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) return is_handle_aborted(handle); return 0; } static inline int ext4_free_metadata_revoke_credits(struct super_block *sb, int blocks) { /* Freeing each metadata block can result in freeing one cluster */ return blocks * EXT4_SB(sb)->s_cluster_ratio; } static inline int ext4_trans_default_revoke_credits(struct super_block *sb) { return ext4_free_metadata_revoke_credits(sb, 8); } #define ext4_journal_start_sb(sb, type, nblocks) \ __ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\ ext4_trans_default_revoke_credits(sb)) #define ext4_journal_start(inode, type, nblocks) \ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \ __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \ (revoke_creds)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks, rsv_blocks, revoke_creds); } #define ext4_journal_stop(handle) \ __ext4_journal_stop(__func__, __LINE__, (handle)) #define ext4_journal_start_reserved(handle, type) \ __ext4_journal_start_reserved((handle), __LINE__, (type)) handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type); static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); } static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2_journal_extend(handle, nblocks, revoke); return 0; } static inline int ext4_journal_restart(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS); return 0; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred); /* * Ensure @handle has at least @check_creds credits available. If not, * transaction will be extended or restarted to contain at least @extend_cred * credits. Before restarting transaction @fn is executed to allow for cleanup * before the transaction is restarted. * * The return value is < 0 in case of error, 0 in case the handle has enough * credits or transaction extension succeeded, 1 in case transaction had to be * restarted. */ #define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \ revoke_cred, fn) \ ({ \ __label__ __ensure_end; \ int err = __ext4_journal_ensure_credits((handle), (check_cred), \ (extend_cred), (revoke_cred)); \ \ if (err <= 0) \ goto __ensure_end; \ err = (fn); \ if (err < 0) \ goto __ensure_end; \ err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \ if (err == 0) \ err = 1; \ __ensure_end: \ err; \ }) /* * Ensure given handle has at least requested amount of credits available, * possibly restarting transaction if needed. We also make sure the transaction * has space for at least ext4_trans_default_revoke_credits(sb) revoke records * as freeing one or two blocks is very common pattern and requesting this is * very cheap. */ static inline int ext4_journal_ensure_credits(handle_t *handle, int credits, int revoke_creds) { return ext4_journal_ensure_credits_fn(handle, credits, credits, revoke_creds, 0); } static inline int ext4_journal_blocks_per_folio(struct inode *inode) { if (EXT4_JOURNAL(inode) != NULL) return jbd2_journal_blocks_per_folio(inode); return 0; } static inline int ext4_journal_force_commit(journal_t *journal) { if (journal) return jbd2_journal_force_commit(journal); return 0; } static inline int ext4_jbd2_inode_add_write(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_write(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_wait(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline void ext4_update_inode_fsync_trans(handle_t *handle, struct inode *inode, int datasync) { struct ext4_inode_info *ei = EXT4_I(inode); if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; } } /* super.c */ int ext4_force_commit(struct super_block *sb); /* * Ext4 inode journal modes */ #define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */ #define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ #define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ int ext4_inode_journal_mode(struct inode *inode); static inline int ext4_should_journal_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE; } static inline int ext4_should_order_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE; } static inline int ext4_should_writeback_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) { if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) return 0; if (!ext4_should_journal_data(inode)) return 0; /* * Data blocks in one extent are contiguous, just account for partial * clusters at extent boundaries */ return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1); } /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking * i_rwsem for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of * b_private. */ static inline int ext4_should_dioread_nolock(struct inode *inode) { if (!test_opt(inode->i_sb, DIOREAD_NOLOCK)) return 0; if (!S_ISREG(inode->i_mode)) return 0; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return 0; if (ext4_should_journal_data(inode)) return 0; /* temporary fix to prevent generic/422 test failures */ if (!test_opt(inode->i_sb, DELALLOC)) return 0; return 1; } /* * Pass journal explicitly as it may not be cached in the sbi->s_journal in some * cases */ static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *journal) { int err = 0; /* * At this point only two things can be operating on the journal. * JBD2 thread performing transaction commit and s_sb_upd_work * issuing sb update through the journal. Once we set * EXT4_JOURNAL_DESTROY, new ext4_handle_error() calls will not * queue s_sb_upd_work and ext4_force_commit() makes sure any * ext4_handle_error() calls from the running transaction commit are * finished. Hence no new s_sb_upd_work can be queued after we * flush it here. */ ext4_set_mount_flag(sbi->s_sb, EXT4_MF_JOURNAL_DESTROY); ext4_force_commit(sbi->s_sb); flush_work(&sbi->s_sb_upd_work); err = jbd2_journal_destroy(journal); sbi->s_journal = NULL; return err; } #endif /* _EXT4_JBD2_H */ |
| 3 3 4 3 2 37 37 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 | /* * Copyright (c) 2006,2007 The Regents of the University of Michigan. * All rights reserved. * * Andy Adamson <andros@citi.umich.edu> * Fred Isaman <iisaman@umich.edu> * * permission is granted to use, copy, create derivative works and * redistribute this software and such derivative works for any purpose, * so long as the name of the university of michigan is not used in * any advertising or publicity pertaining to the use or distribution * of this software without specific, written prior authorization. if * the above copyright notice or any other identification of the * university of michigan is included in any copy of any portion of * this software, then the disclaimer below must also be included. * * this software is provided as is, without representation from the * university of michigan as to its fitness for any purpose, and without * warranty by the university of michigan of any kind, either express * or implied, including without limitation the implied warranties of * merchantability and fitness for a particular purpose. the regents * of the university of michigan shall not be liable for any damages, * including special, indirect, incidental, or consequential damages, * with respect to any claim arising out or in connection with the use * of the software, even if it has been or is hereafter advised of the * possibility of such damages. */ #include <linux/module.h> #include <linux/blkdev.h> #include "blocklayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD static void nfs4_encode_simple(__be32 *p, struct pnfs_block_volume *b) { int i; *p++ = cpu_to_be32(1); *p++ = cpu_to_be32(b->type); *p++ = cpu_to_be32(b->simple.nr_sigs); for (i = 0; i < b->simple.nr_sigs; i++) { p = xdr_encode_hyper(p, b->simple.sigs[i].offset); p = xdr_encode_opaque(p, b->simple.sigs[i].sig, b->simple.sigs[i].sig_len); } } dev_t bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, gfp_t gfp_mask) { struct net *net = server->nfs_client->cl_net; struct nfs_net *nn = net_generic(net, nfs_net_id); struct bl_dev_msg *reply = &nn->bl_mount_reply; struct bl_pipe_msg bl_pipe_msg; struct rpc_pipe_msg *msg = &bl_pipe_msg.msg; struct bl_msg_hdr *bl_msg; DECLARE_WAITQUEUE(wq, current); dev_t dev = 0; int rc; dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); mutex_lock(&nn->bl_mutex); bl_pipe_msg.bl_wq = &nn->bl_wq; b->simple.len += 4; /* single volume */ if (b->simple.len > PAGE_SIZE) goto out_unlock; memset(msg, 0, sizeof(*msg)); msg->len = sizeof(*bl_msg) + b->simple.len; msg->data = kzalloc(msg->len, gfp_mask); if (!msg->data) goto out_unlock; bl_msg = msg->data; bl_msg->type = BL_DEVICE_MOUNT; bl_msg->totallen = b->simple.len; nfs4_encode_simple(msg->data + sizeof(*bl_msg), b); dprintk("%s CALLING USERSPACE DAEMON\n", __func__); add_wait_queue(&nn->bl_wq, &wq); rc = rpc_queue_upcall(nn->bl_device_pipe, msg); if (rc < 0) { remove_wait_queue(&nn->bl_wq, &wq); goto out_free_data; } set_current_state(TASK_UNINTERRUPTIBLE); schedule(); remove_wait_queue(&nn->bl_wq, &wq); if (reply->status != BL_DEVICE_REQUEST_PROC) { printk(KERN_WARNING "%s failed to decode device: %d\n", __func__, reply->status); goto out_free_data; } dev = MKDEV(reply->major, reply->minor); out_free_data: kfree(msg->data); out_unlock: mutex_unlock(&nn->bl_mutex); return dev; } static ssize_t bl_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { struct nfs_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info, nfs_net_id); if (mlen != sizeof (struct bl_dev_msg)) return -EINVAL; if (copy_from_user(&nn->bl_mount_reply, src, mlen) != 0) return -EFAULT; wake_up(&nn->bl_wq); return mlen; } static void bl_pipe_destroy_msg(struct rpc_pipe_msg *msg) { struct bl_pipe_msg *bl_pipe_msg = container_of(msg, struct bl_pipe_msg, msg); if (msg->errno >= 0) return; wake_up(bl_pipe_msg->bl_wq); } static const struct rpc_pipe_ops bl_upcall_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = bl_pipe_downcall, .destroy_msg = bl_pipe_destroy_msg, }; static int nfs4blocklayout_register_sb(struct super_block *sb, struct rpc_pipe *pipe) { struct dentry *dir; int err; dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME); if (dir == NULL) return -ENOENT; err = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe); dput(dir); return err; } static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct super_block *sb = ptr; struct net *net = sb->s_fs_info; struct nfs_net *nn = net_generic(net, nfs_net_id); int ret = 0; if (!try_module_get(THIS_MODULE)) return 0; if (nn->bl_device_pipe == NULL) { module_put(THIS_MODULE); return 0; } switch (event) { case RPC_PIPEFS_MOUNT: ret = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe); break; case RPC_PIPEFS_UMOUNT: rpc_unlink(nn->bl_device_pipe); break; default: ret = -ENOTSUPP; break; } module_put(THIS_MODULE); return ret; } static struct notifier_block nfs4blocklayout_block = { .notifier_call = rpc_pipefs_event, }; static int nfs4blocklayout_register_net(struct net *net, struct rpc_pipe *pipe) { struct super_block *pipefs_sb; int ret; pipefs_sb = rpc_get_sb_net(net); if (!pipefs_sb) return 0; ret = nfs4blocklayout_register_sb(pipefs_sb, pipe); rpc_put_sb_net(net); return ret; } static void nfs4blocklayout_unregister_net(struct net *net, struct rpc_pipe *pipe) { struct super_block *pipefs_sb; pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { rpc_unlink(pipe); rpc_put_sb_net(net); } } static int nfs4blocklayout_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); int err; mutex_init(&nn->bl_mutex); init_waitqueue_head(&nn->bl_wq); nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0); if (IS_ERR(nn->bl_device_pipe)) return PTR_ERR(nn->bl_device_pipe); err = nfs4blocklayout_register_net(net, nn->bl_device_pipe); if (unlikely(err)) rpc_destroy_pipe_data(nn->bl_device_pipe); return err; } static void nfs4blocklayout_net_exit(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); nfs4blocklayout_unregister_net(net, nn->bl_device_pipe); rpc_destroy_pipe_data(nn->bl_device_pipe); nn->bl_device_pipe = NULL; } static struct pernet_operations nfs4blocklayout_net_ops = { .init = nfs4blocklayout_net_init, .exit = nfs4blocklayout_net_exit, }; int __init bl_init_pipefs(void) { int ret; ret = rpc_pipefs_notifier_register(&nfs4blocklayout_block); if (ret) goto out; ret = register_pernet_subsys(&nfs4blocklayout_net_ops); if (ret) goto out_unregister_notifier; return 0; out_unregister_notifier: rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); out: return ret; } void bl_cleanup_pipefs(void) { rpc_pipefs_notifier_unregister(&nfs4blocklayout_block); unregister_pernet_subsys(&nfs4blocklayout_net_ops); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Trace point definitions for core RDMA functions. * * Author: Chuck Lever <chuck.lever@oracle.com> * * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM rdma_core #if !defined(_TRACE_RDMA_CORE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RDMA_CORE_H #include <linux/tracepoint.h> #include <rdma/ib_verbs.h> /* * enum ib_poll_context, from include/rdma/ib_verbs.h */ #define IB_POLL_CTX_LIST \ ib_poll_ctx(DIRECT) \ ib_poll_ctx(SOFTIRQ) \ ib_poll_ctx(WORKQUEUE) \ ib_poll_ctx_end(UNBOUND_WORKQUEUE) #undef ib_poll_ctx #undef ib_poll_ctx_end #define ib_poll_ctx(x) TRACE_DEFINE_ENUM(IB_POLL_##x); #define ib_poll_ctx_end(x) TRACE_DEFINE_ENUM(IB_POLL_##x); IB_POLL_CTX_LIST #undef ib_poll_ctx #undef ib_poll_ctx_end #define ib_poll_ctx(x) { IB_POLL_##x, #x }, #define ib_poll_ctx_end(x) { IB_POLL_##x, #x } #define rdma_show_ib_poll_ctx(x) \ __print_symbolic(x, IB_POLL_CTX_LIST) /** ** Completion Queue events **/ TRACE_EVENT(cq_schedule, TP_PROTO( struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) ), TP_fast_assign( cq->timestamp = ktime_get(); cq->interrupt = true; __entry->cq_id = cq->res.id; ), TP_printk("cq.id=%u", __entry->cq_id) ); TRACE_EVENT(cq_reschedule, TP_PROTO( struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) ), TP_fast_assign( cq->timestamp = ktime_get(); cq->interrupt = false; __entry->cq_id = cq->res.id; ), TP_printk("cq.id=%u", __entry->cq_id) ); TRACE_EVENT(cq_process, TP_PROTO( const struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) __field(bool, interrupt) __field(s64, latency) ), TP_fast_assign( ktime_t latency = ktime_sub(ktime_get(), cq->timestamp); __entry->cq_id = cq->res.id; __entry->latency = ktime_to_us(latency); __entry->interrupt = cq->interrupt; ), TP_printk("cq.id=%u wake-up took %lld [us] from %s", __entry->cq_id, __entry->latency, __entry->interrupt ? "interrupt" : "reschedule" ) ); TRACE_EVENT(cq_poll, TP_PROTO( const struct ib_cq *cq, int requested, int rc ), TP_ARGS(cq, requested, rc), TP_STRUCT__entry( __field(u32, cq_id) __field(int, requested) __field(int, rc) ), TP_fast_assign( __entry->cq_id = cq->res.id; __entry->requested = requested; __entry->rc = rc; ), TP_printk("cq.id=%u requested %d, returned %d", __entry->cq_id, __entry->requested, __entry->rc ) ); TRACE_EVENT(cq_drain_complete, TP_PROTO( const struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) ), TP_fast_assign( __entry->cq_id = cq->res.id; ), TP_printk("cq.id=%u", __entry->cq_id ) ); TRACE_EVENT(cq_modify, TP_PROTO( const struct ib_cq *cq, u16 comps, u16 usec ), TP_ARGS(cq, comps, usec), TP_STRUCT__entry( __field(u32, cq_id) __field(unsigned int, comps) __field(unsigned int, usec) ), TP_fast_assign( __entry->cq_id = cq->res.id; __entry->comps = comps; __entry->usec = usec; ), TP_printk("cq.id=%u comps=%u usec=%u", __entry->cq_id, __entry->comps, __entry->usec ) ); TRACE_EVENT(cq_alloc, TP_PROTO( const struct ib_cq *cq, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx ), TP_ARGS(cq, nr_cqe, comp_vector, poll_ctx), TP_STRUCT__entry( __field(u32, cq_id) __field(int, nr_cqe) __field(int, comp_vector) __field(unsigned long, poll_ctx) ), TP_fast_assign( __entry->cq_id = cq->res.id; __entry->nr_cqe = nr_cqe; __entry->comp_vector = comp_vector; __entry->poll_ctx = poll_ctx; ), TP_printk("cq.id=%u nr_cqe=%d comp_vector=%d poll_ctx=%s", __entry->cq_id, __entry->nr_cqe, __entry->comp_vector, rdma_show_ib_poll_ctx(__entry->poll_ctx) ) ); TRACE_EVENT(cq_alloc_error, TP_PROTO( int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx, int rc ), TP_ARGS(nr_cqe, comp_vector, poll_ctx, rc), TP_STRUCT__entry( __field(int, rc) __field(int, nr_cqe) __field(int, comp_vector) __field(unsigned long, poll_ctx) ), TP_fast_assign( __entry->rc = rc; __entry->nr_cqe = nr_cqe; __entry->comp_vector = comp_vector; __entry->poll_ctx = poll_ctx; ), TP_printk("nr_cqe=%d comp_vector=%d poll_ctx=%s rc=%d", __entry->nr_cqe, __entry->comp_vector, rdma_show_ib_poll_ctx(__entry->poll_ctx), __entry->rc ) ); TRACE_EVENT(cq_free, TP_PROTO( const struct ib_cq *cq ), TP_ARGS(cq), TP_STRUCT__entry( __field(u32, cq_id) ), TP_fast_assign( __entry->cq_id = cq->res.id; ), TP_printk("cq.id=%u", __entry->cq_id) ); /** ** Memory Region events **/ /* * enum ib_mr_type, from include/rdma/ib_verbs.h */ #define IB_MR_TYPE_LIST \ ib_mr_type_item(MEM_REG) \ ib_mr_type_item(SG_GAPS) \ ib_mr_type_item(DM) \ ib_mr_type_item(USER) \ ib_mr_type_item(DMA) \ ib_mr_type_end(INTEGRITY) #undef ib_mr_type_item #undef ib_mr_type_end #define ib_mr_type_item(x) TRACE_DEFINE_ENUM(IB_MR_TYPE_##x); #define ib_mr_type_end(x) TRACE_DEFINE_ENUM(IB_MR_TYPE_##x); IB_MR_TYPE_LIST #undef ib_mr_type_item #undef ib_mr_type_end #define ib_mr_type_item(x) { IB_MR_TYPE_##x, #x }, #define ib_mr_type_end(x) { IB_MR_TYPE_##x, #x } #define rdma_show_ib_mr_type(x) \ __print_symbolic(x, IB_MR_TYPE_LIST) TRACE_EVENT(mr_alloc, TP_PROTO( const struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg, const struct ib_mr *mr ), TP_ARGS(pd, mr_type, max_num_sg, mr), TP_STRUCT__entry( __field(u32, pd_id) __field(u32, mr_id) __field(u32, max_num_sg) __field(int, rc) __field(unsigned long, mr_type) ), TP_fast_assign( __entry->pd_id = pd->res.id; if (IS_ERR(mr)) { __entry->mr_id = 0; __entry->rc = PTR_ERR(mr); } else { __entry->mr_id = mr->res.id; __entry->rc = 0; } __entry->max_num_sg = max_num_sg; __entry->mr_type = mr_type; ), TP_printk("pd.id=%u mr.id=%u type=%s max_num_sg=%u rc=%d", __entry->pd_id, __entry->mr_id, rdma_show_ib_mr_type(__entry->mr_type), __entry->max_num_sg, __entry->rc) ); TRACE_EVENT(mr_integ_alloc, TP_PROTO( const struct ib_pd *pd, u32 max_num_data_sg, u32 max_num_meta_sg, const struct ib_mr *mr ), TP_ARGS(pd, max_num_data_sg, max_num_meta_sg, mr), TP_STRUCT__entry( __field(u32, pd_id) __field(u32, mr_id) __field(u32, max_num_data_sg) __field(u32, max_num_meta_sg) __field(int, rc) ), TP_fast_assign( __entry->pd_id = pd->res.id; if (IS_ERR(mr)) { __entry->mr_id = 0; __entry->rc = PTR_ERR(mr); } else { __entry->mr_id = mr->res.id; __entry->rc = 0; } __entry->max_num_data_sg = max_num_data_sg; __entry->max_num_meta_sg = max_num_meta_sg; ), TP_printk("pd.id=%u mr.id=%u max_num_data_sg=%u max_num_meta_sg=%u rc=%d", __entry->pd_id, __entry->mr_id, __entry->max_num_data_sg, __entry->max_num_meta_sg, __entry->rc) ); TRACE_EVENT(mr_dereg, TP_PROTO( const struct ib_mr *mr ), TP_ARGS(mr), TP_STRUCT__entry( __field(u32, id) ), TP_fast_assign( __entry->id = mr->res.id; ), TP_printk("mr.id=%u", __entry->id) ); #endif /* _TRACE_RDMA_CORE_H */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Released under the GPLv2 only. */ #include <linux/pm.h> #include <linux/acpi.h> struct usb_hub_descriptor; struct usb_dev_state; /* Functions local to drivers/usb/core/ */ extern int usb_create_sysfs_dev_files(struct usb_device *dev); extern void usb_remove_sysfs_dev_files(struct usb_device *dev); extern void usb_create_sysfs_intf_files(struct usb_interface *intf); extern void usb_remove_sysfs_intf_files(struct usb_interface *intf); extern int usb_update_wireless_status_attr(struct usb_interface *intf); extern int usb_create_ep_devs(struct device *parent, struct usb_host_endpoint *endpoint, struct usb_device *udev); extern void usb_remove_ep_devs(struct usb_host_endpoint *endpoint); extern void usb_enable_endpoint(struct usb_device *dev, struct usb_host_endpoint *ep, bool reset_toggle); extern void usb_enable_interface(struct usb_device *dev, struct usb_interface *intf, bool reset_toggles); extern void usb_disable_endpoint(struct usb_device *dev, unsigned int epaddr, bool reset_hardware); extern void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf, bool reset_hardware); extern void usb_release_interface_cache(struct kref *ref); extern void usb_disable_device(struct usb_device *dev, int skip_ep0); extern int usb_deauthorize_device(struct usb_device *); extern int usb_authorize_device(struct usb_device *); extern void usb_deauthorize_interface(struct usb_interface *); extern void usb_authorize_interface(struct usb_interface *); extern void usb_detect_quirks(struct usb_device *udev); extern void usb_detect_interface_quirks(struct usb_device *udev); extern void usb_release_quirk_list(void); extern bool usb_endpoint_is_ignored(struct usb_device *udev, struct usb_host_interface *intf, struct usb_endpoint_descriptor *epd); extern int usb_remove_device(struct usb_device *udev); extern struct usb_device_descriptor *usb_get_device_descriptor( struct usb_device *udev); extern int usb_set_isoch_delay(struct usb_device *dev); extern int usb_get_bos_descriptor(struct usb_device *dev); extern void usb_release_bos_descriptor(struct usb_device *dev); extern int usb_set_configuration(struct usb_device *dev, int configuration); extern int usb_choose_configuration(struct usb_device *udev); extern int usb_generic_driver_probe(struct usb_device *udev); extern void usb_generic_driver_disconnect(struct usb_device *udev); extern int usb_generic_driver_suspend(struct usb_device *udev, pm_message_t msg); extern int usb_generic_driver_resume(struct usb_device *udev, pm_message_t msg); static inline unsigned usb_get_max_power(struct usb_device *udev, struct usb_host_config *c) { /* SuperSpeed power is in 8 mA units; others are in 2 mA units */ unsigned mul = (udev->speed >= USB_SPEED_SUPER ? 8 : 2); return c->desc.bMaxPower * mul; } extern void usb_kick_hub_wq(struct usb_device *dev); extern int usb_match_one_id_intf(struct usb_device *dev, struct usb_host_interface *intf, const struct usb_device_id *id); extern int usb_match_device(struct usb_device *dev, const struct usb_device_id *id); extern const struct usb_device_id *usb_device_match_id(struct usb_device *udev, const struct usb_device_id *id); extern bool usb_driver_applicable(struct usb_device *udev, const struct usb_device_driver *udrv); extern void usb_forced_unbind_intf(struct usb_interface *intf); extern void usb_unbind_and_rebind_marked_interfaces(struct usb_device *udev); extern void usb_hub_release_all_ports(struct usb_device *hdev, struct usb_dev_state *owner); extern bool usb_device_is_owned(struct usb_device *udev); extern int usb_hub_init(void); extern void usb_hub_cleanup(void); extern int usb_major_init(void); extern void usb_major_cleanup(void); extern int usb_device_supports_lpm(struct usb_device *udev); extern int usb_port_disable(struct usb_device *udev); #ifdef CONFIG_PM extern int usb_suspend(struct device *dev, pm_message_t msg); extern int usb_resume(struct device *dev, pm_message_t msg); extern int usb_resume_complete(struct device *dev); extern int usb_port_suspend(struct usb_device *dev, pm_message_t msg); extern int usb_port_resume(struct usb_device *dev, pm_message_t msg); extern void usb_autosuspend_device(struct usb_device *udev); extern int usb_autoresume_device(struct usb_device *udev); extern int usb_remote_wakeup(struct usb_device *dev); extern int usb_runtime_suspend(struct device *dev); extern int usb_runtime_resume(struct device *dev); extern int usb_runtime_idle(struct device *dev); extern int usb_enable_usb2_hardware_lpm(struct usb_device *udev); extern int usb_disable_usb2_hardware_lpm(struct usb_device *udev); extern void usbfs_notify_suspend(struct usb_device *udev); extern void usbfs_notify_resume(struct usb_device *udev); #else static inline int usb_port_suspend(struct usb_device *udev, pm_message_t msg) { return 0; } static inline int usb_port_resume(struct usb_device *udev, pm_message_t msg) { return 0; } #define usb_autosuspend_device(udev) do {} while (0) static inline int usb_autoresume_device(struct usb_device *udev) { return 0; } static inline int usb_enable_usb2_hardware_lpm(struct usb_device *udev) { return 0; } static inline int usb_disable_usb2_hardware_lpm(struct usb_device *udev) { return 0; } #endif extern const struct class usbmisc_class; extern const struct bus_type usb_bus_type; extern struct mutex usb_port_peer_mutex; extern const struct device_type usb_device_type; extern const struct device_type usb_if_device_type; extern const struct device_type usb_ep_device_type; extern const struct device_type usb_port_device_type; extern struct usb_device_driver usb_generic_driver; static inline int is_usb_device(const struct device *dev) { return dev->type == &usb_device_type; } static inline int is_usb_interface(const struct device *dev) { return dev->type == &usb_if_device_type; } static inline int is_usb_endpoint(const struct device *dev) { return dev->type == &usb_ep_device_type; } static inline int is_usb_port(const struct device *dev) { return dev->type == &usb_port_device_type; } static inline int is_root_hub(struct usb_device *udev) { return (udev->parent == NULL); } extern bool is_usb_device_driver(const struct device_driver *drv); /* for labeling diagnostics */ extern const char *usbcore_name; /* sysfs stuff */ extern const struct attribute_group *usb_device_groups[]; extern const struct attribute_group *usb_interface_groups[]; /* usbfs stuff */ extern struct usb_driver usbfs_driver; extern const struct file_operations usbfs_devices_fops; extern const struct file_operations usbdev_file_operations; extern int usb_devio_init(void); extern void usb_devio_cleanup(void); /* * Firmware specific cookie identifying a port's location. '0' == no location * data available */ typedef u32 usb_port_location_t; /* internal notify stuff */ extern void usb_notify_add_device(struct usb_device *udev); extern void usb_notify_remove_device(struct usb_device *udev); extern void usb_notify_add_bus(struct usb_bus *ubus); extern void usb_notify_remove_bus(struct usb_bus *ubus); extern void usb_hub_adjust_deviceremovable(struct usb_device *hdev, struct usb_hub_descriptor *desc); #ifdef CONFIG_ACPI extern int usb_acpi_register(void); extern void usb_acpi_unregister(void); extern acpi_handle usb_get_hub_port_acpi_handle(struct usb_device *hdev, int port1); #else static inline int usb_acpi_register(void) { return 0; }; static inline void usb_acpi_unregister(void) { }; #endif |
| 7 7 7 7 7 7 7 7 7 7 7 7 5 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 | // SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> #include <linux/array_size.h> #include <linux/bitmap.h> #include <linux/cleanup.h> #include <linux/compat.h> #include <linux/debugfs.h> #include <linux/device.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/fwnode.h> #include <linux/idr.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irqdesc.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/module.h> #include <linux/nospec.h> #include <linux/of.h> #include <linux/pinctrl/consumer.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/srcu.h> #include <linux/string.h> #include <linux/string_choices.h> #include <linux/gpio.h> #include <linux/gpio/driver.h> #include <linux/gpio/machine.h> #include <uapi/linux/gpio.h> #include "gpiolib-acpi.h" #include "gpiolib-cdev.h" #include "gpiolib-of.h" #include "gpiolib-shared.h" #include "gpiolib-swnode.h" #include "gpiolib-sysfs.h" #include "gpiolib.h" #define CREATE_TRACE_POINTS #include <trace/events/gpio.h> /* Implementation infrastructure for GPIO interfaces. * * The GPIO programming interface allows for inlining speed-critical * get/set operations for common cases, so that access to SOC-integrated * GPIOs can sometimes cost only an instruction or two per bit. */ /* Device and char device-related information */ static DEFINE_IDA(gpio_ida); static dev_t gpio_devt; #define GPIO_DEV_MAX 256 /* 256 GPIO chip devices supported */ static int gpio_bus_match(struct device *dev, const struct device_driver *drv) { struct fwnode_handle *fwnode = dev_fwnode(dev); /* * Only match if the fwnode doesn't already have a proper struct device * created for it. */ if (fwnode && fwnode->dev != dev) return 0; return 1; } static const struct bus_type gpio_bus_type = { .name = "gpio", .match = gpio_bus_match, }; /* * At the end we want all GPIOs to be dynamically allocated from 0. * However, some legacy drivers still perform fixed allocation. * Until they are all fixed, leave 0-512 space for them. */ #define GPIO_DYNAMIC_BASE 512 /* * Define the maximum of the possible GPIO in the global numberspace. * While the GPIO base and numbers are positive, we limit it with signed * maximum as a lot of code is using negative values for special cases. */ #define GPIO_DYNAMIC_MAX INT_MAX /* * Number of GPIOs to use for the fast path in set array */ #define FASTPATH_NGPIO CONFIG_GPIOLIB_FASTPATH_LIMIT static DEFINE_MUTEX(gpio_lookup_lock); static LIST_HEAD(gpio_lookup_list); static LIST_HEAD(gpio_devices); /* Protects the GPIO device list against concurrent modifications. */ static DEFINE_MUTEX(gpio_devices_lock); /* Ensures coherence during read-only accesses to the list of GPIO devices. */ DEFINE_STATIC_SRCU(gpio_devices_srcu); const char *const gpio_suffixes[] = { "gpios", "gpio", NULL }; static void gpiochip_free_hogs(struct gpio_chip *gc); static int gpiochip_add_irqchip(struct gpio_chip *gc, struct lock_class_key *lock_key, struct lock_class_key *request_key); static void gpiochip_irqchip_remove(struct gpio_chip *gc); static int gpiochip_irqchip_init_hw(struct gpio_chip *gc); static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gc); static void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gc); static bool gpiolib_initialized; const char *gpiod_get_label(struct gpio_desc *desc) { struct gpio_desc_label *label; unsigned long flags; flags = READ_ONCE(desc->flags); label = srcu_dereference_check(desc->label, &desc->gdev->desc_srcu, srcu_read_lock_held(&desc->gdev->desc_srcu)); if (test_bit(GPIOD_FLAG_USED_AS_IRQ, &flags)) return label ? label->str : "interrupt"; if (!test_bit(GPIOD_FLAG_REQUESTED, &flags)) return NULL; return label ? label->str : NULL; } static void desc_free_label(struct rcu_head *rh) { kfree(container_of(rh, struct gpio_desc_label, rh)); } static int desc_set_label(struct gpio_desc *desc, const char *label) { struct gpio_desc_label *new = NULL, *old; if (label) { new = kzalloc_flex(*new, str, strlen(label) + 1); if (!new) return -ENOMEM; strcpy(new->str, label); } old = rcu_replace_pointer(desc->label, new, 1); if (old) call_srcu(&desc->gdev->desc_srcu, &old->rh, desc_free_label); return 0; } /** * gpio_to_desc - Convert a GPIO number to its descriptor * @gpio: global GPIO number * * Returns: * The GPIO descriptor associated with the given GPIO, or %NULL if no GPIO * with the given number exists in the system. */ struct gpio_desc *gpio_to_desc(unsigned gpio) { struct gpio_device *gdev; scoped_guard(srcu, &gpio_devices_srcu) { list_for_each_entry_srcu(gdev, &gpio_devices, list, srcu_read_lock_held(&gpio_devices_srcu)) { if (gdev->base <= gpio && gdev->base + gdev->ngpio > gpio) return &gdev->descs[gpio - gdev->base]; } } return NULL; } EXPORT_SYMBOL_GPL(gpio_to_desc); /* This function is deprecated and will be removed soon, don't use. */ struct gpio_desc *gpiochip_get_desc(struct gpio_chip *gc, unsigned int hwnum) { return gpio_device_get_desc(gc->gpiodev, hwnum); } /** * gpio_device_get_desc() - get the GPIO descriptor corresponding to the given * hardware number for this GPIO device * @gdev: GPIO device to get the descriptor from * @hwnum: hardware number of the GPIO for this chip * * Returns: * A pointer to the GPIO descriptor or %EINVAL if no GPIO exists in the given * chip for the specified hardware number or %ENODEV if the underlying chip * already vanished. * * The reference count of struct gpio_device is *NOT* increased like when the * GPIO is being requested for exclusive usage. It's up to the caller to make * sure the GPIO device will stay alive together with the descriptor returned * by this function. */ struct gpio_desc * gpio_device_get_desc(struct gpio_device *gdev, unsigned int hwnum) { if (hwnum >= gdev->ngpio) return ERR_PTR(-EINVAL); return &gdev->descs[array_index_nospec(hwnum, gdev->ngpio)]; } EXPORT_SYMBOL_GPL(gpio_device_get_desc); /** * desc_to_gpio - convert a GPIO descriptor to the integer namespace * @desc: GPIO descriptor * * This should disappear in the future but is needed since we still * use GPIO numbers for error messages and sysfs nodes. * * Returns: * The global GPIO number for the GPIO specified by its descriptor. */ int desc_to_gpio(const struct gpio_desc *desc) { return desc->gdev->base + (desc - &desc->gdev->descs[0]); } EXPORT_SYMBOL_GPL(desc_to_gpio); /** * gpiod_hwgpio - Return the GPIO number of the passed descriptor relative to * its chip. * @desc: GPIO descriptor * * Returns: * Hardware offset of the GPIO represented by the descriptor. */ int gpiod_hwgpio(const struct gpio_desc *desc) { return desc - &desc->gdev->descs[0]; } EXPORT_SYMBOL_GPL(gpiod_hwgpio); /** * gpiod_to_chip - Return the GPIO chip to which a GPIO descriptor belongs * @desc: descriptor to return the chip of * * *DEPRECATED* * This function is unsafe and should not be used. Using the chip address * without taking the SRCU read lock may result in dereferencing a dangling * pointer. * * Returns: * Address of the GPIO chip backing this device. */ struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc) { if (!desc) return NULL; return gpio_device_get_chip(desc->gdev); } EXPORT_SYMBOL_GPL(gpiod_to_chip); /** * gpiod_to_gpio_device() - Return the GPIO device to which this descriptor * belongs. * @desc: Descriptor for which to return the GPIO device. * * This *DOES NOT* increase the reference count of the GPIO device as it's * expected that the descriptor is requested and the users already holds a * reference to the device. * * Returns: * Address of the GPIO device owning this descriptor. */ struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc) { if (!desc) return NULL; return desc->gdev; } EXPORT_SYMBOL_GPL(gpiod_to_gpio_device); /** * gpio_device_get_base() - Get the base GPIO number allocated by this device * @gdev: GPIO device * * Returns: * First GPIO number in the global GPIO numberspace for this device. */ int gpio_device_get_base(struct gpio_device *gdev) { return gdev->base; } EXPORT_SYMBOL_GPL(gpio_device_get_base); /** * gpio_device_get_label() - Get the label of this GPIO device * @gdev: GPIO device * * Returns: * Pointer to the string containing the GPIO device label. The string's * lifetime is tied to that of the underlying GPIO device. */ const char *gpio_device_get_label(struct gpio_device *gdev) { return gdev->label; } EXPORT_SYMBOL(gpio_device_get_label); /** * gpio_device_get_chip() - Get the gpio_chip implementation of this GPIO device * @gdev: GPIO device * * Returns: * Address of the GPIO chip backing this device. * * *DEPRECATED* * Until we can get rid of all non-driver users of struct gpio_chip, we must * provide a way of retrieving the pointer to it from struct gpio_device. This * is *NOT* safe as the GPIO API is considered to be hot-unpluggable and the * chip can dissapear at any moment (unlike reference-counted struct * gpio_device). * * Use at your own risk. */ struct gpio_chip *gpio_device_get_chip(struct gpio_device *gdev) { return rcu_dereference_check(gdev->chip, 1); } EXPORT_SYMBOL_GPL(gpio_device_get_chip); /** * gpiochip_find_base_unlocked() - Find a global GPIO number base * @ngpio: Number of consecutive GPIOs to number * * Finds and allocates a consecutive range of unsigned integers representing * the GPIOs on the system. Using this numberspace outside of gpiolibs * internals is STRONGLY DISCOURAGED, drivers and consumers should NOT concern * themselves with this numberspace. */ static int gpiochip_find_base_unlocked(u16 ngpio) { unsigned int base = GPIO_DYNAMIC_BASE; struct gpio_device *gdev; list_for_each_entry_srcu(gdev, &gpio_devices, list, lockdep_is_held(&gpio_devices_lock)) { /* found a free space? */ if (gdev->base >= base + ngpio) break; /* nope, check the space right after the chip */ base = gdev->base + gdev->ngpio; if (base < GPIO_DYNAMIC_BASE) base = GPIO_DYNAMIC_BASE; if (base > GPIO_DYNAMIC_MAX - ngpio) break; } if (base <= GPIO_DYNAMIC_MAX - ngpio) { pr_debug("%s: found new base at %d\n", __func__, base); return base; } else { pr_err("%s: cannot find free range\n", __func__); return -ENOSPC; } } /* * This descriptor validation needs to be inserted verbatim into each * function taking a descriptor, so we need to use a preprocessor * macro to avoid endless duplication. If the desc is NULL it is an * optional GPIO and calls should just bail out. */ static int validate_desc(const struct gpio_desc *desc, const char *func) { if (!desc) return 0; if (IS_ERR(desc)) { pr_warn("%s: invalid GPIO (errorpointer: %pe)\n", func, desc); return PTR_ERR(desc); } return 1; } #define VALIDATE_DESC(desc) do { \ int __valid = validate_desc(desc, __func__); \ if (__valid <= 0) \ return __valid; \ } while (0) #define VALIDATE_DESC_VOID(desc) do { \ int __valid = validate_desc(desc, __func__); \ if (__valid <= 0) \ return; \ } while (0) /** * gpiod_is_equal() - Check if two GPIO descriptors refer to the same pin. * @desc: Descriptor to compare. * @other: The second descriptor to compare against. * * Returns: * True if the descriptors refer to the same physical pin. False otherwise. */ bool gpiod_is_equal(const struct gpio_desc *desc, const struct gpio_desc *other) { return validate_desc(desc, __func__) > 0 && !IS_ERR_OR_NULL(other) && desc == other; } EXPORT_SYMBOL_GPL(gpiod_is_equal); static int gpiochip_get_direction(struct gpio_chip *gc, unsigned int offset) { int ret; lockdep_assert_held(&gc->gpiodev->srcu); if (WARN_ON(!gc->get_direction)) return -EOPNOTSUPP; ret = gc->get_direction(gc, offset); if (ret < 0) return ret; if (ret != GPIO_LINE_DIRECTION_OUT && ret != GPIO_LINE_DIRECTION_IN) ret = -EBADE; return ret; } /** * gpiod_get_direction - return the current direction of a GPIO * @desc: GPIO to get the direction of * * Returns: * 0 for output, 1 for input, or an error code in case of error. * * This function may sleep if gpiod_cansleep() is true. */ int gpiod_get_direction(struct gpio_desc *desc) { unsigned long flags; unsigned int offset; int ret; ret = validate_desc(desc, __func__); if (ret <= 0) return -EINVAL; CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; offset = gpiod_hwgpio(desc); flags = READ_ONCE(desc->flags); /* * Open drain emulation using input mode may incorrectly report * input here, fix that up. */ if (test_bit(GPIOD_FLAG_OPEN_DRAIN, &flags) && test_bit(GPIOD_FLAG_IS_OUT, &flags)) return 0; ret = gpiochip_get_direction(guard.gc, offset); if (ret < 0) return ret; /* * GPIO_LINE_DIRECTION_IN or other positive, * otherwise GPIO_LINE_DIRECTION_OUT. */ if (ret > 0) ret = 1; assign_bit(GPIOD_FLAG_IS_OUT, &flags, !ret); WRITE_ONCE(desc->flags, flags); return ret; } EXPORT_SYMBOL_GPL(gpiod_get_direction); /* * Add a new chip to the global chips list, keeping the list of chips sorted * by range(means [base, base + ngpio - 1]) order. * * Returns: * -EBUSY if the new chip overlaps with some other chip's integer space. */ static int gpiodev_add_to_list_unlocked(struct gpio_device *gdev) { struct gpio_device *prev, *next; lockdep_assert_held(&gpio_devices_lock); if (list_empty(&gpio_devices)) { /* initial entry in list */ list_add_tail_rcu(&gdev->list, &gpio_devices); return 0; } next = list_first_entry(&gpio_devices, struct gpio_device, list); if (gdev->base + gdev->ngpio <= next->base) { /* add before first entry */ list_add_rcu(&gdev->list, &gpio_devices); return 0; } prev = list_last_entry(&gpio_devices, struct gpio_device, list); if (prev->base + prev->ngpio <= gdev->base) { /* add behind last entry */ list_add_tail_rcu(&gdev->list, &gpio_devices); return 0; } list_for_each_entry_safe(prev, next, &gpio_devices, list) { /* at the end of the list */ if (&next->list == &gpio_devices) break; /* add between prev and next */ if (prev->base + prev->ngpio <= gdev->base && gdev->base + gdev->ngpio <= next->base) { list_add_rcu(&gdev->list, &prev->list); return 0; } } synchronize_srcu(&gpio_devices_srcu); return -EBUSY; } /* * Convert a GPIO name to its descriptor * Note that there is no guarantee that GPIO names are globally unique! * Hence this function will return, if it exists, a reference to the first GPIO * line found that matches the given name. */ static struct gpio_desc *gpio_name_to_desc(const char * const name) { struct gpio_device *gdev; struct gpio_desc *desc; struct gpio_chip *gc; if (!name) return NULL; guard(srcu)(&gpio_devices_srcu); list_for_each_entry_srcu(gdev, &gpio_devices, list, srcu_read_lock_held(&gpio_devices_srcu)) { guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); if (!gc) continue; for_each_gpio_desc(gc, desc) { if (desc->name && !strcmp(desc->name, name)) return desc; } } return NULL; } /* * Take the names from gc->names and assign them to their GPIO descriptors. * Warn if a name is already used for a GPIO line on a different GPIO chip. * * Note that: * 1. Non-unique names are still accepted, * 2. Name collisions within the same GPIO chip are not reported. */ static void gpiochip_set_desc_names(struct gpio_chip *gc) { struct gpio_device *gdev = gc->gpiodev; int i; /* First check all names if they are unique */ for (i = 0; i != gc->ngpio; ++i) { struct gpio_desc *gpio; gpio = gpio_name_to_desc(gc->names[i]); if (gpio) dev_warn(&gdev->dev, "Detected name collision for GPIO name '%s'\n", gc->names[i]); } /* Then add all names to the GPIO descriptors */ for (i = 0; i != gc->ngpio; ++i) gdev->descs[i].name = gc->names[i]; } /* * gpiochip_set_names - Set GPIO line names using device properties * @chip: GPIO chip whose lines should be named, if possible * * Looks for device property "gpio-line-names" and if it exists assigns * GPIO line names for the chip. The memory allocated for the assigned * names belong to the underlying firmware node and should not be released * by the caller. */ static int gpiochip_set_names(struct gpio_chip *chip) { struct gpio_device *gdev = chip->gpiodev; struct device *dev = &gdev->dev; const char **names; int ret, i; int count; count = device_property_string_array_count(dev, "gpio-line-names"); if (count < 0) return 0; /* * When offset is set in the driver side we assume the driver internally * is using more than one gpiochip per the same device. We have to stop * setting friendly names if the specified ones with 'gpio-line-names' * are less than the offset in the device itself. This means all the * lines are not present for every single pin within all the internal * gpiochips. */ if (count <= chip->offset) { dev_warn(dev, "gpio-line-names too short (length %d), cannot map names for the gpiochip at offset %u\n", count, chip->offset); return 0; } names = kcalloc(count, sizeof(*names), GFP_KERNEL); if (!names) return -ENOMEM; ret = device_property_read_string_array(dev, "gpio-line-names", names, count); if (ret < 0) { dev_warn(dev, "failed to read GPIO line names\n"); kfree(names); return ret; } /* * When more that one gpiochip per device is used, 'count' can * contain at most number gpiochips x chip->ngpio. We have to * correctly distribute all defined lines taking into account * chip->offset as starting point from where we will assign * the names to pins from the 'names' array. Since property * 'gpio-line-names' cannot contains gaps, we have to be sure * we only assign those pins that really exists since chip->ngpio * can be different of the chip->offset. */ count = (count > chip->offset) ? count - chip->offset : count; if (count > chip->ngpio) count = chip->ngpio; for (i = 0; i < count; i++) { /* * Allow overriding "fixed" names provided by the GPIO * provider. The "fixed" names are more often than not * generic and less informative than the names given in * device properties. */ if (names[chip->offset + i] && names[chip->offset + i][0]) gdev->descs[i].name = names[chip->offset + i]; } kfree(names); return 0; } static unsigned long *gpiochip_allocate_mask(struct gpio_chip *gc) { unsigned long *p; p = bitmap_alloc(gc->ngpio, GFP_KERNEL); if (!p) return NULL; /* Assume by default all GPIOs are valid */ bitmap_fill(p, gc->ngpio); return p; } static void gpiochip_free_mask(unsigned long **p) { bitmap_free(*p); *p = NULL; } static unsigned int gpiochip_count_reserved_ranges(struct gpio_chip *gc) { struct device *dev = &gc->gpiodev->dev; int size; /* Format is "start, count, ..." */ size = device_property_count_u32(dev, "gpio-reserved-ranges"); if (size > 0 && size % 2 == 0) return size; return 0; } static int gpiochip_apply_reserved_ranges(struct gpio_chip *gc) { struct device *dev = &gc->gpiodev->dev; unsigned int size; u32 *ranges; int ret; size = gpiochip_count_reserved_ranges(gc); if (size == 0) return 0; ranges = kmalloc_array(size, sizeof(*ranges), GFP_KERNEL); if (!ranges) return -ENOMEM; ret = device_property_read_u32_array(dev, "gpio-reserved-ranges", ranges, size); if (ret) { kfree(ranges); return ret; } while (size) { u32 count = ranges[--size]; u32 start = ranges[--size]; if (start >= gc->ngpio || start + count > gc->ngpio) continue; bitmap_clear(gc->gpiodev->valid_mask, start, count); } kfree(ranges); return 0; } static int gpiochip_init_valid_mask(struct gpio_chip *gc) { int ret; if (!(gpiochip_count_reserved_ranges(gc) || gc->init_valid_mask)) return 0; gc->gpiodev->valid_mask = gpiochip_allocate_mask(gc); if (!gc->gpiodev->valid_mask) return -ENOMEM; ret = gpiochip_apply_reserved_ranges(gc); if (ret) return ret; if (gc->init_valid_mask) return gc->init_valid_mask(gc, gc->gpiodev->valid_mask, gc->ngpio); return 0; } static void gpiochip_free_valid_mask(struct gpio_chip *gc) { gpiochip_free_mask(&gc->gpiodev->valid_mask); } static int gpiochip_add_pin_ranges(struct gpio_chip *gc) { /* * Device Tree platforms are supposed to use "gpio-ranges" * property. This check ensures that the ->add_pin_ranges() * won't be called for them. */ if (device_property_present(&gc->gpiodev->dev, "gpio-ranges")) return 0; if (gc->add_pin_ranges) return gc->add_pin_ranges(gc); return 0; } /** * gpiochip_query_valid_mask - return the GPIO validity information * @gc: gpio chip which validity information is queried * * Returns: bitmap representing valid GPIOs or NULL if all GPIOs are valid * * Some GPIO chips may support configurations where some of the pins aren't * available. These chips can have valid_mask set to represent the valid * GPIOs. This function can be used to retrieve this information. */ const unsigned long *gpiochip_query_valid_mask(const struct gpio_chip *gc) { return gc->gpiodev->valid_mask; } EXPORT_SYMBOL_GPL(gpiochip_query_valid_mask); bool gpiochip_line_is_valid(const struct gpio_chip *gc, unsigned int offset) { /* * hog pins are requested before registering GPIO chip */ if (!gc->gpiodev) return true; /* No mask means all valid */ if (likely(!gc->gpiodev->valid_mask)) return true; return test_bit(offset, gc->gpiodev->valid_mask); } EXPORT_SYMBOL_GPL(gpiochip_line_is_valid); static void gpiod_free_irqs(struct gpio_desc *desc) { int irq = gpiod_to_irq(desc); struct irq_desc *irqd = irq_to_desc(irq); void *cookie; for (;;) { /* * Make sure the action doesn't go away while we're * dereferencing it. Retrieve and store the cookie value. * If the irq is freed after we release the lock, that's * alright - the underlying maple tree lookup will return NULL * and nothing will happen in free_irq(). */ scoped_guard(mutex, &irqd->request_mutex) { if (!irq_desc_has_action(irqd)) return; cookie = irqd->action->dev_id; } free_irq(irq, cookie); } } /* * The chip is going away but there may be users who had requested interrupts * on its GPIO lines who have no idea about its removal and have no way of * being notified about it. We need to free any interrupts still in use here or * we'll leak memory and resources (like procfs files). */ static void gpiochip_free_remaining_irqs(struct gpio_chip *gc) { struct gpio_desc *desc; for_each_gpio_desc_with_flag(gc, desc, GPIOD_FLAG_USED_AS_IRQ) gpiod_free_irqs(desc); } static void gpiodev_release(struct device *dev) { struct gpio_device *gdev = to_gpio_device(dev); /* Call pending kfree()s for descriptor labels. */ synchronize_srcu(&gdev->desc_srcu); cleanup_srcu_struct(&gdev->desc_srcu); ida_free(&gpio_ida, gdev->id); kfree_const(gdev->label); kfree(gdev->descs); cleanup_srcu_struct(&gdev->srcu); kfree(gdev); } static const struct device_type gpio_dev_type = { .name = "gpio_chip", .release = gpiodev_release, }; #ifdef CONFIG_GPIO_CDEV #define gcdev_register(gc, devt) gpiolib_cdev_register((gc), (devt)) #define gcdev_unregister(gdev) gpiolib_cdev_unregister((gdev)) #else /* * gpiolib_cdev_register() indirectly calls device_add(), which is still * required even when cdev is not selected. */ #define gcdev_register(gc, devt) device_add(&(gc)->gpiodev->dev) #define gcdev_unregister(gdev) device_del(&(gdev)->dev) #endif /* * An initial reference count has been held in gpiochip_add_data_with_key(). * The caller should drop the reference via gpio_device_put() on errors. */ static int gpiochip_setup_dev(struct gpio_chip *gc) { struct gpio_device *gdev = gc->gpiodev; struct fwnode_handle *fwnode = dev_fwnode(&gdev->dev); int ret; /* * If fwnode doesn't belong to another device, it's safe to clear its * initialized flag. */ if (fwnode && !fwnode->dev) fwnode_dev_initialized(fwnode, false); ret = gcdev_register(gc, gpio_devt); if (ret) return ret; ret = gpiochip_sysfs_register(gc); if (ret) goto err_remove_device; dev_dbg(&gdev->dev, "registered GPIOs %u to %u on %s\n", gdev->base, gdev->base + gdev->ngpio - 1, gdev->label); return 0; err_remove_device: gcdev_unregister(gdev); return ret; } int gpiochip_add_hog(struct gpio_chip *gc, struct fwnode_handle *fwnode) { struct fwnode_handle *gc_node = dev_fwnode(&gc->gpiodev->dev); struct fwnode_reference_args gpiospec; enum gpiod_flags dflags; const char *name = NULL; struct gpio_desc *desc; unsigned int num_hogs; unsigned long lflags; int ret, argc; /* * For devicetree-based systems, this needs to be defined in bindings * and there's no real default value. For other firmware descriptions * it makes the most sense to use 2 cells for the GPIO offset and * request flags. */ u32 cells = 2; lflags = GPIO_LOOKUP_FLAGS_DEFAULT; dflags = GPIOD_ASIS; name = NULL; argc = fwnode_property_count_u32(fwnode, "gpios"); if (argc < 0) return argc; ret = fwnode_property_read_u32(gc_node, "#gpio-cells", &cells); if (ret && is_of_node(fwnode)) return ret; if (argc % cells) return -EINVAL; num_hogs = argc / cells; u32 *gpios __free(kfree) = kzalloc_objs(*gpios, argc); if (!gpios) return -ENOMEM; ret = fwnode_property_read_u32_array(fwnode, "gpios", gpios, argc); if (ret < 0) return ret; if (fwnode_property_present(fwnode, "input")) dflags |= GPIOD_IN; else if (fwnode_property_present(fwnode, "output-low")) dflags |= GPIOD_OUT_LOW; else if (fwnode_property_present(fwnode, "output-high")) dflags |= GPIOD_OUT_HIGH; else return -EINVAL; fwnode_property_read_string(fwnode, "line-name", &name); for (unsigned int i = 0; i < num_hogs; i++) { if (is_of_node(fwnode)) { /* * OF-nodes need some additional special handling for * translating of devicetree flags. */ memset(&gpiospec, 0, sizeof(gpiospec)); gpiospec.fwnode = fwnode; gpiospec.nargs = cells; for (unsigned int j = 0; j < cells; j++) gpiospec.args[j] = gpios[i * cells + j]; ret = of_gpiochip_get_lflags(gc, &gpiospec, &lflags); if (ret) return ret; } else { /* * GPIO_ACTIVE_LOW is currently the only lookup flag * supported for non-OF firmware nodes. */ if (gpios[i * cells + 1]) lflags |= GPIO_ACTIVE_LOW; } desc = gpiochip_get_desc(gc, gpios[i * cells]); if (IS_ERR(desc)) return PTR_ERR(desc); ret = gpiod_hog(desc, name, lflags, dflags); if (ret) return ret; } return 0; } static int gpiochip_hog_lines(struct gpio_chip *gc) { int ret; device_for_each_child_node_scoped(&gc->gpiodev->dev, fwnode) { if (!fwnode_property_present(fwnode, "gpio-hog")) continue; ret = gpiochip_add_hog(gc, fwnode); if (ret) return ret; } return 0; } static void gpiochip_setup_devs(void) { struct gpio_device *gdev; struct gpio_chip *gc; int ret; guard(srcu)(&gpio_devices_srcu); list_for_each_entry_srcu(gdev, &gpio_devices, list, srcu_read_lock_held(&gpio_devices_srcu)) { guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); if (!gc) { dev_err(&gdev->dev, "Underlying GPIO chip is gone\n"); continue; } ret = gpiochip_setup_dev(gc); if (ret) { gpio_device_put(gdev); dev_err(&gdev->dev, "Failed to initialize gpio device (%d)\n", ret); } } } static void gpiochip_set_data(struct gpio_chip *gc, void *data) { gc->gpiodev->data = data; } /** * gpiochip_get_data() - get per-subdriver data for the chip * @gc: GPIO chip * * Returns: * The per-subdriver data for the chip. */ void *gpiochip_get_data(struct gpio_chip *gc) { return gc->gpiodev->data; } EXPORT_SYMBOL_GPL(gpiochip_get_data); /* * If the calling driver provides the specific firmware node, * use it. Otherwise use the one from the parent device, if any. */ static struct fwnode_handle *gpiochip_choose_fwnode(struct gpio_chip *gc) { if (gc->fwnode) return gc->fwnode; if (gc->parent) return dev_fwnode(gc->parent); return NULL; } int gpiochip_get_ngpios(struct gpio_chip *gc, struct device *dev) { struct fwnode_handle *fwnode = gpiochip_choose_fwnode(gc); u32 ngpios = gc->ngpio; int ret; if (ngpios == 0) { ret = fwnode_property_read_u32(fwnode, "ngpios", &ngpios); if (ret == -ENODATA) /* * -ENODATA means that there is no property found and * we want to issue the error message to the user. * Besides that, we want to return different error code * to state that supplied value is not valid. */ ngpios = 0; else if (ret) return ret; gc->ngpio = ngpios; } if (gc->ngpio == 0) { dev_err(dev, "tried to insert a GPIO chip with zero lines\n"); return -EINVAL; } if (gc->ngpio > FASTPATH_NGPIO) dev_warn(dev, "line cnt %u is greater than fast path cnt %u\n", gc->ngpio, FASTPATH_NGPIO); return 0; } EXPORT_SYMBOL_GPL(gpiochip_get_ngpios); int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, struct lock_class_key *lock_key, struct lock_class_key *request_key) { struct gpio_device *gdev; unsigned int desc_index; int base = 0; int ret; gdev = kzalloc(sizeof(*gdev), GFP_KERNEL); if (!gdev) return -ENOMEM; gc->gpiodev = gdev; gpiochip_set_data(gc, data); ret = ida_alloc(&gpio_ida, GFP_KERNEL); if (ret < 0) goto err_free_gdev; gdev->id = ret; ret = init_srcu_struct(&gdev->srcu); if (ret) goto err_free_ida; rcu_assign_pointer(gdev->chip, gc); ret = init_srcu_struct(&gdev->desc_srcu); if (ret) goto err_cleanup_gdev_srcu; ret = dev_set_name(&gdev->dev, GPIOCHIP_NAME "%d", gdev->id); if (ret) goto err_cleanup_desc_srcu; device_initialize(&gdev->dev); /* * After this point any allocated resources to `gdev` will be * free():ed by gpiodev_release(). If you add new resources * then make sure they get free():ed there. */ gdev->dev.type = &gpio_dev_type; gdev->dev.bus = &gpio_bus_type; gdev->dev.parent = gc->parent; device_set_node(&gdev->dev, gpiochip_choose_fwnode(gc)); ret = gpiochip_get_ngpios(gc, &gdev->dev); if (ret) goto err_put_device; gdev->ngpio = gc->ngpio; gdev->descs = kcalloc(gc->ngpio, sizeof(*gdev->descs), GFP_KERNEL); if (!gdev->descs) { ret = -ENOMEM; goto err_put_device; } gdev->label = kstrdup_const(gc->label ?: "unknown", GFP_KERNEL); if (!gdev->label) { ret = -ENOMEM; goto err_put_device; } gdev->can_sleep = gc->can_sleep; rwlock_init(&gdev->line_state_lock); RAW_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier); BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier); #ifdef CONFIG_PINCTRL INIT_LIST_HEAD(&gdev->pin_ranges); #endif if (gc->parent && gc->parent->driver) gdev->owner = gc->parent->driver->owner; else if (gc->owner) /* TODO: remove chip->owner */ gdev->owner = gc->owner; else gdev->owner = THIS_MODULE; scoped_guard(mutex, &gpio_devices_lock) { /* * TODO: this allocates a Linux GPIO number base in the global * GPIO numberspace for this chip. In the long run we want to * get *rid* of this numberspace and use only descriptors, but * it may be a pipe dream. It will not happen before we get rid * of the sysfs interface anyways. */ base = gc->base; if (base < 0) { base = gpiochip_find_base_unlocked(gc->ngpio); if (base < 0) { ret = base; base = 0; goto err_put_device; } /* * TODO: it should not be necessary to reflect the * assigned base outside of the GPIO subsystem. Go over * drivers and see if anyone makes use of this, else * drop this and assign a poison instead. */ gc->base = base; } else { dev_warn(&gdev->dev, "Static allocation of GPIO base is deprecated, use dynamic allocation.\n"); } gdev->base = base; ret = gpiodev_add_to_list_unlocked(gdev); if (ret) { gpiochip_err(gc, "GPIO integer space overlap, cannot add chip\n"); goto err_put_device; } } if (gc->names) gpiochip_set_desc_names(gc); ret = gpiochip_set_names(gc); if (ret) goto err_remove_from_list; ret = gpiochip_init_valid_mask(gc); if (ret) goto err_remove_from_list; for (desc_index = 0; desc_index < gc->ngpio; desc_index++) { struct gpio_desc *desc = &gdev->descs[desc_index]; desc->gdev = gdev; /* * We would typically want to use gpiochip_get_direction() here * but we must not check the return value and bail-out as pin * controllers can have pins configured to alternate functions * and return -EINVAL. Also: there's no need to take the SRCU * lock here. */ if (gc->get_direction && gpiochip_line_is_valid(gc, desc_index)) assign_bit(GPIOD_FLAG_IS_OUT, &desc->flags, !gc->get_direction(gc, desc_index)); else assign_bit(GPIOD_FLAG_IS_OUT, &desc->flags, !gc->direction_input); } ret = of_gpiochip_add(gc); if (ret) goto err_free_valid_mask; ret = gpiochip_add_pin_ranges(gc); if (ret) goto err_remove_of_chip; acpi_gpiochip_add(gc); ret = gpiochip_hog_lines(gc); if (ret) goto err_remove_of_chip; ret = gpiochip_irqchip_init_valid_mask(gc); if (ret) goto err_free_hogs; ret = gpiochip_irqchip_init_hw(gc); if (ret) goto err_remove_irqchip_mask; ret = gpiochip_add_irqchip(gc, lock_key, request_key); if (ret) goto err_remove_irqchip_mask; ret = gpiochip_setup_shared(gc); if (ret) goto err_remove_irqchip; /* * By first adding the chardev, and then adding the device, * we get a device node entry in sysfs under * /sys/bus/gpio/devices/gpiochipN/dev that can be used for * coldplug of device nodes and other udev business. * We can do this only if gpiolib has been initialized. * Otherwise, defer until later. */ if (gpiolib_initialized) { ret = gpiochip_setup_dev(gc); if (ret) goto err_teardown_shared; } return 0; err_teardown_shared: gpio_device_teardown_shared(gdev); err_remove_irqchip: gpiochip_irqchip_remove(gc); err_remove_irqchip_mask: gpiochip_irqchip_free_valid_mask(gc); err_free_hogs: gpiochip_free_hogs(gc); acpi_gpiochip_remove(gc); gpiochip_remove_pin_ranges(gc); err_remove_of_chip: of_gpiochip_remove(gc); err_free_valid_mask: gpiochip_free_valid_mask(gc); err_remove_from_list: scoped_guard(mutex, &gpio_devices_lock) list_del_rcu(&gdev->list); synchronize_srcu(&gpio_devices_srcu); err_put_device: gpio_device_put(gdev); goto err_print_message; err_cleanup_desc_srcu: cleanup_srcu_struct(&gdev->desc_srcu); err_cleanup_gdev_srcu: cleanup_srcu_struct(&gdev->srcu); err_free_ida: ida_free(&gpio_ida, gdev->id); err_free_gdev: kfree(gdev); err_print_message: /* failures here can mean systems won't boot... */ if (ret != -EPROBE_DEFER) { pr_err("%s: GPIOs %d..%d (%s) failed to register, %d\n", __func__, base, base + (int)gc->ngpio - 1, gc->label ? : "generic", ret); } return ret; } EXPORT_SYMBOL_GPL(gpiochip_add_data_with_key); /** * gpiochip_remove() - unregister a gpio_chip * @gc: the chip to unregister * * A gpio_chip with any GPIOs still requested may not be removed. */ void gpiochip_remove(struct gpio_chip *gc) { struct gpio_device *gdev = gc->gpiodev; /* FIXME: should the legacy sysfs handling be moved to gpio_device? */ gpiochip_sysfs_unregister(gc); gpiochip_free_hogs(gc); gpiochip_free_remaining_irqs(gc); scoped_guard(mutex, &gpio_devices_lock) list_del_rcu(&gdev->list); synchronize_srcu(&gpio_devices_srcu); /* Numb the device, cancelling all outstanding operations */ rcu_assign_pointer(gdev->chip, NULL); synchronize_srcu(&gdev->srcu); gpio_device_teardown_shared(gdev); gpiochip_irqchip_remove(gc); acpi_gpiochip_remove(gc); of_gpiochip_remove(gc); gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); /* * We accept no more calls into the driver from this point, so * NULL the driver data pointer. */ gpiochip_set_data(gc, NULL); /* * The gpiochip side puts its use of the device to rest here: * if there are no userspace clients, the chardev and device will * be removed, else it will be dangling until the last user is * gone. */ gcdev_unregister(gdev); gpio_device_put(gdev); } EXPORT_SYMBOL_GPL(gpiochip_remove); /** * gpio_device_find() - find a specific GPIO device * @data: data to pass to match function * @match: Callback function to check gpio_chip * * Returns: * New reference to struct gpio_device. * * Similar to bus_find_device(). It returns a reference to a gpio_device as * determined by a user supplied @match callback. The callback should return * 0 if the device doesn't match and non-zero if it does. If the callback * returns non-zero, this function will return to the caller and not iterate * over any more gpio_devices. * * The callback takes the GPIO chip structure as argument. During the execution * of the callback function the chip is protected from being freed. TODO: This * actually has yet to be implemented. * * If the function returns non-NULL, the returned reference must be freed by * the caller using gpio_device_put(). */ struct gpio_device *gpio_device_find(const void *data, int (*match)(struct gpio_chip *gc, const void *data)) { struct gpio_device *gdev; struct gpio_chip *gc; might_sleep(); guard(srcu)(&gpio_devices_srcu); list_for_each_entry_srcu(gdev, &gpio_devices, list, srcu_read_lock_held(&gpio_devices_srcu)) { if (!device_is_registered(&gdev->dev)) continue; guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); if (gc && match(gc, data)) return gpio_device_get(gdev); } return NULL; } EXPORT_SYMBOL_GPL(gpio_device_find); static int gpio_chip_match_by_label(struct gpio_chip *gc, const void *label) { return gc->label && !strcmp(gc->label, label); } /** * gpio_device_find_by_label() - wrapper around gpio_device_find() finding the * GPIO device by its backing chip's label * @label: Label to lookup * * Returns: * Reference to the GPIO device or NULL. Reference must be released with * gpio_device_put(). */ struct gpio_device *gpio_device_find_by_label(const char *label) { return gpio_device_find((void *)label, gpio_chip_match_by_label); } EXPORT_SYMBOL_GPL(gpio_device_find_by_label); static int gpio_chip_match_by_fwnode(struct gpio_chip *gc, const void *fwnode) { struct device *dev = &gc->gpiodev->dev; struct fwnode_handle *node = dev_fwnode(dev); if (IS_ERR(fwnode)) return 0; if (device_match_fwnode(dev, fwnode)) return 1; return node && node->secondary == fwnode; } /** * gpio_device_find_by_fwnode() - wrapper around gpio_device_find() finding * the GPIO device by its fwnode * @fwnode: Firmware node to lookup * * Returns: * Reference to the GPIO device or NULL. Reference must be released with * gpio_device_put(). */ struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode) { return gpio_device_find((void *)fwnode, gpio_chip_match_by_fwnode); } EXPORT_SYMBOL_GPL(gpio_device_find_by_fwnode); /** * gpio_device_get() - Increase the reference count of this GPIO device * @gdev: GPIO device to increase the refcount for * * Returns: * Pointer to @gdev. */ struct gpio_device *gpio_device_get(struct gpio_device *gdev) { return to_gpio_device(get_device(&gdev->dev)); } EXPORT_SYMBOL_GPL(gpio_device_get); /** * gpio_device_put() - Decrease the reference count of this GPIO device and * possibly free all resources associated with it. * @gdev: GPIO device to decrease the reference count for */ void gpio_device_put(struct gpio_device *gdev) { put_device(&gdev->dev); } EXPORT_SYMBOL_GPL(gpio_device_put); /** * gpio_device_to_device() - Retrieve the address of the underlying struct * device. * @gdev: GPIO device for which to return the address. * * This does not increase the reference count of the GPIO device nor the * underlying struct device. * * Returns: * Address of struct device backing this GPIO device. */ struct device *gpio_device_to_device(struct gpio_device *gdev) { return &gdev->dev; } EXPORT_SYMBOL_GPL(gpio_device_to_device); #ifdef CONFIG_GPIOLIB_IRQCHIP /* * The following is irqchip helper code for gpiochips. */ static int gpiochip_irqchip_init_hw(struct gpio_chip *gc) { struct gpio_irq_chip *girq = &gc->irq; if (!girq->init_hw) return 0; return girq->init_hw(gc); } static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gc) { struct gpio_irq_chip *girq = &gc->irq; if (!girq->init_valid_mask) return 0; girq->valid_mask = gpiochip_allocate_mask(gc); if (!girq->valid_mask) return -ENOMEM; girq->init_valid_mask(gc, girq->valid_mask, gc->ngpio); return 0; } static void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gc) { gpiochip_free_mask(&gc->irq.valid_mask); } static bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc, unsigned int offset) { if (!gpiochip_line_is_valid(gc, offset)) return false; /* No mask means all valid */ if (likely(!gc->irq.valid_mask)) return true; return test_bit(offset, gc->irq.valid_mask); } #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY /** * gpiochip_set_hierarchical_irqchip() - connects a hierarchical irqchip * to a gpiochip * @gc: the gpiochip to set the irqchip hierarchical handler to * @irqchip: the irqchip to handle this level of the hierarchy, the interrupt * will then percolate up to the parent */ static void gpiochip_set_hierarchical_irqchip(struct gpio_chip *gc, struct irq_chip *irqchip) { /* DT will deal with mapping each IRQ as we go along */ if (is_of_node(gc->irq.fwnode)) return; /* * This is for legacy and boardfile "irqchip" fwnodes: allocate * irqs upfront instead of dynamically since we don't have the * dynamic type of allocation that hardware description languages * provide. Once all GPIO drivers using board files are gone from * the kernel we can delete this code, but for a transitional period * it is necessary to keep this around. */ if (is_fwnode_irqchip(gc->irq.fwnode)) { int i; int ret; for (i = 0; i < gc->ngpio; i++) { struct irq_fwspec fwspec; unsigned int parent_hwirq; unsigned int parent_type; struct gpio_irq_chip *girq = &gc->irq; /* * We call the child to parent translation function * only to check if the child IRQ is valid or not. * Just pick the rising edge type here as that is what * we likely need to support. */ ret = girq->child_to_parent_hwirq(gc, i, IRQ_TYPE_EDGE_RISING, &parent_hwirq, &parent_type); if (ret) { gpiochip_err(gc, "skip set-up on hwirq %d\n", i); continue; } fwspec.fwnode = gc->irq.fwnode; /* This is the hwirq for the GPIO line side of things */ fwspec.param[0] = girq->child_offset_to_irq(gc, i); /* Just pick something */ fwspec.param[1] = IRQ_TYPE_EDGE_RISING; fwspec.param_count = 2; ret = irq_domain_alloc_irqs(gc->irq.domain, 1, NUMA_NO_NODE, &fwspec); if (ret < 0) { gpiochip_err(gc, "can not allocate irq for GPIO line %d parent hwirq %d in hierarchy domain: %d\n", i, parent_hwirq, ret); } } } gpiochip_err(gc, "%s unknown fwnode type proceed anyway\n", __func__); return; } static int gpiochip_hierarchy_irq_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { /* We support standard DT translation */ if (is_of_node(fwspec->fwnode)) return irq_domain_translate_twothreecell(d, fwspec, hwirq, type); /* This is for board files and others not using DT */ if (is_fwnode_irqchip(fwspec->fwnode)) { int ret; ret = irq_domain_translate_twocell(d, fwspec, hwirq, type); if (ret) return ret; WARN_ON(*type == IRQ_TYPE_NONE); return 0; } return -EINVAL; } static int gpiochip_hierarchy_irq_domain_alloc(struct irq_domain *d, unsigned int irq, unsigned int nr_irqs, void *data) { struct gpio_chip *gc = d->host_data; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; struct irq_fwspec *fwspec = data; union gpio_irq_fwspec gpio_parent_fwspec = {}; unsigned int parent_hwirq; unsigned int parent_type; struct gpio_irq_chip *girq = &gc->irq; int ret; /* * The nr_irqs parameter is always one except for PCI multi-MSI * so this should not happen. */ WARN_ON(nr_irqs != 1); ret = gc->irq.child_irq_domain_ops.translate(d, fwspec, &hwirq, &type); if (ret) return ret; gpiochip_dbg(gc, "allocate IRQ %d, hwirq %lu\n", irq, hwirq); ret = girq->child_to_parent_hwirq(gc, hwirq, type, &parent_hwirq, &parent_type); if (ret) { gpiochip_err(gc, "can't look up hwirq %lu\n", hwirq); return ret; } gpiochip_dbg(gc, "found parent hwirq %u\n", parent_hwirq); /* * We set handle_bad_irq because the .set_type() should * always be invoked and set the right type of handler. */ irq_domain_set_info(d, irq, hwirq, gc->irq.chip, gc, girq->handler, NULL, NULL); irq_set_probe(irq); /* This parent only handles asserted level IRQs */ ret = girq->populate_parent_alloc_arg(gc, &gpio_parent_fwspec, parent_hwirq, parent_type); if (ret) return ret; gpiochip_dbg(gc, "alloc_irqs_parent for %d parent hwirq %d\n", irq, parent_hwirq); irq_set_lockdep_class(irq, gc->irq.lock_key, gc->irq.request_key); ret = irq_domain_alloc_irqs_parent(d, irq, 1, &gpio_parent_fwspec); /* * If the parent irqdomain is msi, the interrupts have already * been allocated, so the EEXIST is good. */ if (irq_domain_is_msi(d->parent) && (ret == -EEXIST)) ret = 0; if (ret) gpiochip_err(gc, "failed to allocate parent hwirq %d for hwirq %lu\n", parent_hwirq, hwirq); return ret; } static unsigned int gpiochip_child_offset_to_irq_noop(struct gpio_chip *gc, unsigned int offset) { return offset; } /** * gpiochip_irq_domain_activate() - Lock a GPIO to be used as an IRQ * @domain: The IRQ domain used by this IRQ chip * @data: Outermost irq_data associated with the IRQ * @reserve: If set, only reserve an interrupt vector instead of assigning one * * This function is a wrapper that calls gpiochip_lock_as_irq() and is to be * used as the activate function for the &struct irq_domain_ops. The host_data * for the IRQ domain must be the &struct gpio_chip. * * Returns: * 0 on success, or negative errno on failure. */ static int gpiochip_irq_domain_activate(struct irq_domain *domain, struct irq_data *data, bool reserve) { struct gpio_chip *gc = domain->host_data; unsigned int hwirq = irqd_to_hwirq(data); return gpiochip_lock_as_irq(gc, hwirq); } /** * gpiochip_irq_domain_deactivate() - Unlock a GPIO used as an IRQ * @domain: The IRQ domain used by this IRQ chip * @data: Outermost irq_data associated with the IRQ * * This function is a wrapper that will call gpiochip_unlock_as_irq() and is to * be used as the deactivate function for the &struct irq_domain_ops. The * host_data for the IRQ domain must be the &struct gpio_chip. */ static void gpiochip_irq_domain_deactivate(struct irq_domain *domain, struct irq_data *data) { struct gpio_chip *gc = domain->host_data; unsigned int hwirq = irqd_to_hwirq(data); return gpiochip_unlock_as_irq(gc, hwirq); } static void gpiochip_hierarchy_setup_domain_ops(struct irq_domain_ops *ops) { ops->activate = gpiochip_irq_domain_activate; ops->deactivate = gpiochip_irq_domain_deactivate; ops->alloc = gpiochip_hierarchy_irq_domain_alloc; /* * We only allow overriding the translate() and free() functions for * hierarchical chips, and this should only be done if the user * really need something other than 1:1 translation for translate() * callback and free if user wants to free up any resources which * were allocated during callbacks, for example populate_parent_alloc_arg. */ if (!ops->translate) ops->translate = gpiochip_hierarchy_irq_domain_translate; if (!ops->free) ops->free = irq_domain_free_irqs_common; } static struct irq_domain *gpiochip_hierarchy_create_domain(struct gpio_chip *gc) { struct irq_domain *domain; if (!gc->irq.child_to_parent_hwirq || !gc->irq.fwnode) { gpiochip_err(gc, "missing irqdomain vital data\n"); return ERR_PTR(-EINVAL); } if (!gc->irq.child_offset_to_irq) gc->irq.child_offset_to_irq = gpiochip_child_offset_to_irq_noop; if (!gc->irq.populate_parent_alloc_arg) gc->irq.populate_parent_alloc_arg = gpiochip_populate_parent_fwspec_twocell; gpiochip_hierarchy_setup_domain_ops(&gc->irq.child_irq_domain_ops); domain = irq_domain_create_hierarchy( gc->irq.parent_domain, 0, gc->ngpio, gc->irq.fwnode, &gc->irq.child_irq_domain_ops, gc); if (!domain) return ERR_PTR(-ENOMEM); gpiochip_set_hierarchical_irqchip(gc, gc->irq.chip); return domain; } static bool gpiochip_hierarchy_is_hierarchical(struct gpio_chip *gc) { return !!gc->irq.parent_domain; } int gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *gc, union gpio_irq_fwspec *gfwspec, unsigned int parent_hwirq, unsigned int parent_type) { struct irq_fwspec *fwspec = &gfwspec->fwspec; fwspec->fwnode = gc->irq.parent_domain->fwnode; fwspec->param_count = 2; fwspec->param[0] = parent_hwirq; fwspec->param[1] = parent_type; return 0; } EXPORT_SYMBOL_GPL(gpiochip_populate_parent_fwspec_twocell); int gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *gc, union gpio_irq_fwspec *gfwspec, unsigned int parent_hwirq, unsigned int parent_type) { struct irq_fwspec *fwspec = &gfwspec->fwspec; fwspec->fwnode = gc->irq.parent_domain->fwnode; fwspec->param_count = 4; fwspec->param[0] = 0; fwspec->param[1] = parent_hwirq; fwspec->param[2] = 0; fwspec->param[3] = parent_type; return 0; } EXPORT_SYMBOL_GPL(gpiochip_populate_parent_fwspec_fourcell); #else static struct irq_domain *gpiochip_hierarchy_create_domain(struct gpio_chip *gc) { return ERR_PTR(-EINVAL); } static bool gpiochip_hierarchy_is_hierarchical(struct gpio_chip *gc) { return false; } #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ /** * gpiochip_irq_map() - maps an IRQ into a GPIO irqchip * @d: the irqdomain used by this irqchip * @irq: the global irq number used by this GPIO irqchip irq * @hwirq: the local IRQ/GPIO line offset on this gpiochip * * This function will set up the mapping for a certain IRQ line on a * gpiochip by assigning the gpiochip as chip data, and using the irqchip * stored inside the gpiochip. * * Returns: * 0 on success, or negative errno on failure. */ static int gpiochip_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq) { struct gpio_chip *gc = d->host_data; int ret = 0; if (!gpiochip_irqchip_irq_valid(gc, hwirq)) return -ENXIO; irq_set_chip_data(irq, gc); /* * This lock class tells lockdep that GPIO irqs are in a different * category than their parents, so it won't report false recursion. */ irq_set_lockdep_class(irq, gc->irq.lock_key, gc->irq.request_key); irq_set_chip_and_handler(irq, gc->irq.chip, gc->irq.handler); /* Chips that use nested thread handlers have them marked */ if (gc->irq.threaded) irq_set_nested_thread(irq, 1); irq_set_noprobe(irq); if (gc->irq.num_parents == 1) ret = irq_set_parent(irq, gc->irq.parents[0]); else if (gc->irq.map) ret = irq_set_parent(irq, gc->irq.map[hwirq]); if (ret < 0) return ret; /* * No set-up of the hardware will happen if IRQ_TYPE_NONE * is passed as default type. */ if (gc->irq.default_type != IRQ_TYPE_NONE) irq_set_irq_type(irq, gc->irq.default_type); return 0; } static void gpiochip_irq_unmap(struct irq_domain *d, unsigned int irq) { struct gpio_chip *gc = d->host_data; if (gc->irq.threaded) irq_set_nested_thread(irq, 0); irq_set_chip_and_handler(irq, NULL, NULL); irq_set_chip_data(irq, NULL); } static int gpiochip_irq_select(struct irq_domain *d, struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token) { struct fwnode_handle *fwnode = fwspec->fwnode; struct gpio_chip *gc = d->host_data; unsigned int index = fwspec->param[0]; if (fwspec->param_count == 3 && is_of_node(fwnode)) return of_gpiochip_instance_match(gc, index); /* Fallback for twocells */ return (fwnode && (d->fwnode == fwnode) && (d->bus_token == bus_token)); } static const struct irq_domain_ops gpiochip_domain_ops = { .map = gpiochip_irq_map, .unmap = gpiochip_irq_unmap, .select = gpiochip_irq_select, /* Virtually all GPIO irqchips are twocell:ed */ .xlate = irq_domain_xlate_twothreecell, }; static struct irq_domain *gpiochip_simple_create_domain(struct gpio_chip *gc) { struct fwnode_handle *fwnode = dev_fwnode(&gc->gpiodev->dev); struct irq_domain *domain; domain = irq_domain_create_simple(fwnode, gc->ngpio, gc->irq.first, &gpiochip_domain_ops, gc); if (!domain) return ERR_PTR(-EINVAL); return domain; } static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset) { struct irq_domain *domain = gc->irq.domain; /* * Avoid race condition with other code, which tries to lookup * an IRQ before the irqchip has been properly registered, * i.e. while gpiochip is still being brought up. */ if (!gc->irq.initialized) return -EPROBE_DEFER; if (!gpiochip_irqchip_irq_valid(gc, offset)) return -ENXIO; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY if (irq_domain_is_hierarchy(domain)) { struct irq_fwspec spec; spec.fwnode = domain->fwnode; spec.param_count = 2; spec.param[0] = gc->irq.child_offset_to_irq(gc, offset); spec.param[1] = IRQ_TYPE_NONE; return irq_create_fwspec_mapping(&spec); } #endif return irq_create_mapping(domain, offset); } int gpiochip_irq_reqres(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); unsigned int hwirq = irqd_to_hwirq(d); return gpiochip_reqres_irq(gc, hwirq); } EXPORT_SYMBOL(gpiochip_irq_reqres); void gpiochip_irq_relres(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); unsigned int hwirq = irqd_to_hwirq(d); gpiochip_relres_irq(gc, hwirq); } EXPORT_SYMBOL(gpiochip_irq_relres); static void gpiochip_irq_mask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); unsigned int hwirq = irqd_to_hwirq(d); if (gc->irq.irq_mask) gc->irq.irq_mask(d); gpiochip_disable_irq(gc, hwirq); } static void gpiochip_irq_unmask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); unsigned int hwirq = irqd_to_hwirq(d); gpiochip_enable_irq(gc, hwirq); if (gc->irq.irq_unmask) gc->irq.irq_unmask(d); } static void gpiochip_irq_enable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); unsigned int hwirq = irqd_to_hwirq(d); gpiochip_enable_irq(gc, hwirq); gc->irq.irq_enable(d); } static void gpiochip_irq_disable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); unsigned int hwirq = irqd_to_hwirq(d); gc->irq.irq_disable(d); gpiochip_disable_irq(gc, hwirq); } static void gpiochip_set_irq_hooks(struct gpio_chip *gc) { struct irq_chip *irqchip = gc->irq.chip; if (irqchip->flags & IRQCHIP_IMMUTABLE) return; gpiochip_warn(gc, "not an immutable chip, please consider fixing it!\n"); if (!irqchip->irq_request_resources && !irqchip->irq_release_resources) { irqchip->irq_request_resources = gpiochip_irq_reqres; irqchip->irq_release_resources = gpiochip_irq_relres; } if (WARN_ON(gc->irq.irq_enable)) return; /* Check if the irqchip already has this hook... */ if (irqchip->irq_enable == gpiochip_irq_enable || irqchip->irq_mask == gpiochip_irq_mask) { /* * ...and if so, give a gentle warning that this is bad * practice. */ gpiochip_info(gc, "detected irqchip that is shared with multiple gpiochips: please fix the driver.\n"); return; } if (irqchip->irq_disable) { gc->irq.irq_disable = irqchip->irq_disable; irqchip->irq_disable = gpiochip_irq_disable; } else { gc->irq.irq_mask = irqchip->irq_mask; irqchip->irq_mask = gpiochip_irq_mask; } if (irqchip->irq_enable) { gc->irq.irq_enable = irqchip->irq_enable; irqchip->irq_enable = gpiochip_irq_enable; } else { gc->irq.irq_unmask = irqchip->irq_unmask; irqchip->irq_unmask = gpiochip_irq_unmask; } } static int gpiochip_irqchip_add_allocated_domain(struct gpio_chip *gc, struct irq_domain *domain, bool allocated_externally) { if (!domain) return -EINVAL; if (gc->to_irq) gpiochip_warn(gc, "to_irq is redefined in %s and you shouldn't rely on it\n", __func__); gc->to_irq = gpiochip_to_irq; gc->irq.domain = domain; gc->irq.domain_is_allocated_externally = allocated_externally; /* * Using barrier() here to prevent compiler from reordering * gc->irq.initialized before adding irqdomain. */ barrier(); gc->irq.initialized = true; return 0; } /** * gpiochip_add_irqchip() - adds an IRQ chip to a GPIO chip * @gc: the GPIO chip to add the IRQ chip to * @lock_key: lockdep class for IRQ lock * @request_key: lockdep class for IRQ request * * Returns: * 0 on success, or a negative errno on failure. */ static int gpiochip_add_irqchip(struct gpio_chip *gc, struct lock_class_key *lock_key, struct lock_class_key *request_key) { struct fwnode_handle *fwnode = dev_fwnode(&gc->gpiodev->dev); struct irq_chip *irqchip = gc->irq.chip; struct irq_domain *domain; unsigned int type; unsigned int i; int ret; if (!irqchip) return 0; if (gc->irq.parent_handler && gc->can_sleep) { gpiochip_err(gc, "you cannot have chained interrupts on a chip that may sleep\n"); return -EINVAL; } type = gc->irq.default_type; /* * Specifying a default trigger is a terrible idea if DT or ACPI is * used to configure the interrupts, as you may end up with * conflicting triggers. Tell the user, and reset to NONE. */ if (WARN(fwnode && type != IRQ_TYPE_NONE, "%pfw: Ignoring %u default trigger\n", fwnode, type)) type = IRQ_TYPE_NONE; gc->irq.default_type = type; gc->irq.lock_key = lock_key; gc->irq.request_key = request_key; /* If a parent irqdomain is provided, let's build a hierarchy */ if (gpiochip_hierarchy_is_hierarchical(gc)) { domain = gpiochip_hierarchy_create_domain(gc); } else { domain = gpiochip_simple_create_domain(gc); } if (IS_ERR(domain)) return PTR_ERR(domain); if (gc->irq.parent_handler) { for (i = 0; i < gc->irq.num_parents; i++) { void *data; if (gc->irq.per_parent_data) data = gc->irq.parent_handler_data_array[i]; else data = gc->irq.parent_handler_data ?: gc; /* * The parent IRQ chip is already using the chip_data * for this IRQ chip, so our callbacks simply use the * handler_data. */ irq_set_chained_handler_and_data(gc->irq.parents[i], gc->irq.parent_handler, data); } } gpiochip_set_irq_hooks(gc); ret = gpiochip_irqchip_add_allocated_domain(gc, domain, false); if (ret) return ret; acpi_gpiochip_request_interrupts(gc); return 0; } /** * gpiochip_irqchip_remove() - removes an irqchip added to a gpiochip * @gc: the gpiochip to remove the irqchip from * * This is called only from gpiochip_remove() */ static void gpiochip_irqchip_remove(struct gpio_chip *gc) { struct irq_chip *irqchip = gc->irq.chip; unsigned int offset; acpi_gpiochip_free_interrupts(gc); if (irqchip && gc->irq.parent_handler) { struct gpio_irq_chip *irq = &gc->irq; unsigned int i; for (i = 0; i < irq->num_parents; i++) irq_set_chained_handler_and_data(irq->parents[i], NULL, NULL); } /* Remove all IRQ mappings and delete the domain */ if (!gc->irq.domain_is_allocated_externally && gc->irq.domain) { unsigned int irq; for (offset = 0; offset < gc->ngpio; offset++) { if (!gpiochip_irqchip_irq_valid(gc, offset)) continue; irq = irq_find_mapping(gc->irq.domain, offset); irq_dispose_mapping(irq); } irq_domain_remove(gc->irq.domain); } if (irqchip && !(irqchip->flags & IRQCHIP_IMMUTABLE)) { if (irqchip->irq_request_resources == gpiochip_irq_reqres) { irqchip->irq_request_resources = NULL; irqchip->irq_release_resources = NULL; } if (irqchip->irq_enable == gpiochip_irq_enable) { irqchip->irq_enable = gc->irq.irq_enable; irqchip->irq_disable = gc->irq.irq_disable; } } gc->irq.irq_enable = NULL; gc->irq.irq_disable = NULL; gc->irq.chip = NULL; gpiochip_irqchip_free_valid_mask(gc); } /** * gpiochip_irqchip_add_domain() - adds an irqdomain to a gpiochip * @gc: the gpiochip to add the irqchip to * @domain: the irqdomain to add to the gpiochip * * This function adds an IRQ domain to the gpiochip. * * Returns: * 0 on success, or negative errno on failure. */ int gpiochip_irqchip_add_domain(struct gpio_chip *gc, struct irq_domain *domain) { return gpiochip_irqchip_add_allocated_domain(gc, domain, true); } EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_domain); #else /* CONFIG_GPIOLIB_IRQCHIP */ static inline int gpiochip_add_irqchip(struct gpio_chip *gc, struct lock_class_key *lock_key, struct lock_class_key *request_key) { return 0; } static void gpiochip_irqchip_remove(struct gpio_chip *gc) {} static inline int gpiochip_irqchip_init_hw(struct gpio_chip *gc) { return 0; } static inline int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gc) { return 0; } static inline void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gc) { } #endif /* CONFIG_GPIOLIB_IRQCHIP */ /** * gpiochip_generic_request() - request the gpio function for a pin * @gc: the gpiochip owning the GPIO * @offset: the offset of the GPIO to request for GPIO function * * Returns: * 0 on success, or negative errno on failure. */ int gpiochip_generic_request(struct gpio_chip *gc, unsigned int offset) { #ifdef CONFIG_PINCTRL if (list_empty(&gc->gpiodev->pin_ranges)) return 0; #endif return pinctrl_gpio_request(gc, offset); } EXPORT_SYMBOL_GPL(gpiochip_generic_request); /** * gpiochip_generic_free() - free the gpio function from a pin * @gc: the gpiochip to request the gpio function for * @offset: the offset of the GPIO to free from GPIO function */ void gpiochip_generic_free(struct gpio_chip *gc, unsigned int offset) { #ifdef CONFIG_PINCTRL if (list_empty(&gc->gpiodev->pin_ranges)) return; #endif pinctrl_gpio_free(gc, offset); } EXPORT_SYMBOL_GPL(gpiochip_generic_free); /** * gpiochip_generic_config() - apply configuration for a pin * @gc: the gpiochip owning the GPIO * @offset: the offset of the GPIO to apply the configuration * @config: the configuration to be applied * * Returns: * 0 on success, or negative errno on failure. */ int gpiochip_generic_config(struct gpio_chip *gc, unsigned int offset, unsigned long config) { #ifdef CONFIG_PINCTRL if (list_empty(&gc->gpiodev->pin_ranges)) return -ENOTSUPP; #endif return pinctrl_gpio_set_config(gc, offset, config); } EXPORT_SYMBOL_GPL(gpiochip_generic_config); #ifdef CONFIG_PINCTRL /** * gpiochip_add_pingroup_range() - add a range for GPIO <-> pin mapping * @gc: the gpiochip to add the range for * @pctldev: the pin controller to map to * @gpio_offset: the start offset in the current gpio_chip number space * @pin_group: name of the pin group inside the pin controller * * Calling this function directly from a DeviceTree-supported * pinctrl driver is DEPRECATED. Please see Section 2.1 of * Documentation/devicetree/bindings/gpio/gpio.txt on how to * bind pinctrl and gpio drivers via the "gpio-ranges" property. * * Returns: * 0 on success, or negative errno on failure. */ int gpiochip_add_pingroup_range(struct gpio_chip *gc, struct pinctrl_dev *pctldev, unsigned int gpio_offset, const char *pin_group) { struct gpio_pin_range *pin_range; struct gpio_device *gdev = gc->gpiodev; int ret; pin_range = kzalloc_obj(*pin_range); if (!pin_range) return -ENOMEM; /* Use local offset as range ID */ pin_range->range.id = gpio_offset; pin_range->range.gc = gc; pin_range->range.name = gc->label; pin_range->range.base = gdev->base + gpio_offset; pin_range->pctldev = pctldev; ret = pinctrl_get_group_pins(pctldev, pin_group, &pin_range->range.pins, &pin_range->range.npins); if (ret < 0) { kfree(pin_range); return ret; } pinctrl_add_gpio_range(pctldev, &pin_range->range); gpiochip_dbg(gc, "created GPIO range %d->%d ==> %s PINGRP %s\n", gpio_offset, gpio_offset + pin_range->range.npins - 1, pinctrl_dev_get_devname(pctldev), pin_group); list_add_tail(&pin_range->node, &gdev->pin_ranges); return 0; } EXPORT_SYMBOL_GPL(gpiochip_add_pingroup_range); /** * gpiochip_add_pin_range_with_pins() - add a range for GPIO <-> pin mapping * @gc: the gpiochip to add the range for * @pinctl_name: the dev_name() of the pin controller to map to * @gpio_offset: the start offset in the current gpio_chip number space * @pin_offset: the start offset in the pin controller number space * @pins: the list of non consecutive pins to accumulate in this range (if not * NULL, pin_offset is ignored by pinctrl core) * @npins: the number of pins from the offset of each pin space (GPIO and * pin controller) to accumulate in this range * * Calling this function directly from a DeviceTree-supported * pinctrl driver is DEPRECATED. Please see Section 2.1 of * Documentation/devicetree/bindings/gpio/gpio.txt on how to * bind pinctrl and gpio drivers via the "gpio-ranges" property. * * Returns: * 0 on success, or a negative errno on failure. */ int gpiochip_add_pin_range_with_pins(struct gpio_chip *gc, const char *pinctl_name, unsigned int gpio_offset, unsigned int pin_offset, unsigned int const *pins, unsigned int npins) { struct gpio_pin_range *pin_range; struct gpio_device *gdev = gc->gpiodev; int ret; pin_range = kzalloc_obj(*pin_range); if (!pin_range) return -ENOMEM; /* Use local offset as range ID */ pin_range->range.id = gpio_offset; pin_range->range.gc = gc; pin_range->range.name = gc->label; pin_range->range.base = gdev->base + gpio_offset; pin_range->range.pin_base = pin_offset; pin_range->range.pins = pins; pin_range->range.npins = npins; pin_range->pctldev = pinctrl_find_and_add_gpio_range(pinctl_name, &pin_range->range); if (IS_ERR(pin_range->pctldev)) { ret = PTR_ERR(pin_range->pctldev); gpiochip_err(gc, "could not create pin range\n"); kfree(pin_range); return ret; } if (pin_range->range.pins) gpiochip_dbg(gc, "created GPIO range %d->%d ==> %s %d sparse PIN range { %d, ... }", gpio_offset, gpio_offset + npins - 1, pinctl_name, npins, pins[0]); else gpiochip_dbg(gc, "created GPIO range %d->%d ==> %s PIN %d->%d\n", gpio_offset, gpio_offset + npins - 1, pinctl_name, pin_offset, pin_offset + npins - 1); list_add_tail(&pin_range->node, &gdev->pin_ranges); return 0; } EXPORT_SYMBOL_GPL(gpiochip_add_pin_range_with_pins); /** * gpiochip_remove_pin_ranges() - remove all the GPIO <-> pin mappings * @gc: the chip to remove all the mappings for */ void gpiochip_remove_pin_ranges(struct gpio_chip *gc) { struct gpio_pin_range *pin_range, *tmp; struct gpio_device *gdev = gc->gpiodev; list_for_each_entry_safe(pin_range, tmp, &gdev->pin_ranges, node) { list_del(&pin_range->node); pinctrl_remove_gpio_range(pin_range->pctldev, &pin_range->range); kfree(pin_range); } } EXPORT_SYMBOL_GPL(gpiochip_remove_pin_ranges); #endif /* CONFIG_PINCTRL */ /* These "optional" allocation calls help prevent drivers from stomping * on each other, and help provide better diagnostics in debugfs. * They're called even less than the "set direction" calls. */ int gpiod_request_commit(struct gpio_desc *desc, const char *label) { unsigned int offset; int ret; CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; if (test_and_set_bit(GPIOD_FLAG_REQUESTED, &desc->flags)) return -EBUSY; offset = gpiod_hwgpio(desc); if (!gpiochip_line_is_valid(guard.gc, offset)) { ret = -EINVAL; goto out_clear_bit; } /* NOTE: gpio_request() can be called in early boot, * before IRQs are enabled, for non-sleeping (SOC) GPIOs. */ if (guard.gc->request) { ret = guard.gc->request(guard.gc, offset); if (ret > 0) ret = -EBADE; if (ret) goto out_clear_bit; } if (guard.gc->get_direction) gpiod_get_direction(desc); ret = desc_set_label(desc, label ? : "?"); if (ret) goto out_clear_bit; return 0; out_clear_bit: clear_bit(GPIOD_FLAG_REQUESTED, &desc->flags); return ret; } int gpiod_request(struct gpio_desc *desc, const char *label) { int ret = -EPROBE_DEFER; VALIDATE_DESC(desc); if (try_module_get(desc->gdev->owner)) { ret = gpiod_request_commit(desc, label); if (ret) module_put(desc->gdev->owner); else gpio_device_get(desc->gdev); } if (ret) gpiod_dbg(desc, "%s: status %d\n", __func__, ret); return ret; } void gpiod_free_commit(struct gpio_desc *desc) { unsigned long flags; might_sleep(); CLASS(gpio_chip_guard, guard)(desc); flags = READ_ONCE(desc->flags); if (guard.gc && test_bit(GPIOD_FLAG_REQUESTED, &flags)) { if (guard.gc->free) guard.gc->free(guard.gc, gpiod_hwgpio(desc)); clear_bit(GPIOD_FLAG_ACTIVE_LOW, &flags); clear_bit(GPIOD_FLAG_REQUESTED, &flags); clear_bit(GPIOD_FLAG_OPEN_DRAIN, &flags); clear_bit(GPIOD_FLAG_OPEN_SOURCE, &flags); clear_bit(GPIOD_FLAG_PULL_UP, &flags); clear_bit(GPIOD_FLAG_PULL_DOWN, &flags); clear_bit(GPIOD_FLAG_BIAS_DISABLE, &flags); clear_bit(GPIOD_FLAG_EDGE_RISING, &flags); clear_bit(GPIOD_FLAG_EDGE_FALLING, &flags); clear_bit(GPIOD_FLAG_IS_HOGGED, &flags); #ifdef CONFIG_OF_DYNAMIC WRITE_ONCE(desc->hog, NULL); #endif desc_set_label(desc, NULL); WRITE_ONCE(desc->flags, flags); #ifdef CONFIG_GPIO_CDEV WRITE_ONCE(desc->debounce_period_us, 0); #endif gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_RELEASED); } } void gpiod_free(struct gpio_desc *desc) { VALIDATE_DESC_VOID(desc); gpiod_free_commit(desc); module_put(desc->gdev->owner); gpio_device_put(desc->gdev); } /** * gpiochip_dup_line_label - Get a copy of the consumer label. * @gc: GPIO chip controlling this line. * @offset: Hardware offset of the line. * * Returns: * Pointer to a copy of the consumer label if the line is requested or NULL * if it's not. If a valid pointer was returned, it must be freed using * kfree(). In case of a memory allocation error, the function returns %ENOMEM. * * Must not be called from atomic context. */ char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset) { struct gpio_desc *desc; char *label; desc = gpiochip_get_desc(gc, offset); if (IS_ERR(desc)) return NULL; if (!test_bit(GPIOD_FLAG_REQUESTED, &desc->flags)) return NULL; guard(srcu)(&desc->gdev->desc_srcu); label = kstrdup(gpiod_get_label(desc), GFP_KERNEL); if (!label) return ERR_PTR(-ENOMEM); return label; } EXPORT_SYMBOL_GPL(gpiochip_dup_line_label); static inline const char *function_name_or_default(const char *con_id) { return con_id ?: "(default)"; } /** * gpiochip_request_own_desc - Allow GPIO chip to request its own descriptor * @gc: GPIO chip * @hwnum: hardware number of the GPIO for which to request the descriptor * @label: label for the GPIO * @lflags: lookup flags for this GPIO or 0 if default, this can be used to * specify things like line inversion semantics with the machine flags * such as GPIO_OUT_LOW * @dflags: descriptor request flags for this GPIO or 0 if default, this * can be used to specify consumer semantics such as open drain * * Function allows GPIO chip drivers to request and use their own GPIO * descriptors via gpiolib API. Difference to gpiod_request() is that this * function will not increase reference count of the GPIO chip module. This * allows the GPIO chip module to be unloaded as needed (we assume that the * GPIO chip driver handles freeing the GPIOs it has requested). * * Returns: * A pointer to the GPIO descriptor, or an ERR_PTR()-encoded negative error * code on failure. */ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, unsigned int hwnum, const char *label, enum gpio_lookup_flags lflags, enum gpiod_flags dflags) { struct gpio_desc *desc = gpiochip_get_desc(gc, hwnum); const char *name = function_name_or_default(label); int ret; if (IS_ERR(desc)) { gpiochip_err(gc, "failed to get GPIO %s descriptor\n", name); return desc; } ret = gpiod_request_commit(desc, label); if (ret < 0) return ERR_PTR(ret); ret = gpiod_configure_flags(desc, label, lflags, dflags); if (ret) { gpiod_free_commit(desc); gpiochip_err(gc, "setup of own GPIO %s failed\n", name); return ERR_PTR(ret); } gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_REQUESTED); return desc; } EXPORT_SYMBOL_GPL(gpiochip_request_own_desc); /** * gpiochip_free_own_desc - Free GPIO requested by the chip driver * @desc: GPIO descriptor to free * * Function frees the given GPIO requested previously with * gpiochip_request_own_desc(). */ void gpiochip_free_own_desc(struct gpio_desc *desc) { if (desc) gpiod_free_commit(desc); } EXPORT_SYMBOL_GPL(gpiochip_free_own_desc); /* * Drivers MUST set GPIO direction before making get/set calls. In * some cases this is done in early boot, before IRQs are enabled. * * As a rule these aren't called more than once (except for drivers * using the open-drain emulation idiom) so these are natural places * to accumulate extra debugging checks. Note that we can't (yet) * rely on gpio_request() having been called beforehand. */ int gpio_do_set_config(struct gpio_desc *desc, unsigned long config) { int ret; CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; if (!guard.gc->set_config) return -ENOTSUPP; ret = guard.gc->set_config(guard.gc, gpiod_hwgpio(desc), config); if (ret > 0) ret = -EBADE; #ifdef CONFIG_GPIO_CDEV /* * Special case - if we're setting debounce period, we need to store * it in the descriptor in case user-space wants to know it. */ if (!ret && pinconf_to_config_param(config) == PIN_CONFIG_INPUT_DEBOUNCE) WRITE_ONCE(desc->debounce_period_us, pinconf_to_config_argument(config)); #endif return ret; } static int gpio_set_config_with_argument(struct gpio_desc *desc, enum pin_config_param mode, u32 argument) { unsigned long config; config = pinconf_to_config_packed(mode, argument); return gpio_do_set_config(desc, config); } static int gpio_set_config_with_argument_optional(struct gpio_desc *desc, enum pin_config_param mode, u32 argument) { struct device *dev = &desc->gdev->dev; int gpio = gpiod_hwgpio(desc); int ret; ret = gpio_set_config_with_argument(desc, mode, argument); if (ret != -ENOTSUPP) return ret; switch (mode) { case PIN_CONFIG_PERSIST_STATE: dev_dbg(dev, "Persistence not supported for GPIO %d\n", gpio); break; default: break; } return 0; } static int gpio_set_config(struct gpio_desc *desc, enum pin_config_param mode) { return gpio_set_config_with_argument(desc, mode, 0); } static int gpio_set_bias(struct gpio_desc *desc) { enum pin_config_param bias; unsigned long flags; unsigned int arg; flags = READ_ONCE(desc->flags); if (test_bit(GPIOD_FLAG_BIAS_DISABLE, &flags)) bias = PIN_CONFIG_BIAS_DISABLE; else if (test_bit(GPIOD_FLAG_PULL_UP, &flags)) bias = PIN_CONFIG_BIAS_PULL_UP; else if (test_bit(GPIOD_FLAG_PULL_DOWN, &flags)) bias = PIN_CONFIG_BIAS_PULL_DOWN; else return 0; switch (bias) { case PIN_CONFIG_BIAS_PULL_DOWN: case PIN_CONFIG_BIAS_PULL_UP: arg = 1; break; default: arg = 0; break; } return gpio_set_config_with_argument_optional(desc, bias, arg); } /** * gpio_set_debounce_timeout() - Set debounce timeout * @desc: GPIO descriptor to set the debounce timeout * @debounce: Debounce timeout in microseconds * * The function calls the certain GPIO driver to set debounce timeout * in the hardware. * * Returns: * 0 on success, or negative errno on failure. */ int gpio_set_debounce_timeout(struct gpio_desc *desc, unsigned int debounce) { int ret; ret = gpio_set_config_with_argument_optional(desc, PIN_CONFIG_INPUT_DEBOUNCE, debounce); if (!ret) gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_CONFIG); return ret; } static int gpiochip_direction_input(struct gpio_chip *gc, unsigned int offset) { int ret; lockdep_assert_held(&gc->gpiodev->srcu); if (WARN_ON(!gc->direction_input)) return -EOPNOTSUPP; ret = gc->direction_input(gc, offset); if (ret > 0) ret = -EBADE; return ret; } static int gpiochip_direction_output(struct gpio_chip *gc, unsigned int offset, int value) { int ret; lockdep_assert_held(&gc->gpiodev->srcu); if (WARN_ON(!gc->direction_output)) return -EOPNOTSUPP; ret = gc->direction_output(gc, offset, value); if (ret > 0) ret = -EBADE; return ret; } /** * gpiod_direction_input - set the GPIO direction to input * @desc: GPIO to set to input * * Set the direction of the passed GPIO to input, such as gpiod_get_value() can * be called safely on it. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_direction_input(struct gpio_desc *desc) { int ret; VALIDATE_DESC(desc); ret = gpiod_direction_input_nonotify(desc); if (ret == 0) gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_CONFIG); return ret; } EXPORT_SYMBOL_GPL(gpiod_direction_input); int gpiod_direction_input_nonotify(struct gpio_desc *desc) { int ret = 0, dir; CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; /* * It is legal to have no .get() and .direction_input() specified if * the chip is output-only, but you can't specify .direction_input() * and not support the .get() operation, that doesn't make sense. */ if (!guard.gc->get && guard.gc->direction_input) { gpiod_warn(desc, "%s: missing get() but have direction_input()\n", __func__); return -EIO; } /* * If we have a .direction_input() callback, things are simple, * just call it. Else we are some input-only chip so try to check the * direction (if .get_direction() is supported) else we silently * assume we are in input mode after this. */ if (guard.gc->direction_input) { ret = gpiochip_direction_input(guard.gc, gpiod_hwgpio(desc)); } else if (guard.gc->get_direction) { dir = gpiochip_get_direction(guard.gc, gpiod_hwgpio(desc)); if (dir < 0) return dir; if (dir != GPIO_LINE_DIRECTION_IN) { gpiod_warn(desc, "%s: missing direction_input() operation and line is output\n", __func__); return -EIO; } } if (ret == 0) { clear_bit(GPIOD_FLAG_IS_OUT, &desc->flags); ret = gpio_set_bias(desc); } trace_gpio_direction(desc_to_gpio(desc), 1, ret); return ret; } static int gpiochip_set(struct gpio_chip *gc, unsigned int offset, int value) { int ret; lockdep_assert_held(&gc->gpiodev->srcu); if (WARN_ON(unlikely(!gc->set))) return -EOPNOTSUPP; ret = gc->set(gc, offset, value); if (ret > 0) ret = -EBADE; return ret; } static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value) { int val = !!value, ret = 0, dir; CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; /* * It's OK not to specify .direction_output() if the gpiochip is * output-only, but if there is then not even a .set() operation it * is pretty tricky to drive the output line. */ if (!guard.gc->set && !guard.gc->direction_output) { gpiod_warn(desc, "%s: missing set() and direction_output() operations\n", __func__); return -EIO; } if (guard.gc->direction_output) { ret = gpiochip_direction_output(guard.gc, gpiod_hwgpio(desc), val); } else { /* Check that we are in output mode if we can */ if (guard.gc->get_direction) { dir = gpiochip_get_direction(guard.gc, gpiod_hwgpio(desc)); if (dir < 0) return dir; if (dir != GPIO_LINE_DIRECTION_OUT) { gpiod_warn(desc, "%s: missing direction_output() operation\n", __func__); return -EIO; } } /* * If we can't actively set the direction, we are some * output-only chip, so just drive the output as desired. */ ret = gpiochip_set(guard.gc, gpiod_hwgpio(desc), val); if (ret) return ret; } if (!ret) set_bit(GPIOD_FLAG_IS_OUT, &desc->flags); trace_gpio_value(desc_to_gpio(desc), 0, val); trace_gpio_direction(desc_to_gpio(desc), 0, ret); return ret; } /** * gpiod_direction_output_raw - set the GPIO direction to output * @desc: GPIO to set to output * @value: initial output value of the GPIO * * Set the direction of the passed GPIO to output, such as gpiod_set_value() can * be called safely on it. The initial value of the output must be specified * as raw value on the physical line without regard for the ACTIVE_LOW status. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_direction_output_raw(struct gpio_desc *desc, int value) { int ret; VALIDATE_DESC(desc); ret = gpiod_direction_output_raw_commit(desc, value); if (ret == 0) gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_CONFIG); return ret; } EXPORT_SYMBOL_GPL(gpiod_direction_output_raw); /** * gpiod_direction_output - set the GPIO direction to output * @desc: GPIO to set to output * @value: initial output value of the GPIO * * Set the direction of the passed GPIO to output, such as gpiod_set_value() can * be called safely on it. The initial value of the output must be specified * as the logical value of the GPIO, i.e. taking its ACTIVE_LOW status into * account. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_direction_output(struct gpio_desc *desc, int value) { int ret; VALIDATE_DESC(desc); ret = gpiod_direction_output_nonotify(desc, value); if (ret == 0) gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_CONFIG); return ret; } EXPORT_SYMBOL_GPL(gpiod_direction_output); int gpiod_direction_output_nonotify(struct gpio_desc *desc, int value) { unsigned long flags; int ret; flags = READ_ONCE(desc->flags); if (test_bit(GPIOD_FLAG_ACTIVE_LOW, &flags)) value = !value; else value = !!value; /* GPIOs used for enabled IRQs shall not be set as output */ if (test_bit(GPIOD_FLAG_USED_AS_IRQ, &flags) && test_bit(GPIOD_FLAG_IRQ_IS_ENABLED, &flags)) { gpiod_err(desc, "%s: tried to set a GPIO tied to an IRQ as output\n", __func__); return -EIO; } if (test_bit(GPIOD_FLAG_OPEN_DRAIN, &flags)) { /* First see if we can enable open drain in hardware */ ret = gpio_set_config(desc, PIN_CONFIG_DRIVE_OPEN_DRAIN); if (!ret) goto set_output_value; /* Emulate open drain by not actively driving the line high */ if (value) goto set_output_flag; } else if (test_bit(GPIOD_FLAG_OPEN_SOURCE, &flags)) { ret = gpio_set_config(desc, PIN_CONFIG_DRIVE_OPEN_SOURCE); if (!ret) goto set_output_value; /* Emulate open source by not actively driving the line low */ if (!value) goto set_output_flag; } else { gpio_set_config(desc, PIN_CONFIG_DRIVE_PUSH_PULL); } set_output_value: ret = gpio_set_bias(desc); if (ret) return ret; return gpiod_direction_output_raw_commit(desc, value); set_output_flag: ret = gpiod_direction_input_nonotify(desc); if (ret) return ret; /* * When emulating open-source or open-drain functionalities by not * actively driving the line (setting mode to input) we still need to * set the IS_OUT flag or otherwise we won't be able to set the line * value anymore. */ set_bit(GPIOD_FLAG_IS_OUT, &desc->flags); return 0; } #if IS_ENABLED(CONFIG_HTE) /** * gpiod_enable_hw_timestamp_ns - Enable hardware timestamp in nanoseconds. * * @desc: GPIO to enable. * @flags: Flags related to GPIO edge. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags) { int ret; VALIDATE_DESC(desc); CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; if (!guard.gc->en_hw_timestamp) { gpiod_warn(desc, "%s: hw ts not supported\n", __func__); return -ENOTSUPP; } ret = guard.gc->en_hw_timestamp(guard.gc, gpiod_hwgpio(desc), flags); if (ret) gpiod_warn(desc, "%s: hw ts request failed\n", __func__); return ret; } EXPORT_SYMBOL_GPL(gpiod_enable_hw_timestamp_ns); /** * gpiod_disable_hw_timestamp_ns - Disable hardware timestamp. * * @desc: GPIO to disable. * @flags: Flags related to GPIO edge, same value as used during enable call. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags) { int ret; VALIDATE_DESC(desc); CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; if (!guard.gc->dis_hw_timestamp) { gpiod_warn(desc, "%s: hw ts not supported\n", __func__); return -ENOTSUPP; } ret = guard.gc->dis_hw_timestamp(guard.gc, gpiod_hwgpio(desc), flags); if (ret) gpiod_warn(desc, "%s: hw ts release failed\n", __func__); return ret; } EXPORT_SYMBOL_GPL(gpiod_disable_hw_timestamp_ns); #endif /* CONFIG_HTE */ /** * gpiod_set_config - sets @config for a GPIO * @desc: descriptor of the GPIO for which to set the configuration * @config: Same packed config format as generic pinconf * * Returns: * 0 on success, %-ENOTSUPP if the controller doesn't support setting the * configuration. */ int gpiod_set_config(struct gpio_desc *desc, unsigned long config) { int ret; VALIDATE_DESC(desc); ret = gpio_do_set_config(desc, config); if (!ret) { /* These are the only options we notify the userspace about. */ switch (pinconf_to_config_param(config)) { case PIN_CONFIG_BIAS_DISABLE: case PIN_CONFIG_BIAS_PULL_DOWN: case PIN_CONFIG_BIAS_PULL_UP: case PIN_CONFIG_DRIVE_OPEN_DRAIN: case PIN_CONFIG_DRIVE_OPEN_SOURCE: case PIN_CONFIG_DRIVE_PUSH_PULL: case PIN_CONFIG_INPUT_DEBOUNCE: gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_CONFIG); break; default: break; } } return ret; } EXPORT_SYMBOL_GPL(gpiod_set_config); /** * gpiod_set_debounce - sets @debounce time for a GPIO * @desc: descriptor of the GPIO for which to set debounce time * @debounce: debounce time in microseconds * * Returns: * 0 on success, %-ENOTSUPP if the controller doesn't support setting the * debounce time. */ int gpiod_set_debounce(struct gpio_desc *desc, unsigned int debounce) { unsigned long config; config = pinconf_to_config_packed(PIN_CONFIG_INPUT_DEBOUNCE, debounce); return gpiod_set_config(desc, config); } EXPORT_SYMBOL_GPL(gpiod_set_debounce); /** * gpiod_set_transitory - Lose or retain GPIO state on suspend or reset * @desc: descriptor of the GPIO for which to configure persistence * @transitory: True to lose state on suspend or reset, false for persistence * * Returns: * 0 on success, otherwise a negative error code. */ int gpiod_set_transitory(struct gpio_desc *desc, bool transitory) { VALIDATE_DESC(desc); /* * Handle GPIOD_FLAG_TRANSITORY first, enabling queries to gpiolib for * persistence state. */ assign_bit(GPIOD_FLAG_TRANSITORY, &desc->flags, transitory); /* If the driver supports it, set the persistence state now */ return gpio_set_config_with_argument_optional(desc, PIN_CONFIG_PERSIST_STATE, !transitory); } /** * gpiod_is_active_low - test whether a GPIO is active-low or not * @desc: the gpio descriptor to test * * Returns: * 1 if the GPIO is active-low, 0 otherwise. */ int gpiod_is_active_low(const struct gpio_desc *desc) { VALIDATE_DESC(desc); return test_bit(GPIOD_FLAG_ACTIVE_LOW, &desc->flags); } EXPORT_SYMBOL_GPL(gpiod_is_active_low); /** * gpiod_toggle_active_low - toggle whether a GPIO is active-low or not * @desc: the gpio descriptor to change */ void gpiod_toggle_active_low(struct gpio_desc *desc) { VALIDATE_DESC_VOID(desc); change_bit(GPIOD_FLAG_ACTIVE_LOW, &desc->flags); gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_CONFIG); } EXPORT_SYMBOL_GPL(gpiod_toggle_active_low); static int gpiochip_get(struct gpio_chip *gc, unsigned int offset) { int ret; lockdep_assert_held(&gc->gpiodev->srcu); /* Make sure this is called after checking for gc->get(). */ ret = gc->get(gc, offset); if (ret > 1) { gpiochip_warn(gc, "invalid return value from gc->get(): %d, consider fixing the driver\n", ret); ret = !!ret; } return ret; } static int gpio_chip_get_value(struct gpio_chip *gc, const struct gpio_desc *desc) { return gc->get ? gpiochip_get(gc, gpiod_hwgpio(desc)) : -EIO; } /* I/O calls are only valid after configuration completed; the relevant * "is this a valid GPIO" error checks should already have been done. * * "Get" operations are often inlinable as reading a pin value register, * and masking the relevant bit in that register. * * When "set" operations are inlinable, they involve writing that mask to * one register to set a low value, or a different register to set it high. * Otherwise locking is needed, so there may be little value to inlining. * *------------------------------------------------------------------------ * * IMPORTANT!!! The hot paths -- get/set value -- assume that callers * have requested the GPIO. That can include implicit requesting by * a direction setting call. Marking a gpio as requested locks its chip * in memory, guaranteeing that these table lookups need no more locking * and that gpiochip_remove() will fail. * * REVISIT when debugging, consider adding some instrumentation to ensure * that the GPIO was actually requested. */ static int gpiod_get_raw_value_commit(const struct gpio_desc *desc) { struct gpio_device *gdev; struct gpio_chip *gc; int value; /* FIXME Unable to use gpio_chip_guard due to const desc. */ gdev = desc->gdev; guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); if (!gc) return -ENODEV; value = gpio_chip_get_value(gc, desc); value = value < 0 ? value : !!value; trace_gpio_value(desc_to_gpio(desc), 1, value); return value; } static int gpio_chip_get_multiple(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits) { lockdep_assert_held(&gc->gpiodev->srcu); if (gc->get_multiple) { int ret; ret = gc->get_multiple(gc, mask, bits); if (ret > 0) return -EBADE; return ret; } if (gc->get) { int i, value; for_each_set_bit(i, mask, gc->ngpio) { value = gpiochip_get(gc, i); if (value < 0) return value; __assign_bit(i, bits, value); } return 0; } return -EIO; } /* The 'other' chip must be protected with its GPIO device's SRCU. */ static bool gpio_device_chip_cmp(struct gpio_device *gdev, struct gpio_chip *gc) { guard(srcu)(&gdev->srcu); return gc == srcu_dereference(gdev->chip, &gdev->srcu); } int gpiod_get_array_value_complex(bool raw, bool can_sleep, unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { struct gpio_chip *gc; int ret, i = 0; /* * Validate array_info against desc_array and its size. * It should immediately follow desc_array if both * have been obtained from the same gpiod_get_array() call. */ if (array_info && array_info->desc == desc_array && array_size <= array_info->size && (void *)array_info == desc_array + array_info->size) { if (!can_sleep) WARN_ON(array_info->gdev->can_sleep); guard(srcu)(&array_info->gdev->srcu); gc = srcu_dereference(array_info->gdev->chip, &array_info->gdev->srcu); if (!gc) return -ENODEV; ret = gpio_chip_get_multiple(gc, array_info->get_mask, value_bitmap); if (ret) return ret; if (!raw && !bitmap_empty(array_info->invert_mask, array_size)) bitmap_xor(value_bitmap, value_bitmap, array_info->invert_mask, array_size); i = find_first_zero_bit(array_info->get_mask, array_size); if (i == array_size) return 0; } else { array_info = NULL; } while (i < array_size) { DECLARE_BITMAP(fastpath_mask, FASTPATH_NGPIO); DECLARE_BITMAP(fastpath_bits, FASTPATH_NGPIO); unsigned long *mask, *bits; int first, j; CLASS(gpio_chip_guard, guard)(desc_array[i]); if (!guard.gc) return -ENODEV; if (likely(guard.gc->ngpio <= FASTPATH_NGPIO)) { mask = fastpath_mask; bits = fastpath_bits; } else { gfp_t flags = can_sleep ? GFP_KERNEL : GFP_ATOMIC; mask = bitmap_alloc(guard.gc->ngpio, flags); if (!mask) return -ENOMEM; bits = bitmap_alloc(guard.gc->ngpio, flags); if (!bits) { bitmap_free(mask); return -ENOMEM; } } bitmap_zero(mask, guard.gc->ngpio); if (!can_sleep) WARN_ON(guard.gc->can_sleep); /* collect all inputs belonging to the same chip */ first = i; do { const struct gpio_desc *desc = desc_array[i]; int hwgpio = gpiod_hwgpio(desc); __set_bit(hwgpio, mask); i++; if (array_info) i = find_next_zero_bit(array_info->get_mask, array_size, i); } while ((i < array_size) && gpio_device_chip_cmp(desc_array[i]->gdev, guard.gc)); ret = gpio_chip_get_multiple(guard.gc, mask, bits); if (ret) { if (mask != fastpath_mask) bitmap_free(mask); if (bits != fastpath_bits) bitmap_free(bits); return ret; } for (j = first; j < i; ) { const struct gpio_desc *desc = desc_array[j]; int hwgpio = gpiod_hwgpio(desc); int value = test_bit(hwgpio, bits); if (!raw && test_bit(GPIOD_FLAG_ACTIVE_LOW, &desc->flags)) value = !value; __assign_bit(j, value_bitmap, value); trace_gpio_value(desc_to_gpio(desc), 1, value); j++; if (array_info) j = find_next_zero_bit(array_info->get_mask, i, j); } if (mask != fastpath_mask) bitmap_free(mask); if (bits != fastpath_bits) bitmap_free(bits); } return 0; } /** * gpiod_get_raw_value() - return a gpio's raw value * @desc: gpio whose value will be returned * * Returns: * The GPIO's raw value, i.e. the value of the physical line disregarding * its ACTIVE_LOW status, or negative errno on failure. * * This function can be called from contexts where we cannot sleep, and will * complain if the GPIO chip functions potentially sleep. */ int gpiod_get_raw_value(const struct gpio_desc *desc) { VALIDATE_DESC(desc); /* Should be using gpiod_get_raw_value_cansleep() */ WARN_ON(desc->gdev->can_sleep); return gpiod_get_raw_value_commit(desc); } EXPORT_SYMBOL_GPL(gpiod_get_raw_value); /** * gpiod_get_value() - return a gpio's value * @desc: gpio whose value will be returned * * Returns: * The GPIO's logical value, i.e. taking the ACTIVE_LOW status into * account, or negative errno on failure. * * This function can be called from contexts where we cannot sleep, and will * complain if the GPIO chip functions potentially sleep. */ int gpiod_get_value(const struct gpio_desc *desc) { int value; VALIDATE_DESC(desc); /* Should be using gpiod_get_value_cansleep() */ WARN_ON(desc->gdev->can_sleep); value = gpiod_get_raw_value_commit(desc); if (value < 0) return value; if (test_bit(GPIOD_FLAG_ACTIVE_LOW, &desc->flags)) value = !value; return value; } EXPORT_SYMBOL_GPL(gpiod_get_value); /** * gpiod_get_raw_array_value() - read raw values from an array of GPIOs * @array_size: number of elements in the descriptor array / value bitmap * @desc_array: array of GPIO descriptors whose values will be read * @array_info: information on applicability of fast bitmap processing path * @value_bitmap: bitmap to store the read values * * Read the raw values of the GPIOs, i.e. the values of the physical lines * without regard for their ACTIVE_LOW status. * * This function can be called from contexts where we cannot sleep, * and it will complain if the GPIO chip functions potentially sleep. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_get_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { if (!desc_array) return -EINVAL; return gpiod_get_array_value_complex(true, false, array_size, desc_array, array_info, value_bitmap); } EXPORT_SYMBOL_GPL(gpiod_get_raw_array_value); /** * gpiod_get_array_value() - read values from an array of GPIOs * @array_size: number of elements in the descriptor array / value bitmap * @desc_array: array of GPIO descriptors whose values will be read * @array_info: information on applicability of fast bitmap processing path * @value_bitmap: bitmap to store the read values * * Read the logical values of the GPIOs, i.e. taking their ACTIVE_LOW status * into account. * * This function can be called from contexts where we cannot sleep, * and it will complain if the GPIO chip functions potentially sleep. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_get_array_value(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { if (!desc_array) return -EINVAL; return gpiod_get_array_value_complex(false, false, array_size, desc_array, array_info, value_bitmap); } EXPORT_SYMBOL_GPL(gpiod_get_array_value); /* * gpio_set_open_drain_value_commit() - Set the open drain gpio's value. * @desc: gpio descriptor whose state need to be set. * @value: Non-zero for setting it HIGH otherwise it will set to LOW. */ static int gpio_set_open_drain_value_commit(struct gpio_desc *desc, bool value) { int ret = 0, offset = gpiod_hwgpio(desc); CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; if (value) { ret = gpiochip_direction_input(guard.gc, offset); } else { ret = gpiochip_direction_output(guard.gc, offset, 0); if (!ret) set_bit(GPIOD_FLAG_IS_OUT, &desc->flags); } trace_gpio_direction(desc_to_gpio(desc), value, ret); if (ret < 0) gpiod_err(desc, "%s: Error in set_value for open drain err %d\n", __func__, ret); return ret; } /* * _gpio_set_open_source_value() - Set the open source gpio's value. * @desc: gpio descriptor whose state need to be set. * @value: Non-zero for setting it HIGH otherwise it will set to LOW. */ static int gpio_set_open_source_value_commit(struct gpio_desc *desc, bool value) { int ret = 0, offset = gpiod_hwgpio(desc); CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; if (value) { ret = gpiochip_direction_output(guard.gc, offset, 1); if (!ret) set_bit(GPIOD_FLAG_IS_OUT, &desc->flags); } else { ret = gpiochip_direction_input(guard.gc, offset); } trace_gpio_direction(desc_to_gpio(desc), !value, ret); if (ret < 0) gpiod_err(desc, "%s: Error in set_value for open source err %d\n", __func__, ret); return ret; } static int gpiod_set_raw_value_commit(struct gpio_desc *desc, bool value) { if (unlikely(!test_bit(GPIOD_FLAG_IS_OUT, &desc->flags))) return -EPERM; CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; trace_gpio_value(desc_to_gpio(desc), 0, value); return gpiochip_set(guard.gc, gpiod_hwgpio(desc), value); } /* * set multiple outputs on the same chip; * use the chip's set_multiple function if available; * otherwise set the outputs sequentially; * @chip: the GPIO chip we operate on * @mask: bit mask array; one bit per output; BITS_PER_LONG bits per word * defines which outputs are to be changed * @bits: bit value array; one bit per output; BITS_PER_LONG bits per word * defines the values the outputs specified by mask are to be set to * * Returns: 0 on success, negative error number on failure. */ static int gpiochip_set_multiple(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits) { unsigned int i; int ret; lockdep_assert_held(&gc->gpiodev->srcu); if (gc->set_multiple) { ret = gc->set_multiple(gc, mask, bits); if (ret > 0) ret = -EBADE; return ret; } /* set outputs if the corresponding mask bit is set */ for_each_set_bit(i, mask, gc->ngpio) { ret = gpiochip_set(gc, i, test_bit(i, bits)); if (ret) break; } return ret; } int gpiod_set_array_value_complex(bool raw, bool can_sleep, unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { struct gpio_chip *gc; int i = 0, ret; /* * Validate array_info against desc_array and its size. * It should immediately follow desc_array if both * have been obtained from the same gpiod_get_array() call. */ if (array_info && array_info->desc == desc_array && array_size <= array_info->size && (void *)array_info == desc_array + array_info->size) { if (!can_sleep) WARN_ON(array_info->gdev->can_sleep); for (i = 0; i < array_size; i++) { if (unlikely(!test_bit(GPIOD_FLAG_IS_OUT, &desc_array[i]->flags))) return -EPERM; } guard(srcu)(&array_info->gdev->srcu); gc = srcu_dereference(array_info->gdev->chip, &array_info->gdev->srcu); if (!gc) return -ENODEV; if (!raw && !bitmap_empty(array_info->invert_mask, array_size)) bitmap_xor(value_bitmap, value_bitmap, array_info->invert_mask, array_size); ret = gpiochip_set_multiple(gc, array_info->set_mask, value_bitmap); if (ret) return ret; i = find_first_zero_bit(array_info->set_mask, array_size); if (i == array_size) return 0; } else { array_info = NULL; } while (i < array_size) { DECLARE_BITMAP(fastpath_mask, FASTPATH_NGPIO); DECLARE_BITMAP(fastpath_bits, FASTPATH_NGPIO); unsigned long *mask, *bits; int count = 0; CLASS(gpio_chip_guard, guard)(desc_array[i]); if (!guard.gc) return -ENODEV; if (likely(guard.gc->ngpio <= FASTPATH_NGPIO)) { mask = fastpath_mask; bits = fastpath_bits; } else { gfp_t flags = can_sleep ? GFP_KERNEL : GFP_ATOMIC; mask = bitmap_alloc(guard.gc->ngpio, flags); if (!mask) return -ENOMEM; bits = bitmap_alloc(guard.gc->ngpio, flags); if (!bits) { bitmap_free(mask); return -ENOMEM; } } bitmap_zero(mask, guard.gc->ngpio); if (!can_sleep) WARN_ON(guard.gc->can_sleep); do { struct gpio_desc *desc = desc_array[i]; int hwgpio = gpiod_hwgpio(desc); int value = test_bit(i, value_bitmap); if (unlikely(!test_bit(GPIOD_FLAG_IS_OUT, &desc->flags))) return -EPERM; /* * Pins applicable for fast input but not for * fast output processing may have been already * inverted inside the fast path, skip them. */ if (!raw && !(array_info && test_bit(i, array_info->invert_mask)) && test_bit(GPIOD_FLAG_ACTIVE_LOW, &desc->flags)) value = !value; trace_gpio_value(desc_to_gpio(desc), 0, value); /* * collect all normal outputs belonging to the same chip * open drain and open source outputs are set individually */ if (test_bit(GPIOD_FLAG_OPEN_DRAIN, &desc->flags) && !raw) { gpio_set_open_drain_value_commit(desc, value); } else if (test_bit(GPIOD_FLAG_OPEN_SOURCE, &desc->flags) && !raw) { gpio_set_open_source_value_commit(desc, value); } else { __set_bit(hwgpio, mask); __assign_bit(hwgpio, bits, value); count++; } i++; if (array_info) i = find_next_zero_bit(array_info->set_mask, array_size, i); } while ((i < array_size) && gpio_device_chip_cmp(desc_array[i]->gdev, guard.gc)); /* push collected bits to outputs */ if (count != 0) { ret = gpiochip_set_multiple(guard.gc, mask, bits); if (ret) return ret; } if (mask != fastpath_mask) bitmap_free(mask); if (bits != fastpath_bits) bitmap_free(bits); } return 0; } /** * gpiod_set_raw_value() - assign a gpio's raw value * @desc: gpio whose value will be assigned * @value: value to assign * * Set the raw value of the GPIO, i.e. the value of its physical line without * regard for its ACTIVE_LOW status. * * This function can be called from contexts where we cannot sleep, and will * complain if the GPIO chip functions potentially sleep. * * Returns: * 0 on success, negative error number on failure. */ int gpiod_set_raw_value(struct gpio_desc *desc, int value) { VALIDATE_DESC(desc); /* Should be using gpiod_set_raw_value_cansleep() */ WARN_ON(desc->gdev->can_sleep); return gpiod_set_raw_value_commit(desc, value); } EXPORT_SYMBOL_GPL(gpiod_set_raw_value); /** * gpiod_set_value_nocheck() - set a GPIO line value without checking * @desc: the descriptor to set the value on * @value: value to set * * This sets the value of a GPIO line backing a descriptor, applying * different semantic quirks like active low and open drain/source * handling. * * Returns: * 0 on success, negative error number on failure. */ static int gpiod_set_value_nocheck(struct gpio_desc *desc, int value) { if (test_bit(GPIOD_FLAG_ACTIVE_LOW, &desc->flags)) value = !value; if (test_bit(GPIOD_FLAG_OPEN_DRAIN, &desc->flags)) return gpio_set_open_drain_value_commit(desc, value); else if (test_bit(GPIOD_FLAG_OPEN_SOURCE, &desc->flags)) return gpio_set_open_source_value_commit(desc, value); return gpiod_set_raw_value_commit(desc, value); } /** * gpiod_set_value() - assign a gpio's value * @desc: gpio whose value will be assigned * @value: value to assign * * Set the logical value of the GPIO, i.e. taking its ACTIVE_LOW, * OPEN_DRAIN and OPEN_SOURCE flags into account. * * This function can be called from contexts where we cannot sleep, and will * complain if the GPIO chip functions potentially sleep. * * Returns: * 0 on success, negative error number on failure. */ int gpiod_set_value(struct gpio_desc *desc, int value) { VALIDATE_DESC(desc); /* Should be using gpiod_set_value_cansleep() */ WARN_ON(desc->gdev->can_sleep); return gpiod_set_value_nocheck(desc, value); } EXPORT_SYMBOL_GPL(gpiod_set_value); /** * gpiod_set_raw_array_value() - assign values to an array of GPIOs * @array_size: number of elements in the descriptor array / value bitmap * @desc_array: array of GPIO descriptors whose values will be assigned * @array_info: information on applicability of fast bitmap processing path * @value_bitmap: bitmap of values to assign * * Set the raw values of the GPIOs, i.e. the values of the physical lines * without regard for their ACTIVE_LOW status. * * This function can be called from contexts where we cannot sleep, and will * complain if the GPIO chip functions potentially sleep. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_set_raw_array_value(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { if (!desc_array) return -EINVAL; return gpiod_set_array_value_complex(true, false, array_size, desc_array, array_info, value_bitmap); } EXPORT_SYMBOL_GPL(gpiod_set_raw_array_value); /** * gpiod_set_array_value() - assign values to an array of GPIOs * @array_size: number of elements in the descriptor array / value bitmap * @desc_array: array of GPIO descriptors whose values will be assigned * @array_info: information on applicability of fast bitmap processing path * @value_bitmap: bitmap of values to assign * * Set the logical values of the GPIOs, i.e. taking their ACTIVE_LOW status * into account. * * This function can be called from contexts where we cannot sleep, and will * complain if the GPIO chip functions potentially sleep. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_set_array_value(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { if (!desc_array) return -EINVAL; return gpiod_set_array_value_complex(false, false, array_size, desc_array, array_info, value_bitmap); } EXPORT_SYMBOL_GPL(gpiod_set_array_value); /** * gpiod_cansleep() - report whether gpio value access may sleep * @desc: gpio to check * * Returns: * 0 for non-sleepable, 1 for sleepable, or an error code in case of error. */ int gpiod_cansleep(const struct gpio_desc *desc) { VALIDATE_DESC(desc); return desc->gdev->can_sleep; } EXPORT_SYMBOL_GPL(gpiod_cansleep); /** * gpiod_set_consumer_name() - set the consumer name for the descriptor * @desc: gpio to set the consumer name on * @name: the new consumer name * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_set_consumer_name(struct gpio_desc *desc, const char *name) { int ret; VALIDATE_DESC(desc); ret = desc_set_label(desc, name); if (ret == 0) gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_CONFIG); return ret; } EXPORT_SYMBOL_GPL(gpiod_set_consumer_name); /** * gpiod_is_shared() - check if this GPIO can be shared by multiple consumers * @desc: GPIO to inspect * * Returns: * True if this GPIO can be shared by multiple consumers at once. False if it's * a regular, exclusive GPIO. * * Note: * This function returning true does not mean that this GPIO is currently being * shared. It means the GPIO core has registered the fact that the firmware * configuration indicates that it can be shared by multiple consumers and is * in charge of arbitrating the access. */ bool gpiod_is_shared(const struct gpio_desc *desc) { return test_bit(GPIOD_FLAG_SHARED_PROXY, &desc->flags); } EXPORT_SYMBOL_GPL(gpiod_is_shared); /** * gpiod_to_irq() - return the IRQ corresponding to a GPIO * @desc: gpio whose IRQ will be returned (already requested) * * Returns: * The IRQ corresponding to the passed GPIO, or an error code in case of error. */ int gpiod_to_irq(const struct gpio_desc *desc) { struct gpio_device *gdev; struct gpio_chip *gc; int offset; int ret; ret = validate_desc(desc, __func__); if (ret <= 0) return -EINVAL; gdev = desc->gdev; /* FIXME Cannot use gpio_chip_guard due to const desc. */ guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); if (!gc) return -ENODEV; offset = gpiod_hwgpio(desc); if (gc->to_irq) { ret = gc->to_irq(gc, offset); if (ret) return ret; /* Zero means NO_IRQ */ return -ENXIO; } #ifdef CONFIG_GPIOLIB_IRQCHIP if (gc->irq.chip) { /* * Avoid race condition with other code, which tries to lookup * an IRQ before the irqchip has been properly registered, * i.e. while gpiochip is still being brought up. */ return -EPROBE_DEFER; } #endif return -ENXIO; } EXPORT_SYMBOL_GPL(gpiod_to_irq); /** * gpiochip_lock_as_irq() - lock a GPIO to be used as IRQ * @gc: the chip the GPIO to lock belongs to * @offset: the offset of the GPIO to lock as IRQ * * This is used directly by GPIO drivers that want to lock down * a certain GPIO line to be used for IRQs. * * Returns: * 0 on success, or negative errno on failure. */ int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) { struct gpio_desc *desc; desc = gpiochip_get_desc(gc, offset); if (IS_ERR(desc)) return PTR_ERR(desc); /* * If it's fast: flush the direction setting if something changed * behind our back */ if (!gc->can_sleep && gc->get_direction) { int dir = gpiod_get_direction(desc); if (dir < 0) { gpiochip_err(gc, "%s: cannot get GPIO direction\n", __func__); return dir; } } /* To be valid for IRQ the line needs to be input or open drain */ if (test_bit(GPIOD_FLAG_IS_OUT, &desc->flags) && !test_bit(GPIOD_FLAG_OPEN_DRAIN, &desc->flags)) { gpiochip_err(gc, "%s: tried to flag a GPIO set as output for IRQ\n", __func__); return -EIO; } set_bit(GPIOD_FLAG_USED_AS_IRQ, &desc->flags); set_bit(GPIOD_FLAG_IRQ_IS_ENABLED, &desc->flags); return 0; } EXPORT_SYMBOL_GPL(gpiochip_lock_as_irq); /** * gpiochip_unlock_as_irq() - unlock a GPIO used as IRQ * @gc: the chip the GPIO to lock belongs to * @offset: the offset of the GPIO to lock as IRQ * * This is used directly by GPIO drivers that want to indicate * that a certain GPIO is no longer used exclusively for IRQ. */ void gpiochip_unlock_as_irq(struct gpio_chip *gc, unsigned int offset) { struct gpio_desc *desc; desc = gpiochip_get_desc(gc, offset); if (IS_ERR(desc)) return; clear_bit(GPIOD_FLAG_USED_AS_IRQ, &desc->flags); clear_bit(GPIOD_FLAG_IRQ_IS_ENABLED, &desc->flags); } EXPORT_SYMBOL_GPL(gpiochip_unlock_as_irq); void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset) { struct gpio_desc *desc = gpiochip_get_desc(gc, offset); if (!IS_ERR(desc) && !WARN_ON(!test_bit(GPIOD_FLAG_USED_AS_IRQ, &desc->flags))) clear_bit(GPIOD_FLAG_IRQ_IS_ENABLED, &desc->flags); } EXPORT_SYMBOL_GPL(gpiochip_disable_irq); void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset) { struct gpio_desc *desc = gpiochip_get_desc(gc, offset); if (!IS_ERR(desc) && !WARN_ON(!test_bit(GPIOD_FLAG_USED_AS_IRQ, &desc->flags))) { /* * We must not be output when using IRQ UNLESS we are * open drain. */ WARN_ON(test_bit(GPIOD_FLAG_IS_OUT, &desc->flags) && !test_bit(GPIOD_FLAG_OPEN_DRAIN, &desc->flags)); set_bit(GPIOD_FLAG_IRQ_IS_ENABLED, &desc->flags); } } EXPORT_SYMBOL_GPL(gpiochip_enable_irq); bool gpiochip_line_is_irq(struct gpio_chip *gc, unsigned int offset) { if (offset >= gc->ngpio) return false; return test_bit(GPIOD_FLAG_USED_AS_IRQ, &gc->gpiodev->descs[offset].flags); } EXPORT_SYMBOL_GPL(gpiochip_line_is_irq); int gpiochip_reqres_irq(struct gpio_chip *gc, unsigned int offset) { int ret; if (!try_module_get(gc->gpiodev->owner)) return -ENODEV; ret = gpiochip_lock_as_irq(gc, offset); if (ret) { gpiochip_err(gc, "unable to lock HW IRQ %u for IRQ\n", offset); module_put(gc->gpiodev->owner); return ret; } return 0; } EXPORT_SYMBOL_GPL(gpiochip_reqres_irq); void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset) { gpiochip_unlock_as_irq(gc, offset); module_put(gc->gpiodev->owner); } EXPORT_SYMBOL_GPL(gpiochip_relres_irq); bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset) { if (offset >= gc->ngpio) return false; return test_bit(GPIOD_FLAG_OPEN_DRAIN, &gc->gpiodev->descs[offset].flags); } EXPORT_SYMBOL_GPL(gpiochip_line_is_open_drain); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset) { if (offset >= gc->ngpio) return false; return test_bit(GPIOD_FLAG_OPEN_SOURCE, &gc->gpiodev->descs[offset].flags); } EXPORT_SYMBOL_GPL(gpiochip_line_is_open_source); bool gpiochip_line_is_persistent(struct gpio_chip *gc, unsigned int offset) { if (offset >= gc->ngpio) return false; return !test_bit(GPIOD_FLAG_TRANSITORY, &gc->gpiodev->descs[offset].flags); } EXPORT_SYMBOL_GPL(gpiochip_line_is_persistent); /** * gpiod_get_raw_value_cansleep() - return a gpio's raw value * @desc: gpio whose value will be returned * * Returns: * The GPIO's raw value, i.e. the value of the physical line disregarding * its ACTIVE_LOW status, or negative errno on failure. * * This function is to be called from contexts that can sleep. */ int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc) { might_sleep(); VALIDATE_DESC(desc); return gpiod_get_raw_value_commit(desc); } EXPORT_SYMBOL_GPL(gpiod_get_raw_value_cansleep); /** * gpiod_get_value_cansleep() - return a gpio's value * @desc: gpio whose value will be returned * * Returns: * The GPIO's logical value, i.e. taking the ACTIVE_LOW status into * account, or negative errno on failure. * * This function is to be called from contexts that can sleep. */ int gpiod_get_value_cansleep(const struct gpio_desc *desc) { int value; might_sleep(); VALIDATE_DESC(desc); value = gpiod_get_raw_value_commit(desc); if (value < 0) return value; if (test_bit(GPIOD_FLAG_ACTIVE_LOW, &desc->flags)) value = !value; return value; } EXPORT_SYMBOL_GPL(gpiod_get_value_cansleep); /** * gpiod_get_raw_array_value_cansleep() - read raw values from an array of GPIOs * @array_size: number of elements in the descriptor array / value bitmap * @desc_array: array of GPIO descriptors whose values will be read * @array_info: information on applicability of fast bitmap processing path * @value_bitmap: bitmap to store the read values * * Read the raw values of the GPIOs, i.e. the values of the physical lines * without regard for their ACTIVE_LOW status. * * This function is to be called from contexts that can sleep. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_get_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { might_sleep(); if (!desc_array) return -EINVAL; return gpiod_get_array_value_complex(true, true, array_size, desc_array, array_info, value_bitmap); } EXPORT_SYMBOL_GPL(gpiod_get_raw_array_value_cansleep); /** * gpiod_get_array_value_cansleep() - read values from an array of GPIOs * @array_size: number of elements in the descriptor array / value bitmap * @desc_array: array of GPIO descriptors whose values will be read * @array_info: information on applicability of fast bitmap processing path * @value_bitmap: bitmap to store the read values * * Read the logical values of the GPIOs, i.e. taking their ACTIVE_LOW status * into account. * * This function is to be called from contexts that can sleep. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_get_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { might_sleep(); if (!desc_array) return -EINVAL; return gpiod_get_array_value_complex(false, true, array_size, desc_array, array_info, value_bitmap); } EXPORT_SYMBOL_GPL(gpiod_get_array_value_cansleep); /** * gpiod_set_raw_value_cansleep() - assign a gpio's raw value * @desc: gpio whose value will be assigned * @value: value to assign * * Set the raw value of the GPIO, i.e. the value of its physical line without * regard for its ACTIVE_LOW status. * * This function is to be called from contexts that can sleep. * * Returns: * 0 on success, negative error number on failure. */ int gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value) { might_sleep(); VALIDATE_DESC(desc); return gpiod_set_raw_value_commit(desc, value); } EXPORT_SYMBOL_GPL(gpiod_set_raw_value_cansleep); /** * gpiod_set_value_cansleep() - assign a gpio's value * @desc: gpio whose value will be assigned * @value: value to assign * * Set the logical value of the GPIO, i.e. taking its ACTIVE_LOW status into * account * * This function is to be called from contexts that can sleep. * * Returns: * 0 on success, negative error number on failure. */ int gpiod_set_value_cansleep(struct gpio_desc *desc, int value) { might_sleep(); VALIDATE_DESC(desc); return gpiod_set_value_nocheck(desc, value); } EXPORT_SYMBOL_GPL(gpiod_set_value_cansleep); /** * gpiod_set_raw_array_value_cansleep() - assign values to an array of GPIOs * @array_size: number of elements in the descriptor array / value bitmap * @desc_array: array of GPIO descriptors whose values will be assigned * @array_info: information on applicability of fast bitmap processing path * @value_bitmap: bitmap of values to assign * * Set the raw values of the GPIOs, i.e. the values of the physical lines * without regard for their ACTIVE_LOW status. * * This function is to be called from contexts that can sleep. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_set_raw_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { might_sleep(); if (!desc_array) return -EINVAL; return gpiod_set_array_value_complex(true, true, array_size, desc_array, array_info, value_bitmap); } EXPORT_SYMBOL_GPL(gpiod_set_raw_array_value_cansleep); /** * gpiod_add_lookup_tables() - register GPIO device consumers * @tables: list of tables of consumers to register * @n: number of tables in the list */ void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n) { unsigned int i; guard(mutex)(&gpio_lookup_lock); for (i = 0; i < n; i++) list_add_tail(&tables[i]->list, &gpio_lookup_list); } /** * gpiod_set_array_value_cansleep() - assign values to an array of GPIOs * @array_size: number of elements in the descriptor array / value bitmap * @desc_array: array of GPIO descriptors whose values will be assigned * @array_info: information on applicability of fast bitmap processing path * @value_bitmap: bitmap of values to assign * * Set the logical values of the GPIOs, i.e. taking their ACTIVE_LOW status * into account. * * This function is to be called from contexts that can sleep. * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_set_array_value_cansleep(unsigned int array_size, struct gpio_desc **desc_array, struct gpio_array *array_info, unsigned long *value_bitmap) { might_sleep(); if (!desc_array) return -EINVAL; return gpiod_set_array_value_complex(false, true, array_size, desc_array, array_info, value_bitmap); } EXPORT_SYMBOL_GPL(gpiod_set_array_value_cansleep); void gpiod_line_state_notify(struct gpio_desc *desc, unsigned long action) { guard(read_lock_irqsave)(&desc->gdev->line_state_lock); raw_notifier_call_chain(&desc->gdev->line_state_notifier, action, desc); } /** * gpiod_add_lookup_table() - register GPIO device consumers * @table: table of consumers to register */ void gpiod_add_lookup_table(struct gpiod_lookup_table *table) { gpiod_add_lookup_tables(&table, 1); } EXPORT_SYMBOL_GPL(gpiod_add_lookup_table); /** * gpiod_remove_lookup_table() - unregister GPIO device consumers * @table: table of consumers to unregister */ void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) { /* Nothing to remove */ if (!table) return; guard(mutex)(&gpio_lookup_lock); list_del(&table->list); } EXPORT_SYMBOL_GPL(gpiod_remove_lookup_table); static bool gpiod_match_lookup_table(struct device *dev, const struct gpiod_lookup_table *table) { const char *dev_id = dev ? dev_name(dev) : NULL; lockdep_assert_held(&gpio_lookup_lock); if (table->dev_id && dev_id) { /* * Valid strings on both ends, must be identical to have * a match */ if (!strcmp(table->dev_id, dev_id)) return true; } else { /* * One of the pointers is NULL, so both must be to have * a match */ if (dev_id == table->dev_id) return true; } return false; } static struct gpio_desc *gpio_desc_table_match(struct device *dev, const char *con_id, unsigned int idx, unsigned long *flags, struct gpiod_lookup_table *table) { struct gpio_desc *desc; struct gpiod_lookup *p; struct gpio_chip *gc; lockdep_assert_held(&gpio_lookup_lock); for (p = &table->table[0]; p->key; p++) { /* idx must always match exactly */ if (p->idx != idx) continue; /* If the lookup entry has a con_id, require exact match */ if (p->con_id && (!con_id || strcmp(p->con_id, con_id))) continue; if (p->chip_hwnum == U16_MAX) { desc = gpio_name_to_desc(p->key); if (desc) { *flags = p->flags; return desc; } dev_dbg(dev, "cannot find GPIO line %s, deferring\n", p->key); return ERR_PTR(-EPROBE_DEFER); } struct gpio_device *gdev __free(gpio_device_put) = gpio_device_find_by_label(p->key); if (!gdev) { /* * As the lookup table indicates a chip with * p->key should exist, assume it may * still appear later and let the interested * consumer be probed again or let the Deferred * Probe infrastructure handle the error. */ dev_dbg(dev, "cannot find GPIO chip %s, deferring\n", p->key); return ERR_PTR(-EPROBE_DEFER); } gc = gpio_device_get_chip(gdev); if (gc->ngpio <= p->chip_hwnum) { dev_err(dev, "requested GPIO %u (%u) is out of range [0..%u] for chip %s\n", idx, p->chip_hwnum, gc->ngpio - 1, gc->label); return ERR_PTR(-EINVAL); } desc = gpio_device_get_desc(gdev, p->chip_hwnum); *flags = p->flags; return desc; } return NULL; } static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id, unsigned int idx, unsigned long *flags) { struct gpiod_lookup_table *table; struct gpio_desc *desc; guard(mutex)(&gpio_lookup_lock); list_for_each_entry(table, &gpio_lookup_list, list) { if (!gpiod_match_lookup_table(dev, table)) continue; desc = gpio_desc_table_match(dev, con_id, idx, flags, table); if (!desc) continue; /* On IS_ERR() or match. */ return desc; } return ERR_PTR(-ENOENT); } static int platform_gpio_count(struct device *dev, const char *con_id) { struct gpiod_lookup_table *table; struct gpiod_lookup *p; unsigned int count = 0; scoped_guard(mutex, &gpio_lookup_lock) { list_for_each_entry(table, &gpio_lookup_list, list) { if (!gpiod_match_lookup_table(dev, table)) continue; for (p = &table->table[0]; p->key; p++) { if ((con_id && p->con_id && !strcmp(con_id, p->con_id)) || (!con_id && !p->con_id)) count++; } } } if (!count) return -ENOENT; return count; } static struct gpio_desc *gpiod_find_by_fwnode(struct fwnode_handle *fwnode, struct device *consumer, const char *con_id, unsigned int idx, enum gpiod_flags *flags, unsigned long *lookupflags) { const char *name = function_name_or_default(con_id); struct gpio_desc *desc = ERR_PTR(-ENOENT); if (is_of_node(fwnode)) { dev_dbg(consumer, "using DT '%pfw' for '%s' GPIO lookup\n", fwnode, name); desc = of_find_gpio(to_of_node(fwnode), con_id, idx, lookupflags); } else if (is_acpi_node(fwnode)) { dev_dbg(consumer, "using ACPI '%pfw' for '%s' GPIO lookup\n", fwnode, name); desc = acpi_find_gpio(fwnode, con_id, idx, flags, lookupflags); } else if (is_software_node(fwnode)) { dev_dbg(consumer, "using swnode '%pfw' for '%s' GPIO lookup\n", fwnode, name); desc = swnode_find_gpio(fwnode, con_id, idx, lookupflags); } return desc; } static struct gpio_desc *gpiod_fwnode_lookup(struct fwnode_handle *fwnode, struct device *consumer, const char *con_id, unsigned int idx, enum gpiod_flags *flags, unsigned long *lookupflags) { struct gpio_desc *desc; desc = gpiod_find_by_fwnode(fwnode, consumer, con_id, idx, flags, lookupflags); if (gpiod_not_found(desc) && !IS_ERR_OR_NULL(fwnode)) desc = gpiod_find_by_fwnode(fwnode->secondary, consumer, con_id, idx, flags, lookupflags); return desc; } struct gpio_desc *gpiod_find_and_request(struct device *consumer, struct fwnode_handle *fwnode, const char *con_id, unsigned int idx, enum gpiod_flags flags, const char *label, bool platform_lookup_allowed) { unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT; const char *name = function_name_or_default(con_id); /* * scoped_guard() is implemented as a for loop, meaning static * analyzers will complain about these two not being initialized. */ struct gpio_desc *desc = NULL; int ret = 0; scoped_guard(srcu, &gpio_devices_srcu) { desc = gpiod_fwnode_lookup(fwnode, consumer, con_id, idx, &flags, &lookupflags); if (!IS_ERR_OR_NULL(desc) && test_bit(GPIOD_FLAG_SHARED, &desc->flags)) { /* * We're dealing with a GPIO shared by multiple * consumers. This is the moment to add the machine * lookup table for the proxy device as previously * we only knew the consumer's fwnode. */ ret = gpio_shared_add_proxy_lookup(consumer, fwnode, con_id, lookupflags); if (ret) return ERR_PTR(ret); /* Trigger platform lookup for shared GPIO proxy. */ desc = ERR_PTR(-ENOENT); /* Trigger it even for fwnode-only gpiod_get(). */ platform_lookup_allowed = true; } if (gpiod_not_found(desc) && platform_lookup_allowed) { /* * Either we are not using DT or ACPI, or their lookup * did not return a result or this is a shared GPIO. In * that case, use platform lookup as a fallback. */ dev_dbg(consumer, "using lookup tables for GPIO lookup\n"); desc = gpiod_find(consumer, con_id, idx, &lookupflags); } if (IS_ERR(desc)) { dev_dbg(consumer, "No GPIO consumer %s found\n", name); return desc; } /* * If a connection label was passed use that, else attempt to use * the device name as label */ ret = gpiod_request(desc, label); } if (ret) { if (!(ret == -EBUSY && flags & GPIOD_FLAGS_BIT_NONEXCLUSIVE)) return ERR_PTR(ret); /* * This happens when there are several consumers for the same * GPIO line: we just return here without further * initialization. It's a hack introduced long ago to support * fixed regulators. We now have a better solution with * automated scanning where affected platforms just need to * select the provided Kconfig option. * * FIXME: Remove the GPIOD_FLAGS_BIT_NONEXCLUSIVE flag after * making sure all platforms use the new mechanism. */ dev_info(consumer, "nonexclusive access to GPIO for %s, consider updating your code to using gpio-shared-proxy\n", name); return desc; } ret = gpiod_configure_flags(desc, con_id, lookupflags, flags); if (ret < 0) { gpiod_put(desc); dev_err(consumer, "setup of GPIO %s failed: %d\n", name, ret); return ERR_PTR(ret); } gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_REQUESTED); return desc; } /** * fwnode_gpiod_get_index - obtain a GPIO from firmware node * @fwnode: handle of the firmware node * @con_id: function within the GPIO consumer * @index: index of the GPIO to obtain for the consumer * @flags: GPIO initialization flags * @label: label to attach to the requested GPIO * * This function can be used for drivers that get their configuration * from opaque firmware. * * The function properly finds the corresponding GPIO using whatever is the * underlying firmware interface and then makes sure that the GPIO * descriptor is requested before it is returned to the caller. * * Returns: * On successful request the GPIO pin is configured in accordance with * provided @flags. * * In case of error an ERR_PTR() is returned. */ struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, const char *con_id, int index, enum gpiod_flags flags, const char *label) { return gpiod_find_and_request(NULL, fwnode, con_id, index, flags, label, false); } EXPORT_SYMBOL_GPL(fwnode_gpiod_get_index); /** * gpiod_count - return the number of GPIOs associated with a device / function * @dev: GPIO consumer, can be NULL for system-global GPIOs * @con_id: function within the GPIO consumer * * Returns: * The number of GPIOs associated with a device / function or -ENOENT if no * GPIO has been assigned to the requested function. */ int gpiod_count(struct device *dev, const char *con_id) { const struct fwnode_handle *fwnode = dev ? dev_fwnode(dev) : NULL; int count = -ENOENT; if (is_of_node(fwnode)) count = of_gpio_count(fwnode, con_id); else if (is_acpi_node(fwnode)) count = acpi_gpio_count(fwnode, con_id); else if (is_software_node(fwnode)) count = swnode_gpio_count(fwnode, con_id); if (count < 0) count = platform_gpio_count(dev, con_id); return count; } EXPORT_SYMBOL_GPL(gpiod_count); /** * gpiod_get - obtain a GPIO for a given GPIO function * @dev: GPIO consumer, can be NULL for system-global GPIOs * @con_id: function within the GPIO consumer * @flags: optional GPIO initialization flags * * Returns: * The GPIO descriptor corresponding to the function @con_id of device * dev, -ENOENT if no GPIO has been assigned to the requested function, or * another IS_ERR() code if an error occurred while trying to acquire the GPIO. */ struct gpio_desc *__must_check gpiod_get(struct device *dev, const char *con_id, enum gpiod_flags flags) { return gpiod_get_index(dev, con_id, 0, flags); } EXPORT_SYMBOL_GPL(gpiod_get); /** * gpiod_get_optional - obtain an optional GPIO for a given GPIO function * @dev: GPIO consumer, can be NULL for system-global GPIOs * @con_id: function within the GPIO consumer * @flags: optional GPIO initialization flags * * This is equivalent to gpiod_get(), except that when no GPIO was assigned to * the requested function it will return NULL. This is convenient for drivers * that need to handle optional GPIOs. * * Returns: * The GPIO descriptor corresponding to the function @con_id of device * dev, NULL if no GPIO has been assigned to the requested function, or * another IS_ERR() code if an error occurred while trying to acquire the GPIO. */ struct gpio_desc *__must_check gpiod_get_optional(struct device *dev, const char *con_id, enum gpiod_flags flags) { return gpiod_get_index_optional(dev, con_id, 0, flags); } EXPORT_SYMBOL_GPL(gpiod_get_optional); /** * gpiod_configure_flags - helper function to configure a given GPIO * @desc: gpio whose value will be assigned * @con_id: function within the GPIO consumer * @lflags: bitmask of gpio_lookup_flags GPIO_* values - returned from * of_find_gpio() or of_get_gpio_hog() * @dflags: gpiod_flags - optional GPIO initialization flags * * Returns: * 0 on success, -ENOENT if no GPIO has been assigned to the * requested function and/or index, or another IS_ERR() code if an error * occurred while trying to acquire the GPIO. */ int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, unsigned long lflags, enum gpiod_flags dflags) { const char *name = function_name_or_default(con_id); int ret; if (lflags & GPIO_ACTIVE_LOW) set_bit(GPIOD_FLAG_ACTIVE_LOW, &desc->flags); if (lflags & GPIO_OPEN_DRAIN) set_bit(GPIOD_FLAG_OPEN_DRAIN, &desc->flags); else if (dflags & GPIOD_FLAGS_BIT_OPEN_DRAIN) { /* * This enforces open drain mode from the consumer side. * This is necessary for some busses like I2C, but the lookup * should *REALLY* have specified them as open drain in the * first place, so print a little warning here. */ set_bit(GPIOD_FLAG_OPEN_DRAIN, &desc->flags); gpiod_warn(desc, "enforced open drain please flag it properly in DT/ACPI DSDT/board file\n"); } if (lflags & GPIO_OPEN_SOURCE) set_bit(GPIOD_FLAG_OPEN_SOURCE, &desc->flags); if (((lflags & GPIO_PULL_UP) && (lflags & GPIO_PULL_DOWN)) || ((lflags & GPIO_PULL_UP) && (lflags & GPIO_PULL_DISABLE)) || ((lflags & GPIO_PULL_DOWN) && (lflags & GPIO_PULL_DISABLE))) { gpiod_err(desc, "multiple pull-up, pull-down or pull-disable enabled, invalid configuration\n"); return -EINVAL; } if (lflags & GPIO_PULL_UP) set_bit(GPIOD_FLAG_PULL_UP, &desc->flags); else if (lflags & GPIO_PULL_DOWN) set_bit(GPIOD_FLAG_PULL_DOWN, &desc->flags); else if (lflags & GPIO_PULL_DISABLE) set_bit(GPIOD_FLAG_BIAS_DISABLE, &desc->flags); ret = gpiod_set_transitory(desc, (lflags & GPIO_TRANSITORY)); if (ret < 0) return ret; /* No particular flag request, return here... */ if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) { gpiod_dbg(desc, "no flags found for GPIO %s\n", name); return 0; } /* Process flags */ if (dflags & GPIOD_FLAGS_BIT_DIR_OUT) ret = gpiod_direction_output_nonotify(desc, !!(dflags & GPIOD_FLAGS_BIT_DIR_VAL)); else ret = gpiod_direction_input_nonotify(desc); return ret; } /** * gpiod_get_index - obtain a GPIO from a multi-index GPIO function * @dev: GPIO consumer, can be NULL for system-global GPIOs * @con_id: function within the GPIO consumer * @idx: index of the GPIO to obtain in the consumer * @flags: optional GPIO initialization flags * * This variant of gpiod_get() allows to access GPIOs other than the first * defined one for functions that define several GPIOs. * * Returns: * A valid GPIO descriptor, -ENOENT if no GPIO has been assigned to the * requested function and/or index, or another IS_ERR() code if an error * occurred while trying to acquire the GPIO. */ struct gpio_desc *__must_check gpiod_get_index(struct device *dev, const char *con_id, unsigned int idx, enum gpiod_flags flags) { struct fwnode_handle *fwnode = dev ? dev_fwnode(dev) : NULL; const char *devname = dev ? dev_name(dev) : "?"; const char *label = con_id ?: devname; return gpiod_find_and_request(dev, fwnode, con_id, idx, flags, label, true); } EXPORT_SYMBOL_GPL(gpiod_get_index); /** * gpiod_get_index_optional - obtain an optional GPIO from a multi-index GPIO * function * @dev: GPIO consumer, can be NULL for system-global GPIOs * @con_id: function within the GPIO consumer * @index: index of the GPIO to obtain in the consumer * @flags: optional GPIO initialization flags * * This is equivalent to gpiod_get_index(), except that when no GPIO with the * specified index was assigned to the requested function it will return NULL. * This is convenient for drivers that need to handle optional GPIOs. * * Returns: * A valid GPIO descriptor, NULL if no GPIO has been assigned to the * requested function and/or index, or another IS_ERR() code if an error * occurred while trying to acquire the GPIO. */ struct gpio_desc *__must_check gpiod_get_index_optional(struct device *dev, const char *con_id, unsigned int index, enum gpiod_flags flags) { struct gpio_desc *desc; desc = gpiod_get_index(dev, con_id, index, flags); if (gpiod_not_found(desc)) return NULL; return desc; } EXPORT_SYMBOL_GPL(gpiod_get_index_optional); /** * gpiod_hog - Hog the specified GPIO desc given the provided flags * @desc: gpio whose value will be assigned * @name: gpio line name * @lflags: bitmask of gpio_lookup_flags GPIO_* values - returned from * of_find_gpio() or of_get_gpio_hog() * @dflags: gpiod_flags - optional GPIO initialization flags * * Returns: * 0 on success, or negative errno on failure. */ int gpiod_hog(struct gpio_desc *desc, const char *name, unsigned long lflags, enum gpiod_flags dflags) { struct gpio_device *gdev = desc->gdev; struct gpio_desc *local_desc; int hwnum; int ret; CLASS(gpio_chip_guard, guard)(desc); if (!guard.gc) return -ENODEV; if (test_and_set_bit(GPIOD_FLAG_IS_HOGGED, &desc->flags)) return 0; hwnum = gpiod_hwgpio(desc); local_desc = gpiochip_request_own_desc(guard.gc, hwnum, name, lflags, dflags); if (IS_ERR(local_desc)) { clear_bit(GPIOD_FLAG_IS_HOGGED, &desc->flags); ret = PTR_ERR(local_desc); pr_err("requesting hog GPIO %s (chip %s, offset %d) failed, %d\n", name, gdev->label, hwnum, ret); return ret; } gpiod_dbg(desc, "hogged as %s/%s\n", (dflags & GPIOD_FLAGS_BIT_DIR_OUT) ? "output" : "input", (dflags & GPIOD_FLAGS_BIT_DIR_OUT) ? str_high_low(dflags & GPIOD_FLAGS_BIT_DIR_VAL) : "?"); return 0; } /** * gpiochip_free_hogs - Scan gpio-controller chip and release GPIO hog * @gc: gpio chip to act on */ static void gpiochip_free_hogs(struct gpio_chip *gc) { struct gpio_desc *desc; for_each_gpio_desc_with_flag(gc, desc, GPIOD_FLAG_IS_HOGGED) gpiochip_free_own_desc(desc); } /** * gpiod_get_array - obtain multiple GPIOs from a multi-index GPIO function * @dev: GPIO consumer, can be NULL for system-global GPIOs * @con_id: function within the GPIO consumer * @flags: optional GPIO initialization flags * * This function acquires all the GPIOs defined under a given function. * * Returns: * The GPIO descriptors corresponding to the function @con_id of device * dev, -ENOENT if no GPIO has been assigned to the requested function, * or another IS_ERR() code if an error occurred while trying to acquire * the GPIOs. */ struct gpio_descs *__must_check gpiod_get_array(struct device *dev, const char *con_id, enum gpiod_flags flags) { struct gpio_desc *desc; struct gpio_descs *descs; struct gpio_device *gdev; struct gpio_array *array_info = NULL; int count, bitmap_size; unsigned long dflags; size_t descs_size; count = gpiod_count(dev, con_id); if (count < 0) return ERR_PTR(count); descs_size = struct_size(descs, desc, count); descs = kzalloc(descs_size, GFP_KERNEL); if (!descs) return ERR_PTR(-ENOMEM); for (descs->ndescs = 0; descs->ndescs < count; descs->ndescs++) { desc = gpiod_get_index(dev, con_id, descs->ndescs, flags); if (IS_ERR(desc)) { gpiod_put_array(descs); return ERR_CAST(desc); } descs->desc[descs->ndescs] = desc; gdev = gpiod_to_gpio_device(desc); /* * If pin hardware number of array member 0 is also 0, select * its chip as a candidate for fast bitmap processing path. */ if (descs->ndescs == 0 && gpiod_hwgpio(desc) == 0) { struct gpio_descs *array; bitmap_size = BITS_TO_LONGS(gdev->ngpio > count ? gdev->ngpio : count); array = krealloc(descs, descs_size + struct_size(array_info, invert_mask, 3 * bitmap_size), GFP_KERNEL | __GFP_ZERO); if (!array) { gpiod_put_array(descs); return ERR_PTR(-ENOMEM); } descs = array; array_info = (void *)descs + descs_size; array_info->get_mask = array_info->invert_mask + bitmap_size; array_info->set_mask = array_info->get_mask + bitmap_size; array_info->desc = descs->desc; array_info->size = count; array_info->gdev = gdev; bitmap_set(array_info->get_mask, descs->ndescs, count - descs->ndescs); bitmap_set(array_info->set_mask, descs->ndescs, count - descs->ndescs); descs->info = array_info; } /* If there is no cache for fast bitmap processing path, continue */ if (!array_info) continue; /* Unmark array members which don't belong to the 'fast' chip */ if (array_info->gdev != gdev) { __clear_bit(descs->ndescs, array_info->get_mask); __clear_bit(descs->ndescs, array_info->set_mask); } /* * Detect array members which belong to the 'fast' chip * but their pins are not in hardware order. */ else if (gpiod_hwgpio(desc) != descs->ndescs) { /* * Don't use fast path if all array members processed so * far belong to the same chip as this one but its pin * hardware number is different from its array index. */ if (bitmap_full(array_info->get_mask, descs->ndescs)) { array_info = NULL; } else { __clear_bit(descs->ndescs, array_info->get_mask); __clear_bit(descs->ndescs, array_info->set_mask); } } else { dflags = READ_ONCE(desc->flags); /* Exclude open drain or open source from fast output */ if (test_bit(GPIOD_FLAG_OPEN_DRAIN, &dflags) || test_bit(GPIOD_FLAG_OPEN_SOURCE, &dflags)) __clear_bit(descs->ndescs, array_info->set_mask); /* Identify 'fast' pins which require invertion */ if (gpiod_is_active_low(desc)) __set_bit(descs->ndescs, array_info->invert_mask); } } if (array_info) dev_dbg(dev, "GPIO array info: chip=%s, size=%d, get_mask=%lx, set_mask=%lx, invert_mask=%lx\n", array_info->gdev->label, array_info->size, *array_info->get_mask, *array_info->set_mask, *array_info->invert_mask); return descs; } EXPORT_SYMBOL_GPL(gpiod_get_array); /** * gpiod_get_array_optional - obtain multiple GPIOs from a multi-index GPIO * function * @dev: GPIO consumer, can be NULL for system-global GPIOs * @con_id: function within the GPIO consumer * @flags: optional GPIO initialization flags * * This is equivalent to gpiod_get_array(), except that when no GPIO was * assigned to the requested function it will return NULL. * * Returns: * The GPIO descriptors corresponding to the function @con_id of device * dev, NULL if no GPIO has been assigned to the requested function, * or another IS_ERR() code if an error occurred while trying to acquire * the GPIOs. */ struct gpio_descs *__must_check gpiod_get_array_optional(struct device *dev, const char *con_id, enum gpiod_flags flags) { struct gpio_descs *descs; descs = gpiod_get_array(dev, con_id, flags); if (gpiod_not_found(descs)) return NULL; return descs; } EXPORT_SYMBOL_GPL(gpiod_get_array_optional); /** * gpiod_put - dispose of a GPIO descriptor * @desc: GPIO descriptor to dispose of * * No descriptor can be used after gpiod_put() has been called on it. */ void gpiod_put(struct gpio_desc *desc) { gpiod_free(desc); } EXPORT_SYMBOL_GPL(gpiod_put); /** * gpiod_put_array - dispose of multiple GPIO descriptors * @descs: struct gpio_descs containing an array of descriptors */ void gpiod_put_array(struct gpio_descs *descs) { unsigned int i; for (i = 0; i < descs->ndescs; i++) gpiod_put(descs->desc[i]); kfree(descs); } EXPORT_SYMBOL_GPL(gpiod_put_array); /* * The DT node of some GPIO chips have a "compatible" property, but * never have a struct device added and probed by a driver to register * the GPIO chip with gpiolib. In such cases, fw_devlink=on will cause * the consumers of the GPIO chip to get probe deferred forever because * they will be waiting for a device associated with the GPIO chip * firmware node to get added and bound to a driver. * * To allow these consumers to probe, we associate the struct * gpio_device of the GPIO chip with the firmware node and then simply * bind it to this stub driver. */ static struct device_driver gpio_stub_drv = { .name = "gpio_stub_drv", .bus = &gpio_bus_type, }; static int __init gpiolib_dev_init(void) { int ret; /* Register GPIO sysfs bus */ ret = bus_register(&gpio_bus_type); if (ret < 0) { pr_err("gpiolib: could not register GPIO bus type\n"); return ret; } ret = driver_register(&gpio_stub_drv); if (ret < 0) { pr_err("gpiolib: could not register GPIO stub driver\n"); bus_unregister(&gpio_bus_type); return ret; } ret = alloc_chrdev_region(&gpio_devt, 0, GPIO_DEV_MAX, GPIOCHIP_NAME); if (ret < 0) { pr_err("gpiolib: failed to allocate char dev region\n"); driver_unregister(&gpio_stub_drv); bus_unregister(&gpio_bus_type); return ret; } gpiolib_initialized = true; gpiochip_setup_devs(); #if IS_ENABLED(CONFIG_OF_DYNAMIC) && IS_ENABLED(CONFIG_OF_GPIO) WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier)); #endif /* CONFIG_OF_DYNAMIC && CONFIG_OF_GPIO */ return ret; } core_initcall(gpiolib_dev_init); #ifdef CONFIG_DEBUG_FS static void gpiolib_dbg_show(struct seq_file *s, struct gpio_chip *gc) { bool active_low, is_irq, is_out; struct gpio_desc *desc; unsigned int gpio = 0; unsigned long flags; int value; for_each_gpio_desc(gc, desc) { guard(srcu)(&desc->gdev->desc_srcu); flags = READ_ONCE(desc->flags); is_irq = test_bit(GPIOD_FLAG_USED_AS_IRQ, &flags); if (is_irq || test_bit(GPIOD_FLAG_REQUESTED, &flags)) { gpiod_get_direction(desc); is_out = test_bit(GPIOD_FLAG_IS_OUT, &flags); value = gpio_chip_get_value(gc, desc); active_low = test_bit(GPIOD_FLAG_ACTIVE_LOW, &flags); seq_printf(s, " gpio-%-3u (%-20.20s|%-20.20s) %s %s %s%s\n", gpio, desc->name ?: "", gpiod_get_label(desc), is_out ? "out" : "in ", value >= 0 ? str_hi_lo(value) : "? ", is_irq ? "IRQ " : "", active_low ? "ACTIVE LOW" : ""); } else if (desc->name) { seq_printf(s, " gpio-%-3u (%-20.20s)\n", gpio, desc->name); } gpio++; } } struct gpiolib_seq_priv { bool newline; int idx; }; static void *gpiolib_seq_start(struct seq_file *s, loff_t *pos) { struct gpiolib_seq_priv *priv; struct gpio_device *gdev; loff_t index = *pos; s->private = NULL; priv = kzalloc_obj(*priv); if (!priv) return NULL; s->private = priv; if (*pos > 0) priv->newline = true; priv->idx = srcu_read_lock(&gpio_devices_srcu); list_for_each_entry_srcu(gdev, &gpio_devices, list, srcu_read_lock_held(&gpio_devices_srcu)) { if (index-- == 0) return gdev; } return NULL; } static void *gpiolib_seq_next(struct seq_file *s, void *v, loff_t *pos) { struct gpiolib_seq_priv *priv = s->private; struct gpio_device *gdev = v, *next; next = list_entry_rcu(gdev->list.next, struct gpio_device, list); gdev = &next->list == &gpio_devices ? NULL : next; priv->newline = true; ++*pos; return gdev; } static void gpiolib_seq_stop(struct seq_file *s, void *v) { struct gpiolib_seq_priv *priv; priv = s->private; if (!priv) return; srcu_read_unlock(&gpio_devices_srcu, priv->idx); kfree(priv); } static int gpiolib_seq_show(struct seq_file *s, void *v) { struct gpiolib_seq_priv *priv = s->private; struct gpio_device *gdev = v; struct gpio_chip *gc; struct device *parent; if (priv->newline) seq_putc(s, '\n'); guard(srcu)(&gdev->srcu); gc = srcu_dereference(gdev->chip, &gdev->srcu); if (!gc) { seq_printf(s, "%s: (dangling chip)\n", dev_name(&gdev->dev)); return 0; } seq_printf(s, "%s: %u GPIOs", dev_name(&gdev->dev), gdev->ngpio); parent = gc->parent; if (parent) seq_printf(s, ", parent: %s/%s", parent->bus ? parent->bus->name : "no-bus", dev_name(parent)); if (gc->label) seq_printf(s, ", %s", gc->label); if (gc->can_sleep) seq_printf(s, ", can sleep"); seq_printf(s, ":\n"); if (gc->dbg_show) gc->dbg_show(s, gc); else gpiolib_dbg_show(s, gc); return 0; } static const struct seq_operations gpiolib_sops = { .start = gpiolib_seq_start, .next = gpiolib_seq_next, .stop = gpiolib_seq_stop, .show = gpiolib_seq_show, }; DEFINE_SEQ_ATTRIBUTE(gpiolib); static int __init gpiolib_debugfs_init(void) { /* /sys/kernel/debug/gpio */ debugfs_create_file("gpio", 0444, NULL, NULL, &gpiolib_fops); return 0; } subsys_initcall(gpiolib_debugfs_init); #endif /* DEBUG_FS */ |
| 787 1005 553 146 1183 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_POLL_H #define _LINUX_POLL_H #include <linux/compiler.h> #include <linux/ktime.h> #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #define MAX_STACK_ALLOC 832 #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC #define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC) #define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry)) #define DEFAULT_POLLMASK (EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM) struct poll_table_struct; /* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* * Do not touch the structure directly, use the access function * poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; __poll_t _key; } poll_table; static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { if (p && p->_qproc) { p->_qproc(filp, wait_address, p); /* * This memory barrier is paired in the wq_has_sleeper(). * See the comment above prepare_to_wait(), we need to * ensure that subsequent tests in this thread can't be * reordered with __add_wait_queue() in _qproc() paths. */ smp_mb(); } } /* * Return the set of events that the application wants to poll for. * This is useful for drivers that need to know whether a DMA transfer has * to be started implicitly on poll(). You typically only want to do that * if the application is actually polling for POLLIN and/or POLLOUT. */ static inline __poll_t poll_requested_events(const poll_table *p) { return p ? p->_key : ~(__poll_t)0; } static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) { pt->_qproc = qproc; pt->_key = ~(__poll_t)0; /* all events enabled */ } static inline bool file_can_poll(struct file *file) { return file->f_op->poll; } static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) { if (unlikely(!file->f_op->poll)) return DEFAULT_POLLMASK; return file->f_op->poll(file, pt); } struct poll_table_entry { struct file *filp; __poll_t key; wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; /* * Structures and helpers for select/poll syscall */ struct poll_wqueues { poll_table pt; struct poll_table_page *table; struct task_struct *polling_task; int triggered; int error; int inline_index; struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES]; }; extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern u64 select_estimate_accuracy(struct timespec64 *tv); #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time); extern int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec); #define __MAP(v, from, to) \ (from < to ? (v & from) * (to/from) : (v & from) / (from/to)) static inline __u16 mangle_poll(__poll_t val) { __u16 v = (__force __u16)val; #define M(X) __MAP(v, (__force __u16)EPOLL##X, POLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } static inline __poll_t demangle_poll(u16 val) { #define M(X) (__force __poll_t)__MAP(val, POLL##X, (__force __u16)EPOLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } #undef __MAP #endif /* _LINUX_POLL_H */ |
| 166 181 12 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 | /* * net/tipc/bearer.h: Include file for TIPC bearer code * * Copyright (c) 1996-2006, 2013-2016, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_BEARER_H #define _TIPC_BEARER_H #include "netlink.h" #include "core.h" #include "msg.h" #include <net/genetlink.h> #define MAX_MEDIA 3 /* Identifiers associated with TIPC message header media address info * - address info field is 32 bytes long * - the field's actual content and length is defined per media * - remaining unused bytes in the field are set to zero */ #define TIPC_MEDIA_INFO_SIZE 32 #define TIPC_MEDIA_TYPE_OFFSET 3 #define TIPC_MEDIA_ADDR_OFFSET 4 /* * Identifiers of supported TIPC media types */ #define TIPC_MEDIA_TYPE_ETH 1 #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 /* Minimum bearer MTU */ #define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) /* Identifiers for distinguishing between broadcast/multicast and replicast */ #define TIPC_BROADCAST_SUPPORT 1 #define TIPC_REPLICAST_SUPPORT 2 /** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) * @media_id: TIPC media type identifier * @broadcast: non-zero if address is a broadcast address */ struct tipc_media_addr { u8 value[TIPC_MEDIA_INFO_SIZE]; u8 media_id; u8 broadcast; }; struct tipc_bearer; /** * struct tipc_media - Media specific info exposed to generic bearer layer * @send_msg: routine which handles buffer transmission * @enable_media: routine which enables a media * @disable_media: routine which disables a media * @addr2str: convert media address format to string * @addr2msg: convert from media addr format to discovery msg addr format * @msg2addr: convert from discovery msg addr format to media addr format * @raw2addr: convert from raw addr format to media addr format * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure * @min_win: minimum window (in packets) before declaring link congestion * @max_win: maximum window (in packets) before declaring link congestion * @mtu: max packet size bearer can support for media type not dependent on * underlying device MTU * @type_id: TIPC media identifier * @hwaddr_len: TIPC media address len * @name: media name */ struct tipc_media { int (*send_msg)(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); int (*enable_media)(struct net *net, struct tipc_bearer *b, struct nlattr *attr[]); void (*disable_media)(struct tipc_bearer *b); int (*addr2str)(struct tipc_media_addr *addr, char *strbuf, int bufsz); int (*addr2msg)(char *msg, struct tipc_media_addr *addr); int (*msg2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, char *msg); int (*raw2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, const char *raw); u32 priority; u32 tolerance; u32 min_win; u32 max_win; u32 mtu; u32 type_id; u32 hwaddr_len; char name[TIPC_MAX_MEDIA_NAME]; }; /** * struct tipc_bearer - Generic TIPC bearer structure * @media_ptr: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support * @addr: media-specific address associated with bearer * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer * @bcast_addr: media address used in broadcasting * @pt: packet type for bearer * @rcu: rcu struct for tipc_bearer * @priority: default link priority for bearer * @min_win: minimum window (in packets) before declaring link congestion * @max_win: maximum window (in packets) before declaring link congestion * @tolerance: default link tolerance for bearer * @domain: network domain to which links can be established * @identity: array index of this bearer within TIPC bearer array * @disc: ptr to link setup request * @net_plane: network plane ('A' through 'H') currently associated with bearer * @encap_hlen: encap headers length * @up: bearer up flag (bit 0) * @refcnt: tipc_bearer reference counter * * Note: media-specific code is responsible for initialization of the fields * indicated below when a bearer is enabled; TIPC's generic bearer code takes * care of initializing all other fields. */ struct tipc_bearer { void __rcu *media_ptr; /* initialized by media */ u32 mtu; /* initialized by media */ struct tipc_media_addr addr; /* initialized by media */ char name[TIPC_MAX_BEARER_NAME]; struct tipc_media *media; struct tipc_media_addr bcast_addr; struct packet_type pt; struct rcu_head rcu; u32 priority; u32 min_win; u32 max_win; u32 tolerance; u32 domain; u32 identity; struct tipc_discoverer *disc; char net_plane; u16 encap_hlen; unsigned long up; refcount_t refcnt; }; struct tipc_bearer_names { char media_name[TIPC_MAX_MEDIA_NAME]; char if_name[TIPC_MAX_IF_NAME]; }; /* * TIPC routines available to supported media types */ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b); /* * Routines made available to TIPC by supported media types */ extern struct tipc_media eth_media_info; #ifdef CONFIG_TIPC_MEDIA_IB extern struct tipc_media ib_media_info; #endif #ifdef CONFIG_TIPC_MEDIA_UDP extern struct tipc_media udp_media_info; #endif int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, struct nlattr *attrs[]); bool tipc_bearer_hold(struct tipc_bearer *b); void tipc_bearer_put(struct tipc_bearer *b); void tipc_disable_l2_media(struct tipc_bearer *b); int tipc_l2_send_msg(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest); void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id); struct tipc_media *tipc_media_find(const char *name); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); int tipc_bearer_min_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, struct tipc_media_addr *dest); void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq, struct tipc_media_addr *dst, struct tipc_node *__dnode); void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts); int tipc_attach_loopback(struct net *net); void tipc_detach_loopback(struct net *net); static inline void tipc_loopback_trace(struct net *net, struct sk_buff_head *pkts) { if (unlikely(dev_nit_active(net->loopback_dev))) tipc_clone_to_loopback(net, pkts); } /* check if device MTU is too low for tipc headers */ static inline bool tipc_mtu_bad(struct net_device *dev) { if (dev->mtu >= TIPC_MIN_BEARER_MTU) return false; netdev_warn(dev, "MTU too low for tipc bearer\n"); return true; } #endif /* _TIPC_BEARER_H */ |
| 9 9 9 4 4 1 5 7 2 3 1 1 4 2 1 1 2 2 2 1 2 1 3 3 4 1 3 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | // SPDX-License-Identifier: GPL-2.0 /* * cfg80211 wext compat for managed mode. * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2009, 2020-2023 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(); lockdep_assert_wiphy(wdev->wiphy); 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 < 4; 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; } if (wdev->conn) { bool event = true; if (wdev->wext.connect.channel == chan) return 0; /* 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) return err; } wdev->wext.connect.channel = chan; return cfg80211_mgd_wext_connect(rdev, wdev); } 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; if (wdev->valid_links) return -EOPNOTSUPP; if (wdev->links[0].client.current_bss) chan = wdev->links[0].client.current_bss->pub.channel; else if (wdev->wext.connect.channel) chan = wdev->wext.connect.channel; 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--; 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) return 0; /* 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) return err; } 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); return cfg80211_mgd_wext_connect(rdev, wdev); } 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; if (wdev->valid_links) return -EINVAL; data->flags = 0; if (wdev->links[0].client.current_bss) { const struct element *ssid_elem; rcu_read_lock(); ssid_elem = ieee80211_bss_get_elem( &wdev->links[0].client.current_bss->pub, WLAN_EID_SSID); if (ssid_elem) { data->flags = 1; data->length = ssid_elem->datalen; if (data->length > IW_ESSID_MAX_SIZE) ret = -EINVAL; else memcpy(ssid, ssid_elem->data, 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); } 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; if (wdev->conn) { /* both automatic */ if (!bssid && !wdev->wext.connect.bssid) return 0; /* fixed already - and no change */ if (wdev->wext.connect.bssid && bssid && ether_addr_equal(bssid, wdev->wext.connect.bssid)) return 0; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, false); if (err) return err; } if (bssid) { memcpy(wdev->wext.bssid, bssid, ETH_ALEN); wdev->wext.connect.bssid = wdev->wext.bssid; } else wdev->wext.connect.bssid = NULL; return cfg80211_mgd_wext_connect(rdev, wdev); } 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; if (wdev->valid_links) return -EOPNOTSUPP; if (wdev->links[0].client.current_bss) memcpy(ap_addr->sa_data, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); else eth_zero_addr(ap_addr->sa_data); return 0; } int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ie_len = data->length; u8 *ie = extra; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!ie_len) ie = NULL; guard(wiphy)(wdev->wiphy); /* no change */ if (wdev->wext.ie_len == ie_len && memcmp(wdev->wext.ie, ie, ie_len) == 0) return 0; if (ie_len) { ie = kmemdup(extra, ie_len, GFP_KERNEL); if (!ie) return -ENOMEM; } else { ie = NULL; } kfree(wdev->wext.ie); wdev->wext.ie = ie; wdev->wext.ie_len = ie_len; if (wdev->conn) return cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, false); /* userspace better not think we'll reconnect */ return 0; } int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_mlme *mlme = (struct iw_mlme *)extra; struct cfg80211_registered_device *rdev; 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; guard(wiphy)(&rdev->wiphy); switch (mlme->cmd) { case IW_MLME_DEAUTH: case IW_MLME_DISASSOC: return cfg80211_disconnect(rdev, dev, mlme->reason_code, true); default: return -EOPNOTSUPP; } } |
| 86 85 1 3 1 1 3 85 84 1 1 2 81 5 2 1 1 1 1 1 69 69 69 69 69 69 69 69 69 69 68 69 69 1 20 48 2 3 2 59 58 2 2 2 1 34 23 62 85 2 88 2 2 88 88 1 1 1 3 3 20 81 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * * super.c */ /* * This file implements code to read the superblock, read and initialise * in-memory structures at mount time, and all the VFS glue code to register * the filesystem. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/blkdev.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/vfs.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/seq_file.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/module.h> #include <linux/magic.h> #include <linux/xattr.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" #include "squashfs_fs_i.h" #include "squashfs.h" #include "decompressor.h" #include "xattr.h" static struct file_system_type squashfs_fs_type; static const struct super_operations squashfs_super_ops; enum Opt_errors { Opt_errors_continue, Opt_errors_panic, }; enum squashfs_param { Opt_errors, Opt_threads, }; struct squashfs_mount_opts { enum Opt_errors errors; const struct squashfs_decompressor_thread_ops *thread_ops; int thread_num; }; static const struct constant_table squashfs_param_errors[] = { {"continue", Opt_errors_continue }, {"panic", Opt_errors_panic }, {} }; static const struct fs_parameter_spec squashfs_fs_parameters[] = { fsparam_enum("errors", Opt_errors, squashfs_param_errors), fsparam_string("threads", Opt_threads), {} }; static int squashfs_parse_param_threads_str(const char *str, struct squashfs_mount_opts *opts) { #ifdef CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT if (strcmp(str, "single") == 0) { opts->thread_ops = &squashfs_decompressor_single; return 0; } if (strcmp(str, "multi") == 0) { opts->thread_ops = &squashfs_decompressor_multi; return 0; } if (strcmp(str, "percpu") == 0) { opts->thread_ops = &squashfs_decompressor_percpu; return 0; } #endif return -EINVAL; } static int squashfs_parse_param_threads_num(const char *str, struct squashfs_mount_opts *opts) { #ifdef CONFIG_SQUASHFS_MOUNT_DECOMP_THREADS int ret; unsigned long num; ret = kstrtoul(str, 0, &num); if (ret != 0) return -EINVAL; if (num > 1) { opts->thread_ops = &squashfs_decompressor_multi; if (num > opts->thread_ops->max_decompressors()) return -EINVAL; opts->thread_num = (int)num; return 0; } #ifdef CONFIG_SQUASHFS_DECOMP_SINGLE if (num == 1) { opts->thread_ops = &squashfs_decompressor_single; opts->thread_num = 1; return 0; } #endif #endif /* !CONFIG_SQUASHFS_MOUNT_DECOMP_THREADS */ return -EINVAL; } static int squashfs_parse_param_threads(const char *str, struct squashfs_mount_opts *opts) { int ret = squashfs_parse_param_threads_str(str, opts); if (ret == 0) return ret; return squashfs_parse_param_threads_num(str, opts); } static int squashfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct squashfs_mount_opts *opts = fc->fs_private; struct fs_parse_result result; int opt; opt = fs_parse(fc, squashfs_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_errors: opts->errors = result.uint_32; break; case Opt_threads: if (squashfs_parse_param_threads(param->string, opts) != 0) return -EINVAL; break; default: return -EINVAL; } return 0; } static const struct squashfs_decompressor *supported_squashfs_filesystem( struct fs_context *fc, short major, short minor, short id) { const struct squashfs_decompressor *decompressor; if (major < SQUASHFS_MAJOR) { errorf(fc, "Major/Minor mismatch, older Squashfs %d.%d " "filesystems are unsupported", major, minor); return NULL; } else if (major > SQUASHFS_MAJOR || minor > SQUASHFS_MINOR) { errorf(fc, "Major/Minor mismatch, trying to mount newer " "%d.%d filesystem", major, minor); errorf(fc, "Please update your kernel"); return NULL; } decompressor = squashfs_lookup_decompressor(id); if (!decompressor->supported) { errorf(fc, "Filesystem uses \"%s\" compression. This is not supported", decompressor->name); return NULL; } return decompressor; } static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct squashfs_mount_opts *opts = fc->fs_private; struct squashfs_sb_info *msblk; struct squashfs_super_block *sblk = NULL; struct inode *root; long long root_inode; unsigned short flags; unsigned int fragments; u64 lookup_table_start, xattr_id_table_start, next_table; int err, devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); TRACE("Entered squashfs_fill_superblock\n"); if (!devblksize) { errorf(fc, "squashfs: unable to set blocksize\n"); return -EINVAL; } sb->s_fs_info = kzalloc_obj(*msblk); if (sb->s_fs_info == NULL) { ERROR("Failed to allocate squashfs_sb_info\n"); return -ENOMEM; } msblk = sb->s_fs_info; msblk->thread_ops = opts->thread_ops; msblk->panic_on_errors = (opts->errors == Opt_errors_panic); msblk->devblksize = devblksize; msblk->devblksize_log2 = ffz(~msblk->devblksize); mutex_init(&msblk->meta_index_mutex); /* * msblk->bytes_used is checked in squashfs_read_table to ensure reads * are not beyond filesystem end. But as we're using * squashfs_read_table here to read the superblock (including the value * of bytes_used) we need to set it to an initial sensible dummy value */ msblk->bytes_used = sizeof(*sblk); sblk = squashfs_read_table(sb, SQUASHFS_START, sizeof(*sblk)); if (IS_ERR(sblk)) { errorf(fc, "unable to read squashfs_super_block"); err = PTR_ERR(sblk); sblk = NULL; goto failed_mount; } err = -EINVAL; /* Check it is a SQUASHFS superblock */ sb->s_magic = le32_to_cpu(sblk->s_magic); if (sb->s_magic != SQUASHFS_MAGIC) { if (!(fc->sb_flags & SB_SILENT)) errorf(fc, "Can't find a SQUASHFS superblock on %pg", sb->s_bdev); goto failed_mount; } if (opts->thread_num == 0) { msblk->max_thread_num = msblk->thread_ops->max_decompressors(); } else { msblk->max_thread_num = opts->thread_num; } /* Check the MAJOR & MINOR versions and lookup compression type */ msblk->decompressor = supported_squashfs_filesystem( fc, le16_to_cpu(sblk->s_major), le16_to_cpu(sblk->s_minor), le16_to_cpu(sblk->compression)); if (msblk->decompressor == NULL) goto failed_mount; /* Check the filesystem does not extend beyond the end of the block device */ msblk->bytes_used = le64_to_cpu(sblk->bytes_used); if (msblk->bytes_used < 0 || msblk->bytes_used > bdev_nr_bytes(sb->s_bdev)) goto failed_mount; /* Check block size for sanity */ msblk->block_size = le32_to_cpu(sblk->block_size); if (msblk->block_size > SQUASHFS_FILE_MAX_SIZE) goto insanity; /* * Check the system page size is not larger than the filesystem * block size (by default 128K). This is currently not supported. */ if (PAGE_SIZE > msblk->block_size) { errorf(fc, "Page size > filesystem block size (%d). This is " "currently not supported!", msblk->block_size); goto failed_mount; } /* Check block log for sanity */ msblk->block_log = le16_to_cpu(sblk->block_log); if (msblk->block_log > SQUASHFS_FILE_MAX_LOG) goto failed_mount; /* Check that block_size and block_log match */ if (msblk->block_size != (1 << msblk->block_log)) goto insanity; /* Check the root inode for sanity */ root_inode = le64_to_cpu(sblk->root_inode); if (SQUASHFS_INODE_OFFSET(root_inode) > SQUASHFS_METADATA_SIZE) goto insanity; msblk->inode_table = le64_to_cpu(sblk->inode_table_start); msblk->directory_table = le64_to_cpu(sblk->directory_table_start); msblk->inodes = le32_to_cpu(sblk->inodes); msblk->fragments = le32_to_cpu(sblk->fragments); msblk->ids = le16_to_cpu(sblk->no_ids); flags = le16_to_cpu(sblk->flags); TRACE("Found valid superblock on %pg\n", sb->s_bdev); TRACE("Inodes are %scompressed\n", SQUASHFS_UNCOMPRESSED_INODES(flags) ? "un" : ""); TRACE("Data is %scompressed\n", SQUASHFS_UNCOMPRESSED_DATA(flags) ? "un" : ""); TRACE("Filesystem size %lld bytes\n", msblk->bytes_used); TRACE("Block size %d\n", msblk->block_size); TRACE("Number of inodes %d\n", msblk->inodes); TRACE("Number of fragments %d\n", msblk->fragments); TRACE("Number of ids %d\n", msblk->ids); TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); TRACE("sblk->fragment_table_start %llx\n", (u64) le64_to_cpu(sblk->fragment_table_start)); TRACE("sblk->id_table_start %llx\n", (u64) le64_to_cpu(sblk->id_table_start)); sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_time_min = 0; sb->s_time_max = U32_MAX; sb->s_flags |= SB_RDONLY; sb->s_op = &squashfs_super_ops; msblk->block_cache = squashfs_cache_init("metadata", SQUASHFS_CACHED_BLKS, SQUASHFS_METADATA_SIZE); if (IS_ERR(msblk->block_cache)) { err = PTR_ERR(msblk->block_cache); goto failed_mount; } /* Allocate read_page block */ msblk->read_page = squashfs_cache_init("data", SQUASHFS_READ_PAGES, msblk->block_size); if (IS_ERR(msblk->read_page)) { errorf(fc, "Failed to allocate read_page block"); err = PTR_ERR(msblk->read_page); goto failed_mount; } if (msblk->devblksize == PAGE_SIZE) { struct inode *cache = new_inode(sb); if (cache == NULL) { err = -ENOMEM; goto failed_mount; } set_nlink(cache, 1); cache->i_size = OFFSET_MAX; mapping_set_gfp_mask(cache->i_mapping, GFP_NOFS); msblk->cache_mapping = cache->i_mapping; } msblk->stream = squashfs_decompressor_setup(sb, flags); if (IS_ERR(msblk->stream)) { err = PTR_ERR(msblk->stream); msblk->stream = NULL; goto insanity; } /* Handle xattrs */ sb->s_xattr = squashfs_xattr_handlers; xattr_id_table_start = le64_to_cpu(sblk->xattr_id_table_start); if (xattr_id_table_start == SQUASHFS_INVALID_BLK) { next_table = msblk->bytes_used; goto allocate_id_index_table; } /* Allocate and read xattr id lookup table */ msblk->xattr_id_table = squashfs_read_xattr_id_table(sb, xattr_id_table_start, &msblk->xattr_table, &msblk->xattr_ids); if (IS_ERR(msblk->xattr_id_table)) { errorf(fc, "unable to read xattr id index table"); err = PTR_ERR(msblk->xattr_id_table); msblk->xattr_id_table = NULL; if (err != -ENOTSUPP) goto failed_mount; } next_table = msblk->xattr_table; allocate_id_index_table: /* Allocate and read id index table */ msblk->id_table = squashfs_read_id_index_table(sb, le64_to_cpu(sblk->id_table_start), next_table, msblk->ids); if (IS_ERR(msblk->id_table)) { errorf(fc, "unable to read id index table"); err = PTR_ERR(msblk->id_table); msblk->id_table = NULL; goto failed_mount; } next_table = le64_to_cpu(msblk->id_table[0]); /* Handle inode lookup table */ lookup_table_start = le64_to_cpu(sblk->lookup_table_start); if (lookup_table_start == SQUASHFS_INVALID_BLK) goto handle_fragments; /* Allocate and read inode lookup table */ msblk->inode_lookup_table = squashfs_read_inode_lookup_table(sb, lookup_table_start, next_table, msblk->inodes); if (IS_ERR(msblk->inode_lookup_table)) { errorf(fc, "unable to read inode lookup table"); err = PTR_ERR(msblk->inode_lookup_table); msblk->inode_lookup_table = NULL; goto failed_mount; } next_table = le64_to_cpu(msblk->inode_lookup_table[0]); sb->s_export_op = &squashfs_export_ops; handle_fragments: fragments = msblk->fragments; if (fragments == 0) goto check_directory_table; msblk->fragment_cache = squashfs_cache_init("fragment", min(SQUASHFS_CACHED_FRAGMENTS, fragments), msblk->block_size); if (IS_ERR(msblk->fragment_cache)) { err = PTR_ERR(msblk->fragment_cache); goto failed_mount; } /* Allocate and read fragment index table */ msblk->fragment_index = squashfs_read_fragment_index_table(sb, le64_to_cpu(sblk->fragment_table_start), next_table, fragments); if (IS_ERR(msblk->fragment_index)) { errorf(fc, "unable to read fragment index table"); err = PTR_ERR(msblk->fragment_index); msblk->fragment_index = NULL; goto failed_mount; } next_table = le64_to_cpu(msblk->fragment_index[0]); check_directory_table: /* Sanity check directory_table */ if (msblk->directory_table > next_table) { err = -EINVAL; goto insanity; } /* Sanity check inode_table */ if (msblk->inode_table >= msblk->directory_table) { err = -EINVAL; goto insanity; } /* allocate root */ root = new_inode(sb); if (!root) { err = -ENOMEM; goto failed_mount; } err = squashfs_read_inode(root, root_inode); if (err) { make_bad_inode(root); iput(root); goto failed_mount; } insert_inode_hash(root); sb->s_root = d_make_root(root); if (sb->s_root == NULL) { ERROR("Root inode create failed\n"); err = -ENOMEM; goto failed_mount; } TRACE("Leaving squashfs_fill_super\n"); kfree(sblk); return 0; insanity: errorf(fc, "squashfs image failed sanity check"); failed_mount: squashfs_cache_delete(msblk->block_cache); squashfs_cache_delete(msblk->fragment_cache); squashfs_cache_delete(msblk->read_page); if (msblk->cache_mapping) iput(msblk->cache_mapping->host); msblk->thread_ops->destroy(msblk); kfree(msblk->inode_lookup_table); kfree(msblk->fragment_index); kfree(msblk->id_table); kfree(msblk->xattr_id_table); kfree(sb->s_fs_info); sb->s_fs_info = NULL; kfree(sblk); return err; } static int squashfs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, squashfs_fill_super); } static int squashfs_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct squashfs_sb_info *msblk = sb->s_fs_info; struct squashfs_mount_opts *opts = fc->fs_private; sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; msblk->panic_on_errors = (opts->errors == Opt_errors_panic); return 0; } static void squashfs_free_fs_context(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations squashfs_context_ops = { .get_tree = squashfs_get_tree, .free = squashfs_free_fs_context, .parse_param = squashfs_parse_param, .reconfigure = squashfs_reconfigure, }; static int squashfs_show_options(struct seq_file *s, struct dentry *root) { struct super_block *sb = root->d_sb; struct squashfs_sb_info *msblk = sb->s_fs_info; if (msblk->panic_on_errors) seq_puts(s, ",errors=panic"); else seq_puts(s, ",errors=continue"); #ifdef CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT if (msblk->thread_ops == &squashfs_decompressor_single) { seq_puts(s, ",threads=single"); return 0; } if (msblk->thread_ops == &squashfs_decompressor_percpu) { seq_puts(s, ",threads=percpu"); return 0; } #endif #ifdef CONFIG_SQUASHFS_MOUNT_DECOMP_THREADS seq_printf(s, ",threads=%d", msblk->max_thread_num); #endif return 0; } static int squashfs_init_fs_context(struct fs_context *fc) { struct squashfs_mount_opts *opts; opts = kzalloc_obj(*opts); if (!opts) return -ENOMEM; #ifdef CONFIG_SQUASHFS_DECOMP_SINGLE opts->thread_ops = &squashfs_decompressor_single; #elif defined(CONFIG_SQUASHFS_DECOMP_MULTI) opts->thread_ops = &squashfs_decompressor_multi; #elif defined(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) opts->thread_ops = &squashfs_decompressor_percpu; #else #error "fail: unknown squashfs decompression thread mode?" #endif opts->thread_num = 0; fc->fs_private = opts; fc->ops = &squashfs_context_ops; return 0; } static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct squashfs_sb_info *msblk = dentry->d_sb->s_fs_info; u64 id = huge_encode_dev(dentry->d_sb->s_bdev->bd_dev); TRACE("Entered squashfs_statfs\n"); buf->f_type = SQUASHFS_MAGIC; buf->f_bsize = msblk->block_size; buf->f_blocks = ((msblk->bytes_used - 1) >> msblk->block_log) + 1; buf->f_bfree = buf->f_bavail = 0; buf->f_files = msblk->inodes; buf->f_ffree = 0; buf->f_namelen = SQUASHFS_NAME_LEN; buf->f_fsid = u64_to_fsid(id); return 0; } static void squashfs_put_super(struct super_block *sb) { if (sb->s_fs_info) { struct squashfs_sb_info *sbi = sb->s_fs_info; squashfs_cache_delete(sbi->block_cache); squashfs_cache_delete(sbi->fragment_cache); squashfs_cache_delete(sbi->read_page); if (sbi->cache_mapping) iput(sbi->cache_mapping->host); sbi->thread_ops->destroy(sbi); kfree(sbi->id_table); kfree(sbi->fragment_index); kfree(sbi->meta_index); kfree(sbi->inode_lookup_table); kfree(sbi->xattr_id_table); kfree(sb->s_fs_info); sb->s_fs_info = NULL; } } static struct kmem_cache *squashfs_inode_cachep; static void init_once(void *foo) { struct squashfs_inode_info *ei = foo; inode_init_once(&ei->vfs_inode); } static int __init init_inodecache(void) { squashfs_inode_cachep = kmem_cache_create("squashfs_inode_cache", sizeof(struct squashfs_inode_info), 0, SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, init_once); return squashfs_inode_cachep ? 0 : -ENOMEM; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(squashfs_inode_cachep); } static int __init init_squashfs_fs(void) { int err = init_inodecache(); if (err) return err; err = register_filesystem(&squashfs_fs_type); if (err) { destroy_inodecache(); return err; } pr_info("version 4.0 (2009/01/31) Phillip Lougher\n"); return 0; } static void __exit exit_squashfs_fs(void) { unregister_filesystem(&squashfs_fs_type); destroy_inodecache(); } static struct inode *squashfs_alloc_inode(struct super_block *sb) { struct squashfs_inode_info *ei = alloc_inode_sb(sb, squashfs_inode_cachep, GFP_KERNEL); return ei ? &ei->vfs_inode : NULL; } static void squashfs_free_inode(struct inode *inode) { kmem_cache_free(squashfs_inode_cachep, squashfs_i(inode)); } static struct file_system_type squashfs_fs_type = { .owner = THIS_MODULE, .name = "squashfs", .init_fs_context = squashfs_init_fs_context, .parameters = squashfs_fs_parameters, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; MODULE_ALIAS_FS("squashfs"); static const struct super_operations squashfs_super_ops = { .alloc_inode = squashfs_alloc_inode, .free_inode = squashfs_free_inode, .statfs = squashfs_statfs, .put_super = squashfs_put_super, .show_options = squashfs_show_options, }; module_init(init_squashfs_fs); module_exit(exit_squashfs_fs); MODULE_DESCRIPTION("squashfs 4.0, a compressed read-only filesystem"); MODULE_AUTHOR("Phillip Lougher <phillip@squashfs.org.uk>"); MODULE_LICENSE("GPL"); |
| 1 281 5 400 18 480 19 69 25 53 94 37 62 5 1395 1335 30 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> extern struct file_system_type nullfs_fs_type; extern struct list_head notify_list; struct mnt_namespace { struct ns_common ns; struct mount * root; struct { struct rb_root mounts; /* Protected by namespace_sem */ struct rb_node *mnt_last_node; /* last (rightmost) mount in the rbtree */ struct rb_node *mnt_first_node; /* first (leftmost) mount in the rbtree */ }; struct user_namespace *user_ns; struct ucounts *ucounts; wait_queue_head_t poll; u64 seq_origin; /* Sequence number of origin mount namespace */ u64 event; #ifdef CONFIG_FSNOTIFY __u32 n_fsnotify_mask; struct fsnotify_mark_connector __rcu *n_fsnotify_marks; #endif unsigned int nr_mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; refcount_t passive; /* number references not pinning @mounts */ bool is_anon; } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct mount *mnt_next_for_sb; /* the next two fields are hlist_node, */ struct mount * __aligned(1) *mnt_pprev_for_sb; /* except that LSB of pprev is stolen */ #define WRITE_HOLD 1 /* ... for use by mnt_hold_writers() */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct hlist_head mnt_slave_list;/* list of slave mounts */ struct hlist_node mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ /* * Containing namespace (active or deactivating, non-refcounted). * Normally protected by namespace_sem. * Can also be accessed locklessly under RCU. RCU readers can't rely on * the namespace still being active, but implicitly hold a passive * reference (because an RCU delay happens between a namespace being * deactivated and the corresponding passive refcount drop). */ struct mnt_namespace *mnt_ns; struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; struct list_head to_notify; /* need to queue notification */ struct mnt_namespace *prev_ns; /* previous namespace (NULL if none) */ #endif int mnt_t_flags; /* namespace_sem-protected flags */ int mnt_id; /* mount identifier, reused */ u64 mnt_id_unique; /* mount ID unique until reboot */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; struct mount *overmount; /* mounted on ->mnt_root */ } __randomize_layout; enum { T_SHARED = 1, /* mount is shared */ T_UNBINDABLE = 2, /* mount is unbindable */ T_MARKED = 4, /* internal mark for propagate_... */ T_UMOUNT_CANDIDATE = 8, /* for propagate_umount */ /* * T_SHARED_MASK is the set of flags that should be cleared when a * mount becomes shared. Currently, this is only the flag that says a * mount cannot be bind mounted, since this is how we create a mount * that shares events with another mount. If you add a new T_* * flag, consider how it interacts with shared mounts. */ T_SHARED_MASK = T_UNBINDABLE, }; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(const struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { ns_ref_inc(ns); } extern seqlock_t mount_lock; DEFINE_LOCK_GUARD_0(mount_writer, write_seqlock(&mount_lock), write_sequnlock(&mount_lock)) DEFINE_LOCK_GUARD_0(mount_locked_reader, read_seqlock_excl(&mount_lock), read_sequnlock_excl(&mount_lock)) struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(const struct dentry *dentry); static inline bool is_local_mountpoint(const struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->is_anon; } static inline bool anon_ns_root(const struct mount *m) { struct mnt_namespace *ns = READ_ONCE(m->mnt_ns); return !IS_ERR_OR_NULL(ns) && is_anon_ns(ns) && m == ns->root; } static inline bool mnt_ns_attached(const struct mount *mnt) { return !RB_EMPTY_NODE(&mnt->mnt_node); } static inline bool mnt_ns_empty(const struct mnt_namespace *ns) { return RB_EMPTY_ROOT(&ns->mounts); } static inline void move_from_ns(struct mount *mnt) { struct mnt_namespace *ns = mnt->mnt_ns; WARN_ON(!mnt_ns_attached(mnt)); if (ns->mnt_last_node == &mnt->mnt_node) ns->mnt_last_node = rb_prev(&mnt->mnt_node); if (ns->mnt_first_node == &mnt->mnt_node) ns->mnt_first_node = rb_next(&mnt->mnt_node); rb_erase(&mnt->mnt_node, &ns->mounts); RB_CLEAR_NODE(&mnt->mnt_node); } bool has_locked_children(struct mount *mnt, struct dentry *dentry); struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mnt_ns, bool previous); static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } #ifdef CONFIG_FSNOTIFY static inline void mnt_notify_add(struct mount *m) { /* Optimize the case where there are no watches */ if ((m->mnt_ns && m->mnt_ns->n_fsnotify_marks) || (m->prev_ns && m->prev_ns->n_fsnotify_marks)) list_add_tail(&m->to_notify, ¬ify_list); else m->prev_ns = m->mnt_ns; } #else static inline void mnt_notify_add(struct mount *m) { } #endif static inline struct mount *topmost_overmount(struct mount *m) { while (m->overmount) m = m->overmount; return m; } static inline bool __test_write_hold(struct mount * __aligned(1) *val) { return (unsigned long)val & WRITE_HOLD; } static inline bool test_write_hold(const struct mount *m) { return __test_write_hold(m->mnt_pprev_for_sb); } static inline void set_write_hold(struct mount *m) { m->mnt_pprev_for_sb = (void *)((unsigned long)m->mnt_pprev_for_sb | WRITE_HOLD); } static inline void clear_write_hold(struct mount *m) { m->mnt_pprev_for_sb = (void *)((unsigned long)m->mnt_pprev_for_sb & ~WRITE_HOLD); } struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry); |
| 10006 2146 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(unsigned long call_site, bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 761 23 787 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 | /* 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. * * Definitions for the IP protocol. * * Version: @(#)ip.h 1.0.2 04/28/93 * * Authors: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_IP_H #define _LINUX_IP_H #include <linux/skbuff.h> #include <uapi/linux/ip.h> static inline struct iphdr *ip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_network_header(skb); } static inline struct iphdr *inner_ip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_inner_network_header(skb); } static inline struct iphdr *ipip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_transport_header(skb); } static inline unsigned int ip_transport_len(const struct sk_buff *skb) { return ntohs(ip_hdr(skb)->tot_len) - skb_network_header_len(skb); } static inline unsigned int iph_totlen(const struct sk_buff *skb, const struct iphdr *iph) { u32 len = ntohs(iph->tot_len); return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ? len : skb->len - skb_network_offset(skb); } static inline unsigned int skb_ip_totlen(const struct sk_buff *skb) { return iph_totlen(skb, ip_hdr(skb)); } /* IPv4 datagram length is stored into 16bit field (tot_len) */ #define IP_MAX_MTU 0xFFFFU static inline void iph_set_totlen(struct iphdr *iph, unsigned int len) { iph->tot_len = len <= IP_MAX_MTU ? htons(len) : 0; } #endif /* _LINUX_IP_H */ |
| 6 1 1 4 14 4 1 2 4 2 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 | // SPDX-License-Identifier: GPL-2.0-only /* * * Generic part shared by ipv4 and ipv6 backends. */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> #define NFTA_FIB_F_ALL (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR | \ NFTA_FIB_F_MARK | NFTA_FIB_F_IIF | NFTA_FIB_F_OIF | \ NFTA_FIB_F_PRESENT) const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = { [NFTA_FIB_DREG] = NLA_POLICY_MAX(NLA_BE32, NFT_REG32_MAX), [NFTA_FIB_RESULT] = { .type = NLA_U32 }, [NFTA_FIB_FLAGS] = NLA_POLICY_MASK(NLA_BE32, NFTA_FIB_F_ALL), }; EXPORT_SYMBOL(nft_fib_policy); int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_fib *priv = nft_expr_priv(expr); unsigned int hooks; switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD); break; case NFT_FIB_RESULT_ADDRTYPE: if (priv->flags & NFTA_FIB_F_IIF) hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD); else if (priv->flags & NFTA_FIB_F_OIF) hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_FORWARD); else hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING); break; default: return -EINVAL; } return nft_chain_validate_hooks(ctx->chain, hooks); } EXPORT_SYMBOL_GPL(nft_fib_validate); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_fib *priv = nft_expr_priv(expr); unsigned int len; int err; if (!tb[NFTA_FIB_DREG] || !tb[NFTA_FIB_RESULT] || !tb[NFTA_FIB_FLAGS]) return -EINVAL; priv->flags = ntohl(nla_get_be32(tb[NFTA_FIB_FLAGS])); if (priv->flags == 0) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) == (NFTA_FIB_F_IIF | NFTA_FIB_F_OIF)) return -EINVAL; if ((priv->flags & (NFTA_FIB_F_SADDR | NFTA_FIB_F_DADDR)) == 0) return -EINVAL; priv->result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); switch (priv->result) { case NFT_FIB_RESULT_OIF: if (priv->flags & NFTA_FIB_F_OIF) return -EINVAL; len = sizeof(int); break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_OIF) return -EINVAL; len = IFNAMSIZ; break; case NFT_FIB_RESULT_ADDRTYPE: len = sizeof(u32); break; default: return -EINVAL; } err = nft_parse_register_store(ctx, tb[NFTA_FIB_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); if (err < 0) return err; return 0; } EXPORT_SYMBOL_GPL(nft_fib_init); int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_fib *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_FIB_DREG, priv->dreg)) return -1; if (nla_put_be32(skb, NFTA_FIB_RESULT, htonl(priv->result))) return -1; if (nla_put_be32(skb, NFTA_FIB_FLAGS, htonl(priv->flags))) return -1; return 0; } EXPORT_SYMBOL_GPL(nft_fib_dump); void nft_fib_store_result(void *reg, const struct nft_fib *priv, const struct net_device *dev) { u32 *dreg = reg; int index; switch (priv->result) { case NFT_FIB_RESULT_OIF: index = dev ? dev->ifindex : 0; if (priv->flags & NFTA_FIB_F_PRESENT) nft_reg_store8(dreg, !!index); else *dreg = index; break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_PRESENT) nft_reg_store8(dreg, !!dev); else strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ); break; default: WARN_ON_ONCE(1); *dreg = 0; break; } } EXPORT_SYMBOL_GPL(nft_fib_store_result); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Query routing table from nftables"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); |
| 1 1 175 170 71 109 104 5 105 4 321 355 356 175 321 325 321 7 325 323 5 5 317 9 12 251 7 89 324 89 322 1 320 321 321 5 6 1 137 2 7 135 5 1 8 8 118 111 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2003, 2004 * * This file is part of the SCTP kernel implementation * * This file contains the code relating the chunk abstraction. * * 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: * Jon Grimm <jgrimm@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> /* This file is mostly in anticipation of future work, but initially * populate with fragment tracking for an outbound message. */ /* Initialize datamsg from memory. */ static void sctp_datamsg_init(struct sctp_datamsg *msg) { refcount_set(&msg->refcnt, 1); msg->send_failed = 0; msg->send_error = 0; msg->can_delay = 1; msg->abandoned = 0; msg->expires_at = 0; INIT_LIST_HEAD(&msg->chunks); } /* Allocate and initialize datamsg. */ static struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp) { struct sctp_datamsg *msg; msg = kmalloc_obj(struct sctp_datamsg, gfp); if (msg) { sctp_datamsg_init(msg); SCTP_DBG_OBJCNT_INC(datamsg); } return msg; } void sctp_datamsg_free(struct sctp_datamsg *msg) { struct sctp_chunk *chunk; /* This doesn't have to be a _safe vairant because * sctp_chunk_free() only drops the refs. */ list_for_each_entry(chunk, &msg->chunks, frag_list) sctp_chunk_free(chunk); sctp_datamsg_put(msg); } /* Final destructruction of datamsg memory. */ static void sctp_datamsg_destroy(struct sctp_datamsg *msg) { struct sctp_association *asoc = NULL; struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_ulpevent *ev; int error, sent; /* Release all references. */ list_for_each_safe(pos, temp, &msg->chunks) { list_del_init(pos); chunk = list_entry(pos, struct sctp_chunk, frag_list); if (!msg->send_failed) { sctp_chunk_put(chunk); continue; } asoc = chunk->asoc; error = msg->send_error ?: asoc->outqueue.error; sent = chunk->has_tsn ? SCTP_DATA_SENT : SCTP_DATA_UNSENT; if (sctp_ulpevent_type_enabled(asoc->subscribe, SCTP_SEND_FAILED)) { ev = sctp_ulpevent_make_send_failed(asoc, chunk, sent, error, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } if (sctp_ulpevent_type_enabled(asoc->subscribe, SCTP_SEND_FAILED_EVENT)) { ev = sctp_ulpevent_make_send_failed_event(asoc, chunk, sent, error, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } sctp_chunk_put(chunk); } SCTP_DBG_OBJCNT_DEC(datamsg); kfree(msg); } /* Hold a reference. */ static void sctp_datamsg_hold(struct sctp_datamsg *msg) { refcount_inc(&msg->refcnt); } /* Release a reference. */ void sctp_datamsg_put(struct sctp_datamsg *msg) { if (refcount_dec_and_test(&msg->refcnt)) sctp_datamsg_destroy(msg); } /* Assign a chunk to this datamsg. */ static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chunk) { sctp_datamsg_hold(msg); chunk->msg = msg; } /* A data chunk can have a maximum payload of (2^16 - 20). Break * down any such message into smaller chunks. Opportunistically, fragment * the chunks down to the current MTU constraints. We may get refragmented * later if the PMTU changes, but it is _much better_ to fragment immediately * with a reasonable guess than always doing our fragmentation on the * soft-interrupt. */ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct iov_iter *from) { size_t len, first_len, max_data, remaining; size_t msg_len = iov_iter_count(from); struct sctp_shared_key *shkey = NULL; struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_datamsg *msg; int err; msg = sctp_datamsg_new(GFP_KERNEL); if (!msg) return ERR_PTR(-ENOMEM); /* Note: Calculate this outside of the loop, so that all fragments * have the same expiration. */ if (asoc->peer.prsctp_capable && sinfo->sinfo_timetolive && (SCTP_PR_TTL_ENABLED(sinfo->sinfo_flags) || !SCTP_PR_POLICY(sinfo->sinfo_flags))) msg->expires_at = jiffies + msecs_to_jiffies(sinfo->sinfo_timetolive); /* This is the biggest possible DATA chunk that can fit into * the packet */ max_data = asoc->frag_point; if (unlikely(!max_data)) { max_data = sctp_min_frag_point(sctp_sk(asoc->base.sk), sctp_datachk_len(&asoc->stream)); pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%zu)", __func__, asoc, max_data); } /* If the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with * DATA. */ if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) { const struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc); if (hmac_desc) max_data -= SCTP_PAD4(sizeof(struct sctp_auth_chunk) + hmac_desc->hmac_len); if (sinfo->sinfo_tsn && sinfo->sinfo_ssn != asoc->active_key_id) { shkey = sctp_auth_get_shkey(asoc, sinfo->sinfo_ssn); if (!shkey) { err = -EINVAL; goto errout; } } else { shkey = asoc->shkey; } } /* Set first_len and then account for possible bundles on first frag */ first_len = max_data; /* Check to see if we have a pending SACK and try to let it be bundled * with this message. Do this if we don't have any data queued already. * To check that, look at out_qlen and retransmit list. * NOTE: we will not reduce to account for SACK, if the message would * not have been fragmented. */ if (timer_pending(&asoc->timers[SCTP_EVENT_TIMEOUT_SACK]) && asoc->outqueue.out_qlen == 0 && list_empty(&asoc->outqueue.retransmit) && msg_len > max_data) first_len -= SCTP_PAD4(sizeof(struct sctp_sack_chunk)); /* Encourage Cookie-ECHO bundling. */ if (asoc->state < SCTP_STATE_COOKIE_ECHOED) first_len -= SCTP_ARBITRARY_COOKIE_ECHO_LEN; /* Account for a different sized first fragment */ if (msg_len >= first_len) { msg->can_delay = 0; if (msg_len > first_len) SCTP_INC_STATS(asoc->base.net, SCTP_MIB_FRAGUSRMSGS); } else { /* Which may be the only one... */ first_len = msg_len; } /* Create chunks for all DATA chunks. */ for (remaining = msg_len; remaining; remaining -= len) { u8 frag = SCTP_DATA_MIDDLE_FRAG; if (remaining == msg_len) { /* First frag, which may also be the last */ frag |= SCTP_DATA_FIRST_FRAG; len = first_len; } else { /* Middle frags */ len = max_data; } if (len >= remaining) { /* Last frag, which may also be the first */ len = remaining; frag |= SCTP_DATA_LAST_FRAG; /* The application requests to set the I-bit of the * last DATA chunk of a user message when providing * the user message to the SCTP implementation. */ if ((sinfo->sinfo_flags & SCTP_EOF) || (sinfo->sinfo_flags & SCTP_SACK_IMMEDIATELY)) frag |= SCTP_DATA_SACK_IMM; } chunk = asoc->stream.si->make_datafrag(asoc, sinfo, len, frag, GFP_KERNEL); if (!chunk) { err = -ENOMEM; goto errout; } err = sctp_user_addto_chunk(chunk, len, from); if (err < 0) goto errout_chunk_free; chunk->shkey = shkey; /* Put the chunk->skb back into the form expected by send. */ __skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr - chunk->skb->data); sctp_datamsg_assign(msg, chunk); list_add_tail(&chunk->frag_list, &msg->chunks); } return msg; errout_chunk_free: sctp_chunk_free(chunk); errout: list_for_each_safe(pos, temp, &msg->chunks) { list_del_init(pos); chunk = list_entry(pos, struct sctp_chunk, frag_list); sctp_chunk_free(chunk); } sctp_datamsg_put(msg); return ERR_PTR(err); } /* Check whether this message has expired. */ int sctp_chunk_abandoned(struct sctp_chunk *chunk) { if (!chunk->asoc->peer.prsctp_capable) return 0; if (chunk->msg->abandoned) return 1; if (!chunk->has_tsn && !(chunk->chunk_hdr->flags & SCTP_DATA_FIRST_FRAG)) return 0; if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) && time_after(jiffies, chunk->msg->expires_at)) { struct sctp_stream_out *streamout = SCTP_SO(&chunk->asoc->stream, chunk->sinfo.sinfo_stream); if (chunk->sent_count) { chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(TTL)]++; } else { chunk->asoc->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; streamout->ext->abandoned_unsent[SCTP_PR_INDEX(TTL)]++; } chunk->msg->abandoned = 1; return 1; } else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) && chunk->sent_count > chunk->sinfo.sinfo_timetolive) { struct sctp_stream_out *streamout = SCTP_SO(&chunk->asoc->stream, chunk->sinfo.sinfo_stream); chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++; streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++; chunk->msg->abandoned = 1; return 1; } else if (!SCTP_PR_POLICY(chunk->sinfo.sinfo_flags) && chunk->msg->expires_at && time_after(jiffies, chunk->msg->expires_at)) { chunk->msg->abandoned = 1; return 1; } /* PRIO policy is processed by sendmsg, not here */ return 0; } /* This chunk (and consequently entire message) has failed in its sending. */ void sctp_chunk_fail(struct sctp_chunk *chunk, int error) { chunk->msg->send_failed = 1; chunk->msg->send_error = error; } |
| 217 82 208 206 37 37 12 12 171 172 95 10 1 9 9 7 1 1 9 313 314 315 315 313 2 2 1 2 313 2 2 267 47 414 324 90 90 90 91 91 90 318 411 7 7 4 2 18 2 16 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 | // SPDX-License-Identifier: GPL-2.0 #include <linux/filter.h> #include <linux/mutex.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <linux/module.h> #include <net/sock.h> #include <linux/kernel.h> #include <linux/tcp.h> #include <linux/workqueue.h> #include <linux/nospec.h> #include <linux/cookie.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> static const struct sock_diag_handler __rcu *sock_diag_handlers[AF_MAX]; static const struct sock_diag_inet_compat __rcu *inet_rcv_compat; static struct workqueue_struct *broadcast_wq; DEFINE_COOKIE(sock_cookie); u64 __sock_gen_cookie(struct sock *sk) { u64 res = atomic64_read(&sk->sk_cookie); if (!res) { u64 new = gen_cookie_next(&sock_cookie); atomic64_cmpxchg(&sk->sk_cookie, res, new); /* Another thread might have changed sk_cookie before us. */ res = atomic64_read(&sk->sk_cookie); } return res; } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie) { u64 res; if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE) return 0; res = sock_gen_cookie(sk); if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1]) return -ESTALE; return 0; } EXPORT_SYMBOL_GPL(sock_diag_check_cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie) { u64 res = sock_gen_cookie(sk); cookie[0] = (u32)res; cookie[1] = (u32)(res >> 32); } EXPORT_SYMBOL_GPL(sock_diag_save_cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) { u32 mem[SK_MEMINFO_VARS]; sk_get_meminfo(sk, mem); return nla_put(skb, attrtype, sizeof(mem), &mem); } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; struct sk_filter *filter; struct nlattr *attr; unsigned int flen; int err = 0; if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (!filter) goto out; fprog = filter->prog->orig_prog; if (!fprog) goto out; flen = bpf_classic_proglen(fprog); attr = nla_reserve(skb, attrtype, flen); if (attr == NULL) { err = -EMSGSIZE; goto out; } memcpy(nla_data(attr), fprog->filter, flen); out: rcu_read_unlock(); return err; } EXPORT_SYMBOL(sock_diag_put_filterinfo); struct broadcast_sk { struct sock *sk; struct work_struct work; }; static size_t sock_diag_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct inet_diag_msg) + nla_total_size(sizeof(u8)) /* INET_DIAG_PROTOCOL */ + nla_total_size_64bit(sizeof(struct tcp_info))); /* INET_DIAG_INFO */ } static const struct sock_diag_handler *sock_diag_lock_handler(int family) { const struct sock_diag_handler *handler; rcu_read_lock(); handler = rcu_dereference(sock_diag_handlers[family]); if (handler && !try_module_get(handler->owner)) handler = NULL; rcu_read_unlock(); return handler; } static void sock_diag_unlock_handler(const struct sock_diag_handler *handler) { module_put(handler->owner); } 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; hndl = sock_diag_lock_handler(sk->sk_family); if (hndl) { if (hndl->get_info) err = hndl->get_info(skb, sk); sock_diag_unlock_handler(hndl); } 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_obj(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(const struct sock_diag_inet_compat *ptr) { xchg(&inet_rcv_compat, RCU_INITIALIZER(ptr)); } EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr) { const struct sock_diag_inet_compat *old; old = unrcu_pointer(xchg(&inet_rcv_compat, NULL)); WARN_ON_ONCE(old != ptr); } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); int sock_diag_register(const struct sock_diag_handler *hndl) { int family = hndl->family; if (family >= AF_MAX) return -EINVAL; return !cmpxchg((const struct sock_diag_handler **) &sock_diag_handlers[family], NULL, hndl) ? 0 : -EBUSY; } EXPORT_SYMBOL_GPL(sock_diag_register); void sock_diag_unregister(const struct sock_diag_handler *hndl) { int family = hndl->family; if (family >= AF_MAX) return; xchg((const struct sock_diag_handler **)&sock_diag_handlers[family], NULL); } 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 (!rcu_access_pointer(sock_diag_handlers[req->sdiag_family])) sock_load_diag_module(req->sdiag_family, 0); hndl = sock_diag_lock_handler(req->sdiag_family); if (hndl == NULL) return -ENOENT; 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; sock_diag_unlock_handler(hndl); return err; } static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { const struct sock_diag_inet_compat *ptr; int ret; switch (nlh->nlmsg_type) { case TCPDIAG_GETSOCK: if (!rcu_access_pointer(inet_rcv_compat)) sock_load_diag_module(AF_INET, 0); rcu_read_lock(); ptr = rcu_dereference(inet_rcv_compat); if (ptr && !try_module_get(ptr->owner)) ptr = NULL; rcu_read_unlock(); ret = -EOPNOTSUPP; if (ptr) { ret = ptr->fn(skb, nlh); module_put(ptr->owner); } return ret; case SOCK_DIAG_BY_FAMILY: case SOCK_DESTROY: return __sock_diag_cmd(skb, nlh); default: return -EINVAL; } } static void sock_diag_rcv(struct sk_buff *skb) { netlink_rcv_skb(skb, &sock_diag_rcv_msg); } static int sock_diag_bind(struct net *net, int group) { switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!rcu_access_pointer(sock_diag_handlers[AF_INET])) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!rcu_access_pointer(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", WQ_PERCPU, 0); BUG_ON(!broadcast_wq); return register_pernet_subsys(&diag_net_ops); } device_initcall(sock_diag_init); |
| 62 31 96 3 16 16 16 101 101 110 31 98 55 41 29 29 71 108 55 12 1 10 11 11 2 16 3 14 16 18 15 4 9 2 13 2 11 10 10 14 4 6 68 17 12 10 24 2 19 22 29 15 19 29 34 41 39 26 20 6 8 35 35 3 8 48 29 11 26 30 17 28 22 36 47 48 25 9 6 13 16 17 23 49 15 20 18 8 17 18 36 7 7 3 2 3 9 1 9 5 4 12 12 7 7 7 12 1 12 3 12 12 4 12 4 12 12 12 9 11 12 12 9 3 2 1 5 3 6 9 2 7 12 5 2 5 5 9 1 8 2 1 1 1 5 50 51 7 1 4 4 4 8 8 27 4 27 23 2 22 22 22 22 1 2 3 5 4 35 38 46 8 5 16 16 3 12 2 2 3 6 1 81 5 9 9 5 95 95 75 4 34 2 44 34 13 13 44 44 13 7 34 34 67 2 55 4 6 31 19 44 44 19 3 7 1 56 21 2 5 2 9 2 4 16 18 2 32 19 12 7 74 1 3 11 69 67 51 11 29 1 9 19 30 48 479 445 35 35 72 24 48 5 5 5 5 5 4 2 5 5 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 | // 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_flex(*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; 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; 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_obj(*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_flex(*new, semadj, 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->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; ktime_t expires, *exp = NULL; bool timed_out = false; if (nsops < 1 || semid < 0) return -EINVAL; if (nsops > ns->sc_semopm) return -E2BIG; if (timeout) { if (!timespec64_valid(timeout)) return -EINVAL; expires = ktime_add_safe(ktime_get(), timespec64_to_ktime(*timeout)); exp = &expires; } 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(); timed_out = !schedule_hrtimeout_range(exp, current->timer_slack_ns, HRTIMER_MODE_ABS); /* * 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 (timed_out) 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_objs(*sops, nsops); 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(u64 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 |
| 25 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * 9P Client Definitions * * Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net> */ #ifndef NET_9P_CLIENT_H #define NET_9P_CLIENT_H #include <linux/utsname.h> #include <linux/idr.h> #include <linux/tracepoint-defs.h> /* Number of requests per row */ #define P9_ROW_MAXTAG 255 /* DEFAULT MSIZE = 32 pages worth of payload + P9_HDRSZ + * room for write (16 extra) or read (11 extra) operands. */ #define DEFAULT_MSIZE ((128 * 1024) + P9_IOHDRSZ) /** enum p9_proto_versions - 9P protocol versions * @p9_proto_legacy: 9P Legacy mode, pre-9P2000.u * @p9_proto_2000u: 9P2000.u extension * @p9_proto_2000L: 9P2000.L extension */ enum p9_proto_versions { p9_proto_legacy, p9_proto_2000u, p9_proto_2000L, }; /** * enum p9_trans_status - different states of underlying transports * @Connected: transport is connected and healthy * @Disconnected: transport has been disconnected * @Hung: transport is connected by wedged * * This enumeration details the various states a transport * instatiation can be in. */ enum p9_trans_status { Connected, BeginDisconnect, Disconnected, Hung, }; /** * enum p9_req_status_t - status of a request * @REQ_STATUS_ALLOC: request has been allocated but not sent * @REQ_STATUS_UNSENT: request waiting to be sent * @REQ_STATUS_SENT: request sent to server * @REQ_STATUS_RCVD: response received from server * @REQ_STATUS_FLSHD: request has been flushed * @REQ_STATUS_ERROR: request encountered an error on the client side */ enum p9_req_status_t { REQ_STATUS_ALLOC, REQ_STATUS_UNSENT, REQ_STATUS_SENT, REQ_STATUS_RCVD, REQ_STATUS_FLSHD, REQ_STATUS_ERROR, }; /** * struct p9_req_t - request slots * @status: status of this request slot * @t_err: transport error * @wq: wait_queue for the client to block on for this request * @tc: the request fcall structure * @rc: the response fcall structure * @req_list: link for higher level objects to chain requests */ struct p9_req_t { int status; int t_err; refcount_t refcount; wait_queue_head_t wq; struct p9_fcall tc; struct p9_fcall rc; struct list_head req_list; }; /** * struct p9_client - per client instance state * @lock: protect @fids and @reqs * @msize: maximum data size negotiated by protocol * @proto_version: 9P protocol version to use * @trans_mod: module API instantiated with this client * @status: connection state * @trans: tranport instance state and API * @fids: All active FID handles * @reqs: All active requests. * @name: node name used as client id * * The client structure is used to keep track of various per-client * state that has been instantiated. */ struct p9_client { spinlock_t lock; unsigned int msize; unsigned char proto_version; struct p9_trans_module *trans_mod; enum p9_trans_status status; void *trans; struct kmem_cache *fcall_cache; union { struct { int rfd; int wfd; } fd; struct { u16 port; bool privport; } tcp; } trans_opts; struct idr fids; struct idr reqs; char name[__NEW_UTS_LEN + 1]; }; /** * struct p9_fd_opts - holds client options during parsing * @msize: maximum data size negotiated by protocol * @prot-Oversion: 9P protocol version to use * @trans_mod: module API instantiated with this client * * These parsed options get transferred into client in * apply_client_options() */ struct p9_client_opts { unsigned int msize; unsigned char proto_version; struct p9_trans_module *trans_mod; }; /** * struct p9_fd_opts - per-transport options for fd transport * @rfd: file descriptor for reading (trans=fd) * @wfd: file descriptor for writing (trans=fd) * @port: port to connect to (trans=tcp) * @privport: port is privileged */ struct p9_fd_opts { int rfd; int wfd; u16 port; bool privport; }; /** * struct p9_rdma_opts - Collection of mount options for rdma transport * @port: port of connection * @privport: Whether a privileged port may be used * @sq_depth: The requested depth of the SQ. This really doesn't need * to be any deeper than the number of threads used in the client * @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth * @timeout: Time to wait in msecs for CM events */ struct p9_rdma_opts { short port; bool privport; int sq_depth; int rq_depth; long timeout; }; /** * struct p9_session_opts - holds parsed options for v9fs_session_info * @flags: session options of type &p9_session_flags * @nodev: set to 1 to disable device mapping * @debug: debug level * @afid: authentication handle * @cache: cache mode of type &p9_cache_bits * @cachetag: the tag of the cache associated with this session * @uname: string user name to mount hierarchy as * @aname: mount specifier for remote hierarchy * @dfltuid: default numeric userid to mount hierarchy as * @dfltgid: default numeric groupid to mount hierarchy as * @uid: if %V9FS_ACCESS_SINGLE, the numeric uid which mounted the hierarchy * @session_lock_timeout: retry interval for blocking locks * * This strucure holds options which are parsed and will be transferred * to the v9fs_session_info structure when mounted, and therefore largely * duplicates struct v9fs_session_info. */ struct p9_session_opts { unsigned int flags; unsigned char nodev; unsigned short debug; unsigned int afid; unsigned int cache; #ifdef CONFIG_9P_FSCACHE char *cachetag; #endif char *uname; char *aname; kuid_t dfltuid; kgid_t dfltgid; kuid_t uid; long session_lock_timeout; }; /* Used by mount API to store parsed mount options */ struct v9fs_context { struct p9_client_opts client_opts; struct p9_fd_opts fd_opts; struct p9_rdma_opts rdma_opts; struct p9_session_opts session_opts; }; /** * struct p9_fid - file system entity handle * @clnt: back pointer to instantiating &p9_client * @fid: numeric identifier for this handle * @mode: current mode of this fid (enum?) * @qid: the &p9_qid server identifier this handle points to * @iounit: the server reported maximum transaction size for this file * @uid: the numeric uid of the local user who owns this handle * @rdir: readdir accounting structure (allocated on demand) * @dlist: per-dentry fid tracking * * TODO: This needs lots of explanation. */ enum fid_source { FID_FROM_OTHER, FID_FROM_INODE, FID_FROM_DENTRY, }; struct p9_fid { struct p9_client *clnt; u32 fid; refcount_t count; int mode; struct p9_qid qid; u32 iounit; kuid_t uid; void *rdir; struct hlist_node dlist; /* list of all fids attached to a dentry */ struct hlist_node ilist; }; /** * struct p9_dirent - directory entry structure * @qid: The p9 server qid for this dirent * @d_off: offset to the next dirent * @d_type: type of file * @d_name: file name */ struct p9_dirent { struct p9_qid qid; u64 d_off; unsigned char d_type; char d_name[256]; }; struct iov_iter; int p9_show_client_options(struct seq_file *m, struct p9_client *clnt); int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name); int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name, struct p9_fid *newdirfid, const char *new_name); struct p9_client *p9_client_create(struct fs_context *fc); void p9_client_destroy(struct p9_client *clnt); void p9_client_disconnect(struct p9_client *clnt); void p9_client_begin_disconnect(struct p9_client *clnt); struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, const char *uname, kuid_t n_uname, const char *aname); struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, const unsigned char * const *wnames, int clone); int p9_client_open(struct p9_fid *fid, int mode); int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode, char *extension); int p9_client_link(struct p9_fid *fid, struct p9_fid *oldfid, const char *newname); int p9_client_symlink(struct p9_fid *fid, const char *name, const char *symname, kgid_t gid, struct p9_qid *qid); int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32 mode, kgid_t gid, struct p9_qid *qid); int p9_client_clunk(struct p9_fid *fid); int p9_client_fsync(struct p9_fid *fid, int datasync); int p9_client_remove(struct p9_fid *fid); int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags); int p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err); int p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err); int p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err); struct netfs_io_subrequest; void p9_client_write_subreq(struct netfs_io_subrequest *subreq); int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset); int p9dirent_read(struct p9_client *clnt, char *buf, int len, struct p9_dirent *dirent); struct p9_wstat *p9_client_stat(struct p9_fid *fid); int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst); int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *attr); struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, u64 request_mask); int p9_client_mknod_dotl(struct p9_fid *oldfid, const char *name, int mode, dev_t rdev, kgid_t gid, struct p9_qid *qid); int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode, kgid_t gid, struct p9_qid *qid); int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status); int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *fl); void p9_fcall_fini(struct p9_fcall *fc); struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag); static inline void p9_req_get(struct p9_req_t *r) { refcount_inc(&r->refcount); } static inline int p9_req_try_get(struct p9_req_t *r) { return refcount_inc_not_zero(&r->refcount); } int p9_req_put(struct p9_client *c, struct p9_req_t *r); /* We cannot have the real tracepoints in header files, * use a wrapper function */ DECLARE_TRACEPOINT(9p_fid_ref); void do_trace_9p_fid_get(struct p9_fid *fid); void do_trace_9p_fid_put(struct p9_fid *fid); /* fid reference counting helpers: * - fids used for any length of time should always be referenced through * p9_fid_get(), and released with p9_fid_put() * - v9fs_fid_lookup() or similar will automatically call get for you * and also require a put * - the *_fid_add() helpers will stash the fid in the inode, * at which point it is the responsibility of evict_inode() * to call the put * - the last put will automatically send a clunk to the server */ static inline struct p9_fid *p9_fid_get(struct p9_fid *fid) { if (tracepoint_enabled(9p_fid_ref)) do_trace_9p_fid_get(fid); refcount_inc(&fid->count); return fid; } static inline int p9_fid_put(struct p9_fid *fid) { if (!fid || IS_ERR(fid)) return 0; if (tracepoint_enabled(9p_fid_ref)) do_trace_9p_fid_put(fid); if (!refcount_dec_and_test(&fid->count)) return 0; return p9_client_clunk(fid); } void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status); int p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag, int rewind); int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st); void p9stat_free(struct p9_wstat *stbuf); int p9_is_proto_dotu(struct p9_client *clnt); int p9_is_proto_dotl(struct p9_client *clnt); struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, const char *attr_name, u64 *attr_size); int p9_client_xattrcreate(struct p9_fid *fid, const char *name, u64 attr_size, int flags); int p9_client_readlink(struct p9_fid *fid, char **target); int p9_client_init(void); void p9_client_exit(void); #endif /* NET_9P_CLIENT_H */ |
| 3 43 44 44 44 |